diff options
955 files changed, 31027 insertions, 12938 deletions
diff --git a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt index b878a1e305af..ed1456f5c94d 100644 --- a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt +++ b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt @@ -16,11 +16,13 @@ Required Properties: - clocks: Array of clocks required for SDHC. - Require at least input clock for Xenon IP core. + Require at least input clock for Xenon IP core. For Armada AP806 and + CP110, the AXI clock is also mandatory. - clock-names: Array of names corresponding to clocks property. The input clock for Xenon IP core should be named as "core". + The input clock for the AXI bus must be named as "axi". - reg: * For "marvell,armada-3700-sdhci", two register areas. @@ -106,8 +108,8 @@ Example: compatible = "marvell,armada-ap806-sdhci"; reg = <0xaa0000 0x1000>; interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH> - clocks = <&emmc_clk>; - clock-names = "core"; + clocks = <&emmc_clk>,<&axi_clk>; + clock-names = "core", "axi"; bus-width = <4>; marvell,xenon-phy-slow-mode; marvell,xenon-tun-count = <11>; @@ -126,8 +128,8 @@ Example: interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH> vqmmc-supply = <&sd_vqmmc_regulator>; vmmc-supply = <&sd_vmmc_regulator>; - clocks = <&sdclk>; - clock-names = "core"; + clocks = <&sdclk>, <&axi_clk>; + clock-names = "core", "axi"; bus-width = <4>; marvell,xenon-tun-count = <9>; }; diff --git a/Documentation/devicetree/bindings/net/sh_eth.txt b/Documentation/devicetree/bindings/net/sh_eth.txt index 0115c85a2425..5172799a7f1a 100644 --- a/Documentation/devicetree/bindings/net/sh_eth.txt +++ b/Documentation/devicetree/bindings/net/sh_eth.txt @@ -4,7 +4,8 @@ This file provides information on what the device node for the SH EtherMAC interface contains. Required properties: -- compatible: "renesas,gether-r8a7740" if the device is a part of R8A7740 SoC. +- compatible: Must contain one or more of the following: + "renesas,gether-r8a7740" if the device is a part of R8A7740 SoC. "renesas,ether-r8a7743" if the device is a part of R8A7743 SoC. "renesas,ether-r8a7745" if the device is a part of R8A7745 SoC. "renesas,ether-r8a7778" if the device is a part of R8A7778 SoC. @@ -14,6 +15,14 @@ Required properties: "renesas,ether-r8a7793" if the device is a part of R8A7793 SoC. "renesas,ether-r8a7794" if the device is a part of R8A7794 SoC. "renesas,ether-r7s72100" if the device is a part of R7S72100 SoC. + "renesas,rcar-gen1-ether" for a generic R-Car Gen1 device. + "renesas,rcar-gen2-ether" for a generic R-Car Gen2 or RZ/G1 + device. + + When compatible with the generic version, nodes must list + the SoC-specific version corresponding to the platform + first followed by the generic version. + - reg: offset and length of (1) the E-DMAC/feLic register block (required), (2) the TSU register block (optional). - interrupts: interrupt specifier for the sole interrupt. @@ -36,7 +45,8 @@ Optional properties: Example (Lager board): ethernet@ee700000 { - compatible = "renesas,ether-r8a7790"; + compatible = "renesas,ether-r8a7790", + "renesas,rcar-gen2-ether"; reg = <0 0xee700000 0 0x400>; interrupt-parent = <&gic>; interrupts = <0 162 IRQ_TYPE_LEVEL_HIGH>; diff --git a/Documentation/driver-api/80211/cfg80211.rst b/Documentation/driver-api/80211/cfg80211.rst index 8ffac57e1f5b..eeab91b59457 100644 --- a/Documentation/driver-api/80211/cfg80211.rst +++ b/Documentation/driver-api/80211/cfg80211.rst @@ -300,9 +300,6 @@ Data path helpers :functions: ieee80211_data_to_8023 .. kernel-doc:: include/net/cfg80211.h - :functions: ieee80211_data_from_8023 - -.. kernel-doc:: include/net/cfg80211.h :functions: ieee80211_amsdu_to_8023s .. kernel-doc:: include/net/cfg80211.h diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt index 36f528a7fdd6..8caa60734647 100644 --- a/Documentation/filesystems/overlayfs.txt +++ b/Documentation/filesystems/overlayfs.txt @@ -210,8 +210,11 @@ path as another overlay mount and it may use a lower layer path that is beneath or above the path of another overlay lower layer path. Using an upper layer path and/or a workdir path that are already used by -another overlay mount is not allowed and will fail with EBUSY. Using +another overlay mount is not allowed and may fail with EBUSY. Using partially overlapping paths is not allowed but will not fail with EBUSY. +If files are accessed from two overlayfs mounts which share or overlap the +upper layer and/or workdir path the behavior of the overlay is undefined, +though it will not result in a crash or deadlock. Mounting an overlay using an upper layer path, where the upper layer path was previously used by another mounted overlay in combination with a diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801 index 0500193434cb..d47702456926 100644 --- a/Documentation/i2c/busses/i2c-i801 +++ b/Documentation/i2c/busses/i2c-i801 @@ -36,6 +36,7 @@ Supported adapters: * Intel Gemini Lake (SOC) * Intel Cannon Lake-H (PCH) * Intel Cannon Lake-LP (PCH) + * Intel Cedar Fork (PCH) Datasheets: Publicly available at the Intel website On Intel Patsburg and later chipsets, both the normal host SMBus controller diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index 57f52cdce32e..9ba04c0bab8d 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -2387,7 +2387,7 @@ broadcast: Like active-backup, there is not much advantage to this and packet type ID), so in a "gatewayed" configuration, all outgoing traffic will generally use the same device. Incoming traffic may also end up on a single device, but that is - dependent upon the balancing policy of the peer's 8023.ad + dependent upon the balancing policy of the peer's 802.3ad implementation. In a "local" configuration, traffic will be distributed across the devices in the bond. diff --git a/Documentation/networking/netvsc.txt b/Documentation/networking/netvsc.txt index 93560fb1170a..92f5b31392fa 100644 --- a/Documentation/networking/netvsc.txt +++ b/Documentation/networking/netvsc.txt @@ -19,12 +19,12 @@ Features Receive Side Scaling -------------------- - Hyper-V supports receive side scaling. For TCP, packets are - distributed among available queues based on IP address and port + Hyper-V supports receive side scaling. For TCP & UDP, packets can + be distributed among available queues based on IP address and port number. - For UDP, we can switch UDP hash level between L3 and L4 by ethtool - command. UDP over IPv4 and v6 can be set differently. The default + For TCP & UDP, we can switch hash level between L3 and L4 by ethtool + command. TCP/UDP over IPv4 and v6 can be set differently. The default hash level is L4. We currently only allow switching TX hash level from within the guests. diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt index 7818b5fe448b..381e5b23d61d 100644 --- a/Documentation/networking/regulatory.txt +++ b/Documentation/networking/regulatory.txt @@ -19,6 +19,14 @@ core regulatory domain all wireless devices should adhere to. How to get regulatory domains to the kernel ------------------------------------------- +When the regulatory domain is first set up, the kernel will request a +database file (regulatory.db) containing all the regulatory rules. It +will then use that database when it needs to look up the rules for a +given country. + +How to get regulatory domains to the kernel (old CRDA solution) +--------------------------------------------------------------- + Userspace gets a regulatory domain in the kernel by having a userspace agent build it and send it via nl80211. Only expected regulatory domains will be respected by the kernel. @@ -192,23 +200,5 @@ Then in some part of your code after your wiphy has been registered: Statically compiled regulatory database --------------------------------------- -In most situations the userland solution using CRDA as described -above is the preferred solution. However in some cases a set of -rules built into the kernel itself may be desirable. To account -for this situation, a configuration option has been provided -(i.e. CONFIG_CFG80211_INTERNAL_REGDB). With this option enabled, -the wireless database information contained in net/wireless/db.txt is -used to generate a data structure encoded in net/wireless/regdb.c. -That option also enables code in net/wireless/reg.c which queries -the data in regdb.c as an alternative to using CRDA. - -The file net/wireless/db.txt should be kept up-to-date with the db.txt -file available in the git repository here: - - git://git.kernel.org/pub/scm/linux/kernel/git/sforshee/wireless-regdb.git - -Again, most users in most situations should be using the CRDA package -provided with their distribution, and in most other situations users -should be building and using CRDA on their own rather than using -this option. If you are not absolutely sure that you should be using -CONFIG_CFG80211_INTERNAL_REGDB then _DO_NOT_USE_IT_. +When a database should be fixed into the kernel, it can be provided as a +firmware file at build time that is then linked into the kernel. diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt index 810620153a44..b5407163d53b 100644 --- a/Documentation/networking/rxrpc.txt +++ b/Documentation/networking/rxrpc.txt @@ -280,6 +280,18 @@ Interaction with the user of the RxRPC socket: nominated by a socket option. +Notes on sendmsg: + + (*) MSG_WAITALL can be set to tell sendmsg to ignore signals if the peer is + making progress at accepting packets within a reasonable time such that we + manage to queue up all the data for transmission. This requires the + client to accept at least one packet per 2*RTT time period. + + If this isn't set, sendmsg() will return immediately, either returning + EINTR/ERESTARTSYS if nothing was consumed or returning the amount of data + consumed. + + Notes on recvmsg: (*) If there's a sequence of data messages belonging to a particular call on @@ -782,7 +794,9 @@ The kernel interface functions are as follows: struct key *key, unsigned long user_call_ID, s64 tx_total_len, - gfp_t gfp); + gfp_t gfp, + rxrpc_notify_rx_t notify_rx, + bool upgrade); This allocates the infrastructure to make a new RxRPC call and assigns call and connection numbers. The call will be made on the UDP port that @@ -803,6 +817,13 @@ The kernel interface functions are as follows: allows the kernel to encrypt directly to the packet buffers, thereby saving a copy. The value may not be less than -1. + notify_rx is a pointer to a function to be called when events such as + incoming data packets or remote aborts happen. + + upgrade should be set to true if a client operation should request that + the server upgrade the service to a better one. The resultant service ID + is returned by rxrpc_kernel_recv_data(). + If this function is successful, an opaque reference to the RxRPC call is returned. The caller now holds a reference on this and it must be properly ended. @@ -850,7 +871,8 @@ The kernel interface functions are as follows: size_t size, size_t *_offset, bool want_more, - u32 *_abort) + u32 *_abort, + u16 *_service) This is used to receive data from either the reply part of a client call or the request part of a service call. buf and size specify how much @@ -873,6 +895,9 @@ The kernel interface functions are as follows: If a remote ABORT is detected, the abort code received will be stored in *_abort and ECONNABORTED will be returned. + The service ID that the call ended up with is returned into *_service. + This can be used to see if a call got a service upgrade. + (*) Abort a call. void rxrpc_kernel_abort_call(struct socket *sock, @@ -1020,6 +1045,30 @@ The kernel interface functions are as follows: It returns 0 if the call was requeued and an error otherwise. + (*) Get call RTT. + + u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call); + + Get the RTT time to the peer in use by a call. The value returned is in + nanoseconds. + + (*) Check call still alive. + + u32 rxrpc_kernel_check_life(struct socket *sock, + struct rxrpc_call *call); + + This returns a number that is updated when ACKs are received from the peer + (notably including PING RESPONSE ACKs which we can elicit by sending PING + ACKs to see if the call still exists on the server). The caller should + compare the numbers of two calls to see if the call is still alive after + waiting for a suitable interval. + + This allows the caller to work out if the server is still contactable and + if the call is still alive on the server whilst waiting for the server to + process a client operation. + + This function may transmit a PING ACK. + ======================= CONFIGURABLE PARAMETERS diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt index 3918dae964d4..8ff7b4c8f91b 100644 --- a/Documentation/networking/vrf.txt +++ b/Documentation/networking/vrf.txt @@ -71,7 +71,12 @@ Setup ip ru add iif vrf-blue table 10 3. Set the default route for the table (and hence default route for the VRF). - ip route add table 10 unreachable default + ip route add table 10 unreachable default metric 4278198272 + + This high metric value ensures that the default unreachable route can + be overridden by a routing protocol suite. FRRouting interprets + kernel metrics as a combined admin distance (upper byte) and priority + (lower 3 bytes). Thus the above metric translates to [255/8192]. 4. Enslave L3 interfaces to a VRF device. ip link set dev eth1 master vrf-blue @@ -256,7 +261,7 @@ older form without it. For example: $ ip route show vrf red - prohibit default + unreachable default metric 4278198272 broadcast 10.2.1.0 dev eth1 proto kernel scope link src 10.2.1.2 10.2.1.0/24 dev eth1 proto kernel scope link src 10.2.1.2 local 10.2.1.2 dev eth1 proto kernel scope host src 10.2.1.2 @@ -282,7 +287,7 @@ older form without it. ff00::/8 dev red metric 256 pref medium ff00::/8 dev eth1 metric 256 pref medium ff00::/8 dev eth2 metric 256 pref medium - + unreachable default dev lo metric 4278198272 error -101 pref medium 8. Route Lookup for a VRF @@ -331,7 +336,7 @@ function vrf_create ip link add ${VRF} type vrf table ${TBID} if [ "${VRF}" != "mgmt" ]; then - ip route add table ${TBID} unreachable default + ip route add table ${TBID} unreachable default metric 4278198272 fi ip link set dev ${VRF} up } diff --git a/MAINTAINERS b/MAINTAINERS index f0c37be4e04a..f218fe1e43fe 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -700,9 +700,9 @@ F: include/linux/altera_uart.h F: include/linux/altera_jtaguart.h AMAZON ETHERNET DRIVERS -M: Netanel Belgazal <netanel@annapurnalabs.com> -R: Saeed Bishara <saeed@annapurnalabs.com> -R: Zorik Machulsky <zorik@annapurnalabs.com> +M: Netanel Belgazal <netanel@amazon.com> +R: Saeed Bishara <saeedb@amazon.com> +R: Zorik Machulsky <zorik@amazon.com> L: netdev@vger.kernel.org S: Supported F: Documentation/networking/ena.txt @@ -3329,17 +3329,22 @@ S: Maintained F: drivers/auxdisplay/cfag12864bfb.c F: include/linux/cfag12864b.h -CFG80211 and NL80211 +802.11 (including CFG80211/NL80211) M: Johannes Berg <johannes@sipsolutions.net> L: linux-wireless@vger.kernel.org W: http://wireless.kernel.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git S: Maintained +F: net/wireless/ F: include/uapi/linux/nl80211.h +F: include/linux/ieee80211.h +F: include/net/wext.h F: include/net/cfg80211.h -F: net/wireless/* -X: net/wireless/wext* +F: include/net/iw_handler.h +F: include/net/ieee80211_radiotap.h +F: Documentation/driver-api/80211/cfg80211.rst +F: Documentation/networking/regulatory.txt CHAR and MISC DRIVERS M: Arnd Bergmann <arnd@arndb.de> @@ -5259,7 +5264,8 @@ S: Maintained F: drivers/iommu/exynos-iommu.c EZchip NPS platform support -M: Noam Camus <noamc@ezchip.com> +M: Elad Kanfi <eladkan@mellanox.com> +M: Vineet Gupta <vgupta@synopsys.com> S: Supported F: arch/arc/plat-eznps F: arch/arc/boot/dts/eznps.dts @@ -8207,6 +8213,7 @@ F: Documentation/networking/mac80211-injection.txt F: include/net/mac80211.h F: net/mac80211/ F: drivers/net/wireless/mac80211_hwsim.[ch] +F: Documentation/networking/mac80211_hwsim/README MAILBOX API M: Jassi Brar <jassisinghbrar@gmail.com> @@ -9360,7 +9367,7 @@ NETWORK BLOCK DEVICE (NBD) M: Josef Bacik <jbacik@fb.com> S: Maintained L: linux-block@vger.kernel.org -L: nbd-general@lists.sourceforge.net +L: nbd@other.debian.org F: Documentation/blockdev/nbd.txt F: drivers/block/nbd.c F: include/uapi/linux/nbd.h @@ -11491,6 +11498,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git S: Maintained F: Documentation/rfkill.txt +F: Documentation/ABI/stable/sysfs-class-rfkill F: net/rfkill/ RHASHTABLE @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Fearless Coyote # *DOCUMENTATION* diff --git a/arch/Kconfig b/arch/Kconfig index 1aafb4efbb51..d789a89cb32c 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -937,9 +937,6 @@ config STRICT_MODULE_RWX and non-text memory will be made non-executable. This provides protection against certain security exploits (e.g. writing to text) -config ARCH_WANT_RELAX_ORDER - bool - config ARCH_HAS_REFCOUNT bool help diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index a598641eed98..c84e67fdea09 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -24,7 +24,7 @@ config ARC select GENERIC_SMP_IDLE_THREAD select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK - select HAVE_FUTEX_CMPXCHG + select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_IOREMAP_PROT select HAVE_KPROBES select HAVE_KRETPROBES diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 3a4b52b7e09d..d37f49d6a27f 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -6,8 +6,6 @@ # published by the Free Software Foundation. # -UTS_MACHINE := arc - ifeq ($(CROSS_COMPILE),) ifndef CONFIG_CPU_BIG_ENDIAN CROSS_COMPILE := arc-linux- diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index 2367a67c5f10..e114000a84f5 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -44,7 +44,14 @@ mmcclk: mmcclk { compatible = "fixed-clock"; - clock-frequency = <50000000>; + /* + * DW sdio controller has external ciu clock divider + * controlled via register in SDIO IP. It divides + * sdio_ref_clk (which comes from CGU) by 16 for + * default. So default mmcclk clock (which comes + * to sdk_in) is 25000000 Hz. + */ + clock-frequency = <25000000>; #clock-cells = <0>; }; diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 229d13adbce4..8adde1b492f1 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -12,6 +12,7 @@ /dts-v1/; #include <dt-bindings/net/ti-dp83867.h> +#include <dt-bindings/reset/snps,hsdk-reset.h> / { model = "snps,hsdk"; @@ -57,10 +58,10 @@ }; }; - core_clk: core-clk { + input_clk: input-clk { #clock-cells = <0>; compatible = "fixed-clock"; - clock-frequency = <500000000>; + clock-frequency = <33333333>; }; cpu_intc: cpu-interrupt-controller { @@ -102,6 +103,19 @@ ranges = <0x00000000 0xf0000000 0x10000000>; + cgu_rst: reset-controller@8a0 { + compatible = "snps,hsdk-reset"; + #reset-cells = <1>; + reg = <0x8A0 0x4>, <0xFF0 0x4>; + }; + + core_clk: core-clk@0 { + compatible = "snps,hsdk-core-pll-clock"; + reg = <0x00 0x10>, <0x14B8 0x4>; + #clock-cells = <0>; + clocks = <&input_clk>; + }; + serial: serial@5000 { compatible = "snps,dw-apb-uart"; reg = <0x5000 0x100>; @@ -120,7 +134,17 @@ mmcclk_ciu: mmcclk-ciu { compatible = "fixed-clock"; - clock-frequency = <100000000>; + /* + * DW sdio controller has external ciu clock divider + * controlled via register in SDIO IP. Due to its + * unexpected default value (it should devide by 1 + * but it devides by 8) SDIO IP uses wrong clock and + * works unstable (see STAR 9001204800) + * So add temporary fix and change clock frequency + * from 100000000 to 12500000 Hz until we fix dw sdio + * driver itself. + */ + clock-frequency = <12500000>; #clock-cells = <0>; }; @@ -141,6 +165,8 @@ clocks = <&gmacclk>; clock-names = "stmmaceth"; phy-handle = <&phy0>; + resets = <&cgu_rst HSDK_ETH_RESET>; + reset-names = "stmmaceth"; mdio { #address-cells = <1>; diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index 6980b966a364..ec7c849a5c8e 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -105,7 +105,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index 2233f5777a71..63d3cf69e0b0 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -104,7 +104,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index 30a3d4cf53d2..f613ecac14a7 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -107,7 +107,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index 821a2e562f3f..3507be2af6fe 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -84,5 +84,5 @@ CONFIG_TMPFS=y CONFIG_NFS_FS=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 9a3fcf446388..15f0f6b5fec1 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -63,6 +63,7 @@ CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y # CONFIG_IOMMU_SUPPORT is not set +CONFIG_RESET_HSDK=y CONFIG_EXT3_FS=y CONFIG_VFAT_FS=y CONFIG_TMPFS=y @@ -72,7 +73,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig index c0d6a010751a..4fcf4f2503f6 100644 --- a/arch/arc/configs/vdk_hs38_defconfig +++ b/arch/arc/configs/vdk_hs38_defconfig @@ -94,7 +94,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_SHIRQ=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig index 5c0971787acf..7b71464f6c2f 100644 --- a/arch/arc/configs/vdk_hs38_smp_defconfig +++ b/arch/arc/configs/vdk_hs38_smp_defconfig @@ -98,7 +98,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_SHIRQ=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index ba8e802dba80..b1c56d35f2a9 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -98,6 +98,7 @@ /* Auxiliary registers */ #define AUX_IDENTITY 4 +#define AUX_EXEC_CTRL 8 #define AUX_INTR_VEC_BASE 0x25 #define AUX_VOL 0x5e @@ -135,12 +136,12 @@ struct bcr_identity { #endif }; -struct bcr_isa { +struct bcr_isa_arcv2 { #ifdef CONFIG_CPU_BIG_ENDIAN unsigned int div_rem:4, pad2:4, ldd:1, unalign:1, atomic:1, be:1, - pad1:11, atomic1:1, ver:8; + pad1:12, ver:8; #else - unsigned int ver:8, atomic1:1, pad1:11, be:1, atomic:1, unalign:1, + unsigned int ver:8, pad1:12, be:1, atomic:1, unalign:1, ldd:1, pad2:4, div_rem:4; #endif }; @@ -263,13 +264,13 @@ struct cpuinfo_arc { struct cpuinfo_arc_mmu mmu; struct cpuinfo_arc_bpu bpu; struct bcr_identity core; - struct bcr_isa isa; + struct bcr_isa_arcv2 isa; const char *details, *name; unsigned int vec_base; struct cpuinfo_arc_ccm iccm, dccm; struct { unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, swape:1, pad1:2, - fpu_sp:1, fpu_dp:1, pad2:6, + fpu_sp:1, fpu_dp:1, dual_iss_enb:1, dual_iss_exist:1, pad2:4, debug:1, ap:1, smart:1, rtt:1, pad3:4, timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4; } extn; diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 877cec8f5ea2..fb83844daeea 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -51,6 +51,7 @@ static const struct id_to_str arc_cpu_rel[] = { { 0x51, "R2.0" }, { 0x52, "R2.1" }, { 0x53, "R3.0" }, + { 0x54, "R4.0" }, #endif { 0x00, NULL } }; @@ -62,6 +63,7 @@ static const struct id_to_str arc_cpu_nm[] = { #else { 0x40, "ARC EM" }, { 0x50, "ARC HS38" }, + { 0x54, "ARC HS48" }, #endif { 0x00, "Unknown" } }; @@ -119,11 +121,11 @@ static void read_arc_build_cfg_regs(void) struct bcr_generic bcr; struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; const struct id_to_str *tbl; + struct bcr_isa_arcv2 isa; FIX_PTR(cpu); READ_BCR(AUX_IDENTITY, cpu->core); - READ_BCR(ARC_REG_ISA_CFG_BCR, cpu->isa); for (tbl = &arc_cpu_rel[0]; tbl->id != 0; tbl++) { if (cpu->core.family == tbl->id) { @@ -133,7 +135,7 @@ static void read_arc_build_cfg_regs(void) } for (tbl = &arc_cpu_nm[0]; tbl->id != 0; tbl++) { - if ((cpu->core.family & 0xF0) == tbl->id) + if ((cpu->core.family & 0xF4) == tbl->id) break; } cpu->name = tbl->str; @@ -192,6 +194,14 @@ static void read_arc_build_cfg_regs(void) cpu->bpu.full = bpu.ft; cpu->bpu.num_cache = 256 << bpu.bce; cpu->bpu.num_pred = 2048 << bpu.pte; + + if (cpu->core.family >= 0x54) { + unsigned int exec_ctrl; + + READ_BCR(AUX_EXEC_CTRL, exec_ctrl); + cpu->extn.dual_iss_exist = 1; + cpu->extn.dual_iss_enb = exec_ctrl & 1; + } } READ_BCR(ARC_REG_AP_BCR, bcr); @@ -205,18 +215,25 @@ static void read_arc_build_cfg_regs(void) cpu->extn.debug = cpu->extn.ap | cpu->extn.smart | cpu->extn.rtt; + READ_BCR(ARC_REG_ISA_CFG_BCR, isa); + /* some hacks for lack of feature BCR info in old ARC700 cores */ if (is_isa_arcompact()) { - if (!cpu->isa.ver) /* ISA BCR absent, use Kconfig info */ + if (!isa.ver) /* ISA BCR absent, use Kconfig info */ cpu->isa.atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC); - else - cpu->isa.atomic = cpu->isa.atomic1; + else { + /* ARC700_BUILD only has 2 bits of isa info */ + struct bcr_generic bcr = *(struct bcr_generic *)&isa; + cpu->isa.atomic = bcr.info & 1; + } cpu->isa.be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); /* there's no direct way to distinguish 750 vs. 770 */ if (unlikely(cpu->core.family < 0x34 || cpu->mmu.ver < 3)) cpu->name = "ARC750"; + } else { + cpu->isa = isa; } } @@ -232,10 +249,11 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) "\nIDENTITY\t: ARCVER [%#02x] ARCNUM [%#02x] CHIPID [%#4x]\n", core->family, core->cpu_id, core->chip_id); - n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s\n", + n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s%s%s\n", cpu_id, cpu->name, cpu->details, is_isa_arcompact() ? "ARCompact" : "ARCv2", - IS_AVAIL1(cpu->isa.be, "[Big-Endian]")); + IS_AVAIL1(cpu->isa.be, "[Big-Endian]"), + IS_AVAIL3(cpu->extn.dual_iss_exist, cpu->extn.dual_iss_enb, " Dual-Issue")); n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s%s%s\nISA Extn\t: ", IS_AVAIL1(cpu->extn.timer0, "Timer0 "), diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c index f1ac6790da5f..cf14ebc36916 100644 --- a/arch/arc/plat-axs10x/axs10x.c +++ b/arch/arc/plat-axs10x/axs10x.c @@ -111,6 +111,13 @@ static void __init axs10x_early_init(void) axs10x_enable_gpio_intc_wire(); + /* + * Reset ethernet IP core. + * TODO: get rid of this quirk after axs10x reset driver (or simple + * reset driver) will be available in upstream. + */ + iowrite32((1 << 5), (void __iomem *) CREG_MB_SW_RESET); + scnprintf(mb, 32, "MainBoard v%d", mb_rev); axs10x_print_board_ver(CREG_MB_VER, mb); } diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig index 5a6ed5afb009..bd08de4be75e 100644 --- a/arch/arc/plat-hsdk/Kconfig +++ b/arch/arc/plat-hsdk/Kconfig @@ -6,4 +6,5 @@ # menuconfig ARC_SOC_HSDK - bool "ARC HS Development Kit SOC" + bool "ARC HS Development Kit SOC" + select CLK_HSDK diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c index a2e7fd17e36d..744e62e58788 100644 --- a/arch/arc/plat-hsdk/platform.c +++ b/arch/arc/plat-hsdk/platform.c @@ -38,6 +38,42 @@ static void __init hsdk_init_per_cpu(unsigned int cpu) #define CREG_PAE (CREG_BASE + 0x180) #define CREG_PAE_UPDATE (CREG_BASE + 0x194) +#define CREG_CORE_IF_CLK_DIV (CREG_BASE + 0x4B8) +#define CREG_CORE_IF_CLK_DIV_2 0x1 +#define CGU_BASE ARC_PERIPHERAL_BASE +#define CGU_PLL_STATUS (ARC_PERIPHERAL_BASE + 0x4) +#define CGU_PLL_CTRL (ARC_PERIPHERAL_BASE + 0x0) +#define CGU_PLL_STATUS_LOCK BIT(0) +#define CGU_PLL_STATUS_ERR BIT(1) +#define CGU_PLL_CTRL_1GHZ 0x3A10 +#define HSDK_PLL_LOCK_TIMEOUT 500 + +#define HSDK_PLL_LOCKED() \ + !!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_LOCK) + +#define HSDK_PLL_ERR() \ + !!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_ERR) + +static void __init hsdk_set_cpu_freq_1ghz(void) +{ + u32 timeout = HSDK_PLL_LOCK_TIMEOUT; + + /* + * As we set cpu clock which exceeds 500MHz, the divider for the interface + * clock must be programmed to div-by-2. + */ + iowrite32(CREG_CORE_IF_CLK_DIV_2, (void __iomem *) CREG_CORE_IF_CLK_DIV); + + /* Set cpu clock to 1GHz */ + iowrite32(CGU_PLL_CTRL_1GHZ, (void __iomem *) CGU_PLL_CTRL); + + while (!HSDK_PLL_LOCKED() && timeout--) + cpu_relax(); + + if (!HSDK_PLL_LOCKED() || HSDK_PLL_ERR()) + pr_err("Failed to setup CPU frequency to 1GHz!"); +} + static void __init hsdk_init_early(void) { /* @@ -52,6 +88,12 @@ static void __init hsdk_init_early(void) /* Really apply settings made above */ writel(1, (void __iomem *) CREG_PAE_UPDATE); + + /* + * Setup CPU frequency to 1GHz. + * TODO: remove it after smart hsdk pll driver will be introduced. + */ + hsdk_set_cpu_freq_1ghz(); } static const char *hsdk_compat[] __initconst = { diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 3585a5e26151..f7c4d2146aed 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -95,16 +95,19 @@ #define KERNEL_END _end /* - * The size of the KASAN shadow region. This should be 1/8th of the - * size of the entire kernel virtual address space. + * KASAN requires 1/8th of the kernel virtual address space for the shadow + * region. KASAN can bloat the stack significantly, so double the (minimum) + * stack size when KASAN is in use. */ #ifdef CONFIG_KASAN #define KASAN_SHADOW_SIZE (UL(1) << (VA_BITS - 3)) +#define KASAN_THREAD_SHIFT 1 #else #define KASAN_SHADOW_SIZE (0) +#define KASAN_THREAD_SHIFT 0 #endif -#define MIN_THREAD_SHIFT 14 +#define MIN_THREAD_SHIFT (14 + KASAN_THREAD_SHIFT) /* * VMAP'd stacks are allocated at page granularity, so we must ensure that such diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index f0e6d717885b..d06fbe4cd38d 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -649,4 +649,4 @@ static int __init armv8_deprecated_init(void) return 0; } -late_initcall(armv8_deprecated_init); +core_initcall(armv8_deprecated_init); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index cd52d365d1f0..21e2c95d24e7 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1307,4 +1307,4 @@ static int __init enable_mrs_emulation(void) return 0; } -late_initcall(enable_mrs_emulation); +core_initcall(enable_mrs_emulation); diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index f444f374bd7b..5d547deb6996 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -444,4 +444,4 @@ static int __init fpsimd_init(void) return 0; } -late_initcall(fpsimd_init); +core_initcall(fpsimd_init); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 2069e9bc0fca..b64958b23a7f 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -97,7 +97,7 @@ static void data_abort_decode(unsigned int esr) (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT, (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT); } else { - pr_alert(" ISV = 0, ISS = 0x%08lu\n", esr & ESR_ELx_ISS_MASK); + pr_alert(" ISV = 0, ISS = 0x%08lx\n", esr & ESR_ELx_ISS_MASK); } pr_alert(" CM = %lu, WnR = %lu\n", diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index a45a67d526f8..30f92391a93e 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -146,7 +146,7 @@ void machine_power_off(void) /* prevent soft lockup/stalled CPU messages for endless loop. */ rcu_sysrq_start(); - lockup_detector_suspend(); + lockup_detector_soft_poweroff(); for (;;); } diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 1df770e8cbe0..7275fed271af 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -102,10 +102,10 @@ static void cpufeatures_flush_tlb(void) case PVR_POWER8: case PVR_POWER8E: case PVR_POWER8NVL: - __flush_tlb_power8(POWER8_TLB_SETS); + __flush_tlb_power8(TLB_INVAL_SCOPE_GLOBAL); break; case PVR_POWER9: - __flush_tlb_power9(POWER9_TLB_SETS_HASH); + __flush_tlb_power9(TLB_INVAL_SCOPE_GLOBAL); break; default: pr_err("unknown CPU version for boot TLB flush\n"); diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 48da0f5d2f7f..b82586c53560 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -734,7 +734,29 @@ EXC_REAL(program_check, 0x700, 0x100) EXC_VIRT(program_check, 0x4700, 0x100, 0x700) TRAMP_KVM(PACA_EXGEN, 0x700) EXC_COMMON_BEGIN(program_check_common) - EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) + /* + * It's possible to receive a TM Bad Thing type program check with + * userspace register values (in particular r1), but with SRR1 reporting + * that we came from the kernel. Normally that would confuse the bad + * stack logic, and we would report a bad kernel stack pointer. Instead + * we switch to the emergency stack if we're taking a TM Bad Thing from + * the kernel. + */ + li r10,MSR_PR /* Build a mask of MSR_PR .. */ + oris r10,r10,0x200000@h /* .. and SRR1_PROGTM */ + and r10,r10,r12 /* Mask SRR1 with that. */ + srdi r10,r10,8 /* Shift it so we can compare */ + cmpldi r10,(0x200000 >> 8) /* .. with an immediate. */ + bne 1f /* If != go to normal path. */ + + /* SRR1 had PR=0 and SRR1_PROGTM=1, so use the emergency stack */ + andi. r10,r12,MSR_PR; /* Set CR0 correctly for label */ + /* 3 in EXCEPTION_PROLOG_COMMON */ + mr r10,r1 /* Save r1 */ + ld r1,PACAEMERGSP(r13) /* Use emergency stack */ + subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ + b 3f /* Jump into the macro !! */ +1: EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index b76ca198e09c..72f153c6f3fa 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -624,5 +624,18 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs) long __machine_check_early_realmode_p9(struct pt_regs *regs) { + /* + * On POWER9 DD2.1 and below, it's possible to get a machine check + * caused by a paste instruction where only DSISR bit 25 is set. This + * will result in the MCE handler seeing an unknown event and the kernel + * crashing. An MCE that occurs like this is spurious, so we don't need + * to do anything in terms of servicing it. If there is something that + * needs to be serviced, the CPU will raise the MCE again with the + * correct DSISR so that it can be serviced properly. So detect this + * case and mark it as handled. + */ + if (SRR1_MC_LOADSTORE(regs->msr) && regs->dsisr == 0x02000000) + return 1; + return mce_handle_error(regs, mce_p9_derror_table, mce_p9_ierror_table); } diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 0ac741fae90e..2e3bc16d02b2 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -904,9 +904,6 @@ void __init setup_arch(char **cmdline_p) #endif #endif -#ifdef CONFIG_PPC_64K_PAGES - init_mm.context.pte_frag = NULL; -#endif #ifdef CONFIG_SPAPR_TCE_IOMMU mm_iommu_init(&init_mm); #endif diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index c83c115858c1..b2c002993d78 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -452,9 +452,20 @@ static long restore_tm_sigcontexts(struct task_struct *tsk, if (MSR_TM_RESV(msr)) return -EINVAL; - /* pull in MSR TM from user context */ + /* pull in MSR TS bits from user context */ regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK); + /* + * Ensure that TM is enabled in regs->msr before we leave the signal + * handler. It could be the case that (a) user disabled the TM bit + * through the manipulation of the MSR bits in uc_mcontext or (b) the + * TM bit was disabled because a sufficient number of context switches + * happened whilst in the signal handler and load_tm overflowed, + * disabling the TM bit. In either case we can end up with an illegal + * TM state leading to a TM Bad Thing when we return to userspace. + */ + regs->msr |= MSR_TM; + /* pull in MSR LE from user context */ regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE); diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 2f6eadd9408d..c702a8981452 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -310,9 +310,6 @@ static int start_wd_on_cpu(unsigned int cpu) if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) return 0; - if (watchdog_suspended) - return 0; - if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) return 0; @@ -358,36 +355,39 @@ static void watchdog_calc_timeouts(void) wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5; } -void watchdog_nmi_reconfigure(void) +void watchdog_nmi_stop(void) { int cpu; - watchdog_calc_timeouts(); - for_each_cpu(cpu, &wd_cpus_enabled) stop_wd_on_cpu(cpu); +} +void watchdog_nmi_start(void) +{ + int cpu; + + watchdog_calc_timeouts(); for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) start_wd_on_cpu(cpu); } /* - * This runs after lockup_detector_init() which sets up watchdog_cpumask. + * Invoked from core watchdog init. */ -static int __init powerpc_watchdog_init(void) +int __init watchdog_nmi_probe(void) { int err; - watchdog_calc_timeouts(); - - err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/watchdog:online", - start_wd_on_cpu, stop_wd_on_cpu); - if (err < 0) + err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "powerpc/watchdog:online", + start_wd_on_cpu, stop_wd_on_cpu); + if (err < 0) { pr_warn("Watchdog could not be initialized"); - + return err; + } return 0; } -arch_initcall(powerpc_watchdog_init); static void handle_backtrace_ipi(struct pt_regs *regs) { diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 13304622ab1c..bf457843e032 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -622,7 +622,7 @@ int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server, return -EINVAL; state = &sb->irq_state[idx]; arch_spin_lock(&sb->lock); - *server = state->guest_server; + *server = state->act_server; *priority = state->guest_priority; arch_spin_unlock(&sb->lock); @@ -1331,7 +1331,7 @@ static int xive_get_source(struct kvmppc_xive *xive, long irq, u64 addr) xive->saved_src_count++; /* Convert saved state into something compatible with xics */ - val = state->guest_server; + val = state->act_server; prio = state->saved_scan_prio; if (prio == MASKED) { @@ -1507,7 +1507,6 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr) /* First convert prio and mark interrupt as untargetted */ act_prio = xive_prio_from_guest(guest_prio); state->act_priority = MASKED; - state->guest_server = server; /* * We need to drop the lock due to the mutex below. Hopefully diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index 5938f7644dc1..6ba63f8e8a61 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -35,7 +35,6 @@ struct kvmppc_xive_irq_state { struct xive_irq_data *pt_data; /* XIVE Pass-through associated data */ /* Targetting as set by guest */ - u32 guest_server; /* Current guest selected target */ u8 guest_priority; /* Guest set priority */ u8 saved_priority; /* Saved priority when masking */ diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 65eda1997c3f..f6c7f54c0515 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -361,9 +361,9 @@ static int change_page_attr(struct page *page, int numpages, pgprot_t prot) break; } wmb(); + local_irq_restore(flags); flush_tlb_kernel_range((unsigned long)page_address(start), (unsigned long)page_address(page)); - local_irq_restore(flags); return err; } diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 897aa1400eb8..bbb73aa0eb8f 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -272,7 +272,15 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static unsigned long pnv_memory_block_size(void) { - return 256UL * 1024 * 1024; + /* + * We map the kernel linear region with 1GB large pages on radix. For + * memory hot unplug to work our memory block size must be at least + * this size. + */ + if (radix_enabled()) + return 1UL * 1024 * 1024 * 1024; + else + return 256UL * 1024 * 1024; } #endif diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index f387318678b9..a3b8d7d1316e 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -1402,6 +1402,14 @@ void xive_teardown_cpu(void) if (xive_ops->teardown_cpu) xive_ops->teardown_cpu(cpu, xc); + +#ifdef CONFIG_SMP + /* Get rid of IPI */ + xive_cleanup_cpu_ipi(cpu, xc); +#endif + + /* Disable and free the queues */ + xive_cleanup_cpu_queues(cpu, xc); } void xive_kexec_teardown_cpu(int secondary) diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index f24a70bc6855..d9c4c9366049 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -431,7 +431,11 @@ static int xive_spapr_get_ipi(unsigned int cpu, struct xive_cpu *xc) static void xive_spapr_put_ipi(unsigned int cpu, struct xive_cpu *xc) { + if (!xc->hw_ipi) + return; + xive_irq_bitmap_free(xc->hw_ipi); + xc->hw_ipi = 0; } #endif /* CONFIG_SMP */ diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 0be3828752e5..4e83f950713e 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -44,7 +44,6 @@ config SPARC select ARCH_HAS_SG_CHAIN select CPU_NO_EFFICIENT_FFS select LOCKDEP_SMALL if LOCKDEP - select ARCH_WANT_RELAX_ORDER config SPARC32 def_bool !64BIT diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 1669240c7a25..b305f8247909 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -168,7 +168,6 @@ static int uml_net_open(struct net_device *dev) goto out_close; } - lp->tl.data = (unsigned long) &lp->user; netif_start_queue(dev); /* clear buffer - it can happen that the host side of the interface @@ -278,10 +277,11 @@ static const struct ethtool_ops uml_net_ethtool_ops = { .get_ts_info = ethtool_op_get_ts_info, }; -static void uml_net_user_timer_expire(unsigned long _conn) +static void uml_net_user_timer_expire(struct timer_list *t) { #ifdef undef - struct connection *conn = (struct connection *)_conn; + struct uml_net_private *lp = from_timer(lp, t, tl); + struct connection *conn = &lp->user; dprintk(KERN_INFO "uml_net_user_timer_expire [%p]\n", conn); do_connect(conn); @@ -458,9 +458,8 @@ static void eth_configure(int n, void *init, char *mac, .add_address = transport->user->add_address, .delete_address = transport->user->delete_address }); - init_timer(&lp->tl); + timer_setup(&lp->tl, uml_net_user_timer_expire, 0); spin_lock_init(&lp->lock); - lp->tl.function = uml_net_user_timer_expire; memcpy(lp->mac, dev->dev_addr, sizeof(lp->mac)); if ((transport->user->init != NULL) && diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 829e89cfcee2..9fb9a1f1e47b 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4409,10 +4409,9 @@ static __init int fixup_ht_bug(void) return 0; } - if (lockup_detector_suspend() != 0) { - pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n"); - return 0; - } + cpus_read_lock(); + + hardlockup_detector_perf_stop(); x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED); @@ -4420,9 +4419,7 @@ static __init int fixup_ht_bug(void) x86_pmu.commit_scheduling = NULL; x86_pmu.stop_scheduling = NULL; - lockup_detector_resume(); - - cpus_read_lock(); + hardlockup_detector_perf_restart(); for_each_online_cpu(c) free_excl_cntrs(c); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index bc62e7cbf1b1..59ad3d132353 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -88,7 +88,7 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, bool kvm_para_available(void); unsigned int kvm_arch_para_features(void); void __init kvm_guest_init(void); -void kvm_async_pf_task_wait(u32 token); +void kvm_async_pf_task_wait(u32 token, int interrupt_kernel); void kvm_async_pf_task_wake(u32 token); u32 kvm_read_and_reset_pf_reason(void); extern void kvm_disable_steal_time(void); @@ -103,7 +103,7 @@ static inline void kvm_spinlock_init(void) #else /* CONFIG_KVM_GUEST */ #define kvm_guest_init() do {} while (0) -#define kvm_async_pf_task_wait(T) do {} while(0) +#define kvm_async_pf_task_wait(T, I) do {} while(0) #define kvm_async_pf_task_wake(T) do {} while(0) static inline bool kvm_para_available(void) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index e675704fa6f7..8bb9594d0761 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -117,7 +117,11 @@ static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b, return NULL; } -void kvm_async_pf_task_wait(u32 token) +/* + * @interrupt_kernel: Is this called from a routine which interrupts the kernel + * (other than user space)? + */ +void kvm_async_pf_task_wait(u32 token, int interrupt_kernel) { u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; @@ -140,8 +144,10 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); - n.halted = is_idle_task(current) || preempt_count() > 1 || - rcu_preempt_depth(); + n.halted = is_idle_task(current) || + (IS_ENABLED(CONFIG_PREEMPT_COUNT) + ? preempt_count() > 1 || rcu_preempt_depth() + : interrupt_kernel); init_swait_queue_head(&n.wq); hlist_add_head(&n.link, &b->list); raw_spin_unlock(&b->lock); @@ -269,7 +275,7 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ prev_state = exception_enter(); - kvm_async_pf_task_wait((u32)read_cr2()); + kvm_async_pf_task_wait((u32)read_cr2(), !user_mode(regs)); exception_exit(prev_state); break; case KVM_PV_REASON_PAGE_READY: diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 3ea624452f93..3c48bc8bf08c 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -23,6 +23,7 @@ config KVM depends on HIGH_RES_TIMERS # for TASKSTATS/TASK_DELAY_ACCT: depends on NET && MULTIUSER + depends on X86_LOCAL_APIC select PREEMPT_NOTIFIERS select MMU_NOTIFIER select ANON_INODES diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index a36254cbf776..d90cdc77e077 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -425,8 +425,10 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)); #op " %al \n\t" \ FOP_RET -asm(".global kvm_fastop_exception \n" - "kvm_fastop_exception: xor %esi, %esi; ret"); +asm(".pushsection .fixup, \"ax\"\n" + ".global kvm_fastop_exception \n" + "kvm_fastop_exception: xor %esi, %esi; ret\n" + ".popsection"); FOP_START(setcc) FOP_SETCC(seto) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index eca30c1eb1d9..106d4a029a8a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3837,7 +3837,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, case KVM_PV_REASON_PAGE_NOT_PRESENT: vcpu->arch.apf.host_apf_reason = 0; local_irq_disable(); - kvm_async_pf_task_wait(fault_address); + kvm_async_pf_task_wait(fault_address, 0); local_irq_enable(); break; case KVM_PV_REASON_PAGE_READY: diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 980e73095643..de294d775acf 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -815,10 +815,14 @@ int blk_mq_debugfs_register(struct request_queue *q) goto err; /* - * blk_mq_init_hctx() attempted to do this already, but q->debugfs_dir + * blk_mq_init_sched() attempted to do this already, but q->debugfs_dir * didn't exist yet (because we don't know what to name the directory * until the queue is registered to a gendisk). */ + if (q->elevator && !q->sched_debugfs_dir) + blk_mq_debugfs_register_sched(q); + + /* Similarly, blk_mq_init_hctx() couldn't do this previously. */ queue_for_each_hw_ctx(q, hctx, i) { if (!hctx->debugfs_dir && blk_mq_debugfs_register_hctx(q, hctx)) goto err; diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 0fea76aa0f3f..17816a028dcb 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1911,11 +1911,11 @@ static void throtl_upgrade_state(struct throtl_data *td) tg->disptime = jiffies - 1; throtl_select_dispatch(sq); - throtl_schedule_next_dispatch(sq, false); + throtl_schedule_next_dispatch(sq, true); } rcu_read_unlock(); throtl_select_dispatch(&td->service_queue); - throtl_schedule_next_dispatch(&td->service_queue, false); + throtl_schedule_next_dispatch(&td->service_queue, true); queue_work(kthrotld_workqueue, &td->dispatch_work); } diff --git a/block/bsg-lib.c b/block/bsg-lib.c index dbddff8174e5..15d25ccd51a5 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -207,20 +207,34 @@ static int bsg_init_rq(struct request_queue *q, struct request *req, gfp_t gfp) struct bsg_job *job = blk_mq_rq_to_pdu(req); struct scsi_request *sreq = &job->sreq; + /* called right after the request is allocated for the request_queue */ + + sreq->sense = kzalloc(SCSI_SENSE_BUFFERSIZE, gfp); + if (!sreq->sense) + return -ENOMEM; + + return 0; +} + +static void bsg_initialize_rq(struct request *req) +{ + struct bsg_job *job = blk_mq_rq_to_pdu(req); + struct scsi_request *sreq = &job->sreq; + void *sense = sreq->sense; + + /* called right before the request is given to the request_queue user */ + memset(job, 0, sizeof(*job)); scsi_req_init(sreq); + + sreq->sense = sense; sreq->sense_len = SCSI_SENSE_BUFFERSIZE; - sreq->sense = kzalloc(sreq->sense_len, gfp); - if (!sreq->sense) - return -ENOMEM; job->req = req; - job->reply = sreq->sense; + job->reply = sense; job->reply_len = sreq->sense_len; job->dd_data = job + 1; - - return 0; } static void bsg_exit_rq(struct request_queue *q, struct request *req) @@ -251,6 +265,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name, q->cmd_size = sizeof(struct bsg_job) + dd_job_size; q->init_rq_fn = bsg_init_rq; q->exit_rq_fn = bsg_exit_rq; + q->initialize_rq_fn = bsg_initialize_rq; q->request_fn = bsg_request_fn; ret = blk_init_allocated_queue(q); diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 9565d572f8dd..de56394dd161 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1178,12 +1178,44 @@ dev_put: return ret; } +static bool __init iort_enable_acs(struct acpi_iort_node *iort_node) +{ + if (iort_node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX) { + struct acpi_iort_node *parent; + struct acpi_iort_id_mapping *map; + int i; + + map = ACPI_ADD_PTR(struct acpi_iort_id_mapping, iort_node, + iort_node->mapping_offset); + + for (i = 0; i < iort_node->mapping_count; i++, map++) { + if (!map->output_reference) + continue; + + parent = ACPI_ADD_PTR(struct acpi_iort_node, + iort_table, map->output_reference); + /* + * If we detect a RC->SMMU mapping, make sure + * we enable ACS on the system. + */ + if ((parent->type == ACPI_IORT_NODE_SMMU) || + (parent->type == ACPI_IORT_NODE_SMMU_V3)) { + pci_request_acs(); + return true; + } + } + } + + return false; +} + static void __init iort_init_platform_devices(void) { struct acpi_iort_node *iort_node, *iort_end; struct acpi_table_iort *iort; struct fwnode_handle *fwnode; int i, ret; + bool acs_enabled = false; /* * iort_table and iort both point to the start of IORT table, but @@ -1203,6 +1235,9 @@ static void __init iort_init_platform_devices(void) return; } + if (!acs_enabled) + acs_enabled = iort_enable_acs(iort_node); + if ((iort_node->type == ACPI_IORT_NODE_SMMU) || (iort_node->type == ACPI_IORT_NODE_SMMU_V3)) { diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c index f8b7e86907cc..126855e6cb7d 100644 --- a/drivers/atm/fore200e.c +++ b/drivers/atm/fore200e.c @@ -358,26 +358,33 @@ fore200e_shutdown(struct fore200e* fore200e) case FORE200E_STATE_COMPLETE: kfree(fore200e->stats); + /* fall through */ case FORE200E_STATE_IRQ: free_irq(fore200e->irq, fore200e->atm_dev); + /* fall through */ case FORE200E_STATE_ALLOC_BUF: fore200e_free_rx_buf(fore200e); + /* fall through */ case FORE200E_STATE_INIT_BSQ: fore200e_uninit_bs_queue(fore200e); + /* fall through */ case FORE200E_STATE_INIT_RXQ: fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_rxq.status); fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_rxq.rpd); + /* fall through */ case FORE200E_STATE_INIT_TXQ: fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_txq.status); fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_txq.tpd); + /* fall through */ case FORE200E_STATE_INIT_CMDQ: fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_cmdq.status); + /* fall through */ case FORE200E_STATE_INITIALIZE: /* nothing to do for that state */ @@ -390,6 +397,7 @@ fore200e_shutdown(struct fore200e* fore200e) case FORE200E_STATE_MAP: fore200e->bus->unmap(fore200e); + /* fall through */ case FORE200E_STATE_CONFIGURE: /* nothing to do for that state */ diff --git a/drivers/atm/idt77105.c b/drivers/atm/idt77105.c index 082aa02abc57..d781b3f87693 100644 --- a/drivers/atm/idt77105.c +++ b/drivers/atm/idt77105.c @@ -306,11 +306,9 @@ static int idt77105_start(struct atm_dev *dev) if (start_timer) { start_timer = 0; - setup_timer(&stats_timer, idt77105_stats_timer_func, 0UL); stats_timer.expires = jiffies+IDT77105_STATS_TIMER_PERIOD; add_timer(&stats_timer); - setup_timer(&restart_timer, idt77105_restart_timer_func, 0UL); restart_timer.expires = jiffies+IDT77105_RESTART_TIMER_PERIOD; add_timer(&restart_timer); } diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index 47f3c4ae0594..0e3b9c44c808 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -2073,21 +2073,19 @@ idt77252_rate_logindex(struct idt77252_dev *card, int pcr) } static void -idt77252_est_timer(unsigned long data) +idt77252_est_timer(struct timer_list *t) { - struct vc_map *vc = (struct vc_map *)data; + struct rate_estimator *est = from_timer(est, t, timer); + struct vc_map *vc = est->vc; struct idt77252_dev *card = vc->card; - struct rate_estimator *est; unsigned long flags; u32 rate, cps; u64 ncells; u8 lacr; spin_lock_irqsave(&vc->lock, flags); - est = vc->estimator; - if (!est) + if (!vc->estimator) goto out; - ncells = est->cells; rate = ((u32)(ncells - est->last_cells)) << (7 - est->interval); @@ -2126,10 +2124,11 @@ idt77252_init_est(struct vc_map *vc, int pcr) est->maxcps = pcr < 0 ? -pcr : pcr; est->cps = est->maxcps; est->avcps = est->cps << 5; + est->vc = vc; est->interval = 2; /* XXX: make this configurable */ est->ewma_log = 2; /* XXX: make this configurable */ - setup_timer(&est->timer, idt77252_est_timer, (unsigned long)vc); + timer_setup(&est->timer, idt77252_est_timer, 0); mod_timer(&est->timer, jiffies + ((HZ / 4) << est->interval)); return est; @@ -2209,16 +2208,20 @@ static int idt77252_init_ubr(struct idt77252_dev *card, struct vc_map *vc, struct atm_vcc *vcc, struct atm_qos *qos) { + struct rate_estimator *est = NULL; unsigned long flags; int tcr; spin_lock_irqsave(&vc->lock, flags); if (vc->estimator) { - del_timer(&vc->estimator->timer); - kfree(vc->estimator); + est = vc->estimator; vc->estimator = NULL; } spin_unlock_irqrestore(&vc->lock, flags); + if (est) { + del_timer_sync(&est->timer); + kfree(est); + } tcr = atm_pcr_goal(&qos->txtp); if (tcr == 0) diff --git a/drivers/atm/idt77252.h b/drivers/atm/idt77252.h index 3a82cc23a053..9339197d701c 100644 --- a/drivers/atm/idt77252.h +++ b/drivers/atm/idt77252.h @@ -184,6 +184,8 @@ struct aal1 { unsigned char sequence; }; +struct vc_map; + struct rate_estimator { struct timer_list timer; unsigned int interval; @@ -193,6 +195,7 @@ struct rate_estimator { long avcps; u32 cps; u32 maxcps; + struct vc_map *vc; }; struct vc_map { diff --git a/drivers/atm/suni.c b/drivers/atm/suni.c index b0363149b2fd..b8825f2d79e0 100644 --- a/drivers/atm/suni.c +++ b/drivers/atm/suni.c @@ -53,7 +53,7 @@ static DEFINE_SPINLOCK(sunis_lock); if (atomic_read(&stats->s) < 0) atomic_set(&stats->s,INT_MAX); -static void suni_hz(unsigned long from_timer) +static void suni_hz(struct timer_list *timer) { struct suni_priv *walk; struct atm_dev *dev; @@ -85,7 +85,7 @@ static void suni_hz(unsigned long from_timer) ((GET(TACP_TCC) & 0xff) << 8) | ((GET(TACP_TCCM) & 7) << 16)); } - if (from_timer) mod_timer(&poll_timer,jiffies+HZ); + if (timer) mod_timer(&poll_timer,jiffies+HZ); } @@ -322,13 +322,11 @@ static int suni_start(struct atm_dev *dev) printk(KERN_WARNING "%s(itf %d): no signal\n",dev->type, dev->number); PRIV(dev)->loop_mode = ATM_LM_NONE; - suni_hz(0); /* clear SUNI counters */ + suni_hz(NULL); /* clear SUNI counters */ (void) fetch_stats(dev,NULL,1); /* clear kernel counters */ if (first) { - init_timer(&poll_timer); + timer_setup(&poll_timer, suni_hz, 0); poll_timer.expires = jiffies+HZ; - poll_timer.function = suni_hz; - poll_timer.data = 1; #if 0 printk(KERN_DEBUG "[u] p=0x%lx,n=0x%lx\n",(unsigned long) poll_timer.list.prev, (unsigned long) poll_timer.list.next); diff --git a/drivers/bcma/Kconfig b/drivers/bcma/Kconfig index 54f81c554815..56ee55b66dfe 100644 --- a/drivers/bcma/Kconfig +++ b/drivers/bcma/Kconfig @@ -10,14 +10,15 @@ menuconfig BCMA Bus driver for Broadcom specific Advanced Microcontroller Bus Architecture. +if BCMA + # Support for Block-I/O. SELECT this from the driver that needs it. config BCMA_BLOCKIO bool - depends on BCMA config BCMA_HOST_PCI_POSSIBLE bool - depends on BCMA && PCI = y + depends on PCI = y default y config BCMA_HOST_PCI @@ -28,7 +29,6 @@ config BCMA_HOST_PCI config BCMA_HOST_SOC bool "Support for BCMA in a SoC" - depends on BCMA help Host interface for a Broadcom AIX bus directly mapped into the memory. This only works with the Broadcom SoCs from the @@ -38,7 +38,7 @@ config BCMA_HOST_SOC config BCMA_DRIVER_PCI bool "BCMA Broadcom PCI core driver" - depends on BCMA && PCI + depends on PCI default y help BCMA bus may have many versions of PCIe core. This driver @@ -54,13 +54,13 @@ config BCMA_DRIVER_PCI config BCMA_DRIVER_PCI_HOSTMODE bool "Driver for PCI core working in hostmode" - depends on BCMA && MIPS && BCMA_DRIVER_PCI + depends on MIPS && BCMA_DRIVER_PCI help PCI core hostmode operation (external PCI bus). config BCMA_DRIVER_MIPS bool "BCMA Broadcom MIPS core driver" - depends on BCMA && MIPS + depends on MIPS help Driver for the Broadcom MIPS core attached to Broadcom specific Advanced Microcontroller Bus. @@ -91,7 +91,6 @@ config BCMA_NFLASH config BCMA_DRIVER_GMAC_CMN bool "BCMA Broadcom GBIT MAC COMMON core driver" - depends on BCMA help Driver for the Broadcom GBIT MAC COMMON core attached to Broadcom specific Advanced Microcontroller Bus. @@ -100,7 +99,7 @@ config BCMA_DRIVER_GMAC_CMN config BCMA_DRIVER_GPIO bool "BCMA GPIO driver" - depends on BCMA && GPIOLIB + depends on GPIOLIB select GPIOLIB_IRQCHIP if BCMA_HOST_SOC help Driver to provide access to the GPIO pins of the bcma bus. @@ -109,8 +108,9 @@ config BCMA_DRIVER_GPIO config BCMA_DEBUG bool "BCMA debugging" - depends on BCMA help This turns on additional debugging messages. If unsure, say N + +endif # BCMA diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c index 89af807cf29c..5904ef1aa624 100644 --- a/drivers/bcma/driver_mips.c +++ b/drivers/bcma/driver_mips.c @@ -184,10 +184,11 @@ static void bcma_core_mips_print_irq(struct bcma_device *dev, unsigned int irq) { int i; static const char *irq_name[] = {"2(S)", "3", "4", "5", "6", "D", "I"}; - printk(KERN_DEBUG KBUILD_MODNAME ": core 0x%04x, irq :", dev->id.id); + + bcma_debug(dev->bus, "core 0x%04x, irq :", dev->id.id); for (i = 0; i <= 6; i++) - printk(" %s%s", irq_name[i], i == irq ? "*" : " "); - printk("\n"); + pr_cont(" %s%s", irq_name[i], i == irq ? "*" : " "); + pr_cont("\n"); } static void bcma_core_mips_dump_irq(struct bcma_bus *bus) diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 4a438b8abe27..2dfe99b328f8 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -17,7 +17,7 @@ if BLK_DEV config BLK_DEV_NULL_BLK tristate "Null test block driver" - depends on CONFIGFS_FS + select CONFIGFS_FS config BLK_DEV_FD tristate "Normal floppy disk support" diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 3684e21d543f..883dfebd3014 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -820,9 +820,13 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, * appropriate. */ ret = nbd_handle_cmd(cmd, hctx->queue_num); + if (ret < 0) + ret = BLK_STS_IOERR; + else if (!ret) + ret = BLK_STS_OK; complete(&cmd->send_complete); - return ret < 0 ? BLK_STS_IOERR : BLK_STS_OK; + return ret; } static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, diff --git a/drivers/clk/clk-bulk.c b/drivers/clk/clk-bulk.c index c834f5abfc49..4c10456f8a32 100644 --- a/drivers/clk/clk-bulk.c +++ b/drivers/clk/clk-bulk.c @@ -105,6 +105,7 @@ err: return ret; } +EXPORT_SYMBOL_GPL(clk_bulk_prepare); #endif /* CONFIG_HAVE_CLK_PREPARE */ diff --git a/drivers/clk/rockchip/clk-rk3128.c b/drivers/clk/rockchip/clk-rk3128.c index 62d7854e4b87..5970a50671b9 100644 --- a/drivers/clk/rockchip/clk-rk3128.c +++ b/drivers/clk/rockchip/clk-rk3128.c @@ -315,13 +315,13 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { RK2928_CLKGATE_CON(10), 8, GFLAGS), GATE(SCLK_PVTM_CORE, "clk_pvtm_core", "xin24m", 0, - RK2928_CLKGATE_CON(10), 8, GFLAGS), + RK2928_CLKGATE_CON(10), 0, GFLAGS), GATE(SCLK_PVTM_GPU, "clk_pvtm_gpu", "xin24m", 0, - RK2928_CLKGATE_CON(10), 8, GFLAGS), + RK2928_CLKGATE_CON(10), 1, GFLAGS), GATE(SCLK_PVTM_FUNC, "clk_pvtm_func", "xin24m", 0, - RK2928_CLKGATE_CON(10), 8, GFLAGS), + RK2928_CLKGATE_CON(10), 2, GFLAGS), GATE(SCLK_MIPI_24M, "clk_mipi_24m", "xin24m", CLK_IGNORE_UNUSED, - RK2928_CLKGATE_CON(10), 8, GFLAGS), + RK2928_CLKGATE_CON(2), 15, GFLAGS), COMPOSITE(SCLK_SDMMC, "sclk_sdmmc0", mux_mmc_src_p, 0, RK2928_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 6, DFLAGS, @@ -541,7 +541,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { GATE(0, "pclk_grf", "pclk_cpu", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(5), 4, GFLAGS), GATE(0, "pclk_mipiphy", "pclk_cpu", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(5), 0, GFLAGS), - GATE(0, "pclk_pmu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 2, GFLAGS), + GATE(0, "pclk_pmu", "pclk_pmu_pre", 0, RK2928_CLKGATE_CON(9), 2, GFLAGS), GATE(0, "pclk_pmu_niu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 3, GFLAGS), /* PD_MMC */ @@ -577,6 +577,8 @@ static const char *const rk3128_critical_clocks[] __initconst = { "aclk_peri", "hclk_peri", "pclk_peri", + "pclk_pmu", + "sclk_timer5", }; static struct rockchip_clk_provider *__init rk3128_common_clk_init(struct device_node *np) diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c index e40b77583c47..d8d3cb67b402 100644 --- a/drivers/clk/samsung/clk-exynos4.c +++ b/drivers/clk/samsung/clk-exynos4.c @@ -294,6 +294,18 @@ static const struct samsung_clk_reg_dump src_mask_suspend_e4210[] = { #define PLL_ENABLED (1 << 31) #define PLL_LOCKED (1 << 29) +static void exynos4_clk_enable_pll(u32 reg) +{ + u32 pll_con = readl(reg_base + reg); + pll_con |= PLL_ENABLED; + writel(pll_con, reg_base + reg); + + while (!(pll_con & PLL_LOCKED)) { + cpu_relax(); + pll_con = readl(reg_base + reg); + } +} + static void exynos4_clk_wait_for_pll(u32 reg) { u32 pll_con; @@ -315,6 +327,9 @@ static int exynos4_clk_suspend(void) samsung_clk_save(reg_base, exynos4_save_pll, ARRAY_SIZE(exynos4_clk_pll_regs)); + exynos4_clk_enable_pll(EPLL_CON0); + exynos4_clk_enable_pll(VPLL_CON0); + if (exynos4_soc == EXYNOS4210) { samsung_clk_save(reg_base, exynos4_save_soc, ARRAY_SIZE(exynos4210_clk_save)); diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index d805b6e6fe71..27743be5b768 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -606,11 +606,6 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder, connector->encoder->base.id, connector->encoder->name); - /* ELD Conn_Type */ - connector->eld[5] &= ~(3 << 2); - if (intel_crtc_has_dp_encoder(crtc_state)) - connector->eld[5] |= (1 << 2); - connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2; if (dev_priv->display.audio_codec_enable) diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 183e87e8ea31..00c6aee0a9a1 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -1163,6 +1163,13 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port, is_hdmi = is_dvi && (child->common.device_type & DEVICE_TYPE_NOT_HDMI_OUTPUT) == 0; is_edp = is_dp && (child->common.device_type & DEVICE_TYPE_INTERNAL_CONNECTOR); + if (port == PORT_A && is_dvi) { + DRM_DEBUG_KMS("VBT claims port A supports DVI%s, ignoring\n", + is_hdmi ? "/HDMI" : ""); + is_dvi = false; + is_hdmi = false; + } + info->supports_dvi = is_dvi; info->supports_hdmi = is_hdmi; info->supports_dp = is_dp; diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 965988f79a55..92c1f8e166dc 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -216,7 +216,7 @@ static void gen9_set_dc_state_debugmask(struct drm_i915_private *dev_priv) mask = DC_STATE_DEBUG_MASK_MEMORY_UP; - if (IS_BROXTON(dev_priv)) + if (IS_GEN9_LP(dev_priv)) mask |= DC_STATE_DEBUG_MASK_CORES; /* The below bit doesn't need to be cleared ever afterwards */ diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 4b4fd1f8110b..476681d5940c 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1655,7 +1655,8 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder, out: if (ret && IS_GEN9_LP(dev_priv)) { tmp = I915_READ(BXT_PHY_CTL(port)); - if ((tmp & (BXT_PHY_LANE_POWERDOWN_ACK | + if ((tmp & (BXT_PHY_CMNLANE_POWERDOWN_ACK | + BXT_PHY_LANE_POWERDOWN_ACK | BXT_PHY_LANE_ENABLED)) != BXT_PHY_LANE_ENABLED) DRM_ERROR("Port %c enabled but PHY powered down? " "(PHY_CTL %08x)\n", port_name(port), tmp); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 00cd17c76fdc..64f7b51ed97c 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -12359,7 +12359,6 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct drm_crtc *crtc; struct intel_crtc_state *intel_cstate; - bool hw_check = intel_state->modeset; u64 put_domains[I915_MAX_PIPES] = {}; unsigned crtc_vblank_mask = 0; int i; @@ -12376,7 +12375,6 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) if (needs_modeset(new_crtc_state) || to_intel_crtc_state(new_crtc_state)->update_pipe) { - hw_check = true; put_domains[to_intel_crtc(crtc)->pipe] = modeset_get_crtc_power_domains(crtc, diff --git a/drivers/gpu/drm/i915/intel_dpio_phy.c b/drivers/gpu/drm/i915/intel_dpio_phy.c index 09b670929786..de38d014ed39 100644 --- a/drivers/gpu/drm/i915/intel_dpio_phy.c +++ b/drivers/gpu/drm/i915/intel_dpio_phy.c @@ -208,12 +208,6 @@ static const struct bxt_ddi_phy_info glk_ddi_phy_info[] = { }, }; -static u32 bxt_phy_port_mask(const struct bxt_ddi_phy_info *phy_info) -{ - return (phy_info->dual_channel * BIT(phy_info->channel[DPIO_CH1].port)) | - BIT(phy_info->channel[DPIO_CH0].port); -} - static const struct bxt_ddi_phy_info * bxt_get_phy_list(struct drm_i915_private *dev_priv, int *count) { @@ -313,7 +307,6 @@ bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv, enum dpio_phy phy) { const struct bxt_ddi_phy_info *phy_info; - enum port port; phy_info = bxt_get_phy_info(dev_priv, phy); @@ -335,19 +328,6 @@ bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv, return false; } - for_each_port_masked(port, bxt_phy_port_mask(phy_info)) { - u32 tmp = I915_READ(BXT_PHY_CTL(port)); - - if (tmp & BXT_PHY_CMNLANE_POWERDOWN_ACK) { - DRM_DEBUG_DRIVER("DDI PHY %d powered, but common lane " - "for port %c powered down " - "(PHY_CTL %08x)\n", - phy, port_name(port), tmp); - - return false; - } - } - return true; } diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c index 951e834dd274..28a778b785ac 100644 --- a/drivers/gpu/drm/i915/intel_modes.c +++ b/drivers/gpu/drm/i915/intel_modes.c @@ -30,6 +30,21 @@ #include "intel_drv.h" #include "i915_drv.h" +static void intel_connector_update_eld_conn_type(struct drm_connector *connector) +{ + u8 conn_type; + + if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort || + connector->connector_type == DRM_MODE_CONNECTOR_eDP) { + conn_type = DRM_ELD_CONN_TYPE_DP; + } else { + conn_type = DRM_ELD_CONN_TYPE_HDMI; + } + + connector->eld[DRM_ELD_SAD_COUNT_CONN_TYPE] &= ~DRM_ELD_CONN_TYPE_MASK; + connector->eld[DRM_ELD_SAD_COUNT_CONN_TYPE] |= conn_type; +} + /** * intel_connector_update_modes - update connector from edid * @connector: DRM connector device to use @@ -44,6 +59,8 @@ int intel_connector_update_modes(struct drm_connector *connector, ret = drm_add_edid_modes(connector, edid); drm_edid_to_eld(connector, edid); + intel_connector_update_eld_conn_type(connector); + return ret; } diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index b66d8e136aa3..b3a087cb0860 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -2782,6 +2782,9 @@ static void cnl_display_core_init(struct drm_i915_private *dev_priv, bool resume /* 6. Enable DBUF */ gen9_dbuf_enable(dev_priv); + + if (resume && dev_priv->csr.dmc_payload) + intel_csr_load_program(dev_priv); } #undef CNL_PROCMON_IDX diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c index 9ea6cd5a1370..3cf1a6932fac 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c @@ -302,26 +302,29 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, hdmi->mod_clk = devm_clk_get(dev, "mod"); if (IS_ERR(hdmi->mod_clk)) { dev_err(dev, "Couldn't get the HDMI mod clock\n"); - return PTR_ERR(hdmi->mod_clk); + ret = PTR_ERR(hdmi->mod_clk); + goto err_disable_bus_clk; } clk_prepare_enable(hdmi->mod_clk); hdmi->pll0_clk = devm_clk_get(dev, "pll-0"); if (IS_ERR(hdmi->pll0_clk)) { dev_err(dev, "Couldn't get the HDMI PLL 0 clock\n"); - return PTR_ERR(hdmi->pll0_clk); + ret = PTR_ERR(hdmi->pll0_clk); + goto err_disable_mod_clk; } hdmi->pll1_clk = devm_clk_get(dev, "pll-1"); if (IS_ERR(hdmi->pll1_clk)) { dev_err(dev, "Couldn't get the HDMI PLL 1 clock\n"); - return PTR_ERR(hdmi->pll1_clk); + ret = PTR_ERR(hdmi->pll1_clk); + goto err_disable_mod_clk; } ret = sun4i_tmds_create(hdmi); if (ret) { dev_err(dev, "Couldn't create the TMDS clock\n"); - return ret; + goto err_disable_mod_clk; } writel(SUN4I_HDMI_CTRL_ENABLE, hdmi->base + SUN4I_HDMI_CTRL_REG); @@ -362,7 +365,7 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, ret = sun4i_hdmi_i2c_create(dev, hdmi); if (ret) { dev_err(dev, "Couldn't create the HDMI I2C adapter\n"); - return ret; + goto err_disable_mod_clk; } drm_encoder_helper_add(&hdmi->encoder, @@ -422,6 +425,10 @@ err_cleanup_connector: drm_encoder_cleanup(&hdmi->encoder); err_del_i2c_adapter: i2c_del_adapter(hdmi->i2c); +err_disable_mod_clk: + clk_disable_unprepare(hdmi->mod_clk); +err_disable_bus_clk: + clk_disable_unprepare(hdmi->bus_clk); return ret; } @@ -434,6 +441,8 @@ static void sun4i_hdmi_unbind(struct device *dev, struct device *master, drm_connector_cleanup(&hdmi->connector); drm_encoder_cleanup(&hdmi->encoder); i2c_del_adapter(hdmi->i2c); + clk_disable_unprepare(hdmi->mod_clk); + clk_disable_unprepare(hdmi->bus_clk); } static const struct component_ops sun4i_hdmi_ops = { diff --git a/drivers/hwmon/xgene-hwmon.c b/drivers/hwmon/xgene-hwmon.c index 9c0dbb8191ad..e1be61095532 100644 --- a/drivers/hwmon/xgene-hwmon.c +++ b/drivers/hwmon/xgene-hwmon.c @@ -630,7 +630,7 @@ static int xgene_hwmon_probe(struct platform_device *pdev) sizeof(struct slimpro_resp_msg) * ASYNC_MSG_FIFO_SIZE, GFP_KERNEL); if (rc) - goto out_mbox_free; + return -ENOMEM; INIT_WORK(&ctx->workq, xgene_hwmon_evt_work); @@ -646,7 +646,8 @@ static int xgene_hwmon_probe(struct platform_device *pdev) if (IS_ERR(ctx->mbox_chan)) { dev_err(&pdev->dev, "SLIMpro mailbox channel request failed\n"); - return -ENODEV; + rc = -ENODEV; + goto out_mbox_free; } } else { struct acpi_pcct_hw_reduced *cppc_ss; @@ -654,7 +655,8 @@ static int xgene_hwmon_probe(struct platform_device *pdev) if (device_property_read_u32(&pdev->dev, "pcc-channel", &ctx->mbox_idx)) { dev_err(&pdev->dev, "no pcc-channel property\n"); - return -ENODEV; + rc = -ENODEV; + goto out_mbox_free; } cl->rx_callback = xgene_hwmon_pcc_rx_cb; @@ -662,7 +664,8 @@ static int xgene_hwmon_probe(struct platform_device *pdev) if (IS_ERR(ctx->mbox_chan)) { dev_err(&pdev->dev, "PPC channel request failed\n"); - return -ENODEV; + rc = -ENODEV; + goto out_mbox_free; } /* @@ -675,13 +678,13 @@ static int xgene_hwmon_probe(struct platform_device *pdev) if (!cppc_ss) { dev_err(&pdev->dev, "PPC subspace not found\n"); rc = -ENODEV; - goto out_mbox_free; + goto out; } if (!ctx->mbox_chan->mbox->txdone_irq) { dev_err(&pdev->dev, "PCC IRQ not supported\n"); rc = -ENODEV; - goto out_mbox_free; + goto out; } /* @@ -696,14 +699,14 @@ static int xgene_hwmon_probe(struct platform_device *pdev) } else { dev_err(&pdev->dev, "Failed to get PCC comm region\n"); rc = -ENODEV; - goto out_mbox_free; + goto out; } if (!ctx->pcc_comm_addr) { dev_err(&pdev->dev, "Failed to ioremap PCC comm region\n"); rc = -ENOMEM; - goto out_mbox_free; + goto out; } /* diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index c06dce2c1da7..45a3f3ca29b3 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -131,6 +131,7 @@ config I2C_I801 Gemini Lake (SOC) Cannon Lake-H (PCH) Cannon Lake-LP (PCH) + Cedar Fork (PCH) This driver can also be built as a module. If so, the module will be called i2c-i801. diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index e114e4e00d29..9e12a53ef7b8 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -68,6 +68,7 @@ * Gemini Lake (SOC) 0x31d4 32 hard yes yes yes * Cannon Lake-H (PCH) 0xa323 32 hard yes yes yes * Cannon Lake-LP (PCH) 0x9da3 32 hard yes yes yes + * Cedar Fork (PCH) 0x18df 32 hard yes yes yes * * Features supported by this driver: * Software PEC no @@ -204,6 +205,7 @@ /* Older devices have their ID defined in <linux/pci_ids.h> */ #define PCI_DEVICE_ID_INTEL_BAYTRAIL_SMBUS 0x0f12 +#define PCI_DEVICE_ID_INTEL_CDF_SMBUS 0x18df #define PCI_DEVICE_ID_INTEL_DNV_SMBUS 0x19df #define PCI_DEVICE_ID_INTEL_COUGARPOINT_SMBUS 0x1c22 #define PCI_DEVICE_ID_INTEL_PATSBURG_SMBUS 0x1d22 @@ -1025,6 +1027,7 @@ static const struct pci_device_id i801_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BRASWELL_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CDF_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DNV_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BROXTON_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS) }, @@ -1513,6 +1516,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) case PCI_DEVICE_ID_INTEL_CANNONLAKE_LP_SMBUS: case PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS: case PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS: + case PCI_DEVICE_ID_INTEL_CDF_SMBUS: case PCI_DEVICE_ID_INTEL_DNV_SMBUS: case PCI_DEVICE_ID_INTEL_KABYLAKE_PCH_H_SMBUS: priv->features |= FEATURE_I2C_BLOCK_READ; diff --git a/drivers/i2c/busses/i2c-sprd.c b/drivers/i2c/busses/i2c-sprd.c index 22e08ae1704f..25fcc3c1e32b 100644 --- a/drivers/i2c/busses/i2c-sprd.c +++ b/drivers/i2c/busses/i2c-sprd.c @@ -627,6 +627,7 @@ static const struct dev_pm_ops sprd_i2c_pm_ops = { static const struct of_device_id sprd_i2c_of_match[] = { { .compatible = "sprd,sc9860-i2c", }, + {}, }; static struct platform_driver sprd_i2c_driver = { diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index 47c67b0ca896..d4a6e9c2e9aa 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -215,7 +215,7 @@ struct stm32f7_i2c_dev { unsigned int msg_num; unsigned int msg_id; struct stm32f7_i2c_msg f7_msg; - struct stm32f7_i2c_setup *setup; + struct stm32f7_i2c_setup setup; struct stm32f7_i2c_timings timing; }; @@ -265,7 +265,7 @@ static struct stm32f7_i2c_spec i2c_specs[] = { }, }; -struct stm32f7_i2c_setup stm32f7_setup = { +static const struct stm32f7_i2c_setup stm32f7_setup = { .rise_time = STM32F7_I2C_RISE_TIME_DEFAULT, .fall_time = STM32F7_I2C_FALL_TIME_DEFAULT, .dnf = STM32F7_I2C_DNF_DEFAULT, @@ -537,7 +537,7 @@ static void stm32f7_i2c_hw_config(struct stm32f7_i2c_dev *i2c_dev) writel_relaxed(timing, i2c_dev->base + STM32F7_I2C_TIMINGR); /* Enable I2C */ - if (i2c_dev->setup->analog_filter) + if (i2c_dev->setup.analog_filter) stm32f7_i2c_clr_bits(i2c_dev->base + STM32F7_I2C_CR1, STM32F7_I2C_CR1_ANFOFF); else @@ -887,22 +887,19 @@ static int stm32f7_i2c_probe(struct platform_device *pdev) } setup = of_device_get_match_data(&pdev->dev); - i2c_dev->setup->rise_time = setup->rise_time; - i2c_dev->setup->fall_time = setup->fall_time; - i2c_dev->setup->dnf = setup->dnf; - i2c_dev->setup->analog_filter = setup->analog_filter; + i2c_dev->setup = *setup; ret = device_property_read_u32(i2c_dev->dev, "i2c-scl-rising-time-ns", &rise_time); if (!ret) - i2c_dev->setup->rise_time = rise_time; + i2c_dev->setup.rise_time = rise_time; ret = device_property_read_u32(i2c_dev->dev, "i2c-scl-falling-time-ns", &fall_time); if (!ret) - i2c_dev->setup->fall_time = fall_time; + i2c_dev->setup.fall_time = fall_time; - ret = stm32f7_i2c_setup_timing(i2c_dev, i2c_dev->setup); + ret = stm32f7_i2c_setup_timing(i2c_dev, &i2c_dev->setup); if (ret) goto clk_free; diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 01b2adfd8226..eaf39e5db08b 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -1451,6 +1451,7 @@ int ide_host_register(struct ide_host *host, const struct ide_port_info *d, if (hwif_init(hwif) == 0) { printk(KERN_INFO "%s: failed to initialize IDE " "interface\n", hwif->name); + device_unregister(hwif->portdev); device_unregister(&hwif->gendev); ide_disable_port(hwif); continue; diff --git a/drivers/ide/ide-scan-pci.c b/drivers/ide/ide-scan-pci.c index 86aa88aeb3a6..acf874800ca4 100644 --- a/drivers/ide/ide-scan-pci.c +++ b/drivers/ide/ide-scan-pci.c @@ -56,6 +56,7 @@ static int __init ide_scan_pcidev(struct pci_dev *dev) { struct list_head *l; struct pci_driver *d; + int ret; list_for_each(l, &ide_pci_drivers) { d = list_entry(l, struct pci_driver, node); @@ -63,10 +64,14 @@ static int __init ide_scan_pcidev(struct pci_dev *dev) const struct pci_device_id *id = pci_match_id(d->id_table, dev); - if (id != NULL && d->probe(dev, id) >= 0) { - dev->driver = d; - pci_dev_get(dev); - return 1; + if (id != NULL) { + pci_assign_irq(dev); + ret = d->probe(dev, id); + if (ret >= 0) { + dev->driver = d; + pci_dev_get(dev); + return 1; + } } } } diff --git a/drivers/ide/setup-pci.c b/drivers/ide/setup-pci.c index 112d2fe1bcdb..fdc8e813170c 100644 --- a/drivers/ide/setup-pci.c +++ b/drivers/ide/setup-pci.c @@ -179,6 +179,7 @@ EXPORT_SYMBOL_GPL(ide_setup_pci_noise); /** * ide_pci_enable - do PCI enables * @dev: PCI device + * @bars: PCI BARs mask * @d: IDE port info * * Enable the IDE PCI device. We attempt to enable the device in full @@ -189,9 +190,10 @@ EXPORT_SYMBOL_GPL(ide_setup_pci_noise); * Returns zero on success or an error code */ -static int ide_pci_enable(struct pci_dev *dev, const struct ide_port_info *d) +static int ide_pci_enable(struct pci_dev *dev, int bars, + const struct ide_port_info *d) { - int ret, bars; + int ret; if (pci_enable_device(dev)) { ret = pci_enable_device_io(dev); @@ -216,18 +218,6 @@ static int ide_pci_enable(struct pci_dev *dev, const struct ide_port_info *d) goto out; } - if (d->host_flags & IDE_HFLAG_SINGLE) - bars = (1 << 2) - 1; - else - bars = (1 << 4) - 1; - - if ((d->host_flags & IDE_HFLAG_NO_DMA) == 0) { - if (d->host_flags & IDE_HFLAG_CS5520) - bars |= (1 << 2); - else - bars |= (1 << 4); - } - ret = pci_request_selected_regions(dev, bars, d->name); if (ret < 0) printk(KERN_ERR "%s %s: can't reserve resources\n", @@ -403,6 +393,7 @@ int ide_hwif_setup_dma(ide_hwif_t *hwif, const struct ide_port_info *d) /** * ide_setup_pci_controller - set up IDE PCI * @dev: PCI device + * @bars: PCI BARs mask * @d: IDE port info * @noisy: verbose flag * @@ -411,7 +402,7 @@ int ide_hwif_setup_dma(ide_hwif_t *hwif, const struct ide_port_info *d) * and enables it if need be */ -static int ide_setup_pci_controller(struct pci_dev *dev, +static int ide_setup_pci_controller(struct pci_dev *dev, int bars, const struct ide_port_info *d, int noisy) { int ret; @@ -420,7 +411,7 @@ static int ide_setup_pci_controller(struct pci_dev *dev, if (noisy) ide_setup_pci_noise(dev, d); - ret = ide_pci_enable(dev, d); + ret = ide_pci_enable(dev, bars, d); if (ret < 0) goto out; @@ -428,16 +419,20 @@ static int ide_setup_pci_controller(struct pci_dev *dev, if (ret < 0) { printk(KERN_ERR "%s %s: error accessing PCI regs\n", d->name, pci_name(dev)); - goto out; + goto out_free_bars; } if (!(pcicmd & PCI_COMMAND_IO)) { /* is device disabled? */ ret = ide_pci_configure(dev, d); if (ret < 0) - goto out; + goto out_free_bars; printk(KERN_INFO "%s %s: device enabled (Linux)\n", d->name, pci_name(dev)); } + goto out; + +out_free_bars: + pci_release_selected_regions(dev, bars); out: return ret; } @@ -540,13 +535,28 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2, { struct pci_dev *pdev[] = { dev1, dev2 }; struct ide_host *host; - int ret, i, n_ports = dev2 ? 4 : 2; + int ret, i, n_ports = dev2 ? 4 : 2, bars; struct ide_hw hw[4], *hws[] = { NULL, NULL, NULL, NULL }; + if (d->host_flags & IDE_HFLAG_SINGLE) + bars = (1 << 2) - 1; + else + bars = (1 << 4) - 1; + + if ((d->host_flags & IDE_HFLAG_NO_DMA) == 0) { + if (d->host_flags & IDE_HFLAG_CS5520) + bars |= (1 << 2); + else + bars |= (1 << 4); + } + for (i = 0; i < n_ports / 2; i++) { - ret = ide_setup_pci_controller(pdev[i], d, !i); - if (ret < 0) + ret = ide_setup_pci_controller(pdev[i], bars, d, !i); + if (ret < 0) { + if (i == 1) + pci_release_selected_regions(pdev[0], bars); goto out; + } ide_pci_setup_ports(pdev[i], d, &hw[i*2], &hws[i*2]); } @@ -554,7 +564,7 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2, host = ide_host_alloc(d, hws, n_ports); if (host == NULL) { ret = -ENOMEM; - goto out; + goto out_free_bars; } host->dev[0] = &dev1->dev; @@ -576,7 +586,7 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2, * do_ide_setup_pci_device() on the first device! */ if (ret < 0) - goto out; + goto out_free_bars; /* fixup IRQ */ if (ide_pci_is_in_compatibility_mode(pdev[i])) { @@ -589,6 +599,13 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2, ret = ide_host_register(host, d, hws); if (ret) ide_host_free(host); + else + goto out; + +out_free_bars: + i = n_ports / 2; + while (i--) + pci_release_selected_regions(pdev[i], bars); out: return ret; } diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c index 30825bb9b8e9..8861c052155a 100644 --- a/drivers/infiniband/core/iwpm_msg.c +++ b/drivers/infiniband/core/iwpm_msg.c @@ -100,6 +100,8 @@ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client) if (ret) goto pid_query_error; + nlmsg_end(skb, nlh); + pr_debug("%s: Multicasting a nlmsg (dev = %s ifname = %s iwpm = %s)\n", __func__, pm_msg->dev_name, pm_msg->if_name, iwpm_ulib_name); @@ -170,6 +172,8 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) &pm_msg->loc_addr, IWPM_NLA_MANAGE_ADDR); if (ret) goto add_mapping_error; + + nlmsg_end(skb, nlh); nlmsg_request->req_buffer = pm_msg; ret = rdma_nl_unicast_wait(skb, iwpm_user_pid); @@ -246,6 +250,8 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) &pm_msg->rem_addr, IWPM_NLA_QUERY_REMOTE_ADDR); if (ret) goto query_mapping_error; + + nlmsg_end(skb, nlh); nlmsg_request->req_buffer = pm_msg; ret = rdma_nl_unicast_wait(skb, iwpm_user_pid); @@ -308,6 +314,8 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client) if (ret) goto remove_mapping_error; + nlmsg_end(skb, nlh); + ret = rdma_nl_unicast_wait(skb, iwpm_user_pid); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c index c81c55942626..3c4faadb8cdd 100644 --- a/drivers/infiniband/core/iwpm_util.c +++ b/drivers/infiniband/core/iwpm_util.c @@ -597,6 +597,9 @@ static int send_mapinfo_num(u32 mapping_num, u8 nl_client, int iwpm_pid) &mapping_num, IWPM_NLA_MAPINFO_SEND_NUM); if (ret) goto mapinfo_num_error; + + nlmsg_end(skb, nlh); + ret = rdma_nl_unicast(skb, iwpm_pid); if (ret) { skb = NULL; @@ -678,6 +681,8 @@ int iwpm_send_mapinfo(u8 nl_client, int iwpm_pid) if (ret) goto send_mapping_info_unlock; + nlmsg_end(skb, nlh); + iwpm_print_sockaddr(&map_info->local_sockaddr, "send_mapping_info: Local sockaddr:"); iwpm_print_sockaddr(&map_info->mapped_sockaddr, diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c index d1f5345f04f0..42ca5346777d 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c +++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c @@ -48,7 +48,7 @@ * @wqe: cqp wqe for header * @header: header for the cqp wqe */ -static inline void i40iw_insert_wqe_hdr(u64 *wqe, u64 header) +void i40iw_insert_wqe_hdr(u64 *wqe, u64 header) { wmb(); /* make sure WQE is populated before polarity is set */ set_64bit_val(wqe, 24, header); diff --git a/drivers/infiniband/hw/i40iw/i40iw_p.h b/drivers/infiniband/hw/i40iw/i40iw_p.h index e217a1259f57..5498ad01c280 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_p.h +++ b/drivers/infiniband/hw/i40iw/i40iw_p.h @@ -59,6 +59,8 @@ enum i40iw_status_code i40iw_sc_mr_fast_register(struct i40iw_sc_qp *qp, struct i40iw_fast_reg_stag_info *info, bool post_sq); +void i40iw_insert_wqe_hdr(u64 *wqe, u64 header); + /* HMC/FPM functions */ enum i40iw_status_code i40iw_sc_init_iw_hmc(struct i40iw_sc_dev *dev, u8 hmc_fn_id); diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.c b/drivers/infiniband/hw/i40iw/i40iw_puda.c index c2cab20c4bc5..59f70676f0e0 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_puda.c +++ b/drivers/infiniband/hw/i40iw/i40iw_puda.c @@ -123,12 +123,11 @@ static void i40iw_puda_post_recvbuf(struct i40iw_puda_rsrc *rsrc, u32 wqe_idx, get_64bit_val(wqe, 24, &offset24); offset24 = (offset24) ? 0 : LS_64(1, I40IWQPSQ_VALID); - set_64bit_val(wqe, 24, offset24); set_64bit_val(wqe, 0, buf->mem.pa); set_64bit_val(wqe, 8, LS_64(buf->mem.size, I40IWQPSQ_FRAG_LEN)); - set_64bit_val(wqe, 24, offset24); + i40iw_insert_wqe_hdr(wqe, offset24); } /** @@ -409,9 +408,7 @@ enum i40iw_status_code i40iw_puda_send(struct i40iw_sc_qp *qp, set_64bit_val(wqe, 8, LS_64(info->len, I40IWQPSQ_FRAG_LEN)); set_64bit_val(wqe, 16, header[0]); - /* Ensure all data is written before writing valid bit */ - wmb(); - set_64bit_val(wqe, 24, header[1]); + i40iw_insert_wqe_hdr(wqe, header[1]); i40iw_debug_buf(qp->dev, I40IW_DEBUG_PUDA, "PUDA SEND WQE", wqe, 32); i40iw_qp_post_wr(&qp->qp_uk); @@ -539,7 +536,7 @@ static enum i40iw_status_code i40iw_puda_qp_wqe(struct i40iw_sc_dev *dev, struct LS_64(2, I40IW_CQPSQ_QP_NEXTIWSTATE) | LS_64(cqp->polarity, I40IW_CQPSQ_WQEVALID); - set_64bit_val(wqe, 24, header); + i40iw_insert_wqe_hdr(wqe, header); i40iw_debug_buf(cqp->dev, I40IW_DEBUG_PUDA, "PUDA CQE", wqe, 32); i40iw_sc_cqp_post_sq(cqp); @@ -655,7 +652,7 @@ static enum i40iw_status_code i40iw_puda_cq_wqe(struct i40iw_sc_dev *dev, struct LS_64(1, I40IW_CQPSQ_CQ_ENCEQEMASK) | LS_64(1, I40IW_CQPSQ_CQ_CEQIDVALID) | LS_64(cqp->polarity, I40IW_CQPSQ_WQEVALID); - set_64bit_val(wqe, 24, header); + i40iw_insert_wqe_hdr(wqe, header); i40iw_debug_buf(dev, I40IW_DEBUG_PUDA, "PUDA CQE", wqe, I40IW_CQP_WQE_SIZE * 8); diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 28b3d02d511b..62be0a41ad0b 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -826,12 +826,14 @@ static int i40iw_query_qp(struct ib_qp *ibqp, attr->cap.max_inline_data = I40IW_MAX_INLINE_DATA_SIZE; attr->cap.max_send_sge = I40IW_MAX_WQ_FRAGMENT_COUNT; attr->cap.max_recv_sge = I40IW_MAX_WQ_FRAGMENT_COUNT; + attr->port_num = 1; init_attr->event_handler = iwqp->ibqp.event_handler; init_attr->qp_context = iwqp->ibqp.qp_context; init_attr->send_cq = iwqp->ibqp.send_cq; init_attr->recv_cq = iwqp->ibqp.recv_cq; init_attr->srq = iwqp->ibqp.srq; init_attr->cap = attr->cap; + init_attr->port_num = 1; return 0; } diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index d6fbad8f34aa..552f7bd4ecc3 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -4174,9 +4174,9 @@ err_bfreg: err_uar_page: mlx5_put_uars_page(dev->mdev, dev->mdev->priv.uar); -err_cnt: - mlx5_ib_cleanup_cong_debugfs(dev); err_cong: + mlx5_ib_cleanup_cong_debugfs(dev); +err_cnt: if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) mlx5_ib_dealloc_counters(dev); diff --git a/drivers/infiniband/hw/qedr/Kconfig b/drivers/infiniband/hw/qedr/Kconfig index 6c9f3923e838..60e867d80b88 100644 --- a/drivers/infiniband/hw/qedr/Kconfig +++ b/drivers/infiniband/hw/qedr/Kconfig @@ -2,6 +2,7 @@ config INFINIBAND_QEDR tristate "QLogic RoCE driver" depends on 64BIT && QEDE select QED_LL2 + select QED_OOO select QED_RDMA ---help--- This driver provides low-level InfiniBand over Ethernet diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h index b2bb42e2805d..254083b524bd 100644 --- a/drivers/infiniband/hw/qedr/qedr.h +++ b/drivers/infiniband/hw/qedr/qedr.h @@ -387,7 +387,7 @@ struct qedr_qp { u8 wqe_size; u8 smac[ETH_ALEN]; - u16 vlan_id; + u16 vlan; int rc; } *rqe_wr_id; diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c index 4689e802b332..ad8965397cf7 100644 --- a/drivers/infiniband/hw/qedr/qedr_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_cm.c @@ -105,7 +105,7 @@ void qedr_ll2_complete_rx_packet(void *cxt, qp->rqe_wr_id[qp->rq.gsi_cons].rc = data->u.data_length_error ? -EINVAL : 0; - qp->rqe_wr_id[qp->rq.gsi_cons].vlan_id = data->vlan; + qp->rqe_wr_id[qp->rq.gsi_cons].vlan = data->vlan; /* note: length stands for data length i.e. GRH is excluded */ qp->rqe_wr_id[qp->rq.gsi_cons].sg_list[0].length = data->length.data_length; @@ -694,6 +694,7 @@ int qedr_gsi_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) struct qedr_cq *cq = get_qedr_cq(ibcq); struct qedr_qp *qp = dev->gsi_qp; unsigned long flags; + u16 vlan_id; int i = 0; spin_lock_irqsave(&cq->cq_lock, flags); @@ -712,9 +713,14 @@ int qedr_gsi_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) wc[i].wc_flags |= IB_WC_GRH | IB_WC_IP_CSUM_OK; ether_addr_copy(wc[i].smac, qp->rqe_wr_id[qp->rq.cons].smac); wc[i].wc_flags |= IB_WC_WITH_SMAC; - if (qp->rqe_wr_id[qp->rq.cons].vlan_id) { + + vlan_id = qp->rqe_wr_id[qp->rq.cons].vlan & + VLAN_VID_MASK; + if (vlan_id) { wc[i].wc_flags |= IB_WC_WITH_VLAN; - wc[i].vlan_id = qp->rqe_wr_id[qp->rq.cons].vlan_id; + wc[i].vlan_id = vlan_id; + wc[i].sl = (qp->rqe_wr_id[qp->rq.cons].vlan & + VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } qedr_inc_sw_cons(&qp->rq); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 6cd61638b441..fe690f82af29 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -893,13 +893,17 @@ dev_stop: void ipoib_pkey_dev_check_presence(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); + struct rdma_netdev *rn = netdev_priv(dev); if (!(priv->pkey & 0x7fff) || ib_find_pkey(priv->ca, priv->port, priv->pkey, - &priv->pkey_index)) + &priv->pkey_index)) { clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags); - else + } else { + if (rn->set_id) + rn->set_id(dev, priv->pkey_index); set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags); + } } void ipoib_ib_dev_up(struct net_device *dev) @@ -1203,10 +1207,15 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, ipoib_ib_dev_down(dev); if (level == IPOIB_FLUSH_HEAVY) { + rtnl_lock(); if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) ipoib_ib_dev_stop(dev); - if (ipoib_ib_dev_open(dev) != 0) + + result = ipoib_ib_dev_open(dev); + rtnl_unlock(); + if (result) return; + if (netif_queue_stopped(dev)) netif_start_queue(dev); } diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c index 2da3ff650e1d..c990c6bbffc2 100644 --- a/drivers/isdn/gigaset/bas-gigaset.c +++ b/drivers/isdn/gigaset/bas-gigaset.c @@ -433,10 +433,11 @@ static void check_pending(struct bas_cardstate *ucs) * argument: * controller state structure */ -static void cmd_in_timeout(unsigned long data) +static void cmd_in_timeout(struct timer_list *t) { - struct cardstate *cs = (struct cardstate *) data; - struct bas_cardstate *ucs = cs->hw.bas; + struct bas_cardstate *ucs = from_timer(ucs, t, timer_cmd_in); + struct urb *urb = ucs->urb_int_in; + struct cardstate *cs = urb->context; int rc; if (!ucs->rcvbuf_size) { @@ -639,10 +640,11 @@ static void int_in_work(struct work_struct *work) * argument: * controller state structure */ -static void int_in_resubmit(unsigned long data) +static void int_in_resubmit(struct timer_list *t) { - struct cardstate *cs = (struct cardstate *) data; - struct bas_cardstate *ucs = cs->hw.bas; + struct bas_cardstate *ucs = from_timer(ucs, t, timer_int_in); + struct urb *urb = ucs->urb_int_in; + struct cardstate *cs = urb->context; int rc; if (ucs->retry_int_in++ >= BAS_RETRY) { @@ -1441,10 +1443,11 @@ error: * argument: * controller state structure */ -static void req_timeout(unsigned long data) +static void req_timeout(struct timer_list *t) { - struct cardstate *cs = (struct cardstate *) data; - struct bas_cardstate *ucs = cs->hw.bas; + struct bas_cardstate *ucs = from_timer(ucs, t, timer_ctrl); + struct urb *urb = ucs->urb_int_in; + struct cardstate *cs = urb->context; int pending; unsigned long flags; @@ -1837,10 +1840,11 @@ static void write_command_callback(struct urb *urb) * argument: * controller state structure */ -static void atrdy_timeout(unsigned long data) +static void atrdy_timeout(struct timer_list *t) { - struct cardstate *cs = (struct cardstate *) data; - struct bas_cardstate *ucs = cs->hw.bas; + struct bas_cardstate *ucs = from_timer(ucs, t, timer_atrdy); + struct urb *urb = ucs->urb_int_in; + struct cardstate *cs = urb->context; dev_warn(cs->dev, "timeout waiting for HD_READY_SEND_ATDATA\n"); @@ -2200,7 +2204,7 @@ static int gigaset_initcshw(struct cardstate *cs) { struct bas_cardstate *ucs; - cs->hw.bas = ucs = kmalloc(sizeof *ucs, GFP_KERNEL); + cs->hw.bas = ucs = kzalloc(sizeof(*ucs), GFP_KERNEL); if (!ucs) { pr_err("out of memory\n"); return -ENOMEM; @@ -2212,19 +2216,11 @@ static int gigaset_initcshw(struct cardstate *cs) return -ENOMEM; } - ucs->urb_cmd_in = NULL; - ucs->urb_cmd_out = NULL; - ucs->rcvbuf = NULL; - ucs->rcvbuf_size = 0; - spin_lock_init(&ucs->lock); - ucs->pending = 0; - - ucs->basstate = 0; - setup_timer(&ucs->timer_ctrl, req_timeout, (unsigned long) cs); - setup_timer(&ucs->timer_atrdy, atrdy_timeout, (unsigned long) cs); - setup_timer(&ucs->timer_cmd_in, cmd_in_timeout, (unsigned long) cs); - setup_timer(&ucs->timer_int_in, int_in_resubmit, (unsigned long) cs); + timer_setup(&ucs->timer_ctrl, req_timeout, 0); + timer_setup(&ucs->timer_atrdy, atrdy_timeout, 0); + timer_setup(&ucs->timer_cmd_in, cmd_in_timeout, 0); + timer_setup(&ucs->timer_int_in, int_in_resubmit, 0); init_waitqueue_head(&ucs->waitqueue); INIT_WORK(&ucs->int_in_wq, int_in_work); diff --git a/drivers/isdn/gigaset/common.c b/drivers/isdn/gigaset/common.c index 7c7814497e3e..15482c5de33c 100644 --- a/drivers/isdn/gigaset/common.c +++ b/drivers/isdn/gigaset/common.c @@ -153,9 +153,9 @@ static int test_timeout(struct at_state_t *at_state) return 1; } -static void timer_tick(unsigned long data) +static void timer_tick(struct timer_list *t) { - struct cardstate *cs = (struct cardstate *) data; + struct cardstate *cs = from_timer(cs, t, timer); unsigned long flags; unsigned channel; struct at_state_t *at_state; @@ -687,7 +687,7 @@ struct cardstate *gigaset_initcs(struct gigaset_driver *drv, int channels, cs->ignoreframes = ignoreframes; INIT_LIST_HEAD(&cs->temp_at_states); cs->running = 0; - init_timer(&cs->timer); /* clear next & prev */ + timer_setup(&cs->timer, timer_tick, 0); spin_lock_init(&cs->ev_lock); cs->ev_tail = 0; cs->ev_head = 0; @@ -768,7 +768,6 @@ struct cardstate *gigaset_initcs(struct gigaset_driver *drv, int channels, spin_lock_irqsave(&cs->lock, flags); cs->running = 1; spin_unlock_irqrestore(&cs->lock, flags); - setup_timer(&cs->timer, timer_tick, (unsigned long) cs); cs->timer.expires = jiffies + msecs_to_jiffies(GIG_TICK); add_timer(&cs->timer); diff --git a/drivers/isdn/hardware/mISDN/mISDNipac.c b/drivers/isdn/hardware/mISDN/mISDNipac.c index e240010b93fa..4d78f870435e 100644 --- a/drivers/isdn/hardware/mISDN/mISDNipac.c +++ b/drivers/isdn/hardware/mISDN/mISDNipac.c @@ -172,7 +172,6 @@ isac_fill_fifo(struct isac_hw *isac) pr_debug("%s: %s dbusytimer running\n", isac->name, __func__); del_timer(&isac->dch.timer); } - init_timer(&isac->dch.timer); isac->dch.timer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ)/1000); add_timer(&isac->dch.timer); if (isac->dch.debug & DEBUG_HW_DFIFO) { @@ -727,8 +726,9 @@ isac_release(struct isac_hw *isac) } static void -dbusy_timer_handler(struct isac_hw *isac) +dbusy_timer_handler(struct timer_list *t) { + struct isac_hw *isac = from_timer(isac, t, dch.timer); int rbch, star; u_long flags; @@ -796,8 +796,7 @@ isac_init(struct isac_hw *isac) } isac->mon_tx = NULL; isac->mon_rx = NULL; - setup_timer(&isac->dch.timer, (void *)dbusy_timer_handler, - (long)isac); + timer_setup(&isac->dch.timer, dbusy_timer_handler, 0); isac->mocr = 0xaa; if (isac->type & IPAC_TYPE_ISACX) { /* Disable all IRQ */ diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c index d80072fef434..536d5137f49d 100644 --- a/drivers/isdn/hardware/mISDN/w6692.c +++ b/drivers/isdn/hardware/mISDN/w6692.c @@ -311,7 +311,6 @@ W6692_fill_Dfifo(struct w6692_hw *card) pr_debug("%s: fill_Dfifo dbusytimer running\n", card->name); del_timer(&dch->timer); } - init_timer(&dch->timer); dch->timer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ) / 1000); add_timer(&dch->timer); if (debug & DEBUG_HW_DFIFO) { @@ -819,8 +818,9 @@ w6692_irq(int intno, void *dev_id) } static void -dbusy_timer_handler(struct dchannel *dch) +dbusy_timer_handler(struct timer_list *t) { + struct dchannel *dch = from_timer(dch, t, timer); struct w6692_hw *card = dch->hw; int rbch, star; u_long flags; @@ -852,8 +852,7 @@ static void initW6692(struct w6692_hw *card) { u8 val; - setup_timer(&card->dch.timer, (void *)dbusy_timer_handler, - (u_long)&card->dch); + timer_setup(&card->dch.timer, dbusy_timer_handler, 0); w6692_mode(&card->bc[0], ISDN_P_NONE); w6692_mode(&card->bc[1], ISDN_P_NONE); WriteW6692(card, W_D_CTL, 0x00); diff --git a/drivers/isdn/hisax/amd7930_fn.c b/drivers/isdn/hisax/amd7930_fn.c index dcf4c2a9fcea..77debda2221b 100644 --- a/drivers/isdn/hisax/amd7930_fn.c +++ b/drivers/isdn/hisax/amd7930_fn.c @@ -398,7 +398,6 @@ Amd7930_fill_Dfifo(struct IsdnCardState *cs) debugl1(cs, "Amd7930: fill_Dfifo dbusytimer running"); del_timer(&cs->dbusytimer); } - init_timer(&cs->dbusytimer); cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ) / 1000); add_timer(&cs->dbusytimer); @@ -686,8 +685,9 @@ DC_Close_Amd7930(struct IsdnCardState *cs) { static void -dbusy_timer_handler(struct IsdnCardState *cs) +dbusy_timer_handler(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, dbusytimer); u_long flags; struct PStack *stptr; WORD dtcr, der; @@ -790,5 +790,5 @@ void Amd7930_init(struct IsdnCardState *cs) void setup_Amd7930(struct IsdnCardState *cs) { INIT_WORK(&cs->tqueue, Amd7930_bh); - setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs); + timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0); } diff --git a/drivers/isdn/hisax/arcofi.c b/drivers/isdn/hisax/arcofi.c index 9826bad49e2c..2f784f96d439 100644 --- a/drivers/isdn/hisax/arcofi.c +++ b/drivers/isdn/hisax/arcofi.c @@ -23,7 +23,6 @@ add_arcofi_timer(struct IsdnCardState *cs) { if (test_and_set_bit(FLG_ARCOFI_TIMER, &cs->HW_Flags)) { del_timer(&cs->dc.isac.arcofitimer); } - init_timer(&cs->dc.isac.arcofitimer); cs->dc.isac.arcofitimer.expires = jiffies + ((ARCOFI_TIMER_VALUE * HZ) / 1000); add_timer(&cs->dc.isac.arcofitimer); } @@ -112,7 +111,8 @@ arcofi_fsm(struct IsdnCardState *cs, int event, void *data) { } static void -arcofi_timer(struct IsdnCardState *cs) { +arcofi_timer(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, dc.isac.arcofitimer); arcofi_fsm(cs, ARCOFI_TIMEOUT, NULL); } @@ -125,7 +125,7 @@ clear_arcofi(struct IsdnCardState *cs) { void init_arcofi(struct IsdnCardState *cs) { - setup_timer(&cs->dc.isac.arcofitimer, (void *)arcofi_timer, (long)cs); + timer_setup(&cs->dc.isac.arcofitimer, arcofi_timer, 0); init_waitqueue_head(&cs->dc.isac.arcofi_wait); test_and_set_bit(HW_ARCOFI, &cs->HW_Flags); } diff --git a/drivers/isdn/hisax/diva.c b/drivers/isdn/hisax/diva.c index 3fc94e7741ae..38bdd3f7b960 100644 --- a/drivers/isdn/hisax/diva.c +++ b/drivers/isdn/hisax/diva.c @@ -798,8 +798,9 @@ reset_diva(struct IsdnCardState *cs) #define DIVA_ASSIGN 1 static void -diva_led_handler(struct IsdnCardState *cs) +diva_led_handler(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, hw.diva.tl); int blink = 0; if ((cs->subtyp == DIVA_IPAC_ISA) || @@ -828,7 +829,6 @@ diva_led_handler(struct IsdnCardState *cs) byteout(cs->hw.diva.ctrl, cs->hw.diva.ctrl_reg); if (blink) { - init_timer(&cs->hw.diva.tl); cs->hw.diva.tl.expires = jiffies + ((blink * HZ) / 1000); add_timer(&cs->hw.diva.tl); } @@ -900,7 +900,7 @@ Diva_card_msg(struct IsdnCardState *cs, int mt, void *arg) (cs->subtyp != DIVA_IPAC_PCI) && (cs->subtyp != DIVA_IPACX_PCI)) { spin_lock_irqsave(&cs->lock, flags); - diva_led_handler(cs); + diva_led_handler(&cs->hw.diva.tl); spin_unlock_irqrestore(&cs->lock, flags); } return (0); @@ -978,8 +978,7 @@ static int setup_diva_common(struct IsdnCardState *cs) printk(KERN_INFO "Diva: IPACX Design Id: %x\n", MemReadISAC_IPACX(cs, IPACX_ID) & 0x3F); } else { /* DIVA 2.0 */ - setup_timer(&cs->hw.diva.tl, (void *)diva_led_handler, - (long)cs); + timer_setup(&cs->hw.diva.tl, diva_led_handler, 0); cs->readisac = &ReadISAC; cs->writeisac = &WriteISAC; cs->readisacfifo = &ReadISACfifo; diff --git a/drivers/isdn/hisax/elsa.c b/drivers/isdn/hisax/elsa.c index 03bc5d504e22..b21c05820f44 100644 --- a/drivers/isdn/hisax/elsa.c +++ b/drivers/isdn/hisax/elsa.c @@ -606,8 +606,9 @@ check_arcofi(struct IsdnCardState *cs) #endif /* ARCOFI_USE */ static void -elsa_led_handler(struct IsdnCardState *cs) +elsa_led_handler(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, hw.elsa.tl); int blink = 0; if (cs->subtyp == ELSA_PCMCIA || cs->subtyp == ELSA_PCMCIA_IPAC) @@ -640,7 +641,6 @@ elsa_led_handler(struct IsdnCardState *cs) } else byteout(cs->hw.elsa.ctrl, cs->hw.elsa.ctrl_reg); if (blink) { - init_timer(&cs->hw.elsa.tl); cs->hw.elsa.tl.expires = jiffies + ((blink * HZ) / 1000); add_timer(&cs->hw.elsa.tl); } @@ -715,7 +715,7 @@ Elsa_card_msg(struct IsdnCardState *cs, int mt, void *arg) init_modem(cs); } #endif - elsa_led_handler(cs); + elsa_led_handler(&cs->hw.elsa.tl); return (ret); case (MDL_REMOVE | REQUEST): cs->hw.elsa.status &= 0; @@ -767,7 +767,7 @@ Elsa_card_msg(struct IsdnCardState *cs, int mt, void *arg) else cs->hw.elsa.status &= ~ELSA_BAD_PWR; } - elsa_led_handler(cs); + elsa_led_handler(&cs->hw.elsa.tl); return (ret); } @@ -1147,7 +1147,7 @@ static int setup_elsa_common(struct IsdnCard *card) init_arcofi(cs); #endif setup_isac(cs); - setup_timer(&cs->hw.elsa.tl, (void *)elsa_led_handler, (long)cs); + timer_setup(&cs->hw.elsa.tl, elsa_led_handler, 0); /* Teste Timer */ if (cs->hw.elsa.timer) { byteout(cs->hw.elsa.trig, 0xff); diff --git a/drivers/isdn/hisax/fsm.c b/drivers/isdn/hisax/fsm.c index d63266fa8cbd..3e020ec0f65e 100644 --- a/drivers/isdn/hisax/fsm.c +++ b/drivers/isdn/hisax/fsm.c @@ -85,8 +85,9 @@ FsmChangeState(struct FsmInst *fi, int newstate) } static void -FsmExpireTimer(struct FsmTimer *ft) +FsmExpireTimer(struct timer_list *t) { + struct FsmTimer *ft = from_timer(ft, t, tl); #if FSM_TIMER_DEBUG if (ft->fi->debug) ft->fi->printdebug(ft->fi, "FsmExpireTimer %lx", (long) ft); @@ -102,7 +103,7 @@ FsmInitTimer(struct FsmInst *fi, struct FsmTimer *ft) if (ft->fi->debug) ft->fi->printdebug(ft->fi, "FsmInitTimer %lx", (long) ft); #endif - setup_timer(&ft->tl, (void *)FsmExpireTimer, (long)ft); + timer_setup(&ft->tl, FsmExpireTimer, 0); } void @@ -131,7 +132,6 @@ FsmAddTimer(struct FsmTimer *ft, ft->fi->printdebug(ft->fi, "FsmAddTimer already active!"); return -1; } - init_timer(&ft->tl); ft->event = event; ft->arg = arg; ft->tl.expires = jiffies + (millisec * HZ) / 1000; @@ -152,7 +152,6 @@ FsmRestartTimer(struct FsmTimer *ft, if (timer_pending(&ft->tl)) del_timer(&ft->tl); - init_timer(&ft->tl); ft->event = event; ft->arg = arg; ft->tl.expires = jiffies + (millisec * HZ) / 1000; diff --git a/drivers/isdn/hisax/hfc4s8s_l1.c b/drivers/isdn/hisax/hfc4s8s_l1.c index 9090cc1e1f29..e9bb8fb67ad0 100644 --- a/drivers/isdn/hisax/hfc4s8s_l1.c +++ b/drivers/isdn/hisax/hfc4s8s_l1.c @@ -591,8 +591,9 @@ bch_l2l1(struct hisax_if *ifc, int pr, void *arg) /* layer 1 timer function */ /**************************/ static void -hfc_l1_timer(struct hfc4s8s_l1 *l1) +hfc_l1_timer(struct timer_list *t) { + struct hfc4s8s_l1 *l1 = from_timer(l1, t, l1_timer); u_long flags; if (!l1->enabled) @@ -1396,8 +1397,7 @@ setup_instance(hfc4s8s_hw *hw) l1p = hw->l1 + i; spin_lock_init(&l1p->lock); l1p->hw = hw; - setup_timer(&l1p->l1_timer, (void *)hfc_l1_timer, - (long)(l1p)); + timer_setup(&l1p->l1_timer, hfc_l1_timer, 0); l1p->st_num = i; skb_queue_head_init(&l1p->d_tx_queue); l1p->d_if.ifc.priv = hw->l1 + i; diff --git a/drivers/isdn/hisax/hfc_2bds0.c b/drivers/isdn/hisax/hfc_2bds0.c index ad8597a1a07e..86b82172e992 100644 --- a/drivers/isdn/hisax/hfc_2bds0.c +++ b/drivers/isdn/hisax/hfc_2bds0.c @@ -1014,7 +1014,7 @@ setstack_hfcd(struct PStack *st, struct IsdnCardState *cs) } static void -hfc_dbusy_timer(struct IsdnCardState *cs) +hfc_dbusy_timer(struct timer_list *t) { } @@ -1073,6 +1073,6 @@ set_cs_func(struct IsdnCardState *cs) cs->writeisacfifo = &dummyf; cs->BC_Read_Reg = &ReadReg; cs->BC_Write_Reg = &WriteReg; - setup_timer(&cs->dbusytimer, (void *)hfc_dbusy_timer, (long)cs); + timer_setup(&cs->dbusytimer, hfc_dbusy_timer, 0); INIT_WORK(&cs->tqueue, hfcd_bh); } diff --git a/drivers/isdn/hisax/hfc_pci.c b/drivers/isdn/hisax/hfc_pci.c index f9ca35cc32b1..8e5b03161b2f 100644 --- a/drivers/isdn/hisax/hfc_pci.c +++ b/drivers/isdn/hisax/hfc_pci.c @@ -165,8 +165,9 @@ reset_hfcpci(struct IsdnCardState *cs) /* Timer function called when kernel timer expires */ /***************************************************/ static void -hfcpci_Timer(struct IsdnCardState *cs) +hfcpci_Timer(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, hw.hfcpci.timer); cs->hw.hfcpci.timer.expires = jiffies + 75; /* WD RESET */ /* WriteReg(cs, HFCD_DATA, HFCD_CTMT, cs->hw.hfcpci.ctmt | 0x80); @@ -1095,7 +1096,7 @@ hfcpci_interrupt(int intno, void *dev_id) /* timer callback for D-chan busy resolution. Currently no function */ /********************************************************************/ static void -hfcpci_dbusy_timer(struct IsdnCardState *cs) +hfcpci_dbusy_timer(struct timer_list *t) { } @@ -1582,7 +1583,7 @@ inithfcpci(struct IsdnCardState *cs) cs->bcs[1].BC_SetStack = setstack_2b; cs->bcs[0].BC_Close = close_hfcpci; cs->bcs[1].BC_Close = close_hfcpci; - setup_timer(&cs->dbusytimer, (void *)hfcpci_dbusy_timer, (long)cs); + timer_setup(&cs->dbusytimer, hfcpci_dbusy_timer, 0); mode_hfcpci(cs->bcs, 0, 0); mode_hfcpci(cs->bcs + 1, 0, 1); } @@ -1744,7 +1745,7 @@ setup_hfcpci(struct IsdnCard *card) cs->BC_Write_Reg = NULL; cs->irq_func = &hfcpci_interrupt; cs->irq_flags |= IRQF_SHARED; - setup_timer(&cs->hw.hfcpci.timer, (void *)hfcpci_Timer, (long)cs); + timer_setup(&cs->hw.hfcpci.timer, hfcpci_Timer, 0); cs->cardmsg = &hfcpci_card_msg; cs->auxcmd = &hfcpci_auxcmd; diff --git a/drivers/isdn/hisax/hfc_sx.c b/drivers/isdn/hisax/hfc_sx.c index 3aef8e1a90e4..d925f579bc80 100644 --- a/drivers/isdn/hisax/hfc_sx.c +++ b/drivers/isdn/hisax/hfc_sx.c @@ -418,8 +418,9 @@ reset_hfcsx(struct IsdnCardState *cs) /* Timer function called when kernel timer expires */ /***************************************************/ static void -hfcsx_Timer(struct IsdnCardState *cs) +hfcsx_Timer(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, hw.hfcsx.timer); cs->hw.hfcsx.timer.expires = jiffies + 75; /* WD RESET */ /* WriteReg(cs, HFCD_DATA, HFCD_CTMT, cs->hw.hfcsx.ctmt | 0x80); @@ -860,7 +861,7 @@ hfcsx_interrupt(int intno, void *dev_id) /* timer callback for D-chan busy resolution. Currently no function */ /********************************************************************/ static void -hfcsx_dbusy_timer(struct IsdnCardState *cs) +hfcsx_dbusy_timer(struct timer_list *t) { } @@ -1495,7 +1496,7 @@ int setup_hfcsx(struct IsdnCard *card) } else return (0); /* no valid card type */ - setup_timer(&cs->dbusytimer, (void *)hfcsx_dbusy_timer, (long)cs); + timer_setup(&cs->dbusytimer, hfcsx_dbusy_timer, 0); INIT_WORK(&cs->tqueue, hfcsx_bh); cs->readisac = NULL; cs->writeisac = NULL; @@ -1507,7 +1508,7 @@ int setup_hfcsx(struct IsdnCard *card) cs->hw.hfcsx.b_fifo_size = 0; /* fifo size still unknown */ cs->hw.hfcsx.cirm = ccd_sp_irqtab[cs->irq & 0xF]; /* RAM not evaluated */ - setup_timer(&cs->hw.hfcsx.timer, (void *)hfcsx_Timer, (long)cs); + timer_setup(&cs->hw.hfcsx.timer, hfcsx_Timer, 0); reset_hfcsx(cs); cs->cardmsg = &hfcsx_card_msg; diff --git a/drivers/isdn/hisax/hfc_usb.c b/drivers/isdn/hisax/hfc_usb.c index e8212185d386..97ecb3073045 100644 --- a/drivers/isdn/hisax/hfc_usb.c +++ b/drivers/isdn/hisax/hfc_usb.c @@ -343,8 +343,9 @@ handle_led(hfcusb_data *hfc, int event) /* ISDN l1 timer T3 expires */ static void -l1_timer_expire_t3(hfcusb_data *hfc) +l1_timer_expire_t3(struct timer_list *t) { + hfcusb_data *hfc = from_timer(hfc, t, t3_timer); hfc->d_if.ifc.l1l2(&hfc->d_if.ifc, PH_DEACTIVATE | INDICATION, NULL); @@ -360,8 +361,9 @@ l1_timer_expire_t3(hfcusb_data *hfc) /* ISDN l1 timer T4 expires */ static void -l1_timer_expire_t4(hfcusb_data *hfc) +l1_timer_expire_t4(struct timer_list *t) { + hfcusb_data *hfc = from_timer(hfc, t, t4_timer); hfc->d_if.ifc.l1l2(&hfc->d_if.ifc, PH_DEACTIVATE | INDICATION, NULL); @@ -1165,10 +1167,10 @@ hfc_usb_init(hfcusb_data *hfc) hfc->old_led_state = 0; /* init the t3 timer */ - setup_timer(&hfc->t3_timer, (void *)l1_timer_expire_t3, (long)hfc); + timer_setup(&hfc->t3_timer, l1_timer_expire_t3, 0); /* init the t4 timer */ - setup_timer(&hfc->t4_timer, (void *)l1_timer_expire_t4, (long)hfc); + timer_setup(&hfc->t4_timer, l1_timer_expire_t4, 0); /* init the background machinery for control requests */ hfc->ctrl_read.bRequestType = 0xc0; diff --git a/drivers/isdn/hisax/hfcscard.c b/drivers/isdn/hisax/hfcscard.c index 467287096918..380bbeda9c74 100644 --- a/drivers/isdn/hisax/hfcscard.c +++ b/drivers/isdn/hisax/hfcscard.c @@ -41,8 +41,9 @@ hfcs_interrupt(int intno, void *dev_id) } static void -hfcs_Timer(struct IsdnCardState *cs) +hfcs_Timer(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, hw.hfcD.timer); cs->hw.hfcD.timer.expires = jiffies + 75; /* WD RESET */ /* WriteReg(cs, HFCD_DATA, HFCD_CTMT, cs->hw.hfcD.ctmt | 0x80); @@ -253,7 +254,7 @@ int setup_hfcs(struct IsdnCard *card) outb(0x57, cs->hw.hfcD.addr | 1); } set_cs_func(cs); - setup_timer(&cs->hw.hfcD.timer, (void *)hfcs_Timer, (long)cs); + timer_setup(&cs->hw.hfcD.timer, hfcs_Timer, 0); cs->cardmsg = &hfcs_card_msg; cs->irq_func = &hfcs_interrupt; return (1); diff --git a/drivers/isdn/hisax/icc.c b/drivers/isdn/hisax/icc.c index 8d1804572b32..831dd1bb81ef 100644 --- a/drivers/isdn/hisax/icc.c +++ b/drivers/isdn/hisax/icc.c @@ -168,7 +168,6 @@ icc_fill_fifo(struct IsdnCardState *cs) debugl1(cs, "icc_fill_fifo dbusytimer running"); del_timer(&cs->dbusytimer); } - init_timer(&cs->dbusytimer); cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ)/1000); add_timer(&cs->dbusytimer); if (cs->debug & L1_DEB_ISAC_FIFO) { @@ -580,8 +579,9 @@ DC_Close_icc(struct IsdnCardState *cs) { } static void -dbusy_timer_handler(struct IsdnCardState *cs) +dbusy_timer_handler(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, dbusytimer); struct PStack *stptr; int rbch, star; @@ -676,5 +676,5 @@ clear_pending_icc_ints(struct IsdnCardState *cs) void setup_icc(struct IsdnCardState *cs) { INIT_WORK(&cs->tqueue, icc_bh); - setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs); + timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0); } diff --git a/drivers/isdn/hisax/ipacx.c b/drivers/isdn/hisax/ipacx.c index c426b4fea28a..c7086c1534bd 100644 --- a/drivers/isdn/hisax/ipacx.c +++ b/drivers/isdn/hisax/ipacx.c @@ -35,7 +35,7 @@ static void ph_command(struct IsdnCardState *cs, unsigned int command); static inline void cic_int(struct IsdnCardState *cs); static void dch_l2l1(struct PStack *st, int pr, void *arg); -static void dbusy_timer_handler(struct IsdnCardState *cs); +static void dbusy_timer_handler(struct timer_list *t); static void dch_empty_fifo(struct IsdnCardState *cs, int count); static void dch_fill_fifo(struct IsdnCardState *cs); static inline void dch_int(struct IsdnCardState *cs); @@ -198,8 +198,9 @@ dch_l2l1(struct PStack *st, int pr, void *arg) //---------------------------------------------------------- //---------------------------------------------------------- static void -dbusy_timer_handler(struct IsdnCardState *cs) +dbusy_timer_handler(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, dbusytimer); struct PStack *st; int rbchd, stard; @@ -298,7 +299,6 @@ dch_fill_fifo(struct IsdnCardState *cs) debugl1(cs, "dch_fill_fifo dbusytimer running"); del_timer(&cs->dbusytimer); } - init_timer(&cs->dbusytimer); cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ)/1000); add_timer(&cs->dbusytimer); @@ -424,7 +424,7 @@ dch_init(struct IsdnCardState *cs) cs->setstack_d = dch_setstack; - setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs); + timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0); cs->writeisac(cs, IPACX_TR_CONF0, 0x00); // clear LDD cs->writeisac(cs, IPACX_TR_CONF2, 0x00); // enable transmitter diff --git a/drivers/isdn/hisax/isac.c b/drivers/isdn/hisax/isac.c index ea965f29a555..bd40e0671ded 100644 --- a/drivers/isdn/hisax/isac.c +++ b/drivers/isdn/hisax/isac.c @@ -171,7 +171,6 @@ isac_fill_fifo(struct IsdnCardState *cs) debugl1(cs, "isac_fill_fifo dbusytimer running"); del_timer(&cs->dbusytimer); } - init_timer(&cs->dbusytimer); cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ)/1000); add_timer(&cs->dbusytimer); if (cs->debug & L1_DEB_ISAC_FIFO) { @@ -584,8 +583,9 @@ DC_Close_isac(struct IsdnCardState *cs) } static void -dbusy_timer_handler(struct IsdnCardState *cs) +dbusy_timer_handler(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, dbusytimer); struct PStack *stptr; int rbch, star; @@ -677,5 +677,5 @@ void clear_pending_isac_ints(struct IsdnCardState *cs) void setup_isac(struct IsdnCardState *cs) { INIT_WORK(&cs->tqueue, isac_bh); - setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs); + timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0); } diff --git a/drivers/isdn/hisax/isar.c b/drivers/isdn/hisax/isar.c index 98b4b67ea337..d01ff116797b 100644 --- a/drivers/isdn/hisax/isar.c +++ b/drivers/isdn/hisax/isar.c @@ -1267,7 +1267,8 @@ isar_int_main(struct IsdnCardState *cs) } static void -ftimer_handler(struct BCState *bcs) { +ftimer_handler(struct timer_list *t) { + struct BCState *bcs = from_timer(bcs, t, hw.isar.ftimer); if (bcs->cs->debug) debugl1(bcs->cs, "ftimer flags %04lx", bcs->Flag); @@ -1902,8 +1903,6 @@ void initisar(struct IsdnCardState *cs) cs->bcs[1].BC_SetStack = setstack_isar; cs->bcs[0].BC_Close = close_isarstate; cs->bcs[1].BC_Close = close_isarstate; - setup_timer(&cs->bcs[0].hw.isar.ftimer, (void *)ftimer_handler, - (long)&cs->bcs[0]); - setup_timer(&cs->bcs[1].hw.isar.ftimer, (void *)ftimer_handler, - (long)&cs->bcs[1]); + timer_setup(&cs->bcs[0].hw.isar.ftimer, ftimer_handler, 0); + timer_setup(&cs->bcs[1].hw.isar.ftimer, ftimer_handler, 0); } diff --git a/drivers/isdn/hisax/isdnl3.c b/drivers/isdn/hisax/isdnl3.c index 569ce52c567b..bb3f9ec62749 100644 --- a/drivers/isdn/hisax/isdnl3.c +++ b/drivers/isdn/hisax/isdnl3.c @@ -160,8 +160,9 @@ newl3state(struct l3_process *pc, int state) } static void -L3ExpireTimer(struct L3Timer *t) +L3ExpireTimer(struct timer_list *timer) { + struct L3Timer *t = from_timer(t, timer, tl); t->pc->st->lli.l4l3(t->pc->st, t->event, t->pc); } @@ -169,7 +170,7 @@ void L3InitTimer(struct l3_process *pc, struct L3Timer *t) { t->pc = pc; - setup_timer(&t->tl, (void *)L3ExpireTimer, (long)t); + timer_setup(&t->tl, L3ExpireTimer, 0); } void @@ -186,7 +187,6 @@ L3AddTimer(struct L3Timer *t, printk(KERN_WARNING "L3AddTimer: timer already active!\n"); return -1; } - init_timer(&t->tl); t->event = event; t->tl.expires = jiffies + (millisec * HZ) / 1000; add_timer(&t->tl); diff --git a/drivers/isdn/hisax/saphir.c b/drivers/isdn/hisax/saphir.c index 6b2d0eccdd56..db906cb37a3f 100644 --- a/drivers/isdn/hisax/saphir.c +++ b/drivers/isdn/hisax/saphir.c @@ -159,8 +159,9 @@ Start_ISAC: } static void -SaphirWatchDog(struct IsdnCardState *cs) +SaphirWatchDog(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, hw.saphir.timer); u_long flags; spin_lock_irqsave(&cs->lock, flags); @@ -268,9 +269,7 @@ int setup_saphir(struct IsdnCard *card) cs->irq, cs->hw.saphir.cfg_reg); setup_isac(cs); - cs->hw.saphir.timer.function = (void *) SaphirWatchDog; - cs->hw.saphir.timer.data = (long) cs; - init_timer(&cs->hw.saphir.timer); + timer_setup(&cs->hw.saphir.timer, SaphirWatchDog, 0); cs->hw.saphir.timer.expires = jiffies + 4 * HZ; add_timer(&cs->hw.saphir.timer); if (saphir_reset(cs)) { diff --git a/drivers/isdn/hisax/teleint.c b/drivers/isdn/hisax/teleint.c index 950399f066ef..247aa33076b1 100644 --- a/drivers/isdn/hisax/teleint.c +++ b/drivers/isdn/hisax/teleint.c @@ -179,8 +179,9 @@ Start_ISAC: } static void -TeleInt_Timer(struct IsdnCardState *cs) +TeleInt_Timer(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, hw.hfc.timer); int stat = 0; u_long flags; @@ -278,7 +279,7 @@ int setup_TeleInt(struct IsdnCard *card) cs->bcs[0].hw.hfc.send = NULL; cs->bcs[1].hw.hfc.send = NULL; cs->hw.hfc.fifosize = 7 * 1024 + 512; - setup_timer(&cs->hw.hfc.timer, (void *)TeleInt_Timer, (long)cs); + timer_setup(&cs->hw.hfc.timer, TeleInt_Timer, 0); if (!request_region(cs->hw.hfc.addr, 2, "TeleInt isdn")) { printk(KERN_WARNING "HiSax: TeleInt config port %x-%x already in use\n", diff --git a/drivers/isdn/hisax/w6692.c b/drivers/isdn/hisax/w6692.c index 6f6733b7c1e4..c4be1644f5bb 100644 --- a/drivers/isdn/hisax/w6692.c +++ b/drivers/isdn/hisax/w6692.c @@ -188,7 +188,6 @@ W6692_fill_fifo(struct IsdnCardState *cs) debugl1(cs, "W6692_fill_fifo dbusytimer running"); del_timer(&cs->dbusytimer); } - init_timer(&cs->dbusytimer); cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ) / 1000); add_timer(&cs->dbusytimer); if (cs->debug & L1_DEB_ISAC_FIFO) { @@ -684,8 +683,9 @@ DC_Close_W6692(struct IsdnCardState *cs) } static void -dbusy_timer_handler(struct IsdnCardState *cs) +dbusy_timer_handler(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, dbusytimer); struct PStack *stptr; int rbch, star; u_long flags; @@ -904,8 +904,7 @@ static void initW6692(struct IsdnCardState *cs, int part) if (part & 1) { cs->setstack_d = setstack_W6692; cs->DC_Close = DC_Close_W6692; - setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, - (long)cs); + timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0); resetW6692(cs); ph_command(cs, W_L1CMD_RST); cs->dc.w6692.ph_state = W_L1CMD_RST; diff --git a/drivers/isdn/isdnloop/isdnloop.c b/drivers/isdn/isdnloop/isdnloop.c index e97232646ba1..a4597e96c916 100644 --- a/drivers/isdn/isdnloop/isdnloop.c +++ b/drivers/isdn/isdnloop/isdnloop.c @@ -90,9 +90,9 @@ isdnloop_bchan_send(isdnloop_card *card, int ch) * data = pointer to card struct, set by kernel timer.data */ static void -isdnloop_pollbchan(unsigned long data) +isdnloop_pollbchan(struct timer_list *t) { - isdnloop_card *card = (isdnloop_card *) data; + isdnloop_card *card = from_timer(card, t, rb_timer); unsigned long flags; if (card->flags & ISDNLOOP_FLAGS_B1ACTIVE) @@ -305,9 +305,9 @@ isdnloop_putmsg(isdnloop_card *card, unsigned char c) * data = pointer to card struct */ static void -isdnloop_polldchan(unsigned long data) +isdnloop_polldchan(struct timer_list *t) { - isdnloop_card *card = (isdnloop_card *) data; + isdnloop_card *card = from_timer(card, t, st_timer); struct sk_buff *skb; int avail; int left; @@ -373,8 +373,6 @@ isdnloop_polldchan(unsigned long data) card->flags |= ISDNLOOP_FLAGS_RBTIMER; spin_lock_irqsave(&card->isdnloop_lock, flags); del_timer(&card->rb_timer); - card->rb_timer.function = isdnloop_pollbchan; - card->rb_timer.data = (unsigned long) card; card->rb_timer.expires = jiffies + ISDNLOOP_TIMER_BCREAD; add_timer(&card->rb_timer); spin_unlock_irqrestore(&card->isdnloop_lock, flags); @@ -588,9 +586,10 @@ isdnloop_atimeout(isdnloop_card *card, int ch) * Wrapper for isdnloop_atimeout(). */ static void -isdnloop_atimeout0(unsigned long data) +isdnloop_atimeout0(struct timer_list *t) { - isdnloop_card *card = (isdnloop_card *) data; + isdnloop_card *card = from_timer(card, t, c_timer[0]); + isdnloop_atimeout(card, 0); } @@ -598,9 +597,10 @@ isdnloop_atimeout0(unsigned long data) * Wrapper for isdnloop_atimeout(). */ static void -isdnloop_atimeout1(unsigned long data) +isdnloop_atimeout1(struct timer_list *t) { - isdnloop_card *card = (isdnloop_card *) data; + isdnloop_card *card = from_timer(card, t, c_timer[1]); + isdnloop_atimeout(card, 1); } @@ -617,13 +617,9 @@ isdnloop_start_ctimer(isdnloop_card *card, int ch) unsigned long flags; spin_lock_irqsave(&card->isdnloop_lock, flags); - init_timer(&card->c_timer[ch]); + timer_setup(&card->c_timer[ch], ch ? isdnloop_atimeout1 + : isdnloop_atimeout0, 0); card->c_timer[ch].expires = jiffies + ISDNLOOP_TIMER_ALERTWAIT; - if (ch) - card->c_timer[ch].function = isdnloop_atimeout1; - else - card->c_timer[ch].function = isdnloop_atimeout0; - card->c_timer[ch].data = (unsigned long) card; add_timer(&card->c_timer[ch]); spin_unlock_irqrestore(&card->isdnloop_lock, flags); } @@ -1113,10 +1109,9 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp) sdef.ptype); return -EINVAL; } - init_timer(&card->st_timer); + timer_setup(&card->rb_timer, isdnloop_pollbchan, 0); + timer_setup(&card->st_timer, isdnloop_polldchan, 0); card->st_timer.expires = jiffies + ISDNLOOP_TIMER_DCREAD; - card->st_timer.function = isdnloop_polldchan; - card->st_timer.data = (unsigned long) card; add_timer(&card->st_timer); card->flags |= ISDNLOOP_FLAGS_RUNNING; spin_unlock_irqrestore(&card->isdnloop_lock, flags); diff --git a/drivers/isdn/mISDN/dsp.h b/drivers/isdn/mISDN/dsp.h index fc1733a08845..fa09d511a8ed 100644 --- a/drivers/isdn/mISDN/dsp.h +++ b/drivers/isdn/mISDN/dsp.h @@ -259,7 +259,7 @@ extern u8 *dsp_dtmf_goertzel_decode(struct dsp *dsp, u8 *data, int len, extern int dsp_tone(struct dsp *dsp, int tone); extern void dsp_tone_copy(struct dsp *dsp, u8 *data, int len); -extern void dsp_tone_timeout(void *arg); +extern void dsp_tone_timeout(struct timer_list *t); extern void dsp_bf_encrypt(struct dsp *dsp, u8 *data, int len); extern void dsp_bf_decrypt(struct dsp *dsp, u8 *data, int len); diff --git a/drivers/isdn/mISDN/dsp_core.c b/drivers/isdn/mISDN/dsp_core.c index 880e9d367a39..cd036e87335a 100644 --- a/drivers/isdn/mISDN/dsp_core.c +++ b/drivers/isdn/mISDN/dsp_core.c @@ -1092,7 +1092,7 @@ dspcreate(struct channel_req *crq) ndsp->pcm_bank_tx = -1; ndsp->hfc_conf = -1; /* current conference number */ /* set tone timer */ - setup_timer(&ndsp->tone.tl, (void *)dsp_tone_timeout, (long)ndsp); + timer_setup(&ndsp->tone.tl, dsp_tone_timeout, 0); if (dtmfthreshold < 20 || dtmfthreshold > 500) dtmfthreshold = 200; @@ -1202,9 +1202,7 @@ static int __init dsp_init(void) } /* set sample timer */ - dsp_spl_tl.function = (void *)dsp_cmx_send; - dsp_spl_tl.data = 0; - init_timer(&dsp_spl_tl); + timer_setup(&dsp_spl_tl, (void *)dsp_cmx_send, 0); dsp_spl_tl.expires = jiffies + dsp_tics; dsp_spl_jiffies = dsp_spl_tl.expires; add_timer(&dsp_spl_tl); diff --git a/drivers/isdn/mISDN/dsp_tones.c b/drivers/isdn/mISDN/dsp_tones.c index 057e0d6a369b..8389e2105cdc 100644 --- a/drivers/isdn/mISDN/dsp_tones.c +++ b/drivers/isdn/mISDN/dsp_tones.c @@ -457,9 +457,9 @@ dsp_tone_hw_message(struct dsp *dsp, u8 *sample, int len) * timer expires * *****************/ void -dsp_tone_timeout(void *arg) +dsp_tone_timeout(struct timer_list *t) { - struct dsp *dsp = arg; + struct dsp *dsp = from_timer(dsp, t, tone.tl); struct dsp_tone *tone = &dsp->tone; struct pattern *pat = (struct pattern *)tone->pattern; int index = tone->index; @@ -478,7 +478,6 @@ dsp_tone_timeout(void *arg) else dsp_tone_hw_message(dsp, pat->data[index], *(pat->siz[index])); /* set timer */ - init_timer(&tone->tl); tone->tl.expires = jiffies + (pat->seq[index] * HZ) / 8000; add_timer(&tone->tl); } @@ -541,7 +540,6 @@ dsp_tone(struct dsp *dsp, int tone) /* set timer */ if (timer_pending(&tonet->tl)) del_timer(&tonet->tl); - init_timer(&tonet->tl); tonet->tl.expires = jiffies + (pat->seq[0] * HZ) / 8000; add_timer(&tonet->tl); } else { diff --git a/drivers/isdn/mISDN/fsm.c b/drivers/isdn/mISDN/fsm.c index 92e6570b1143..cabcb906e0b5 100644 --- a/drivers/isdn/mISDN/fsm.c +++ b/drivers/isdn/mISDN/fsm.c @@ -100,8 +100,9 @@ mISDN_FsmChangeState(struct FsmInst *fi, int newstate) EXPORT_SYMBOL(mISDN_FsmChangeState); static void -FsmExpireTimer(struct FsmTimer *ft) +FsmExpireTimer(struct timer_list *t) { + struct FsmTimer *ft = from_timer(ft, t, tl); #if FSM_TIMER_DEBUG if (ft->fi->debug) ft->fi->printdebug(ft->fi, "FsmExpireTimer %lx", (long) ft); @@ -117,7 +118,7 @@ mISDN_FsmInitTimer(struct FsmInst *fi, struct FsmTimer *ft) if (ft->fi->debug) ft->fi->printdebug(ft->fi, "mISDN_FsmInitTimer %lx", (long) ft); #endif - setup_timer(&ft->tl, (void *)FsmExpireTimer, (long)ft); + timer_setup(&ft->tl, FsmExpireTimer, 0); } EXPORT_SYMBOL(mISDN_FsmInitTimer); @@ -153,7 +154,6 @@ mISDN_FsmAddTimer(struct FsmTimer *ft, } return -1; } - init_timer(&ft->tl); ft->event = event; ft->arg = arg; ft->tl.expires = jiffies + (millisec * HZ) / 1000; @@ -175,7 +175,6 @@ mISDN_FsmRestartTimer(struct FsmTimer *ft, if (timer_pending(&ft->tl)) del_timer(&ft->tl); - init_timer(&ft->tl); ft->event = event; ft->arg = arg; ft->tl.expires = jiffies + (millisec * HZ) / 1000; diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c index 6be2041248d3..b5d590e378ac 100644 --- a/drivers/isdn/mISDN/l1oip_core.c +++ b/drivers/isdn/mISDN/l1oip_core.c @@ -842,17 +842,18 @@ l1oip_send_bh(struct work_struct *work) * timer stuff */ static void -l1oip_keepalive(void *data) +l1oip_keepalive(struct timer_list *t) { - struct l1oip *hc = (struct l1oip *)data; + struct l1oip *hc = from_timer(hc, t, keep_tl); schedule_work(&hc->workq); } static void -l1oip_timeout(void *data) +l1oip_timeout(struct timer_list *t) { - struct l1oip *hc = (struct l1oip *)data; + struct l1oip *hc = from_timer(hc, t, + timeout_tl); struct dchannel *dch = hc->chan[hc->d_idx].dch; if (debug & DEBUG_L1OIP_MSG) @@ -1437,13 +1438,11 @@ init_card(struct l1oip *hc, int pri, int bundle) if (ret) return ret; - hc->keep_tl.function = (void *)l1oip_keepalive; - hc->keep_tl.data = (ulong)hc; - init_timer(&hc->keep_tl); + timer_setup(&hc->keep_tl, l1oip_keepalive, 0); hc->keep_tl.expires = jiffies + 2 * HZ; /* two seconds first time */ add_timer(&hc->keep_tl); - setup_timer(&hc->timeout_tl, (void *)l1oip_timeout, (ulong)hc); + timer_setup(&hc->timeout_tl, l1oip_timeout, 0); hc->timeout_on = 0; /* state that we have timer off */ return 0; diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c index b1e135fc1fb5..c50a34340f67 100644 --- a/drivers/isdn/mISDN/timerdev.c +++ b/drivers/isdn/mISDN/timerdev.c @@ -162,9 +162,9 @@ mISDN_poll(struct file *filep, poll_table *wait) } static void -dev_expire_timer(unsigned long data) +dev_expire_timer(struct timer_list *t) { - struct mISDNtimer *timer = (void *)data; + struct mISDNtimer *timer = from_timer(timer, t, tl); u_long flags; spin_lock_irqsave(&timer->dev->lock, flags); @@ -189,7 +189,7 @@ misdn_add_timer(struct mISDNtimerdev *dev, int timeout) if (!timer) return -ENOMEM; timer->dev = dev; - setup_timer(&timer->tl, dev_expire_timer, (long)timer); + timer_setup(&timer->tl, dev_expire_timer, 0); spin_lock_irq(&dev->lock); id = timer->id = dev->next_id++; if (dev->next_id < 0) diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c index 7d5286b05036..1841d0359bac 100644 --- a/drivers/md/bcache/closure.c +++ b/drivers/md/bcache/closure.c @@ -64,7 +64,7 @@ EXPORT_SYMBOL(closure_put); void __closure_wake_up(struct closure_waitlist *wait_list) { struct llist_node *list; - struct closure *cl; + struct closure *cl, *t; struct llist_node *reverse = NULL; list = llist_del_all(&wait_list->list); @@ -73,7 +73,7 @@ void __closure_wake_up(struct closure_waitlist *wait_list) reverse = llist_reverse_order(list); /* Then do the wakeups */ - llist_for_each_entry(cl, reverse, list) { + llist_for_each_entry_safe(cl, t, reverse, list) { closure_set_waiting(cl, 0); closure_sub(cl, CLOSURE_WAITING + 1); } diff --git a/drivers/misc/cxl/cxllib.c b/drivers/misc/cxl/cxllib.c index 5dba23ca2e5f..dc9bc1807fdf 100644 --- a/drivers/misc/cxl/cxllib.c +++ b/drivers/misc/cxl/cxllib.c @@ -219,8 +219,17 @@ int cxllib_handle_fault(struct mm_struct *mm, u64 addr, u64 size, u64 flags) down_read(&mm->mmap_sem); - for (dar = addr; dar < addr + size; dar += page_size) { - if (!vma || dar < vma->vm_start || dar > vma->vm_end) { + vma = find_vma(mm, addr); + if (!vma) { + pr_err("Can't find vma for addr %016llx\n", addr); + rc = -EFAULT; + goto out; + } + /* get the size of the pages allocated */ + page_size = vma_kernel_pagesize(vma); + + for (dar = (addr & ~(page_size - 1)); dar < (addr + size); dar += page_size) { + if (dar < vma->vm_start || dar >= vma->vm_end) { vma = find_vma(mm, addr); if (!vma) { pr_err("Can't find vma for addr %016llx\n", addr); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 29fc1e662891..2ad7b5c69156 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1634,8 +1634,6 @@ static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq, } mqrq->areq.mrq = &brq->mrq; - - mmc_queue_bounce_pre(mqrq); } static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, @@ -1829,7 +1827,6 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req) brq = &mq_rq->brq; old_req = mmc_queue_req_to_req(mq_rq); type = rq_data_dir(old_req) == READ ? MMC_BLK_READ : MMC_BLK_WRITE; - mmc_queue_bounce_post(mq_rq); switch (status) { case MMC_BLK_SUCCESS: diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index a7eb623f8daa..36217ad5e9b1 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1286,6 +1286,23 @@ out_err: return err; } +static void mmc_select_driver_type(struct mmc_card *card) +{ + int card_drv_type, drive_strength, drv_type; + + card_drv_type = card->ext_csd.raw_driver_strength | + mmc_driver_type_mask(0); + + drive_strength = mmc_select_drive_strength(card, + card->ext_csd.hs200_max_dtr, + card_drv_type, &drv_type); + + card->drive_strength = drive_strength; + + if (drv_type) + mmc_set_driver_type(card->host, drv_type); +} + static int mmc_select_hs400es(struct mmc_card *card) { struct mmc_host *host = card->host; @@ -1341,6 +1358,8 @@ static int mmc_select_hs400es(struct mmc_card *card) goto out_err; } + mmc_select_driver_type(card); + /* Switch card to HS400 */ val = EXT_CSD_TIMING_HS400 | card->drive_strength << EXT_CSD_DRV_STR_SHIFT; @@ -1374,23 +1393,6 @@ out_err: return err; } -static void mmc_select_driver_type(struct mmc_card *card) -{ - int card_drv_type, drive_strength, drv_type; - - card_drv_type = card->ext_csd.raw_driver_strength | - mmc_driver_type_mask(0); - - drive_strength = mmc_select_drive_strength(card, - card->ext_csd.hs200_max_dtr, - card_drv_type, &drv_type); - - card->drive_strength = drive_strength; - - if (drv_type) - mmc_set_driver_type(card->host, drv_type); -} - /* * For device supporting HS200 mode, the following sequence * should be done before executing the tuning process. diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 74c663b1c0a7..0a4e77a5ba33 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -23,8 +23,6 @@ #include "core.h" #include "card.h" -#define MMC_QUEUE_BOUNCESZ 65536 - /* * Prepare a MMC request. This just filters out odd stuff. */ @@ -150,26 +148,6 @@ static void mmc_queue_setup_discard(struct request_queue *q, queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, q); } -static unsigned int mmc_queue_calc_bouncesz(struct mmc_host *host) -{ - unsigned int bouncesz = MMC_QUEUE_BOUNCESZ; - - if (host->max_segs != 1 || (host->caps & MMC_CAP_NO_BOUNCE_BUFF)) - return 0; - - if (bouncesz > host->max_req_size) - bouncesz = host->max_req_size; - if (bouncesz > host->max_seg_size) - bouncesz = host->max_seg_size; - if (bouncesz > host->max_blk_count * 512) - bouncesz = host->max_blk_count * 512; - - if (bouncesz <= 512) - return 0; - - return bouncesz; -} - /** * mmc_init_request() - initialize the MMC-specific per-request data * @q: the request queue @@ -184,26 +162,9 @@ static int mmc_init_request(struct request_queue *q, struct request *req, struct mmc_card *card = mq->card; struct mmc_host *host = card->host; - if (card->bouncesz) { - mq_rq->bounce_buf = kmalloc(card->bouncesz, gfp); - if (!mq_rq->bounce_buf) - return -ENOMEM; - if (card->bouncesz > 512) { - mq_rq->sg = mmc_alloc_sg(1, gfp); - if (!mq_rq->sg) - return -ENOMEM; - mq_rq->bounce_sg = mmc_alloc_sg(card->bouncesz / 512, - gfp); - if (!mq_rq->bounce_sg) - return -ENOMEM; - } - } else { - mq_rq->bounce_buf = NULL; - mq_rq->bounce_sg = NULL; - mq_rq->sg = mmc_alloc_sg(host->max_segs, gfp); - if (!mq_rq->sg) - return -ENOMEM; - } + mq_rq->sg = mmc_alloc_sg(host->max_segs, gfp); + if (!mq_rq->sg) + return -ENOMEM; return 0; } @@ -212,13 +173,6 @@ static void mmc_exit_request(struct request_queue *q, struct request *req) { struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req); - /* It is OK to kfree(NULL) so this will be smooth */ - kfree(mq_rq->bounce_sg); - mq_rq->bounce_sg = NULL; - - kfree(mq_rq->bounce_buf); - mq_rq->bounce_buf = NULL; - kfree(mq_rq->sg); mq_rq->sg = NULL; } @@ -242,12 +196,6 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask) limit = (u64)dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT; - /* - * mmc_init_request() depends on card->bouncesz so it must be calculated - * before blk_init_allocated_queue() starts allocating requests. - */ - card->bouncesz = mmc_queue_calc_bouncesz(host); - mq->card = card; mq->queue = blk_alloc_queue(GFP_KERNEL); if (!mq->queue) @@ -271,17 +219,11 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, if (mmc_can_erase(card)) mmc_queue_setup_discard(mq->queue, card); - if (card->bouncesz) { - blk_queue_max_hw_sectors(mq->queue, card->bouncesz / 512); - blk_queue_max_segments(mq->queue, card->bouncesz / 512); - blk_queue_max_segment_size(mq->queue, card->bouncesz); - } else { - blk_queue_bounce_limit(mq->queue, limit); - blk_queue_max_hw_sectors(mq->queue, - min(host->max_blk_count, host->max_req_size / 512)); - blk_queue_max_segments(mq->queue, host->max_segs); - blk_queue_max_segment_size(mq->queue, host->max_seg_size); - } + blk_queue_bounce_limit(mq->queue, limit); + blk_queue_max_hw_sectors(mq->queue, + min(host->max_blk_count, host->max_req_size / 512)); + blk_queue_max_segments(mq->queue, host->max_segs); + blk_queue_max_segment_size(mq->queue, host->max_seg_size); sema_init(&mq->thread_sem, 1); @@ -370,56 +312,7 @@ void mmc_queue_resume(struct mmc_queue *mq) */ unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq) { - unsigned int sg_len; - size_t buflen; - struct scatterlist *sg; struct request *req = mmc_queue_req_to_req(mqrq); - int i; - - if (!mqrq->bounce_buf) - return blk_rq_map_sg(mq->queue, req, mqrq->sg); - - sg_len = blk_rq_map_sg(mq->queue, req, mqrq->bounce_sg); - - mqrq->bounce_sg_len = sg_len; - - buflen = 0; - for_each_sg(mqrq->bounce_sg, sg, sg_len, i) - buflen += sg->length; - - sg_init_one(mqrq->sg, mqrq->bounce_buf, buflen); - - return 1; -} - -/* - * If writing, bounce the data to the buffer before the request - * is sent to the host driver - */ -void mmc_queue_bounce_pre(struct mmc_queue_req *mqrq) -{ - if (!mqrq->bounce_buf) - return; - - if (rq_data_dir(mmc_queue_req_to_req(mqrq)) != WRITE) - return; - - sg_copy_to_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len, - mqrq->bounce_buf, mqrq->sg[0].length); -} - -/* - * If reading, bounce the data from the buffer after the request - * has been handled by the host driver - */ -void mmc_queue_bounce_post(struct mmc_queue_req *mqrq) -{ - if (!mqrq->bounce_buf) - return; - - if (rq_data_dir(mmc_queue_req_to_req(mqrq)) != READ) - return; - sg_copy_from_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len, - mqrq->bounce_buf, mqrq->sg[0].length); + return blk_rq_map_sg(mq->queue, req, mqrq->sg); } diff --git a/drivers/mmc/core/queue.h b/drivers/mmc/core/queue.h index 04fc89360a7a..f18d3f656baa 100644 --- a/drivers/mmc/core/queue.h +++ b/drivers/mmc/core/queue.h @@ -49,9 +49,6 @@ enum mmc_drv_op { struct mmc_queue_req { struct mmc_blk_request brq; struct scatterlist *sg; - char *bounce_buf; - struct scatterlist *bounce_sg; - unsigned int bounce_sg_len; struct mmc_async_req areq; enum mmc_drv_op drv_op; int drv_op_result; @@ -81,11 +78,8 @@ extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *, extern void mmc_cleanup_queue(struct mmc_queue *); extern void mmc_queue_suspend(struct mmc_queue *); extern void mmc_queue_resume(struct mmc_queue *); - extern unsigned int mmc_queue_map_sg(struct mmc_queue *, struct mmc_queue_req *); -extern void mmc_queue_bounce_pre(struct mmc_queue_req *); -extern void mmc_queue_bounce_post(struct mmc_queue_req *); extern int mmc_access_rpmb(struct mmc_queue *); diff --git a/drivers/mmc/host/cavium.c b/drivers/mmc/host/cavium.c index 27fb625cbcf3..fbd29f00fca0 100644 --- a/drivers/mmc/host/cavium.c +++ b/drivers/mmc/host/cavium.c @@ -1038,7 +1038,7 @@ int cvm_mmc_of_slot_probe(struct device *dev, struct cvm_mmc_host *host) */ mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED | MMC_CAP_ERASE | MMC_CAP_CMD23 | MMC_CAP_POWER_OFF_CARD | - MMC_CAP_3_3V_DDR | MMC_CAP_NO_BOUNCE_BUFF; + MMC_CAP_3_3V_DDR; if (host->use_sg) mmc->max_segs = 16; diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index c885c2d4b904..85745ef179e2 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -531,8 +531,7 @@ static int meson_mmc_clk_init(struct meson_host *host) div->shift = __ffs(CLK_DIV_MASK); div->width = __builtin_popcountl(CLK_DIV_MASK); div->hw.init = &init; - div->flags = (CLK_DIVIDER_ONE_BASED | - CLK_DIVIDER_ROUND_CLOSEST); + div->flags = CLK_DIVIDER_ONE_BASED; clk = devm_clk_register(host->dev, &div->hw); if (WARN_ON(IS_ERR(clk))) @@ -717,6 +716,22 @@ static int meson_mmc_clk_phase_tuning(struct mmc_host *mmc, u32 opcode, static int meson_mmc_execute_tuning(struct mmc_host *mmc, u32 opcode) { struct meson_host *host = mmc_priv(mmc); + int ret; + + /* + * If this is the initial tuning, try to get a sane Rx starting + * phase before doing the actual tuning. + */ + if (!mmc->doing_retune) { + ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk); + + if (ret) + return ret; + } + + ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->tx_clk); + if (ret) + return ret; return meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk); } @@ -746,6 +761,11 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) case MMC_POWER_UP: if (!IS_ERR(mmc->supply.vmmc)) mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, ios->vdd); + + /* Reset phases */ + clk_set_phase(host->rx_clk, 0); + clk_set_phase(host->tx_clk, 270); + break; case MMC_POWER_ON: @@ -759,8 +779,6 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) host->vqmmc_enabled = true; } - /* Reset rx phase */ - clk_set_phase(host->rx_clk, 0); break; } diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c index 59ab194cb009..c763b404510f 100644 --- a/drivers/mmc/host/pxamci.c +++ b/drivers/mmc/host/pxamci.c @@ -702,11 +702,7 @@ static int pxamci_probe(struct platform_device *pdev) pxamci_init_ocr(host); - /* - * This architecture used to disable bounce buffers through its - * defconfig, now it is done at runtime as a host property. - */ - mmc->caps = MMC_CAP_NO_BOUNCE_BUFF; + mmc->caps = 0; host->cmdat = 0; if (!cpu_is_pxa25x()) { mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_SDIO_IRQ; diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c index 2eec2e652c53..0842bbc2d7ad 100644 --- a/drivers/mmc/host/sdhci-xenon.c +++ b/drivers/mmc/host/sdhci-xenon.c @@ -466,6 +466,7 @@ static int xenon_probe(struct platform_device *pdev) { struct sdhci_pltfm_host *pltfm_host; struct sdhci_host *host; + struct xenon_priv *priv; int err; host = sdhci_pltfm_init(pdev, &sdhci_xenon_pdata, @@ -474,6 +475,7 @@ static int xenon_probe(struct platform_device *pdev) return PTR_ERR(host); pltfm_host = sdhci_priv(host); + priv = sdhci_pltfm_priv(pltfm_host); /* * Link Xenon specific mmc_host_ops function, @@ -491,9 +493,20 @@ static int xenon_probe(struct platform_device *pdev) if (err) goto free_pltfm; + priv->axi_clk = devm_clk_get(&pdev->dev, "axi"); + if (IS_ERR(priv->axi_clk)) { + err = PTR_ERR(priv->axi_clk); + if (err == -EPROBE_DEFER) + goto err_clk; + } else { + err = clk_prepare_enable(priv->axi_clk); + if (err) + goto err_clk; + } + err = mmc_of_parse(host->mmc); if (err) - goto err_clk; + goto err_clk_axi; sdhci_get_of_property(pdev); @@ -502,11 +515,11 @@ static int xenon_probe(struct platform_device *pdev) /* Xenon specific dt parse */ err = xenon_probe_dt(pdev); if (err) - goto err_clk; + goto err_clk_axi; err = xenon_sdhc_prepare(host); if (err) - goto err_clk; + goto err_clk_axi; pm_runtime_get_noresume(&pdev->dev); pm_runtime_set_active(&pdev->dev); @@ -527,6 +540,8 @@ remove_sdhc: pm_runtime_disable(&pdev->dev); pm_runtime_put_noidle(&pdev->dev); xenon_sdhc_unprepare(host); +err_clk_axi: + clk_disable_unprepare(priv->axi_clk); err_clk: clk_disable_unprepare(pltfm_host->clk); free_pltfm: @@ -538,6 +553,7 @@ static int xenon_remove(struct platform_device *pdev) { struct sdhci_host *host = platform_get_drvdata(pdev); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host); pm_runtime_get_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); @@ -546,7 +562,7 @@ static int xenon_remove(struct platform_device *pdev) sdhci_remove_host(host, 0); xenon_sdhc_unprepare(host); - + clk_disable_unprepare(priv->axi_clk); clk_disable_unprepare(pltfm_host->clk); sdhci_pltfm_free(pdev); diff --git a/drivers/mmc/host/sdhci-xenon.h b/drivers/mmc/host/sdhci-xenon.h index 2bc0510c0769..9994995c7c56 100644 --- a/drivers/mmc/host/sdhci-xenon.h +++ b/drivers/mmc/host/sdhci-xenon.h @@ -83,6 +83,7 @@ struct xenon_priv { unsigned char bus_width; unsigned char timing; unsigned int clock; + struct clk *axi_clk; int phy_type; /* diff --git a/drivers/net/appletalk/ltpc.c b/drivers/net/appletalk/ltpc.c index e4aa374caa4d..75a5a9b87c5a 100644 --- a/drivers/net/appletalk/ltpc.c +++ b/drivers/net/appletalk/ltpc.c @@ -694,6 +694,7 @@ static int do_read(struct net_device *dev, void *cbuf, int cbuflen, /* end of idle handlers -- what should be seen is do_read, do_write */ static struct timer_list ltpc_timer; +static struct net_device *ltpc_timer_dev; static netdev_tx_t ltpc_xmit(struct sk_buff *skb, struct net_device *dev); @@ -867,10 +868,8 @@ static void set_multicast_list(struct net_device *dev) static int ltpc_poll_counter; -static void ltpc_poll(unsigned long l) +static void ltpc_poll(struct timer_list *unused) { - struct net_device *dev = (struct net_device *) l; - del_timer(<pc_timer); if(debug & DEBUG_VERBOSE) { @@ -880,14 +879,10 @@ static void ltpc_poll(unsigned long l) } ltpc_poll_counter--; } - - if (!dev) - return; /* we've been downed */ /* poll 20 times per second */ - idle(dev); + idle(ltpc_timer_dev); ltpc_timer.expires = jiffies + HZ/20; - add_timer(<pc_timer); } @@ -1165,7 +1160,8 @@ struct net_device * __init ltpc_probe(void) dev->irq = 0; /* polled mode -- 20 times per second */ /* this is really, really slow... should it poll more often? */ - setup_timer(<pc_timer, ltpc_poll, (unsigned long)dev); + ltpc_timer_dev = dev; + timer_setup(<pc_timer, ltpc_poll, 0); ltpc_timer.expires = jiffies + HZ/20; add_timer(<pc_timer); @@ -1252,8 +1248,6 @@ static void __exit ltpc_cleanup(void) if(debug & DEBUG_VERBOSE) printk("unregister_netdev\n"); unregister_netdev(dev_ltpc); - ltpc_timer.data = 0; /* signal the poll routine that we're done */ - del_timer_sync(<pc_timer); if(debug & DEBUG_VERBOSE) printk("freeing irq\n"); diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index d4ce092def83..b48cf0487b43 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1354,7 +1354,7 @@ int b53_br_join(struct dsa_switch *ds, int port, struct net_device *br) b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan); b53_for_each_port(dev, i) { - if (ds->ports[i].bridge_dev != br) + if (dsa_to_port(ds, i)->bridge_dev != br) continue; /* Add this local port to the remote port VLAN control @@ -1390,7 +1390,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *br) b53_for_each_port(dev, i) { /* Don't touch the remaining ports */ - if (ds->ports[i].bridge_dev != br) + if (dsa_to_port(ds, i)->bridge_dev != br) continue; b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), ®); diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 7aecc98d0a18..b43c063b9634 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -205,6 +205,19 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port, if (port == priv->moca_port) bcm_sf2_port_intr_enable(priv, port); + /* Set per-queue pause threshold to 32 */ + core_writel(priv, 32, CORE_TXQ_THD_PAUSE_QN_PORT(port)); + + /* Set ACB threshold to 24 */ + for (i = 0; i < SF2_NUM_EGRESS_QUEUES; i++) { + reg = acb_readl(priv, ACB_QUEUE_CFG(port * + SF2_NUM_EGRESS_QUEUES + i)); + reg &= ~XOFF_THRESHOLD_MASK; + reg |= 24; + acb_writel(priv, reg, ACB_QUEUE_CFG(port * + SF2_NUM_EGRESS_QUEUES + i)); + } + return b53_enable_port(ds, port, phy); } @@ -588,7 +601,7 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port, * state machine and make it go in PHY_FORCING state instead. */ if (!status->link) - netif_carrier_off(ds->ports[port].netdev); + netif_carrier_off(ds->ports[port].slave); status->duplex = 1; } else { status->link = 1; @@ -613,6 +626,20 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port, status->pause = 1; } +static void bcm_sf2_enable_acb(struct dsa_switch *ds) +{ + struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); + u32 reg; + + /* Enable ACB globally */ + reg = acb_readl(priv, ACB_CONTROL); + reg |= (ACB_FLUSH_MASK << ACB_FLUSH_SHIFT); + acb_writel(priv, reg, ACB_CONTROL); + reg &= ~(ACB_FLUSH_MASK << ACB_FLUSH_SHIFT); + reg |= ACB_EN | ACB_ALGORITHM; + acb_writel(priv, reg, ACB_CONTROL); +} + static int bcm_sf2_sw_suspend(struct dsa_switch *ds) { struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); @@ -655,13 +682,15 @@ static int bcm_sf2_sw_resume(struct dsa_switch *ds) bcm_sf2_imp_setup(ds, port); } + bcm_sf2_enable_acb(ds); + return 0; } static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port, struct ethtool_wolinfo *wol) { - struct net_device *p = ds->ports[port].cpu_dp->netdev; + struct net_device *p = ds->ports[port].cpu_dp->master; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); struct ethtool_wolinfo pwol; @@ -684,7 +713,7 @@ static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port, static int bcm_sf2_sw_set_wol(struct dsa_switch *ds, int port, struct ethtool_wolinfo *wol) { - struct net_device *p = ds->ports[port].cpu_dp->netdev; + struct net_device *p = ds->ports[port].cpu_dp->master; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); s8 cpu_port = ds->ports[port].cpu_dp->index; struct ethtool_wolinfo pwol; @@ -766,6 +795,7 @@ static int bcm_sf2_sw_setup(struct dsa_switch *ds) } bcm_sf2_sw_configure_vlan(ds); + bcm_sf2_enable_acb(ds); return 0; } diff --git a/drivers/net/dsa/bcm_sf2_regs.h b/drivers/net/dsa/bcm_sf2_regs.h index d8b8074a47b9..d1596dfca323 100644 --- a/drivers/net/dsa/bcm_sf2_regs.h +++ b/drivers/net/dsa/bcm_sf2_regs.h @@ -115,6 +115,24 @@ enum bcm_sf2_reg_offs { #define P7_IRQ_OFF 0 #define P_IRQ_OFF(x) ((6 - (x)) * P_NUM_IRQ) +/* Register set relative to 'ACB' */ +#define ACB_CONTROL 0x00 +#define ACB_EN (1 << 0) +#define ACB_ALGORITHM (1 << 1) +#define ACB_FLUSH_SHIFT 2 +#define ACB_FLUSH_MASK 0x3 + +#define ACB_QUEUE_0_CFG 0x08 +#define XOFF_THRESHOLD_MASK 0x7ff +#define XON_EN (1 << 11) +#define TOTAL_XOFF_THRESHOLD_SHIFT 12 +#define TOTAL_XOFF_THRESHOLD_MASK 0x7ff +#define TOTAL_XOFF_EN (1 << 23) +#define TOTAL_XON_EN (1 << 24) +#define PKTLEN_SHIFT 25 +#define PKTLEN_MASK 0x3f +#define ACB_QUEUE_CFG(x) (ACB_QUEUE_0_CFG + ((x) * 0x4)) + /* Register set relative to 'CORE' */ #define CORE_G_PCTL_PORT0 0x00000 #define CORE_G_PCTL_PORT(x) (CORE_G_PCTL_PORT0 + (x * 0x4)) @@ -237,6 +255,11 @@ enum bcm_sf2_reg_offs { #define CORE_PORT_VLAN_CTL_PORT(x) (0xc400 + ((x) * 0x8)) #define PORT_VLAN_CTRL_MASK 0x1ff +#define CORE_TXQ_THD_PAUSE_QN_PORT_0 0x2c80 +#define TXQ_PAUSE_THD_MASK 0x7ff +#define CORE_TXQ_THD_PAUSE_QN_PORT(x) (CORE_TXQ_THD_PAUSE_QN_PORT_0 + \ + (x) * 0x8) + #define CORE_DEFAULT_1Q_TAG_P(x) (0xd040 + ((x) * 8)) #define CFI_SHIFT 12 #define PRI_SHIFT 13 diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index d55051abf4ed..3a3f4f7ba364 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -110,13 +110,6 @@ static void dsa_loop_get_ethtool_stats(struct dsa_switch *ds, int port, data[i] = ps->ports[port].mib[i].val; } -static int dsa_loop_set_addr(struct dsa_switch *ds, u8 *addr) -{ - dev_dbg(ds->dev, "%s\n", __func__); - - return 0; -} - static int dsa_loop_phy_read(struct dsa_switch *ds, int port, int regnum) { struct dsa_loop_priv *ps = ds->priv; @@ -263,7 +256,6 @@ static const struct dsa_switch_ops dsa_loop_driver = { .get_strings = dsa_loop_get_strings, .get_ethtool_stats = dsa_loop_get_ethtool_stats, .get_sset_count = dsa_loop_get_sset_count, - .set_addr = dsa_loop_set_addr, .phy_read = dsa_loop_phy_read, .phy_write = dsa_loop_phy_write, .port_bridge_join = dsa_loop_port_bridge_join, diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index 07355db2ad81..09a748327fc6 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -18,6 +18,7 @@ #include <linux/mutex.h> #include <linux/mii.h> #include <linux/phy.h> +#include <linux/if_bridge.h> #include "lan9303.h" @@ -146,6 +147,7 @@ # define LAN9303_SWE_PORT_STATE_FORWARDING_PORT0 (0) # define LAN9303_SWE_PORT_STATE_LEARNING_PORT0 BIT(1) # define LAN9303_SWE_PORT_STATE_BLOCKING_PORT0 BIT(0) +# define LAN9303_SWE_PORT_STATE_DISABLED_PORT0 (3) #define LAN9303_SWE_PORT_MIRROR 0x1846 # define LAN9303_SWE_PORT_MIRROR_SNIFF_ALL BIT(8) # define LAN9303_SWE_PORT_MIRROR_SNIFFER_PORT2 BIT(7) @@ -156,7 +158,9 @@ # define LAN9303_SWE_PORT_MIRROR_MIRRORED_PORT0 BIT(2) # define LAN9303_SWE_PORT_MIRROR_ENABLE_RX_MIRRORING BIT(1) # define LAN9303_SWE_PORT_MIRROR_ENABLE_TX_MIRRORING BIT(0) +# define LAN9303_SWE_PORT_MIRROR_DISABLED 0 #define LAN9303_SWE_INGRESS_PORT_TYPE 0x1847 +#define LAN9303_SWE_INGRESS_PORT_TYPE_VLAN 3 #define LAN9303_BM_CFG 0x1c00 #define LAN9303_BM_EGRSS_PORT_TYPE 0x1c0c # define LAN9303_BM_EGRSS_PORT_TYPE_SPECIAL_TAG_PORT2 (BIT(17) | BIT(16)) @@ -510,11 +514,30 @@ static int lan9303_enable_processing_port(struct lan9303 *chip, LAN9303_MAC_TX_CFG_X_TX_ENABLE); } +/* forward special tagged packets from port 0 to port 1 *or* port 2 */ +static int lan9303_setup_tagging(struct lan9303 *chip) +{ + int ret; + u32 val; + /* enable defining the destination port via special VLAN tagging + * for port 0 + */ + ret = lan9303_write_switch_reg(chip, LAN9303_SWE_INGRESS_PORT_TYPE, + LAN9303_SWE_INGRESS_PORT_TYPE_VLAN); + if (ret) + return ret; + + /* tag incoming packets at port 1 and 2 on their way to port 0 to be + * able to discover their source port + */ + val = LAN9303_BM_EGRSS_PORT_TYPE_SPECIAL_TAG_PORT0; + return lan9303_write_switch_reg(chip, LAN9303_BM_EGRSS_PORT_TYPE, val); +} + /* We want a special working switch: * - do not forward packets between port 1 and 2 * - forward everything from port 1 to port 0 * - forward everything from port 2 to port 0 - * - forward special tagged packets from port 0 to port 1 *or* port 2 */ static int lan9303_separate_ports(struct lan9303 *chip) { @@ -529,22 +552,6 @@ static int lan9303_separate_ports(struct lan9303 *chip) if (ret) return ret; - /* enable defining the destination port via special VLAN tagging - * for port 0 - */ - ret = lan9303_write_switch_reg(chip, LAN9303_SWE_INGRESS_PORT_TYPE, - 0x03); - if (ret) - return ret; - - /* tag incoming packets at port 1 and 2 on their way to port 0 to be - * able to discover their source port - */ - ret = lan9303_write_switch_reg(chip, LAN9303_BM_EGRSS_PORT_TYPE, - LAN9303_BM_EGRSS_PORT_TYPE_SPECIAL_TAG_PORT0); - if (ret) - return ret; - /* prevent port 1 and 2 from forwarding packets by their own */ return lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_STATE, LAN9303_SWE_PORT_STATE_FORWARDING_PORT0 | @@ -552,6 +559,16 @@ static int lan9303_separate_ports(struct lan9303 *chip) LAN9303_SWE_PORT_STATE_BLOCKING_PORT2); } +static void lan9303_bridge_ports(struct lan9303 *chip) +{ + /* ports bridged: remove mirroring */ + lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_MIRROR, + LAN9303_SWE_PORT_MIRROR_DISABLED); + + lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_STATE, + chip->swe_port_state); +} + static int lan9303_handle_reset(struct lan9303 *chip) { if (!chip->reset_gpio) @@ -644,6 +661,10 @@ static int lan9303_setup(struct dsa_switch *ds) return -EINVAL; } + ret = lan9303_setup_tagging(chip); + if (ret) + dev_err(chip->dev, "failed to setup port tagging %d\n", ret); + ret = lan9303_separate_ports(chip); if (ret) dev_err(chip->dev, "failed to separate ports %d\n", ret); @@ -836,6 +857,72 @@ static void lan9303_port_disable(struct dsa_switch *ds, int port, } } +static int lan9303_port_bridge_join(struct dsa_switch *ds, int port, + struct net_device *br) +{ + struct lan9303 *chip = ds->priv; + + dev_dbg(chip->dev, "%s(port %d)\n", __func__, port); + if (dsa_to_port(ds, 1)->bridge_dev == dsa_to_port(ds, 2)->bridge_dev) { + lan9303_bridge_ports(chip); + chip->is_bridged = true; /* unleash stp_state_set() */ + } + + return 0; +} + +static void lan9303_port_bridge_leave(struct dsa_switch *ds, int port, + struct net_device *br) +{ + struct lan9303 *chip = ds->priv; + + dev_dbg(chip->dev, "%s(port %d)\n", __func__, port); + if (chip->is_bridged) { + lan9303_separate_ports(chip); + chip->is_bridged = false; + } +} + +static void lan9303_port_stp_state_set(struct dsa_switch *ds, int port, + u8 state) +{ + int portmask, portstate; + struct lan9303 *chip = ds->priv; + + dev_dbg(chip->dev, "%s(port %d, state %d)\n", + __func__, port, state); + + switch (state) { + case BR_STATE_DISABLED: + portstate = LAN9303_SWE_PORT_STATE_DISABLED_PORT0; + break; + case BR_STATE_BLOCKING: + case BR_STATE_LISTENING: + portstate = LAN9303_SWE_PORT_STATE_BLOCKING_PORT0; + break; + case BR_STATE_LEARNING: + portstate = LAN9303_SWE_PORT_STATE_LEARNING_PORT0; + break; + case BR_STATE_FORWARDING: + portstate = LAN9303_SWE_PORT_STATE_FORWARDING_PORT0; + break; + default: + portstate = LAN9303_SWE_PORT_STATE_DISABLED_PORT0; + dev_err(chip->dev, "unknown stp state: port %d, state %d\n", + port, state); + } + + portmask = 0x3 << (port * 2); + portstate <<= (port * 2); + + chip->swe_port_state = (chip->swe_port_state & ~portmask) | portstate; + + if (chip->is_bridged) + lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_STATE, + chip->swe_port_state); + /* else: touching SWE_PORT_STATE would break port separation */ +} + static const struct dsa_switch_ops lan9303_switch_ops = { .get_tag_protocol = lan9303_get_tag_protocol, .setup = lan9303_setup, @@ -847,6 +934,9 @@ static const struct dsa_switch_ops lan9303_switch_ops = { .get_sset_count = lan9303_get_sset_count, .port_enable = lan9303_port_enable, .port_disable = lan9303_port_disable, + .port_bridge_join = lan9303_port_bridge_join, + .port_bridge_leave = lan9303_port_bridge_leave, + .port_stp_state_set = lan9303_port_stp_state_set, }; static int lan9303_register_switch(struct lan9303 *chip) diff --git a/drivers/net/dsa/lan9303.h b/drivers/net/dsa/lan9303.h index 4d8be555ff4d..68ecd544b658 100644 --- a/drivers/net/dsa/lan9303.h +++ b/drivers/net/dsa/lan9303.h @@ -21,6 +21,8 @@ struct lan9303 { struct dsa_switch *ds; struct mutex indirect_mutex; /* protect indexed register access */ const struct lan9303_phy_ops *ops; + bool is_bridged; /* true if port 1 and 2 are bridged */ + u32 swe_port_state; /* remember SWE_PORT_STATE while not bridged */ }; extern const struct regmap_access_table lan9303_register_set; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 034241696ce2..21431be2831e 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -782,7 +782,7 @@ mt7530_port_bridge_join(struct dsa_switch *ds, int port, * and not being setup until the port becomes enabled. */ if (ds->enabled_port_mask & BIT(i) && i != port) { - if (ds->ports[i].bridge_dev != bridge) + if (dsa_to_port(ds, i)->bridge_dev != bridge) continue; if (priv->ports[i].enable) mt7530_set(priv, MT7530_PCR_P(i), @@ -819,7 +819,7 @@ mt7530_port_bridge_leave(struct dsa_switch *ds, int port, * is kept and not being setup until the port becomes enabled. */ if (ds->enabled_port_mask & BIT(i) && i != port) { - if (ds->ports[i].bridge_dev != bridge) + if (dsa_to_port(ds, i)->bridge_dev != bridge) continue; if (priv->ports[i].enable) mt7530_clear(priv, MT7530_PCR_P(i), @@ -933,7 +933,7 @@ mt7530_setup(struct dsa_switch *ds) * controller also is the container for two GMACs nodes representing * as two netdev instances. */ - dn = ds->ports[MT7530_CPU_PORT].netdev->dev.of_node->parent; + dn = ds->ports[MT7530_CPU_PORT].master->dev.of_node->parent; priv->ethernet = syscon_node_to_regmap(dn); if (IS_ERR(priv->ethernet)) return PTR_ERR(priv->ethernet); diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c index 621cdc46ad81..f78b9e13be1c 100644 --- a/drivers/net/dsa/mv88e6060.c +++ b/drivers/net/dsa/mv88e6060.c @@ -9,6 +9,7 @@ */ #include <linux/delay.h> +#include <linux/etherdevice.h> #include <linux/jiffies.h> #include <linux/list.h> #include <linux/module.h> @@ -176,7 +177,7 @@ static int mv88e6060_setup_port(struct dsa_switch *ds, int p) ((p & 0xf) << PORT_VLAN_MAP_DBNUM_SHIFT) | (dsa_is_cpu_port(ds, p) ? ds->enabled_port_mask : - BIT(ds->ports[p].cpu_dp->index))); + BIT(dsa_to_port(ds, p)->cpu_dp->index))); /* Port Association Vector: when learning source addresses * of packets, add the address to the address database using @@ -188,6 +189,27 @@ static int mv88e6060_setup_port(struct dsa_switch *ds, int p) return 0; } +static int mv88e6060_setup_addr(struct dsa_switch *ds) +{ + u8 addr[ETH_ALEN]; + u16 val; + + eth_random_addr(addr); + + val = addr[0] << 8 | addr[1]; + + /* The multicast bit is always transmitted as a zero, so the switch uses + * bit 8 for "DiffAddr", where 0 means all ports transmit the same SA. + */ + val &= 0xfeff; + + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, val); + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_23, (addr[2] << 8) | addr[3]); + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_45, (addr[4] << 8) | addr[5]); + + return 0; +} + static int mv88e6060_setup(struct dsa_switch *ds) { int ret; @@ -203,6 +225,10 @@ static int mv88e6060_setup(struct dsa_switch *ds) if (ret < 0) return ret; + ret = mv88e6060_setup_addr(ds); + if (ret < 0) + return ret; + for (i = 0; i < MV88E6060_PORTS; i++) { ret = mv88e6060_setup_port(ds, i); if (ret < 0) @@ -212,16 +238,6 @@ static int mv88e6060_setup(struct dsa_switch *ds) return 0; } -static int mv88e6060_set_addr(struct dsa_switch *ds, u8 *addr) -{ - /* Use the same MAC Address as FD Pause frames for all ports */ - REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, (addr[0] << 9) | addr[1]); - REG_WRITE(REG_GLOBAL, GLOBAL_MAC_23, (addr[2] << 8) | addr[3]); - REG_WRITE(REG_GLOBAL, GLOBAL_MAC_45, (addr[4] << 8) | addr[5]); - - return 0; -} - static int mv88e6060_port_to_phy_addr(int port) { if (port >= 0 && port < MV88E6060_PORTS) @@ -256,7 +272,6 @@ static const struct dsa_switch_ops mv88e6060_switch_ops = { .get_tag_protocol = mv88e6060_get_tag_protocol, .probe = mv88e6060_drv_probe, .setup = mv88e6060_setup, - .set_addr = mv88e6060_set_addr, .phy_read = mv88e6060_phy_read, .phy_write = mv88e6060_phy_write, }; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index d74c7335c512..677d6902807e 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -851,7 +851,7 @@ static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port) for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) if (dsa_is_cpu_port(chip->ds, i) || dsa_is_dsa_port(chip->ds, i) || - (br && chip->ds->ports[i].bridge_dev == br)) + (br && dsa_to_port(chip->ds, i)->bridge_dev == br)) pvlan |= BIT(i); return pvlan; @@ -932,6 +932,19 @@ static int mv88e6xxx_irl_setup(struct mv88e6xxx_chip *chip) return 0; } +static int mv88e6xxx_mac_setup(struct mv88e6xxx_chip *chip) +{ + if (chip->info->ops->set_switch_mac) { + u8 addr[ETH_ALEN]; + + eth_random_addr(addr); + + return chip->info->ops->set_switch_mac(chip, addr); + } + + return 0; +} + static int mv88e6xxx_pvt_map(struct mv88e6xxx_chip *chip, int dev, int port) { u16 pvlan = 0; @@ -1124,23 +1137,23 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, if (dsa_is_dsa_port(ds, i) || dsa_is_cpu_port(ds, i)) continue; - if (!ds->ports[port].netdev) + if (!ds->ports[port].slave) continue; if (vlan.member[i] == MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_NON_MEMBER) continue; - if (ds->ports[i].bridge_dev == + if (dsa_to_port(ds, i)->bridge_dev == ds->ports[port].bridge_dev) break; /* same bridge, check next VLAN */ - if (!ds->ports[i].bridge_dev) + if (!dsa_to_port(ds, i)->bridge_dev) continue; dev_err(ds->dev, "p%d: hw VLAN %d already used by %s\n", port, vlan.vid, - netdev_name(ds->ports[i].bridge_dev)); + netdev_name(dsa_to_port(ds, i)->bridge_dev)); err = -EOPNOTSUPP; goto unlock; } @@ -2013,6 +2026,10 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) if (err) goto unlock; + err = mv88e6xxx_mac_setup(chip); + if (err) + goto unlock; + err = mv88e6xxx_phy_setup(chip); if (err) goto unlock; @@ -2043,21 +2060,6 @@ unlock: return err; } -static int mv88e6xxx_set_addr(struct dsa_switch *ds, u8 *addr) -{ - struct mv88e6xxx_chip *chip = ds->priv; - int err; - - if (!chip->info->ops->set_switch_mac) - return -EOPNOTSUPP; - - mutex_lock(&chip->reg_lock); - err = chip->info->ops->set_switch_mac(chip, addr); - mutex_unlock(&chip->reg_lock); - - return err; -} - static int mv88e6xxx_mdio_read(struct mii_bus *bus, int phy, int reg) { struct mv88e6xxx_mdio_bus *mdio_bus = bus->priv; @@ -3785,7 +3787,6 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .probe = mv88e6xxx_drv_probe, .get_tag_protocol = mv88e6xxx_get_tag_protocol, .setup = mv88e6xxx_setup, - .set_addr = mv88e6xxx_set_addr, .adjust_link = mv88e6xxx_adjust_link, .get_strings = mv88e6xxx_get_strings, .get_ethtool_stats = mv88e6xxx_get_ethtool_stats, diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 82f09711ac1a..d1b0b1fb632f 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -700,7 +700,7 @@ qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) int i; for (i = 1; i < QCA8K_NUM_PORTS; i++) { - if (ds->ports[i].bridge_dev != br) + if (dsa_to_port(ds, i)->bridge_dev != br) continue; /* Add this port to the portvlan mask of the other ports * in the bridge @@ -725,7 +725,7 @@ qca8k_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br) int i; for (i = 1; i < QCA8K_NUM_PORTS; i++) { - if (ds->ports[i].bridge_dev != br) + if (dsa_to_port(ds, i)->bridge_dev != br) continue; /* Remove this port to the portvlan mask of the other ports * in the bridge diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c index 47c844cc9d27..48bc7fa0258c 100644 --- a/drivers/net/ethernet/3com/3c574_cs.c +++ b/drivers/net/ethernet/3com/3c574_cs.c @@ -225,7 +225,7 @@ static unsigned short read_eeprom(unsigned int ioaddr, int index); static void tc574_wait_for_completion(struct net_device *dev, int cmd); static void tc574_reset(struct net_device *dev); -static void media_check(unsigned long arg); +static void media_check(struct timer_list *t); static int el3_open(struct net_device *dev); static netdev_tx_t el3_start_xmit(struct sk_buff *skb, struct net_device *dev); @@ -377,7 +377,7 @@ static int tc574_config(struct pcmcia_device *link) lp->autoselect = config & Autoselect ? 1 : 0; } - init_timer(&lp->media); + timer_setup(&lp->media, media_check, 0); { int phy; @@ -681,8 +681,6 @@ static int el3_open(struct net_device *dev) netif_start_queue(dev); tc574_reset(dev); - lp->media.function = media_check; - lp->media.data = (unsigned long) dev; lp->media.expires = jiffies + HZ; add_timer(&lp->media); @@ -859,10 +857,10 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id) (and as a last resort, poll the NIC for events), and to monitor the MII, reporting changes in cable status. */ -static void media_check(unsigned long arg) +static void media_check(struct timer_list *t) { - struct net_device *dev = (struct net_device *) arg; - struct el3_private *lp = netdev_priv(dev); + struct el3_private *lp = from_timer(lp, t, media); + struct net_device *dev = lp->p_dev->priv; unsigned int ioaddr = dev->base_addr; unsigned long flags; unsigned short /* cable, */ media, partner; diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c index e28254a00599..2b2695311bda 100644 --- a/drivers/net/ethernet/3com/3c589_cs.c +++ b/drivers/net/ethernet/3com/3c589_cs.c @@ -163,7 +163,7 @@ static void tc589_release(struct pcmcia_device *link); static u16 read_eeprom(unsigned int ioaddr, int index); static void tc589_reset(struct net_device *dev); -static void media_check(unsigned long arg); +static void media_check(struct timer_list *t); static int el3_config(struct net_device *dev, struct ifmap *map); static int el3_open(struct net_device *dev); static netdev_tx_t el3_start_xmit(struct sk_buff *skb, @@ -517,7 +517,7 @@ static int el3_open(struct net_device *dev) netif_start_queue(dev); tc589_reset(dev); - setup_timer(&lp->media, media_check, (unsigned long)dev); + timer_setup(&lp->media, media_check, 0); mod_timer(&lp->media, jiffies + HZ); dev_dbg(&link->dev, "%s: opened, status %4.4x.\n", @@ -676,10 +676,10 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id) return IRQ_RETVAL(handled); } -static void media_check(unsigned long arg) +static void media_check(struct timer_list *t) { - struct net_device *dev = (struct net_device *)(arg); - struct el3_private *lp = netdev_priv(dev); + struct el3_private *lp = from_timer(lp, t, media); + struct net_device *dev = lp->p_dev->priv; unsigned int ioaddr = dev->base_addr; u16 media, errs; unsigned long flags; diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 402d9090ad29..f4e13a7014bd 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -759,8 +759,8 @@ static int vortex_open(struct net_device *dev); static void mdio_sync(struct vortex_private *vp, int bits); static int mdio_read(struct net_device *dev, int phy_id, int location); static void mdio_write(struct net_device *vp, int phy_id, int location, int value); -static void vortex_timer(unsigned long arg); -static void rx_oom_timer(unsigned long arg); +static void vortex_timer(struct timer_list *t); +static void rx_oom_timer(struct timer_list *t); static netdev_tx_t vortex_start_xmit(struct sk_buff *skb, struct net_device *dev); static netdev_tx_t boomerang_start_xmit(struct sk_buff *skb, @@ -1599,9 +1599,9 @@ vortex_up(struct net_device *dev) dev->name, media_tbl[dev->if_port].name); } - setup_timer(&vp->timer, vortex_timer, (unsigned long)dev); + timer_setup(&vp->timer, vortex_timer, 0); mod_timer(&vp->timer, RUN_AT(media_tbl[dev->if_port].wait)); - setup_timer(&vp->rx_oom_timer, rx_oom_timer, (unsigned long)dev); + timer_setup(&vp->rx_oom_timer, rx_oom_timer, 0); if (vortex_debug > 1) pr_debug("%s: Initial media type %s.\n", @@ -1784,10 +1784,10 @@ out: } static void -vortex_timer(unsigned long data) +vortex_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct vortex_private *vp = netdev_priv(dev); + struct vortex_private *vp = from_timer(vp, t, timer); + struct net_device *dev = vp->mii.dev; void __iomem *ioaddr = vp->ioaddr; int next_tick = 60*HZ; int ok = 0; @@ -2687,10 +2687,10 @@ boomerang_rx(struct net_device *dev) * for some memory. Otherwise there is no way to restart the rx process. */ static void -rx_oom_timer(unsigned long arg) +rx_oom_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)arg; - struct vortex_private *vp = netdev_priv(dev); + struct vortex_private *vp = from_timer(vp, t, rx_oom_timer); + struct net_device *dev = vp->mii.dev; spin_lock_irq(&vp->lock); if ((vp->cur_rx - vp->dirty_rx) == RX_RING_SIZE) /* This test is redundant, but makes me feel good */ diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h index 305dc1996b4e..4532e574ebcd 100644 --- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h +++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h @@ -627,6 +627,12 @@ enum ena_admin_flow_hash_proto { ENA_ADMIN_RSS_NOT_IP = 7, + /* TCPv6 with extension header */ + ENA_ADMIN_RSS_TCP6_EX = 8, + + /* IPv6 with extension header */ + ENA_ADMIN_RSS_IP6_EX = 9, + ENA_ADMIN_RSS_PROTO_NUM = 16, }; diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index ded29af648c9..bf2de5298005 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -63,6 +63,8 @@ #define ENA_REGS_ADMIN_INTR_MASK 1 +#define ENA_POLL_MS 5 + /*****************************************************************************/ /*****************************************************************************/ /*****************************************************************************/ @@ -533,7 +535,7 @@ static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_c goto err; } - msleep(100); + msleep(ENA_POLL_MS); } if (unlikely(comp_ctx->status == ENA_CMD_ABORTED)) { @@ -746,6 +748,9 @@ static int wait_for_reset_state(struct ena_com_dev *ena_dev, u32 timeout, { u32 val, i; + /* Convert timeout from resolution of 100ms to ENA_POLL_MS */ + timeout = (timeout * 100) / ENA_POLL_MS; + for (i = 0; i < timeout; i++) { val = ena_com_reg_bar_read32(ena_dev, ENA_REGS_DEV_STS_OFF); @@ -758,8 +763,7 @@ static int wait_for_reset_state(struct ena_com_dev *ena_dev, u32 timeout, exp_state) return 0; - /* The resolution of the timeout is 100ms */ - msleep(100); + msleep(ENA_POLL_MS); } return -ETIME; @@ -1253,7 +1257,7 @@ void ena_com_wait_for_abort_completion(struct ena_com_dev *ena_dev) spin_lock_irqsave(&admin_queue->q_lock, flags); while (atomic_read(&admin_queue->outstanding_cmds) != 0) { spin_unlock_irqrestore(&admin_queue->q_lock, flags); - msleep(20); + msleep(ENA_POLL_MS); spin_lock_irqsave(&admin_queue->q_lock, flags); } spin_unlock_irqrestore(&admin_queue->q_lock, flags); diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index b1212debc2e1..0d97311a1b26 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -60,8 +60,8 @@ struct ena_stats { static const struct ena_stats ena_stats_global_strings[] = { ENA_STAT_GLOBAL_ENTRY(tx_timeout), - ENA_STAT_GLOBAL_ENTRY(io_suspend), - ENA_STAT_GLOBAL_ENTRY(io_resume), + ENA_STAT_GLOBAL_ENTRY(suspend), + ENA_STAT_GLOBAL_ENTRY(resume), ENA_STAT_GLOBAL_ENTRY(wd_expired), ENA_STAT_GLOBAL_ENTRY(interface_up), ENA_STAT_GLOBAL_ENTRY(interface_down), @@ -81,6 +81,7 @@ static const struct ena_stats ena_stats_tx_strings[] = { ENA_STAT_TX_ENTRY(doorbells), ENA_STAT_TX_ENTRY(prepare_ctx_err), ENA_STAT_TX_ENTRY(bad_req_id), + ENA_STAT_TX_ENTRY(missed_tx), }; static const struct ena_stats ena_stats_rx_strings[] = { diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index f7dc22f65d9f..47bdbf9bdefb 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2361,38 +2361,6 @@ static const struct net_device_ops ena_netdev_ops = { #endif /* CONFIG_NET_POLL_CONTROLLER */ }; -static void ena_device_io_suspend(struct work_struct *work) -{ - struct ena_adapter *adapter = - container_of(work, struct ena_adapter, suspend_io_task); - struct net_device *netdev = adapter->netdev; - - /* ena_napi_disable_all disables only the IO handling. - * We are still subject to AENQ keep alive watchdog. - */ - u64_stats_update_begin(&adapter->syncp); - adapter->dev_stats.io_suspend++; - u64_stats_update_begin(&adapter->syncp); - ena_napi_disable_all(adapter); - netif_tx_lock(netdev); - netif_device_detach(netdev); - netif_tx_unlock(netdev); -} - -static void ena_device_io_resume(struct work_struct *work) -{ - struct ena_adapter *adapter = - container_of(work, struct ena_adapter, resume_io_task); - struct net_device *netdev = adapter->netdev; - - u64_stats_update_begin(&adapter->syncp); - adapter->dev_stats.io_resume++; - u64_stats_update_end(&adapter->syncp); - - netif_device_attach(netdev); - ena_napi_enable_all(adapter); -} - static int ena_device_validate_params(struct ena_adapter *adapter, struct ena_com_dev_get_features_ctx *get_feat_ctx) { @@ -2561,38 +2529,31 @@ err_disable_msix: return rc; } -static void ena_fw_reset_device(struct work_struct *work) +static void ena_destroy_device(struct ena_adapter *adapter) { - struct ena_com_dev_get_features_ctx get_feat_ctx; - struct ena_adapter *adapter = - container_of(work, struct ena_adapter, reset_task); struct net_device *netdev = adapter->netdev; struct ena_com_dev *ena_dev = adapter->ena_dev; - struct pci_dev *pdev = adapter->pdev; - bool dev_up, wd_state; - int rc; - - if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) { - dev_err(&pdev->dev, - "device reset schedule while reset bit is off\n"); - return; - } + bool dev_up; netif_carrier_off(netdev); del_timer_sync(&adapter->timer_service); - rtnl_lock(); - dev_up = test_bit(ENA_FLAG_DEV_UP, &adapter->flags); + adapter->dev_up_before_reset = dev_up; + ena_com_set_admin_running_state(ena_dev, false); - /* After calling ena_close the tx queues and the napi - * are disabled so no one can interfere or touch the - * data structures - */ ena_close(netdev); + /* Before releasing the ENA resources, a device reset is required. + * (to prevent the device from accessing them). + * In case the reset flag is set and the device is up, ena_close + * already perform the reset, so it can be skipped. + */ + if (!(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags) && dev_up)) + ena_com_dev_reset(adapter->ena_dev, adapter->reset_reason); + ena_free_mgmnt_irq(adapter); ena_disable_msix(adapter); @@ -2606,9 +2567,17 @@ static void ena_fw_reset_device(struct work_struct *work) ena_com_mmio_reg_read_request_destroy(ena_dev); adapter->reset_reason = ENA_REGS_RESET_NORMAL; + clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); +} - /* Finish with the destroy part. Start the init part */ +static int ena_restore_device(struct ena_adapter *adapter) +{ + struct ena_com_dev_get_features_ctx get_feat_ctx; + struct ena_com_dev *ena_dev = adapter->ena_dev; + struct pci_dev *pdev = adapter->pdev; + bool wd_state; + int rc; rc = ena_device_init(ena_dev, adapter->pdev, &get_feat_ctx, &wd_state); if (rc) { @@ -2630,7 +2599,7 @@ static void ena_fw_reset_device(struct work_struct *work) goto err_device_destroy; } /* If the interface was up before the reset bring it up */ - if (dev_up) { + if (adapter->dev_up_before_reset) { rc = ena_up(adapter); if (rc) { dev_err(&pdev->dev, "Failed to create I/O queues\n"); @@ -2639,24 +2608,38 @@ static void ena_fw_reset_device(struct work_struct *work) } mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); - - rtnl_unlock(); - dev_err(&pdev->dev, "Device reset completed successfully\n"); - return; + return rc; err_disable_msix: ena_free_mgmnt_irq(adapter); ena_disable_msix(adapter); err_device_destroy: ena_com_admin_destroy(ena_dev); err: - rtnl_unlock(); - clear_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags); dev_err(&pdev->dev, "Reset attempt failed. Can not reset the device\n"); + + return rc; +} + +static void ena_fw_reset_device(struct work_struct *work) +{ + struct ena_adapter *adapter = + container_of(work, struct ena_adapter, reset_task); + struct pci_dev *pdev = adapter->pdev; + + if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) { + dev_err(&pdev->dev, + "device reset schedule while reset bit is off\n"); + return; + } + rtnl_lock(); + ena_destroy_device(adapter); + ena_restore_device(adapter); + rtnl_unlock(); } static int check_missing_comp_in_queue(struct ena_adapter *adapter, @@ -2665,7 +2648,7 @@ static int check_missing_comp_in_queue(struct ena_adapter *adapter, struct ena_tx_buffer *tx_buf; unsigned long last_jiffies; u32 missed_tx = 0; - int i; + int i, rc = 0; for (i = 0; i < tx_ring->ring_size; i++) { tx_buf = &tx_ring->tx_buffer_info[i]; @@ -2679,21 +2662,25 @@ static int check_missing_comp_in_queue(struct ena_adapter *adapter, tx_buf->print_once = 1; missed_tx++; - - if (unlikely(missed_tx > adapter->missing_tx_completion_threshold)) { - netif_err(adapter, tx_err, adapter->netdev, - "The number of lost tx completions is above the threshold (%d > %d). Reset the device\n", - missed_tx, - adapter->missing_tx_completion_threshold); - adapter->reset_reason = - ENA_REGS_RESET_MISS_TX_CMPL; - set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); - return -EIO; - } } } - return 0; + if (unlikely(missed_tx > adapter->missing_tx_completion_threshold)) { + netif_err(adapter, tx_err, adapter->netdev, + "The number of lost tx completions is above the threshold (%d > %d). Reset the device\n", + missed_tx, + adapter->missing_tx_completion_threshold); + adapter->reset_reason = + ENA_REGS_RESET_MISS_TX_CMPL; + set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); + rc = -EIO; + } + + u64_stats_update_begin(&tx_ring->syncp); + tx_ring->tx_stats.missed_tx = missed_tx; + u64_stats_update_end(&tx_ring->syncp); + + return rc; } static void check_for_missing_tx_completions(struct ena_adapter *adapter) @@ -3275,8 +3262,6 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_rss; } - INIT_WORK(&adapter->suspend_io_task, ena_device_io_suspend); - INIT_WORK(&adapter->resume_io_task, ena_device_io_resume); INIT_WORK(&adapter->reset_task, ena_fw_reset_device); adapter->last_keep_alive_jiffies = jiffies; @@ -3310,8 +3295,6 @@ err_free_msix: err_worker_destroy: ena_com_destroy_interrupt_moderation(ena_dev); del_timer(&adapter->timer_service); - cancel_work_sync(&adapter->suspend_io_task); - cancel_work_sync(&adapter->resume_io_task); err_netdev_destroy: free_netdev(netdev); err_device_destroy: @@ -3381,10 +3364,6 @@ static void ena_remove(struct pci_dev *pdev) cancel_work_sync(&adapter->reset_task); - cancel_work_sync(&adapter->suspend_io_task); - - cancel_work_sync(&adapter->resume_io_task); - /* Reset the device only if the device is running. */ if (test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags)) ena_com_dev_reset(ena_dev, adapter->reset_reason); @@ -3418,11 +3397,59 @@ static void ena_remove(struct pci_dev *pdev) vfree(ena_dev); } +#ifdef CONFIG_PM +/* ena_suspend - PM suspend callback + * @pdev: PCI device information struct + * @state:power state + */ +static int ena_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct ena_adapter *adapter = pci_get_drvdata(pdev); + + u64_stats_update_begin(&adapter->syncp); + adapter->dev_stats.suspend++; + u64_stats_update_end(&adapter->syncp); + + rtnl_lock(); + if (unlikely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) { + dev_err(&pdev->dev, + "ignoring device reset request as the device is being suspended\n"); + clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); + } + ena_destroy_device(adapter); + rtnl_unlock(); + return 0; +} + +/* ena_resume - PM resume callback + * @pdev: PCI device information struct + * + */ +static int ena_resume(struct pci_dev *pdev) +{ + struct ena_adapter *adapter = pci_get_drvdata(pdev); + int rc; + + u64_stats_update_begin(&adapter->syncp); + adapter->dev_stats.resume++; + u64_stats_update_end(&adapter->syncp); + + rtnl_lock(); + rc = ena_restore_device(adapter); + rtnl_unlock(); + return rc; +} +#endif + static struct pci_driver ena_pci_driver = { .name = DRV_MODULE_NAME, .id_table = ena_pci_tbl, .probe = ena_probe, .remove = ena_remove, +#ifdef CONFIG_PM + .suspend = ena_suspend, + .resume = ena_resume, +#endif .sriov_configure = ena_sriov_configure, }; @@ -3503,16 +3530,6 @@ static void ena_notification(void *adapter_data, ENA_ADMIN_NOTIFICATION); switch (aenq_e->aenq_common_desc.syndrom) { - case ENA_ADMIN_SUSPEND: - /* Suspend just the IO queues. - * We deliberately don't suspend admin so the timer and - * the keep_alive events should remain. - */ - queue_work(ena_wq, &adapter->suspend_io_task); - break; - case ENA_ADMIN_RESUME: - queue_work(ena_wq, &adapter->resume_io_task); - break; case ENA_ADMIN_UPDATE_HINTS: hints = (struct ena_admin_ena_hw_hints *) (&aenq_e->inline_data_w4); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index 29bb5704260b..ed8bd0a579c4 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -44,7 +44,7 @@ #include "ena_eth_com.h" #define DRV_MODULE_VER_MAJOR 1 -#define DRV_MODULE_VER_MINOR 2 +#define DRV_MODULE_VER_MINOR 3 #define DRV_MODULE_VER_SUBMINOR 0 #define DRV_MODULE_NAME "ena" @@ -52,7 +52,7 @@ #define DRV_MODULE_VERSION \ __stringify(DRV_MODULE_VER_MAJOR) "." \ __stringify(DRV_MODULE_VER_MINOR) "." \ - __stringify(DRV_MODULE_VER_SUBMINOR) "k" + __stringify(DRV_MODULE_VER_SUBMINOR) "K" #endif #define DEVICE_NAME "Elastic Network Adapter (ENA)" @@ -185,6 +185,7 @@ struct ena_stats_tx { u64 tx_poll; u64 doorbells; u64 bad_req_id; + u64 missed_tx; }; struct ena_stats_rx { @@ -257,8 +258,8 @@ struct ena_ring { struct ena_stats_dev { u64 tx_timeout; - u64 io_suspend; - u64 io_resume; + u64 suspend; + u64 resume; u64 wd_expired; u64 interface_up; u64 interface_down; @@ -326,11 +327,10 @@ struct ena_adapter { /* timer service */ struct work_struct reset_task; - struct work_struct suspend_io_task; - struct work_struct resume_io_task; struct timer_list timer_service; bool wd_state; + bool dev_up_before_reset; unsigned long last_keep_alive_jiffies; struct u64_stats_sync syncp; diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index 7f22af6e37e0..358f7ab77c70 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -1669,9 +1669,9 @@ static int amd8111e_resume(struct pci_dev *pci_dev) return 0; } -static void amd8111e_config_ipg(struct net_device *dev) +static void amd8111e_config_ipg(struct timer_list *t) { - struct amd8111e_priv *lp = netdev_priv(dev); + struct amd8111e_priv *lp = from_timer(lp, t, ipg_data.ipg_timer); struct ipg_info *ipg_data = &lp->ipg_data; void __iomem *mmio = lp->mmio; unsigned int prev_col_cnt = ipg_data->col_cnt; @@ -1883,8 +1883,7 @@ static int amd8111e_probe_one(struct pci_dev *pdev, /* Initialize software ipg timer */ if(lp->options & OPTION_DYN_IPG_ENABLE){ - setup_timer(&lp->ipg_data.ipg_timer, - (void *)&amd8111e_config_ipg, (unsigned long)dev); + timer_setup(&lp->ipg_data.ipg_timer, amd8111e_config_ipg, 0); lp->ipg_data.ipg_timer.expires = jiffies + IPG_CONVERGE_JIFFIES; lp->ipg_data.ipg = DEFAULT_IPG; diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index eac740c476ce..5a655d289dd5 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -157,7 +157,7 @@ static irqreturn_t bmac_misc_intr(int irq, void *dev_id); static irqreturn_t bmac_txdma_intr(int irq, void *dev_id); static irqreturn_t bmac_rxdma_intr(int irq, void *dev_id); static void bmac_set_timeout(struct net_device *dev); -static void bmac_tx_timeout(unsigned long data); +static void bmac_tx_timeout(struct timer_list *t); static int bmac_output(struct sk_buff *skb, struct net_device *dev); static void bmac_start(struct net_device *dev); @@ -555,8 +555,6 @@ static inline void bmac_set_timeout(struct net_device *dev) if (bp->timeout_active) del_timer(&bp->tx_timeout); bp->tx_timeout.expires = jiffies + TX_TIMEOUT; - bp->tx_timeout.function = bmac_tx_timeout; - bp->tx_timeout.data = (unsigned long) dev; add_timer(&bp->tx_timeout); bp->timeout_active = 1; spin_unlock_irqrestore(&bp->lock, flags); @@ -1321,7 +1319,7 @@ static int bmac_probe(struct macio_dev *mdev, const struct of_device_id *match) bp->queue = (struct sk_buff_head *)(bp->rx_cmds + N_RX_RING + 1); skb_queue_head_init(bp->queue); - init_timer(&bp->tx_timeout); + timer_setup(&bp->tx_timeout, bmac_tx_timeout, 0); ret = request_irq(dev->irq, bmac_misc_intr, 0, "BMAC-misc", dev); if (ret) { @@ -1471,10 +1469,10 @@ bmac_output(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } -static void bmac_tx_timeout(unsigned long data) +static void bmac_tx_timeout(struct timer_list *t) { - struct net_device *dev = (struct net_device *) data; - struct bmac_data *bp = netdev_priv(dev); + struct bmac_data *bp = from_timer(bp, t, tx_timeout); + struct net_device *dev = macio_get_drvdata(bp->mdev); volatile struct dbdma_regs __iomem *td = bp->tx_dma; volatile struct dbdma_regs __iomem *rd = bp->rx_dma; volatile struct dbdma_cmd *cp; diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c index e58b157b7d7c..0b5429d76bcf 100644 --- a/drivers/net/ethernet/apple/mace.c +++ b/drivers/net/ethernet/apple/mace.c @@ -86,7 +86,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id); static irqreturn_t mace_txdma_intr(int irq, void *dev_id); static irqreturn_t mace_rxdma_intr(int irq, void *dev_id); static void mace_set_timeout(struct net_device *dev); -static void mace_tx_timeout(unsigned long data); +static void mace_tx_timeout(struct timer_list *t); static inline void dbdma_reset(volatile struct dbdma_regs __iomem *dma); static inline void mace_clean_rings(struct mace_data *mp); static void __mace_set_address(struct net_device *dev, void *addr); @@ -196,7 +196,7 @@ static int mace_probe(struct macio_dev *mdev, const struct of_device_id *match) memset((char *) mp->tx_cmds, 0, (NCMDS_TX*N_TX_RING + N_RX_RING + 2) * sizeof(struct dbdma_cmd)); - init_timer(&mp->tx_timeout); + timer_setup(&mp->tx_timeout, mace_tx_timeout, 0); spin_lock_init(&mp->lock); mp->timeout_active = 0; @@ -521,8 +521,6 @@ static inline void mace_set_timeout(struct net_device *dev) if (mp->timeout_active) del_timer(&mp->tx_timeout); mp->tx_timeout.expires = jiffies + TX_TIMEOUT; - mp->tx_timeout.function = mace_tx_timeout; - mp->tx_timeout.data = (unsigned long) dev; add_timer(&mp->tx_timeout); mp->timeout_active = 1; } @@ -801,10 +799,10 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static void mace_tx_timeout(unsigned long data) +static void mace_tx_timeout(struct timer_list *t) { - struct net_device *dev = (struct net_device *) data; - struct mace_data *mp = netdev_priv(dev); + struct mace_data *mp = from_timer(mp, t, tx_timeout); + struct net_device *dev = macio_get_drvdata(mp->mdev); volatile struct mace __iomem *mb = mp->mace; volatile struct dbdma_regs __iomem *td = mp->tx_dma; volatile struct dbdma_regs __iomem *rd = mp->rx_dma; diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 67134ece1107..af75156919ed 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -184,6 +184,7 @@ config BGMAC_PLATFORM config SYSTEMPORT tristate "Broadcom SYSTEMPORT internal MAC support" depends on OF + depends on NET_DSA || !NET_DSA select MII select PHYLIB select FIXED_PHY diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index f6bc13fe8a99..d9346e2ac720 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -295,16 +295,13 @@ static int bcm_enet_refill_rx(struct net_device *dev) /* * timer callback to defer refill rx queue in case we're OOM */ -static void bcm_enet_refill_rx_timer(unsigned long data) +static void bcm_enet_refill_rx_timer(struct timer_list *t) { - struct net_device *dev; - struct bcm_enet_priv *priv; - - dev = (struct net_device *)data; - priv = netdev_priv(dev); + struct bcm_enet_priv *priv = from_timer(priv, t, rx_timeout); + struct net_device *dev = priv->net_dev; spin_lock(&priv->rx_lock); - bcm_enet_refill_rx((struct net_device *)data); + bcm_enet_refill_rx(dev); spin_unlock(&priv->rx_lock); } @@ -1860,8 +1857,7 @@ static int bcm_enet_probe(struct platform_device *pdev) spin_lock_init(&priv->rx_lock); /* init rx timeout (used for oom) */ - setup_timer(&priv->rx_timeout, bcm_enet_refill_rx_timer, - (unsigned long)dev); + timer_setup(&priv->rx_timeout, bcm_enet_refill_rx_timer, 0); /* init the mib update lock&work */ mutex_init(&priv->mib_update_lock); @@ -2015,9 +2011,9 @@ static inline int bcm_enet_port_is_rgmii(int portid) /* * enet sw PHY polling */ -static void swphy_poll_timer(unsigned long data) +static void swphy_poll_timer(struct timer_list *t) { - struct bcm_enet_priv *priv = (struct bcm_enet_priv *)data; + struct bcm_enet_priv *priv = from_timer(priv, t, swphy_poll); unsigned int i; for (i = 0; i < priv->num_ports; i++) { @@ -2326,7 +2322,7 @@ static int bcm_enetsw_open(struct net_device *dev) } /* start phy polling timer */ - setup_timer(&priv->swphy_poll, swphy_poll_timer, (unsigned long)priv); + timer_setup(&priv->swphy_poll, swphy_poll_timer, 0); mod_timer(&priv->swphy_poll, jiffies); return 0; @@ -2743,9 +2739,7 @@ static int bcm_enetsw_probe(struct platform_device *pdev) spin_lock_init(&priv->rx_lock); /* init rx timeout (used for oom) */ - init_timer(&priv->rx_timeout); - priv->rx_timeout.function = bcm_enet_refill_rx_timer; - priv->rx_timeout.data = (unsigned long)dev; + timer_setup(&priv->rx_timeout, bcm_enet_refill_rx_timer, 0); /* register netdevice */ dev->netdev_ops = &bcm_enetsw_ops; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 83eec9a8c275..dafc26690555 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1416,9 +1416,20 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv, tdma_writel(priv, 0, TDMA_DESC_RING_COUNT(index)); tdma_writel(priv, 1, TDMA_DESC_RING_INTR_CONTROL(index)); tdma_writel(priv, 0, TDMA_DESC_RING_PROD_CONS_INDEX(index)); - tdma_writel(priv, RING_IGNORE_STATUS, TDMA_DESC_RING_MAPPING(index)); + + /* Configure QID and port mapping */ + reg = tdma_readl(priv, TDMA_DESC_RING_MAPPING(index)); + reg &= ~(RING_QID_MASK | RING_PORT_ID_MASK << RING_PORT_ID_SHIFT); + reg |= ring->switch_queue & RING_QID_MASK; + reg |= ring->switch_port << RING_PORT_ID_SHIFT; + tdma_writel(priv, reg, TDMA_DESC_RING_MAPPING(index)); tdma_writel(priv, 0, TDMA_DESC_RING_PCP_DEI_VID(index)); + /* Enable ACB algorithm 2 */ + reg = tdma_readl(priv, TDMA_CONTROL); + reg |= tdma_control_bit(priv, ACB_ALGO); + tdma_writel(priv, reg, TDMA_CONTROL); + /* Do not use tdma_control_bit() here because TSB_SWAP1 collides * with the original definition of ACB_ALGO */ @@ -1447,8 +1458,9 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv, napi_enable(&ring->napi); netif_dbg(priv, hw, priv->netdev, - "TDMA cfg, size=%d, desc_cpu=%p\n", - ring->size, ring->desc_cpu); + "TDMA cfg, size=%d, desc_cpu=%p switch q=%d,port=%d\n", + ring->size, ring->desc_cpu, ring->switch_queue, + ring->switch_port); return 0; } @@ -2011,6 +2023,92 @@ static const struct ethtool_ops bcm_sysport_ethtool_ops = { .set_link_ksettings = phy_ethtool_set_link_ksettings, }; +static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, + select_queue_fallback_t fallback) +{ + struct bcm_sysport_priv *priv = netdev_priv(dev); + u16 queue = skb_get_queue_mapping(skb); + struct bcm_sysport_tx_ring *tx_ring; + unsigned int q, port; + + if (!netdev_uses_dsa(dev)) + return fallback(dev, skb); + + /* DSA tagging layer will have configured the correct queue */ + q = BRCM_TAG_GET_QUEUE(queue); + port = BRCM_TAG_GET_PORT(queue); + tx_ring = priv->ring_map[q + port * priv->per_port_num_tx_queues]; + + return tx_ring->index; +} + +static int bcm_sysport_map_queues(struct net_device *dev, + struct dsa_notifier_register_info *info) +{ + struct bcm_sysport_priv *priv = netdev_priv(dev); + struct bcm_sysport_tx_ring *ring; + struct net_device *slave_dev; + unsigned int num_tx_queues; + unsigned int q, start, port; + + /* We can't be setting up queue inspection for non directly attached + * switches + */ + if (info->switch_number) + return 0; + + port = info->port_number; + slave_dev = info->info.dev; + + /* On SYSTEMPORT Lite we have twice as less queues, so we cannot do a + * 1:1 mapping, we can only do a 2:1 mapping. By reducing the number of + * per-port (slave_dev) network devices queue, we achieve just that. + * This need to happen now before any slave network device is used such + * it accurately reflects the number of real TX queues. + */ + if (priv->is_lite) + netif_set_real_num_tx_queues(slave_dev, + slave_dev->num_tx_queues / 2); + num_tx_queues = slave_dev->real_num_tx_queues; + + if (priv->per_port_num_tx_queues && + priv->per_port_num_tx_queues != num_tx_queues) + netdev_warn(slave_dev, "asymetric number of per-port queues\n"); + + priv->per_port_num_tx_queues = num_tx_queues; + + start = find_first_zero_bit(&priv->queue_bitmap, dev->num_tx_queues); + for (q = 0; q < num_tx_queues; q++) { + ring = &priv->tx_rings[q + start]; + + /* Just remember the mapping actual programming done + * during bcm_sysport_init_tx_ring + */ + ring->switch_queue = q; + ring->switch_port = port; + priv->ring_map[q + port * num_tx_queues] = ring; + + /* Set all queues as being used now */ + set_bit(q + start, &priv->queue_bitmap); + } + + return 0; +} + +static int bcm_sysport_dsa_notifier(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct dsa_notifier_register_info *info; + + if (event != DSA_PORT_REGISTER) + return NOTIFY_DONE; + + info = ptr; + + return notifier_from_errno(bcm_sysport_map_queues(info->master, info)); +} + static const struct net_device_ops bcm_sysport_netdev_ops = { .ndo_start_xmit = bcm_sysport_xmit, .ndo_tx_timeout = bcm_sysport_tx_timeout, @@ -2023,6 +2121,7 @@ static const struct net_device_ops bcm_sysport_netdev_ops = { .ndo_poll_controller = bcm_sysport_poll_controller, #endif .ndo_get_stats64 = bcm_sysport_get_stats64, + .ndo_select_queue = bcm_sysport_select_queue, }; #define REV_FMT "v%2x.%02x" @@ -2172,10 +2271,18 @@ static int bcm_sysport_probe(struct platform_device *pdev) u64_stats_init(&priv->syncp); + priv->dsa_notifier.notifier_call = bcm_sysport_dsa_notifier; + + ret = register_dsa_notifier(&priv->dsa_notifier); + if (ret) { + dev_err(&pdev->dev, "failed to register DSA notifier\n"); + goto err_deregister_fixed_link; + } + ret = register_netdev(dev); if (ret) { dev_err(&pdev->dev, "failed to register net_device\n"); - goto err_deregister_fixed_link; + goto err_deregister_notifier; } priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK; @@ -2188,6 +2295,8 @@ static int bcm_sysport_probe(struct platform_device *pdev) return 0; +err_deregister_notifier: + unregister_dsa_notifier(&priv->dsa_notifier); err_deregister_fixed_link: if (of_phy_is_fixed_link(dn)) of_phy_deregister_fixed_link(dn); @@ -2199,11 +2308,13 @@ err_free_netdev: static int bcm_sysport_remove(struct platform_device *pdev) { struct net_device *dev = dev_get_drvdata(&pdev->dev); + struct bcm_sysport_priv *priv = netdev_priv(dev); struct device_node *dn = pdev->dev.of_node; /* Not much to do, ndo_close has been called * and we use managed allocations */ + unregister_dsa_notifier(&priv->dsa_notifier); unregister_netdev(dev); if (of_phy_is_fixed_link(dn)) of_phy_deregister_fixed_link(dn); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index 82e401df199e..82f70a6783cb 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -404,7 +404,7 @@ struct bcm_rsb { #define RING_CONS_INDEX_MASK 0xffff #define RING_MAPPING 0x14 -#define RING_QID_MASK 0x3 +#define RING_QID_MASK 0x7 #define RING_PORT_ID_SHIFT 3 #define RING_PORT_ID_MASK 0x7 #define RING_IGNORE_STATUS (1 << 6) @@ -712,6 +712,8 @@ struct bcm_sysport_tx_ring { struct bcm_sysport_priv *priv; /* private context backpointer */ unsigned long packets; /* packets statistics */ unsigned long bytes; /* bytes statistics */ + unsigned int switch_queue; /* switch port queue number */ + unsigned int switch_port; /* switch port queue number */ }; /* Driver private structure */ @@ -765,5 +767,12 @@ struct bcm_sysport_priv { /* For atomic update generic 64bit value on 32bit Machine */ struct u64_stats_sync syncp; + + /* map information between switch port queues and local queues */ + struct notifier_block dsa_notifier; + unsigned int per_port_num_tx_queues; + unsigned long queue_bitmap; + struct bcm_sysport_tx_ring *ring_map[DSA_MAX_PORTS * 8]; + }; #endif /* __BCM_SYSPORT_H */ diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c index 6322594ab260..6fe074c1588b 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c @@ -184,13 +184,19 @@ static int bgmac_probe(struct bcma_device *core) if (!bgmac_is_bcm4707_family(core) && !(ci->id == BCMA_CHIP_ID_BCM53573 && core->core_unit == 1)) { + struct phy_device *phydev; + mii_bus = bcma_mdio_mii_register(bgmac); if (IS_ERR(mii_bus)) { err = PTR_ERR(mii_bus); goto err; } - bgmac->mii_bus = mii_bus; + + phydev = mdiobus_get_phy(bgmac->mii_bus, bgmac->phyaddr); + if (ci->id == BCMA_CHIP_ID_BCM53573 && phydev && + (phydev->drv->phy_id & phydev->drv->phy_id_mask) == PHY_ID_BCM54210E) + phydev->dev_flags |= PHY_BRCM_EN_MASTER_MODE; } if (core->bus->hosttype == BCMA_HOSTTYPE_PCI) { diff --git a/drivers/net/ethernet/broadcom/bnxt/Makefile b/drivers/net/ethernet/broadcom/bnxt/Makefile index 4f0cb8e1ffc0..457201f409a7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/Makefile +++ b/drivers/net/ethernet/broadcom/bnxt/Makefile @@ -1,3 +1,4 @@ obj-$(CONFIG_BNXT) += bnxt_en.o -bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o bnxt_tc.o +bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o +bnxt_en-$(CONFIG_BNXT_FLOWER_OFFLOAD) += bnxt_tc.o diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 7dd3d131043a..4730c048ed9b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -23,8 +23,6 @@ #include "bnxt_tc.h" #include "bnxt_vfr.h" -#ifdef CONFIG_BNXT_FLOWER_OFFLOAD - #define BNXT_FID_INVALID 0xffff #define VLAN_TCI(vid, prio) ((vid) | ((prio) << VLAN_PRIO_SHIFT)) @@ -833,6 +831,3 @@ void bnxt_shutdown_tc(struct bnxt *bp) rhashtable_destroy(&tc_info->flow_table); rhashtable_destroy(&tc_info->l2_table); } - -#else -#endif diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index 6e13c937d715..a843076597ec 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -1693,9 +1693,9 @@ err_return: /* Timer callbacks */ /* a) IOC timer */ static void -bnad_ioc_timeout(unsigned long data) +bnad_ioc_timeout(struct timer_list *t) { - struct bnad *bnad = (struct bnad *)data; + struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.ioc_timer); unsigned long flags; spin_lock_irqsave(&bnad->bna_lock, flags); @@ -1704,9 +1704,9 @@ bnad_ioc_timeout(unsigned long data) } static void -bnad_ioc_hb_check(unsigned long data) +bnad_ioc_hb_check(struct timer_list *t) { - struct bnad *bnad = (struct bnad *)data; + struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.hb_timer); unsigned long flags; spin_lock_irqsave(&bnad->bna_lock, flags); @@ -1715,9 +1715,9 @@ bnad_ioc_hb_check(unsigned long data) } static void -bnad_iocpf_timeout(unsigned long data) +bnad_iocpf_timeout(struct timer_list *t) { - struct bnad *bnad = (struct bnad *)data; + struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.iocpf_timer); unsigned long flags; spin_lock_irqsave(&bnad->bna_lock, flags); @@ -1726,9 +1726,9 @@ bnad_iocpf_timeout(unsigned long data) } static void -bnad_iocpf_sem_timeout(unsigned long data) +bnad_iocpf_sem_timeout(struct timer_list *t) { - struct bnad *bnad = (struct bnad *)data; + struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.sem_timer); unsigned long flags; spin_lock_irqsave(&bnad->bna_lock, flags); @@ -1748,9 +1748,9 @@ bnad_iocpf_sem_timeout(unsigned long data) /* b) Dynamic Interrupt Moderation Timer */ static void -bnad_dim_timeout(unsigned long data) +bnad_dim_timeout(struct timer_list *t) { - struct bnad *bnad = (struct bnad *)data; + struct bnad *bnad = from_timer(bnad, t, dim_timer); struct bnad_rx_info *rx_info; struct bnad_rx_ctrl *rx_ctrl; int i, j; @@ -1781,9 +1781,9 @@ bnad_dim_timeout(unsigned long data) /* c) Statistics Timer */ static void -bnad_stats_timeout(unsigned long data) +bnad_stats_timeout(struct timer_list *t) { - struct bnad *bnad = (struct bnad *)data; + struct bnad *bnad = from_timer(bnad, t, stats_timer); unsigned long flags; if (!netif_running(bnad->netdev) || @@ -1804,8 +1804,7 @@ bnad_dim_timer_start(struct bnad *bnad) { if (bnad->cfg_flags & BNAD_CF_DIM_ENABLED && !test_bit(BNAD_RF_DIM_TIMER_RUNNING, &bnad->run_flags)) { - setup_timer(&bnad->dim_timer, bnad_dim_timeout, - (unsigned long)bnad); + timer_setup(&bnad->dim_timer, bnad_dim_timeout, 0); set_bit(BNAD_RF_DIM_TIMER_RUNNING, &bnad->run_flags); mod_timer(&bnad->dim_timer, jiffies + msecs_to_jiffies(BNAD_DIM_TIMER_FREQ)); @@ -1823,8 +1822,7 @@ bnad_stats_timer_start(struct bnad *bnad) spin_lock_irqsave(&bnad->bna_lock, flags); if (!test_and_set_bit(BNAD_RF_STATS_TIMER_RUNNING, &bnad->run_flags)) { - setup_timer(&bnad->stats_timer, bnad_stats_timeout, - (unsigned long)bnad); + timer_setup(&bnad->stats_timer, bnad_stats_timeout, 0); mod_timer(&bnad->stats_timer, jiffies + msecs_to_jiffies(BNAD_STATS_TIMER_FREQ)); } @@ -3692,14 +3690,11 @@ bnad_pci_probe(struct pci_dev *pdev, goto res_free; /* Set up timers */ - setup_timer(&bnad->bna.ioceth.ioc.ioc_timer, bnad_ioc_timeout, - (unsigned long)bnad); - setup_timer(&bnad->bna.ioceth.ioc.hb_timer, bnad_ioc_hb_check, - (unsigned long)bnad); - setup_timer(&bnad->bna.ioceth.ioc.iocpf_timer, bnad_iocpf_timeout, - (unsigned long)bnad); - setup_timer(&bnad->bna.ioceth.ioc.sem_timer, bnad_iocpf_sem_timeout, - (unsigned long)bnad); + timer_setup(&bnad->bna.ioceth.ioc.ioc_timer, bnad_ioc_timeout, 0); + timer_setup(&bnad->bna.ioceth.ioc.hb_timer, bnad_ioc_hb_check, 0); + timer_setup(&bnad->bna.ioceth.ioc.iocpf_timer, bnad_iocpf_timeout, 0); + timer_setup(&bnad->bna.ioceth.ioc.sem_timer, bnad_iocpf_sem_timeout, + 0); /* * Start the chip diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index 2e993ce43b66..4c3b5688529b 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -435,8 +435,7 @@ static void delete_glists(struct lio *lio) do { g = (struct octnic_gather *) list_delete_head(&lio->glist[i]); - if (g) - kfree(g); + kfree(g); } while (g); if (lio->glists_virt_base && lio->glists_virt_base[i] && @@ -748,7 +747,7 @@ static void octeon_destroy_resources(struct octeon_device *oct) if (lio_wait_for_oq_pkts(oct)) dev_err(&oct->pci_dev->dev, "OQ had pending packets\n"); - + /* fall through */ case OCT_DEV_INTR_SET_DONE: /* Disable interrupts */ oct->fn_list.disable_interrupt(oct, OCTEON_ALL_INTR); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index d68478afccbf..71989e180289 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -566,8 +566,10 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, return true; default: bpf_warn_invalid_xdp_action(action); + /* fall through */ case XDP_ABORTED: trace_xdp_exception(nic->netdev, prog, action); + /* fall through */ case XDP_DROP: /* Check if it's a recycled page, if not * unmap the DMA mapping. diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c index 75e439918700..30de26ef3da4 100644 --- a/drivers/net/ethernet/chelsio/cxgb/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb/sge.c @@ -1882,10 +1882,10 @@ send: /* * Callback for the Tx buffer reclaim timer. Runs with softirqs disabled. */ -static void sge_tx_reclaim_cb(unsigned long data) +static void sge_tx_reclaim_cb(struct timer_list *t) { int i; - struct sge *sge = (struct sge *)data; + struct sge *sge = from_timer(sge, t, tx_reclaim_timer); for (i = 0; i < SGE_CMDQ_N; ++i) { struct cmdQ *q = &sge->cmdQ[i]; @@ -1978,10 +1978,10 @@ void t1_sge_start(struct sge *sge) /* * Callback for the T2 ESPI 'stuck packet feature' workaorund */ -static void espibug_workaround_t204(unsigned long data) +static void espibug_workaround_t204(struct timer_list *t) { - struct adapter *adapter = (struct adapter *)data; - struct sge *sge = adapter->sge; + struct sge *sge = from_timer(sge, t, espibug_timer); + struct adapter *adapter = sge->adapter; unsigned int nports = adapter->params.nports; u32 seop[MAX_NPORTS]; @@ -2021,10 +2021,10 @@ static void espibug_workaround_t204(unsigned long data) mod_timer(&sge->espibug_timer, jiffies + sge->espibug_timeout); } -static void espibug_workaround(unsigned long data) +static void espibug_workaround(struct timer_list *t) { - struct adapter *adapter = (struct adapter *)data; - struct sge *sge = adapter->sge; + struct sge *sge = from_timer(sge, t, espibug_timer); + struct adapter *adapter = sge->adapter; if (netif_running(adapter->port[0].dev)) { struct sk_buff *skb = sge->espibug_skb[0]; @@ -2075,18 +2075,15 @@ struct sge *t1_sge_create(struct adapter *adapter, struct sge_params *p) goto nomem_port; } - setup_timer(&sge->tx_reclaim_timer, sge_tx_reclaim_cb, - (unsigned long)sge); + timer_setup(&sge->tx_reclaim_timer, sge_tx_reclaim_cb, 0); if (is_T2(sge->adapter)) { - init_timer(&sge->espibug_timer); + timer_setup(&sge->espibug_timer, + adapter->params.nports > 1 ? espibug_workaround_t204 : espibug_workaround, + 0); - if (adapter->params.nports > 1) { + if (adapter->params.nports > 1) tx_sched_init(sge); - sge->espibug_timer.function = espibug_workaround_t204; - } else - sge->espibug_timer.function = espibug_workaround; - sge->espibug_timer.data = (unsigned long)sge->adapter; sge->espibug_timeout = 1; /* for T204, every 10ms */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/Makefile b/drivers/net/ethernet/chelsio/cxgb4/Makefile index fecd7aab673b..43c86b74dfb8 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/Makefile +++ b/drivers/net/ethernet/chelsio/cxgb4/Makefile @@ -4,9 +4,10 @@ obj-$(CONFIG_CHELSIO_T4) += cxgb4.o -cxgb4-objs := cxgb4_main.o l2t.o t4_hw.o sge.o clip_tbl.o cxgb4_ethtool.o \ +cxgb4-objs := cxgb4_main.o l2t.o smt.o t4_hw.o sge.o clip_tbl.o cxgb4_ethtool.o \ cxgb4_uld.o sched.o cxgb4_filter.o cxgb4_tc_u32.o \ - cxgb4_ptp.o cxgb4_tc_flower.o + cxgb4_ptp.o cxgb4_tc_flower.o cxgb4_cudbg.o \ + cudbg_common.o cudbg_lib.o cxgb4-$(CONFIG_CHELSIO_T4_DCB) += cxgb4_dcb.o cxgb4-$(CONFIG_CHELSIO_T4_FCOE) += cxgb4_fcoe.o cxgb4-$(CONFIG_DEBUG_FS) += cxgb4_debugfs.o diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_common.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_common.c new file mode 100644 index 000000000000..f78ba1743b5a --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_common.c @@ -0,0 +1,54 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#include "cxgb4.h" +#include "cudbg_if.h" +#include "cudbg_lib_common.h" + +int cudbg_get_buff(struct cudbg_buffer *pdbg_buff, u32 size, + struct cudbg_buffer *pin_buff) +{ + u32 offset; + + offset = pdbg_buff->offset; + if (offset + size > pdbg_buff->size) + return CUDBG_STATUS_NO_MEM; + + pin_buff->data = (char *)pdbg_buff->data + offset; + pin_buff->offset = offset; + pin_buff->size = size; + pdbg_buff->size -= size; + return 0; +} + +void cudbg_put_buff(struct cudbg_buffer *pin_buff, + struct cudbg_buffer *pdbg_buff) +{ + pdbg_buff->size += pin_buff->size; + pin_buff->data = NULL; + pin_buff->offset = 0; + pin_buff->size = 0; +} + +void cudbg_update_buff(struct cudbg_buffer *pin_buff, + struct cudbg_buffer *pout_buff) +{ + /* We already write to buffer provided by ethool, so just + * increment offset to next free space. + */ + pout_buff->offset += pin_buff->size; +} diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h new file mode 100644 index 000000000000..d7f3392f618f --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h @@ -0,0 +1,181 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#ifndef __CUDBG_ENTITY_H__ +#define __CUDBG_ENTITY_H__ + +#define EDC0_FLAG 3 +#define EDC1_FLAG 4 + +struct card_mem { + u16 size_edc0; + u16 size_edc1; + u16 mem_flag; +}; + +struct cudbg_mbox_log { + struct mbox_cmd entry; + u32 hi[MBOX_LEN / 8]; + u32 lo[MBOX_LEN / 8]; +}; + +struct ireg_field { + u32 ireg_addr; + u32 ireg_data; + u32 ireg_local_offset; + u32 ireg_offset_range; +}; + +struct ireg_buf { + struct ireg_field tp_pio; + u32 outbuf[32]; +}; + +#define IREG_NUM_ELEM 4 + +static const u32 t6_tp_pio_array[][IREG_NUM_ELEM] = { + {0x7e40, 0x7e44, 0x020, 28}, /* t6_tp_pio_regs_20_to_3b */ + {0x7e40, 0x7e44, 0x040, 10}, /* t6_tp_pio_regs_40_to_49 */ + {0x7e40, 0x7e44, 0x050, 10}, /* t6_tp_pio_regs_50_to_59 */ + {0x7e40, 0x7e44, 0x060, 14}, /* t6_tp_pio_regs_60_to_6d */ + {0x7e40, 0x7e44, 0x06F, 1}, /* t6_tp_pio_regs_6f */ + {0x7e40, 0x7e44, 0x070, 6}, /* t6_tp_pio_regs_70_to_75 */ + {0x7e40, 0x7e44, 0x130, 18}, /* t6_tp_pio_regs_130_to_141 */ + {0x7e40, 0x7e44, 0x145, 19}, /* t6_tp_pio_regs_145_to_157 */ + {0x7e40, 0x7e44, 0x160, 1}, /* t6_tp_pio_regs_160 */ + {0x7e40, 0x7e44, 0x230, 25}, /* t6_tp_pio_regs_230_to_248 */ + {0x7e40, 0x7e44, 0x24a, 3}, /* t6_tp_pio_regs_24c */ + {0x7e40, 0x7e44, 0x8C0, 1} /* t6_tp_pio_regs_8c0 */ +}; + +static const u32 t5_tp_pio_array[][IREG_NUM_ELEM] = { + {0x7e40, 0x7e44, 0x020, 28}, /* t5_tp_pio_regs_20_to_3b */ + {0x7e40, 0x7e44, 0x040, 19}, /* t5_tp_pio_regs_40_to_52 */ + {0x7e40, 0x7e44, 0x054, 2}, /* t5_tp_pio_regs_54_to_55 */ + {0x7e40, 0x7e44, 0x060, 13}, /* t5_tp_pio_regs_60_to_6c */ + {0x7e40, 0x7e44, 0x06F, 1}, /* t5_tp_pio_regs_6f */ + {0x7e40, 0x7e44, 0x120, 4}, /* t5_tp_pio_regs_120_to_123 */ + {0x7e40, 0x7e44, 0x12b, 2}, /* t5_tp_pio_regs_12b_to_12c */ + {0x7e40, 0x7e44, 0x12f, 21}, /* t5_tp_pio_regs_12f_to_143 */ + {0x7e40, 0x7e44, 0x145, 19}, /* t5_tp_pio_regs_145_to_157 */ + {0x7e40, 0x7e44, 0x230, 25}, /* t5_tp_pio_regs_230_to_248 */ + {0x7e40, 0x7e44, 0x8C0, 1} /* t5_tp_pio_regs_8c0 */ +}; + +static const u32 t6_tp_tm_pio_array[][IREG_NUM_ELEM] = { + {0x7e18, 0x7e1c, 0x0, 12} +}; + +static const u32 t5_tp_tm_pio_array[][IREG_NUM_ELEM] = { + {0x7e18, 0x7e1c, 0x0, 12} +}; + +static const u32 t6_tp_mib_index_array[6][IREG_NUM_ELEM] = { + {0x7e50, 0x7e54, 0x0, 13}, + {0x7e50, 0x7e54, 0x10, 6}, + {0x7e50, 0x7e54, 0x18, 21}, + {0x7e50, 0x7e54, 0x30, 32}, + {0x7e50, 0x7e54, 0x50, 22}, + {0x7e50, 0x7e54, 0x68, 12} +}; + +static const u32 t5_tp_mib_index_array[9][IREG_NUM_ELEM] = { + {0x7e50, 0x7e54, 0x0, 13}, + {0x7e50, 0x7e54, 0x10, 6}, + {0x7e50, 0x7e54, 0x18, 8}, + {0x7e50, 0x7e54, 0x20, 13}, + {0x7e50, 0x7e54, 0x30, 16}, + {0x7e50, 0x7e54, 0x40, 16}, + {0x7e50, 0x7e54, 0x50, 16}, + {0x7e50, 0x7e54, 0x60, 6}, + {0x7e50, 0x7e54, 0x68, 4} +}; + +static const u32 t5_sge_dbg_index_array[2][IREG_NUM_ELEM] = { + {0x10cc, 0x10d0, 0x0, 16}, + {0x10cc, 0x10d4, 0x0, 16}, +}; + +static const u32 t5_pcie_pdbg_array[][IREG_NUM_ELEM] = { + {0x5a04, 0x5a0c, 0x00, 0x20}, /* t5_pcie_pdbg_regs_00_to_20 */ + {0x5a04, 0x5a0c, 0x21, 0x20}, /* t5_pcie_pdbg_regs_21_to_40 */ + {0x5a04, 0x5a0c, 0x41, 0x10}, /* t5_pcie_pdbg_regs_41_to_50 */ +}; + +static const u32 t5_pcie_cdbg_array[][IREG_NUM_ELEM] = { + {0x5a10, 0x5a18, 0x00, 0x20}, /* t5_pcie_cdbg_regs_00_to_20 */ + {0x5a10, 0x5a18, 0x21, 0x18}, /* t5_pcie_cdbg_regs_21_to_37 */ +}; + +static const u32 t5_pm_rx_array[][IREG_NUM_ELEM] = { + {0x8FD0, 0x8FD4, 0x10000, 0x20}, /* t5_pm_rx_regs_10000_to_10020 */ + {0x8FD0, 0x8FD4, 0x10021, 0x0D}, /* t5_pm_rx_regs_10021_to_1002c */ +}; + +static const u32 t5_pm_tx_array[][IREG_NUM_ELEM] = { + {0x8FF0, 0x8FF4, 0x10000, 0x20}, /* t5_pm_tx_regs_10000_to_10020 */ + {0x8FF0, 0x8FF4, 0x10021, 0x1D}, /* t5_pm_tx_regs_10021_to_1003c */ +}; + +static const u32 t6_ma_ireg_array[][IREG_NUM_ELEM] = { + {0x78f8, 0x78fc, 0xa000, 23}, /* t6_ma_regs_a000_to_a016 */ + {0x78f8, 0x78fc, 0xa400, 30}, /* t6_ma_regs_a400_to_a41e */ + {0x78f8, 0x78fc, 0xa800, 20} /* t6_ma_regs_a800_to_a813 */ +}; + +static const u32 t6_ma_ireg_array2[][IREG_NUM_ELEM] = { + {0x78f8, 0x78fc, 0xe400, 17}, /* t6_ma_regs_e400_to_e600 */ + {0x78f8, 0x78fc, 0xe640, 13} /* t6_ma_regs_e640_to_e7c0 */ +}; + +static const u32 t6_up_cim_reg_array[][IREG_NUM_ELEM] = { + {0x7b50, 0x7b54, 0x2000, 0x20}, /* up_cim_2000_to_207c */ + {0x7b50, 0x7b54, 0x2080, 0x1d}, /* up_cim_2080_to_20fc */ + {0x7b50, 0x7b54, 0x00, 0x20}, /* up_cim_00_to_7c */ + {0x7b50, 0x7b54, 0x80, 0x20}, /* up_cim_80_to_fc */ + {0x7b50, 0x7b54, 0x100, 0x11}, /* up_cim_100_to_14c */ + {0x7b50, 0x7b54, 0x200, 0x10}, /* up_cim_200_to_23c */ + {0x7b50, 0x7b54, 0x240, 0x2}, /* up_cim_240_to_244 */ + {0x7b50, 0x7b54, 0x250, 0x2}, /* up_cim_250_to_254 */ + {0x7b50, 0x7b54, 0x260, 0x2}, /* up_cim_260_to_264 */ + {0x7b50, 0x7b54, 0x270, 0x2}, /* up_cim_270_to_274 */ + {0x7b50, 0x7b54, 0x280, 0x20}, /* up_cim_280_to_2fc */ + {0x7b50, 0x7b54, 0x300, 0x20}, /* up_cim_300_to_37c */ + {0x7b50, 0x7b54, 0x380, 0x14}, /* up_cim_380_to_3cc */ + +}; + +static const u32 t5_up_cim_reg_array[][IREG_NUM_ELEM] = { + {0x7b50, 0x7b54, 0x2000, 0x20}, /* up_cim_2000_to_207c */ + {0x7b50, 0x7b54, 0x2080, 0x19}, /* up_cim_2080_to_20ec */ + {0x7b50, 0x7b54, 0x00, 0x20}, /* up_cim_00_to_7c */ + {0x7b50, 0x7b54, 0x80, 0x20}, /* up_cim_80_to_fc */ + {0x7b50, 0x7b54, 0x100, 0x11}, /* up_cim_100_to_14c */ + {0x7b50, 0x7b54, 0x200, 0x10}, /* up_cim_200_to_23c */ + {0x7b50, 0x7b54, 0x240, 0x2}, /* up_cim_240_to_244 */ + {0x7b50, 0x7b54, 0x250, 0x2}, /* up_cim_250_to_254 */ + {0x7b50, 0x7b54, 0x260, 0x2}, /* up_cim_260_to_264 */ + {0x7b50, 0x7b54, 0x270, 0x2}, /* up_cim_270_to_274 */ + {0x7b50, 0x7b54, 0x280, 0x20}, /* up_cim_280_to_2fc */ + {0x7b50, 0x7b54, 0x300, 0x20}, /* up_cim_300_to_37c */ + {0x7b50, 0x7b54, 0x380, 0x14}, /* up_cim_380_to_3cc */ +}; + +static const u32 t6_hma_ireg_array[][IREG_NUM_ELEM] = { + {0x51320, 0x51324, 0xa000, 32} /* t6_hma_regs_a000_to_a01f */ +}; +#endif /* __CUDBG_ENTITY_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h new file mode 100644 index 000000000000..9b8005e67811 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h @@ -0,0 +1,69 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#ifndef __CUDBG_IF_H__ +#define __CUDBG_IF_H__ + +/* Error codes */ +#define CUDBG_STATUS_NO_MEM -19 +#define CUDBG_STATUS_ENTITY_NOT_FOUND -24 +#define CUDBG_SYSTEM_ERROR -29 + +#define CUDBG_MAJOR_VERSION 1 +#define CUDBG_MINOR_VERSION 14 + +enum cudbg_dbg_entity_type { + CUDBG_REG_DUMP = 1, + CUDBG_DEV_LOG = 2, + CUDBG_CIM_IBQ_TP0 = 6, + CUDBG_CIM_IBQ_TP1 = 7, + CUDBG_CIM_IBQ_ULP = 8, + CUDBG_CIM_IBQ_SGE0 = 9, + CUDBG_CIM_IBQ_SGE1 = 10, + CUDBG_CIM_IBQ_NCSI = 11, + CUDBG_CIM_OBQ_ULP0 = 12, + CUDBG_CIM_OBQ_ULP1 = 13, + CUDBG_CIM_OBQ_ULP2 = 14, + CUDBG_CIM_OBQ_ULP3 = 15, + CUDBG_CIM_OBQ_SGE = 16, + CUDBG_CIM_OBQ_NCSI = 17, + CUDBG_EDC0 = 18, + CUDBG_EDC1 = 19, + CUDBG_TP_INDIRECT = 36, + CUDBG_SGE_INDIRECT = 37, + CUDBG_CIM_OBQ_RXQ0 = 47, + CUDBG_CIM_OBQ_RXQ1 = 48, + CUDBG_PCIE_INDIRECT = 50, + CUDBG_PM_INDIRECT = 51, + CUDBG_MA_INDIRECT = 61, + CUDBG_UP_CIM_INDIRECT = 64, + CUDBG_MBOX_LOG = 66, + CUDBG_HMA_INDIRECT = 67, + CUDBG_MAX_ENTITY = 70, +}; + +struct cudbg_init { + struct adapter *adap; /* Pointer to adapter structure */ + void *outbuf; /* Output buffer */ + u32 outbuf_size; /* Output buffer size */ +}; + +static inline unsigned int cudbg_mbytes_to_bytes(unsigned int size) +{ + return size * 1024 * 1024; +} +#endif /* __CUDBG_IF_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c new file mode 100644 index 000000000000..c451b2e42a6c --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -0,0 +1,867 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#include "t4_regs.h" +#include "cxgb4.h" +#include "cudbg_if.h" +#include "cudbg_lib_common.h" +#include "cudbg_lib.h" +#include "cudbg_entity.h" + +static void cudbg_write_and_release_buff(struct cudbg_buffer *pin_buff, + struct cudbg_buffer *dbg_buff) +{ + cudbg_update_buff(pin_buff, dbg_buff); + cudbg_put_buff(pin_buff, dbg_buff); +} + +static int is_fw_attached(struct cudbg_init *pdbg_init) +{ + struct adapter *padap = pdbg_init->adap; + + if (!(padap->flags & FW_OK) || padap->use_bd) + return 0; + + return 1; +} + +/* This function will add additional padding bytes into debug_buffer to make it + * 4 byte aligned. + */ +void cudbg_align_debug_buffer(struct cudbg_buffer *dbg_buff, + struct cudbg_entity_hdr *entity_hdr) +{ + u8 zero_buf[4] = {0}; + u8 padding, remain; + + remain = (dbg_buff->offset - entity_hdr->start_offset) % 4; + padding = 4 - remain; + if (remain) { + memcpy(((u8 *)dbg_buff->data) + dbg_buff->offset, &zero_buf, + padding); + dbg_buff->offset += padding; + entity_hdr->num_pad = padding; + } + entity_hdr->size = dbg_buff->offset - entity_hdr->start_offset; +} + +struct cudbg_entity_hdr *cudbg_get_entity_hdr(void *outbuf, int i) +{ + struct cudbg_hdr *cudbg_hdr = (struct cudbg_hdr *)outbuf; + + return (struct cudbg_entity_hdr *) + ((char *)outbuf + cudbg_hdr->hdr_len + + (sizeof(struct cudbg_entity_hdr) * (i - 1))); +} + +int cudbg_collect_reg_dump(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + u32 buf_size = 0; + int rc = 0; + + if (is_t4(padap->params.chip)) + buf_size = T4_REGMAP_SIZE; + else if (is_t5(padap->params.chip) || is_t6(padap->params.chip)) + buf_size = T5_REGMAP_SIZE; + + rc = cudbg_get_buff(dbg_buff, buf_size, &temp_buff); + if (rc) + return rc; + t4_get_regs(padap, (void *)temp_buff.data, temp_buff.size); + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_fw_devlog(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct devlog_params *dparams; + int rc = 0; + + rc = t4_init_devlog_params(padap); + if (rc < 0) { + cudbg_err->sys_err = rc; + return rc; + } + + dparams = &padap->params.devlog; + rc = cudbg_get_buff(dbg_buff, dparams->size, &temp_buff); + if (rc) + return rc; + + /* Collect FW devlog */ + if (dparams->start != 0) { + spin_lock(&padap->win0_lock); + rc = t4_memory_rw(padap, padap->params.drv_memwin, + dparams->memtype, dparams->start, + dparams->size, + (__be32 *)(char *)temp_buff.data, + 1); + spin_unlock(&padap->win0_lock); + if (rc) { + cudbg_err->sys_err = rc; + cudbg_put_buff(&temp_buff, dbg_buff); + return rc; + } + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +static int cudbg_read_cim_ibq(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err, int qid) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + int no_of_read_words, rc = 0; + u32 qsize; + + /* collect CIM IBQ */ + qsize = CIM_IBQ_SIZE * 4 * sizeof(u32); + rc = cudbg_get_buff(dbg_buff, qsize, &temp_buff); + if (rc) + return rc; + + /* t4_read_cim_ibq will return no. of read words or error */ + no_of_read_words = t4_read_cim_ibq(padap, qid, + (u32 *)((u32 *)temp_buff.data + + temp_buff.offset), qsize); + /* no_of_read_words is less than or equal to 0 means error */ + if (no_of_read_words <= 0) { + if (!no_of_read_words) + rc = CUDBG_SYSTEM_ERROR; + else + rc = no_of_read_words; + cudbg_err->sys_err = rc; + cudbg_put_buff(&temp_buff, dbg_buff); + return rc; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_cim_ibq_tp0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 0); +} + +int cudbg_collect_cim_ibq_tp1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 1); +} + +int cudbg_collect_cim_ibq_ulp(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 2); +} + +int cudbg_collect_cim_ibq_sge0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 3); +} + +int cudbg_collect_cim_ibq_sge1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 4); +} + +int cudbg_collect_cim_ibq_ncsi(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 5); +} + +static int cudbg_read_cim_obq(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err, int qid) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + int no_of_read_words, rc = 0; + u32 qsize; + + /* collect CIM OBQ */ + qsize = 6 * CIM_OBQ_SIZE * 4 * sizeof(u32); + rc = cudbg_get_buff(dbg_buff, qsize, &temp_buff); + if (rc) + return rc; + + /* t4_read_cim_obq will return no. of read words or error */ + no_of_read_words = t4_read_cim_obq(padap, qid, + (u32 *)((u32 *)temp_buff.data + + temp_buff.offset), qsize); + /* no_of_read_words is less than or equal to 0 means error */ + if (no_of_read_words <= 0) { + if (!no_of_read_words) + rc = CUDBG_SYSTEM_ERROR; + else + rc = no_of_read_words; + cudbg_err->sys_err = rc; + cudbg_put_buff(&temp_buff, dbg_buff); + return rc; + } + temp_buff.size = no_of_read_words * 4; + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_cim_obq_ulp0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 0); +} + +int cudbg_collect_cim_obq_ulp1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 1); +} + +int cudbg_collect_cim_obq_ulp2(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 2); +} + +int cudbg_collect_cim_obq_ulp3(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 3); +} + +int cudbg_collect_cim_obq_sge(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 4); +} + +int cudbg_collect_cim_obq_ncsi(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 5); +} + +int cudbg_collect_obq_sge_rx_q0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 6); +} + +int cudbg_collect_obq_sge_rx_q1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 7); +} + +static int cudbg_read_fw_mem(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, u8 mem_type, + unsigned long tot_len, + struct cudbg_error *cudbg_err) +{ + unsigned long bytes, bytes_left, bytes_read = 0; + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + int rc = 0; + + bytes_left = tot_len; + while (bytes_left > 0) { + bytes = min_t(unsigned long, bytes_left, + (unsigned long)CUDBG_CHUNK_SIZE); + rc = cudbg_get_buff(dbg_buff, bytes, &temp_buff); + if (rc) + return rc; + spin_lock(&padap->win0_lock); + rc = t4_memory_rw(padap, MEMWIN_NIC, mem_type, + bytes_read, bytes, + (__be32 *)temp_buff.data, + 1); + spin_unlock(&padap->win0_lock); + if (rc) { + cudbg_err->sys_err = rc; + cudbg_put_buff(&temp_buff, dbg_buff); + return rc; + } + bytes_left -= bytes; + bytes_read += bytes; + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + } + return rc; +} + +static void cudbg_collect_mem_info(struct cudbg_init *pdbg_init, + struct card_mem *mem_info) +{ + struct adapter *padap = pdbg_init->adap; + u32 value; + + value = t4_read_reg(padap, MA_EDRAM0_BAR_A); + value = EDRAM0_SIZE_G(value); + mem_info->size_edc0 = (u16)value; + + value = t4_read_reg(padap, MA_EDRAM1_BAR_A); + value = EDRAM1_SIZE_G(value); + mem_info->size_edc1 = (u16)value; + + value = t4_read_reg(padap, MA_TARGET_MEM_ENABLE_A); + if (value & EDRAM0_ENABLE_F) + mem_info->mem_flag |= (1 << EDC0_FLAG); + if (value & EDRAM1_ENABLE_F) + mem_info->mem_flag |= (1 << EDC1_FLAG); +} + +static void cudbg_t4_fwcache(struct cudbg_init *pdbg_init, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + int rc; + + if (is_fw_attached(pdbg_init)) { + /* Flush uP dcache before reading edcX/mcX */ + rc = t4_fwcache(padap, FW_PARAM_DEV_FWCACHE_FLUSH); + if (rc) + cudbg_err->sys_warn = rc; + } +} + +static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err, + u8 mem_type) +{ + struct card_mem mem_info = {0}; + unsigned long flag, size; + int rc; + + cudbg_t4_fwcache(pdbg_init, cudbg_err); + cudbg_collect_mem_info(pdbg_init, &mem_info); + switch (mem_type) { + case MEM_EDC0: + flag = (1 << EDC0_FLAG); + size = cudbg_mbytes_to_bytes(mem_info.size_edc0); + break; + case MEM_EDC1: + flag = (1 << EDC1_FLAG); + size = cudbg_mbytes_to_bytes(mem_info.size_edc1); + break; + default: + rc = CUDBG_STATUS_ENTITY_NOT_FOUND; + goto err; + } + + if (mem_info.mem_flag & flag) { + rc = cudbg_read_fw_mem(pdbg_init, dbg_buff, mem_type, + size, cudbg_err); + if (rc) + goto err; + } else { + rc = CUDBG_STATUS_ENTITY_NOT_FOUND; + goto err; + } +err: + return rc; +} + +int cudbg_collect_edc0_meminfo(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_collect_mem_region(pdbg_init, dbg_buff, cudbg_err, + MEM_EDC0); +} + +int cudbg_collect_edc1_meminfo(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_collect_mem_region(pdbg_init, dbg_buff, cudbg_err, + MEM_EDC1); +} + +int cudbg_collect_tp_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct ireg_buf *ch_tp_pio; + int i, rc, n = 0; + u32 size; + + if (is_t5(padap->params.chip)) + n = sizeof(t5_tp_pio_array) + + sizeof(t5_tp_tm_pio_array) + + sizeof(t5_tp_mib_index_array); + else + n = sizeof(t6_tp_pio_array) + + sizeof(t6_tp_tm_pio_array) + + sizeof(t6_tp_mib_index_array); + + n = n / (IREG_NUM_ELEM * sizeof(u32)); + size = sizeof(struct ireg_buf) * n; + rc = cudbg_get_buff(dbg_buff, size, &temp_buff); + if (rc) + return rc; + + ch_tp_pio = (struct ireg_buf *)temp_buff.data; + + /* TP_PIO */ + if (is_t5(padap->params.chip)) + n = sizeof(t5_tp_pio_array) / (IREG_NUM_ELEM * sizeof(u32)); + else if (is_t6(padap->params.chip)) + n = sizeof(t6_tp_pio_array) / (IREG_NUM_ELEM * sizeof(u32)); + + for (i = 0; i < n; i++) { + struct ireg_field *tp_pio = &ch_tp_pio->tp_pio; + u32 *buff = ch_tp_pio->outbuf; + + if (is_t5(padap->params.chip)) { + tp_pio->ireg_addr = t5_tp_pio_array[i][0]; + tp_pio->ireg_data = t5_tp_pio_array[i][1]; + tp_pio->ireg_local_offset = t5_tp_pio_array[i][2]; + tp_pio->ireg_offset_range = t5_tp_pio_array[i][3]; + } else if (is_t6(padap->params.chip)) { + tp_pio->ireg_addr = t6_tp_pio_array[i][0]; + tp_pio->ireg_data = t6_tp_pio_array[i][1]; + tp_pio->ireg_local_offset = t6_tp_pio_array[i][2]; + tp_pio->ireg_offset_range = t6_tp_pio_array[i][3]; + } + t4_tp_pio_read(padap, buff, tp_pio->ireg_offset_range, + tp_pio->ireg_local_offset, true); + ch_tp_pio++; + } + + /* TP_TM_PIO */ + if (is_t5(padap->params.chip)) + n = sizeof(t5_tp_tm_pio_array) / (IREG_NUM_ELEM * sizeof(u32)); + else if (is_t6(padap->params.chip)) + n = sizeof(t6_tp_tm_pio_array) / (IREG_NUM_ELEM * sizeof(u32)); + + for (i = 0; i < n; i++) { + struct ireg_field *tp_pio = &ch_tp_pio->tp_pio; + u32 *buff = ch_tp_pio->outbuf; + + if (is_t5(padap->params.chip)) { + tp_pio->ireg_addr = t5_tp_tm_pio_array[i][0]; + tp_pio->ireg_data = t5_tp_tm_pio_array[i][1]; + tp_pio->ireg_local_offset = t5_tp_tm_pio_array[i][2]; + tp_pio->ireg_offset_range = t5_tp_tm_pio_array[i][3]; + } else if (is_t6(padap->params.chip)) { + tp_pio->ireg_addr = t6_tp_tm_pio_array[i][0]; + tp_pio->ireg_data = t6_tp_tm_pio_array[i][1]; + tp_pio->ireg_local_offset = t6_tp_tm_pio_array[i][2]; + tp_pio->ireg_offset_range = t6_tp_tm_pio_array[i][3]; + } + t4_tp_tm_pio_read(padap, buff, tp_pio->ireg_offset_range, + tp_pio->ireg_local_offset, true); + ch_tp_pio++; + } + + /* TP_MIB_INDEX */ + if (is_t5(padap->params.chip)) + n = sizeof(t5_tp_mib_index_array) / + (IREG_NUM_ELEM * sizeof(u32)); + else if (is_t6(padap->params.chip)) + n = sizeof(t6_tp_mib_index_array) / + (IREG_NUM_ELEM * sizeof(u32)); + + for (i = 0; i < n ; i++) { + struct ireg_field *tp_pio = &ch_tp_pio->tp_pio; + u32 *buff = ch_tp_pio->outbuf; + + if (is_t5(padap->params.chip)) { + tp_pio->ireg_addr = t5_tp_mib_index_array[i][0]; + tp_pio->ireg_data = t5_tp_mib_index_array[i][1]; + tp_pio->ireg_local_offset = + t5_tp_mib_index_array[i][2]; + tp_pio->ireg_offset_range = + t5_tp_mib_index_array[i][3]; + } else if (is_t6(padap->params.chip)) { + tp_pio->ireg_addr = t6_tp_mib_index_array[i][0]; + tp_pio->ireg_data = t6_tp_mib_index_array[i][1]; + tp_pio->ireg_local_offset = + t6_tp_mib_index_array[i][2]; + tp_pio->ireg_offset_range = + t6_tp_mib_index_array[i][3]; + } + t4_tp_mib_read(padap, buff, tp_pio->ireg_offset_range, + tp_pio->ireg_local_offset, true); + ch_tp_pio++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct ireg_buf *ch_sge_dbg; + int i, rc; + + rc = cudbg_get_buff(dbg_buff, sizeof(*ch_sge_dbg) * 2, &temp_buff); + if (rc) + return rc; + + ch_sge_dbg = (struct ireg_buf *)temp_buff.data; + for (i = 0; i < 2; i++) { + struct ireg_field *sge_pio = &ch_sge_dbg->tp_pio; + u32 *buff = ch_sge_dbg->outbuf; + + sge_pio->ireg_addr = t5_sge_dbg_index_array[i][0]; + sge_pio->ireg_data = t5_sge_dbg_index_array[i][1]; + sge_pio->ireg_local_offset = t5_sge_dbg_index_array[i][2]; + sge_pio->ireg_offset_range = t5_sge_dbg_index_array[i][3]; + t4_read_indirect(padap, + sge_pio->ireg_addr, + sge_pio->ireg_data, + buff, + sge_pio->ireg_offset_range, + sge_pio->ireg_local_offset); + ch_sge_dbg++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_pcie_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct ireg_buf *ch_pcie; + int i, rc, n; + u32 size; + + n = sizeof(t5_pcie_pdbg_array) / (IREG_NUM_ELEM * sizeof(u32)); + size = sizeof(struct ireg_buf) * n * 2; + rc = cudbg_get_buff(dbg_buff, size, &temp_buff); + if (rc) + return rc; + + ch_pcie = (struct ireg_buf *)temp_buff.data; + /* PCIE_PDBG */ + for (i = 0; i < n; i++) { + struct ireg_field *pcie_pio = &ch_pcie->tp_pio; + u32 *buff = ch_pcie->outbuf; + + pcie_pio->ireg_addr = t5_pcie_pdbg_array[i][0]; + pcie_pio->ireg_data = t5_pcie_pdbg_array[i][1]; + pcie_pio->ireg_local_offset = t5_pcie_pdbg_array[i][2]; + pcie_pio->ireg_offset_range = t5_pcie_pdbg_array[i][3]; + t4_read_indirect(padap, + pcie_pio->ireg_addr, + pcie_pio->ireg_data, + buff, + pcie_pio->ireg_offset_range, + pcie_pio->ireg_local_offset); + ch_pcie++; + } + + /* PCIE_CDBG */ + n = sizeof(t5_pcie_cdbg_array) / (IREG_NUM_ELEM * sizeof(u32)); + for (i = 0; i < n; i++) { + struct ireg_field *pcie_pio = &ch_pcie->tp_pio; + u32 *buff = ch_pcie->outbuf; + + pcie_pio->ireg_addr = t5_pcie_cdbg_array[i][0]; + pcie_pio->ireg_data = t5_pcie_cdbg_array[i][1]; + pcie_pio->ireg_local_offset = t5_pcie_cdbg_array[i][2]; + pcie_pio->ireg_offset_range = t5_pcie_cdbg_array[i][3]; + t4_read_indirect(padap, + pcie_pio->ireg_addr, + pcie_pio->ireg_data, + buff, + pcie_pio->ireg_offset_range, + pcie_pio->ireg_local_offset); + ch_pcie++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_pm_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct ireg_buf *ch_pm; + int i, rc, n; + u32 size; + + n = sizeof(t5_pm_rx_array) / (IREG_NUM_ELEM * sizeof(u32)); + size = sizeof(struct ireg_buf) * n * 2; + rc = cudbg_get_buff(dbg_buff, size, &temp_buff); + if (rc) + return rc; + + ch_pm = (struct ireg_buf *)temp_buff.data; + /* PM_RX */ + for (i = 0; i < n; i++) { + struct ireg_field *pm_pio = &ch_pm->tp_pio; + u32 *buff = ch_pm->outbuf; + + pm_pio->ireg_addr = t5_pm_rx_array[i][0]; + pm_pio->ireg_data = t5_pm_rx_array[i][1]; + pm_pio->ireg_local_offset = t5_pm_rx_array[i][2]; + pm_pio->ireg_offset_range = t5_pm_rx_array[i][3]; + t4_read_indirect(padap, + pm_pio->ireg_addr, + pm_pio->ireg_data, + buff, + pm_pio->ireg_offset_range, + pm_pio->ireg_local_offset); + ch_pm++; + } + + /* PM_TX */ + n = sizeof(t5_pm_tx_array) / (IREG_NUM_ELEM * sizeof(u32)); + for (i = 0; i < n; i++) { + struct ireg_field *pm_pio = &ch_pm->tp_pio; + u32 *buff = ch_pm->outbuf; + + pm_pio->ireg_addr = t5_pm_tx_array[i][0]; + pm_pio->ireg_data = t5_pm_tx_array[i][1]; + pm_pio->ireg_local_offset = t5_pm_tx_array[i][2]; + pm_pio->ireg_offset_range = t5_pm_tx_array[i][3]; + t4_read_indirect(padap, + pm_pio->ireg_addr, + pm_pio->ireg_data, + buff, + pm_pio->ireg_offset_range, + pm_pio->ireg_local_offset); + ch_pm++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_ma_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct ireg_buf *ma_indr; + int i, rc, n; + u32 size, j; + + if (CHELSIO_CHIP_VERSION(padap->params.chip) < CHELSIO_T6) + return CUDBG_STATUS_ENTITY_NOT_FOUND; + + n = sizeof(t6_ma_ireg_array) / (IREG_NUM_ELEM * sizeof(u32)); + size = sizeof(struct ireg_buf) * n * 2; + rc = cudbg_get_buff(dbg_buff, size, &temp_buff); + if (rc) + return rc; + + ma_indr = (struct ireg_buf *)temp_buff.data; + for (i = 0; i < n; i++) { + struct ireg_field *ma_fli = &ma_indr->tp_pio; + u32 *buff = ma_indr->outbuf; + + ma_fli->ireg_addr = t6_ma_ireg_array[i][0]; + ma_fli->ireg_data = t6_ma_ireg_array[i][1]; + ma_fli->ireg_local_offset = t6_ma_ireg_array[i][2]; + ma_fli->ireg_offset_range = t6_ma_ireg_array[i][3]; + t4_read_indirect(padap, ma_fli->ireg_addr, ma_fli->ireg_data, + buff, ma_fli->ireg_offset_range, + ma_fli->ireg_local_offset); + ma_indr++; + } + + n = sizeof(t6_ma_ireg_array2) / (IREG_NUM_ELEM * sizeof(u32)); + for (i = 0; i < n; i++) { + struct ireg_field *ma_fli = &ma_indr->tp_pio; + u32 *buff = ma_indr->outbuf; + + ma_fli->ireg_addr = t6_ma_ireg_array2[i][0]; + ma_fli->ireg_data = t6_ma_ireg_array2[i][1]; + ma_fli->ireg_local_offset = t6_ma_ireg_array2[i][2]; + for (j = 0; j < t6_ma_ireg_array2[i][3]; j++) { + t4_read_indirect(padap, ma_fli->ireg_addr, + ma_fli->ireg_data, buff, 1, + ma_fli->ireg_local_offset); + buff++; + ma_fli->ireg_local_offset += 0x20; + } + ma_indr++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_up_cim_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct ireg_buf *up_cim; + int i, rc, n; + u32 size; + + n = sizeof(t5_up_cim_reg_array) / (IREG_NUM_ELEM * sizeof(u32)); + size = sizeof(struct ireg_buf) * n; + rc = cudbg_get_buff(dbg_buff, size, &temp_buff); + if (rc) + return rc; + + up_cim = (struct ireg_buf *)temp_buff.data; + for (i = 0; i < n; i++) { + struct ireg_field *up_cim_reg = &up_cim->tp_pio; + u32 *buff = up_cim->outbuf; + + if (is_t5(padap->params.chip)) { + up_cim_reg->ireg_addr = t5_up_cim_reg_array[i][0]; + up_cim_reg->ireg_data = t5_up_cim_reg_array[i][1]; + up_cim_reg->ireg_local_offset = + t5_up_cim_reg_array[i][2]; + up_cim_reg->ireg_offset_range = + t5_up_cim_reg_array[i][3]; + } else if (is_t6(padap->params.chip)) { + up_cim_reg->ireg_addr = t6_up_cim_reg_array[i][0]; + up_cim_reg->ireg_data = t6_up_cim_reg_array[i][1]; + up_cim_reg->ireg_local_offset = + t6_up_cim_reg_array[i][2]; + up_cim_reg->ireg_offset_range = + t6_up_cim_reg_array[i][3]; + } + + rc = t4_cim_read(padap, up_cim_reg->ireg_local_offset, + up_cim_reg->ireg_offset_range, buff); + if (rc) { + cudbg_put_buff(&temp_buff, dbg_buff); + return rc; + } + up_cim++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_mbox_log *mboxlog = NULL; + struct cudbg_buffer temp_buff = { 0 }; + struct mbox_cmd_log *log = NULL; + struct mbox_cmd *entry; + unsigned int entry_idx; + u16 mbox_cmds; + int i, k, rc; + u64 flit; + u32 size; + + log = padap->mbox_log; + mbox_cmds = padap->mbox_log->size; + size = sizeof(struct cudbg_mbox_log) * mbox_cmds; + rc = cudbg_get_buff(dbg_buff, size, &temp_buff); + if (rc) + return rc; + + mboxlog = (struct cudbg_mbox_log *)temp_buff.data; + for (k = 0; k < mbox_cmds; k++) { + entry_idx = log->cursor + k; + if (entry_idx >= log->size) + entry_idx -= log->size; + + entry = mbox_cmd_log_entry(log, entry_idx); + /* skip over unused entries */ + if (entry->timestamp == 0) + continue; + + memcpy(&mboxlog->entry, entry, sizeof(struct mbox_cmd)); + for (i = 0; i < MBOX_LEN / 8; i++) { + flit = entry->cmd[i]; + mboxlog->hi[i] = (u32)(flit >> 32); + mboxlog->lo[i] = (u32)flit; + } + mboxlog++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_hma_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct ireg_buf *hma_indr; + int i, rc, n; + u32 size; + + if (CHELSIO_CHIP_VERSION(padap->params.chip) < CHELSIO_T6) + return CUDBG_STATUS_ENTITY_NOT_FOUND; + + n = sizeof(t6_hma_ireg_array) / (IREG_NUM_ELEM * sizeof(u32)); + size = sizeof(struct ireg_buf) * n; + rc = cudbg_get_buff(dbg_buff, size, &temp_buff); + if (rc) + return rc; + + hma_indr = (struct ireg_buf *)temp_buff.data; + for (i = 0; i < n; i++) { + struct ireg_field *hma_fli = &hma_indr->tp_pio; + u32 *buff = hma_indr->outbuf; + + hma_fli->ireg_addr = t6_hma_ireg_array[i][0]; + hma_fli->ireg_data = t6_hma_ireg_array[i][1]; + hma_fli->ireg_local_offset = t6_hma_ireg_array[i][2]; + hma_fli->ireg_offset_range = t6_hma_ireg_array[i][3]; + t4_read_indirect(padap, hma_fli->ireg_addr, hma_fli->ireg_data, + buff, hma_fli->ireg_offset_range, + hma_fli->ireg_local_offset); + hma_indr++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h new file mode 100644 index 000000000000..c4440c1d0142 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h @@ -0,0 +1,103 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#ifndef __CUDBG_LIB_H__ +#define __CUDBG_LIB_H__ + +int cudbg_collect_reg_dump(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_fw_devlog(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_ibq_tp0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_ibq_tp1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_ibq_ulp(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_ibq_sge0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_ibq_sge1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_ibq_ncsi(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_obq_ulp0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_obq_ulp1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_obq_ulp2(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_obq_ulp3(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_obq_sge(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_obq_ncsi(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_edc0_meminfo(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_edc1_meminfo(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_tp_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_obq_sge_rx_q0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_obq_sge_rx_q1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_pcie_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_pm_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_ma_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_up_cim_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_hma_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); + +struct cudbg_entity_hdr *cudbg_get_entity_hdr(void *outbuf, int i); +void cudbg_align_debug_buffer(struct cudbg_buffer *dbg_buff, + struct cudbg_entity_hdr *entity_hdr); +#endif /* __CUDBG_LIB_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h new file mode 100644 index 000000000000..b150c5d1f7c0 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h @@ -0,0 +1,81 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#ifndef __CUDBG_LIB_COMMON_H__ +#define __CUDBG_LIB_COMMON_H__ + +#define CUDBG_SIGNATURE 67856866 /* CUDB in ascii */ + +enum cudbg_dump_type { + CUDBG_DUMP_TYPE_MINI = 1, +}; + +enum cudbg_compression_type { + CUDBG_COMPRESSION_NONE = 1, +}; + +struct cudbg_hdr { + u32 signature; + u32 hdr_len; + u16 major_ver; + u16 minor_ver; + u32 data_len; + u32 hdr_flags; + u16 max_entities; + u8 chip_ver; + u8 dump_type:3; + u8 reserved1:1; + u8 compress_type:4; + u32 reserved[8]; +}; + +struct cudbg_entity_hdr { + u32 entity_type; + u32 start_offset; + u32 size; + int hdr_flags; + u32 sys_warn; + u32 sys_err; + u8 num_pad; + u8 flag; /* bit 0 is used to indicate ext data */ + u8 reserved1[2]; + u32 next_ext_offset; /* pointer to next extended entity meta data */ + u32 reserved[5]; +}; + +struct cudbg_buffer { + u32 size; + u32 offset; + char *data; +}; + +struct cudbg_error { + int sys_err; + int sys_warn; + int app_err; +}; + +#define CDUMP_MAX_COMP_BUF_SIZE ((64 * 1024) - 1) +#define CUDBG_CHUNK_SIZE ((CDUMP_MAX_COMP_BUF_SIZE / 1024) * 1024) + +int cudbg_get_buff(struct cudbg_buffer *pdbg_buff, u32 size, + struct cudbg_buffer *pin_buff); +void cudbg_put_buff(struct cudbg_buffer *pin_buff, + struct cudbg_buffer *pdbg_buff); +void cudbg_update_buff(struct cudbg_buffer *pin_buff, + struct cudbg_buffer *pout_buff); +#endif /* __CUDBG_LIB_COMMON_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 0db3ab6ad094..92a0b022687e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -367,6 +367,7 @@ struct adapter_params { unsigned int max_ird_adapter; /* Max read depth per adapter */ bool fr_nsmr_tpte_wr_support; /* FW support for FR_NSMR_TPTE_WR */ u8 fw_caps_support; /* 32-bit Port Capabilities */ + bool filter2_wr_support; /* FW support for FILTER2_WR */ /* MPS Buffer Group Map[per Port]. Bit i is set if buffer group i is * used by the Port @@ -858,6 +859,7 @@ struct adapter { unsigned int clipt_start; unsigned int clipt_end; struct clip_tbl *clipt; + struct smt_data *smt; struct cxgb4_uld_info *uld; void *uld_handle[CXGB4_ULD_MAX]; unsigned int num_uld; @@ -909,6 +911,9 @@ struct adapter { /* TC flower offload */ DECLARE_HASHTABLE(flower_anymatch_tbl, 9); struct timer_list flower_stats_timer; + + /* Ethtool Dump */ + struct ethtool_dump eth_dump; }; /* Support for "sched-class" command to allow a TX Scheduling Class to be @@ -1060,10 +1065,19 @@ struct ch_filter_specification { uint32_t newdmac:1; /* rewrite destination MAC address */ uint32_t newsmac:1; /* rewrite source MAC address */ uint32_t newvlan:2; /* rewrite VLAN Tag */ + uint32_t nat_mode:3; /* specify NAT operation mode */ uint8_t dmac[ETH_ALEN]; /* new destination MAC address */ uint8_t smac[ETH_ALEN]; /* new source MAC address */ uint16_t vlan; /* VLAN Tag to insert */ + u8 nat_lip[16]; /* local IP to use after NAT'ing */ + u8 nat_fip[16]; /* foreign IP to use after NAT'ing */ + u16 nat_lport; /* local port to use after NAT'ing */ + u16 nat_fport; /* foreign port to use after NAT'ing */ + + /* reservation for future additions */ + u8 rsvd[24]; + /* Filter rule value/mask pairs. */ struct ch_filter_tuple val; @@ -1083,6 +1097,10 @@ enum { VLAN_REWRITE }; +enum { + NAT_MODE_ALL = 7, /* NAT on entire 4-tuple */ +}; + /* Host shadow copy of ingress filter entry. This is in host native format * and doesn't match the ordering or bit order, etc. of the hardware of the * firmware command. The use of bit-field structure elements is purely to @@ -1095,9 +1113,9 @@ struct filter_entry { u32 locked:1; /* filter is administratively locked */ u32 pending:1; /* filter action is pending firmware reply */ - u32 smtidx:8; /* Source MAC Table index for smac */ struct filter_ctx *ctx; /* Caller's completion hook */ struct l2t_entry *l2t; /* Layer Two Table entry for dmac */ + struct smt_entry *smt; /* Source Mac Table entry for smac */ struct net_device *dev; /* Associated net device */ u32 tid; /* This will store the actual tid */ @@ -1456,7 +1474,7 @@ unsigned int qtimer_val(const struct adapter *adap, int t4_init_devlog_params(struct adapter *adapter); int t4_init_sge_params(struct adapter *adapter); -int t4_init_tp_params(struct adapter *adap); +int t4_init_tp_params(struct adapter *adap, bool sleep_ok); int t4_filter_field_shift(const struct adapter *adap, int filter_sel); int t4_init_rss_mode(struct adapter *adap, int mbox); int t4_init_portinfo(struct port_info *pi, int mbox, @@ -1470,14 +1488,15 @@ int t4_config_glbl_rss(struct adapter *adapter, int mbox, unsigned int mode, int t4_config_vi_rss(struct adapter *adapter, int mbox, unsigned int viid, unsigned int flags, unsigned int defq); int t4_read_rss(struct adapter *adapter, u16 *entries); -void t4_read_rss_key(struct adapter *adapter, u32 *key); -void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx); +void t4_read_rss_key(struct adapter *adapter, u32 *key, bool sleep_ok); +void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx, + bool sleep_ok); void t4_read_rss_pf_config(struct adapter *adapter, unsigned int index, - u32 *valp); + u32 *valp, bool sleep_ok); void t4_read_rss_vf_config(struct adapter *adapter, unsigned int index, - u32 *vfl, u32 *vfh); -u32 t4_read_rss_pf_map(struct adapter *adapter); -u32 t4_read_rss_pf_mask(struct adapter *adapter); + u32 *vfl, u32 *vfh, bool sleep_ok); +u32 t4_read_rss_pf_map(struct adapter *adapter, bool sleep_ok); +u32 t4_read_rss_pf_mask(struct adapter *adapter, bool sleep_ok); unsigned int t4_get_mps_bg_map(struct adapter *adapter, int pidx); unsigned int t4_get_tp_ch_map(struct adapter *adapter, int pidx); @@ -1508,14 +1527,18 @@ void t4_read_cong_tbl(struct adapter *adap, u16 incr[NMTUS][NCCTRL_WIN]); void t4_tp_wr_bits_indirect(struct adapter *adap, unsigned int addr, unsigned int mask, unsigned int val); void t4_tp_read_la(struct adapter *adap, u64 *la_buf, unsigned int *wrptr); -void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st); -void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st); -void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st); -void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st); +void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st, + bool sleep_ok); +void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st, + bool sleep_ok); +void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st, + bool sleep_ok); +void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st, + bool sleep_ok); void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4, - struct tp_tcp_stats *v6); + struct tp_tcp_stats *v6, bool sleep_ok); void t4_get_fcoe_stats(struct adapter *adap, unsigned int idx, - struct tp_fcoe_stats *st); + struct tp_fcoe_stats *st, bool sleep_ok); void t4_load_mtus(struct adapter *adap, const unsigned short *mtus, const unsigned short *alpha, const unsigned short *beta); @@ -1624,6 +1647,13 @@ void t4_idma_monitor(struct adapter *adapter, int hz, int ticks); int t4_set_vf_mac_acl(struct adapter *adapter, unsigned int vf, unsigned int naddr, u8 *addr); +void t4_tp_pio_read(struct adapter *adap, u32 *buff, u32 nregs, + u32 start_index, bool sleep_ok); +void t4_tp_tm_pio_read(struct adapter *adap, u32 *buff, u32 nregs, + u32 start_index, bool sleep_ok); +void t4_tp_mib_read(struct adapter *adap, u32 *buff, u32 nregs, + u32 start_index, bool sleep_ok); + void t4_uld_mem_free(struct adapter *adap); int t4_uld_mem_alloc(struct adapter *adap); void t4_uld_clean_up(struct adapter *adap); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c new file mode 100644 index 000000000000..9d97080a9d17 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c @@ -0,0 +1,296 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#include "t4_regs.h" +#include "cxgb4.h" +#include "cxgb4_cudbg.h" +#include "cudbg_entity.h" + +static const struct cxgb4_collect_entity cxgb4_collect_mem_dump[] = { + { CUDBG_EDC0, cudbg_collect_edc0_meminfo }, + { CUDBG_EDC1, cudbg_collect_edc1_meminfo }, +}; + +static const struct cxgb4_collect_entity cxgb4_collect_hw_dump[] = { + { CUDBG_MBOX_LOG, cudbg_collect_mbox_log }, + { CUDBG_DEV_LOG, cudbg_collect_fw_devlog }, + { CUDBG_REG_DUMP, cudbg_collect_reg_dump }, + { CUDBG_CIM_IBQ_TP0, cudbg_collect_cim_ibq_tp0 }, + { CUDBG_CIM_IBQ_TP1, cudbg_collect_cim_ibq_tp1 }, + { CUDBG_CIM_IBQ_ULP, cudbg_collect_cim_ibq_ulp }, + { CUDBG_CIM_IBQ_SGE0, cudbg_collect_cim_ibq_sge0 }, + { CUDBG_CIM_IBQ_SGE1, cudbg_collect_cim_ibq_sge1 }, + { CUDBG_CIM_IBQ_NCSI, cudbg_collect_cim_ibq_ncsi }, + { CUDBG_CIM_OBQ_ULP0, cudbg_collect_cim_obq_ulp0 }, + { CUDBG_CIM_OBQ_ULP1, cudbg_collect_cim_obq_ulp1 }, + { CUDBG_CIM_OBQ_ULP2, cudbg_collect_cim_obq_ulp2 }, + { CUDBG_CIM_OBQ_ULP3, cudbg_collect_cim_obq_ulp3 }, + { CUDBG_CIM_OBQ_SGE, cudbg_collect_cim_obq_sge }, + { CUDBG_CIM_OBQ_NCSI, cudbg_collect_cim_obq_ncsi }, + { CUDBG_TP_INDIRECT, cudbg_collect_tp_indirect }, + { CUDBG_SGE_INDIRECT, cudbg_collect_sge_indirect }, + { CUDBG_CIM_OBQ_RXQ0, cudbg_collect_obq_sge_rx_q0 }, + { CUDBG_CIM_OBQ_RXQ1, cudbg_collect_obq_sge_rx_q1 }, + { CUDBG_PCIE_INDIRECT, cudbg_collect_pcie_indirect }, + { CUDBG_PM_INDIRECT, cudbg_collect_pm_indirect }, + { CUDBG_MA_INDIRECT, cudbg_collect_ma_indirect }, + { CUDBG_UP_CIM_INDIRECT, cudbg_collect_up_cim_indirect }, + { CUDBG_HMA_INDIRECT, cudbg_collect_hma_indirect }, +}; + +static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity) +{ + u32 value, n = 0, len = 0; + + switch (entity) { + case CUDBG_REG_DUMP: + switch (CHELSIO_CHIP_VERSION(adap->params.chip)) { + case CHELSIO_T4: + len = T4_REGMAP_SIZE; + break; + case CHELSIO_T5: + case CHELSIO_T6: + len = T5_REGMAP_SIZE; + break; + default: + break; + } + break; + case CUDBG_DEV_LOG: + len = adap->params.devlog.size; + break; + case CUDBG_CIM_IBQ_TP0: + case CUDBG_CIM_IBQ_TP1: + case CUDBG_CIM_IBQ_ULP: + case CUDBG_CIM_IBQ_SGE0: + case CUDBG_CIM_IBQ_SGE1: + case CUDBG_CIM_IBQ_NCSI: + len = CIM_IBQ_SIZE * 4 * sizeof(u32); + break; + case CUDBG_CIM_OBQ_ULP0: + case CUDBG_CIM_OBQ_ULP1: + case CUDBG_CIM_OBQ_ULP2: + case CUDBG_CIM_OBQ_ULP3: + case CUDBG_CIM_OBQ_SGE: + case CUDBG_CIM_OBQ_NCSI: + case CUDBG_CIM_OBQ_RXQ0: + case CUDBG_CIM_OBQ_RXQ1: + len = 6 * CIM_OBQ_SIZE * 4 * sizeof(u32); + break; + case CUDBG_EDC0: + value = t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A); + if (value & EDRAM0_ENABLE_F) { + value = t4_read_reg(adap, MA_EDRAM0_BAR_A); + len = EDRAM0_SIZE_G(value); + } + len = cudbg_mbytes_to_bytes(len); + break; + case CUDBG_EDC1: + value = t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A); + if (value & EDRAM1_ENABLE_F) { + value = t4_read_reg(adap, MA_EDRAM1_BAR_A); + len = EDRAM1_SIZE_G(value); + } + len = cudbg_mbytes_to_bytes(len); + break; + case CUDBG_TP_INDIRECT: + switch (CHELSIO_CHIP_VERSION(adap->params.chip)) { + case CHELSIO_T5: + n = sizeof(t5_tp_pio_array) + + sizeof(t5_tp_tm_pio_array) + + sizeof(t5_tp_mib_index_array); + break; + case CHELSIO_T6: + n = sizeof(t6_tp_pio_array) + + sizeof(t6_tp_tm_pio_array) + + sizeof(t6_tp_mib_index_array); + break; + default: + break; + } + n = n / (IREG_NUM_ELEM * sizeof(u32)); + len = sizeof(struct ireg_buf) * n; + break; + case CUDBG_SGE_INDIRECT: + len = sizeof(struct ireg_buf) * 2; + break; + case CUDBG_PCIE_INDIRECT: + n = sizeof(t5_pcie_pdbg_array) / (IREG_NUM_ELEM * sizeof(u32)); + len = sizeof(struct ireg_buf) * n * 2; + break; + case CUDBG_PM_INDIRECT: + n = sizeof(t5_pm_rx_array) / (IREG_NUM_ELEM * sizeof(u32)); + len = sizeof(struct ireg_buf) * n * 2; + break; + case CUDBG_MA_INDIRECT: + if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5) { + n = sizeof(t6_ma_ireg_array) / + (IREG_NUM_ELEM * sizeof(u32)); + len = sizeof(struct ireg_buf) * n * 2; + } + break; + case CUDBG_UP_CIM_INDIRECT: + n = sizeof(t5_up_cim_reg_array) / (IREG_NUM_ELEM * sizeof(u32)); + len = sizeof(struct ireg_buf) * n; + break; + case CUDBG_MBOX_LOG: + len = sizeof(struct cudbg_mbox_log) * adap->mbox_log->size; + break; + case CUDBG_HMA_INDIRECT: + if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5) { + n = sizeof(t6_hma_ireg_array) / + (IREG_NUM_ELEM * sizeof(u32)); + len = sizeof(struct ireg_buf) * n; + } + break; + default: + break; + } + + return len; +} + +u32 cxgb4_get_dump_length(struct adapter *adap, u32 flag) +{ + u32 i, entity; + u32 len = 0; + + if (flag & CXGB4_ETH_DUMP_HW) { + for (i = 0; i < ARRAY_SIZE(cxgb4_collect_hw_dump); i++) { + entity = cxgb4_collect_hw_dump[i].entity; + len += cxgb4_get_entity_length(adap, entity); + } + } + + if (flag & CXGB4_ETH_DUMP_MEM) { + for (i = 0; i < ARRAY_SIZE(cxgb4_collect_mem_dump); i++) { + entity = cxgb4_collect_mem_dump[i].entity; + len += cxgb4_get_entity_length(adap, entity); + } + } + + return len; +} + +static void cxgb4_cudbg_collect_entity(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + const struct cxgb4_collect_entity *e_arr, + u32 arr_size, void *buf, u32 *tot_size) +{ + struct adapter *adap = pdbg_init->adap; + struct cudbg_error cudbg_err = { 0 }; + struct cudbg_entity_hdr *entity_hdr; + u32 entity_size, i; + u32 total_size = 0; + int ret; + + for (i = 0; i < arr_size; i++) { + const struct cxgb4_collect_entity *e = &e_arr[i]; + + /* Skip entities that won't fit in output buffer */ + entity_size = cxgb4_get_entity_length(adap, e->entity); + if (entity_size > + pdbg_init->outbuf_size - *tot_size - total_size) + continue; + + entity_hdr = cudbg_get_entity_hdr(buf, e->entity); + entity_hdr->entity_type = e->entity; + entity_hdr->start_offset = dbg_buff->offset; + memset(&cudbg_err, 0, sizeof(struct cudbg_error)); + ret = e->collect_cb(pdbg_init, dbg_buff, &cudbg_err); + if (ret) { + entity_hdr->size = 0; + dbg_buff->offset = entity_hdr->start_offset; + } else { + cudbg_align_debug_buffer(dbg_buff, entity_hdr); + } + + /* Log error and continue with next entity */ + if (cudbg_err.sys_err) + ret = CUDBG_SYSTEM_ERROR; + + entity_hdr->hdr_flags = ret; + entity_hdr->sys_err = cudbg_err.sys_err; + entity_hdr->sys_warn = cudbg_err.sys_warn; + total_size += entity_hdr->size; + } + + *tot_size += total_size; +} + +int cxgb4_cudbg_collect(struct adapter *adap, void *buf, u32 *buf_size, + u32 flag) +{ + struct cudbg_init cudbg_init = { 0 }; + struct cudbg_buffer dbg_buff = { 0 }; + u32 size, min_size, total_size = 0; + struct cudbg_hdr *cudbg_hdr; + + size = *buf_size; + + cudbg_init.adap = adap; + cudbg_init.outbuf = buf; + cudbg_init.outbuf_size = size; + + dbg_buff.data = buf; + dbg_buff.size = size; + dbg_buff.offset = 0; + + cudbg_hdr = (struct cudbg_hdr *)buf; + cudbg_hdr->signature = CUDBG_SIGNATURE; + cudbg_hdr->hdr_len = sizeof(struct cudbg_hdr); + cudbg_hdr->major_ver = CUDBG_MAJOR_VERSION; + cudbg_hdr->minor_ver = CUDBG_MINOR_VERSION; + cudbg_hdr->max_entities = CUDBG_MAX_ENTITY; + cudbg_hdr->chip_ver = adap->params.chip; + cudbg_hdr->dump_type = CUDBG_DUMP_TYPE_MINI; + cudbg_hdr->compress_type = CUDBG_COMPRESSION_NONE; + + min_size = sizeof(struct cudbg_hdr) + + sizeof(struct cudbg_entity_hdr) * + cudbg_hdr->max_entities; + if (size < min_size) + return -ENOMEM; + + dbg_buff.offset += min_size; + total_size = dbg_buff.offset; + + if (flag & CXGB4_ETH_DUMP_HW) + cxgb4_cudbg_collect_entity(&cudbg_init, &dbg_buff, + cxgb4_collect_hw_dump, + ARRAY_SIZE(cxgb4_collect_hw_dump), + buf, + &total_size); + + if (flag & CXGB4_ETH_DUMP_MEM) + cxgb4_cudbg_collect_entity(&cudbg_init, &dbg_buff, + cxgb4_collect_mem_dump, + ARRAY_SIZE(cxgb4_collect_mem_dump), + buf, + &total_size); + + cudbg_hdr->data_len = total_size; + *buf_size = total_size; + return 0; +} + +void cxgb4_init_ethtool_dump(struct adapter *adapter) +{ + adapter->eth_dump.flag = CXGB4_ETH_DUMP_NONE; + adapter->eth_dump.version = adapter->params.fw_vers; + adapter->eth_dump.len = 0; +} diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h new file mode 100644 index 000000000000..c099b5aa2214 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h @@ -0,0 +1,44 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#ifndef __CXGB4_CUDBG_H__ +#define __CXGB4_CUDBG_H__ + +#include "cudbg_if.h" +#include "cudbg_lib_common.h" +#include "cudbg_lib.h" + +typedef int (*cudbg_collect_callback_t)(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); + +struct cxgb4_collect_entity { + enum cudbg_dbg_entity_type entity; + cudbg_collect_callback_t collect_cb; +}; + +enum CXGB4_ETHTOOL_DUMP_FLAGS { + CXGB4_ETH_DUMP_NONE = ETH_FW_DUMP_DISABLE, + CXGB4_ETH_DUMP_MEM = (1 << 0), /* On-Chip Memory Dumps */ + CXGB4_ETH_DUMP_HW = (1 << 1), /* various FW and HW dumps */ +}; + +u32 cxgb4_get_dump_length(struct adapter *adap, u32 flag); +int cxgb4_cudbg_collect(struct adapter *adap, void *buf, u32 *buf_size, + u32 flag); +void cxgb4_init_ethtool_dump(struct adapter *adapter); +#endif /* __CXGB4_CUDBG_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 76540b0e082d..917663b35603 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -2211,7 +2211,7 @@ static int rss_key_show(struct seq_file *seq, void *v) { u32 key[10]; - t4_read_rss_key(seq->private, key); + t4_read_rss_key(seq->private, key, true); seq_printf(seq, "%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x\n", key[9], key[8], key[7], key[6], key[5], key[4], key[3], key[2], key[1], key[0]); @@ -2248,7 +2248,7 @@ static ssize_t rss_key_write(struct file *file, const char __user *buf, } } - t4_write_rss_key(adap, key, -1); + t4_write_rss_key(adap, key, -1, true); return count; } @@ -2325,12 +2325,13 @@ static int rss_pf_config_open(struct inode *inode, struct file *file) return -ENOMEM; pfconf = (struct rss_pf_conf *)p->data; - rss_pf_map = t4_read_rss_pf_map(adapter); - rss_pf_mask = t4_read_rss_pf_mask(adapter); + rss_pf_map = t4_read_rss_pf_map(adapter, true); + rss_pf_mask = t4_read_rss_pf_mask(adapter, true); for (pf = 0; pf < 8; pf++) { pfconf[pf].rss_pf_map = rss_pf_map; pfconf[pf].rss_pf_mask = rss_pf_mask; - t4_read_rss_pf_config(adapter, pf, &pfconf[pf].rss_pf_config); + t4_read_rss_pf_config(adapter, pf, &pfconf[pf].rss_pf_config, + true); } return 0; } @@ -2393,7 +2394,7 @@ static int rss_vf_config_open(struct inode *inode, struct file *file) vfconf = (struct rss_vf_conf *)p->data; for (vf = 0; vf < vfcount; vf++) { t4_read_rss_vf_config(adapter, vf, &vfconf[vf].rss_vf_vfl, - &vfconf[vf].rss_vf_vfh); + &vfconf[vf].rss_vf_vfh, true); } return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index a71af1e587e2..1b7f6b9ccc8b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -21,6 +21,7 @@ #include "cxgb4.h" #include "t4_regs.h" #include "t4fw_api.h" +#include "cxgb4_cudbg.h" #define EEPROM_MAGIC 0x38E2F10C @@ -335,10 +336,10 @@ static void collect_adapter_stats(struct adapter *adap, struct adapter_stats *s) memset(s, 0, sizeof(*s)); spin_lock(&adap->stats_lock); - t4_tp_get_tcp_stats(adap, &v4, &v6); - t4_tp_get_rdma_stats(adap, &rdma_stats); - t4_get_usm_stats(adap, &usm_stats); - t4_tp_get_err_stats(adap, &err_stats); + t4_tp_get_tcp_stats(adap, &v4, &v6, false); + t4_tp_get_rdma_stats(adap, &rdma_stats, false); + t4_get_usm_stats(adap, &usm_stats, false); + t4_tp_get_err_stats(adap, &err_stats, false); spin_unlock(&adap->stats_lock); s->db_drop = adap->db_stats.db_drop; @@ -388,9 +389,9 @@ static void collect_channel_stats(struct adapter *adap, struct channel_stats *s, memset(s, 0, sizeof(*s)); spin_lock(&adap->stats_lock); - t4_tp_get_cpl_stats(adap, &cpl_stats); - t4_tp_get_err_stats(adap, &err_stats); - t4_get_fcoe_stats(adap, i, &fcoe_stats); + t4_tp_get_cpl_stats(adap, &cpl_stats, false); + t4_tp_get_err_stats(adap, &err_stats, false); + t4_get_fcoe_stats(adap, i, &fcoe_stats, false); spin_unlock(&adap->stats_lock); s->cpl_req = cpl_stats.req[i]; @@ -1374,6 +1375,56 @@ static int get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, return -EOPNOTSUPP; } +static int set_dump(struct net_device *dev, struct ethtool_dump *eth_dump) +{ + struct adapter *adapter = netdev2adap(dev); + u32 len = 0; + + len = sizeof(struct cudbg_hdr) + + sizeof(struct cudbg_entity_hdr) * CUDBG_MAX_ENTITY; + len += cxgb4_get_dump_length(adapter, eth_dump->flag); + + adapter->eth_dump.flag = eth_dump->flag; + adapter->eth_dump.len = len; + return 0; +} + +static int get_dump_flag(struct net_device *dev, struct ethtool_dump *eth_dump) +{ + struct adapter *adapter = netdev2adap(dev); + + eth_dump->flag = adapter->eth_dump.flag; + eth_dump->len = adapter->eth_dump.len; + eth_dump->version = adapter->eth_dump.version; + return 0; +} + +static int get_dump_data(struct net_device *dev, struct ethtool_dump *eth_dump, + void *buf) +{ + struct adapter *adapter = netdev2adap(dev); + u32 len = 0; + int ret = 0; + + if (adapter->eth_dump.flag == CXGB4_ETH_DUMP_NONE) + return -ENOENT; + + len = sizeof(struct cudbg_hdr) + + sizeof(struct cudbg_entity_hdr) * CUDBG_MAX_ENTITY; + len += cxgb4_get_dump_length(adapter, adapter->eth_dump.flag); + if (eth_dump->len < len) + return -ENOMEM; + + ret = cxgb4_cudbg_collect(adapter, buf, &len, adapter->eth_dump.flag); + if (ret) + return ret; + + eth_dump->flag = adapter->eth_dump.flag; + eth_dump->len = len; + eth_dump->version = adapter->eth_dump.version; + return 0; +} + static const struct ethtool_ops cxgb_ethtool_ops = { .get_link_ksettings = get_link_ksettings, .set_link_ksettings = set_link_ksettings, @@ -1404,7 +1455,10 @@ static const struct ethtool_ops cxgb_ethtool_ops = { .get_rxfh = get_rss_table, .set_rxfh = set_rss_table, .flash_device = set_flash, - .get_ts_info = get_ts_info + .get_ts_info = get_ts_info, + .set_dump = set_dump, + .get_dump_flag = get_dump_flag, + .get_dump_data = get_dump_data, }; void cxgb4_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 15361ca2857c..89272f29f807 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -34,7 +34,9 @@ #include "cxgb4.h" #include "t4_regs.h" +#include "t4_tcb.h" #include "l2t.h" +#include "smt.h" #include "t4fw_api.h" #include "cxgb4_filter.h" @@ -311,7 +313,7 @@ static int del_filter_wr(struct adapter *adapter, int fidx) int set_filter_wr(struct adapter *adapter, int fidx) { struct filter_entry *f = &adapter->tids.ftid_tab[fidx]; - struct fw_filter_wr *fwr; + struct fw_filter2_wr *fwr; struct sk_buff *skb; skb = alloc_skb(sizeof(*fwr), GFP_KERNEL); @@ -332,6 +334,21 @@ int set_filter_wr(struct adapter *adapter, int fidx) } } + /* If the new filter requires loopback Source MAC rewriting then + * we need to allocate a SMT entry for the filter. + */ + if (f->fs.newsmac) { + f->smt = cxgb4_smt_alloc_switching(f->dev, f->fs.smac); + if (!f->smt) { + if (f->l2t) { + cxgb4_l2t_release(f->l2t); + f->l2t = NULL; + } + kfree_skb(skb); + return -ENOMEM; + } + } + fwr = __skb_put_zero(skb, sizeof(*fwr)); /* It would be nice to put most of the following in t4_hw.c but most @@ -342,7 +359,10 @@ int set_filter_wr(struct adapter *adapter, int fidx) * filter specification structure but for now it's easiest to simply * put this fairly direct code in line ... */ - fwr->op_pkd = htonl(FW_WR_OP_V(FW_FILTER_WR)); + if (adapter->params.filter2_wr_support) + fwr->op_pkd = htonl(FW_WR_OP_V(FW_FILTER2_WR)); + else + fwr->op_pkd = htonl(FW_WR_OP_V(FW_FILTER_WR)); fwr->len16_pkd = htonl(FW_WR_LEN16_V(sizeof(*fwr) / 16)); fwr->tid_to_iq = htonl(FW_FILTER_WR_TID_V(f->tid) | @@ -357,7 +377,6 @@ int set_filter_wr(struct adapter *adapter, int fidx) FW_FILTER_WR_DIRSTEERHASH_V(f->fs.dirsteerhash) | FW_FILTER_WR_LPBK_V(f->fs.action == FILTER_SWITCH) | FW_FILTER_WR_DMAC_V(f->fs.newdmac) | - FW_FILTER_WR_SMAC_V(f->fs.newsmac) | FW_FILTER_WR_INSVLAN_V(f->fs.newvlan == VLAN_INSERT || f->fs.newvlan == VLAN_REWRITE) | FW_FILTER_WR_RMVLAN_V(f->fs.newvlan == VLAN_REMOVE || @@ -404,8 +423,18 @@ int set_filter_wr(struct adapter *adapter, int fidx) fwr->lpm = htons(f->fs.mask.lport); fwr->fp = htons(f->fs.val.fport); fwr->fpm = htons(f->fs.mask.fport); - if (f->fs.newsmac) - memcpy(fwr->sma, f->fs.smac, sizeof(fwr->sma)); + + if (adapter->params.filter2_wr_support) { + fwr->natmode_to_ulp_type = + FW_FILTER2_WR_ULP_TYPE_V(f->fs.nat_mode ? + ULP_MODE_TCPDDP : + ULP_MODE_NONE) | + FW_FILTER2_WR_NATMODE_V(f->fs.nat_mode); + memcpy(fwr->newlip, f->fs.nat_lip, sizeof(fwr->newlip)); + memcpy(fwr->newfip, f->fs.nat_fip, sizeof(fwr->newfip)); + fwr->newlport = htons(f->fs.nat_lport); + fwr->newfport = htons(f->fs.nat_fport); + } /* Mark the filter as "pending" and ship off the Filter Work Request. * When we get the Work Request Reply we'll clear the pending status. @@ -463,6 +492,9 @@ void clear_filter(struct adapter *adap, struct filter_entry *f) if (f->l2t) cxgb4_l2t_release(f->l2t); + if (f->smt) + cxgb4_smt_release(f->smt); + /* The zeroing of the filter rule below clears the filter valid, * pending, locked flags, l2t pointer, etc. so it's all we need for * this operation. @@ -757,6 +789,62 @@ out: return ret; } +static int set_tcb_field(struct adapter *adap, struct filter_entry *f, + unsigned int ftid, u16 word, u64 mask, u64 val, + int no_reply) +{ + struct cpl_set_tcb_field *req; + struct sk_buff *skb; + + skb = alloc_skb(sizeof(struct cpl_set_tcb_field), GFP_ATOMIC); + if (!skb) + return -ENOMEM; + + req = (struct cpl_set_tcb_field *)__skb_put(skb, sizeof(*req)); + memset(req, 0, sizeof(*req)); + INIT_TP_WR_CPL(req, CPL_SET_TCB_FIELD, ftid); + req->reply_ctrl = htons(REPLY_CHAN_V(0) | + QUEUENO_V(adap->sge.fw_evtq.abs_id) | + NO_REPLY_V(no_reply)); + req->word_cookie = htons(TCB_WORD_V(word) | TCB_COOKIE_V(ftid)); + req->mask = cpu_to_be64(mask); + req->val = cpu_to_be64(val); + set_wr_txq(skb, CPL_PRIORITY_CONTROL, f->fs.val.iport & 0x3); + t4_ofld_send(adap, skb); + return 0; +} + +/* Set one of the t_flags bits in the TCB. + */ +static int set_tcb_tflag(struct adapter *adap, struct filter_entry *f, + unsigned int ftid, unsigned int bit_pos, + unsigned int val, int no_reply) +{ + return set_tcb_field(adap, f, ftid, TCB_T_FLAGS_W, 1ULL << bit_pos, + (unsigned long long)val << bit_pos, no_reply); +} + +static int configure_filter_smac(struct adapter *adap, struct filter_entry *f) +{ + int err; + + /* do a set-tcb for smac-sel and CWR bit.. */ + err = set_tcb_tflag(adap, f, f->tid, TF_CCTRL_CWR_S, 1, 1); + if (err) + goto smac_err; + + err = set_tcb_field(adap, f, f->tid, TCB_SMAC_SEL_W, + TCB_SMAC_SEL_V(TCB_SMAC_SEL_M), + TCB_SMAC_SEL_V(f->smt->idx), 1); + if (!err) + return 0; + +smac_err: + dev_err(adap->pdev_dev, "filter %u smac config failed with error %u\n", + f->tid, err); + return err; +} + /* Handle a filter write/deletion reply. */ void filter_rpl(struct adapter *adap, const struct cpl_set_tcb_rpl *rpl) { @@ -795,19 +883,23 @@ void filter_rpl(struct adapter *adap, const struct cpl_set_tcb_rpl *rpl) clear_filter(adap, f); if (ctx) ctx->result = 0; - } else if (ret == FW_FILTER_WR_SMT_TBL_FULL) { - dev_err(adap->pdev_dev, "filter %u setup failed due to full SMT\n", - idx); - clear_filter(adap, f); - if (ctx) - ctx->result = -ENOMEM; } else if (ret == FW_FILTER_WR_FLT_ADDED) { - f->smtidx = (be64_to_cpu(rpl->oldval) >> 24) & 0xff; - f->pending = 0; /* asynchronous setup completed */ - f->valid = 1; - if (ctx) { - ctx->result = 0; - ctx->tid = idx; + int err = 0; + + if (f->fs.newsmac) + err = configure_filter_smac(adap, f); + + if (!err) { + f->pending = 0; /* async setup completed */ + f->valid = 1; + if (ctx) { + ctx->result = 0; + ctx->tid = idx; + } + } else { + clear_filter(adap, f); + if (ctx) + ctx->result = err; } } else { /* Something went wrong. Issue a warning about the diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index fe4cbe22d5d7..c478291db93f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -77,10 +77,12 @@ #include "cxgb4_debugfs.h" #include "clip_tbl.h" #include "l2t.h" +#include "smt.h" #include "sched.h" #include "cxgb4_tc_u32.h" #include "cxgb4_tc_flower.h" #include "cxgb4_ptp.h" +#include "cxgb4_cudbg.h" char cxgb4_driver_name[] = KBUILD_MODNAME; @@ -562,6 +564,10 @@ static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp, const struct cpl_l2t_write_rpl *p = (void *)rsp; do_l2t_write_rpl(q->adap, p); + } else if (opcode == CPL_SMT_WRITE_RPL) { + const struct cpl_smt_write_rpl *p = (void *)rsp; + + do_smt_write_rpl(q->adap, p); } else if (opcode == CPL_SET_TCB_RPL) { const struct cpl_set_tcb_rpl *p = (void *)rsp; @@ -1638,7 +1644,7 @@ void cxgb4_get_tcp_stats(struct pci_dev *pdev, struct tp_tcp_stats *v4, struct adapter *adap = pci_get_drvdata(pdev); spin_lock(&adap->stats_lock); - t4_tp_get_tcp_stats(adap, v4, v6); + t4_tp_get_tcp_stats(adap, v4, v6, false); spin_unlock(&adap->stats_lock); } EXPORT_SYMBOL(cxgb4_get_tcp_stats); @@ -3904,6 +3910,16 @@ static int adap_init0(struct adapter *adap) 1, params, val); adap->params.fr_nsmr_tpte_wr_support = (ret == 0 && val[0] != 0); + /* See if FW supports FW_FILTER2 work request */ + if (is_t4(adap->params.chip)) { + adap->params.filter2_wr_support = 0; + } else { + params[0] = FW_PARAM_DEV(FILTER2_WR); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, + 1, params, val); + adap->params.filter2_wr_support = (ret == 0 && val[0] != 0); + } + /* * Get device capabilities so we can determine what resources we need * to manage. @@ -4076,7 +4092,7 @@ static int adap_init0(struct adapter *adap) } t4_init_sge_params(adap); adap->flags |= FW_OK; - t4_init_tp_params(adap); + t4_init_tp_params(adap, true); return 0; /* @@ -4640,6 +4656,7 @@ static void free_some_resources(struct adapter *adapter) { unsigned int i; + kvfree(adapter->smt); kvfree(adapter->l2t); t4_cleanup_sched(adapter); kvfree(adapter->tids.tid_tab); @@ -5035,6 +5052,8 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) cxgb4_set_ethtool_ops(netdev); } + cxgb4_init_ethtool_dump(adapter); + pci_set_drvdata(pdev, adapter); if (adapter->flags & FW_OK) { @@ -5064,6 +5083,12 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) */ cfg_queues(adapter); + adapter->smt = t4_init_smt(); + if (!adapter->smt) { + /* We tolerate a lack of SMT, giving up some functionality */ + dev_warn(&pdev->dev, "could not allocate SMT, continuing\n"); + } + adapter->l2t = t4_init_l2t(adapter->l2t_start, adapter->l2t_end); if (!adapter->l2t) { /* We tolerate a lack of L2T, giving up some functionality */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index 92a311767381..9b6aabe4f963 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -32,8 +32,9 @@ * SOFTWARE. */ -#include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_mirred.h> +#include <net/tc_act/tc_pedit.h> +#include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_vlan.h> #include "cxgb4.h" @@ -41,6 +42,27 @@ #define STATS_CHECK_PERIOD (HZ / 2) +struct ch_tc_pedit_fields pedits[] = { + PEDIT_FIELDS(ETH_, DMAC_31_0, 4, dmac, 0), + PEDIT_FIELDS(ETH_, DMAC_47_32, 2, dmac, 4), + PEDIT_FIELDS(ETH_, SMAC_15_0, 2, smac, 0), + PEDIT_FIELDS(ETH_, SMAC_47_16, 4, smac, 2), + PEDIT_FIELDS(IP4_, SRC, 4, nat_fip, 0), + PEDIT_FIELDS(IP4_, DST, 4, nat_lip, 0), + PEDIT_FIELDS(IP6_, SRC_31_0, 4, nat_fip, 0), + PEDIT_FIELDS(IP6_, SRC_63_32, 4, nat_fip, 4), + PEDIT_FIELDS(IP6_, SRC_95_64, 4, nat_fip, 8), + PEDIT_FIELDS(IP6_, SRC_127_96, 4, nat_fip, 12), + PEDIT_FIELDS(IP6_, DST_31_0, 4, nat_lip, 0), + PEDIT_FIELDS(IP6_, DST_63_32, 4, nat_lip, 4), + PEDIT_FIELDS(IP6_, DST_95_64, 4, nat_lip, 8), + PEDIT_FIELDS(IP6_, DST_127_96, 4, nat_lip, 12), + PEDIT_FIELDS(TCP_, SPORT, 2, nat_fport, 0), + PEDIT_FIELDS(TCP_, DPORT, 2, nat_lport, 0), + PEDIT_FIELDS(UDP_, SPORT, 2, nat_fport, 0), + PEDIT_FIELDS(UDP_, DPORT, 2, nat_lport, 0), +}; + static struct ch_tc_flower_entry *allocate_flower_entry(void) { struct ch_tc_flower_entry *new = kzalloc(sizeof(*new), GFP_KERNEL); @@ -113,6 +135,11 @@ static void cxgb4_process_flow_match(struct net_device *dev, memcpy(&fs->val.fip[0], &key->src, sizeof(key->src)); memcpy(&fs->mask.lip[0], &mask->dst, sizeof(mask->dst)); memcpy(&fs->mask.fip[0], &mask->src, sizeof(mask->src)); + + /* also initialize nat_lip/fip to same values */ + memcpy(&fs->nat_lip[0], &key->dst, sizeof(key->dst)); + memcpy(&fs->nat_fip[0], &key->src, sizeof(key->src)); + } if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { @@ -130,6 +157,10 @@ static void cxgb4_process_flow_match(struct net_device *dev, memcpy(&fs->val.fip[0], key->src.s6_addr, sizeof(key->src)); memcpy(&fs->mask.lip[0], mask->dst.s6_addr, sizeof(mask->dst)); memcpy(&fs->mask.fip[0], mask->src.s6_addr, sizeof(mask->src)); + + /* also initialize nat_lip/fip to same values */ + memcpy(&fs->nat_lip[0], key->dst.s6_addr, sizeof(key->dst)); + memcpy(&fs->nat_fip[0], key->src.s6_addr, sizeof(key->src)); } if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_PORTS)) { @@ -145,6 +176,57 @@ static void cxgb4_process_flow_match(struct net_device *dev, fs->mask.lport = cpu_to_be16(mask->dst); fs->val.fport = cpu_to_be16(key->src); fs->mask.fport = cpu_to_be16(mask->src); + + /* also initialize nat_lport/fport to same values */ + fs->nat_lport = cpu_to_be16(key->dst); + fs->nat_fport = cpu_to_be16(key->src); + } + + if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_IP)) { + struct flow_dissector_key_ip *key, *mask; + + key = skb_flow_dissector_target(cls->dissector, + FLOW_DISSECTOR_KEY_IP, + cls->key); + mask = skb_flow_dissector_target(cls->dissector, + FLOW_DISSECTOR_KEY_IP, + cls->mask); + fs->val.tos = key->tos; + fs->mask.tos = mask->tos; + } + + if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_dissector_key_vlan *key, *mask; + u16 vlan_tci, vlan_tci_mask; + + key = skb_flow_dissector_target(cls->dissector, + FLOW_DISSECTOR_KEY_VLAN, + cls->key); + mask = skb_flow_dissector_target(cls->dissector, + FLOW_DISSECTOR_KEY_VLAN, + cls->mask); + vlan_tci = key->vlan_id | (key->vlan_priority << + VLAN_PRIO_SHIFT); + vlan_tci_mask = mask->vlan_id | (mask->vlan_priority << + VLAN_PRIO_SHIFT); + fs->val.ivlan = cpu_to_be16(vlan_tci); + fs->mask.ivlan = cpu_to_be16(vlan_tci_mask); + + /* Chelsio adapters use ivlan_vld bit to match vlan packets + * as 802.1Q. Also, when vlan tag is present in packets, + * ethtype match is used then to match on ethtype of inner + * header ie. the header following the vlan header. + * So, set the ivlan_vld based on ethtype info supplied by + * TC for vlan packets if its 802.1Q. And then reset the + * ethtype value else, hw will try to match the supplied + * ethtype value with ethtype of inner header. + */ + if (fs->val.ethtype == ETH_P_8021Q) { + fs->val.ivlan_vld = 1; + fs->mask.ivlan_vld = 1; + fs->val.ethtype = 0; + fs->mask.ethtype = 0; + } } /* Match only packets coming from the ingress port where this @@ -157,19 +239,162 @@ static void cxgb4_process_flow_match(struct net_device *dev, static int cxgb4_validate_flow_match(struct net_device *dev, struct tc_cls_flower_offload *cls) { + u16 ethtype_mask = 0; + u16 ethtype_key = 0; + if (cls->dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS))) { + BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_VLAN) | + BIT(FLOW_DISSECTOR_KEY_IP))) { netdev_warn(dev, "Unsupported key used: 0x%x\n", cls->dissector->used_keys); return -EOPNOTSUPP; } + + if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_dissector_key_basic *key = + skb_flow_dissector_target(cls->dissector, + FLOW_DISSECTOR_KEY_BASIC, + cls->key); + struct flow_dissector_key_basic *mask = + skb_flow_dissector_target(cls->dissector, + FLOW_DISSECTOR_KEY_BASIC, + cls->mask); + ethtype_key = ntohs(key->n_proto); + ethtype_mask = ntohs(mask->n_proto); + } + + if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_IP)) { + u16 eth_ip_type = ethtype_key & ethtype_mask; + struct flow_dissector_key_ip *mask; + + if (eth_ip_type != ETH_P_IP && eth_ip_type != ETH_P_IPV6) { + netdev_err(dev, "IP Key supported only with IPv4/v6"); + return -EINVAL; + } + + mask = skb_flow_dissector_target(cls->dissector, + FLOW_DISSECTOR_KEY_IP, + cls->mask); + if (mask->ttl) { + netdev_warn(dev, "ttl match unsupported for offload"); + return -EOPNOTSUPP; + } + } + return 0; } +static void offload_pedit(struct ch_filter_specification *fs, u32 val, u32 mask, + u8 field) +{ + u32 set_val = val & ~mask; + u32 offset = 0; + u8 size = 1; + int i; + + for (i = 0; i < ARRAY_SIZE(pedits); i++) { + if (pedits[i].field == field) { + offset = pedits[i].offset; + size = pedits[i].size; + break; + } + } + memcpy((u8 *)fs + offset, &set_val, size); +} + +static void process_pedit_field(struct ch_filter_specification *fs, u32 val, + u32 mask, u32 offset, u8 htype) +{ + switch (htype) { + case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH: + switch (offset) { + case PEDIT_ETH_DMAC_31_0: + fs->newdmac = 1; + offload_pedit(fs, val, mask, ETH_DMAC_31_0); + break; + case PEDIT_ETH_DMAC_47_32_SMAC_15_0: + if (~mask & PEDIT_ETH_DMAC_MASK) + offload_pedit(fs, val, mask, ETH_DMAC_47_32); + else + offload_pedit(fs, val >> 16, mask >> 16, + ETH_SMAC_15_0); + break; + case PEDIT_ETH_SMAC_47_16: + fs->newsmac = 1; + offload_pedit(fs, val, mask, ETH_SMAC_47_16); + } + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4: + switch (offset) { + case PEDIT_IP4_SRC: + offload_pedit(fs, val, mask, IP4_SRC); + break; + case PEDIT_IP4_DST: + offload_pedit(fs, val, mask, IP4_DST); + } + fs->nat_mode = NAT_MODE_ALL; + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6: + switch (offset) { + case PEDIT_IP6_SRC_31_0: + offload_pedit(fs, val, mask, IP6_SRC_31_0); + break; + case PEDIT_IP6_SRC_63_32: + offload_pedit(fs, val, mask, IP6_SRC_63_32); + break; + case PEDIT_IP6_SRC_95_64: + offload_pedit(fs, val, mask, IP6_SRC_95_64); + break; + case PEDIT_IP6_SRC_127_96: + offload_pedit(fs, val, mask, IP6_SRC_127_96); + break; + case PEDIT_IP6_DST_31_0: + offload_pedit(fs, val, mask, IP6_DST_31_0); + break; + case PEDIT_IP6_DST_63_32: + offload_pedit(fs, val, mask, IP6_DST_63_32); + break; + case PEDIT_IP6_DST_95_64: + offload_pedit(fs, val, mask, IP6_DST_95_64); + break; + case PEDIT_IP6_DST_127_96: + offload_pedit(fs, val, mask, IP6_DST_127_96); + } + fs->nat_mode = NAT_MODE_ALL; + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP: + switch (offset) { + case PEDIT_TCP_SPORT_DPORT: + if (~mask & PEDIT_TCP_UDP_SPORT_MASK) + offload_pedit(fs, cpu_to_be32(val) >> 16, + cpu_to_be32(mask) >> 16, + TCP_SPORT); + else + offload_pedit(fs, cpu_to_be32(val), + cpu_to_be32(mask), TCP_DPORT); + } + fs->nat_mode = NAT_MODE_ALL; + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP: + switch (offset) { + case PEDIT_UDP_SPORT_DPORT: + if (~mask & PEDIT_TCP_UDP_SPORT_MASK) + offload_pedit(fs, cpu_to_be32(val) >> 16, + cpu_to_be32(mask) >> 16, + UDP_SPORT); + else + offload_pedit(fs, cpu_to_be32(val), + cpu_to_be32(mask), UDP_DPORT); + } + fs->nat_mode = NAT_MODE_ALL; + } +} + static void cxgb4_process_flow_actions(struct net_device *in, struct tc_cls_flower_offload *cls, struct ch_filter_specification *fs) @@ -179,7 +404,9 @@ static void cxgb4_process_flow_actions(struct net_device *in, tcf_exts_to_list(cls->exts, &actions); list_for_each_entry(a, &actions, list) { - if (is_tcf_gact_shot(a)) { + if (is_tcf_gact_ok(a)) { + fs->action = FILTER_PASS; + } else if (is_tcf_gact_shot(a)) { fs->action = FILTER_DROP; } else if (is_tcf_mirred_egress_redirect(a)) { int ifindex = tcf_mirred_ifindex(a); @@ -210,19 +437,152 @@ static void cxgb4_process_flow_actions(struct net_device *in, default: break; } + } else if (is_tcf_pedit(a)) { + u32 mask, val, offset; + int nkeys, i; + u8 htype; + + nkeys = tcf_pedit_nkeys(a); + for (i = 0; i < nkeys; i++) { + htype = tcf_pedit_htype(a, i); + mask = tcf_pedit_mask(a, i); + val = tcf_pedit_val(a, i); + offset = tcf_pedit_offset(a, i); + + process_pedit_field(fs, val, mask, offset, + htype); + } + } + } +} + +static bool valid_l4_mask(u32 mask) +{ + u16 hi, lo; + + /* Either the upper 16-bits (SPORT) OR the lower + * 16-bits (DPORT) can be set, but NOT BOTH. + */ + hi = (mask >> 16) & 0xFFFF; + lo = mask & 0xFFFF; + + return hi && lo ? false : true; +} + +static bool valid_pedit_action(struct net_device *dev, + const struct tc_action *a) +{ + u32 mask, offset; + u8 cmd, htype; + int nkeys, i; + + nkeys = tcf_pedit_nkeys(a); + for (i = 0; i < nkeys; i++) { + htype = tcf_pedit_htype(a, i); + cmd = tcf_pedit_cmd(a, i); + mask = tcf_pedit_mask(a, i); + offset = tcf_pedit_offset(a, i); + + if (cmd != TCA_PEDIT_KEY_EX_CMD_SET) { + netdev_err(dev, "%s: Unsupported pedit cmd\n", + __func__); + return false; + } + + switch (htype) { + case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH: + switch (offset) { + case PEDIT_ETH_DMAC_31_0: + case PEDIT_ETH_DMAC_47_32_SMAC_15_0: + case PEDIT_ETH_SMAC_47_16: + break; + default: + netdev_err(dev, "%s: Unsupported pedit field\n", + __func__); + return false; + } + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4: + switch (offset) { + case PEDIT_IP4_SRC: + case PEDIT_IP4_DST: + break; + default: + netdev_err(dev, "%s: Unsupported pedit field\n", + __func__); + return false; + } + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6: + switch (offset) { + case PEDIT_IP6_SRC_31_0: + case PEDIT_IP6_SRC_63_32: + case PEDIT_IP6_SRC_95_64: + case PEDIT_IP6_SRC_127_96: + case PEDIT_IP6_DST_31_0: + case PEDIT_IP6_DST_63_32: + case PEDIT_IP6_DST_95_64: + case PEDIT_IP6_DST_127_96: + break; + default: + netdev_err(dev, "%s: Unsupported pedit field\n", + __func__); + return false; + } + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP: + switch (offset) { + case PEDIT_TCP_SPORT_DPORT: + if (!valid_l4_mask(~mask)) { + netdev_err(dev, "%s: Unsupported mask for TCP L4 ports\n", + __func__); + return false; + } + break; + default: + netdev_err(dev, "%s: Unsupported pedit field\n", + __func__); + return false; + } + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP: + switch (offset) { + case PEDIT_UDP_SPORT_DPORT: + if (!valid_l4_mask(~mask)) { + netdev_err(dev, "%s: Unsupported mask for UDP L4 ports\n", + __func__); + return false; + } + break; + default: + netdev_err(dev, "%s: Unsupported pedit field\n", + __func__); + return false; + } + break; + default: + netdev_err(dev, "%s: Unsupported pedit type\n", + __func__); + return false; } } + return true; } static int cxgb4_validate_flow_actions(struct net_device *dev, struct tc_cls_flower_offload *cls) { const struct tc_action *a; + bool act_redir = false; + bool act_pedit = false; + bool act_vlan = false; LIST_HEAD(actions); tcf_exts_to_list(cls->exts, &actions); list_for_each_entry(a, &actions, list) { - if (is_tcf_gact_shot(a)) { + if (is_tcf_gact_ok(a)) { + /* Do nothing */ + } else if (is_tcf_gact_shot(a)) { /* Do nothing */ } else if (is_tcf_mirred_egress_redirect(a)) { struct adapter *adap = netdev2adap(dev); @@ -247,6 +607,7 @@ static int cxgb4_validate_flow_actions(struct net_device *dev, __func__); return -EINVAL; } + act_redir = true; } else if (is_tcf_vlan(a)) { u16 proto = be16_to_cpu(tcf_vlan_push_proto(a)); u32 vlan_action = tcf_vlan_action(a); @@ -267,11 +628,25 @@ static int cxgb4_validate_flow_actions(struct net_device *dev, __func__); return -EOPNOTSUPP; } + act_vlan = true; + } else if (is_tcf_pedit(a)) { + bool pedit_valid = valid_pedit_action(dev, a); + + if (!pedit_valid) + return -EOPNOTSUPP; + act_pedit = true; } else { netdev_err(dev, "%s: Unsupported action\n", __func__); return -EOPNOTSUPP; } } + + if ((act_pedit || act_vlan) && !act_redir) { + netdev_err(dev, "%s: pedit/vlan rewrite invalid without egress redirect\n", + __func__); + return -EINVAL; + } + return 0; } @@ -299,8 +674,8 @@ int cxgb4_tc_flower_replace(struct net_device *dev, fs = &ch_flower->fs; fs->hitcnts = 1; - cxgb4_process_flow_actions(dev, cls, fs); cxgb4_process_flow_match(dev, cls, fs); + cxgb4_process_flow_actions(dev, cls, fs); fidx = cxgb4_get_free_ftid(dev, fs->type ? PF_INET6 : PF_INET); if (fidx < 0) { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h index 604feffc752e..202d5c9ec303 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h @@ -54,6 +54,60 @@ struct ch_tc_flower_entry { u32 filter_id; }; +enum { + ETH_DMAC_31_0, /* dmac bits 0.. 31 */ + ETH_DMAC_47_32, /* dmac bits 32..47 */ + ETH_SMAC_15_0, /* smac bits 0.. 15 */ + ETH_SMAC_47_16, /* smac bits 16..47 */ + + IP4_SRC, /* 32-bit IPv4 src */ + IP4_DST, /* 32-bit IPv4 dst */ + + IP6_SRC_31_0, /* src bits 0.. 31 */ + IP6_SRC_63_32, /* src bits 63.. 32 */ + IP6_SRC_95_64, /* src bits 95.. 64 */ + IP6_SRC_127_96, /* src bits 127..96 */ + + IP6_DST_31_0, /* dst bits 0.. 31 */ + IP6_DST_63_32, /* dst bits 63.. 32 */ + IP6_DST_95_64, /* dst bits 95.. 64 */ + IP6_DST_127_96, /* dst bits 127..96 */ + + TCP_SPORT, /* 16-bit TCP sport */ + TCP_DPORT, /* 16-bit TCP dport */ + + UDP_SPORT, /* 16-bit UDP sport */ + UDP_DPORT, /* 16-bit UDP dport */ +}; + +struct ch_tc_pedit_fields { + u8 field; + u8 size; + u32 offset; +}; + +#define PEDIT_FIELDS(type, field, size, fs_field, offset) \ + { type## field, size, \ + offsetof(struct ch_filter_specification, fs_field) + (offset) } + +#define PEDIT_ETH_DMAC_MASK 0xffff +#define PEDIT_TCP_UDP_SPORT_MASK 0xffff +#define PEDIT_ETH_DMAC_31_0 0x0 +#define PEDIT_ETH_DMAC_47_32_SMAC_15_0 0x4 +#define PEDIT_ETH_SMAC_47_16 0x8 +#define PEDIT_IP4_SRC 0xC +#define PEDIT_IP4_DST 0x10 +#define PEDIT_IP6_SRC_31_0 0x8 +#define PEDIT_IP6_SRC_63_32 0xC +#define PEDIT_IP6_SRC_95_64 0x10 +#define PEDIT_IP6_SRC_127_96 0x14 +#define PEDIT_IP6_DST_31_0 0x18 +#define PEDIT_IP6_DST_63_32 0x1C +#define PEDIT_IP6_DST_95_64 0x20 +#define PEDIT_IP6_DST_127_96 0x24 +#define PEDIT_TCP_SPORT_DPORT 0x0 +#define PEDIT_UDP_SPORT_DPORT 0x0 + int cxgb4_tc_flower_replace(struct net_device *dev, struct tc_cls_flower_offload *cls); int cxgb4_tc_flower_destroy(struct net_device *dev, diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.c b/drivers/net/ethernet/chelsio/cxgb4/smt.c new file mode 100644 index 000000000000..7b2207a2a130 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/smt.c @@ -0,0 +1,247 @@ +/* + * This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux. + * + * Copyright (c) 2017 Chelsio Communications, Inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include "cxgb4.h" +#include "smt.h" +#include "t4_msg.h" +#include "t4fw_api.h" +#include "t4_regs.h" +#include "t4_values.h" + +struct smt_data *t4_init_smt(void) +{ + unsigned int smt_size; + struct smt_data *s; + int i; + + smt_size = SMT_SIZE; + + s = kvzalloc(sizeof(*s) + smt_size * sizeof(struct smt_entry), + GFP_KERNEL); + if (!s) + return NULL; + s->smt_size = smt_size; + rwlock_init(&s->lock); + for (i = 0; i < s->smt_size; ++i) { + s->smtab[i].idx = i; + s->smtab[i].state = SMT_STATE_UNUSED; + memset(&s->smtab[i].src_mac, 0, ETH_ALEN); + spin_lock_init(&s->smtab[i].lock); + atomic_set(&s->smtab[i].refcnt, 0); + } + return s; +} + +static struct smt_entry *find_or_alloc_smte(struct smt_data *s, u8 *smac) +{ + struct smt_entry *first_free = NULL; + struct smt_entry *e, *end; + + for (e = &s->smtab[0], end = &s->smtab[s->smt_size]; e != end; ++e) { + if (atomic_read(&e->refcnt) == 0) { + if (!first_free) + first_free = e; + } else { + if (e->state == SMT_STATE_SWITCHING) { + /* This entry is actually in use. See if we can + * re-use it ? + */ + if (memcmp(e->src_mac, smac, ETH_ALEN) == 0) + goto found_reuse; + } + } + } + + if (first_free) { + e = first_free; + goto found; + } + return NULL; + +found: + e->state = SMT_STATE_UNUSED; + +found_reuse: + return e; +} + +static void t4_smte_free(struct smt_entry *e) +{ + spin_lock_bh(&e->lock); + if (atomic_read(&e->refcnt) == 0) { /* hasn't been recycled */ + e->state = SMT_STATE_UNUSED; + } + spin_unlock_bh(&e->lock); +} + +/** + * @e: smt entry to release + * + * Releases ref count and frees up an smt entry from SMT table + */ +void cxgb4_smt_release(struct smt_entry *e) +{ + if (atomic_dec_and_test(&e->refcnt)) + t4_smte_free(e); +} +EXPORT_SYMBOL(cxgb4_smt_release); + +void do_smt_write_rpl(struct adapter *adap, const struct cpl_smt_write_rpl *rpl) +{ + unsigned int smtidx = TID_TID_G(GET_TID(rpl)); + struct smt_data *s = adap->smt; + + if (unlikely(rpl->status != CPL_ERR_NONE)) { + struct smt_entry *e = &s->smtab[smtidx]; + + dev_err(adap->pdev_dev, + "Unexpected SMT_WRITE_RPL status %u for entry %u\n", + rpl->status, smtidx); + spin_lock(&e->lock); + e->state = SMT_STATE_ERROR; + spin_unlock(&e->lock); + return; + } +} + +static int write_smt_entry(struct adapter *adapter, struct smt_entry *e) +{ + struct cpl_t6_smt_write_req *t6req; + struct smt_data *s = adapter->smt; + struct cpl_smt_write_req *req; + struct sk_buff *skb; + int size; + u8 row; + + if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5) { + size = sizeof(*req); + skb = alloc_skb(size, GFP_ATOMIC); + if (!skb) + return -ENOMEM; + /* Source MAC Table (SMT) contains 256 SMAC entries + * organized in 128 rows of 2 entries each. + */ + req = (struct cpl_smt_write_req *)__skb_put(skb, size); + INIT_TP_WR(req, 0); + + /* Each row contains an SMAC pair. + * LSB selects the SMAC entry within a row + */ + row = (e->idx >> 1); + if (e->idx & 1) { + req->pfvf1 = 0x0; + memcpy(req->src_mac1, e->src_mac, ETH_ALEN); + + /* fill pfvf0/src_mac0 with entry + * at prev index from smt-tab. + */ + req->pfvf0 = 0x0; + memcpy(req->src_mac0, s->smtab[e->idx - 1].src_mac, + ETH_ALEN); + } else { + req->pfvf0 = 0x0; + memcpy(req->src_mac0, e->src_mac, ETH_ALEN); + + /* fill pfvf1/src_mac1 with entry + * at next index from smt-tab + */ + req->pfvf1 = 0x0; + memcpy(req->src_mac1, s->smtab[e->idx + 1].src_mac, + ETH_ALEN); + } + } else { + size = sizeof(*t6req); + skb = alloc_skb(size, GFP_ATOMIC); + if (!skb) + return -ENOMEM; + /* Source MAC Table (SMT) contains 256 SMAC entries */ + t6req = (struct cpl_t6_smt_write_req *)__skb_put(skb, size); + INIT_TP_WR(t6req, 0); + req = (struct cpl_smt_write_req *)t6req; + + /* fill pfvf0/src_mac0 from smt-tab */ + req->pfvf0 = 0x0; + memcpy(req->src_mac0, s->smtab[e->idx].src_mac, ETH_ALEN); + row = e->idx; + } + + OPCODE_TID(req) = + htonl(MK_OPCODE_TID(CPL_SMT_WRITE_REQ, e->idx | + TID_QID_V(adapter->sge.fw_evtq.abs_id))); + req->params = htonl(SMTW_NORPL_V(0) | + SMTW_IDX_V(row) | + SMTW_OVLAN_IDX_V(0)); + t4_mgmt_tx(adapter, skb); + return 0; +} + +static struct smt_entry *t4_smt_alloc_switching(struct adapter *adap, u16 pfvf, + u8 *smac) +{ + struct smt_data *s = adap->smt; + struct smt_entry *e; + + write_lock_bh(&s->lock); + e = find_or_alloc_smte(s, smac); + if (e) { + spin_lock(&e->lock); + if (!atomic_read(&e->refcnt)) { + atomic_set(&e->refcnt, 1); + e->state = SMT_STATE_SWITCHING; + e->pfvf = pfvf; + memcpy(e->src_mac, smac, ETH_ALEN); + write_smt_entry(adap, e); + } else { + atomic_inc(&e->refcnt); + } + spin_unlock(&e->lock); + } + write_unlock_bh(&s->lock); + return e; +} + +/** + * @dev: net_device pointer + * @smac: MAC address to add to SMT + * Returns pointer to the SMT entry created + * + * Allocates an SMT entry to be used by switching rule of a filter. + */ +struct smt_entry *cxgb4_smt_alloc_switching(struct net_device *dev, u8 *smac) +{ + struct adapter *adap = netdev2adap(dev); + + return t4_smt_alloc_switching(adap, 0x0, smac); +} +EXPORT_SYMBOL(cxgb4_smt_alloc_switching); diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.h b/drivers/net/ethernet/chelsio/cxgb4/smt.h new file mode 100644 index 000000000000..d6c2cc271398 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/smt.h @@ -0,0 +1,76 @@ +/* + * This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux. + * + * Copyright (c) 2017 Chelsio Communications, Inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __CXGB4_SMT_H +#define __CXGB4_SMT_H + +#include <linux/spinlock.h> +#include <linux/if_ether.h> +#include <linux/atomic.h> + +struct adapter; +struct cpl_smt_write_rpl; + +/* SMT related handling. Heavily adapted based on l2t ops in l2t.h/l2t.c + */ +enum { + SMT_STATE_SWITCHING, + SMT_STATE_UNUSED, + SMT_STATE_ERROR +}; + +enum { + SMT_SIZE = 256 +}; + +struct smt_entry { + u16 state; + u16 idx; + u16 pfvf; + u8 src_mac[ETH_ALEN]; + atomic_t refcnt; + spinlock_t lock; /* protect smt entry add,removal */ +}; + +struct smt_data { + unsigned int smt_size; + rwlock_t lock; + struct smt_entry smtab[0]; +}; + +struct smt_data *t4_init_smt(void); +struct smt_entry *cxgb4_smt_alloc_switching(struct net_device *dev, u8 *smac); +void cxgb4_smt_release(struct smt_entry *e); +void do_smt_write_rpl(struct adapter *p, const struct cpl_smt_write_rpl *rpl); +#endif /* __CXGB4_SMT_H */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index b65ce26ff72f..006414758f65 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -5052,23 +5052,26 @@ static unsigned int t4_use_ldst(struct adapter *adap) } /** - * t4_fw_tp_pio_rw - Access TP PIO through LDST - * @adap: the adapter - * @vals: where the indirect register values are stored/written - * @nregs: how many indirect registers to read/write - * @start_idx: index of first indirect register to read/write - * @rw: Read (1) or Write (0) + * t4_tp_fw_ldst_rw - Access TP indirect register through LDST + * @adap: the adapter + * @cmd: TP fw ldst address space type + * @vals: where the indirect register values are stored/written + * @nregs: how many indirect registers to read/write + * @start_idx: index of first indirect register to read/write + * @rw: Read (1) or Write (0) + * @sleep_ok: if true we may sleep while awaiting command completion * - * Access TP PIO registers through LDST + * Access TP indirect registers through LDST */ -static void t4_fw_tp_pio_rw(struct adapter *adap, u32 *vals, unsigned int nregs, - unsigned int start_index, unsigned int rw) +static int t4_tp_fw_ldst_rw(struct adapter *adap, int cmd, u32 *vals, + unsigned int nregs, unsigned int start_index, + unsigned int rw, bool sleep_ok) { - int ret, i; - int cmd = FW_LDST_ADDRSPC_TP_PIO; + int ret = 0; + unsigned int i; struct fw_ldst_cmd c; - for (i = 0 ; i < nregs; i++) { + for (i = 0; i < nregs; i++) { memset(&c, 0, sizeof(c)); c.op_to_addrspace = cpu_to_be32(FW_CMD_OP_V(FW_LDST_CMD) | FW_CMD_REQUEST_F | @@ -5079,26 +5082,147 @@ static void t4_fw_tp_pio_rw(struct adapter *adap, u32 *vals, unsigned int nregs, c.u.addrval.addr = cpu_to_be32(start_index + i); c.u.addrval.val = rw ? 0 : cpu_to_be32(vals[i]); - ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c); - if (!ret && rw) + ret = t4_wr_mbox_meat(adap, adap->mbox, &c, sizeof(c), &c, + sleep_ok); + if (ret) + return ret; + + if (rw) vals[i] = be32_to_cpu(c.u.addrval.val); } + return 0; +} + +/** + * t4_tp_indirect_rw - Read/Write TP indirect register through LDST or backdoor + * @adap: the adapter + * @reg_addr: Address Register + * @reg_data: Data register + * @buff: where the indirect register values are stored/written + * @nregs: how many indirect registers to read/write + * @start_index: index of first indirect register to read/write + * @rw: READ(1) or WRITE(0) + * @sleep_ok: if true we may sleep while awaiting command completion + * + * Read/Write TP indirect registers through LDST if possible. + * Else, use backdoor access + **/ +static void t4_tp_indirect_rw(struct adapter *adap, u32 reg_addr, u32 reg_data, + u32 *buff, u32 nregs, u32 start_index, int rw, + bool sleep_ok) +{ + int rc = -EINVAL; + int cmd; + + switch (reg_addr) { + case TP_PIO_ADDR_A: + cmd = FW_LDST_ADDRSPC_TP_PIO; + break; + case TP_TM_PIO_ADDR_A: + cmd = FW_LDST_ADDRSPC_TP_TM_PIO; + break; + case TP_MIB_INDEX_A: + cmd = FW_LDST_ADDRSPC_TP_MIB; + break; + default: + goto indirect_access; + } + + if (t4_use_ldst(adap)) + rc = t4_tp_fw_ldst_rw(adap, cmd, buff, nregs, start_index, rw, + sleep_ok); + +indirect_access: + + if (rc) { + if (rw) + t4_read_indirect(adap, reg_addr, reg_data, buff, nregs, + start_index); + else + t4_write_indirect(adap, reg_addr, reg_data, buff, nregs, + start_index); + } +} + +/** + * t4_tp_pio_read - Read TP PIO registers + * @adap: the adapter + * @buff: where the indirect register values are written + * @nregs: how many indirect registers to read + * @start_index: index of first indirect register to read + * @sleep_ok: if true we may sleep while awaiting command completion + * + * Read TP PIO Registers + **/ +void t4_tp_pio_read(struct adapter *adap, u32 *buff, u32 nregs, + u32 start_index, bool sleep_ok) +{ + t4_tp_indirect_rw(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, buff, nregs, + start_index, 1, sleep_ok); +} + +/** + * t4_tp_pio_write - Write TP PIO registers + * @adap: the adapter + * @buff: where the indirect register values are stored + * @nregs: how many indirect registers to write + * @start_index: index of first indirect register to write + * @sleep_ok: if true we may sleep while awaiting command completion + * + * Write TP PIO Registers + **/ +static void t4_tp_pio_write(struct adapter *adap, u32 *buff, u32 nregs, + u32 start_index, bool sleep_ok) +{ + t4_tp_indirect_rw(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, buff, nregs, + start_index, 0, sleep_ok); +} + +/** + * t4_tp_tm_pio_read - Read TP TM PIO registers + * @adap: the adapter + * @buff: where the indirect register values are written + * @nregs: how many indirect registers to read + * @start_index: index of first indirect register to read + * @sleep_ok: if true we may sleep while awaiting command completion + * + * Read TP TM PIO Registers + **/ +void t4_tp_tm_pio_read(struct adapter *adap, u32 *buff, u32 nregs, + u32 start_index, bool sleep_ok) +{ + t4_tp_indirect_rw(adap, TP_TM_PIO_ADDR_A, TP_TM_PIO_DATA_A, buff, + nregs, start_index, 1, sleep_ok); +} + +/** + * t4_tp_mib_read - Read TP MIB registers + * @adap: the adapter + * @buff: where the indirect register values are written + * @nregs: how many indirect registers to read + * @start_index: index of first indirect register to read + * @sleep_ok: if true we may sleep while awaiting command completion + * + * Read TP MIB Registers + **/ +void t4_tp_mib_read(struct adapter *adap, u32 *buff, u32 nregs, u32 start_index, + bool sleep_ok) +{ + t4_tp_indirect_rw(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, buff, nregs, + start_index, 1, sleep_ok); } /** * t4_read_rss_key - read the global RSS key * @adap: the adapter * @key: 10-entry array holding the 320-bit RSS key + * @sleep_ok: if true we may sleep while awaiting command completion * * Reads the global 320-bit RSS key. */ -void t4_read_rss_key(struct adapter *adap, u32 *key) +void t4_read_rss_key(struct adapter *adap, u32 *key, bool sleep_ok) { - if (t4_use_ldst(adap)) - t4_fw_tp_pio_rw(adap, key, 10, TP_RSS_SECRET_KEY0_A, 1); - else - t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, key, 10, - TP_RSS_SECRET_KEY0_A); + t4_tp_pio_read(adap, key, 10, TP_RSS_SECRET_KEY0_A, sleep_ok); } /** @@ -5106,12 +5230,14 @@ void t4_read_rss_key(struct adapter *adap, u32 *key) * @adap: the adapter * @key: 10-entry array holding the 320-bit RSS key * @idx: which RSS key to write + * @sleep_ok: if true we may sleep while awaiting command completion * * Writes one of the RSS keys with the given 320-bit value. If @idx is * 0..15 the corresponding entry in the RSS key table is written, * otherwise the global RSS key is written. */ -void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx) +void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx, + bool sleep_ok) { u8 rss_key_addr_cnt = 16; u32 vrt = t4_read_reg(adap, TP_RSS_CONFIG_VRT_A); @@ -5124,11 +5250,7 @@ void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx) (vrt & KEYEXTEND_F) && (KEYMODE_G(vrt) == 3)) rss_key_addr_cnt = 32; - if (t4_use_ldst(adap)) - t4_fw_tp_pio_rw(adap, (void *)key, 10, TP_RSS_SECRET_KEY0_A, 0); - else - t4_write_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, key, 10, - TP_RSS_SECRET_KEY0_A); + t4_tp_pio_write(adap, (void *)key, 10, TP_RSS_SECRET_KEY0_A, sleep_ok); if (idx >= 0 && idx < rss_key_addr_cnt) { if (rss_key_addr_cnt > 16) @@ -5146,19 +5268,15 @@ void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx) * @adapter: the adapter * @index: the entry in the PF RSS table to read * @valp: where to store the returned value + * @sleep_ok: if true we may sleep while awaiting command completion * * Reads the PF RSS Configuration Table at the specified index and returns * the value found there. */ void t4_read_rss_pf_config(struct adapter *adapter, unsigned int index, - u32 *valp) + u32 *valp, bool sleep_ok) { - if (t4_use_ldst(adapter)) - t4_fw_tp_pio_rw(adapter, valp, 1, - TP_RSS_PF0_CONFIG_A + index, 1); - else - t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A, - valp, 1, TP_RSS_PF0_CONFIG_A + index); + t4_tp_pio_read(adapter, valp, 1, TP_RSS_PF0_CONFIG_A + index, sleep_ok); } /** @@ -5167,12 +5285,13 @@ void t4_read_rss_pf_config(struct adapter *adapter, unsigned int index, * @index: the entry in the VF RSS table to read * @vfl: where to store the returned VFL * @vfh: where to store the returned VFH + * @sleep_ok: if true we may sleep while awaiting command completion * * Reads the VF RSS Configuration Table at the specified index and returns * the (VFL, VFH) values found there. */ void t4_read_rss_vf_config(struct adapter *adapter, unsigned int index, - u32 *vfl, u32 *vfh) + u32 *vfl, u32 *vfh, bool sleep_ok) { u32 vrt, mask, data; @@ -5193,50 +5312,37 @@ void t4_read_rss_vf_config(struct adapter *adapter, unsigned int index, /* Grab the VFL/VFH values ... */ - if (t4_use_ldst(adapter)) { - t4_fw_tp_pio_rw(adapter, vfl, 1, TP_RSS_VFL_CONFIG_A, 1); - t4_fw_tp_pio_rw(adapter, vfh, 1, TP_RSS_VFH_CONFIG_A, 1); - } else { - t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A, - vfl, 1, TP_RSS_VFL_CONFIG_A); - t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A, - vfh, 1, TP_RSS_VFH_CONFIG_A); - } + t4_tp_pio_read(adapter, vfl, 1, TP_RSS_VFL_CONFIG_A, sleep_ok); + t4_tp_pio_read(adapter, vfh, 1, TP_RSS_VFH_CONFIG_A, sleep_ok); } /** * t4_read_rss_pf_map - read PF RSS Map * @adapter: the adapter + * @sleep_ok: if true we may sleep while awaiting command completion * * Reads the PF RSS Map register and returns its value. */ -u32 t4_read_rss_pf_map(struct adapter *adapter) +u32 t4_read_rss_pf_map(struct adapter *adapter, bool sleep_ok) { u32 pfmap; - if (t4_use_ldst(adapter)) - t4_fw_tp_pio_rw(adapter, &pfmap, 1, TP_RSS_PF_MAP_A, 1); - else - t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A, - &pfmap, 1, TP_RSS_PF_MAP_A); + t4_tp_pio_read(adapter, &pfmap, 1, TP_RSS_PF_MAP_A, sleep_ok); return pfmap; } /** * t4_read_rss_pf_mask - read PF RSS Mask * @adapter: the adapter + * @sleep_ok: if true we may sleep while awaiting command completion * * Reads the PF RSS Mask register and returns its value. */ -u32 t4_read_rss_pf_mask(struct adapter *adapter) +u32 t4_read_rss_pf_mask(struct adapter *adapter, bool sleep_ok) { u32 pfmask; - if (t4_use_ldst(adapter)) - t4_fw_tp_pio_rw(adapter, &pfmask, 1, TP_RSS_PF_MSK_A, 1); - else - t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A, - &pfmask, 1, TP_RSS_PF_MSK_A); + t4_tp_pio_read(adapter, &pfmask, 1, TP_RSS_PF_MSK_A, sleep_ok); return pfmask; } @@ -5245,12 +5351,13 @@ u32 t4_read_rss_pf_mask(struct adapter *adapter) * @adap: the adapter * @v4: holds the TCP/IP counter values * @v6: holds the TCP/IPv6 counter values + * @sleep_ok: if true we may sleep while awaiting command completion * * Returns the values of TP's TCP/IP and TCP/IPv6 MIB counters. * Either @v4 or @v6 may be %NULL to skip the corresponding stats. */ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4, - struct tp_tcp_stats *v6) + struct tp_tcp_stats *v6, bool sleep_ok) { u32 val[TP_MIB_TCP_RXT_SEG_LO_A - TP_MIB_TCP_OUT_RST_A + 1]; @@ -5259,16 +5366,16 @@ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4, #define STAT64(x) (((u64)STAT(x##_HI) << 32) | STAT(x##_LO)) if (v4) { - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val, - ARRAY_SIZE(val), TP_MIB_TCP_OUT_RST_A); + t4_tp_mib_read(adap, val, ARRAY_SIZE(val), + TP_MIB_TCP_OUT_RST_A, sleep_ok); v4->tcp_out_rsts = STAT(OUT_RST); v4->tcp_in_segs = STAT64(IN_SEG); v4->tcp_out_segs = STAT64(OUT_SEG); v4->tcp_retrans_segs = STAT64(RXT_SEG); } if (v6) { - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val, - ARRAY_SIZE(val), TP_MIB_TCP_V6OUT_RST_A); + t4_tp_mib_read(adap, val, ARRAY_SIZE(val), + TP_MIB_TCP_V6OUT_RST_A, sleep_ok); v6->tcp_out_rsts = STAT(OUT_RST); v6->tcp_in_segs = STAT64(IN_SEG); v6->tcp_out_segs = STAT64(OUT_SEG); @@ -5283,63 +5390,66 @@ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4, * t4_tp_get_err_stats - read TP's error MIB counters * @adap: the adapter * @st: holds the counter values + * @sleep_ok: if true we may sleep while awaiting command completion * * Returns the values of TP's error counters. */ -void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st) +void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st, + bool sleep_ok) { int nchan = adap->params.arch.nchan; - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->mac_in_errs, nchan, TP_MIB_MAC_IN_ERR_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->hdr_in_errs, nchan, TP_MIB_HDR_IN_ERR_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tcp_in_errs, nchan, TP_MIB_TCP_IN_ERR_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tnl_cong_drops, nchan, TP_MIB_TNL_CNG_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->ofld_chan_drops, nchan, TP_MIB_OFD_CHN_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tnl_tx_drops, nchan, TP_MIB_TNL_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->ofld_vlan_drops, nchan, TP_MIB_OFD_VLN_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tcp6_in_errs, nchan, TP_MIB_TCP_V6IN_ERR_0_A); - - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - &st->ofld_no_neigh, 2, TP_MIB_OFD_ARP_DROP_A); + t4_tp_mib_read(adap, st->mac_in_errs, nchan, TP_MIB_MAC_IN_ERR_0_A, + sleep_ok); + t4_tp_mib_read(adap, st->hdr_in_errs, nchan, TP_MIB_HDR_IN_ERR_0_A, + sleep_ok); + t4_tp_mib_read(adap, st->tcp_in_errs, nchan, TP_MIB_TCP_IN_ERR_0_A, + sleep_ok); + t4_tp_mib_read(adap, st->tnl_cong_drops, nchan, + TP_MIB_TNL_CNG_DROP_0_A, sleep_ok); + t4_tp_mib_read(adap, st->ofld_chan_drops, nchan, + TP_MIB_OFD_CHN_DROP_0_A, sleep_ok); + t4_tp_mib_read(adap, st->tnl_tx_drops, nchan, TP_MIB_TNL_DROP_0_A, + sleep_ok); + t4_tp_mib_read(adap, st->ofld_vlan_drops, nchan, + TP_MIB_OFD_VLN_DROP_0_A, sleep_ok); + t4_tp_mib_read(adap, st->tcp6_in_errs, nchan, + TP_MIB_TCP_V6IN_ERR_0_A, sleep_ok); + t4_tp_mib_read(adap, &st->ofld_no_neigh, 2, TP_MIB_OFD_ARP_DROP_A, + sleep_ok); } /** * t4_tp_get_cpl_stats - read TP's CPL MIB counters * @adap: the adapter * @st: holds the counter values + * @sleep_ok: if true we may sleep while awaiting command completion * * Returns the values of TP's CPL counters. */ -void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st) +void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st, + bool sleep_ok) { int nchan = adap->params.arch.nchan; - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->req, - nchan, TP_MIB_CPL_IN_REQ_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->rsp, - nchan, TP_MIB_CPL_OUT_RSP_0_A); + t4_tp_mib_read(adap, st->req, nchan, TP_MIB_CPL_IN_REQ_0_A, sleep_ok); + t4_tp_mib_read(adap, st->rsp, nchan, TP_MIB_CPL_OUT_RSP_0_A, sleep_ok); } /** * t4_tp_get_rdma_stats - read TP's RDMA MIB counters * @adap: the adapter * @st: holds the counter values + * @sleep_ok: if true we may sleep while awaiting command completion * * Returns the values of TP's RDMA counters. */ -void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st) +void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st, + bool sleep_ok) { - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->rqe_dfr_pkt, - 2, TP_MIB_RQE_DFR_PKT_A); + t4_tp_mib_read(adap, &st->rqe_dfr_pkt, 2, TP_MIB_RQE_DFR_PKT_A, + sleep_ok); } /** @@ -5347,20 +5457,24 @@ void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st) * @adap: the adapter * @idx: the port index * @st: holds the counter values + * @sleep_ok: if true we may sleep while awaiting command completion * * Returns the values of TP's FCoE counters for the selected port. */ void t4_get_fcoe_stats(struct adapter *adap, unsigned int idx, - struct tp_fcoe_stats *st) + struct tp_fcoe_stats *st, bool sleep_ok) { u32 val[2]; - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->frames_ddp, - 1, TP_MIB_FCOE_DDP_0_A + idx); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->frames_drop, - 1, TP_MIB_FCOE_DROP_0_A + idx); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val, - 2, TP_MIB_FCOE_BYTE_0_HI_A + 2 * idx); + t4_tp_mib_read(adap, &st->frames_ddp, 1, TP_MIB_FCOE_DDP_0_A + idx, + sleep_ok); + + t4_tp_mib_read(adap, &st->frames_drop, 1, + TP_MIB_FCOE_DROP_0_A + idx, sleep_ok); + + t4_tp_mib_read(adap, val, 2, TP_MIB_FCOE_BYTE_0_HI_A + 2 * idx, + sleep_ok); + st->octets_ddp = ((u64)val[0] << 32) | val[1]; } @@ -5368,15 +5482,16 @@ void t4_get_fcoe_stats(struct adapter *adap, unsigned int idx, * t4_get_usm_stats - read TP's non-TCP DDP MIB counters * @adap: the adapter * @st: holds the counter values + * @sleep_ok: if true we may sleep while awaiting command completion * * Returns the values of TP's counters for non-TCP directly-placed packets. */ -void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st) +void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st, + bool sleep_ok) { u32 val[4]; - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val, 4, - TP_MIB_USM_PKTS_A); + t4_tp_mib_read(adap, val, 4, TP_MIB_USM_PKTS_A, sleep_ok); st->frames = val[0]; st->drops = val[1]; st->octets = ((u64)val[2] << 32) | val[3]; @@ -8205,7 +8320,7 @@ struct flash_desc { u32 size_mb; }; -static int get_flash_params(struct adapter *adap) +static int t4_get_flash_params(struct adapter *adap) { /* Table for non-Numonix supported flash parts. Numonix parts are left * to the preexisting code. All flash parts have 64KB sectors. @@ -8214,40 +8329,137 @@ static int get_flash_params(struct adapter *adap) { 0x150201, 4 << 20 }, /* Spansion 4MB S25FL032P */ }; + unsigned int part, manufacturer; + unsigned int density, size; + u32 flashid = 0; int ret; - u32 info; + + /* Issue a Read ID Command to the Flash part. We decode supported + * Flash parts and their sizes from this. There's a newer Query + * Command which can retrieve detailed geometry information but many + * Flash parts don't support it. + */ ret = sf1_write(adap, 1, 1, 0, SF_RD_ID); if (!ret) - ret = sf1_read(adap, 3, 0, 1, &info); + ret = sf1_read(adap, 3, 0, 1, &flashid); t4_write_reg(adap, SF_OP_A, 0); /* unlock SF */ if (ret) return ret; - for (ret = 0; ret < ARRAY_SIZE(supported_flash); ++ret) - if (supported_flash[ret].vendor_and_model_id == info) { - adap->params.sf_size = supported_flash[ret].size_mb; + /* Check to see if it's one of our non-standard supported Flash parts. + */ + for (part = 0; part < ARRAY_SIZE(supported_flash); part++) + if (supported_flash[part].vendor_and_model_id == flashid) { + adap->params.sf_size = supported_flash[part].size_mb; adap->params.sf_nsec = adap->params.sf_size / SF_SEC_SIZE; - return 0; + goto found; } - if ((info & 0xff) != 0x20) /* not a Numonix flash */ - return -EINVAL; - info >>= 16; /* log2 of size */ - if (info >= 0x14 && info < 0x18) - adap->params.sf_nsec = 1 << (info - 16); - else if (info == 0x18) - adap->params.sf_nsec = 64; - else + /* Decode Flash part size. The code below looks repetative with + * common encodings, but that's not guaranteed in the JEDEC + * specification for the Read JADEC ID command. The only thing that + * we're guaranteed by the JADEC specification is where the + * Manufacturer ID is in the returned result. After that each + * Manufacturer ~could~ encode things completely differently. + * Note, all Flash parts must have 64KB sectors. + */ + manufacturer = flashid & 0xff; + switch (manufacturer) { + case 0x20: { /* Micron/Numonix */ + /* This Density -> Size decoding table is taken from Micron + * Data Sheets. + */ + density = (flashid >> 16) & 0xff; + switch (density) { + case 0x14: /* 1MB */ + size = 1 << 20; + break; + case 0x15: /* 2MB */ + size = 1 << 21; + break; + case 0x16: /* 4MB */ + size = 1 << 22; + break; + case 0x17: /* 8MB */ + size = 1 << 23; + break; + case 0x18: /* 16MB */ + size = 1 << 24; + break; + case 0x19: /* 32MB */ + size = 1 << 25; + break; + case 0x20: /* 64MB */ + size = 1 << 26; + break; + case 0x21: /* 128MB */ + size = 1 << 27; + break; + case 0x22: /* 256MB */ + size = 1 << 28; + break; + + default: + dev_err(adap->pdev_dev, "Micron Flash Part has bad size, ID = %#x, Density code = %#x\n", + flashid, density); + return -EINVAL; + } + break; + } + case 0xc2: { /* Macronix */ + /* This Density -> Size decoding table is taken from Macronix + * Data Sheets. + */ + density = (flashid >> 16) & 0xff; + switch (density) { + case 0x17: /* 8MB */ + size = 1 << 23; + break; + case 0x18: /* 16MB */ + size = 1 << 24; + break; + default: + dev_err(adap->pdev_dev, "Macronix Flash Part has bad size, ID = %#x, Density code = %#x\n", + flashid, density); + return -EINVAL; + } + break; + } + case 0xef: { /* Winbond */ + /* This Density -> Size decoding table is taken from Winbond + * Data Sheets. + */ + density = (flashid >> 16) & 0xff; + switch (density) { + case 0x17: /* 8MB */ + size = 1 << 23; + break; + case 0x18: /* 16MB */ + size = 1 << 24; + break; + default: + dev_err(adap->pdev_dev, "Winbond Flash Part has bad size, ID = %#x, Density code = %#x\n", + flashid, density); + return -EINVAL; + } + break; + } + default: + dev_err(adap->pdev_dev, "Unsupported Flash Part, ID = %#x\n", + flashid); return -EINVAL; - adap->params.sf_size = 1 << info; - adap->params.sf_fw_start = - t4_read_reg(adap, CIM_BOOT_CFG_A) & BOOTADDR_M; + } + + /* Store decoded Flash size and fall through into vetting code. */ + adap->params.sf_size = size; + adap->params.sf_nsec = size / SF_SEC_SIZE; +found: if (adap->params.sf_size < FLASH_MIN_SIZE) - dev_warn(adap->pdev_dev, "WARNING!!! FLASH size %#x < %#x!!!\n", - adap->params.sf_size, FLASH_MIN_SIZE); + dev_warn(adap->pdev_dev, "WARNING: Flash Part ID %#x, size %#x < %#x\n", + flashid, adap->params.sf_size, FLASH_MIN_SIZE); return 0; } @@ -8285,7 +8497,7 @@ int t4_prep_adapter(struct adapter *adapter) get_pci_mode(adapter, &adapter->params.pci); pl_rev = REV_G(t4_read_reg(adapter, PL_REV_A)); - ret = get_flash_params(adapter); + ret = t4_get_flash_params(adapter); if (ret < 0) { dev_err(adapter->pdev_dev, "error %d identifying flash\n", ret); return ret; @@ -8567,10 +8779,11 @@ int t4_init_sge_params(struct adapter *adapter) /** * t4_init_tp_params - initialize adap->params.tp * @adap: the adapter + * @sleep_ok: if true we may sleep while awaiting command completion * * Initialize various fields of the adapter's TP Parameters structure. */ -int t4_init_tp_params(struct adapter *adap) +int t4_init_tp_params(struct adapter *adap, bool sleep_ok) { int chan; u32 v; @@ -8586,19 +8799,11 @@ int t4_init_tp_params(struct adapter *adap) /* Cache the adapter's Compressed Filter Mode and global Incress * Configuration. */ - if (t4_use_ldst(adap)) { - t4_fw_tp_pio_rw(adap, &adap->params.tp.vlan_pri_map, 1, - TP_VLAN_PRI_MAP_A, 1); - t4_fw_tp_pio_rw(adap, &adap->params.tp.ingress_config, 1, - TP_INGRESS_CONFIG_A, 1); - } else { - t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, - &adap->params.tp.vlan_pri_map, 1, - TP_VLAN_PRI_MAP_A); - t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, - &adap->params.tp.ingress_config, 1, - TP_INGRESS_CONFIG_A); - } + t4_tp_pio_read(adap, &adap->params.tp.vlan_pri_map, 1, + TP_VLAN_PRI_MAP_A, sleep_ok); + t4_tp_pio_read(adap, &adap->params.tp.ingress_config, 1, + TP_INGRESS_CONFIG_A, sleep_ok); + /* For T6, cache the adapter's compressed error vector * and passing outer header info for encapsulated packets. */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h index b0ff78da8aa2..ce4838d907da 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h @@ -50,6 +50,7 @@ enum { CPL_RX_DATA_ACK = 0xD, CPL_TX_PKT = 0xE, CPL_L2T_WRITE_REQ = 0x12, + CPL_SMT_WRITE_REQ = 0x14, CPL_TID_RELEASE = 0x1A, CPL_TX_DATA_ISO = 0x1F, @@ -60,6 +61,7 @@ enum { CPL_PEER_CLOSE = 0x26, CPL_ABORT_REQ_RSS = 0x2B, CPL_ABORT_RPL_RSS = 0x2D, + CPL_SMT_WRITE_RPL = 0x2E, CPL_RX_PHYS_ADDR = 0x30, CPL_CLOSE_CON_RPL = 0x32, @@ -681,8 +683,8 @@ struct cpl_set_tcb_field { }; /* cpl_set_tcb_field.word_cookie fields */ -#define TCB_WORD_S 0 -#define TCB_WORD(x) ((x) << TCB_WORD_S) +#define TCB_WORD_S 0 +#define TCB_WORD_V(x) ((x) << TCB_WORD_S) #define TCB_COOKIE_S 5 #define TCB_COOKIE_M 0x7 @@ -1266,6 +1268,44 @@ struct cpl_l2t_write_rpl { u8 rsvd[3]; }; +struct cpl_smt_write_req { + WR_HDR; + union opcode_tid ot; + __be32 params; + __be16 pfvf1; + u8 src_mac1[6]; + __be16 pfvf0; + u8 src_mac0[6]; +}; + +struct cpl_t6_smt_write_req { + WR_HDR; + union opcode_tid ot; + __be32 params; + __be64 tag; + __be16 pfvf0; + u8 src_mac0[6]; + __be32 local_ip; + __be32 rsvd; +}; + +struct cpl_smt_write_rpl { + union opcode_tid ot; + u8 status; + u8 rsvd[3]; +}; + +/* cpl_smt_{read,write}_req.params fields */ +#define SMTW_OVLAN_IDX_S 16 +#define SMTW_OVLAN_IDX_V(x) ((x) << SMTW_OVLAN_IDX_S) + +#define SMTW_IDX_S 20 +#define SMTW_IDX_V(x) ((x) << SMTW_IDX_S) + +#define SMTW_NORPL_S 31 +#define SMTW_NORPL_V(x) ((x) << SMTW_NORPL_S) +#define SMTW_NORPL_F SMTW_NORPL_V(1U) + struct cpl_rdma_terminate { union opcode_tid ot; __be16 rsvd; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index 633e9751a25e..8c22bb8c9fbf 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -181,6 +181,8 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x50a7), /* Custom T580-CR */ CH_PCI_ID_TABLE_FENTRY(0x50a8), /* Custom T580-KR */ CH_PCI_ID_TABLE_FENTRY(0x50a9), /* Custom T580-KR */ + CH_PCI_ID_TABLE_FENTRY(0x50aa), /* Custom T580-CR */ + CH_PCI_ID_TABLE_FENTRY(0x50ab), /* Custom T520-CR */ /* T6 adapters: */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index dac90837842b..82614e078f50 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -1447,6 +1447,8 @@ #define LKPTBLQUEUE0_M 0x3ffU #define LKPTBLQUEUE0_G(x) (((x) >> LKPTBLQUEUE0_S) & LKPTBLQUEUE0_M) +#define TP_TM_PIO_ADDR_A 0x7e18 +#define TP_TM_PIO_DATA_A 0x7e1c #define TP_PIO_ADDR_A 0x7e40 #define TP_PIO_DATA_A 0x7e44 #define TP_MIB_INDEX_A 0x7e50 diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h b/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h new file mode 100644 index 000000000000..c1c76663034d --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h @@ -0,0 +1,47 @@ +/* + * This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux. + * + * Copyright (c) 2017 Chelsio Communications, Inc. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __T4_TCB_H +#define __T4_TCB_H + +#define TCB_SMAC_SEL_W 0 +#define TCB_SMAC_SEL_S 24 +#define TCB_SMAC_SEL_M 0xffULL +#define TCB_SMAC_SEL_V(x) ((x) << TCB_SMAC_SEL_S) + +#define TCB_T_FLAGS_W 1 + +#define TF_CCTRL_CWR_S 61 + +#endif /* __T4_TCB_H */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index ca2756dcefc5..875d4a72b3ef 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -105,7 +105,8 @@ enum fw_wr_opcodes { FW_ISCSI_TX_DATA_WR = 0x45, FW_PTP_TX_PKT_WR = 0x46, FW_CRYPTO_LOOKASIDE_WR = 0X6d, - FW_LASTC2E_WR = 0x70 + FW_LASTC2E_WR = 0x70, + FW_FILTER2_WR = 0x77 }; struct fw_wr_hdr { @@ -201,6 +202,51 @@ struct fw_filter_wr { __u8 sma[6]; }; +struct fw_filter2_wr { + __be32 op_pkd; + __be32 len16_pkd; + __be64 r3; + __be32 tid_to_iq; + __be32 del_filter_to_l2tix; + __be16 ethtype; + __be16 ethtypem; + __u8 frag_to_ovlan_vldm; + __u8 smac_sel; + __be16 rx_chan_rx_rpl_iq; + __be32 maci_to_matchtypem; + __u8 ptcl; + __u8 ptclm; + __u8 ttyp; + __u8 ttypm; + __be16 ivlan; + __be16 ivlanm; + __be16 ovlan; + __be16 ovlanm; + __u8 lip[16]; + __u8 lipm[16]; + __u8 fip[16]; + __u8 fipm[16]; + __be16 lp; + __be16 lpm; + __be16 fp; + __be16 fpm; + __be16 r7; + __u8 sma[6]; + __be16 r8; + __u8 filter_type_swapmac; + __u8 natmode_to_ulp_type; + __be16 newlport; + __be16 newfport; + __u8 newlip[16]; + __u8 newfip[16]; + __be32 natseqcheck; + __be32 r9; + __be64 r10; + __be64 r11; + __be64 r12; + __be64 r13; +}; + #define FW_FILTER_WR_TID_S 12 #define FW_FILTER_WR_TID_M 0xfffff #define FW_FILTER_WR_TID_V(x) ((x) << FW_FILTER_WR_TID_S) @@ -385,6 +431,32 @@ struct fw_filter_wr { #define FW_FILTER_WR_RX_RPL_IQ_G(x) \ (((x) >> FW_FILTER_WR_RX_RPL_IQ_S) & FW_FILTER_WR_RX_RPL_IQ_M) +#define FW_FILTER2_WR_FILTER_TYPE_S 1 +#define FW_FILTER2_WR_FILTER_TYPE_M 0x1 +#define FW_FILTER2_WR_FILTER_TYPE_V(x) ((x) << FW_FILTER2_WR_FILTER_TYPE_S) +#define FW_FILTER2_WR_FILTER_TYPE_G(x) \ + (((x) >> FW_FILTER2_WR_FILTER_TYPE_S) & FW_FILTER2_WR_FILTER_TYPE_M) +#define FW_FILTER2_WR_FILTER_TYPE_F FW_FILTER2_WR_FILTER_TYPE_V(1U) + +#define FW_FILTER2_WR_NATMODE_S 5 +#define FW_FILTER2_WR_NATMODE_M 0x7 +#define FW_FILTER2_WR_NATMODE_V(x) ((x) << FW_FILTER2_WR_NATMODE_S) +#define FW_FILTER2_WR_NATMODE_G(x) \ + (((x) >> FW_FILTER2_WR_NATMODE_S) & FW_FILTER2_WR_NATMODE_M) + +#define FW_FILTER2_WR_NATFLAGCHECK_S 4 +#define FW_FILTER2_WR_NATFLAGCHECK_M 0x1 +#define FW_FILTER2_WR_NATFLAGCHECK_V(x) ((x) << FW_FILTER2_WR_NATFLAGCHECK_S) +#define FW_FILTER2_WR_NATFLAGCHECK_G(x) \ + (((x) >> FW_FILTER2_WR_NATFLAGCHECK_S) & FW_FILTER2_WR_NATFLAGCHECK_M) +#define FW_FILTER2_WR_NATFLAGCHECK_F FW_FILTER2_WR_NATFLAGCHECK_V(1U) + +#define FW_FILTER2_WR_ULP_TYPE_S 0 +#define FW_FILTER2_WR_ULP_TYPE_M 0xf +#define FW_FILTER2_WR_ULP_TYPE_V(x) ((x) << FW_FILTER2_WR_ULP_TYPE_S) +#define FW_FILTER2_WR_ULP_TYPE_G(x) \ + (((x) >> FW_FILTER2_WR_ULP_TYPE_S) & FW_FILTER2_WR_ULP_TYPE_M) + #define FW_FILTER_WR_MACI_S 23 #define FW_FILTER_WR_MACI_M 0x1ff #define FW_FILTER_WR_MACI_V(x) ((x) << FW_FILTER_WR_MACI_S) @@ -1127,6 +1199,7 @@ enum fw_params_param_dev { FW_PARAMS_PARAM_DEV_SCFGREV = 0x1A, FW_PARAMS_PARAM_DEV_VPDREV = 0x1B, FW_PARAMS_PARAM_DEV_RI_FR_NSMR_TPTE_WR = 0x1C, + FW_PARAMS_PARAM_DEV_FILTER2_WR = 0x1D, FW_PARAMS_PARAM_DEV_MPSBGMAP = 0x1E, }; diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index c87b8cc42963..13430f75496c 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -333,8 +333,8 @@ static void de_set_rx_mode (struct net_device *dev); static void de_tx (struct de_private *de); static void de_clean_rings (struct de_private *de); static void de_media_interrupt (struct de_private *de, u32 status); -static void de21040_media_timer (unsigned long data); -static void de21041_media_timer (unsigned long data); +static void de21040_media_timer (struct timer_list *t); +static void de21041_media_timer (struct timer_list *t); static unsigned int de_ok_to_advertise (struct de_private *de, u32 new_media); @@ -959,9 +959,9 @@ static void de_next_media (struct de_private *de, const u32 *media, } } -static void de21040_media_timer (unsigned long data) +static void de21040_media_timer (struct timer_list *t) { - struct de_private *de = (struct de_private *) data; + struct de_private *de = from_timer(de, t, media_timer); struct net_device *dev = de->dev; u32 status = dr32(SIAStatus); unsigned int carrier; @@ -1040,9 +1040,9 @@ static unsigned int de_ok_to_advertise (struct de_private *de, u32 new_media) return 1; } -static void de21041_media_timer (unsigned long data) +static void de21041_media_timer (struct timer_list *t) { - struct de_private *de = (struct de_private *) data; + struct de_private *de = from_timer(de, t, media_timer); struct net_device *dev = de->dev; u32 status = dr32(SIAStatus); unsigned int carrier; @@ -1999,12 +1999,9 @@ static int de_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) de->msg_enable = (debug < 0 ? DE_DEF_MSG_ENABLE : debug); de->board_idx = board_idx; spin_lock_init (&de->lock); - init_timer(&de->media_timer); - if (de->de21040) - de->media_timer.function = de21040_media_timer; - else - de->media_timer.function = de21041_media_timer; - de->media_timer.data = (unsigned long) de; + timer_setup(&de->media_timer, + de->de21040 ? de21040_media_timer : de21041_media_timer, + 0); netif_carrier_off(dev); diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c index 299812e92db7..a31b4df3e7ff 100644 --- a/drivers/net/ethernet/dec/tulip/de4x5.c +++ b/drivers/net/ethernet/dec/tulip/de4x5.c @@ -912,7 +912,7 @@ static int de4x5_init(struct net_device *dev); static int de4x5_sw_reset(struct net_device *dev); static int de4x5_rx(struct net_device *dev); static int de4x5_tx(struct net_device *dev); -static void de4x5_ast(struct net_device *dev); +static void de4x5_ast(struct timer_list *t); static int de4x5_txur(struct net_device *dev); static int de4x5_rx_ovfc(struct net_device *dev); @@ -1147,8 +1147,7 @@ de4x5_hw_init(struct net_device *dev, u_long iobase, struct device *gendev) lp->timeout = -1; lp->gendev = gendev; spin_lock_init(&lp->lock); - setup_timer(&lp->timer, (void (*)(unsigned long))de4x5_ast, - (unsigned long)dev); + timer_setup(&lp->timer, de4x5_ast, 0); de4x5_parse_params(dev); /* @@ -1741,9 +1740,10 @@ de4x5_tx(struct net_device *dev) } static void -de4x5_ast(struct net_device *dev) +de4x5_ast(struct timer_list *t) { - struct de4x5_private *lp = netdev_priv(dev); + struct de4x5_private *lp = from_timer(lp, t, timer); + struct net_device *dev = dev_get_drvdata(lp->gendev); int next_tick = DE4X5_AUTOSENSE_MS; int dt; @@ -2369,7 +2369,7 @@ autoconf_media(struct net_device *dev) lp->media = INIT; lp->tcount = 0; - de4x5_ast(dev); + de4x5_ast(&lp->timer); return lp->media; } diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c index 6585f737d08b..17ef7a28873d 100644 --- a/drivers/net/ethernet/dec/tulip/dmfe.c +++ b/drivers/net/ethernet/dec/tulip/dmfe.c @@ -331,7 +331,7 @@ static void dmfe_phy_write_1bit(void __iomem *, u32); static u16 dmfe_phy_read_1bit(void __iomem *); static u8 dmfe_sense_speed(struct dmfe_board_info *); static void dmfe_process_mode(struct dmfe_board_info *); -static void dmfe_timer(unsigned long); +static void dmfe_timer(struct timer_list *); static inline u32 cal_CRC(unsigned char *, unsigned int, u8); static void dmfe_rx_packet(struct net_device *, struct dmfe_board_info *); static void dmfe_free_tx_pkt(struct net_device *, struct dmfe_board_info *); @@ -596,7 +596,7 @@ static int dmfe_open(struct net_device *dev) netif_wake_queue(dev); /* set and active a timer process */ - setup_timer(&db->timer, dmfe_timer, (unsigned long)dev); + timer_setup(&db->timer, dmfe_timer, 0); db->timer.expires = DMFE_TIMER_WUT + HZ * 2; add_timer(&db->timer); @@ -1128,10 +1128,10 @@ static const struct ethtool_ops netdev_ethtool_ops = { * Dynamic media sense, allocate Rx buffer... */ -static void dmfe_timer(unsigned long data) +static void dmfe_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct dmfe_board_info *db = netdev_priv(dev); + struct dmfe_board_info *db = from_timer(db, t, timer); + struct net_device *dev = pci_get_drvdata(db->pdev); void __iomem *ioaddr = db->ioaddr; u32 tmp_cr8; unsigned char tmp_cr12; diff --git a/drivers/net/ethernet/dec/tulip/interrupt.c b/drivers/net/ethernet/dec/tulip/interrupt.c index 8df80880ecaa..c1ca0765d56d 100644 --- a/drivers/net/ethernet/dec/tulip/interrupt.c +++ b/drivers/net/ethernet/dec/tulip/interrupt.c @@ -102,10 +102,10 @@ int tulip_refill_rx(struct net_device *dev) #ifdef CONFIG_TULIP_NAPI -void oom_timer(unsigned long data) +void oom_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct tulip_private *tp = netdev_priv(dev); + struct tulip_private *tp = from_timer(tp, t, oom_timer); + napi_schedule(&tp->napi); } diff --git a/drivers/net/ethernet/dec/tulip/pnic.c b/drivers/net/ethernet/dec/tulip/pnic.c index 7bcccf5cac7a..3fb39e32e1b4 100644 --- a/drivers/net/ethernet/dec/tulip/pnic.c +++ b/drivers/net/ethernet/dec/tulip/pnic.c @@ -84,10 +84,10 @@ void pnic_lnk_change(struct net_device *dev, int csr5) } } -void pnic_timer(unsigned long data) +void pnic_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct tulip_private *tp = netdev_priv(dev); + struct tulip_private *tp = from_timer(tp, t, timer); + struct net_device *dev = tp->dev; void __iomem *ioaddr = tp->base_addr; int next_tick = 60*HZ; diff --git a/drivers/net/ethernet/dec/tulip/pnic2.c b/drivers/net/ethernet/dec/tulip/pnic2.c index 5895fc43f6e0..412adaa7fdf8 100644 --- a/drivers/net/ethernet/dec/tulip/pnic2.c +++ b/drivers/net/ethernet/dec/tulip/pnic2.c @@ -76,10 +76,10 @@ #include <linux/delay.h> -void pnic2_timer(unsigned long data) +void pnic2_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct tulip_private *tp = netdev_priv(dev); + struct tulip_private *tp = from_timer(tp, t, timer); + struct net_device *dev = tp->dev; void __iomem *ioaddr = tp->base_addr; int next_tick = 60*HZ; diff --git a/drivers/net/ethernet/dec/tulip/timer.c b/drivers/net/ethernet/dec/tulip/timer.c index 523d9dde50a2..642e9dfc5451 100644 --- a/drivers/net/ethernet/dec/tulip/timer.c +++ b/drivers/net/ethernet/dec/tulip/timer.c @@ -137,10 +137,10 @@ void tulip_media_task(struct work_struct *work) } -void mxic_timer(unsigned long data) +void mxic_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct tulip_private *tp = netdev_priv(dev); + struct tulip_private *tp = from_timer(tp, t, timer); + struct net_device *dev = tp->dev; void __iomem *ioaddr = tp->base_addr; int next_tick = 60*HZ; @@ -154,10 +154,10 @@ void mxic_timer(unsigned long data) } -void comet_timer(unsigned long data) +void comet_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct tulip_private *tp = netdev_priv(dev); + struct tulip_private *tp = from_timer(tp, t, timer); + struct net_device *dev = tp->dev; int next_tick = 2*HZ; if (tulip_debug > 1) diff --git a/drivers/net/ethernet/dec/tulip/tulip.h b/drivers/net/ethernet/dec/tulip/tulip.h index 06660dbc44b7..b458140aeaef 100644 --- a/drivers/net/ethernet/dec/tulip/tulip.h +++ b/drivers/net/ethernet/dec/tulip/tulip.h @@ -43,7 +43,7 @@ struct tulip_chip_table { int io_size; int valid_intrs; /* CSR7 interrupt enable settings */ int flags; - void (*media_timer) (unsigned long); + void (*media_timer) (struct timer_list *); work_func_t media_task; }; @@ -476,7 +476,7 @@ void t21142_lnk_change(struct net_device *dev, int csr5); /* PNIC2.c */ void pnic2_lnk_change(struct net_device *dev, int csr5); -void pnic2_timer(unsigned long data); +void pnic2_timer(struct timer_list *t); void pnic2_start_nway(struct net_device *dev); void pnic2_lnk_change(struct net_device *dev, int csr5); @@ -504,19 +504,19 @@ void tulip_find_mii (struct net_device *dev, int board_idx); /* pnic.c */ void pnic_do_nway(struct net_device *dev); void pnic_lnk_change(struct net_device *dev, int csr5); -void pnic_timer(unsigned long data); +void pnic_timer(struct timer_list *t); /* timer.c */ void tulip_media_task(struct work_struct *work); -void mxic_timer(unsigned long data); -void comet_timer(unsigned long data); +void mxic_timer(struct timer_list *t); +void comet_timer(struct timer_list *t); /* tulip_core.c */ extern int tulip_debug; extern const char * const medianame[]; extern const char tulip_media_cap[]; extern const struct tulip_chip_table tulip_tbl[]; -void oom_timer(unsigned long data); +void oom_timer(struct timer_list *t); extern u8 t21040_csr13[]; static inline void tulip_start_rxtx(struct tulip_private *tp) diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index 851b6d1f5a42..00d02a0967d0 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -123,10 +123,10 @@ int tulip_debug = TULIP_DEBUG; int tulip_debug = 1; #endif -static void tulip_timer(unsigned long data) +static void tulip_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct tulip_private *tp = netdev_priv(dev); + struct tulip_private *tp = from_timer(tp, t, timer); + struct net_device *dev = tp->dev; if (netif_running(dev)) schedule_work(&tp->media_work); @@ -505,7 +505,7 @@ media_picked: tp->timer.expires = RUN_AT(next_tick); add_timer(&tp->timer); #ifdef CONFIG_TULIP_NAPI - setup_timer(&tp->oom_timer, oom_timer, (unsigned long)dev); + timer_setup(&tp->oom_timer, oom_timer, 0); #endif } @@ -780,8 +780,7 @@ static void tulip_down (struct net_device *dev) spin_unlock_irqrestore (&tp->lock, flags); - setup_timer(&tp->timer, tulip_tbl[tp->chip_id].media_timer, - (unsigned long)dev); + timer_setup(&tp->timer, tulip_tbl[tp->chip_id].media_timer, 0); dev->if_port = tp->saved_if_port; @@ -1470,8 +1469,7 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->csr0 = csr0; spin_lock_init(&tp->lock); spin_lock_init(&tp->mii_lock); - setup_timer(&tp->timer, tulip_tbl[tp->chip_id].media_timer, - (unsigned long)dev); + timer_setup(&tp->timer, tulip_tbl[tp->chip_id].media_timer, 0); INIT_WORK(&tp->media_work, tulip_tbl[tp->chip_id].media_task); diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c index 5fbbc0caba99..488a744084c9 100644 --- a/drivers/net/ethernet/dec/tulip/uli526x.c +++ b/drivers/net/ethernet/dec/tulip/uli526x.c @@ -241,7 +241,7 @@ static void phy_write_1bit(struct uli526x_board_info *db, u32); static u16 phy_read_1bit(struct uli526x_board_info *db); static u8 uli526x_sense_speed(struct uli526x_board_info *); static void uli526x_process_mode(struct uli526x_board_info *); -static void uli526x_timer(unsigned long); +static void uli526x_timer(struct timer_list *t); static void uli526x_rx_packet(struct net_device *, struct uli526x_board_info *); static void uli526x_free_tx_pkt(struct net_device *, struct uli526x_board_info *); static void uli526x_reuse_skb(struct uli526x_board_info *, struct sk_buff *); @@ -491,7 +491,7 @@ static int uli526x_open(struct net_device *dev) netif_wake_queue(dev); /* set and active a timer process */ - setup_timer(&db->timer, uli526x_timer, (unsigned long)dev); + timer_setup(&db->timer, uli526x_timer, 0); db->timer.expires = ULI526X_TIMER_WUT + HZ * 2; add_timer(&db->timer); @@ -1021,10 +1021,10 @@ static const struct ethtool_ops netdev_ethtool_ops = { * Dynamic media sense, allocate Rx buffer... */ -static void uli526x_timer(unsigned long data) +static void uli526x_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *) data; - struct uli526x_board_info *db = netdev_priv(dev); + struct uli526x_board_info *db = from_timer(db, t, timer); + struct net_device *dev = pci_get_drvdata(db->pdev); struct uli_phy_ops *phy = &db->phy; void __iomem *ioaddr = db->ioaddr; unsigned long flags; diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c index 6f88d687b6d2..70cb2d689c2c 100644 --- a/drivers/net/ethernet/dec/tulip/winbond-840.c +++ b/drivers/net/ethernet/dec/tulip/winbond-840.c @@ -327,7 +327,7 @@ static int mdio_read(struct net_device *dev, int phy_id, int location); static void mdio_write(struct net_device *dev, int phy_id, int location, int value); static int netdev_open(struct net_device *dev); static int update_link(struct net_device *dev); -static void netdev_timer(unsigned long data); +static void netdev_timer(struct timer_list *t); static void init_rxtx_rings(struct net_device *dev); static void free_rxtx_rings(struct netdev_private *np); static void init_registers(struct net_device *dev); @@ -655,7 +655,7 @@ static int netdev_open(struct net_device *dev) netdev_dbg(dev, "Done netdev_open()\n"); /* Set the timer to check for link beat. */ - setup_timer(&np->timer, netdev_timer, (unsigned long)dev); + timer_setup(&np->timer, netdev_timer, 0); np->timer.expires = jiffies + 1*HZ; add_timer(&np->timer); return 0; @@ -772,10 +772,10 @@ static inline void update_csr6(struct net_device *dev, int new) np->mii_if.full_duplex = 1; } -static void netdev_timer(unsigned long data) +static void netdev_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct netdev_private *np = netdev_priv(dev); + struct netdev_private *np = from_timer(np, t, timer); + struct net_device *dev = pci_get_drvdata(np->pci_dev); void __iomem *ioaddr = np->base_addr; if (debug > 2) diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index 778f974e2928..a2f6758d38dd 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -68,7 +68,7 @@ static const int max_intrloop = 50; static const int multicast_filter_limit = 0x40; static int rio_open (struct net_device *dev); -static void rio_timer (unsigned long data); +static void rio_timer (struct timer_list *t); static void rio_tx_timeout (struct net_device *dev); static netdev_tx_t start_xmit (struct sk_buff *skb, struct net_device *dev); static irqreturn_t rio_interrupt (int irq, void *dev_instance); @@ -644,7 +644,7 @@ static int rio_open(struct net_device *dev) return i; } - setup_timer(&np->timer, rio_timer, (unsigned long)dev); + timer_setup(&np->timer, rio_timer, 0); np->timer.expires = jiffies + 1 * HZ; add_timer(&np->timer); @@ -655,10 +655,10 @@ static int rio_open(struct net_device *dev) } static void -rio_timer (unsigned long data) +rio_timer (struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct netdev_private *np = netdev_priv(dev); + struct netdev_private *np = from_timer(np, t, timer); + struct net_device *dev = pci_get_drvdata(np->pdev); unsigned int entry; int next_tick = 1*HZ; unsigned long flags; diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 9ed8e4b81530..78db8e62a83f 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -21,6 +21,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/clk.h> #include <linux/dma-mapping.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> @@ -59,6 +60,9 @@ /* Min number of tx ring entries before stopping queue */ #define TX_THRESHOLD (MAX_SKB_FRAGS + 1) +#define FTGMAC_100MHZ 100000000 +#define FTGMAC_25MHZ 25000000 + struct ftgmac100 { /* Registers */ struct resource *res; @@ -96,6 +100,7 @@ struct ftgmac100 { struct napi_struct napi; struct work_struct reset_task; struct mii_bus *mii_bus; + struct clk *clk; /* Link management */ int cur_speed; @@ -1734,6 +1739,22 @@ static void ftgmac100_ncsi_handler(struct ncsi_dev *nd) nd->link_up ? "up" : "down"); } +static void ftgmac100_setup_clk(struct ftgmac100 *priv) +{ + priv->clk = devm_clk_get(priv->dev, NULL); + if (IS_ERR(priv->clk)) + return; + + clk_prepare_enable(priv->clk); + + /* Aspeed specifies a 100MHz clock is required for up to + * 1000Mbit link speeds. As NCSI is limited to 100Mbit, 25MHz + * is sufficient + */ + clk_set_rate(priv->clk, priv->use_ncsi ? FTGMAC_25MHZ : + FTGMAC_100MHZ); +} + static int ftgmac100_probe(struct platform_device *pdev) { struct resource *res; @@ -1830,6 +1851,9 @@ static int ftgmac100_probe(struct platform_device *pdev) goto err_setup_mdio; } + if (priv->is_aspeed) + ftgmac100_setup_clk(priv); + /* Default ring sizes */ priv->rx_q_entries = priv->new_rx_q_entries = DEF_RX_QUEUE_ENTRIES; priv->tx_q_entries = priv->new_tx_q_entries = DEF_TX_QUEUE_ENTRIES; @@ -1883,6 +1907,8 @@ static int ftgmac100_remove(struct platform_device *pdev) unregister_netdev(netdev); + clk_disable_unprepare(priv->clk); + /* There's a small chance the reset task will have been re-queued, * during stop, make sure it's gone before we free the structure. */ diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 42258060f142..a8d0be824149 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -385,34 +385,19 @@ out: static struct mac_device *dpaa_mac_dev_get(struct platform_device *pdev) { - struct platform_device *of_dev; struct dpaa_eth_data *eth_data; - struct device *dpaa_dev, *dev; - struct device_node *mac_node; + struct device *dpaa_dev; struct mac_device *mac_dev; dpaa_dev = &pdev->dev; eth_data = dpaa_dev->platform_data; - if (!eth_data) + if (!eth_data) { + dev_err(dpaa_dev, "eth_data missing\n"); return ERR_PTR(-ENODEV); - - mac_node = eth_data->mac_node; - - of_dev = of_find_device_by_node(mac_node); - if (!of_dev) { - dev_err(dpaa_dev, "of_find_device_by_node(%pOF) failed\n", - mac_node); - of_node_put(mac_node); - return ERR_PTR(-EINVAL); } - of_node_put(mac_node); - - dev = &of_dev->dev; - - mac_dev = dev_get_drvdata(dev); + mac_dev = eth_data->mac_dev; if (!mac_dev) { - dev_err(dpaa_dev, "dev_get_drvdata(%s) failed\n", - dev_name(dev)); + dev_err(dpaa_dev, "mac_dev missing\n"); return ERR_PTR(-EINVAL); } @@ -2435,6 +2420,44 @@ static void dpaa_eth_napi_disable(struct dpaa_priv *priv) } } +static void dpaa_adjust_link(struct net_device *net_dev) +{ + struct mac_device *mac_dev; + struct dpaa_priv *priv; + + priv = netdev_priv(net_dev); + mac_dev = priv->mac_dev; + mac_dev->adjust_link(mac_dev); +} + +static int dpaa_phy_init(struct net_device *net_dev) +{ + struct mac_device *mac_dev; + struct phy_device *phy_dev; + struct dpaa_priv *priv; + + priv = netdev_priv(net_dev); + mac_dev = priv->mac_dev; + + phy_dev = of_phy_connect(net_dev, mac_dev->phy_node, + &dpaa_adjust_link, 0, + mac_dev->phy_if); + if (!phy_dev) { + netif_err(priv, ifup, net_dev, "init_phy() failed\n"); + return -ENODEV; + } + + /* Remove any features not supported by the controller */ + phy_dev->supported &= mac_dev->if_support; + phy_dev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause); + phy_dev->advertising = phy_dev->supported; + + mac_dev->phy_dev = phy_dev; + net_dev->phydev = phy_dev; + + return 0; +} + static int dpaa_open(struct net_device *net_dev) { struct mac_device *mac_dev; @@ -2445,12 +2468,8 @@ static int dpaa_open(struct net_device *net_dev) mac_dev = priv->mac_dev; dpaa_eth_napi_enable(priv); - net_dev->phydev = mac_dev->init_phy(net_dev, priv->mac_dev); - if (!net_dev->phydev) { - netif_err(priv, ifup, net_dev, "init_phy() failed\n"); - err = -ENODEV; + if (dpaa_phy_init(net_dev)) goto phy_init_failed; - } for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) { err = fman_port_enable(mac_dev->port[i]); @@ -2658,7 +2677,13 @@ static int dpaa_eth_probe(struct platform_device *pdev) int err = 0, i, channel; struct device *dev; - dev = &pdev->dev; + /* device used for DMA mapping */ + dev = pdev->dev.parent; + err = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(40)); + if (err) { + dev_err(dev, "dma_coerce_mask_and_coherent() failed\n"); + return err; + } /* Allocate this early, so we can store relevant information in * the private area @@ -2666,7 +2691,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) net_dev = alloc_etherdev_mq(sizeof(*priv), DPAA_ETH_TXQ_NUM); if (!net_dev) { dev_err(dev, "alloc_etherdev_mq() failed\n"); - goto alloc_etherdev_mq_failed; + return -ENOMEM; } /* Do this here, so we can be verbose early */ @@ -2682,7 +2707,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) if (IS_ERR(mac_dev)) { dev_err(dev, "dpaa_mac_dev_get() failed\n"); err = PTR_ERR(mac_dev); - goto mac_probe_failed; + goto free_netdev; } /* If fsl_fm_max_frm is set to a higher value than the all-common 1500, @@ -2700,21 +2725,13 @@ static int dpaa_eth_probe(struct platform_device *pdev) priv->buf_layout[RX].priv_data_size = DPAA_RX_PRIV_DATA_SIZE; /* Rx */ priv->buf_layout[TX].priv_data_size = DPAA_TX_PRIV_DATA_SIZE; /* Tx */ - /* device used for DMA mapping */ - set_dma_ops(dev, get_dma_ops(&pdev->dev)); - err = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(40)); - if (err) { - dev_err(dev, "dma_coerce_mask_and_coherent() failed\n"); - goto dev_mask_failed; - } - /* bp init */ for (i = 0; i < DPAA_BPS_NUM; i++) { int err; dpaa_bps[i] = dpaa_bp_alloc(dev); if (IS_ERR(dpaa_bps[i])) - return PTR_ERR(dpaa_bps[i]); + goto free_dpaa_bps; /* the raw size of the buffers used for reception */ dpaa_bps[i]->raw_size = bpool_buffer_raw_size(i, DPAA_BPS_NUM); /* avoid runtime computations by keeping the usable size here */ @@ -2722,11 +2739,8 @@ static int dpaa_eth_probe(struct platform_device *pdev) dpaa_bps[i]->dev = dev; err = dpaa_bp_alloc_pool(dpaa_bps[i]); - if (err < 0) { - dpaa_bps_free(priv); - priv->dpaa_bps[i] = NULL; - goto bp_create_failed; - } + if (err < 0) + goto free_dpaa_bps; priv->dpaa_bps[i] = dpaa_bps[i]; } @@ -2737,7 +2751,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) err = dpaa_alloc_all_fqs(dev, &priv->dpaa_fq_list, &port_fqs); if (err < 0) { dev_err(dev, "dpaa_alloc_all_fqs() failed\n"); - goto fq_probe_failed; + goto free_dpaa_bps; } priv->mac_dev = mac_dev; @@ -2746,7 +2760,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) if (channel < 0) { dev_err(dev, "dpaa_get_channel() failed\n"); err = channel; - goto get_channel_failed; + goto free_dpaa_bps; } priv->channel = (u16)channel; @@ -2766,20 +2780,20 @@ static int dpaa_eth_probe(struct platform_device *pdev) err = dpaa_eth_cgr_init(priv); if (err < 0) { dev_err(dev, "Error initializing CGR\n"); - goto tx_cgr_init_failed; + goto free_dpaa_bps; } err = dpaa_ingress_cgr_init(priv); if (err < 0) { dev_err(dev, "Error initializing ingress CGR\n"); - goto rx_cgr_init_failed; + goto delete_egress_cgr; } /* Add the FQs to the interface, and make them active */ list_for_each_entry_safe(dpaa_fq, tmp, &priv->dpaa_fq_list, list) { err = dpaa_fq_init(dpaa_fq, false); if (err < 0) - goto fq_alloc_failed; + goto free_dpaa_fqs; } priv->tx_headroom = dpaa_get_headroom(&priv->buf_layout[TX]); @@ -2789,7 +2803,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) err = dpaa_eth_init_ports(mac_dev, dpaa_bps, DPAA_BPS_NUM, &port_fqs, &priv->buf_layout[0], dev); if (err) - goto init_ports_failed; + goto free_dpaa_fqs; /* Rx traffic distribution based on keygen hashing defaults to on */ priv->keygen_in_use = true; @@ -2798,7 +2812,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) if (!priv->percpu_priv) { dev_err(dev, "devm_alloc_percpu() failed\n"); err = -ENOMEM; - goto alloc_percpu_failed; + goto free_dpaa_fqs; } for_each_possible_cpu(i) { percpu_priv = per_cpu_ptr(priv->percpu_priv, i); @@ -2811,11 +2825,11 @@ static int dpaa_eth_probe(struct platform_device *pdev) /* Initialize NAPI */ err = dpaa_napi_add(net_dev); if (err < 0) - goto napi_add_failed; + goto delete_dpaa_napi; err = dpaa_netdev_init(net_dev, &dpaa_ops, tx_timeout); if (err < 0) - goto netdev_init_failed; + goto delete_dpaa_napi; dpaa_eth_sysfs_init(&net_dev->dev); @@ -2824,32 +2838,21 @@ static int dpaa_eth_probe(struct platform_device *pdev) return 0; -netdev_init_failed: -napi_add_failed: +delete_dpaa_napi: dpaa_napi_del(net_dev); -alloc_percpu_failed: -init_ports_failed: +free_dpaa_fqs: dpaa_fq_free(dev, &priv->dpaa_fq_list); -fq_alloc_failed: qman_delete_cgr_safe(&priv->ingress_cgr); qman_release_cgrid(priv->ingress_cgr.cgrid); -rx_cgr_init_failed: +delete_egress_cgr: qman_delete_cgr_safe(&priv->cgr_data.cgr); qman_release_cgrid(priv->cgr_data.cgr.cgrid); -tx_cgr_init_failed: -get_channel_failed: +free_dpaa_bps: dpaa_bps_free(priv); -bp_create_failed: -fq_probe_failed: -dev_mask_failed: -mac_probe_failed: +free_netdev: dev_set_drvdata(dev, NULL); free_netdev(net_dev); -alloc_etherdev_mq_failed: - for (i = 0; i < DPAA_BPS_NUM && dpaa_bps[i]; i++) { - if (atomic_read(&dpaa_bps[i]->refs) == 0) - devm_kfree(dev, dpaa_bps[i]); - } + return err; } diff --git a/drivers/net/ethernet/freescale/fman/Makefile b/drivers/net/ethernet/freescale/fman/Makefile index 2c38119b172c..4ae524a352a2 100644 --- a/drivers/net/ethernet/freescale/fman/Makefile +++ b/drivers/net/ethernet/freescale/fman/Makefile @@ -1,9 +1,9 @@ subdir-ccflags-y += -I$(srctree)/drivers/net/ethernet/freescale/fman -obj-$(CONFIG_FSL_FMAN) += fsl_fman.o -obj-$(CONFIG_FSL_FMAN) += fsl_fman_port.o -obj-$(CONFIG_FSL_FMAN) += fsl_mac.o +obj-$(CONFIG_FSL_FMAN) += fsl_dpaa_fman.o +obj-$(CONFIG_FSL_FMAN) += fsl_dpaa_fman_port.o +obj-$(CONFIG_FSL_FMAN) += fsl_dpaa_mac.o -fsl_fman-objs := fman_muram.o fman.o fman_sp.o fman_keygen.o -fsl_fman_port-objs := fman_port.o -fsl_mac-objs:= mac.o fman_dtsec.o fman_memac.o fman_tgec.o +fsl_dpaa_fman-objs := fman_muram.o fman.o fman_sp.o fman_keygen.o +fsl_dpaa_fman_port-objs := fman_port.o +fsl_dpaa_mac-objs:= mac.o fman_dtsec.o fman_memac.o fman_tgec.o diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 387eb4a88b72..1d6da1ea7bfb 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -57,9 +57,7 @@ struct mac_priv_s { struct device *dev; void __iomem *vaddr; u8 cell_index; - phy_interface_t phy_if; struct fman *fman; - struct device_node *phy_node; struct device_node *internal_phy_node; /* List of multicast addresses */ struct list_head mc_addr_list; @@ -106,7 +104,7 @@ static void set_fman_mac_params(struct mac_device *mac_dev, resource_size(mac_dev->res)); memcpy(¶ms->addr, mac_dev->addr, sizeof(mac_dev->addr)); params->max_speed = priv->max_speed; - params->phy_if = priv->phy_if; + params->phy_if = mac_dev->phy_if; params->basex_if = false; params->mac_id = priv->cell_index; params->fm = (void *)priv->fman; @@ -419,15 +417,12 @@ void fman_get_pause_cfg(struct mac_device *mac_dev, bool *rx_pause, } EXPORT_SYMBOL(fman_get_pause_cfg); -static void adjust_link_void(struct net_device *net_dev) +static void adjust_link_void(struct mac_device *mac_dev) { } -static void adjust_link_dtsec(struct net_device *net_dev) +static void adjust_link_dtsec(struct mac_device *mac_dev) { - struct device *dev = net_dev->dev.parent; - struct dpaa_eth_data *eth_data = dev->platform_data; - struct mac_device *mac_dev = eth_data->mac_dev; struct phy_device *phy_dev = mac_dev->phy_dev; struct fman_mac *fman_mac; bool rx_pause, tx_pause; @@ -444,14 +439,12 @@ static void adjust_link_dtsec(struct net_device *net_dev) fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause); err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause); if (err < 0) - netdev_err(net_dev, "fman_set_mac_active_pause() = %d\n", err); + dev_err(mac_dev->priv->dev, "fman_set_mac_active_pause() = %d\n", + err); } -static void adjust_link_memac(struct net_device *net_dev) +static void adjust_link_memac(struct mac_device *mac_dev) { - struct device *dev = net_dev->dev.parent; - struct dpaa_eth_data *eth_data = dev->platform_data; - struct mac_device *mac_dev = eth_data->mac_dev; struct phy_device *phy_dev = mac_dev->phy_dev; struct fman_mac *fman_mac; bool rx_pause, tx_pause; @@ -463,60 +456,12 @@ static void adjust_link_memac(struct net_device *net_dev) fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause); err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause); if (err < 0) - netdev_err(net_dev, "fman_set_mac_active_pause() = %d\n", err); -} - -/* Initializes driver's PHY state, and attaches to the PHY. - * Returns 0 on success. - */ -static struct phy_device *init_phy(struct net_device *net_dev, - struct mac_device *mac_dev, - void (*adj_lnk)(struct net_device *)) -{ - struct phy_device *phy_dev; - struct mac_priv_s *priv = mac_dev->priv; - - phy_dev = of_phy_connect(net_dev, priv->phy_node, adj_lnk, 0, - priv->phy_if); - if (!phy_dev) { - netdev_err(net_dev, "Could not connect to PHY\n"); - return NULL; - } - - /* Remove any features not supported by the controller */ - phy_dev->supported &= mac_dev->if_support; - /* Enable the symmetric and asymmetric PAUSE frame advertisements, - * as most of the PHY drivers do not enable them by default. - */ - phy_dev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause); - phy_dev->advertising = phy_dev->supported; - - mac_dev->phy_dev = phy_dev; - - return phy_dev; -} - -static struct phy_device *dtsec_init_phy(struct net_device *net_dev, - struct mac_device *mac_dev) -{ - return init_phy(net_dev, mac_dev, &adjust_link_dtsec); -} - -static struct phy_device *tgec_init_phy(struct net_device *net_dev, - struct mac_device *mac_dev) -{ - return init_phy(net_dev, mac_dev, adjust_link_void); -} - -static struct phy_device *memac_init_phy(struct net_device *net_dev, - struct mac_device *mac_dev) -{ - return init_phy(net_dev, mac_dev, &adjust_link_memac); + dev_err(mac_dev->priv->dev, "fman_set_mac_active_pause() = %d\n", + err); } static void setup_dtsec(struct mac_device *mac_dev) { - mac_dev->init_phy = dtsec_init_phy; mac_dev->init = dtsec_initialization; mac_dev->set_promisc = dtsec_set_promiscuous; mac_dev->change_addr = dtsec_modify_mac_address; @@ -528,14 +473,13 @@ static void setup_dtsec(struct mac_device *mac_dev) mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; - + mac_dev->adjust_link = adjust_link_dtsec; mac_dev->priv->enable = dtsec_enable; mac_dev->priv->disable = dtsec_disable; } static void setup_tgec(struct mac_device *mac_dev) { - mac_dev->init_phy = tgec_init_phy; mac_dev->init = tgec_initialization; mac_dev->set_promisc = tgec_set_promiscuous; mac_dev->change_addr = tgec_modify_mac_address; @@ -547,14 +491,13 @@ static void setup_tgec(struct mac_device *mac_dev) mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; - + mac_dev->adjust_link = adjust_link_void; mac_dev->priv->enable = tgec_enable; mac_dev->priv->disable = tgec_disable; } static void setup_memac(struct mac_device *mac_dev) { - mac_dev->init_phy = memac_init_phy; mac_dev->init = memac_initialization; mac_dev->set_promisc = memac_set_promiscuous; mac_dev->change_addr = memac_modify_mac_address; @@ -566,7 +509,7 @@ static void setup_memac(struct mac_device *mac_dev) mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; - + mac_dev->adjust_link = adjust_link_memac; mac_dev->priv->enable = memac_enable; mac_dev->priv->disable = memac_disable; } @@ -599,8 +542,7 @@ static const u16 phy2speed[] = { }; static struct platform_device *dpaa_eth_add_device(int fman_id, - struct mac_device *mac_dev, - struct device_node *node) + struct mac_device *mac_dev) { struct platform_device *pdev; struct dpaa_eth_data data; @@ -613,17 +555,14 @@ static struct platform_device *dpaa_eth_add_device(int fman_id, data.mac_dev = mac_dev; data.mac_hw_id = priv->cell_index; data.fman_hw_id = fman_id; - data.mac_node = node; mutex_lock(ð_lock); - pdev = platform_device_alloc("dpaa-ethernet", dpaa_eth_dev_cnt); if (!pdev) { ret = -ENOMEM; goto no_mem; } - pdev->dev.of_node = node; pdev->dev.parent = priv->dev; set_dma_ops(&pdev->dev, get_dma_ops(priv->dev)); @@ -706,9 +645,6 @@ static int mac_probe(struct platform_device *_of_dev) goto _return; } - /* Register mac_dev */ - dev_set_drvdata(dev, mac_dev); - INIT_LIST_HEAD(&priv->mc_addr_list); /* Get the FM node */ @@ -717,7 +653,7 @@ static int mac_probe(struct platform_device *_of_dev) dev_err(dev, "of_get_parent(%pOF) failed\n", mac_node); err = -EINVAL; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } of_dev = of_find_device_by_node(dev_node); @@ -751,7 +687,7 @@ static int mac_probe(struct platform_device *_of_dev) if (err < 0) { dev_err(dev, "of_address_to_resource(%pOF) = %d\n", mac_node, err); - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } mac_dev->res = __devm_request_region(dev, @@ -761,7 +697,7 @@ static int mac_probe(struct platform_device *_of_dev) if (!mac_dev->res) { dev_err(dev, "__devm_request_mem_region(mac) failed\n"); err = -EBUSY; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } priv->vaddr = devm_ioremap(dev, mac_dev->res->start, @@ -769,7 +705,7 @@ static int mac_probe(struct platform_device *_of_dev) if (!priv->vaddr) { dev_err(dev, "devm_ioremap() failed\n"); err = -EIO; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } if (!of_device_is_available(mac_node)) { @@ -786,7 +722,7 @@ static int mac_probe(struct platform_device *_of_dev) if (err) { dev_err(dev, "failed to read cell-index for %pOF\n", mac_node); err = -EINVAL; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } priv->cell_index = (u8)val; @@ -795,7 +731,7 @@ static int mac_probe(struct platform_device *_of_dev) if (!mac_addr) { dev_err(dev, "of_get_mac_address(%pOF) failed\n", mac_node); err = -EINVAL; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } memcpy(mac_dev->addr, mac_addr, sizeof(mac_dev->addr)); @@ -805,14 +741,14 @@ static int mac_probe(struct platform_device *_of_dev) dev_err(dev, "of_count_phandle_with_args(%pOF, fsl,fman-ports) failed\n", mac_node); err = nph; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } if (nph != ARRAY_SIZE(mac_dev->port)) { dev_err(dev, "Not supported number of fman-ports handles of mac node %pOF from device tree\n", mac_node); err = -EINVAL; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) { @@ -851,13 +787,13 @@ static int mac_probe(struct platform_device *_of_dev) mac_node); phy_if = PHY_INTERFACE_MODE_SGMII; } - priv->phy_if = phy_if; + mac_dev->phy_if = phy_if; - priv->speed = phy2speed[priv->phy_if]; + priv->speed = phy2speed[mac_dev->phy_if]; priv->max_speed = priv->speed; mac_dev->if_support = DTSEC_SUPPORTED; /* We don't support half-duplex in SGMII mode */ - if (priv->phy_if == PHY_INTERFACE_MODE_SGMII) + if (mac_dev->phy_if == PHY_INTERFACE_MODE_SGMII) mac_dev->if_support &= ~(SUPPORTED_10baseT_Half | SUPPORTED_100baseT_Half); @@ -866,30 +802,30 @@ static int mac_probe(struct platform_device *_of_dev) mac_dev->if_support |= SUPPORTED_1000baseT_Full; /* The 10G interface only supports one mode */ - if (priv->phy_if == PHY_INTERFACE_MODE_XGMII) + if (mac_dev->phy_if == PHY_INTERFACE_MODE_XGMII) mac_dev->if_support = SUPPORTED_10000baseT_Full; /* Get the rest of the PHY information */ - priv->phy_node = of_parse_phandle(mac_node, "phy-handle", 0); - if (!priv->phy_node && of_phy_is_fixed_link(mac_node)) { + mac_dev->phy_node = of_parse_phandle(mac_node, "phy-handle", 0); + if (!mac_dev->phy_node && of_phy_is_fixed_link(mac_node)) { struct phy_device *phy; err = of_phy_register_fixed_link(mac_node); if (err) - goto _return_dev_set_drvdata; + goto _return_of_get_parent; priv->fixed_link = kzalloc(sizeof(*priv->fixed_link), GFP_KERNEL); if (!priv->fixed_link) { err = -ENOMEM; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } - priv->phy_node = of_node_get(mac_node); - phy = of_phy_find_device(priv->phy_node); + mac_dev->phy_node = of_node_get(mac_node); + phy = of_phy_find_device(mac_dev->phy_node); if (!phy) { err = -EINVAL; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } priv->fixed_link->link = phy->link; @@ -904,8 +840,8 @@ static int mac_probe(struct platform_device *_of_dev) err = mac_dev->init(mac_dev); if (err < 0) { dev_err(dev, "mac_dev->init() = %d\n", err); - of_node_put(priv->phy_node); - goto _return_dev_set_drvdata; + of_node_put(mac_dev->phy_node); + goto _return_of_get_parent; } /* pause frame autonegotiation enabled */ @@ -926,7 +862,7 @@ static int mac_probe(struct platform_device *_of_dev) mac_dev->addr[0], mac_dev->addr[1], mac_dev->addr[2], mac_dev->addr[3], mac_dev->addr[4], mac_dev->addr[5]); - priv->eth_dev = dpaa_eth_add_device(fman_id, mac_dev, mac_node); + priv->eth_dev = dpaa_eth_add_device(fman_id, mac_dev); if (IS_ERR(priv->eth_dev)) { dev_err(dev, "failed to add Ethernet platform device for MAC %d\n", priv->cell_index); @@ -937,9 +873,8 @@ static int mac_probe(struct platform_device *_of_dev) _return_of_node_put: of_node_put(dev_node); -_return_dev_set_drvdata: +_return_of_get_parent: kfree(priv->fixed_link); - dev_set_drvdata(dev, NULL); _return: return err; } diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h index d7313f0c5135..eefb3357e304 100644 --- a/drivers/net/ethernet/freescale/fman/mac.h +++ b/drivers/net/ethernet/freescale/fman/mac.h @@ -50,6 +50,8 @@ struct mac_device { struct fman_port *port[2]; u32 if_support; struct phy_device *phy_dev; + phy_interface_t phy_if; + struct device_node *phy_node; bool autoneg_pause; bool rx_pause_req; @@ -58,11 +60,10 @@ struct mac_device { bool tx_pause_active; bool promisc; - struct phy_device *(*init_phy)(struct net_device *net_dev, - struct mac_device *mac_dev); int (*init)(struct mac_device *mac_dev); int (*start)(struct mac_device *mac_dev); int (*stop)(struct mac_device *mac_dev); + void (*adjust_link)(struct mac_device *mac_dev); int (*set_promisc)(struct fman_mac *mac_dev, bool enable); int (*change_addr)(struct fman_mac *mac_dev, enet_addr_t *enet_addr); int (*set_multi)(struct net_device *net_dev, @@ -82,7 +83,6 @@ struct mac_device { }; struct dpaa_eth_data { - struct device_node *mac_node; struct mac_device *mac_dev; int mac_hw_id; int fman_hw_id; diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index 753259091b22..7892f2f0c6b5 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -1023,8 +1023,6 @@ static int fs_enet_probe(struct platform_device *ofdev) ndev->ethtool_ops = &fs_ethtool_ops; - init_timer(&fep->phy_timer_list); - netif_carrier_off(ndev); ndev->features |= NETIF_F_SG; diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h index 5ce516c8a62a..dd306deb7cf1 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h @@ -137,7 +137,6 @@ struct fs_enet_private { cbd_t __iomem *cur_rx; cbd_t __iomem *cur_tx; int tx_free; - struct timer_list phy_timer_list; const struct phy_info *phy; u32 msg_enable; struct mii_if_info mii_if; diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 9d7cb0387bf7..30000b6aa7b8 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -78,7 +78,7 @@ config HNS_ENET config HNS3 tristate "Hisilicon Network Subsystem Support HNS3 (Framework)" - depends on PCI + depends on PCI ---help--- This selects the framework support for Hisilicon Network Subsystem 3. This layer facilitates clients like ENET, RoCE and user-space ethernet @@ -87,7 +87,7 @@ config HNS3 config HNS3_HCLGE tristate "Hisilicon HNS3 HCLGE Acceleration Engine & Compatibility Layer Support" - depends on PCI_MSI + depends on PCI_MSI depends on HNS3 ---help--- This selects the HNS3_HCLGE network acceleration engine & its hardware @@ -96,7 +96,7 @@ config HNS3_HCLGE config HNS3_ENET tristate "Hisilicon HNS3 Ethernet Device Support" - depends on 64BIT && PCI + depends on 64BIT && PCI depends on HNS3 && HNS3_HCLGE ---help--- This selects the Ethernet Driver for Hisilicon Network Subsystem 3 for hip08 diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 36520634c96a..91565c8fee08 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -2159,9 +2159,9 @@ static void hns_nic_task_schedule(struct hns_nic_priv *priv) (void)schedule_work(&priv->service_task); } -static void hns_nic_service_timer(unsigned long data) +static void hns_nic_service_timer(struct timer_list *t) { - struct hns_nic_priv *priv = (struct hns_nic_priv *)data; + struct hns_nic_priv *priv = from_timer(priv, t, service_timer); (void)mod_timer(&priv->service_timer, jiffies + SERVICE_TIMER_HZ); @@ -2451,8 +2451,7 @@ static int hns_nic_dev_probe(struct platform_device *pdev) /* carrier off reporting is important to ethtool even BEFORE open */ netif_carrier_off(ndev); - setup_timer(&priv->service_timer, hns_nic_service_timer, - (unsigned long)priv); + timer_setup(&priv->service_timer, hns_nic_service_timer, 0); INIT_WORK(&priv->service_task, hns_nic_service_task); set_bit(NIC_STATE_SERVICE_INITED, &priv->state); diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index c677530841cf..3acd8db0a794 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -339,6 +339,10 @@ struct hnae3_ae_ops { u8 *hfunc); int (*set_rss)(struct hnae3_handle *handle, const u32 *indir, const u8 *key, const u8 hfunc); + int (*set_rss_tuple)(struct hnae3_handle *handle, + struct ethtool_rxnfc *cmd); + int (*get_rss_tuple)(struct hnae3_handle *handle, + struct ethtool_rxnfc *cmd); int (*get_tc_size)(struct hnae3_handle *handle); @@ -377,6 +381,7 @@ struct hnae3_dcb_ops { u8 (*setdcbx)(struct hnae3_handle *, u8); int (*map_update)(struct hnae3_handle *); + int (*setup_tc)(struct hnae3_handle *, u8, u8 *); }; struct hnae3_ae_algo { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index 8b511e6e0ce9..60960e588b5f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -85,6 +85,15 @@ static int hclge_init_cmd_queue(struct hclge_dev *hdev, int ring_type) return 0; } +void hclge_cmd_reuse_desc(struct hclge_desc *desc, bool is_read) +{ + desc->flag = cpu_to_le16(HCLGE_CMD_FLAG_NO_INTR | HCLGE_CMD_FLAG_IN); + if (is_read) + desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_WR); + else + desc->flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR); +} + void hclge_cmd_setup_basic_desc(struct hclge_desc *desc, enum hclge_opcode_type opcode, bool is_read) { @@ -208,7 +217,7 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) * which will be use for hardware to write back */ ntc = hw->cmq.csq.next_to_use; - opcode = desc[0].opcode; + opcode = le16_to_cpu(desc[0].opcode); while (handle < num) { desc_to_use = &hw->cmq.csq.desc[hw->cmq.csq.next_to_use]; *desc_to_use = desc[handle]; @@ -225,7 +234,7 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) * If the command is sync, wait for the firmware to write back, * if multi descriptors to be sent, use the first one to check */ - if (HCLGE_SEND_SYNC(desc->flag)) { + if (HCLGE_SEND_SYNC(le16_to_cpu(desc->flag))) { do { if (hclge_cmd_csq_done(hw)) break; @@ -244,9 +253,9 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) pr_debug("Get cmd desc:\n"); if (likely(!hclge_is_special_opcode(opcode))) - desc_ret = desc[handle].retval; + desc_ret = le16_to_cpu(desc[handle].retval); else - desc_ret = desc[0].retval; + desc_ret = le16_to_cpu(desc[0].retval); if ((enum hclge_cmd_return_status)desc_ret == HCLGE_CMD_EXEC_SUCCESS) @@ -276,15 +285,15 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) return retval; } -enum hclge_cmd_status hclge_cmd_query_firmware_version(struct hclge_hw *hw, - u32 *version) +static enum hclge_cmd_status hclge_cmd_query_firmware_version( + struct hclge_hw *hw, u32 *version) { - struct hclge_query_version *resp; + struct hclge_query_version_cmd *resp; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_FW_VER, 1); - resp = (struct hclge_query_version *)desc.data; + resp = (struct hclge_query_version_cmd *)desc.data; ret = hclge_cmd_send(hw, &desc, 1); if (!ret) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 6b6d28eff664..b4373345c2b4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -221,12 +221,12 @@ enum hclge_opcode_type { #define HCLGE_RCB_INIT_QUERY_TIMEOUT 10 #define HCLGE_RCB_INIT_FLAG_EN_B 0 #define HCLGE_RCB_INIT_FLAG_FINI_B 8 -struct hclge_config_rcb_init { +struct hclge_config_rcb_init_cmd { __le16 rcb_init_flag; u8 rsv[22]; }; -struct hclge_tqp_map { +struct hclge_tqp_map_cmd { __le16 tqp_id; /* Absolute tqp id for in this pf */ u8 tqp_vf; /* VF id */ #define HCLGE_TQP_MAP_TYPE_PF 0 @@ -246,15 +246,15 @@ enum hclge_int_type { HCLGE_INT_EVENT, }; -struct hclge_ctrl_vector_chain { +struct hclge_ctrl_vector_chain_cmd { u8 int_vector_id; u8 int_cause_num; #define HCLGE_INT_TYPE_S 0 -#define HCLGE_INT_TYPE_M 0x3 +#define HCLGE_INT_TYPE_M GENMASK(1, 0) #define HCLGE_TQP_ID_S 2 -#define HCLGE_TQP_ID_M (0x7ff << HCLGE_TQP_ID_S) +#define HCLGE_TQP_ID_M GENMASK(12, 2) #define HCLGE_INT_GL_IDX_S 13 -#define HCLGE_INT_GL_IDX_M (0x3 << HCLGE_INT_GL_IDX_S) +#define HCLGE_INT_GL_IDX_M GENMASK(14, 13) __le16 tqp_type_and_id[HCLGE_VECTOR_ELEMENTS_PER_CMD]; u8 vfid; u8 rsv; @@ -263,18 +263,18 @@ struct hclge_ctrl_vector_chain { #define HCLGE_TC_NUM 8 #define HCLGE_TC0_PRI_BUF_EN_B 15 /* Bit 15 indicate enable or not */ #define HCLGE_BUF_UNIT_S 7 /* Buf size is united by 128 bytes */ -struct hclge_tx_buff_alloc { +struct hclge_tx_buff_alloc_cmd { __le16 tx_pkt_buff[HCLGE_TC_NUM]; u8 tx_buff_rsv[8]; }; -struct hclge_rx_priv_buff { +struct hclge_rx_priv_buff_cmd { __le16 buf_num[HCLGE_TC_NUM]; __le16 shared_buf; u8 rsv[6]; }; -struct hclge_query_version { +struct hclge_query_version_cmd { __le32 firmware; __le32 firmware_rsv[5]; }; @@ -328,14 +328,14 @@ struct hclge_pkt_buf_alloc { }; #define HCLGE_RX_COM_WL_EN_B 15 -struct hclge_rx_com_wl_buf { +struct hclge_rx_com_wl_buf_cmd { __le16 high_wl; __le16 low_wl; u8 rsv[20]; }; #define HCLGE_RX_PKT_EN_B 15 -struct hclge_rx_pkt_buf { +struct hclge_rx_pkt_buf_cmd { __le16 high_pkt; __le16 low_pkt; u8 rsv[20]; @@ -348,7 +348,7 @@ struct hclge_rx_pkt_buf { #define HCLGE_PF_MAC_NUM_MASK 0x3 #define HCLGE_PF_STATE_MAIN BIT(HCLGE_PF_STATE_MAIN_B) #define HCLGE_PF_STATE_DONE BIT(HCLGE_PF_STATE_DONE_B) -struct hclge_func_status { +struct hclge_func_status_cmd { __le32 vf_rst_state[4]; u8 pf_state; u8 mac_id; @@ -359,7 +359,7 @@ struct hclge_func_status { u8 rsv[2]; }; -struct hclge_pf_res { +struct hclge_pf_res_cmd { __le16 tqp_num; __le16 buf_size; __le16 msixcap_localid_ba_nic; @@ -372,30 +372,30 @@ struct hclge_pf_res { }; #define HCLGE_CFG_OFFSET_S 0 -#define HCLGE_CFG_OFFSET_M 0xfffff /* Byte (8-10.3) */ +#define HCLGE_CFG_OFFSET_M GENMASK(19, 0) #define HCLGE_CFG_RD_LEN_S 24 -#define HCLGE_CFG_RD_LEN_M (0xf << HCLGE_CFG_RD_LEN_S) +#define HCLGE_CFG_RD_LEN_M GENMASK(27, 24) #define HCLGE_CFG_RD_LEN_BYTES 16 #define HCLGE_CFG_RD_LEN_UNIT 4 #define HCLGE_CFG_VMDQ_S 0 -#define HCLGE_CFG_VMDQ_M (0xff << HCLGE_CFG_VMDQ_S) +#define HCLGE_CFG_VMDQ_M GENMASK(7, 0) #define HCLGE_CFG_TC_NUM_S 8 -#define HCLGE_CFG_TC_NUM_M (0xff << HCLGE_CFG_TC_NUM_S) +#define HCLGE_CFG_TC_NUM_M GENMASK(15, 8) #define HCLGE_CFG_TQP_DESC_N_S 16 -#define HCLGE_CFG_TQP_DESC_N_M (0xffff << HCLGE_CFG_TQP_DESC_N_S) +#define HCLGE_CFG_TQP_DESC_N_M GENMASK(31, 16) #define HCLGE_CFG_PHY_ADDR_S 0 -#define HCLGE_CFG_PHY_ADDR_M (0x1f << HCLGE_CFG_PHY_ADDR_S) +#define HCLGE_CFG_PHY_ADDR_M GENMASK(4, 0) #define HCLGE_CFG_MEDIA_TP_S 8 -#define HCLGE_CFG_MEDIA_TP_M (0xff << HCLGE_CFG_MEDIA_TP_S) +#define HCLGE_CFG_MEDIA_TP_M GENMASK(15, 8) #define HCLGE_CFG_RX_BUF_LEN_S 16 -#define HCLGE_CFG_RX_BUF_LEN_M (0xffff << HCLGE_CFG_RX_BUF_LEN_S) +#define HCLGE_CFG_RX_BUF_LEN_M GENMASK(31, 16) #define HCLGE_CFG_MAC_ADDR_H_S 0 -#define HCLGE_CFG_MAC_ADDR_H_M (0xffff << HCLGE_CFG_MAC_ADDR_H_S) +#define HCLGE_CFG_MAC_ADDR_H_M GENMASK(15, 0) #define HCLGE_CFG_DEFAULT_SPEED_S 16 -#define HCLGE_CFG_DEFAULT_SPEED_M (0xff << HCLGE_CFG_DEFAULT_SPEED_S) +#define HCLGE_CFG_DEFAULT_SPEED_M GENMASK(23, 16) -struct hclge_cfg_param { +struct hclge_cfg_param_cmd { __le32 offset; __le32 rsv; __le32 param[4]; @@ -405,7 +405,7 @@ struct hclge_cfg_param { #define HCLGE_DESC_NUM 0x40 #define HCLGE_ALLOC_VALID_B 0 -struct hclge_vf_num { +struct hclge_vf_num_cmd { u8 alloc_valid; u8 rsv[23]; }; @@ -413,13 +413,13 @@ struct hclge_vf_num { #define HCLGE_RSS_DEFAULT_OUTPORT_B 4 #define HCLGE_RSS_HASH_KEY_OFFSET_B 4 #define HCLGE_RSS_HASH_KEY_NUM 16 -struct hclge_rss_config { +struct hclge_rss_config_cmd { u8 hash_config; u8 rsv[7]; u8 hash_key[HCLGE_RSS_HASH_KEY_NUM]; }; -struct hclge_rss_input_tuple { +struct hclge_rss_input_tuple_cmd { u8 ipv4_tcp_en; u8 ipv4_udp_en; u8 ipv4_sctp_en; @@ -433,26 +433,26 @@ struct hclge_rss_input_tuple { #define HCLGE_RSS_CFG_TBL_SIZE 16 -struct hclge_rss_indirection_table { - u16 start_table_index; - u16 rss_set_bitmap; +struct hclge_rss_indirection_table_cmd { + __le16 start_table_index; + __le16 rss_set_bitmap; u8 rsv[4]; u8 rss_result[HCLGE_RSS_CFG_TBL_SIZE]; }; #define HCLGE_RSS_TC_OFFSET_S 0 -#define HCLGE_RSS_TC_OFFSET_M (0x3ff << HCLGE_RSS_TC_OFFSET_S) +#define HCLGE_RSS_TC_OFFSET_M GENMASK(9, 0) #define HCLGE_RSS_TC_SIZE_S 12 -#define HCLGE_RSS_TC_SIZE_M (0x7 << HCLGE_RSS_TC_SIZE_S) +#define HCLGE_RSS_TC_SIZE_M GENMASK(14, 12) #define HCLGE_RSS_TC_VALID_B 15 -struct hclge_rss_tc_mode { - u16 rss_tc_mode[HCLGE_MAX_TC_NUM]; +struct hclge_rss_tc_mode_cmd { + __le16 rss_tc_mode[HCLGE_MAX_TC_NUM]; u8 rsv[8]; }; #define HCLGE_LINK_STS_B 0 #define HCLGE_LINK_STATUS BIT(HCLGE_LINK_STS_B) -struct hclge_link_status { +struct hclge_link_status_cmd { u8 status; u8 rsv[23]; }; @@ -467,7 +467,7 @@ struct hclge_promisc_param { #define HCLGE_PROMISC_EN_UC 0x1 #define HCLGE_PROMISC_EN_MC 0x2 #define HCLGE_PROMISC_EN_BC 0x4 -struct hclge_promisc_cfg { +struct hclge_promisc_cfg_cmd { u8 flag; u8 vf_id; __le16 rsv0; @@ -495,18 +495,18 @@ enum hclge_promisc_type { #define HCLGE_MAC_TX_UNDER_MIN_ERR_B 21 #define HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B 22 -struct hclge_config_mac_mode { +struct hclge_config_mac_mode_cmd { __le32 txrx_pad_fcs_loop_en; u8 rsv[20]; }; #define HCLGE_CFG_SPEED_S 0 -#define HCLGE_CFG_SPEED_M (0x3f << HCLGE_CFG_SPEED_S) +#define HCLGE_CFG_SPEED_M GENMASK(5, 0) #define HCLGE_CFG_DUPLEX_B 7 #define HCLGE_CFG_DUPLEX_M BIT(HCLGE_CFG_DUPLEX_B) -struct hclge_config_mac_speed_dup { +struct hclge_config_mac_speed_dup_cmd { u8 speed_dup; #define HCLGE_CFG_MAC_SPEED_CHANGE_EN_B 0 @@ -518,17 +518,17 @@ struct hclge_config_mac_speed_dup { #define HCLGE_QUERY_AN_B 0 #define HCLGE_QUERY_DUPLEX_B 2 -#define HCLGE_QUERY_SPEED_M (0x1f << HCLGE_QUERY_SPEED_S) +#define HCLGE_QUERY_SPEED_M GENMASK(4, 0) #define HCLGE_QUERY_AN_M BIT(HCLGE_QUERY_AN_B) #define HCLGE_QUERY_DUPLEX_M BIT(HCLGE_QUERY_DUPLEX_B) -struct hclge_query_an_speed_dup { +struct hclge_query_an_speed_dup_cmd { u8 an_syn_dup_speed; u8 pause; u8 rsv[23]; }; -#define HCLGE_RING_ID_MASK 0x3ff +#define HCLGE_RING_ID_MASK GENMASK(9, 0) #define HCLGE_TQP_ENABLE_B 0 #define HCLGE_MAC_CFG_AN_EN_B 0 @@ -539,7 +539,7 @@ struct hclge_query_an_speed_dup { #define HCLGE_MAC_CFG_AN_EN BIT(HCLGE_MAC_CFG_AN_EN_B) -struct hclge_config_auto_neg { +struct hclge_config_auto_neg_cmd { __le32 cfg_an_cmd_flag; u8 rsv[20]; }; @@ -548,7 +548,7 @@ struct hclge_config_auto_neg { #define HCLGE_MAC_MAX_MTU 9728 #define HCLGE_MAC_UPLINK_PORT 0x100 -struct hclge_config_max_frm_size { +struct hclge_config_max_frm_size_cmd { __le16 max_frm_size; u8 rsv[22]; }; @@ -565,10 +565,10 @@ enum hclge_mac_vlan_tbl_opcode { #define HCLGE_MAC_EPORT_SW_EN_B 0xc #define HCLGE_MAC_EPORT_TYPE_B 0xb #define HCLGE_MAC_EPORT_VFID_S 0x3 -#define HCLGE_MAC_EPORT_VFID_M (0xff << HCLGE_MAC_EPORT_VFID_S) +#define HCLGE_MAC_EPORT_VFID_M GENMASK(10, 3) #define HCLGE_MAC_EPORT_PFID_S 0x0 -#define HCLGE_MAC_EPORT_PFID_M (0x7 << HCLGE_MAC_EPORT_PFID_S) -struct hclge_mac_vlan_tbl_entry { +#define HCLGE_MAC_EPORT_PFID_M GENMASK(2, 0) +struct hclge_mac_vlan_tbl_entry_cmd { u8 flags; u8 resp_code; __le16 vlan_tag; @@ -583,15 +583,15 @@ struct hclge_mac_vlan_tbl_entry { }; #define HCLGE_CFG_MTA_MAC_SEL_S 0x0 -#define HCLGE_CFG_MTA_MAC_SEL_M (0x3 << HCLGE_CFG_MTA_MAC_SEL_S) +#define HCLGE_CFG_MTA_MAC_SEL_M GENMASK(1, 0) #define HCLGE_CFG_MTA_MAC_EN_B 0x7 -struct hclge_mta_filter_mode { +struct hclge_mta_filter_mode_cmd { u8 dmac_sel_en; /* Use lowest 2 bit as sel_mode, bit 7 as enable */ u8 rsv[23]; }; #define HCLGE_CFG_FUNC_MTA_ACCEPT_B 0x0 -struct hclge_cfg_func_mta_filter { +struct hclge_cfg_func_mta_filter_cmd { u8 accept; /* Only used lowest 1 bit */ u8 function_id; u8 rsv[22]; @@ -599,14 +599,14 @@ struct hclge_cfg_func_mta_filter { #define HCLGE_CFG_MTA_ITEM_ACCEPT_B 0x0 #define HCLGE_CFG_MTA_ITEM_IDX_S 0x0 -#define HCLGE_CFG_MTA_ITEM_IDX_M (0xfff << HCLGE_CFG_MTA_ITEM_IDX_S) -struct hclge_cfg_func_mta_item { - u16 item_idx; /* Only used lowest 12 bit */ +#define HCLGE_CFG_MTA_ITEM_IDX_M GENMASK(11, 0) +struct hclge_cfg_func_mta_item_cmd { + __le16 item_idx; /* Only used lowest 12 bit */ u8 accept; /* Only used lowest 1 bit */ u8 rsv[21]; }; -struct hclge_mac_vlan_add { +struct hclge_mac_vlan_add_cmd { __le16 flags; __le16 mac_addr_hi16; __le32 mac_addr_lo32; @@ -619,7 +619,7 @@ struct hclge_mac_vlan_add { }; #define HNS3_MAC_VLAN_CFG_FLAG_BIT 0 -struct hclge_mac_vlan_remove { +struct hclge_mac_vlan_remove_cmd { __le16 flags; __le16 mac_addr_hi16; __le32 mac_addr_lo32; @@ -631,21 +631,21 @@ struct hclge_mac_vlan_remove { u8 rsv[4]; }; -struct hclge_vlan_filter_ctrl { +struct hclge_vlan_filter_ctrl_cmd { u8 vlan_type; u8 vlan_fe; u8 rsv[22]; }; -struct hclge_vlan_filter_pf_cfg { +struct hclge_vlan_filter_pf_cfg_cmd { u8 vlan_offset; u8 vlan_cfg; u8 rsv[2]; u8 vlan_offset_bitmap[20]; }; -struct hclge_vlan_filter_vf_cfg { - u16 vlan_id; +struct hclge_vlan_filter_vf_cfg_cmd { + __le16 vlan_id; u8 resp_code; u8 rsv; u8 vlan_cfg; @@ -653,14 +653,14 @@ struct hclge_vlan_filter_vf_cfg { u8 vf_bitmap[16]; }; -struct hclge_cfg_com_tqp_queue { +struct hclge_cfg_com_tqp_queue_cmd { __le16 tqp_id; __le16 stream_id; u8 enable; u8 rsv[19]; }; -struct hclge_cfg_tx_queue_pointer { +struct hclge_cfg_tx_queue_pointer_cmd { __le16 tqp_id; __le16 tx_tail; __le16 tx_head; @@ -670,12 +670,12 @@ struct hclge_cfg_tx_queue_pointer { }; #define HCLGE_TSO_MSS_MIN_S 0 -#define HCLGE_TSO_MSS_MIN_M (0x3FFF << HCLGE_TSO_MSS_MIN_S) +#define HCLGE_TSO_MSS_MIN_M GENMASK(13, 0) #define HCLGE_TSO_MSS_MAX_S 16 -#define HCLGE_TSO_MSS_MAX_M (0x3FFF << HCLGE_TSO_MSS_MAX_S) +#define HCLGE_TSO_MSS_MAX_M GENMASK(29, 16) -struct hclge_cfg_tso_status { +struct hclge_cfg_tso_status_cmd { __le16 tso_mss_min; __le16 tso_mss_max; u8 rsv[20]; @@ -685,7 +685,7 @@ struct hclge_cfg_tso_status { #define HCLGE_TSO_MSS_MAX 9668 #define HCLGE_TQP_RESET_B 0 -struct hclge_reset_tqp_queue { +struct hclge_reset_tqp_queue_cmd { __le16 tqp_id; u8 reset_req; u8 ready_to_reset; @@ -739,6 +739,7 @@ struct hclge_hw; int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num); void hclge_cmd_setup_basic_desc(struct hclge_desc *desc, enum hclge_opcode_type opcode, bool is_read); +void hclge_cmd_reuse_desc(struct hclge_desc *desc, bool is_read); int hclge_cmd_set_promisc_mode(struct hclge_dev *hdev, struct hclge_promisc_param *param); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index 1b30a6f966d8..5018d6633133 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -178,7 +178,8 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets) u8 num_tc = 0; int ret; - if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) + if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) || + hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE) return -EINVAL; ret = hclge_ets_validate(hdev, ets, &num_tc, &map_changed); @@ -228,7 +229,8 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) struct hclge_dev *hdev = vport->back; u8 i, j, pfc_map, *prio_tc; - if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) + if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) || + hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE) return -EINVAL; prio_tc = hdev->tm_info.prio_tc; @@ -257,6 +259,9 @@ static u8 hclge_getdcbx(struct hnae3_handle *h) struct hclge_vport *vport = hclge_get_vport(h); struct hclge_dev *hdev = vport->back; + if (hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE) + return 0; + return hdev->dcbx_cap; } @@ -276,6 +281,43 @@ static u8 hclge_setdcbx(struct hnae3_handle *h, u8 mode) return 0; } +/* Set up TC for hardware offloaded mqprio in channel mode */ +static int hclge_setup_tc(struct hnae3_handle *h, u8 tc, u8 *prio_tc) +{ + struct hclge_vport *vport = hclge_get_vport(h); + struct hclge_dev *hdev = vport->back; + int ret; + + if (hdev->flag & HCLGE_FLAG_DCB_ENABLE) + return -EINVAL; + + if (tc > hdev->tc_max) { + dev_err(&hdev->pdev->dev, + "setup tc failed, tc(%u) > tc_max(%u)\n", + tc, hdev->tc_max); + return -EINVAL; + } + + hclge_tm_schd_info_update(hdev, tc); + + ret = hclge_tm_prio_tc_info_update(hdev, prio_tc); + if (ret) + return ret; + + ret = hclge_tm_init_hw(hdev); + if (ret) + return ret; + + hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE; + + if (tc > 1) + hdev->flag |= HCLGE_FLAG_MQPRIO_ENABLE; + else + hdev->flag &= ~HCLGE_FLAG_MQPRIO_ENABLE; + + return 0; +} + static const struct hnae3_dcb_ops hns3_dcb_ops = { .ieee_getets = hclge_ieee_getets, .ieee_setets = hclge_ieee_setets, @@ -284,6 +326,7 @@ static const struct hnae3_dcb_ops hns3_dcb_ops = { .getdcbx = hclge_getdcbx, .setdcbx = hclge_setdcbx, .map_update = hclge_map_update, + .setup_tc = hclge_setup_tc, }; void hclge_dcb_ops_set(struct hclge_dev *hdev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 1a13614af3de..6e93943c489a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -362,7 +362,7 @@ static int hclge_64_bit_update_stats(struct hclge_dev *hdev) #define HCLGE_64_BIT_RTN_DATANUM 4 u64 *data = (u64 *)(&hdev->hw_stats.all_64_bit_stats); struct hclge_desc desc[HCLGE_64_BIT_CMD_NUM]; - u64 *desc_data; + __le64 *desc_data; int i, k, n; int ret; @@ -376,14 +376,14 @@ static int hclge_64_bit_update_stats(struct hclge_dev *hdev) for (i = 0; i < HCLGE_64_BIT_CMD_NUM; i++) { if (unlikely(i == 0)) { - desc_data = (u64 *)(&desc[i].data[0]); + desc_data = (__le64 *)(&desc[i].data[0]); n = HCLGE_64_BIT_RTN_DATANUM - 1; } else { - desc_data = (u64 *)(&desc[i]); + desc_data = (__le64 *)(&desc[i]); n = HCLGE_64_BIT_RTN_DATANUM; } for (k = 0; k < n; k++) { - *data++ += cpu_to_le64(*desc_data); + *data++ += le64_to_cpu(*desc_data); desc_data++; } } @@ -411,7 +411,7 @@ static int hclge_32_bit_update_stats(struct hclge_dev *hdev) struct hclge_desc desc[HCLGE_32_BIT_CMD_NUM]; struct hclge_32_bit_stats *all_32_bit_stats; - u32 *desc_data; + __le32 *desc_data; int i, k, n; u64 *data; int ret; @@ -431,21 +431,27 @@ static int hclge_32_bit_update_stats(struct hclge_dev *hdev) hclge_reset_partial_32bit_counter(all_32_bit_stats); for (i = 0; i < HCLGE_32_BIT_CMD_NUM; i++) { if (unlikely(i == 0)) { + __le16 *desc_data_16bit; + all_32_bit_stats->igu_rx_err_pkt += - cpu_to_le32(desc[i].data[0]); + le32_to_cpu(desc[i].data[0]); + + desc_data_16bit = (__le16 *)&desc[i].data[1]; all_32_bit_stats->igu_rx_no_eof_pkt += - cpu_to_le32(desc[i].data[1] & 0xffff); + le16_to_cpu(*desc_data_16bit); + + desc_data_16bit++; all_32_bit_stats->igu_rx_no_sof_pkt += - cpu_to_le32((desc[i].data[1] >> 16) & 0xffff); + le16_to_cpu(*desc_data_16bit); - desc_data = (u32 *)(&desc[i].data[2]); + desc_data = &desc[i].data[2]; n = HCLGE_32_BIT_RTN_DATANUM - 4; } else { - desc_data = (u32 *)(&desc[i]); + desc_data = (__le32 *)&desc[i]; n = HCLGE_32_BIT_RTN_DATANUM; } for (k = 0; k < n; k++) { - *data++ += cpu_to_le32(*desc_data); + *data++ += le32_to_cpu(*desc_data); desc_data++; } } @@ -460,7 +466,7 @@ static int hclge_mac_update_stats(struct hclge_dev *hdev) u64 *data = (u64 *)(&hdev->hw_stats.mac_stats); struct hclge_desc desc[HCLGE_MAC_CMD_NUM]; - u64 *desc_data; + __le64 *desc_data; int i, k, n; int ret; @@ -475,14 +481,14 @@ static int hclge_mac_update_stats(struct hclge_dev *hdev) for (i = 0; i < HCLGE_MAC_CMD_NUM; i++) { if (unlikely(i == 0)) { - desc_data = (u64 *)(&desc[i].data[0]); + desc_data = (__le64 *)(&desc[i].data[0]); n = HCLGE_RTN_DATA_NUM - 2; } else { - desc_data = (u64 *)(&desc[i]); + desc_data = (__le64 *)(&desc[i]); n = HCLGE_RTN_DATA_NUM; } for (k = 0; k < n; k++) { - *data++ += cpu_to_le64(*desc_data); + *data++ += le64_to_cpu(*desc_data); desc_data++; } } @@ -508,7 +514,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle) HCLGE_OPC_QUERY_RX_STATUS, true); - desc[0].data[0] = (tqp->index & 0x1ff); + desc[0].data[0] = cpu_to_le32((tqp->index & 0x1ff)); ret = hclge_cmd_send(&hdev->hw, desc, 1); if (ret) { dev_err(&hdev->pdev->dev, @@ -517,7 +523,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle) return ret; } tqp->tqp_stats.rcb_rx_ring_pktnum_rcd += - cpu_to_le32(desc[0].data[4]); + le32_to_cpu(desc[0].data[4]); } for (i = 0; i < kinfo->num_tqps; i++) { @@ -528,7 +534,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle) HCLGE_OPC_QUERY_TX_STATUS, true); - desc[0].data[0] = (tqp->index & 0x1ff); + desc[0].data[0] = cpu_to_le32((tqp->index & 0x1ff)); ret = hclge_cmd_send(&hdev->hw, desc, 1); if (ret) { dev_err(&hdev->pdev->dev, @@ -537,7 +543,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle) return ret; } tqp->tqp_stats.rcb_tx_ring_pktnum_rcd += - cpu_to_le32(desc[0].data[4]); + le32_to_cpu(desc[0].data[4]); } return 0; @@ -552,12 +558,12 @@ static u64 *hclge_tqps_get_stats(struct hnae3_handle *handle, u64 *data) for (i = 0; i < kinfo->num_tqps; i++) { tqp = container_of(kinfo->tqp[i], struct hclge_tqp, q); - *buff++ = cpu_to_le64(tqp->tqp_stats.rcb_tx_ring_pktnum_rcd); + *buff++ = tqp->tqp_stats.rcb_tx_ring_pktnum_rcd; } for (i = 0; i < kinfo->num_tqps; i++) { tqp = container_of(kinfo->tqp[i], struct hclge_tqp, q); - *buff++ = cpu_to_le64(tqp->tqp_stats.rcb_rx_ring_pktnum_rcd); + *buff++ = tqp->tqp_stats.rcb_rx_ring_pktnum_rcd; } return buff; @@ -820,7 +826,7 @@ static void hclge_get_stats(struct hnae3_handle *handle, u64 *data) } static int hclge_parse_func_status(struct hclge_dev *hdev, - struct hclge_func_status *status) + struct hclge_func_status_cmd *status) { if (!(status->pf_state & HCLGE_PF_STATE_DONE)) return -EINVAL; @@ -837,13 +843,13 @@ static int hclge_parse_func_status(struct hclge_dev *hdev, static int hclge_query_function_status(struct hclge_dev *hdev) { - struct hclge_func_status *req; + struct hclge_func_status_cmd *req; struct hclge_desc desc; int timeout = 0; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_FUNC_STATUS, true); - req = (struct hclge_func_status *)desc.data; + req = (struct hclge_func_status_cmd *)desc.data; do { ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -868,7 +874,7 @@ static int hclge_query_function_status(struct hclge_dev *hdev) static int hclge_query_pf_resource(struct hclge_dev *hdev) { - struct hclge_pf_res *req; + struct hclge_pf_res_cmd *req; struct hclge_desc desc; int ret; @@ -880,7 +886,7 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev) return ret; } - req = (struct hclge_pf_res *)desc.data; + req = (struct hclge_pf_res_cmd *)desc.data; hdev->num_tqps = __le16_to_cpu(req->tqp_num); hdev->pkt_buf_size = __le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S; @@ -938,12 +944,12 @@ static int hclge_parse_speed(int speed_cmd, int *speed) static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) { - struct hclge_cfg_param *req; + struct hclge_cfg_param_cmd *req; u64 mac_addr_tmp_high; u64 mac_addr_tmp; int i; - req = (struct hclge_cfg_param *)desc[0].data; + req = (struct hclge_cfg_param_cmd *)desc[0].data; /* get the configuration */ cfg->vmdq_vport_num = hnae_get_field(__le32_to_cpu(req->param[0]), @@ -978,7 +984,7 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) for (i = 0; i < ETH_ALEN; i++) cfg->mac_addr[i] = (mac_addr_tmp >> (8 * i)) & 0xff; - req = (struct hclge_cfg_param *)desc[1].data; + req = (struct hclge_cfg_param_cmd *)desc[1].data; cfg->numa_node_map = __le32_to_cpu(req->param[0]); } @@ -989,20 +995,21 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) static int hclge_get_cfg(struct hclge_dev *hdev, struct hclge_cfg *hcfg) { struct hclge_desc desc[HCLGE_PF_CFG_DESC_NUM]; - struct hclge_cfg_param *req; + struct hclge_cfg_param_cmd *req; int i, ret; for (i = 0; i < HCLGE_PF_CFG_DESC_NUM; i++) { - req = (struct hclge_cfg_param *)desc[i].data; + u32 offset = 0; + + req = (struct hclge_cfg_param_cmd *)desc[i].data; hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_GET_CFG_PARAM, true); - hnae_set_field(req->offset, HCLGE_CFG_OFFSET_M, + hnae_set_field(offset, HCLGE_CFG_OFFSET_M, HCLGE_CFG_OFFSET_S, i * HCLGE_CFG_RD_LEN_BYTES); /* Len should be united by 4 bytes when send to hardware */ - hnae_set_field(req->offset, HCLGE_CFG_RD_LEN_M, - HCLGE_CFG_RD_LEN_S, + hnae_set_field(offset, HCLGE_CFG_RD_LEN_M, HCLGE_CFG_RD_LEN_S, HCLGE_CFG_RD_LEN_BYTES / HCLGE_CFG_RD_LEN_UNIT); - req->offset = cpu_to_le32(req->offset); + req->offset = cpu_to_le32(offset); } ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_PF_CFG_DESC_NUM); @@ -1099,16 +1106,23 @@ static int hclge_configure(struct hclge_dev *hdev) static int hclge_config_tso(struct hclge_dev *hdev, int tso_mss_min, int tso_mss_max) { - struct hclge_cfg_tso_status *req; + struct hclge_cfg_tso_status_cmd *req; struct hclge_desc desc; + u16 tso_mss; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TSO_GENERIC_CONFIG, false); - req = (struct hclge_cfg_tso_status *)desc.data; - hnae_set_field(req->tso_mss_min, HCLGE_TSO_MSS_MIN_M, + req = (struct hclge_cfg_tso_status_cmd *)desc.data; + + tso_mss = 0; + hnae_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M, HCLGE_TSO_MSS_MIN_S, tso_mss_min); - hnae_set_field(req->tso_mss_max, HCLGE_TSO_MSS_MIN_M, + req->tso_mss_min = cpu_to_le16(tso_mss); + + tso_mss = 0; + hnae_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M, HCLGE_TSO_MSS_MIN_S, tso_mss_max); + req->tso_mss_max = cpu_to_le16(tso_mss); return hclge_cmd_send(&hdev->hw, &desc, 1); } @@ -1144,15 +1158,15 @@ static int hclge_alloc_tqps(struct hclge_dev *hdev) static int hclge_map_tqps_to_func(struct hclge_dev *hdev, u16 func_id, u16 tqp_pid, u16 tqp_vid, bool is_pf) { - struct hclge_tqp_map *req; + struct hclge_tqp_map_cmd *req; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SET_TQP_MAP, false); - req = (struct hclge_tqp_map *)desc.data; + req = (struct hclge_tqp_map_cmd *)desc.data; req->tqp_id = cpu_to_le16(tqp_pid); - req->tqp_vf = cpu_to_le16(func_id); + req->tqp_vf = func_id; req->tqp_flag = !is_pf << HCLGE_TQP_MAP_TYPE_B | 1 << HCLGE_TQP_MAP_EN_B; req->tqp_vid = cpu_to_le16(tqp_vid); @@ -1340,12 +1354,12 @@ static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, /* TX buffer size is unit by 128 byte */ #define HCLGE_BUF_SIZE_UNIT_SHIFT 7 #define HCLGE_BUF_SIZE_UPDATE_EN_MSK BIT(15) - struct hclge_tx_buff_alloc *req; + struct hclge_tx_buff_alloc_cmd *req; struct hclge_desc desc; int ret; u8 i; - req = (struct hclge_tx_buff_alloc *)desc.data; + req = (struct hclge_tx_buff_alloc_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0); for (i = 0; i < HCLGE_TC_NUM; i++) { @@ -1536,8 +1550,8 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev, * @buf_alloc: pointer to buffer calculation data * @return: 0: calculate sucessful, negative: fail */ -int hclge_rx_buffer_calc(struct hclge_dev *hdev, - struct hclge_pkt_buf_alloc *buf_alloc) +static int hclge_rx_buffer_calc(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) { u32 rx_all = hdev->pkt_buf_size; int no_pfc_priv_num, pfc_priv_num; @@ -1672,13 +1686,13 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev, struct hclge_pkt_buf_alloc *buf_alloc) { - struct hclge_rx_priv_buff *req; + struct hclge_rx_priv_buff_cmd *req; struct hclge_desc desc; int ret; int i; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RX_PRIV_BUFF_ALLOC, false); - req = (struct hclge_rx_priv_buff *)desc.data; + req = (struct hclge_rx_priv_buff_cmd *)desc.data; /* Alloc private buffer TCs */ for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { @@ -1687,7 +1701,7 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev, req->buf_num[i] = cpu_to_le16(priv->buf_size >> HCLGE_BUF_UNIT_S); req->buf_num[i] |= - cpu_to_le16(true << HCLGE_TC0_PRI_BUF_EN_B); + cpu_to_le16(1 << HCLGE_TC0_PRI_BUF_EN_B); } req->shared_buf = @@ -2000,11 +2014,11 @@ static void hclge_check_speed_dup(struct hclge_dev *hdev, int duplex, int speed) int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex) { - struct hclge_config_mac_speed_dup *req; + struct hclge_config_mac_speed_dup_cmd *req; struct hclge_desc desc; int ret; - req = (struct hclge_config_mac_speed_dup *)desc.data; + req = (struct hclge_config_mac_speed_dup_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_SPEED_DUP, false); @@ -2075,12 +2089,12 @@ static int hclge_cfg_mac_speed_dup_h(struct hnae3_handle *handle, int speed, static int hclge_query_mac_an_speed_dup(struct hclge_dev *hdev, int *speed, u8 *duplex) { - struct hclge_query_an_speed_dup *req; + struct hclge_query_an_speed_dup_cmd *req; struct hclge_desc desc; int speed_tmp; int ret; - req = (struct hclge_query_an_speed_dup *)desc.data; + req = (struct hclge_query_an_speed_dup_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_AN_RESULT, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -2108,11 +2122,11 @@ static int hclge_query_mac_an_speed_dup(struct hclge_dev *hdev, int *speed, static int hclge_query_autoneg_result(struct hclge_dev *hdev) { struct hclge_mac *mac = &hdev->hw.mac; - struct hclge_query_an_speed_dup *req; + struct hclge_query_an_speed_dup_cmd *req; struct hclge_desc desc; int ret; - req = (struct hclge_query_an_speed_dup *)desc.data; + req = (struct hclge_query_an_speed_dup_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_AN_RESULT, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -2129,14 +2143,16 @@ static int hclge_query_autoneg_result(struct hclge_dev *hdev) static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable) { - struct hclge_config_auto_neg *req; + struct hclge_config_auto_neg_cmd *req; struct hclge_desc desc; + u32 flag = 0; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_AN_MODE, false); - req = (struct hclge_config_auto_neg *)desc.data; - hnae_set_bit(req->cfg_an_cmd_flag, HCLGE_MAC_CFG_AN_EN_B, !!enable); + req = (struct hclge_config_auto_neg_cmd *)desc.data; + hnae_set_bit(flag, HCLGE_MAC_CFG_AN_EN_B, !!enable); + req->cfg_an_cmd_flag = cpu_to_le32(flag); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { @@ -2214,7 +2230,7 @@ static void hclge_task_schedule(struct hclge_dev *hdev) static int hclge_get_mac_link_status(struct hclge_dev *hdev) { - struct hclge_link_status *req; + struct hclge_link_status_cmd *req; struct hclge_desc desc; int link_status; int ret; @@ -2227,7 +2243,7 @@ static int hclge_get_mac_link_status(struct hclge_dev *hdev) return ret; } - req = (struct hclge_link_status *)desc.data; + req = (struct hclge_link_status_cmd *)desc.data; link_status = req->status & HCLGE_LINK_STATUS; return !!link_status; @@ -2334,11 +2350,11 @@ static int hclge_get_status(struct hnae3_handle *handle) return hdev->hw.mac.link; } -static void hclge_service_timer(unsigned long data) +static void hclge_service_timer(struct timer_list *t) { - struct hclge_dev *hdev = (struct hclge_dev *)data; - (void)mod_timer(&hdev->service_timer, jiffies + HZ); + struct hclge_dev *hdev = from_timer(hdev, t, service_timer); + mod_timer(&hdev->service_timer, jiffies + HZ); hclge_task_schedule(hdev); } @@ -2451,7 +2467,7 @@ static u32 hclge_get_rss_indir_size(struct hnae3_handle *handle) static int hclge_get_rss_algo(struct hclge_dev *hdev) { - struct hclge_rss_config *req; + struct hclge_rss_config_cmd *req; struct hclge_desc desc; int rss_hash_algo; int ret; @@ -2465,7 +2481,7 @@ static int hclge_get_rss_algo(struct hclge_dev *hdev) return ret; } - req = (struct hclge_rss_config *)desc.data; + req = (struct hclge_rss_config_cmd *)desc.data; rss_hash_algo = (req->hash_config & HCLGE_RSS_HASH_ALGO_MASK); if (rss_hash_algo == HCLGE_RSS_HASH_ALGO_TOEPLITZ) @@ -2477,13 +2493,13 @@ static int hclge_get_rss_algo(struct hclge_dev *hdev) static int hclge_set_rss_algo_key(struct hclge_dev *hdev, const u8 hfunc, const u8 *key) { - struct hclge_rss_config *req; + struct hclge_rss_config_cmd *req; struct hclge_desc desc; int key_offset; int key_size; int ret; - req = (struct hclge_rss_config *)desc.data; + req = (struct hclge_rss_config_cmd *)desc.data; for (key_offset = 0; key_offset < 3; key_offset++) { hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_GENERIC_CONFIG, @@ -2514,19 +2530,20 @@ static int hclge_set_rss_algo_key(struct hclge_dev *hdev, static int hclge_set_rss_indir_table(struct hclge_dev *hdev, const u32 *indir) { - struct hclge_rss_indirection_table *req; + struct hclge_rss_indirection_table_cmd *req; struct hclge_desc desc; int i, j; int ret; - req = (struct hclge_rss_indirection_table *)desc.data; + req = (struct hclge_rss_indirection_table_cmd *)desc.data; for (i = 0; i < HCLGE_RSS_CFG_TBL_NUM; i++) { hclge_cmd_setup_basic_desc (&desc, HCLGE_OPC_RSS_INDIR_TABLE, false); - req->start_table_index = i * HCLGE_RSS_CFG_TBL_SIZE; - req->rss_set_bitmap = HCLGE_RSS_SET_BITMAP_MSK; + req->start_table_index = + cpu_to_le16(i * HCLGE_RSS_CFG_TBL_SIZE); + req->rss_set_bitmap = cpu_to_le16(HCLGE_RSS_SET_BITMAP_MSK); for (j = 0; j < HCLGE_RSS_CFG_TBL_SIZE; j++) req->rss_result[j] = @@ -2546,21 +2563,24 @@ static int hclge_set_rss_indir_table(struct hclge_dev *hdev, const u32 *indir) static int hclge_set_rss_tc_mode(struct hclge_dev *hdev, u16 *tc_valid, u16 *tc_size, u16 *tc_offset) { - struct hclge_rss_tc_mode *req; + struct hclge_rss_tc_mode_cmd *req; struct hclge_desc desc; int ret; int i; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_TC_MODE, false); - req = (struct hclge_rss_tc_mode *)desc.data; + req = (struct hclge_rss_tc_mode_cmd *)desc.data; for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { - hnae_set_bit(req->rss_tc_mode[i], HCLGE_RSS_TC_VALID_B, - (tc_valid[i] & 0x1)); - hnae_set_field(req->rss_tc_mode[i], HCLGE_RSS_TC_SIZE_M, + u16 mode = 0; + + hnae_set_bit(mode, HCLGE_RSS_TC_VALID_B, (tc_valid[i] & 0x1)); + hnae_set_field(mode, HCLGE_RSS_TC_SIZE_M, HCLGE_RSS_TC_SIZE_S, tc_size[i]); - hnae_set_field(req->rss_tc_mode[i], HCLGE_RSS_TC_OFFSET_M, + hnae_set_field(mode, HCLGE_RSS_TC_OFFSET_M, HCLGE_RSS_TC_OFFSET_S, tc_offset[i]); + + req->rss_tc_mode[i] = cpu_to_le16(mode); } ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -2575,15 +2595,13 @@ static int hclge_set_rss_tc_mode(struct hclge_dev *hdev, u16 *tc_valid, static int hclge_set_rss_input_tuple(struct hclge_dev *hdev) { -#define HCLGE_RSS_INPUT_TUPLE_OTHER 0xf -#define HCLGE_RSS_INPUT_TUPLE_SCTP 0x1f - struct hclge_rss_input_tuple *req; + struct hclge_rss_input_tuple_cmd *req; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_INPUT_TUPLE, false); - req = (struct hclge_rss_input_tuple *)desc.data; + req = (struct hclge_rss_input_tuple_cmd *)desc.data; req->ipv4_tcp_en = HCLGE_RSS_INPUT_TUPLE_OTHER; req->ipv4_udp_en = HCLGE_RSS_INPUT_TUPLE_OTHER; req->ipv4_sctp_en = HCLGE_RSS_INPUT_TUPLE_SCTP; @@ -2657,6 +2675,161 @@ static int hclge_set_rss(struct hnae3_handle *handle, const u32 *indir, return ret; } +static u8 hclge_get_rss_hash_bits(struct ethtool_rxnfc *nfc) +{ + u8 hash_sets = nfc->data & RXH_L4_B_0_1 ? HCLGE_S_PORT_BIT : 0; + + if (nfc->data & RXH_L4_B_2_3) + hash_sets |= HCLGE_D_PORT_BIT; + else + hash_sets &= ~HCLGE_D_PORT_BIT; + + if (nfc->data & RXH_IP_SRC) + hash_sets |= HCLGE_S_IP_BIT; + else + hash_sets &= ~HCLGE_S_IP_BIT; + + if (nfc->data & RXH_IP_DST) + hash_sets |= HCLGE_D_IP_BIT; + else + hash_sets &= ~HCLGE_D_IP_BIT; + + if (nfc->flow_type == SCTP_V4_FLOW || nfc->flow_type == SCTP_V6_FLOW) + hash_sets |= HCLGE_V_TAG_BIT; + + return hash_sets; +} + +static int hclge_set_rss_tuple(struct hnae3_handle *handle, + struct ethtool_rxnfc *nfc) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hclge_rss_input_tuple_cmd *req; + struct hclge_desc desc; + u8 tuple_sets; + int ret; + + if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3)) + return -EINVAL; + + req = (struct hclge_rss_input_tuple_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_INPUT_TUPLE, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Read rss tuple fail, status = %d\n", ret); + return ret; + } + + hclge_cmd_reuse_desc(&desc, false); + + tuple_sets = hclge_get_rss_hash_bits(nfc); + switch (nfc->flow_type) { + case TCP_V4_FLOW: + req->ipv4_tcp_en = tuple_sets; + break; + case TCP_V6_FLOW: + req->ipv6_tcp_en = tuple_sets; + break; + case UDP_V4_FLOW: + req->ipv4_udp_en = tuple_sets; + break; + case UDP_V6_FLOW: + req->ipv6_udp_en = tuple_sets; + break; + case SCTP_V4_FLOW: + req->ipv4_sctp_en = tuple_sets; + break; + case SCTP_V6_FLOW: + if ((nfc->data & RXH_L4_B_0_1) || + (nfc->data & RXH_L4_B_2_3)) + return -EINVAL; + + req->ipv6_sctp_en = tuple_sets; + break; + case IPV4_FLOW: + req->ipv4_fragment_en = HCLGE_RSS_INPUT_TUPLE_OTHER; + break; + case IPV6_FLOW: + req->ipv6_fragment_en = HCLGE_RSS_INPUT_TUPLE_OTHER; + break; + default: + return -EINVAL; + } + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "Set rss tuple fail, status = %d\n", ret); + + return ret; +} + +static int hclge_get_rss_tuple(struct hnae3_handle *handle, + struct ethtool_rxnfc *nfc) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hclge_rss_input_tuple_cmd *req; + struct hclge_desc desc; + u8 tuple_sets; + int ret; + + nfc->data = 0; + + req = (struct hclge_rss_input_tuple_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_INPUT_TUPLE, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Read rss tuple fail, status = %d\n", ret); + return ret; + } + + switch (nfc->flow_type) { + case TCP_V4_FLOW: + tuple_sets = req->ipv4_tcp_en; + break; + case UDP_V4_FLOW: + tuple_sets = req->ipv4_udp_en; + break; + case TCP_V6_FLOW: + tuple_sets = req->ipv6_tcp_en; + break; + case UDP_V6_FLOW: + tuple_sets = req->ipv6_udp_en; + break; + case SCTP_V4_FLOW: + tuple_sets = req->ipv4_sctp_en; + break; + case SCTP_V6_FLOW: + tuple_sets = req->ipv6_sctp_en; + break; + case IPV4_FLOW: + case IPV6_FLOW: + tuple_sets = HCLGE_S_IP_BIT | HCLGE_D_IP_BIT; + break; + default: + return -EINVAL; + } + + if (!tuple_sets) + return 0; + + if (tuple_sets & HCLGE_D_PORT_BIT) + nfc->data |= RXH_L4_B_2_3; + if (tuple_sets & HCLGE_S_PORT_BIT) + nfc->data |= RXH_L4_B_0_1; + if (tuple_sets & HCLGE_D_IP_BIT) + nfc->data |= RXH_IP_DST; + if (tuple_sets & HCLGE_S_IP_BIT) + nfc->data |= RXH_IP_SRC; + + return 0; +} + static int hclge_get_tc_size(struct hnae3_handle *handle) { struct hclge_vport *vport = hclge_get_vport(handle); @@ -2750,7 +2923,7 @@ int hclge_map_vport_ring_to_vector(struct hclge_vport *vport, int vector_id, struct hnae3_ring_chain_node *ring_chain) { struct hclge_dev *hdev = vport->back; - struct hclge_ctrl_vector_chain *req; + struct hclge_ctrl_vector_chain_cmd *req; struct hnae3_ring_chain_node *node; struct hclge_desc desc; int ret; @@ -2758,20 +2931,21 @@ int hclge_map_vport_ring_to_vector(struct hclge_vport *vport, int vector_id, hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_ADD_RING_TO_VECTOR, false); - req = (struct hclge_ctrl_vector_chain *)desc.data; + req = (struct hclge_ctrl_vector_chain_cmd *)desc.data; req->int_vector_id = vector_id; i = 0; for (node = ring_chain; node; node = node->next) { - hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_TYPE_M, - HCLGE_INT_TYPE_S, + u16 type_and_id = 0; + + hnae_set_field(type_and_id, HCLGE_INT_TYPE_M, HCLGE_INT_TYPE_S, hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); - hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M, - HCLGE_TQP_ID_S, node->tqp_index); - hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_GL_IDX_M, + hnae_set_field(type_and_id, HCLGE_TQP_ID_M, HCLGE_TQP_ID_S, + node->tqp_index); + hnae_set_field(type_and_id, HCLGE_INT_GL_IDX_M, HCLGE_INT_GL_IDX_S, hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); - req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]); + req->tqp_type_and_id[i] = cpu_to_le16(type_and_id); req->vfid = vport->vport_id; if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) { @@ -2807,9 +2981,9 @@ int hclge_map_vport_ring_to_vector(struct hclge_vport *vport, int vector_id, return 0; } -int hclge_map_handle_ring_to_vector(struct hnae3_handle *handle, - int vector, - struct hnae3_ring_chain_node *ring_chain) +static int hclge_map_handle_ring_to_vector( + struct hnae3_handle *handle, int vector, + struct hnae3_ring_chain_node *ring_chain) { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; @@ -2831,7 +3005,7 @@ static int hclge_unmap_ring_from_vector( { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - struct hclge_ctrl_vector_chain *req; + struct hclge_ctrl_vector_chain_cmd *req; struct hnae3_ring_chain_node *node; struct hclge_desc desc; int i, vector_id; @@ -2846,21 +3020,22 @@ static int hclge_unmap_ring_from_vector( hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_DEL_RING_TO_VECTOR, false); - req = (struct hclge_ctrl_vector_chain *)desc.data; + req = (struct hclge_ctrl_vector_chain_cmd *)desc.data; req->int_vector_id = vector_id; i = 0; for (node = ring_chain; node; node = node->next) { - hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_TYPE_M, - HCLGE_INT_TYPE_S, + u16 type_and_id = 0; + + hnae_set_field(type_and_id, HCLGE_INT_TYPE_M, HCLGE_INT_TYPE_S, hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); - hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M, - HCLGE_TQP_ID_S, node->tqp_index); - hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_GL_IDX_M, + hnae_set_field(type_and_id, HCLGE_TQP_ID_M, HCLGE_TQP_ID_S, + node->tqp_index); + hnae_set_field(type_and_id, HCLGE_INT_GL_IDX_M, HCLGE_INT_GL_IDX_S, hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); - req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]); + req->tqp_type_and_id[i] = cpu_to_le16(type_and_id); req->vfid = vport->vport_id; if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) { @@ -2898,13 +3073,13 @@ static int hclge_unmap_ring_from_vector( int hclge_cmd_set_promisc_mode(struct hclge_dev *hdev, struct hclge_promisc_param *param) { - struct hclge_promisc_cfg *req; + struct hclge_promisc_cfg_cmd *req; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_PROMISC_MODE, false); - req = (struct hclge_promisc_cfg *)desc.data; + req = (struct hclge_promisc_cfg_cmd *)desc.data; req->vf_id = param->vf_id; req->flag = (param->enable << HCLGE_PROMISC_EN_B); @@ -2946,29 +3121,27 @@ static void hclge_set_promisc_mode(struct hnae3_handle *handle, u32 en) static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) { struct hclge_desc desc; - struct hclge_config_mac_mode *req = - (struct hclge_config_mac_mode *)desc.data; + struct hclge_config_mac_mode_cmd *req = + (struct hclge_config_mac_mode_cmd *)desc.data; + u32 loop_en = 0; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, false); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_TX_EN_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_RX_EN_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_PAD_TX_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_PAD_RX_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_1588_TX_B, 0); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_1588_RX_B, 0); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_APP_LP_B, 0); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_LINE_LP_B, 0); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_FCS_TX_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_RX_FCS_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, - HCLGE_MAC_RX_FCS_STRIP_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, - HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, - HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, - HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_TX_EN_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_RX_EN_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_PAD_TX_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_PAD_RX_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_1588_TX_B, 0); + hnae_set_bit(loop_en, HCLGE_MAC_1588_RX_B, 0); + hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0); + hnae_set_bit(loop_en, HCLGE_MAC_LINE_LP_B, 0); + hnae_set_bit(loop_en, HCLGE_MAC_FCS_TX_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_RX_FCS_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable); + req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) @@ -2980,8 +3153,8 @@ static int hclge_tqp_enable(struct hclge_dev *hdev, int tqp_id, int stream_id, bool enable) { struct hclge_desc desc; - struct hclge_cfg_com_tqp_queue *req = - (struct hclge_cfg_com_tqp_queue *)desc.data; + struct hclge_cfg_com_tqp_queue_cmd *req = + (struct hclge_cfg_com_tqp_queue_cmd *)desc.data; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_COM_TQP_QUEUE, false); @@ -3031,7 +3204,7 @@ static int hclge_ae_start(struct hnae3_handle *handle) /* mac enable */ hclge_cfg_mac_mode(hdev, true); clear_bit(HCLGE_STATE_DOWN, &hdev->state); - (void)mod_timer(&hdev->service_timer, jiffies + HZ); + mod_timer(&hdev->service_timer, jiffies + HZ); ret = hclge_mac_start_phy(hdev); if (ret) @@ -3145,16 +3318,16 @@ static int hclge_update_desc_vfid(struct hclge_desc *desc, int vfid, bool clr) word_num = vfid / 32; bit_num = vfid % 32; if (clr) - desc[1].data[word_num] &= ~(1 << bit_num); + desc[1].data[word_num] &= cpu_to_le32(~(1 << bit_num)); else - desc[1].data[word_num] |= (1 << bit_num); + desc[1].data[word_num] |= cpu_to_le32(1 << bit_num); } else { word_num = (vfid - 192) / 32; bit_num = vfid % 32; if (clr) - desc[2].data[word_num] &= ~(1 << bit_num); + desc[2].data[word_num] &= cpu_to_le32(~(1 << bit_num)); else - desc[2].data[word_num] |= (1 << bit_num); + desc[2].data[word_num] |= cpu_to_le32(1 << bit_num); } return 0; @@ -3174,7 +3347,7 @@ static bool hclge_is_all_function_id_zero(struct hclge_desc *desc) return true; } -static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry *new_req, +static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry_cmd *new_req, const u8 *addr) { const unsigned char *mac_addr = addr; @@ -3186,8 +3359,8 @@ static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry *new_req, new_req->mac_addr_lo16 = cpu_to_le16(low_val & 0xffff); } -u16 hclge_get_mac_addr_to_mta_index(struct hclge_vport *vport, - const u8 *addr) +static u16 hclge_get_mac_addr_to_mta_index(struct hclge_vport *vport, + const u8 *addr) { u16 high_val = addr[1] | (addr[0] << 8); struct hclge_dev *hdev = vport->back; @@ -3201,11 +3374,11 @@ static int hclge_set_mta_filter_mode(struct hclge_dev *hdev, enum hclge_mta_dmac_sel_type mta_mac_sel, bool enable) { - struct hclge_mta_filter_mode *req; + struct hclge_mta_filter_mode_cmd *req; struct hclge_desc desc; int ret; - req = (struct hclge_mta_filter_mode *)desc.data; + req = (struct hclge_mta_filter_mode_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_MODE_CFG, false); hnae_set_bit(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_EN_B, @@ -3228,11 +3401,11 @@ int hclge_cfg_func_mta_filter(struct hclge_dev *hdev, u8 func_id, bool enable) { - struct hclge_cfg_func_mta_filter *req; + struct hclge_cfg_func_mta_filter_cmd *req; struct hclge_desc desc; int ret; - req = (struct hclge_cfg_func_mta_filter *)desc.data; + req = (struct hclge_cfg_func_mta_filter_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_FUNC_CFG, false); hnae_set_bit(req->accept, HCLGE_CFG_FUNC_MTA_ACCEPT_B, @@ -3255,17 +3428,18 @@ static int hclge_set_mta_table_item(struct hclge_vport *vport, bool enable) { struct hclge_dev *hdev = vport->back; - struct hclge_cfg_func_mta_item *req; + struct hclge_cfg_func_mta_item_cmd *req; struct hclge_desc desc; + u16 item_idx = 0; int ret; - req = (struct hclge_cfg_func_mta_item *)desc.data; + req = (struct hclge_cfg_func_mta_item_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_TBL_ITEM_CFG, false); hnae_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable); - hnae_set_field(req->item_idx, HCLGE_CFG_MTA_ITEM_IDX_M, + hnae_set_field(item_idx, HCLGE_CFG_MTA_ITEM_IDX_M, HCLGE_CFG_MTA_ITEM_IDX_S, idx); - req->item_idx = cpu_to_le16(req->item_idx); + req->item_idx = cpu_to_le16(item_idx); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { @@ -3279,16 +3453,17 @@ static int hclge_set_mta_table_item(struct hclge_vport *vport, } static int hclge_remove_mac_vlan_tbl(struct hclge_vport *vport, - struct hclge_mac_vlan_tbl_entry *req) + struct hclge_mac_vlan_tbl_entry_cmd *req) { struct hclge_dev *hdev = vport->back; struct hclge_desc desc; u8 resp_code; + u16 retval; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_REMOVE, false); - memcpy(desc.data, req, sizeof(struct hclge_mac_vlan_tbl_entry)); + memcpy(desc.data, req, sizeof(struct hclge_mac_vlan_tbl_entry_cmd)); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { @@ -3297,19 +3472,21 @@ static int hclge_remove_mac_vlan_tbl(struct hclge_vport *vport, ret); return ret; } - resp_code = (desc.data[0] >> 8) & 0xff; + resp_code = (le32_to_cpu(desc.data[0]) >> 8) & 0xff; + retval = le16_to_cpu(desc.retval); - return hclge_get_mac_vlan_cmd_status(vport, desc.retval, resp_code, + return hclge_get_mac_vlan_cmd_status(vport, retval, resp_code, HCLGE_MAC_VLAN_REMOVE); } static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport, - struct hclge_mac_vlan_tbl_entry *req, + struct hclge_mac_vlan_tbl_entry_cmd *req, struct hclge_desc *desc, bool is_mc) { struct hclge_dev *hdev = vport->back; u8 resp_code; + u16 retval; int ret; hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_MAC_VLAN_ADD, true); @@ -3317,7 +3494,7 @@ static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport, desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); memcpy(desc[0].data, req, - sizeof(struct hclge_mac_vlan_tbl_entry)); + sizeof(struct hclge_mac_vlan_tbl_entry_cmd)); hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_MAC_VLAN_ADD, true); @@ -3329,7 +3506,7 @@ static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport, } else { memcpy(desc[0].data, req, - sizeof(struct hclge_mac_vlan_tbl_entry)); + sizeof(struct hclge_mac_vlan_tbl_entry_cmd)); ret = hclge_cmd_send(&hdev->hw, desc, 1); } if (ret) { @@ -3338,19 +3515,21 @@ static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport, ret); return ret; } - resp_code = (desc[0].data[0] >> 8) & 0xff; + resp_code = (le32_to_cpu(desc[0].data[0]) >> 8) & 0xff; + retval = le16_to_cpu(desc[0].retval); - return hclge_get_mac_vlan_cmd_status(vport, desc[0].retval, resp_code, + return hclge_get_mac_vlan_cmd_status(vport, retval, resp_code, HCLGE_MAC_VLAN_LKUP); } static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport, - struct hclge_mac_vlan_tbl_entry *req, + struct hclge_mac_vlan_tbl_entry_cmd *req, struct hclge_desc *mc_desc) { struct hclge_dev *hdev = vport->back; int cfg_status; u8 resp_code; + u16 retval; int ret; if (!mc_desc) { @@ -3359,10 +3538,13 @@ static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport, hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_ADD, false); - memcpy(desc.data, req, sizeof(struct hclge_mac_vlan_tbl_entry)); + memcpy(desc.data, req, + sizeof(struct hclge_mac_vlan_tbl_entry_cmd)); ret = hclge_cmd_send(&hdev->hw, &desc, 1); - resp_code = (desc.data[0] >> 8) & 0xff; - cfg_status = hclge_get_mac_vlan_cmd_status(vport, desc.retval, + resp_code = (le32_to_cpu(desc.data[0]) >> 8) & 0xff; + retval = le16_to_cpu(desc.retval); + + cfg_status = hclge_get_mac_vlan_cmd_status(vport, retval, resp_code, HCLGE_MAC_VLAN_ADD); } else { @@ -3373,11 +3555,12 @@ static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport, mc_desc[2].flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR); mc_desc[2].flag &= cpu_to_le16(~HCLGE_CMD_FLAG_NEXT); memcpy(mc_desc[0].data, req, - sizeof(struct hclge_mac_vlan_tbl_entry)); + sizeof(struct hclge_mac_vlan_tbl_entry_cmd)); ret = hclge_cmd_send(&hdev->hw, mc_desc, 3); - resp_code = (mc_desc[0].data[0] >> 8) & 0xff; - cfg_status = hclge_get_mac_vlan_cmd_status(vport, - mc_desc[0].retval, + resp_code = (le32_to_cpu(mc_desc[0].data[0]) >> 8) & 0xff; + retval = le16_to_cpu(mc_desc[0].retval); + + cfg_status = hclge_get_mac_vlan_cmd_status(vport, retval, resp_code, HCLGE_MAC_VLAN_ADD); } @@ -3404,8 +3587,9 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport, const unsigned char *addr) { struct hclge_dev *hdev = vport->back; - struct hclge_mac_vlan_tbl_entry req; + struct hclge_mac_vlan_tbl_entry_cmd req; enum hclge_cmd_status status; + u16 egress_port = 0; /* mac addr check */ if (is_zero_ether_addr(addr) || @@ -3425,15 +3609,15 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport, hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 0); hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0); - hnae_set_bit(req.egress_port, - HCLGE_MAC_EPORT_SW_EN_B, 0); - hnae_set_bit(req.egress_port, - HCLGE_MAC_EPORT_TYPE_B, 0); - hnae_set_field(req.egress_port, HCLGE_MAC_EPORT_VFID_M, + + hnae_set_bit(egress_port, HCLGE_MAC_EPORT_SW_EN_B, 0); + hnae_set_bit(egress_port, HCLGE_MAC_EPORT_TYPE_B, 0); + hnae_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M, HCLGE_MAC_EPORT_VFID_S, vport->vport_id); - hnae_set_field(req.egress_port, HCLGE_MAC_EPORT_PFID_M, + hnae_set_field(egress_port, HCLGE_MAC_EPORT_PFID_M, HCLGE_MAC_EPORT_PFID_S, 0); - req.egress_port = cpu_to_le16(req.egress_port); + + req.egress_port = cpu_to_le16(egress_port); hclge_prepare_mac_addr(&req, addr); @@ -3454,7 +3638,7 @@ int hclge_rm_uc_addr_common(struct hclge_vport *vport, const unsigned char *addr) { struct hclge_dev *hdev = vport->back; - struct hclge_mac_vlan_tbl_entry req; + struct hclge_mac_vlan_tbl_entry_cmd req; enum hclge_cmd_status status; /* mac addr check */ @@ -3488,7 +3672,7 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, const unsigned char *addr) { struct hclge_dev *hdev = vport->back; - struct hclge_mac_vlan_tbl_entry req; + struct hclge_mac_vlan_tbl_entry_cmd req; struct hclge_desc desc[3]; u16 tbl_idx; int status; @@ -3539,7 +3723,7 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport, const unsigned char *addr) { struct hclge_dev *hdev = vport->back; - struct hclge_mac_vlan_tbl_entry req; + struct hclge_mac_vlan_tbl_entry_cmd req; enum hclge_cmd_status status; struct hclge_desc desc[3]; u16 tbl_idx; @@ -3622,13 +3806,13 @@ static int hclge_set_mac_addr(struct hnae3_handle *handle, void *p) static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type, bool filter_en) { - struct hclge_vlan_filter_ctrl *req; + struct hclge_vlan_filter_ctrl_cmd *req; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_FILTER_CTRL, false); - req = (struct hclge_vlan_filter_ctrl *)desc.data; + req = (struct hclge_vlan_filter_ctrl_cmd *)desc.data; req->vlan_type = vlan_type; req->vlan_fe = filter_en; @@ -3646,8 +3830,8 @@ int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid, bool is_kill, u16 vlan, u8 qos, __be16 proto) { #define HCLGE_MAX_VF_BYTES 16 - struct hclge_vlan_filter_vf_cfg *req0; - struct hclge_vlan_filter_vf_cfg *req1; + struct hclge_vlan_filter_vf_cfg_cmd *req0; + struct hclge_vlan_filter_vf_cfg_cmd *req1; struct hclge_desc desc[2]; u8 vf_byte_val; u8 vf_byte_off; @@ -3663,10 +3847,10 @@ int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid, vf_byte_off = vfid / 8; vf_byte_val = 1 << (vfid % 8); - req0 = (struct hclge_vlan_filter_vf_cfg *)desc[0].data; - req1 = (struct hclge_vlan_filter_vf_cfg *)desc[1].data; + req0 = (struct hclge_vlan_filter_vf_cfg_cmd *)desc[0].data; + req1 = (struct hclge_vlan_filter_vf_cfg_cmd *)desc[1].data; - req0->vlan_id = vlan; + req0->vlan_id = cpu_to_le16(vlan); req0->vlan_cfg = is_kill; if (vf_byte_off < HCLGE_MAX_VF_BYTES) @@ -3707,7 +3891,7 @@ static int hclge_set_port_vlan_filter(struct hnae3_handle *handle, { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - struct hclge_vlan_filter_pf_cfg *req; + struct hclge_vlan_filter_pf_cfg_cmd *req; struct hclge_desc desc; u8 vlan_offset_byte_val; u8 vlan_offset_byte; @@ -3720,7 +3904,7 @@ static int hclge_set_port_vlan_filter(struct hnae3_handle *handle, vlan_offset_byte = (vlan_id % 160) / 8; vlan_offset_byte_val = 1 << (vlan_id % 8); - req = (struct hclge_vlan_filter_pf_cfg *)desc.data; + req = (struct hclge_vlan_filter_pf_cfg_cmd *)desc.data; req->vlan_offset = vlan_offset_160; req->vlan_cfg = is_kill; req->vlan_offset_bitmap[vlan_offset_byte] = vlan_offset_byte_val; @@ -3782,7 +3966,7 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev) static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu) { struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_config_max_frm_size *req; + struct hclge_config_max_frm_size_cmd *req; struct hclge_dev *hdev = vport->back; struct hclge_desc desc; int ret; @@ -3793,7 +3977,7 @@ static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu) hdev->mps = new_mtu; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAX_FRM_SIZE, false); - req = (struct hclge_config_max_frm_size *)desc.data; + req = (struct hclge_config_max_frm_size_cmd *)desc.data; req->max_frm_size = cpu_to_le16(new_mtu); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -3808,13 +3992,13 @@ static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu) static int hclge_send_reset_tqp_cmd(struct hclge_dev *hdev, u16 queue_id, bool enable) { - struct hclge_reset_tqp_queue *req; + struct hclge_reset_tqp_queue_cmd *req; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RESET_TQP_QUEUE, false); - req = (struct hclge_reset_tqp_queue *)desc.data; + req = (struct hclge_reset_tqp_queue_cmd *)desc.data; req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK); hnae_set_bit(req->reset_req, HCLGE_TQP_RESET_B, enable); @@ -3830,13 +4014,13 @@ static int hclge_send_reset_tqp_cmd(struct hclge_dev *hdev, u16 queue_id, static int hclge_get_reset_status(struct hclge_dev *hdev, u16 queue_id) { - struct hclge_reset_tqp_queue *req; + struct hclge_reset_tqp_queue_cmd *req; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RESET_TQP_QUEUE, true); - req = (struct hclge_reset_tqp_queue *)desc.data; + req = (struct hclge_reset_tqp_queue_cmd *)desc.data; req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -4252,8 +4436,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_dcb_ops_set(hdev); - setup_timer(&hdev->service_timer, hclge_service_timer, - (unsigned long)hdev); + timer_setup(&hdev->service_timer, hclge_service_timer, 0); INIT_WORK(&hdev->service_task, hclge_service_task); set_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state); @@ -4280,7 +4463,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) if (IS_ENABLED(CONFIG_PCI_IOV)) hclge_disable_sriov(hdev); - if (hdev->service_timer.data) + if (hdev->service_timer.function) del_timer_sync(&hdev->service_timer); if (hdev->service_task.func) cancel_work_sync(&hdev->service_task); @@ -4313,6 +4496,8 @@ static const struct hnae3_ae_ops hclge_ops = { .get_rss_indir_size = hclge_get_rss_indir_size, .get_rss = hclge_get_rss, .set_rss = hclge_set_rss, + .set_rss_tuple = hclge_set_rss_tuple, + .get_rss_tuple = hclge_get_rss_tuple, .get_tc_size = hclge_get_tc_size, .get_mac_addr = hclge_get_mac_addr, .set_mac_addr = hclge_set_mac_addr, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 7c66c00e8a3e..bca4430bb7e7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -32,7 +32,7 @@ #define HCLGE_VECTOR_VF_OFFSET 0x100000 #define HCLGE_RSS_IND_TBL_SIZE 512 -#define HCLGE_RSS_SET_BITMAP_MSK 0xffff +#define HCLGE_RSS_SET_BITMAP_MSK GENMASK(15, 0) #define HCLGE_RSS_KEY_SIZE 40 #define HCLGE_RSS_HASH_ALGO_TOEPLITZ 0 #define HCLGE_RSS_HASH_ALGO_SIMPLE 1 @@ -41,6 +41,14 @@ #define HCLGE_RSS_CFG_TBL_NUM \ (HCLGE_RSS_IND_TBL_SIZE / HCLGE_RSS_CFG_TBL_SIZE) +#define HCLGE_RSS_INPUT_TUPLE_OTHER GENMASK(3, 0) +#define HCLGE_RSS_INPUT_TUPLE_SCTP GENMASK(4, 0) +#define HCLGE_D_PORT_BIT BIT(0) +#define HCLGE_S_PORT_BIT BIT(1) +#define HCLGE_D_IP_BIT BIT(2) +#define HCLGE_S_IP_BIT BIT(3) +#define HCLGE_V_TAG_BIT BIT(4) + #define HCLGE_RSS_TC_SIZE_0 1 #define HCLGE_RSS_TC_SIZE_1 2 #define HCLGE_RSS_TC_SIZE_2 4 @@ -65,7 +73,7 @@ #define HCLGE_PHY_CSS_REG 17 #define HCLGE_PHY_MDIX_CTRL_S (5) -#define HCLGE_PHY_MDIX_CTRL_M (3 << HCLGE_PHY_MDIX_CTRL_S) +#define HCLGE_PHY_MDIX_CTRL_M GENMASK(6, 5) #define HCLGE_PHY_MDIX_STATUS_B (6) #define HCLGE_PHY_SPEED_DUP_RESOLVE_B (11) @@ -462,6 +470,7 @@ struct hclge_dev { #define HCLGE_FLAG_MAIN 0x00000004 #define HCLGE_FLAG_DCB_CAPABLE 0x00000008 #define HCLGE_FLAG_DCB_ENABLE 0x00000010 +#define HCLGE_FLAG_MQPRIO_ENABLE 0x00000020 u32 flag; u32 pkt_buf_size; /* Total pf buf size for tx/rx */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 359ee670d1e1..1ae6eae82eb3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -283,6 +283,7 @@ static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev, struct hclge_pg_shapping_cmd *shap_cfg_cmd; enum hclge_opcode_type opcode; struct hclge_desc desc; + u32 shapping_para = 0; opcode = bucket ? HCLGE_OPC_TM_PG_P_SHAPPING : HCLGE_OPC_TM_PG_C_SHAPPING; @@ -292,11 +293,13 @@ static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev, shap_cfg_cmd->pg_id = pg_id; - hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_B, ir_b); - hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_U, ir_u); - hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_S, ir_s); - hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, BS_B, bs_b); - hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, BS_S, bs_s); + hclge_tm_set_field(shapping_para, IR_B, ir_b); + hclge_tm_set_field(shapping_para, IR_U, ir_u); + hclge_tm_set_field(shapping_para, IR_S, ir_s); + hclge_tm_set_field(shapping_para, BS_B, bs_b); + hclge_tm_set_field(shapping_para, BS_S, bs_s); + + shap_cfg_cmd->pg_shapping_para = cpu_to_le32(shapping_para); return hclge_cmd_send(&hdev->hw, &desc, 1); } @@ -337,6 +340,7 @@ static int hclge_tm_pri_shapping_cfg(struct hclge_dev *hdev, struct hclge_pri_shapping_cmd *shap_cfg_cmd; enum hclge_opcode_type opcode; struct hclge_desc desc; + u32 shapping_para = 0; opcode = bucket ? HCLGE_OPC_TM_PRI_P_SHAPPING : HCLGE_OPC_TM_PRI_C_SHAPPING; @@ -347,11 +351,13 @@ static int hclge_tm_pri_shapping_cfg(struct hclge_dev *hdev, shap_cfg_cmd->pri_id = pri_id; - hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_B, ir_b); - hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_U, ir_u); - hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_S, ir_s); - hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, BS_B, bs_b); - hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, BS_S, bs_s); + hclge_tm_set_field(shapping_para, IR_B, ir_b); + hclge_tm_set_field(shapping_para, IR_U, ir_u); + hclge_tm_set_field(shapping_para, IR_S, ir_s); + hclge_tm_set_field(shapping_para, BS_B, bs_b); + hclge_tm_set_field(shapping_para, BS_S, bs_s); + + shap_cfg_cmd->pri_shapping_para = cpu_to_le32(shapping_para); return hclge_cmd_send(&hdev->hw, &desc, 1); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c index 9832172bfb08..925619a7c50a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c @@ -13,8 +13,7 @@ static int hns3_dcbnl_ieee_getets(struct net_device *ndev, struct ieee_ets *ets) { - struct hns3_nic_priv *priv = netdev_priv(ndev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(ndev); if (h->kinfo.dcb_ops->ieee_getets) return h->kinfo.dcb_ops->ieee_getets(h, ets); @@ -25,8 +24,7 @@ int hns3_dcbnl_ieee_getets(struct net_device *ndev, struct ieee_ets *ets) static int hns3_dcbnl_ieee_setets(struct net_device *ndev, struct ieee_ets *ets) { - struct hns3_nic_priv *priv = netdev_priv(ndev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(ndev); if (h->kinfo.dcb_ops->ieee_setets) return h->kinfo.dcb_ops->ieee_setets(h, ets); @@ -37,8 +35,7 @@ int hns3_dcbnl_ieee_setets(struct net_device *ndev, struct ieee_ets *ets) static int hns3_dcbnl_ieee_getpfc(struct net_device *ndev, struct ieee_pfc *pfc) { - struct hns3_nic_priv *priv = netdev_priv(ndev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(ndev); if (h->kinfo.dcb_ops->ieee_getpfc) return h->kinfo.dcb_ops->ieee_getpfc(h, pfc); @@ -49,8 +46,7 @@ int hns3_dcbnl_ieee_getpfc(struct net_device *ndev, struct ieee_pfc *pfc) static int hns3_dcbnl_ieee_setpfc(struct net_device *ndev, struct ieee_pfc *pfc) { - struct hns3_nic_priv *priv = netdev_priv(ndev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(ndev); if (h->kinfo.dcb_ops->ieee_setpfc) return h->kinfo.dcb_ops->ieee_setpfc(h, pfc); @@ -61,8 +57,7 @@ int hns3_dcbnl_ieee_setpfc(struct net_device *ndev, struct ieee_pfc *pfc) /* DCBX configuration */ static u8 hns3_dcbnl_getdcbx(struct net_device *ndev) { - struct hns3_nic_priv *priv = netdev_priv(ndev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(ndev); if (h->kinfo.dcb_ops->getdcbx) return h->kinfo.dcb_ops->getdcbx(h); @@ -73,8 +68,7 @@ static u8 hns3_dcbnl_getdcbx(struct net_device *ndev) /* return 0 if successful, otherwise fail */ static u8 hns3_dcbnl_setdcbx(struct net_device *ndev, u8 mode) { - struct hns3_nic_priv *priv = netdev_priv(ndev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(ndev); if (h->kinfo.dcb_ops->setdcbx) return h->kinfo.dcb_ops->setdcbx(h, mode); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c index c31506514e5d..8fa4e658b273 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c @@ -19,12 +19,13 @@ #include <linux/sctp.h> #include <linux/vermagic.h> #include <net/gre.h> +#include <net/pkt_cls.h> #include <net/vxlan.h> #include "hnae3.h" #include "hns3_enet.h" -const char hns3_driver_name[] = "hns3"; +static const char hns3_driver_name[] = "hns3"; const char hns3_driver_version[] = VERMAGIC_STRING; static const char hns3_driver_string[] = "Hisilicon Ethernet Network Driver for Hip08 Family"; @@ -198,8 +199,7 @@ static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector) static int hns3_nic_set_real_num_queue(struct net_device *netdev) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); struct hnae3_knic_private_info *kinfo = &h->kinfo; unsigned int queue_size = kinfo->rss_size * kinfo->num_tc; int ret; @@ -305,24 +305,10 @@ static int hns3_nic_net_stop(struct net_device *netdev) return 0; } -void hns3_set_multicast_list(struct net_device *netdev) -{ - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; - struct netdev_hw_addr *ha = NULL; - - if (h->ae_algo->ops->set_mc_addr) { - netdev_for_each_mc_addr(ha, netdev) - if (h->ae_algo->ops->set_mc_addr(h, ha->addr)) - netdev_err(netdev, "set multicast fail\n"); - } -} - static int hns3_nic_uc_sync(struct net_device *netdev, const unsigned char *addr) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (h->ae_algo->ops->add_uc_addr) return h->ae_algo->ops->add_uc_addr(h, addr); @@ -333,8 +319,7 @@ static int hns3_nic_uc_sync(struct net_device *netdev, static int hns3_nic_uc_unsync(struct net_device *netdev, const unsigned char *addr) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (h->ae_algo->ops->rm_uc_addr) return h->ae_algo->ops->rm_uc_addr(h, addr); @@ -345,8 +330,7 @@ static int hns3_nic_uc_unsync(struct net_device *netdev, static int hns3_nic_mc_sync(struct net_device *netdev, const unsigned char *addr) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (h->ae_algo->ops->add_mc_addr) return h->ae_algo->ops->add_mc_addr(h, addr); @@ -357,8 +341,7 @@ static int hns3_nic_mc_sync(struct net_device *netdev, static int hns3_nic_mc_unsync(struct net_device *netdev, const unsigned char *addr) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (h->ae_algo->ops->rm_mc_addr) return h->ae_algo->ops->rm_mc_addr(h, addr); @@ -366,10 +349,9 @@ static int hns3_nic_mc_unsync(struct net_device *netdev, return 0; } -void hns3_nic_set_rx_mode(struct net_device *netdev) +static void hns3_nic_set_rx_mode(struct net_device *netdev) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (h->ae_algo->ops->set_promisc_mode) { if (netdev->flags & IFF_PROMISC) @@ -768,7 +750,7 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, if (type == DESC_TYPE_SKB) { skb = (struct sk_buff *)priv; - paylen = cpu_to_le16(skb->len); + paylen = skb->len; if (skb->ip_summed == CHECKSUM_PARTIAL) { skb_reset_mac_len(skb); @@ -802,7 +784,7 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, cpu_to_le32(ol_type_vlan_len_msec); desc->tx.type_cs_vlan_tso_len = cpu_to_le32(type_cs_vlan_tso); - desc->tx.paylen = cpu_to_le16(paylen); + desc->tx.paylen = cpu_to_le32(paylen); desc->tx.mss = cpu_to_le16(mss); } @@ -1025,8 +1007,7 @@ out_net_tx_busy: static int hns3_nic_net_set_mac_address(struct net_device *netdev, void *p) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); struct sockaddr *mac_addr = p; int ret; @@ -1206,61 +1187,80 @@ static void hns3_nic_udp_tunnel_del(struct net_device *netdev, } } -static int hns3_setup_tc(struct net_device *netdev, u8 tc) +static int hns3_setup_tc(struct net_device *netdev, void *type_data) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct tc_mqprio_qopt_offload *mqprio_qopt = type_data; + struct hnae3_handle *h = hns3_get_handle(netdev); struct hnae3_knic_private_info *kinfo = &h->kinfo; + u8 *prio_tc = mqprio_qopt->qopt.prio_tc_map; + u8 tc = mqprio_qopt->qopt.num_tc; + u16 mode = mqprio_qopt->mode; + u8 hw = mqprio_qopt->qopt.hw; + bool if_running; unsigned int i; int ret; + if (!((hw == TC_MQPRIO_HW_OFFLOAD_TCS && + mode == TC_MQPRIO_MODE_CHANNEL) || (!hw && tc == 0))) + return -EOPNOTSUPP; + if (tc > HNAE3_MAX_TC) return -EINVAL; - if (kinfo->num_tc == tc) - return 0; - if (!netdev) return -EINVAL; - if (!tc) { - netdev_reset_tc(netdev); - return 0; + if_running = netif_running(netdev); + if (if_running) { + hns3_nic_net_stop(netdev); + msleep(100); } - /* Set num_tc for netdev */ - ret = netdev_set_num_tc(netdev, tc); + ret = (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ? + kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP; if (ret) - return ret; + goto out; + + if (tc <= 1) { + netdev_reset_tc(netdev); + } else { + ret = netdev_set_num_tc(netdev, tc); + if (ret) + goto out; + + for (i = 0; i < HNAE3_MAX_TC; i++) { + if (!kinfo->tc_info[i].enable) + continue; - /* Set per TC queues for the VSI */ - for (i = 0; i < HNAE3_MAX_TC; i++) { - if (kinfo->tc_info[i].enable) netdev_set_tc_queue(netdev, kinfo->tc_info[i].tc, kinfo->tc_info[i].tqp_count, kinfo->tc_info[i].tqp_offset); + } } - return 0; + ret = hns3_nic_set_real_num_queue(netdev); + +out: + if (if_running) + hns3_nic_net_open(netdev); + + return ret; } static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { - struct tc_mqprio_qopt *mqprio = type_data; - if (type != TC_SETUP_MQPRIO) return -EOPNOTSUPP; - return hns3_setup_tc(dev, mqprio->num_tc); + return hns3_setup_tc(dev, type_data); } static int hns3_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); int ret = -EIO; if (h->ae_algo->ops->set_vlan_filter) @@ -1272,8 +1272,7 @@ static int hns3_vlan_rx_add_vid(struct net_device *netdev, static int hns3_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); int ret = -EIO; if (h->ae_algo->ops->set_vlan_filter) @@ -1285,8 +1284,7 @@ static int hns3_vlan_rx_kill_vid(struct net_device *netdev, static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, __be16 vlan_proto) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); int ret = -EIO; if (h->ae_algo->ops->set_vf_vlan_filter) @@ -1298,8 +1296,7 @@ static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); bool if_running = netif_running(netdev); int ret; @@ -2609,7 +2606,7 @@ static void hns3_fini_ring(struct hns3_enet_ring *ring) ring->next_to_use = 0; } -int hns3_buf_size2type(u32 buf_size) +static int hns3_buf_size2type(u32 buf_size) { int bd_size_type; @@ -2662,7 +2659,7 @@ static void hns3_init_ring_hw(struct hns3_enet_ring *ring) } } -static int hns3_init_all_ring(struct hns3_nic_priv *priv) +int hns3_init_all_ring(struct hns3_nic_priv *priv) { struct hnae3_handle *h = priv->ae_handle; int ring_num = h->kinfo.num_tqps * 2; @@ -2686,12 +2683,12 @@ static int hns3_init_all_ring(struct hns3_nic_priv *priv) out_when_alloc_ring_memory: for (j = i - 1; j >= 0; j--) - hns3_fini_ring(priv->ring_data[i].ring); + hns3_fini_ring(priv->ring_data[j].ring); return -ENOMEM; } -static int hns3_uninit_all_ring(struct hns3_nic_priv *priv) +int hns3_uninit_all_ring(struct hns3_nic_priv *priv) { struct hnae3_handle *h = priv->ae_handle; int i; @@ -2921,7 +2918,7 @@ err_out: return ret; } -const struct hnae3_client_ops client_ops = { +static const struct hnae3_client_ops client_ops = { .init_instance = hns3_client_init, .uninit_instance = hns3_client_uninit, .link_status_change = hns3_link_status_change, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h index 481eada73e2d..66599890b4d4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h @@ -76,6 +76,8 @@ enum hns3_nic_state { #define HNS3_RING_NAME_LEN 16 #define HNS3_BUFFER_SIZE_2048 2048 #define HNS3_RING_MAX_PENDING 32768 +#define HNS3_RING_MIN_PENDING 8 +#define HNS3_RING_BD_MULTIPLE 8 #define HNS3_MAX_MTU 9728 #define HNS3_BD_SIZE_512_TYPE 0 @@ -587,9 +589,14 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value) #define hns3_for_each_ring(pos, head) \ for (pos = (head).ring; pos; pos = pos->next) +#define hns3_get_handle(ndev) \ + (((struct hns3_nic_priv *)netdev_priv(ndev))->ae_handle) + void hns3_ethtool_set_ops(struct net_device *netdev); int hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget); +int hns3_init_all_ring(struct hns3_nic_priv *priv); +int hns3_uninit_all_ring(struct hns3_nic_priv *priv); #ifdef CONFIG_HNS3_DCB void hns3_dcbnl_setup(struct hnae3_handle *handle); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c index d636399232fb..ddbd7f30c6a4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c @@ -102,8 +102,7 @@ static void hns3_driv_to_eth_caps(u32 caps, struct ethtool_link_ksettings *cmd, static int hns3_get_sset_count(struct net_device *netdev, int stringset) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); const struct hnae3_ae_ops *ops = h->ae_algo->ops; if (!ops->get_sset_count) @@ -164,8 +163,7 @@ static u8 *hns3_get_strings_tqps(struct hnae3_handle *handle, u8 *data) static void hns3_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); const struct hnae3_ae_ops *ops = h->ae_algo->ops; char *buff = (char *)data; @@ -217,11 +215,10 @@ static u64 *hns3_get_stats_tqps(struct hnae3_handle *handle, u64 *data) * @stats: statistics info. * @data: statistics data. */ -void hns3_get_stats(struct net_device *netdev, struct ethtool_stats *stats, - u64 *data) +static void hns3_get_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *data) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); u64 *p = data; if (!h->ae_algo->ops->get_stats || !h->ae_algo->ops->update_stats) { @@ -262,10 +259,7 @@ static void hns3_get_drvinfo(struct net_device *netdev, static u32 hns3_get_link(struct net_device *netdev) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h; - - h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (h->ae_algo && h->ae_algo->ops && h->ae_algo->ops->get_status) return h->ae_algo->ops->get_status(h); @@ -277,7 +271,8 @@ static void hns3_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *param) { struct hns3_nic_priv *priv = netdev_priv(netdev); - int queue_num = priv->ae_handle->kinfo.num_tqps; + struct hnae3_handle *h = priv->ae_handle; + int queue_num = h->kinfo.num_tqps; param->tx_max_pending = HNS3_RING_MAX_PENDING; param->rx_max_pending = HNS3_RING_MAX_PENDING; @@ -289,8 +284,7 @@ static void hns3_get_ringparam(struct net_device *netdev, static void hns3_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *param) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (h->ae_algo && h->ae_algo->ops && h->ae_algo->ops->get_pauseparam) h->ae_algo->ops->get_pauseparam(h, ¶m->autoneg, @@ -300,8 +294,7 @@ static void hns3_get_pauseparam(struct net_device *netdev, static int hns3_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); u32 supported_caps; u32 advertised_caps; u8 media_type = HNAE3_MEDIA_TYPE_UNKNOWN; @@ -392,8 +385,7 @@ static int hns3_get_link_ksettings(struct net_device *netdev, static u32 hns3_get_rss_key_size(struct net_device *netdev) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_rss_key_size) @@ -404,8 +396,7 @@ static u32 hns3_get_rss_key_size(struct net_device *netdev) static u32 hns3_get_rss_indir_size(struct net_device *netdev) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_rss_indir_size) @@ -417,8 +408,7 @@ static u32 hns3_get_rss_indir_size(struct net_device *netdev) static int hns3_get_rss(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_rss) return -EOPNOTSUPP; @@ -429,8 +419,7 @@ static int hns3_get_rss(struct net_device *netdev, u32 *indir, u8 *key, static int hns3_set_rss(struct net_device *netdev, const u32 *indir, const u8 *key, const u8 hfunc) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->set_rss) return -EOPNOTSUPP; @@ -454,16 +443,17 @@ static int hns3_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_tc_size) return -EOPNOTSUPP; switch (cmd->cmd) { case ETHTOOL_GRXRINGS: - cmd->data = h->ae_algo->ops->get_tc_size(h); + cmd->data = h->kinfo.num_tc * h->kinfo.rss_size; break; + case ETHTOOL_GRXFH: + return h->ae_algo->ops->get_rss_tuple(h, cmd); default: return -EOPNOTSUPP; } @@ -471,15 +461,108 @@ static int hns3_get_rxnfc(struct net_device *netdev, return 0; } +static int hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv, + u32 new_desc_num) +{ + struct hnae3_handle *h = priv->ae_handle; + int i; + + h->kinfo.num_desc = new_desc_num; + + for (i = 0; i < h->kinfo.num_tqps * 2; i++) + priv->ring_data[i].ring->desc_num = new_desc_num; + + return hns3_init_all_ring(priv); +} + +static int hns3_set_ringparam(struct net_device *ndev, + struct ethtool_ringparam *param) +{ + struct hns3_nic_priv *priv = netdev_priv(ndev); + struct hnae3_handle *h = priv->ae_handle; + bool if_running = netif_running(ndev); + u32 old_desc_num, new_desc_num; + int ret; + + if (param->rx_mini_pending || param->rx_jumbo_pending) + return -EINVAL; + + if (param->tx_pending != param->rx_pending) { + netdev_err(ndev, + "Descriptors of tx and rx must be equal"); + return -EINVAL; + } + + if (param->tx_pending > HNS3_RING_MAX_PENDING || + param->tx_pending < HNS3_RING_MIN_PENDING) { + netdev_err(ndev, + "Descriptors requested (Tx/Rx: %d) out of range [%d-%d]\n", + param->tx_pending, HNS3_RING_MIN_PENDING, + HNS3_RING_MAX_PENDING); + return -EINVAL; + } + + new_desc_num = param->tx_pending; + + /* Hardware requires that its descriptors must be multiple of eight */ + new_desc_num = ALIGN(new_desc_num, HNS3_RING_BD_MULTIPLE); + old_desc_num = h->kinfo.num_desc; + if (old_desc_num == new_desc_num) + return 0; + + netdev_info(ndev, + "Changing descriptor count from %d to %d.\n", + old_desc_num, new_desc_num); + + if (if_running) + dev_close(ndev); + + ret = hns3_uninit_all_ring(priv); + if (ret) + return ret; + + ret = hns3_change_all_ring_bd_num(priv, new_desc_num); + if (ret) { + ret = hns3_change_all_ring_bd_num(priv, old_desc_num); + if (ret) { + netdev_err(ndev, + "Revert to old bd num fail, ret=%d.\n", ret); + return ret; + } + } + + if (if_running) + ret = dev_open(ndev); + + return ret; +} + +static int hns3_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) +{ + struct hnae3_handle *h = hns3_get_handle(netdev); + + if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->set_rss_tuple) + return -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_SRXFH: + return h->ae_algo->ops->set_rss_tuple(h, cmd); + default: + return -EOPNOTSUPP; + } +} + static const struct ethtool_ops hns3_ethtool_ops = { .get_drvinfo = hns3_get_drvinfo, .get_link = hns3_get_link, .get_ringparam = hns3_get_ringparam, + .set_ringparam = hns3_set_ringparam, .get_pauseparam = hns3_get_pauseparam, .get_strings = hns3_get_strings, .get_ethtool_stats = hns3_get_stats, .get_sset_count = hns3_get_sset_count, .get_rxnfc = hns3_get_rxnfc, + .set_rxnfc = hns3_set_rxnfc, .get_rxfh_key_size = hns3_get_rss_key_size, .get_rxfh_indir_size = hns3_get_rss_indir_size, .get_rxfh = hns3_get_rss, diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 4bc14a901571..b991703319f9 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -553,6 +553,10 @@ static int reset_tx_pools(struct ibmvnic_adapter *adapter) if (rc) return rc; + rc = reset_long_term_buff(adapter, &tx_pool->tso_ltb); + if (rc) + return rc; + memset(tx_pool->tx_buff, 0, adapter->req_tx_entries_per_subcrq * sizeof(struct ibmvnic_tx_buff)); @@ -562,6 +566,7 @@ static int reset_tx_pools(struct ibmvnic_adapter *adapter) tx_pool->consumer_index = 0; tx_pool->producer_index = 0; + tx_pool->tso_index = 0; } return 0; @@ -581,6 +586,7 @@ static void release_tx_pools(struct ibmvnic_adapter *adapter) tx_pool = &adapter->tx_pool[i]; kfree(tx_pool->tx_buff); free_long_term_buff(adapter, &tx_pool->long_term_buff); + free_long_term_buff(adapter, &tx_pool->tso_ltb); kfree(tx_pool->free_map); } @@ -625,6 +631,16 @@ static int init_tx_pools(struct net_device *netdev) return -1; } + /* alloc TSO ltb */ + if (alloc_long_term_buff(adapter, &tx_pool->tso_ltb, + IBMVNIC_TSO_BUFS * + IBMVNIC_TSO_BUF_SZ)) { + release_tx_pools(adapter); + return -1; + } + + tx_pool->tso_index = 0; + tx_pool->free_map = kcalloc(adapter->req_tx_entries_per_subcrq, sizeof(int), GFP_KERNEL); if (!tx_pool->free_map) { @@ -1201,11 +1217,41 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) be32_to_cpu(adapter->login_rsp_buf->off_txsubm_subcrqs)); index = tx_pool->free_map[tx_pool->consumer_index]; - offset = index * adapter->req_mtu; - dst = tx_pool->long_term_buff.buff + offset; - memset(dst, 0, adapter->req_mtu); - skb_copy_from_linear_data(skb, dst, skb->len); - data_dma_addr = tx_pool->long_term_buff.addr + offset; + + if (skb_is_gso(skb)) { + offset = tx_pool->tso_index * IBMVNIC_TSO_BUF_SZ; + dst = tx_pool->tso_ltb.buff + offset; + memset(dst, 0, IBMVNIC_TSO_BUF_SZ); + data_dma_addr = tx_pool->tso_ltb.addr + offset; + tx_pool->tso_index++; + if (tx_pool->tso_index == IBMVNIC_TSO_BUFS) + tx_pool->tso_index = 0; + } else { + offset = index * adapter->req_mtu; + dst = tx_pool->long_term_buff.buff + offset; + memset(dst, 0, adapter->req_mtu); + data_dma_addr = tx_pool->long_term_buff.addr + offset; + } + + if (skb_shinfo(skb)->nr_frags) { + int cur, i; + + /* Copy the head */ + skb_copy_from_linear_data(skb, dst, skb_headlen(skb)); + cur = skb_headlen(skb); + + /* Copy the frags */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + memcpy(dst + cur, + page_address(skb_frag_page(frag)) + + frag->page_offset, skb_frag_size(frag)); + cur += skb_frag_size(frag); + } + } else { + skb_copy_from_linear_data(skb, dst, skb->len); + } tx_pool->consumer_index = (tx_pool->consumer_index + 1) % @@ -1226,7 +1272,10 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_crq.v1.n_sge = 1; tx_crq.v1.flags1 = IBMVNIC_TX_COMP_NEEDED; tx_crq.v1.correlator = cpu_to_be32(index); - tx_crq.v1.dma_reg = cpu_to_be16(tx_pool->long_term_buff.map_id); + if (skb_is_gso(skb)) + tx_crq.v1.dma_reg = cpu_to_be16(tx_pool->tso_ltb.map_id); + else + tx_crq.v1.dma_reg = cpu_to_be16(tx_pool->long_term_buff.map_id); tx_crq.v1.sge_len = cpu_to_be32(skb->len); tx_crq.v1.ioba = cpu_to_be64(data_dma_addr); @@ -1251,6 +1300,11 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_crq.v1.flags1 |= IBMVNIC_TX_CHKSUM_OFFLOAD; hdrs += 2; } + if (skb_is_gso(skb)) { + tx_crq.v1.flags1 |= IBMVNIC_TX_LSO; + tx_crq.v1.mss = cpu_to_be16(skb_shinfo(skb)->gso_size); + hdrs += 2; + } /* determine if l2/3/4 headers are sent to firmware */ if ((*hdrs >> 7) & 1 && (skb->protocol == htons(ETH_P_IP) || @@ -2941,14 +2995,14 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter) adapter->ip_offload_ctrl.udp_ipv4_chksum = buf->udp_ipv4_chksum; adapter->ip_offload_ctrl.tcp_ipv6_chksum = buf->tcp_ipv6_chksum; adapter->ip_offload_ctrl.udp_ipv6_chksum = buf->udp_ipv6_chksum; + adapter->ip_offload_ctrl.large_tx_ipv4 = buf->large_tx_ipv4; + adapter->ip_offload_ctrl.large_tx_ipv6 = buf->large_tx_ipv6; - /* large_tx/rx disabled for now, additional features needed */ - adapter->ip_offload_ctrl.large_tx_ipv4 = 0; - adapter->ip_offload_ctrl.large_tx_ipv6 = 0; + /* large_rx disabled for now, additional features needed */ adapter->ip_offload_ctrl.large_rx_ipv4 = 0; adapter->ip_offload_ctrl.large_rx_ipv6 = 0; - adapter->netdev->features = NETIF_F_GSO; + adapter->netdev->features = NETIF_F_SG | NETIF_F_GSO; if (buf->tcp_ipv4_chksum || buf->udp_ipv4_chksum) adapter->netdev->features |= NETIF_F_IP_CSUM; @@ -2960,6 +3014,13 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter) (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))) adapter->netdev->features |= NETIF_F_RXCSUM; + if (buf->large_tx_ipv4) + adapter->netdev->features |= NETIF_F_TSO; + if (buf->large_tx_ipv6) + adapter->netdev->features |= NETIF_F_TSO6; + + adapter->netdev->hw_features |= adapter->netdev->features; + memset(&crq, 0, sizeof(crq)); crq.control_ip_offload.first = IBMVNIC_CRQ_CMD; crq.control_ip_offload.cmd = CONTROL_IP_OFFLOAD; diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index d02257ccc377..7aa347a21e78 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -39,6 +39,9 @@ #define IBMVNIC_BUFFS_PER_POOL 100 #define IBMVNIC_MAX_TX_QUEUES 5 +#define IBMVNIC_TSO_BUF_SZ 65536 +#define IBMVNIC_TSO_BUFS 64 + struct ibmvnic_login_buffer { __be32 len; __be32 version; @@ -896,6 +899,8 @@ struct ibmvnic_tx_pool { wait_queue_head_t ibmvnic_tx_comp_q; struct task_struct *work_thread; struct ibmvnic_long_term_buff long_term_buff; + struct ibmvnic_long_term_buff tso_ltb; + int tso_index; }; struct ibmvnic_rx_buff { diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 184f11242f56..44b3937f7e81 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -1710,9 +1710,9 @@ static void e100_adjust_adaptive_ifs(struct nic *nic, int speed, int duplex) } } -static void e100_watchdog(unsigned long data) +static void e100_watchdog(struct timer_list *t) { - struct nic *nic = (struct nic *)data; + struct nic *nic = from_timer(nic, t, watchdog); struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET }; u32 speed; @@ -2920,7 +2920,7 @@ static int e100_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); - setup_timer(&nic->watchdog, e100_watchdog, (unsigned long)nic); + timer_setup(&nic->watchdog, e100_watchdog, 0); INIT_WORK(&nic->tx_timeout_task, e100_tx_timeout_task); diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 0641c0098738..afb7ebe20b24 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -398,6 +398,7 @@ #define E1000_ICR_LSC 0x00000004 /* Link Status Change */ #define E1000_ICR_RXSEQ 0x00000008 /* Rx sequence error */ #define E1000_ICR_RXDMT0 0x00000010 /* Rx desc min. threshold (0) */ +#define E1000_ICR_RXO 0x00000040 /* Receiver Overrun */ #define E1000_ICR_RXT0 0x00000080 /* Rx timer intr (ring 0) */ #define E1000_ICR_ECCER 0x00400000 /* Uncorrectable ECC Error */ /* If this bit asserted, the driver should claim the interrupt */ diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 98e68888abb1..2311b31bdcac 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -94,10 +94,6 @@ struct e1000_info; */ #define E1000_CHECK_RESET_COUNT 25 -#define DEFAULT_RDTR 0 -#define DEFAULT_RADV 8 -#define BURST_RDTR 0x20 -#define BURST_RADV 0x20 #define PCICFG_DESC_RING_STATUS 0xe4 #define FLUSH_DESC_REQUIRED 0x100 diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c index b322011ec282..f457c5703d0c 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.c +++ b/drivers/net/ethernet/intel/e1000e/mac.c @@ -410,6 +410,9 @@ void e1000e_clear_hw_cntrs_base(struct e1000_hw *hw) * Checks to see of the link status of the hardware has changed. If a * change in link status has been detected, then we read the PHY registers * to get the current speed/duplex if link exists. + * + * Returns a negative error code (-E1000_ERR_*) or 0 (link down) or 1 (link + * up). **/ s32 e1000e_check_for_copper_link(struct e1000_hw *hw) { @@ -423,7 +426,7 @@ s32 e1000e_check_for_copper_link(struct e1000_hw *hw) * Change or Rx Sequence Error interrupt. */ if (!mac->get_link_status) - return 0; + return 1; /* First we want to see if the MII Status Register reports * link. If so, then we want to get the current speed/duplex @@ -461,10 +464,12 @@ s32 e1000e_check_for_copper_link(struct e1000_hw *hw) * different link partner. */ ret_val = e1000e_config_fc_after_link_up(hw); - if (ret_val) + if (ret_val) { e_dbg("Error configuring flow control\n"); + return ret_val; + } - return ret_val; + return 1; } /** diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 8436c5f2c3e8..f2f49239b015 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -1071,7 +1071,8 @@ next_desc: } static void e1000_put_txbuf(struct e1000_ring *tx_ring, - struct e1000_buffer *buffer_info) + struct e1000_buffer *buffer_info, + bool drop) { struct e1000_adapter *adapter = tx_ring->adapter; @@ -1085,7 +1086,10 @@ static void e1000_put_txbuf(struct e1000_ring *tx_ring, buffer_info->dma = 0; } if (buffer_info->skb) { - dev_kfree_skb_any(buffer_info->skb); + if (drop) + dev_kfree_skb_any(buffer_info->skb); + else + dev_consume_skb_any(buffer_info->skb); buffer_info->skb = NULL; } buffer_info->time_stamp = 0; @@ -1199,7 +1203,7 @@ static void e1000e_tx_hwtstamp_work(struct work_struct *work) wmb(); /* force write prior to skb_tstamp_tx */ skb_tstamp_tx(skb, &shhwtstamps); - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); } else if (time_after(jiffies, adapter->tx_hwtstamp_start + adapter->tx_timeout_factor * HZ)) { dev_kfree_skb_any(adapter->tx_hwtstamp_skb); @@ -1254,7 +1258,7 @@ static bool e1000_clean_tx_irq(struct e1000_ring *tx_ring) } } - e1000_put_txbuf(tx_ring, buffer_info); + e1000_put_txbuf(tx_ring, buffer_info, false); tx_desc->upper.data = 0; i++; @@ -1910,14 +1914,30 @@ static irqreturn_t e1000_msix_other(int __always_unused irq, void *data) struct net_device *netdev = data; struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; + u32 icr; + bool enable = true; + + icr = er32(ICR); + if (icr & E1000_ICR_RXO) { + ew32(ICR, E1000_ICR_RXO); + enable = false; + /* napi poll will re-enable Other, make sure it runs */ + if (napi_schedule_prep(&adapter->napi)) { + adapter->total_rx_bytes = 0; + adapter->total_rx_packets = 0; + __napi_schedule(&adapter->napi); + } + } + if (icr & E1000_ICR_LSC) { + ew32(ICR, E1000_ICR_LSC); + hw->mac.get_link_status = true; + /* guard against interrupt when we're going down */ + if (!test_bit(__E1000_DOWN, &adapter->state)) + mod_timer(&adapter->watchdog_timer, jiffies + 1); + } - hw->mac.get_link_status = true; - - /* guard against interrupt when we're going down */ - if (!test_bit(__E1000_DOWN, &adapter->state)) { - mod_timer(&adapter->watchdog_timer, jiffies + 1); + if (enable && !test_bit(__E1000_DOWN, &adapter->state)) ew32(IMS, E1000_IMS_OTHER); - } return IRQ_HANDLED; } @@ -2421,7 +2441,7 @@ static void e1000_clean_tx_ring(struct e1000_ring *tx_ring) for (i = 0; i < tx_ring->count; i++) { buffer_info = &tx_ring->buffer_info[i]; - e1000_put_txbuf(tx_ring, buffer_info); + e1000_put_txbuf(tx_ring, buffer_info, false); } netdev_reset_queue(adapter->netdev); @@ -2687,7 +2707,8 @@ static int e1000e_poll(struct napi_struct *napi, int weight) napi_complete_done(napi, work_done); if (!test_bit(__E1000_DOWN, &adapter->state)) { if (adapter->msix_entries) - ew32(IMS, adapter->rx_ring->ims_val); + ew32(IMS, adapter->rx_ring->ims_val | + E1000_IMS_OTHER); else e1000_irq_enable(adapter); } @@ -3004,8 +3025,8 @@ static void e1000_configure_tx(struct e1000_adapter *adapter) hw->mac.ops.config_collision_dist(hw); - /* SPT and CNP Si errata workaround to avoid data corruption */ - if (hw->mac.type >= e1000_pch_spt) { + /* SPT and KBL Si errata workaround to avoid data corruption */ + if (hw->mac.type == e1000_pch_spt) { u32 reg_val; reg_val = er32(IOSFPC); @@ -3013,7 +3034,9 @@ static void e1000_configure_tx(struct e1000_adapter *adapter) ew32(IOSFPC, reg_val); reg_val = er32(TARC(0)); - reg_val |= E1000_TARC0_CB_MULTIQ_3_REQ; + /* SPT and KBL Si errata workaround to avoid Tx hang */ + reg_val &= ~BIT(28); + reg_val |= BIT(29); ew32(TARC(0), reg_val); } } @@ -3223,14 +3246,6 @@ static void e1000_configure_rx(struct e1000_adapter *adapter) */ ew32(RXDCTL(0), E1000_RXDCTL_DMA_BURST_ENABLE); ew32(RXDCTL(1), E1000_RXDCTL_DMA_BURST_ENABLE); - - /* override the delay timers for enabling bursting, only if - * the value was not set by the user via module options - */ - if (adapter->rx_int_delay == DEFAULT_RDTR) - adapter->rx_int_delay = BURST_RDTR; - if (adapter->rx_abs_int_delay == DEFAULT_RADV) - adapter->rx_abs_int_delay = BURST_RADV; } /* set the Receive Delay Timer Register */ @@ -4204,7 +4219,7 @@ static void e1000e_trigger_lsc(struct e1000_adapter *adapter) struct e1000_hw *hw = &adapter->hw; if (adapter->msix_entries) - ew32(ICS, E1000_ICS_OTHER); + ew32(ICS, E1000_ICS_LSC | E1000_ICS_OTHER); else ew32(ICS, E1000_ICS_LSC); } @@ -4808,9 +4823,9 @@ static void e1000e_update_phy_task(struct work_struct *work) * Need to wait a few seconds after link up to get diagnostic information from * the phy **/ -static void e1000_update_phy_info(unsigned long data) +static void e1000_update_phy_info(struct timer_list *t) { - struct e1000_adapter *adapter = (struct e1000_adapter *)data; + struct e1000_adapter *adapter = from_timer(adapter, t, phy_info_timer); if (test_bit(__E1000_DOWN, &adapter->state)) return; @@ -5074,14 +5089,14 @@ static bool e1000e_has_link(struct e1000_adapter *adapter) /* get_link_status is set on LSC (link status) interrupt or * Rx sequence error interrupt. get_link_status will stay - * false until the check_for_link establishes link + * true until the check_for_link establishes link * for copper adapters ONLY */ switch (hw->phy.media_type) { case e1000_media_type_copper: if (hw->mac.get_link_status) { ret_val = hw->mac.ops.check_for_link(hw); - link_active = !hw->mac.get_link_status; + link_active = ret_val > 0; } else { link_active = true; } @@ -5092,14 +5107,14 @@ static bool e1000e_has_link(struct e1000_adapter *adapter) break; case e1000_media_type_internal_serdes: ret_val = hw->mac.ops.check_for_link(hw); - link_active = adapter->hw.mac.serdes_has_link; + link_active = hw->mac.serdes_has_link; break; default: case e1000_media_type_unknown: break; } - if ((ret_val == E1000_ERR_PHY) && (hw->phy.type == e1000_phy_igp_3) && + if ((ret_val == -E1000_ERR_PHY) && (hw->phy.type == e1000_phy_igp_3) && (er32(CTRL) & E1000_PHY_CTRL_GBE_DISABLE)) { /* See e1000_kmrn_lock_loss_workaround_ich8lan() */ e_info("Gigabit has been disabled, downgrading speed\n"); @@ -5144,9 +5159,9 @@ static void e1000e_check_82574_phy_workaround(struct e1000_adapter *adapter) * e1000_watchdog - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void e1000_watchdog(unsigned long data) +static void e1000_watchdog(struct timer_list *t) { - struct e1000_adapter *adapter = (struct e1000_adapter *)data; + struct e1000_adapter *adapter = from_timer(adapter, t, watchdog_timer); /* Do the rest outside of interrupt context */ schedule_work(&adapter->watchdog_task); @@ -5614,7 +5629,7 @@ dma_error: i += tx_ring->count; i--; buffer_info = &tx_ring->buffer_info[i]; - e1000_put_txbuf(tx_ring, buffer_info); + e1000_put_txbuf(tx_ring, buffer_info, true); } return 0; @@ -7252,10 +7267,8 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_eeprom; } - setup_timer(&adapter->watchdog_timer, e1000_watchdog, - (unsigned long)adapter); - setup_timer(&adapter->phy_info_timer, e1000_update_phy_info, - (unsigned long)adapter); + timer_setup(&adapter->watchdog_timer, e1000_watchdog, 0); + timer_setup(&adapter->phy_info_timer, e1000_update_phy_info, 0); INIT_WORK(&adapter->reset_task, e1000_reset_task); INIT_WORK(&adapter->watchdog_task, e1000_watchdog_task); @@ -7408,7 +7421,7 @@ static void e1000_remove(struct pci_dev *pdev) if (adapter->flags & FLAG_HAS_HW_TIMESTAMP) { cancel_work_sync(&adapter->tx_hwtstamp_work); if (adapter->tx_hwtstamp_skb) { - dev_kfree_skb_any(adapter->tx_hwtstamp_skb); + dev_consume_skb_any(adapter->tx_hwtstamp_skb); adapter->tx_hwtstamp_skb = NULL; } } diff --git a/drivers/net/ethernet/intel/e1000e/param.c b/drivers/net/ethernet/intel/e1000e/param.c index 6d8c39abee16..47da51864543 100644 --- a/drivers/net/ethernet/intel/e1000e/param.c +++ b/drivers/net/ethernet/intel/e1000e/param.c @@ -73,17 +73,25 @@ E1000_PARAM(TxAbsIntDelay, "Transmit Absolute Interrupt Delay"); /* Receive Interrupt Delay in units of 1.024 microseconds * hardware will likely hang if you set this to anything but zero. * + * Burst variant is used as default if device has FLAG2_DMA_BURST. + * * Valid Range: 0-65535 */ E1000_PARAM(RxIntDelay, "Receive Interrupt Delay"); +#define DEFAULT_RDTR 0 +#define BURST_RDTR 0x20 #define MAX_RXDELAY 0xFFFF #define MIN_RXDELAY 0 /* Receive Absolute Interrupt Delay in units of 1.024 microseconds * + * Burst variant is used as default if device has FLAG2_DMA_BURST. + * * Valid Range: 0-65535 */ E1000_PARAM(RxAbsIntDelay, "Receive Absolute Interrupt Delay"); +#define DEFAULT_RADV 8 +#define BURST_RADV 0x20 #define MAX_RXABSDELAY 0xFFFF #define MIN_RXABSDELAY 0 @@ -297,6 +305,9 @@ void e1000e_check_options(struct e1000_adapter *adapter) .max = MAX_RXDELAY } } }; + if (adapter->flags2 & FLAG2_DMA_BURST) + opt.def = BURST_RDTR; + if (num_RxIntDelay > bd) { adapter->rx_int_delay = RxIntDelay[bd]; e1000_validate_option(&adapter->rx_int_delay, &opt, @@ -307,7 +318,7 @@ void e1000e_check_options(struct e1000_adapter *adapter) } /* Receive Absolute Interrupt Delay */ { - static const struct e1000_option opt = { + static struct e1000_option opt = { .type = range_option, .name = "Receive Absolute Interrupt Delay", .err = "using default of " @@ -317,6 +328,9 @@ void e1000e_check_options(struct e1000_adapter *adapter) .max = MAX_RXABSDELAY } } }; + if (adapter->flags2 & FLAG2_DMA_BURST) + opt.def = BURST_RADV; + if (num_RxAbsIntDelay > bd) { adapter->rx_abs_int_delay = RxAbsIntDelay[bd]; e1000_validate_option(&adapter->rx_abs_int_delay, &opt, diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index d78d47b41a71..86ff0969efb6 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -1744,6 +1744,7 @@ s32 e1000e_phy_has_link_generic(struct e1000_hw *hw, u32 iterations, s32 ret_val = 0; u16 i, phy_status; + *success = false; for (i = 0; i < iterations; i++) { /* Some PHYs require the MII_BMSR register to be read * twice due to the link bit being sticky. No harm doing @@ -1763,16 +1764,16 @@ s32 e1000e_phy_has_link_generic(struct e1000_hw *hw, u32 iterations, ret_val = e1e_rphy(hw, MII_BMSR, &phy_status); if (ret_val) break; - if (phy_status & BMSR_LSTATUS) + if (phy_status & BMSR_LSTATUS) { + *success = true; break; + } if (usec_interval >= 1000) msleep(usec_interval / 1000); else udelay(usec_interval); } - *success = (i < iterations); - return ret_val; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 1e9ae3197b17..7f605221a686 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -213,9 +213,10 @@ static void fm10k_start_service_event(struct fm10k_intfc *interface) * fm10k_service_timer - Timer Call-back * @data: pointer to interface cast into an unsigned long **/ -static void fm10k_service_timer(unsigned long data) +static void fm10k_service_timer(struct timer_list *t) { - struct fm10k_intfc *interface = (struct fm10k_intfc *)data; + struct fm10k_intfc *interface = from_timer(interface, t, + service_timer); /* Reset the timer */ mod_timer(&interface->service_timer, (HZ * 2) + jiffies); @@ -2315,8 +2316,7 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Initialize service timer and service task late in order to avoid * cleanup issues. */ - setup_timer(&interface->service_timer, &fm10k_service_timer, - (unsigned long)interface); + timer_setup(&interface->service_timer, fm10k_service_timer, 0); INIT_WORK(&interface->service_task, fm10k_service_task); /* Setup the MAC/VLAN queue */ diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 439c63cb2a0c..eb017763646d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -54,6 +54,7 @@ #include <linux/clocksource.h> #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> +#include <net/pkt_cls.h> #include "i40e_type.h" #include "i40e_prototype.h" #include "i40e_client.h" @@ -87,6 +88,7 @@ #define I40E_AQ_LEN 256 #define I40E_AQ_WORK_LIMIT 66 /* max number of VFs + a little */ #define I40E_MAX_USER_PRIORITY 8 +#define I40E_MAX_QUEUES_PER_CH 64 #define I40E_DEFAULT_TRAFFIC_CLASS BIT(0) #define I40E_DEFAULT_MSG_ENABLE 4 #define I40E_QUEUE_WAIT_RETRY_LIMIT 10 @@ -126,6 +128,11 @@ /* default to trying for four seconds */ #define I40E_TRY_LINK_TIMEOUT (4 * HZ) +/* BW rate limiting */ +#define I40E_BW_CREDIT_DIVISOR 50 /* 50Mbps per BW credit */ +#define I40E_BW_MBPS_DIVISOR 125000 /* rate / (1000000 / 8) Mbps */ +#define I40E_MAX_BW_INACTIVE_ACCUM 4 /* accumulate 4 credits max */ + /* driver state flags */ enum i40e_state_t { __I40E_TESTING, @@ -157,6 +164,8 @@ enum i40e_state_t { __I40E_STATE_SIZE__, }; +#define I40E_PF_RESET_FLAG BIT_ULL(__I40E_PF_RESET_REQUESTED) + /* VSI state flags */ enum i40e_vsi_state_t { __I40E_VSI_DOWN, @@ -338,6 +347,25 @@ struct i40e_flex_pit { u8 pit_index; }; +struct i40e_channel { + struct list_head list; + bool initialized; + u8 type; + u16 vsi_number; /* Assigned VSI number from AQ 'Add VSI' response */ + u16 stat_counter_idx; + u16 base_queue; + u16 num_queue_pairs; /* Requested by user */ + u16 seid; + + u8 enabled_tc; + struct i40e_aqc_vsi_properties_data info; + + u64 max_tx_rate; + + /* track this channel belongs to which VSI */ + struct i40e_vsi *parent_vsi; +}; + /* struct that defines the Ethernet device */ struct i40e_pf { struct pci_dev *pdev; @@ -350,7 +378,7 @@ struct i40e_pf { u16 num_vmdq_vsis; /* num vmdq vsis this PF has set up */ u16 num_vmdq_qps; /* num queue pairs per vmdq pool */ u16 num_vmdq_msix; /* num queue vectors per vmdq pool */ - u16 num_req_vfs; /* num VFs requested for this VF */ + u16 num_req_vfs; /* num VFs requested for this PF */ u16 num_vf_qps; /* num queue pairs per VF */ u16 num_lan_qps; /* num lan queues this PF has set up */ u16 num_lan_msix; /* num queue vectors for the base PF vsi */ @@ -403,55 +431,58 @@ struct i40e_pf { struct timer_list service_timer; struct work_struct service_task; - u64 hw_features; -#define I40E_HW_RSS_AQ_CAPABLE BIT_ULL(0) -#define I40E_HW_128_QP_RSS_CAPABLE BIT_ULL(1) -#define I40E_HW_ATR_EVICT_CAPABLE BIT_ULL(2) -#define I40E_HW_WB_ON_ITR_CAPABLE BIT_ULL(3) -#define I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE BIT_ULL(4) -#define I40E_HW_NO_PCI_LINK_CHECK BIT_ULL(5) -#define I40E_HW_100M_SGMII_CAPABLE BIT_ULL(6) -#define I40E_HW_NO_DCB_SUPPORT BIT_ULL(7) -#define I40E_HW_USE_SET_LLDP_MIB BIT_ULL(8) -#define I40E_HW_GENEVE_OFFLOAD_CAPABLE BIT_ULL(9) -#define I40E_HW_PTP_L4_CAPABLE BIT_ULL(10) -#define I40E_HW_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(11) -#define I40E_HW_MPLS_HDR_OFFLOAD_CAPABLE BIT_ULL(12) -#define I40E_HW_HAVE_CRT_RETIMER BIT_ULL(13) -#define I40E_HW_OUTER_UDP_CSUM_CAPABLE BIT_ULL(14) -#define I40E_HW_PHY_CONTROLS_LEDS BIT_ULL(15) -#define I40E_HW_STOP_FW_LLDP BIT_ULL(16) -#define I40E_HW_PORT_ID_VALID BIT_ULL(17) -#define I40E_HW_RESTART_AUTONEG BIT_ULL(18) - - u64 flags; -#define I40E_FLAG_RX_CSUM_ENABLED BIT_ULL(1) -#define I40E_FLAG_MSI_ENABLED BIT_ULL(2) -#define I40E_FLAG_MSIX_ENABLED BIT_ULL(3) -#define I40E_FLAG_HW_ATR_EVICT_ENABLED BIT_ULL(4) -#define I40E_FLAG_RSS_ENABLED BIT_ULL(6) -#define I40E_FLAG_VMDQ_ENABLED BIT_ULL(7) -#define I40E_FLAG_IWARP_ENABLED BIT_ULL(10) -#define I40E_FLAG_FILTER_SYNC BIT_ULL(15) -#define I40E_FLAG_SERVICE_CLIENT_REQUESTED BIT_ULL(16) -#define I40E_FLAG_SRIOV_ENABLED BIT_ULL(19) -#define I40E_FLAG_DCB_ENABLED BIT_ULL(20) -#define I40E_FLAG_FD_SB_ENABLED BIT_ULL(21) -#define I40E_FLAG_FD_ATR_ENABLED BIT_ULL(22) -#define I40E_FLAG_FD_SB_AUTO_DISABLED BIT_ULL(23) -#define I40E_FLAG_FD_ATR_AUTO_DISABLED BIT_ULL(24) -#define I40E_FLAG_PTP BIT_ULL(25) -#define I40E_FLAG_MFP_ENABLED BIT_ULL(26) -#define I40E_FLAG_UDP_FILTER_SYNC BIT_ULL(27) -#define I40E_FLAG_DCB_CAPABLE BIT_ULL(29) -#define I40E_FLAG_VEB_STATS_ENABLED BIT_ULL(37) -#define I40E_FLAG_LINK_POLLING_ENABLED BIT_ULL(39) -#define I40E_FLAG_VEB_MODE_ENABLED BIT_ULL(40) -#define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT_ULL(51) -#define I40E_FLAG_CLIENT_RESET BIT_ULL(54) -#define I40E_FLAG_TEMP_LINK_POLLING BIT_ULL(55) -#define I40E_FLAG_CLIENT_L2_CHANGE BIT_ULL(56) -#define I40E_FLAG_LEGACY_RX BIT_ULL(58) + u32 hw_features; +#define I40E_HW_RSS_AQ_CAPABLE BIT(0) +#define I40E_HW_128_QP_RSS_CAPABLE BIT(1) +#define I40E_HW_ATR_EVICT_CAPABLE BIT(2) +#define I40E_HW_WB_ON_ITR_CAPABLE BIT(3) +#define I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE BIT(4) +#define I40E_HW_NO_PCI_LINK_CHECK BIT(5) +#define I40E_HW_100M_SGMII_CAPABLE BIT(6) +#define I40E_HW_NO_DCB_SUPPORT BIT(7) +#define I40E_HW_USE_SET_LLDP_MIB BIT(8) +#define I40E_HW_GENEVE_OFFLOAD_CAPABLE BIT(9) +#define I40E_HW_PTP_L4_CAPABLE BIT(10) +#define I40E_HW_WOL_MC_MAGIC_PKT_WAKE BIT(11) +#define I40E_HW_MPLS_HDR_OFFLOAD_CAPABLE BIT(12) +#define I40E_HW_HAVE_CRT_RETIMER BIT(13) +#define I40E_HW_OUTER_UDP_CSUM_CAPABLE BIT(14) +#define I40E_HW_PHY_CONTROLS_LEDS BIT(15) +#define I40E_HW_STOP_FW_LLDP BIT(16) +#define I40E_HW_PORT_ID_VALID BIT(17) +#define I40E_HW_RESTART_AUTONEG BIT(18) + + u32 flags; +#define I40E_FLAG_RX_CSUM_ENABLED BIT(0) +#define I40E_FLAG_MSI_ENABLED BIT(1) +#define I40E_FLAG_MSIX_ENABLED BIT(2) +#define I40E_FLAG_RSS_ENABLED BIT(3) +#define I40E_FLAG_VMDQ_ENABLED BIT(4) +#define I40E_FLAG_FILTER_SYNC BIT(5) +#define I40E_FLAG_SRIOV_ENABLED BIT(6) +#define I40E_FLAG_DCB_CAPABLE BIT(7) +#define I40E_FLAG_DCB_ENABLED BIT(8) +#define I40E_FLAG_FD_SB_ENABLED BIT(9) +#define I40E_FLAG_FD_ATR_ENABLED BIT(10) +#define I40E_FLAG_FD_SB_AUTO_DISABLED BIT(11) +#define I40E_FLAG_FD_ATR_AUTO_DISABLED BIT(12) +#define I40E_FLAG_MFP_ENABLED BIT(13) +#define I40E_FLAG_UDP_FILTER_SYNC BIT(14) +#define I40E_FLAG_HW_ATR_EVICT_ENABLED BIT(15) +#define I40E_FLAG_VEB_MODE_ENABLED BIT(16) +#define I40E_FLAG_VEB_STATS_ENABLED BIT(17) +#define I40E_FLAG_LINK_POLLING_ENABLED BIT(18) +#define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT(19) +#define I40E_FLAG_TEMP_LINK_POLLING BIT(20) +#define I40E_FLAG_LEGACY_RX BIT(21) +#define I40E_FLAG_PTP BIT(22) +#define I40E_FLAG_IWARP_ENABLED BIT(23) +#define I40E_FLAG_SERVICE_CLIENT_REQUESTED BIT(24) +#define I40E_FLAG_CLIENT_L2_CHANGE BIT(25) +#define I40E_FLAG_CLIENT_RESET BIT(26) +#define I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED BIT(27) +#define I40E_FLAG_SOURCE_PRUNING_DISABLED BIT(28) +#define I40E_FLAG_TC_MQPRIO BIT(29) struct i40e_client_instance *cinst; bool stat_offsets_loaded; @@ -532,6 +563,8 @@ struct i40e_pf { u32 ioremap_len; u32 fd_inv; u16 phy_led_val; + + u16 override_q_count; }; /** @@ -675,6 +708,7 @@ struct i40e_vsi { enum i40e_vsi_type type; /* VSI type, e.g., LAN, FCoE, etc */ s16 vf_id; /* Virtual function ID for SRIOV VSIs */ + struct tc_mqprio_qopt_offload mqprio_qopt; /* queue parameters */ struct i40e_tc_configuration tc_config; struct i40e_aqc_vsi_properties_data info; @@ -696,6 +730,16 @@ struct i40e_vsi { bool current_isup; /* Sync 'link up' logging */ enum i40e_aq_link_speed current_speed; /* Sync link speed logging */ + /* channel specific fields */ + u16 cnt_q_avail; /* num of queues available for channel usage */ + u16 orig_rss_size; + u16 current_rss_size; + bool reconfig_rss; + + u16 next_base_queue; /* next queue to be used for channel setup */ + + struct list_head ch_list; + void *priv; /* client driver data reference. */ /* VSI specific handlers */ @@ -947,9 +991,6 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector) struct i40e_hw *hw = &pf->hw; u32 val; - /* definitely clear the PBA here, as this function is meant to - * clean out all previous interrupts AND enable the interrupt - */ val = I40E_PFINT_DYN_CTLN_INTENA_MASK | I40E_PFINT_DYN_CTLN_CLEARPBA_MASK | (I40E_ITR_NONE << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT); @@ -958,7 +999,7 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector) } void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf); -void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba); +void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf); int i40e_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd); int i40e_open(struct net_device *netdev); int i40e_close(struct net_device *netdev); @@ -1003,4 +1044,7 @@ static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi) { return !!vsi->xdp_prog; } + +int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch); +int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate); #endif /* _I40E_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 4c85ea9cd89a..6a5db1b33fa2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -1771,9 +1771,12 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_25GBASE_CR = 0x20, I40E_PHY_TYPE_25GBASE_SR = 0x21, I40E_PHY_TYPE_25GBASE_LR = 0x22, + I40E_PHY_TYPE_25GBASE_AOC = 0x23, + I40E_PHY_TYPE_25GBASE_ACC = 0x24, + I40E_PHY_TYPE_MAX, + I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD, I40E_PHY_TYPE_EMPTY = 0xFE, I40E_PHY_TYPE_DEFAULT = 0xFF, - I40E_PHY_TYPE_MAX }; #define I40E_LINK_SPEED_100MB_SHIFT 0x1 @@ -1830,6 +1833,8 @@ struct i40e_aq_get_phy_abilities_resp { #define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02 #define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04 #define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08 +#define I40E_AQ_PHY_TYPE_EXT_25G_AOC 0x10 +#define I40E_AQ_PHY_TYPE_EXT_25G_ACC 0x20 u8 fec_cfg_curr_mod_ext_info; #define I40E_AQ_ENABLE_FEC_KR 0x01 #define I40E_AQ_ENABLE_FEC_RS 0x02 diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 60542beda7ad..8d0ee006606b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1180,6 +1180,8 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw) case I40E_PHY_TYPE_40GBASE_AOC: case I40E_PHY_TYPE_10GBASE_AOC: case I40E_PHY_TYPE_25GBASE_CR: + case I40E_PHY_TYPE_25GBASE_AOC: + case I40E_PHY_TYPE_25GBASE_ACC: media = I40E_MEDIA_TYPE_DA; break; case I40E_PHY_TYPE_1000BASE_KX: @@ -1567,36 +1569,57 @@ i40e_status i40e_aq_get_phy_capabilities(struct i40e_hw *hw, struct i40e_aq_desc desc; i40e_status status; u16 abilities_size = sizeof(struct i40e_aq_get_phy_abilities_resp); + u16 max_delay = I40E_MAX_PHY_TIMEOUT, total_delay = 0; if (!abilities) return I40E_ERR_PARAM; - i40e_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_get_phy_abilities); + do { + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_phy_abilities); - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); - if (abilities_size > I40E_AQ_LARGE_BUF) - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); + if (abilities_size > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - if (qualified_modules) - desc.params.external.param0 |= + if (qualified_modules) + desc.params.external.param0 |= cpu_to_le32(I40E_AQ_PHY_REPORT_QUALIFIED_MODULES); - if (report_init) - desc.params.external.param0 |= + if (report_init) + desc.params.external.param0 |= cpu_to_le32(I40E_AQ_PHY_REPORT_INITIAL_VALUES); - status = i40e_asq_send_command(hw, &desc, abilities, abilities_size, - cmd_details); + status = i40e_asq_send_command(hw, &desc, abilities, + abilities_size, cmd_details); - if (hw->aq.asq_last_status == I40E_AQ_RC_EIO) - status = I40E_ERR_UNKNOWN_PHY; + if (status) + break; + + if (hw->aq.asq_last_status == I40E_AQ_RC_EIO) { + status = I40E_ERR_UNKNOWN_PHY; + break; + } else if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN) { + usleep_range(1000, 2000); + total_delay++; + status = I40E_ERR_TIMEOUT; + } + } while ((hw->aq.asq_last_status != I40E_AQ_RC_OK) && + (total_delay < max_delay)); + + if (status) + return status; if (report_init) { if (hw->mac.type == I40E_MAC_XL710 && hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && - hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) + hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) { status = i40e_aq_get_link_info(hw, true, NULL, NULL); + } else { + hw->phy.phy_types = le32_to_cpu(abilities->phy_type); + hw->phy.phy_types |= + ((u64)abilities->phy_type_ext << 32); + } } return status; diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 8f326f87a815..2b8bbc84e34f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -278,8 +278,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) rx_ring->netdev, rx_ring->rx_bi); dev_info(&pf->pdev->dev, - " rx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n", - i, rx_ring->state, + " rx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n", + i, *rx_ring->state, rx_ring->queue_index, rx_ring->reg_idx); dev_info(&pf->pdev->dev, @@ -334,8 +334,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) tx_ring->netdev, tx_ring->tx_bi); dev_info(&pf->pdev->dev, - " tx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n", - i, tx_ring->state, + " tx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n", + i, *tx_ring->state, tx_ring->queue_index, tx_ring->reg_idx); dev_info(&pf->pdev->dev, @@ -798,8 +798,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, */ if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; - i40e_do_reset_safe(pf, - BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } vsi = i40e_vsi_setup(pf, I40E_VSI_VMDQ2, vsi_seid, 0); diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.c b/drivers/net/ethernet/intel/i40e/i40e_diag.c index f141e78d409e..76ed56641864 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.c +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.c @@ -36,7 +36,9 @@ static i40e_status i40e_diag_reg_pattern_test(struct i40e_hw *hw, u32 reg, u32 mask) { - const u32 patterns[] = {0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF}; + static const u32 patterns[] = { + 0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF + }; u32 pat, val, orig_val; int i; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 1136d02e2e95..9eb618799a30 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -227,6 +227,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = { I40E_PRIV_FLAG("veb-stats", I40E_FLAG_VEB_STATS_ENABLED, 0), I40E_PRIV_FLAG("hw-atr-eviction", I40E_FLAG_HW_ATR_EVICT_ENABLED, 0), I40E_PRIV_FLAG("legacy-rx", I40E_FLAG_LEGACY_RX, 0), + I40E_PRIV_FLAG("disable-source-pruning", + I40E_FLAG_SOURCE_PRUNING_DISABLED, 0), }; #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags) @@ -251,428 +253,557 @@ static void i40e_partition_setting_complaint(struct i40e_pf *pf) /** * i40e_phy_type_to_ethtool - convert the phy_types to ethtool link modes - * @phy_types: PHY types to convert - * @supported: pointer to the ethtool supported variable to fill in - * @advertising: pointer to the ethtool advertising variable to fill in + * @pf: PF struct with phy_types + * @ks: ethtool link ksettings struct to fill out * **/ -static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, - u32 *advertising) +static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, + struct ethtool_link_ksettings *ks) { struct i40e_link_status *hw_link_info = &pf->hw.phy.link_info; u64 phy_types = pf->hw.phy.phy_types; - *supported = 0x0; - *advertising = 0x0; + ethtool_link_ksettings_zero_link_mode(ks, supported); + ethtool_link_ksettings_zero_link_mode(ks, advertising); if (phy_types & I40E_CAP_PHY_TYPE_SGMII) { - *supported |= SUPPORTED_Autoneg | - SUPPORTED_1000baseT_Full; - *advertising |= ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - *advertising |= ADVERTISED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); if (pf->hw_features & I40E_HW_100M_SGMII_CAPABLE) { - *supported |= SUPPORTED_100baseT_Full; - *advertising |= ADVERTISED_100baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 100baseT_Full); } } if (phy_types & I40E_CAP_PHY_TYPE_XAUI || phy_types & I40E_CAP_PHY_TYPE_XFI || phy_types & I40E_CAP_PHY_TYPE_SFI || phy_types & I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU || - phy_types & I40E_CAP_PHY_TYPE_10GBASE_AOC) - *supported |= SUPPORTED_10000baseT_Full; - if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU || - phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 || - phy_types & I40E_CAP_PHY_TYPE_10GBASE_T || - phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR || - phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR) { - *supported |= SUPPORTED_Autoneg | - SUPPORTED_10000baseT_Full; - *advertising |= ADVERTISED_Autoneg; + phy_types & I40E_CAP_PHY_TYPE_10GBASE_AOC) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - *advertising |= ADVERTISED_10000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); + } + if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_T) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); } if (phy_types & I40E_CAP_PHY_TYPE_XLAUI || phy_types & I40E_CAP_PHY_TYPE_XLPPI || phy_types & I40E_CAP_PHY_TYPE_40GBASE_AOC) - *supported |= SUPPORTED_40000baseCR4_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4_CU || phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4) { - *supported |= SUPPORTED_Autoneg | - SUPPORTED_40000baseCR4_Full; - *advertising |= ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_40GB) - *advertising |= ADVERTISED_40000baseCR4_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseCR4_Full); } if (phy_types & I40E_CAP_PHY_TYPE_100BASE_TX) { - *supported |= SUPPORTED_Autoneg | - SUPPORTED_100baseT_Full; - *advertising |= ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) - *advertising |= ADVERTISED_100baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 100baseT_Full); } - if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_T || - phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX || - phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX || - phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL) { - *supported |= SUPPORTED_Autoneg | - SUPPORTED_1000baseT_Full; - *advertising |= ADVERTISED_Autoneg; + if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_T) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - *advertising |= ADVERTISED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); } if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_SR4) - *supported |= SUPPORTED_40000baseSR4_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseSR4_Full); if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_LR4) - *supported |= SUPPORTED_40000baseLR4_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseLR4_Full); if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_KR4) { - *supported |= SUPPORTED_40000baseKR4_Full | - SUPPORTED_Autoneg; - *advertising |= ADVERTISED_40000baseKR4_Full | - ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseLR4_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseLR4_Full); } if (phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2) { - *supported |= SUPPORTED_20000baseKR2_Full | - SUPPORTED_Autoneg; - *advertising |= ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, + 20000baseKR2_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_20GB) - *advertising |= ADVERTISED_20000baseKR2_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 20000baseKR2_Full); } - if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR) { - if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) - *supported |= SUPPORTED_10000baseKR_Full | - SUPPORTED_Autoneg; - *advertising |= ADVERTISED_Autoneg; + if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseKX4_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) - *advertising |= ADVERTISED_10000baseKR_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseKX4_Full); } - if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4) { - *supported |= SUPPORTED_10000baseKX4_Full | - SUPPORTED_Autoneg; - *advertising |= ADVERTISED_Autoneg; + if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR && + !(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseKR_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - *advertising |= ADVERTISED_10000baseKX4_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseKR_Full); } - if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX) { - if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) - *supported |= SUPPORTED_1000baseKX_Full | - SUPPORTED_Autoneg; - *advertising |= ADVERTISED_Autoneg; + if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX && + !(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseKX_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) - *advertising |= ADVERTISED_1000baseKX_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseKX_Full); } - if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR || - phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR || - phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR || + /* need to add 25G PHY types */ + if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseKR_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseKR_Full); + } + if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseCR_Full); + } + if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR || phy_types & I40E_CAP_PHY_TYPE_25GBASE_LR) { - *supported |= SUPPORTED_Autoneg; - *advertising |= ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseSR_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseSR_Full); + } + if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_AOC || + phy_types & I40E_CAP_PHY_TYPE_25GBASE_ACC) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseCR_Full); + } + /* need to add new 10G PHY types */ + if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseCR_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseCR_Full); + } + if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseSR_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseSR_Full); + } + if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseLR_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseLR_Full); + } + if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseX_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseX_Full); + } + /* Autoneg PHY types */ + if (phy_types & I40E_CAP_PHY_TYPE_SGMII || + phy_types & I40E_CAP_PHY_TYPE_40GBASE_KR4 || + phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4_CU || + phy_types & I40E_CAP_PHY_TYPE_40GBASE_CR4 || + phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR || + phy_types & I40E_CAP_PHY_TYPE_25GBASE_LR || + phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR || + phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR || + phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2 || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_T || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4 || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU || + phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_T || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_LX || + phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX || + phy_types & I40E_CAP_PHY_TYPE_100BASE_TX) { + ethtool_link_ksettings_add_link_mode(ks, supported, + Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + Autoneg); } } /** * i40e_get_settings_link_up - Get the Link settings for when link is up * @hw: hw structure - * @ecmd: ethtool command to fill in + * @ks: ethtool ksettings to fill in * @netdev: network interface device structure - * + * @pf: pointer to physical function struct **/ static void i40e_get_settings_link_up(struct i40e_hw *hw, - struct ethtool_link_ksettings *cmd, + struct ethtool_link_ksettings *ks, struct net_device *netdev, struct i40e_pf *pf) { struct i40e_link_status *hw_link_info = &hw->phy.link_info; + struct ethtool_link_ksettings cap_ksettings; u32 link_speed = hw_link_info->link_speed; - u32 e_advertising = 0x0; - u32 e_supported = 0x0; - u32 supported, advertising; - - ethtool_convert_link_mode_to_legacy_u32(&supported, - cmd->link_modes.supported); - ethtool_convert_link_mode_to_legacy_u32(&advertising, - cmd->link_modes.advertising); /* Initialize supported and advertised settings based on phy settings */ switch (hw_link_info->phy_type) { case I40E_PHY_TYPE_40GBASE_CR4: case I40E_PHY_TYPE_40GBASE_CR4_CU: - supported = SUPPORTED_Autoneg | - SUPPORTED_40000baseCR4_Full; - advertising = ADVERTISED_Autoneg | - ADVERTISED_40000baseCR4_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseCR4_Full); break; case I40E_PHY_TYPE_XLAUI: case I40E_PHY_TYPE_XLPPI: case I40E_PHY_TYPE_40GBASE_AOC: - supported = SUPPORTED_40000baseCR4_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); break; case I40E_PHY_TYPE_40GBASE_SR4: - supported = SUPPORTED_40000baseSR4_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseSR4_Full); break; case I40E_PHY_TYPE_40GBASE_LR4: - supported = SUPPORTED_40000baseLR4_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseLR4_Full); break; + case I40E_PHY_TYPE_25GBASE_SR: + case I40E_PHY_TYPE_25GBASE_LR: case I40E_PHY_TYPE_10GBASE_SR: case I40E_PHY_TYPE_10GBASE_LR: case I40E_PHY_TYPE_1000BASE_SX: case I40E_PHY_TYPE_1000BASE_LX: - supported = SUPPORTED_10000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseSR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseSR_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseSR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseSR_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseLR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseLR_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseX_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseX_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); if (hw_link_info->module_type[2] & I40E_MODULE_TYPE_1000BASE_SX || hw_link_info->module_type[2] & I40E_MODULE_TYPE_1000BASE_LX) { - supported |= SUPPORTED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - advertising |= ADVERTISED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode( + ks, advertising, 1000baseT_Full); } if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - advertising |= ADVERTISED_10000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); break; case I40E_PHY_TYPE_10GBASE_T: case I40E_PHY_TYPE_1000BASE_T: case I40E_PHY_TYPE_100BASE_TX: - supported = SUPPORTED_Autoneg | - SUPPORTED_10000baseT_Full | - SUPPORTED_1000baseT_Full | - SUPPORTED_100baseT_Full; - advertising = ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - advertising |= ADVERTISED_10000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - advertising |= ADVERTISED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) - advertising |= ADVERTISED_100baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 100baseT_Full); break; case I40E_PHY_TYPE_1000BASE_T_OPTICAL: - supported = SUPPORTED_Autoneg | - SUPPORTED_1000baseT_Full; - advertising = ADVERTISED_Autoneg | - ADVERTISED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); break; case I40E_PHY_TYPE_10GBASE_CR1_CU: case I40E_PHY_TYPE_10GBASE_CR1: - supported = SUPPORTED_Autoneg | - SUPPORTED_10000baseT_Full; - advertising = ADVERTISED_Autoneg | - ADVERTISED_10000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); break; case I40E_PHY_TYPE_XAUI: case I40E_PHY_TYPE_XFI: case I40E_PHY_TYPE_SFI: case I40E_PHY_TYPE_10GBASE_SFPP_CU: case I40E_PHY_TYPE_10GBASE_AOC: - supported = SUPPORTED_10000baseT_Full; - advertising = SUPPORTED_10000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); break; case I40E_PHY_TYPE_SGMII: - supported = SUPPORTED_Autoneg | - SUPPORTED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - advertising |= ADVERTISED_1000baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); if (pf->hw_features & I40E_HW_100M_SGMII_CAPABLE) { - supported |= SUPPORTED_100baseT_Full; + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) - advertising |= ADVERTISED_100baseT_Full; + ethtool_link_ksettings_add_link_mode( + ks, advertising, 100baseT_Full); } break; case I40E_PHY_TYPE_40GBASE_KR4: + case I40E_PHY_TYPE_25GBASE_KR: case I40E_PHY_TYPE_20GBASE_KR2: case I40E_PHY_TYPE_10GBASE_KR: case I40E_PHY_TYPE_10GBASE_KX4: case I40E_PHY_TYPE_1000BASE_KX: - supported |= SUPPORTED_40000baseKR4_Full | - SUPPORTED_20000baseKR2_Full | - SUPPORTED_10000baseKR_Full | - SUPPORTED_10000baseKX4_Full | - SUPPORTED_1000baseKX_Full | - SUPPORTED_Autoneg; - advertising |= ADVERTISED_40000baseKR4_Full | - ADVERTISED_20000baseKR2_Full | - ADVERTISED_10000baseKR_Full | - ADVERTISED_10000baseKX4_Full | - ADVERTISED_1000baseKX_Full | - ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseKR4_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseKR_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 20000baseKR2_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseKR_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseKX4_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseKX_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseKR4_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseKR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 20000baseKR2_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseKR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseKX4_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseKX_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); break; - case I40E_PHY_TYPE_25GBASE_KR: case I40E_PHY_TYPE_25GBASE_CR: - case I40E_PHY_TYPE_25GBASE_SR: - case I40E_PHY_TYPE_25GBASE_LR: - supported = SUPPORTED_Autoneg; - advertising = ADVERTISED_Autoneg; - /* TODO: add speeds when ethtool is ready to support*/ + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseCR_Full); + break; + case I40E_PHY_TYPE_25GBASE_AOC: + case I40E_PHY_TYPE_25GBASE_ACC: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseCR_Full); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseCR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseCR_Full); break; default: /* if we got here and link is up something bad is afoot */ - netdev_info(netdev, "WARNING: Link is up but PHY type 0x%x is not recognized.\n", + netdev_info(netdev, + "WARNING: Link is up but PHY type 0x%x is not recognized.\n", hw_link_info->phy_type); } /* Now that we've worked out everything that could be supported by the - * current PHY type, get what is supported by the NVM and them to - * get what is truly supported + * current PHY type, get what is supported by the NVM and intersect + * them to get what is truly supported */ - i40e_phy_type_to_ethtool(pf, &e_supported, - &e_advertising); - - supported = supported & e_supported; - advertising = advertising & e_advertising; + memset(&cap_ksettings, 0, sizeof(struct ethtool_link_ksettings)); + i40e_phy_type_to_ethtool(pf, &cap_ksettings); + ethtool_intersect_link_masks(ks, &cap_ksettings); /* Set speed and duplex */ switch (link_speed) { case I40E_LINK_SPEED_40GB: - cmd->base.speed = SPEED_40000; + ks->base.speed = SPEED_40000; break; case I40E_LINK_SPEED_25GB: -#ifdef SPEED_25000 - cmd->base.speed = SPEED_25000; -#else - netdev_info(netdev, - "Speed is 25G, display not supported by this version of ethtool.\n"); -#endif + ks->base.speed = SPEED_25000; break; case I40E_LINK_SPEED_20GB: - cmd->base.speed = SPEED_20000; + ks->base.speed = SPEED_20000; break; case I40E_LINK_SPEED_10GB: - cmd->base.speed = SPEED_10000; + ks->base.speed = SPEED_10000; break; case I40E_LINK_SPEED_1GB: - cmd->base.speed = SPEED_1000; + ks->base.speed = SPEED_1000; break; case I40E_LINK_SPEED_100MB: - cmd->base.speed = SPEED_100; + ks->base.speed = SPEED_100; break; default: break; } - cmd->base.duplex = DUPLEX_FULL; - - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, - supported); - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, - advertising); + ks->base.duplex = DUPLEX_FULL; } /** * i40e_get_settings_link_down - Get the Link settings for when link is down * @hw: hw structure - * @ecmd: ethtool command to fill in + * @ks: ethtool ksettings to fill in + * @pf: pointer to physical function struct * * Reports link settings that can be determined when link is down **/ static void i40e_get_settings_link_down(struct i40e_hw *hw, - struct ethtool_link_ksettings *cmd, + struct ethtool_link_ksettings *ks, struct i40e_pf *pf) { - u32 supported, advertising; - /* link is down and the driver needs to fall back on * supported phy types to figure out what info to display */ - i40e_phy_type_to_ethtool(pf, &supported, &advertising); - - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, - supported); - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, - advertising); + i40e_phy_type_to_ethtool(pf, ks); /* With no link speed and duplex are unknown */ - cmd->base.speed = SPEED_UNKNOWN; - cmd->base.duplex = DUPLEX_UNKNOWN; + ks->base.speed = SPEED_UNKNOWN; + ks->base.duplex = DUPLEX_UNKNOWN; } /** - * i40e_get_settings - Get Link Speed and Duplex settings + * i40e_get_link_ksettings - Get Link Speed and Duplex settings * @netdev: network interface device structure - * @ecmd: ethtool command + * @ks: ethtool ksettings * * Reports speed/duplex settings based on media_type **/ static int i40e_get_link_ksettings(struct net_device *netdev, - struct ethtool_link_ksettings *cmd) + struct ethtool_link_ksettings *ks) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_pf *pf = np->vsi->back; struct i40e_hw *hw = &pf->hw; struct i40e_link_status *hw_link_info = &hw->phy.link_info; bool link_up = hw_link_info->link_info & I40E_AQ_LINK_UP; - u32 advertising; + + ethtool_link_ksettings_zero_link_mode(ks, supported); + ethtool_link_ksettings_zero_link_mode(ks, advertising); if (link_up) - i40e_get_settings_link_up(hw, cmd, netdev, pf); + i40e_get_settings_link_up(hw, ks, netdev, pf); else - i40e_get_settings_link_down(hw, cmd, pf); + i40e_get_settings_link_down(hw, ks, pf); /* Now set the settings that don't rely on link being up/down */ /* Set autoneg settings */ - cmd->base.autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ? - AUTONEG_ENABLE : AUTONEG_DISABLE); + ks->base.autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ? + AUTONEG_ENABLE : AUTONEG_DISABLE); + /* Set media type settings */ switch (hw->phy.media_type) { case I40E_MEDIA_TYPE_BACKPLANE: - ethtool_link_ksettings_add_link_mode(cmd, supported, - Autoneg); - ethtool_link_ksettings_add_link_mode(cmd, supported, - Backplane); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - Autoneg); - ethtool_link_ksettings_add_link_mode(cmd, advertising, + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, Backplane); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, Backplane); - cmd->base.port = PORT_NONE; + ks->base.port = PORT_NONE; break; case I40E_MEDIA_TYPE_BASET: - ethtool_link_ksettings_add_link_mode(cmd, supported, TP); - ethtool_link_ksettings_add_link_mode(cmd, advertising, TP); - cmd->base.port = PORT_TP; + ethtool_link_ksettings_add_link_mode(ks, supported, TP); + ethtool_link_ksettings_add_link_mode(ks, advertising, TP); + ks->base.port = PORT_TP; break; case I40E_MEDIA_TYPE_DA: case I40E_MEDIA_TYPE_CX4: - ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); - ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE); - cmd->base.port = PORT_DA; + ethtool_link_ksettings_add_link_mode(ks, supported, FIBRE); + ethtool_link_ksettings_add_link_mode(ks, advertising, FIBRE); + ks->base.port = PORT_DA; break; case I40E_MEDIA_TYPE_FIBER: - ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); - cmd->base.port = PORT_FIBRE; + ethtool_link_ksettings_add_link_mode(ks, supported, FIBRE); + ks->base.port = PORT_FIBRE; break; case I40E_MEDIA_TYPE_UNKNOWN: default: - cmd->base.port = PORT_OTHER; + ks->base.port = PORT_OTHER; break; } /* Set flow control settings */ - ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); + ethtool_link_ksettings_add_link_mode(ks, supported, Pause); switch (hw->fc.requested_mode) { case I40E_FC_FULL: - ethtool_link_ksettings_add_link_mode(cmd, advertising, - Pause); + ethtool_link_ksettings_add_link_mode(ks, advertising, Pause); break; case I40E_FC_TX_PAUSE: - ethtool_link_ksettings_add_link_mode(cmd, advertising, + ethtool_link_ksettings_add_link_mode(ks, advertising, Asym_Pause); break; case I40E_FC_RX_PAUSE: - ethtool_link_ksettings_add_link_mode(cmd, advertising, - Pause); - ethtool_link_ksettings_add_link_mode(cmd, advertising, + ethtool_link_ksettings_add_link_mode(ks, advertising, Pause); + ethtool_link_ksettings_add_link_mode(ks, advertising, Asym_Pause); break; default: - ethtool_convert_link_mode_to_legacy_u32( - &advertising, cmd->link_modes.advertising); - - advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); - - ethtool_convert_legacy_u32_to_link_mode( - cmd->link_modes.advertising, advertising); + ethtool_link_ksettings_del_link_mode(ks, advertising, Pause); + ethtool_link_ksettings_del_link_mode(ks, advertising, + Asym_Pause); break; } @@ -680,30 +811,28 @@ static int i40e_get_link_ksettings(struct net_device *netdev, } /** - * i40e_set_settings - Set Speed and Duplex + * i40e_set_link_ksettings - Set Speed and Duplex * @netdev: network interface device structure - * @ecmd: ethtool command + * @ks: ethtool ksettings * * Set speed/duplex per media_types advertised/forced **/ static int i40e_set_link_ksettings(struct net_device *netdev, - const struct ethtool_link_ksettings *cmd) + const struct ethtool_link_ksettings *ks) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_aq_get_phy_abilities_resp abilities; + struct ethtool_link_ksettings safe_ks; + struct ethtool_link_ksettings copy_ks; struct i40e_aq_set_phy_config config; struct i40e_pf *pf = np->vsi->back; struct i40e_vsi *vsi = np->vsi; struct i40e_hw *hw = &pf->hw; - struct ethtool_link_ksettings safe_cmd; - struct ethtool_link_ksettings copy_cmd; + bool autoneg_changed = false; i40e_status status = 0; - bool change = false; int timeout = 50; int err = 0; - u32 autoneg; - u32 advertise; - u32 tmp; + u8 autoneg; /* Changing port settings is not supported if this isn't the * port's controlling PF @@ -712,17 +841,14 @@ static int i40e_set_link_ksettings(struct net_device *netdev, i40e_partition_setting_complaint(pf); return -EOPNOTSUPP; } - if (vsi != pf->vsi[pf->lan_vsi]) return -EOPNOTSUPP; - if (hw->phy.media_type != I40E_MEDIA_TYPE_BASET && hw->phy.media_type != I40E_MEDIA_TYPE_FIBER && hw->phy.media_type != I40E_MEDIA_TYPE_BACKPLANE && hw->phy.media_type != I40E_MEDIA_TYPE_DA && hw->phy.link_info.link_info & I40E_AQ_LINK_UP) return -EOPNOTSUPP; - if (hw->device_id == I40E_DEV_ID_KX_B || hw->device_id == I40E_DEV_ID_KX_C || hw->device_id == I40E_DEV_ID_20G_KR2 || @@ -731,31 +857,37 @@ static int i40e_set_link_ksettings(struct net_device *netdev, return -EOPNOTSUPP; } - /* copy the cmd to copy_cmd to avoid modifying the origin */ - memcpy(©_cmd, cmd, sizeof(struct ethtool_link_ksettings)); + /* copy the ksettings to copy_ks to avoid modifying the origin */ + memcpy(©_ks, ks, sizeof(struct ethtool_link_ksettings)); - /* get our own copy of the bits to check against */ - memset(&safe_cmd, 0, sizeof(struct ethtool_link_ksettings)); - i40e_get_link_ksettings(netdev, &safe_cmd); + /* save autoneg out of ksettings */ + autoneg = copy_ks.base.autoneg; - /* save autoneg and speed out of cmd */ - autoneg = cmd->base.autoneg; - ethtool_convert_link_mode_to_legacy_u32(&advertise, - cmd->link_modes.advertising); + memset(&safe_ks, 0, sizeof(safe_ks)); + /* Get link modes supported by hardware and check against modes + * requested by the user. Return an error if unsupported mode was set. + */ + i40e_phy_type_to_ethtool(pf, &safe_ks); + if (!bitmap_subset(copy_ks.link_modes.advertising, + safe_ks.link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS)) + return -EINVAL; - /* set autoneg and speed back to what they currently are */ - copy_cmd.base.autoneg = safe_cmd.base.autoneg; - ethtool_convert_link_mode_to_legacy_u32( - &tmp, safe_cmd.link_modes.advertising); - ethtool_convert_legacy_u32_to_link_mode( - copy_cmd.link_modes.advertising, tmp); + /* get our own copy of the bits to check against */ + memset(&safe_ks, 0, sizeof(struct ethtool_link_ksettings)); + safe_ks.base.cmd = copy_ks.base.cmd; + safe_ks.base.link_mode_masks_nwords = + copy_ks.base.link_mode_masks_nwords; + i40e_get_link_ksettings(netdev, &safe_ks); - copy_cmd.base.cmd = safe_cmd.base.cmd; + /* set autoneg back to what it currently is */ + copy_ks.base.autoneg = safe_ks.base.autoneg; - /* If copy_cmd and safe_cmd are not the same now, then they are - * trying to set something that we do not support + /* If copy_ks.base and safe_ks.base are not the same now, then they are + * trying to set something that we do not support. */ - if (memcmp(©_cmd, &safe_cmd, sizeof(struct ethtool_link_ksettings))) + if (memcmp(©_ks.base, &safe_ks.base, + sizeof(struct ethtool_link_settings))) return -EOPNOTSUPP; while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) { @@ -784,8 +916,9 @@ static int i40e_set_link_ksettings(struct net_device *netdev, /* If autoneg was not already enabled */ if (!(hw->phy.link_info.an_info & I40E_AQ_AN_COMPLETED)) { /* If autoneg is not supported, return error */ - if (!ethtool_link_ksettings_test_link_mode( - &safe_cmd, supported, Autoneg)) { + if (!ethtool_link_ksettings_test_link_mode(&safe_ks, + supported, + Autoneg)) { netdev_info(netdev, "Autoneg not supported on this phy\n"); err = -EINVAL; goto done; @@ -793,7 +926,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev, /* Autoneg is allowed to change */ config.abilities = abilities.abilities | I40E_AQ_PHY_ENABLE_AN; - change = true; + autoneg_changed = true; } } else { /* If autoneg is currently enabled */ @@ -801,8 +934,9 @@ static int i40e_set_link_ksettings(struct net_device *netdev, /* If autoneg is supported 10GBASE_T is the only PHY * that can disable it, so otherwise return error */ - if (ethtool_link_ksettings_test_link_mode( - &safe_cmd, supported, Autoneg) && + if (ethtool_link_ksettings_test_link_mode(&safe_ks, + supported, + Autoneg) && hw->phy.link_info.phy_type != I40E_PHY_TYPE_10GBASE_T) { netdev_info(netdev, "Autoneg cannot be disabled on this phy\n"); @@ -812,32 +946,49 @@ static int i40e_set_link_ksettings(struct net_device *netdev, /* Autoneg is allowed to change */ config.abilities = abilities.abilities & ~I40E_AQ_PHY_ENABLE_AN; - change = true; + autoneg_changed = true; } } - ethtool_convert_link_mode_to_legacy_u32(&tmp, - safe_cmd.link_modes.supported); - if (advertise & ~tmp) { - err = -EINVAL; - goto done; - } - - if (advertise & ADVERTISED_100baseT_Full) + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 100baseT_Full)) config.link_speed |= I40E_LINK_SPEED_100MB; - if (advertise & ADVERTISED_1000baseT_Full || - advertise & ADVERTISED_1000baseKX_Full) + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseT_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseX_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseKX_Full)) config.link_speed |= I40E_LINK_SPEED_1GB; - if (advertise & ADVERTISED_10000baseT_Full || - advertise & ADVERTISED_10000baseKX4_Full || - advertise & ADVERTISED_10000baseKR_Full) + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseT_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseKX4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseKR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseCR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseSR_Full)) config.link_speed |= I40E_LINK_SPEED_10GB; - if (advertise & ADVERTISED_20000baseKR2_Full) + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 20000baseKR2_Full)) config.link_speed |= I40E_LINK_SPEED_20GB; - if (advertise & ADVERTISED_40000baseKR4_Full || - advertise & ADVERTISED_40000baseCR4_Full || - advertise & ADVERTISED_40000baseSR4_Full || - advertise & ADVERTISED_40000baseLR4_Full) + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseCR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseKR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseSR_Full)) + config.link_speed |= I40E_LINK_SPEED_25GB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseKR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseCR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseSR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseLR4_Full)) config.link_speed |= I40E_LINK_SPEED_40GB; /* If speed didn't get set, set it to what it currently is. @@ -846,8 +997,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev, */ if (!config.link_speed) config.link_speed = abilities.link_speed; - - if (change || (abilities.link_speed != config.link_speed)) { + if (autoneg_changed || abilities.link_speed != config.link_speed) { /* copy over the rest of the abilities */ config.phy_type = abilities.phy_type; config.phy_type_ext = abilities.phy_type_ext; @@ -874,7 +1024,8 @@ static int i40e_set_link_ksettings(struct net_device *netdev, /* make the aq call */ status = i40e_aq_set_phy_config(hw, &config, NULL); if (status) { - netdev_info(netdev, "Set phy config failed, err %s aq_err %s\n", + netdev_info(netdev, + "Set phy config failed, err %s aq_err %s\n", i40e_stat_str(hw, status), i40e_aq_str(hw, hw->aq.asq_last_status)); err = -EAGAIN; @@ -883,7 +1034,8 @@ static int i40e_set_link_ksettings(struct net_device *netdev, status = i40e_update_link_info(hw); if (status) - netdev_dbg(netdev, "Updating link info failed with err %s aq_err %s\n", + netdev_dbg(netdev, + "Updating link info failed with err %s aq_err %s\n", i40e_stat_str(hw, status), i40e_aq_str(hw, hw->aq.asq_last_status)); @@ -2008,7 +2160,9 @@ static int i40e_set_phys_id(struct net_device *netdev, if (!(pf->hw_features & I40E_HW_PHY_CONTROLS_LEDS)) { pf->led_status = i40e_led_get(hw); } else { - i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_ALL, NULL); + if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE)) + i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_ALL, + NULL); ret = i40e_led_get_phy(hw, &temp_status, &pf->phy_led_val); pf->led_status = temp_status; @@ -2033,7 +2187,8 @@ static int i40e_set_phys_id(struct net_device *netdev, ret = i40e_led_set_phy(hw, false, pf->led_status, (pf->phy_led_val | I40E_PHY_LED_MODE_ORIG)); - i40e_aq_set_phy_debug(hw, 0, NULL); + if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE)) + i40e_aq_set_phy_debug(hw, 0, NULL); } break; default: @@ -2071,14 +2226,13 @@ static int __i40e_get_coalesce(struct net_device *netdev, ec->tx_max_coalesced_frames_irq = vsi->work_limit; ec->rx_max_coalesced_frames_irq = vsi->work_limit; - /* rx and tx usecs has per queue value. If user doesn't specify the queue, - * return queue 0's value to represent. + /* rx and tx usecs has per queue value. If user doesn't specify the + * queue, return queue 0's value to represent. */ - if (queue < 0) { + if (queue < 0) queue = 0; - } else if (queue >= vsi->num_queue_pairs) { + else if (queue >= vsi->num_queue_pairs) return -EINVAL; - } rx_ring = vsi->rx_rings[queue]; tx_ring = vsi->tx_rings[queue]; @@ -2092,7 +2246,6 @@ static int __i40e_get_coalesce(struct net_device *netdev, ec->rx_coalesce_usecs = rx_ring->rx_itr_setting & ~I40E_ITR_DYNAMIC; ec->tx_coalesce_usecs = tx_ring->tx_itr_setting & ~I40E_ITR_DYNAMIC; - /* we use the _usecs_high to store/set the interrupt rate limit * that the hardware supports, that almost but not quite * fits the original intent of the ethtool variable, @@ -2142,7 +2295,6 @@ static int i40e_get_per_queue_coalesce(struct net_device *netdev, u32 queue, * * Change the ITR settings for a specific queue. **/ - static void i40e_set_itr_per_queue(struct i40e_vsi *vsi, struct ethtool_coalesce *ec, int queue) @@ -2264,8 +2416,8 @@ static int __i40e_set_coalesce(struct net_device *netdev, vsi->int_rate_limit); } - /* rx and tx usecs has per queue value. If user doesn't specify the queue, - * apply to all queues. + /* rx and tx usecs has per queue value. If user doesn't specify the + * queue, apply to all queues. */ if (queue < 0) { for (i = 0; i < vsi->num_queue_pairs; i++) @@ -2647,7 +2799,7 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, switch (cmd->cmd) { case ETHTOOL_GRXRINGS: - cmd->data = vsi->num_queue_pairs; + cmd->data = vsi->rss_size; ret = 0; break; case ETHTOOL_GRXFH: @@ -3892,6 +4044,12 @@ static int i40e_set_channels(struct net_device *dev, if (vsi->type != I40E_VSI_MAIN) return -EINVAL; + /* We do not support setting channels via ethtool when TCs are + * configured through mqprio + */ + if (pf->flags & I40E_FLAG_TC_MQPRIO) + return -EINVAL; + /* verify they are not requesting separate vectors */ if (!count || ch->rx_count || ch->tx_count) return -EINVAL; @@ -3959,6 +4117,16 @@ static u32 i40e_get_rxfh_indir_size(struct net_device *netdev) return I40E_HLUT_ARRAY_SIZE; } +/** + * i40e_get_rxfh - get the rx flow hash indirection table + * @netdev: network interface device structure + * @indir: indirection table + * @key: hash key + * @hfunc: hash function + * + * Reads the indirection table directly from the hardware. Returns 0 on + * success. + **/ static int i40e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc) { @@ -4090,7 +4258,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - u64 orig_flags, new_flags, changed_flags; + u32 orig_flags, new_flags, changed_flags; u32 i, j; orig_flags = READ_ONCE(pf->flags); @@ -4142,12 +4310,12 @@ flags_complete: return -EOPNOTSUPP; /* Compare and exchange the new flags into place. If we failed, that - * is if cmpxchg64 returns anything but the old value, this means that + * is if cmpxchg returns anything but the old value, this means that * something else has modified the flags variable since we copied it * originally. We'll just punt with an error and log something in the * message buffer. */ - if (cmpxchg64(&pf->flags, orig_flags, new_flags) != orig_flags) { + if (cmpxchg(&pf->flags, orig_flags, new_flags) != orig_flags) { dev_warn(&pf->pdev->dev, "Unable to update pf->flags as it was modified by another thread...\n"); return -EAGAIN; @@ -4189,8 +4357,9 @@ flags_complete: /* Issue reset to cause things to take effect, as additional bits * are added we will need to create a mask of bits requiring reset */ - if ((changed_flags & I40E_FLAG_VEB_STATS_ENABLED) || - ((changed_flags & I40E_FLAG_LEGACY_RX) && netif_running(dev))) + if (changed_flags & (I40E_FLAG_VEB_STATS_ENABLED | + I40E_FLAG_LEGACY_RX | + I40E_FLAG_SOURCE_PRUNING_DISABLED)) i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true); return 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 3f9e89b054ec..54ff34faca37 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1589,6 +1589,170 @@ static int i40e_set_mac(struct net_device *netdev, void *p) } /** + * i40e_config_rss_aq - Prepare for RSS using AQ commands + * @vsi: vsi structure + * @seed: RSS hash seed + **/ +static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed, + u8 *lut, u16 lut_size) +{ + struct i40e_pf *pf = vsi->back; + struct i40e_hw *hw = &pf->hw; + int ret = 0; + + if (seed) { + struct i40e_aqc_get_set_rss_key_data *seed_dw = + (struct i40e_aqc_get_set_rss_key_data *)seed; + ret = i40e_aq_set_rss_key(hw, vsi->id, seed_dw); + if (ret) { + dev_info(&pf->pdev->dev, + "Cannot set RSS key, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return ret; + } + } + if (lut) { + bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false; + + ret = i40e_aq_set_rss_lut(hw, vsi->id, pf_lut, lut, lut_size); + if (ret) { + dev_info(&pf->pdev->dev, + "Cannot set RSS lut, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return ret; + } + } + return ret; +} + +/** + * i40e_vsi_config_rss - Prepare for VSI(VMDq) RSS if used + * @vsi: VSI structure + **/ +static int i40e_vsi_config_rss(struct i40e_vsi *vsi) +{ + struct i40e_pf *pf = vsi->back; + u8 seed[I40E_HKEY_ARRAY_SIZE]; + u8 *lut; + int ret; + + if (!(pf->hw_features & I40E_HW_RSS_AQ_CAPABLE)) + return 0; + if (!vsi->rss_size) + vsi->rss_size = min_t(int, pf->alloc_rss_size, + vsi->num_queue_pairs); + if (!vsi->rss_size) + return -EINVAL; + lut = kzalloc(vsi->rss_table_size, GFP_KERNEL); + if (!lut) + return -ENOMEM; + + /* Use the user configured hash keys and lookup table if there is one, + * otherwise use default + */ + if (vsi->rss_lut_user) + memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size); + else + i40e_fill_rss_lut(pf, lut, vsi->rss_table_size, vsi->rss_size); + if (vsi->rss_hkey_user) + memcpy(seed, vsi->rss_hkey_user, I40E_HKEY_ARRAY_SIZE); + else + netdev_rss_key_fill((void *)seed, I40E_HKEY_ARRAY_SIZE); + ret = i40e_config_rss_aq(vsi, seed, lut, vsi->rss_table_size); + kfree(lut); + return ret; +} + +/** + * i40e_vsi_setup_queue_map_mqprio - Prepares mqprio based tc_config + * @vsi: the VSI being configured, + * @ctxt: VSI context structure + * @enabled_tc: number of traffic classes to enable + * + * Prepares VSI tc_config to have queue configurations based on MQPRIO options. + **/ +static int i40e_vsi_setup_queue_map_mqprio(struct i40e_vsi *vsi, + struct i40e_vsi_context *ctxt, + u8 enabled_tc) +{ + u16 qcount = 0, max_qcount, qmap, sections = 0; + int i, override_q, pow, num_qps, ret; + u8 netdev_tc = 0, offset = 0; + + if (vsi->type != I40E_VSI_MAIN) + return -EINVAL; + sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID; + sections |= I40E_AQ_VSI_PROP_SCHED_VALID; + vsi->tc_config.numtc = vsi->mqprio_qopt.qopt.num_tc; + vsi->tc_config.enabled_tc = enabled_tc ? enabled_tc : 1; + num_qps = vsi->mqprio_qopt.qopt.count[0]; + + /* find the next higher power-of-2 of num queue pairs */ + pow = ilog2(num_qps); + if (!is_power_of_2(num_qps)) + pow++; + qmap = (offset << I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) | + (pow << I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT); + + /* Setup queue offset/count for all TCs for given VSI */ + max_qcount = vsi->mqprio_qopt.qopt.count[0]; + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { + /* See if the given TC is enabled for the given VSI */ + if (vsi->tc_config.enabled_tc & BIT(i)) { + offset = vsi->mqprio_qopt.qopt.offset[i]; + qcount = vsi->mqprio_qopt.qopt.count[i]; + if (qcount > max_qcount) + max_qcount = qcount; + vsi->tc_config.tc_info[i].qoffset = offset; + vsi->tc_config.tc_info[i].qcount = qcount; + vsi->tc_config.tc_info[i].netdev_tc = netdev_tc++; + } else { + /* TC is not enabled so set the offset to + * default queue and allocate one queue + * for the given TC. + */ + vsi->tc_config.tc_info[i].qoffset = 0; + vsi->tc_config.tc_info[i].qcount = 1; + vsi->tc_config.tc_info[i].netdev_tc = 0; + } + } + + /* Set actual Tx/Rx queue pairs */ + vsi->num_queue_pairs = offset + qcount; + + /* Setup queue TC[0].qmap for given VSI context */ + ctxt->info.tc_mapping[0] = cpu_to_le16(qmap); + ctxt->info.mapping_flags |= cpu_to_le16(I40E_AQ_VSI_QUE_MAP_CONTIG); + ctxt->info.queue_mapping[0] = cpu_to_le16(vsi->base_queue); + ctxt->info.valid_sections |= cpu_to_le16(sections); + + /* Reconfigure RSS for main VSI with max queue count */ + vsi->rss_size = max_qcount; + ret = i40e_vsi_config_rss(vsi); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Failed to reconfig rss for num_queues (%u)\n", + max_qcount); + return ret; + } + vsi->reconfig_rss = true; + dev_dbg(&vsi->back->pdev->dev, + "Reconfigured rss with num_queues (%u)\n", max_qcount); + + /* Find queue count available for channel VSIs and starting offset + * for channel VSIs + */ + override_q = vsi->mqprio_qopt.qopt.count[0]; + if (override_q && override_q < vsi->num_queue_pairs) { + vsi->cnt_q_avail = vsi->num_queue_pairs - override_q; + vsi->next_base_queue = override_q; + } + return 0; +} + +/** * i40e_vsi_setup_queue_map - Setup a VSI queue map based on enabled_tc * @vsi: the VSI being setup * @ctxt: VSI context structure @@ -1626,7 +1790,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, numtc = 1; } } else { - /* At least TC0 is enabled in case of non-DCB case */ + /* At least TC0 is enabled in non-DCB, non-MQPRIO case */ numtc = 1; } @@ -1776,11 +1940,6 @@ static void i40e_set_rx_mode(struct net_device *netdev) vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; vsi->back->flags |= I40E_FLAG_FILTER_SYNC; } - - /* schedule our worker thread which will take care of - * applying the new filter changes - */ - i40e_service_event_schedule(vsi->back); } /** @@ -2884,22 +3043,18 @@ static void i40e_vsi_free_rx_resources(struct i40e_vsi *vsi) **/ static void i40e_config_xps_tx_ring(struct i40e_ring *ring) { - struct i40e_vsi *vsi = ring->vsi; + int cpu; - if (!ring->q_vector || !ring->netdev) + if (!ring->q_vector || !ring->netdev || ring->ch) return; - if ((vsi->tc_config.numtc <= 1) && - !test_and_set_bit(__I40E_TX_XPS_INIT_DONE, &ring->state)) { - netif_set_xps_queue(ring->netdev, - get_cpu_mask(ring->q_vector->v_idx), - ring->queue_index); - } + /* We only initialize XPS once, so as not to overwrite user settings */ + if (test_and_set_bit(__I40E_TX_XPS_INIT_DONE, ring->state)) + return; - /* schedule our worker thread which will take care of - * applying the new filter changes - */ - i40e_service_event_schedule(vsi->back); + cpu = cpumask_local_spread(ring->q_vector->v_idx, -1); + netif_set_xps_queue(ring->netdev, get_cpu_mask(cpu), + ring->queue_index); } /** @@ -2953,7 +3108,14 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) * initialization. This has to be done regardless of * DCB as by default everything is mapped to TC0. */ - tx_ctx.rdylist = le16_to_cpu(vsi->info.qs_handle[ring->dcb_tc]); + + if (ring->ch) + tx_ctx.rdylist = + le16_to_cpu(ring->ch->info.qs_handle[ring->dcb_tc]); + + else + tx_ctx.rdylist = le16_to_cpu(vsi->info.qs_handle[ring->dcb_tc]); + tx_ctx.rdylist_act = 0; /* clear the context in the HMC */ @@ -2975,12 +3137,23 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) } /* Now associate this queue with this PCI function */ - if (vsi->type == I40E_VSI_VMDQ2) { - qtx_ctl = I40E_QTX_CTL_VM_QUEUE; - qtx_ctl |= ((vsi->id) << I40E_QTX_CTL_VFVM_INDX_SHIFT) & - I40E_QTX_CTL_VFVM_INDX_MASK; + if (ring->ch) { + if (ring->ch->type == I40E_VSI_VMDQ2) + qtx_ctl = I40E_QTX_CTL_VM_QUEUE; + else + return -EINVAL; + + qtx_ctl |= (ring->ch->vsi_number << + I40E_QTX_CTL_VFVM_INDX_SHIFT) & + I40E_QTX_CTL_VFVM_INDX_MASK; } else { - qtx_ctl = I40E_QTX_CTL_PF_QUEUE; + if (vsi->type == I40E_VSI_VMDQ2) { + qtx_ctl = I40E_QTX_CTL_VM_QUEUE; + qtx_ctl |= ((vsi->id) << I40E_QTX_CTL_VFVM_INDX_SHIFT) & + I40E_QTX_CTL_VFVM_INDX_MASK; + } else { + qtx_ctl = I40E_QTX_CTL_PF_QUEUE; + } } qtx_ctl |= ((hw->pf_id << I40E_QTX_CTL_PF_INDX_SHIFT) & @@ -3009,7 +3182,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) struct i40e_hmc_obj_rxq rx_ctx; i40e_status err = 0; - ring->state = 0; + bitmap_zero(ring->state, __I40E_RING_STATE_NBITS); /* clear the context structure first */ memset(&rx_ctx, 0, sizeof(rx_ctx)); @@ -3034,7 +3207,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) if (hw->revision_id == 0) rx_ctx.lrxqthresh = 0; else - rx_ctx.lrxqthresh = 2; + rx_ctx.lrxqthresh = 1; rx_ctx.crcstrip = 1; rx_ctx.l2tsel = 1; /* this controls whether VLAN is stripped from inner headers */ @@ -3149,6 +3322,7 @@ static void i40e_vsi_config_dcb_rings(struct i40e_vsi *vsi) rx_ring->dcb_tc = 0; tx_ring->dcb_tc = 0; } + return; } for (n = 0; n < I40E_MAX_TRAFFIC_CLASS; n++) { @@ -3407,15 +3581,14 @@ void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf) /** * i40e_irq_dynamic_enable_icr0 - Enable default interrupt generation for icr0 * @pf: board private structure - * @clearpba: true when all pending interrupt events should be cleared **/ -void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba) +void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; u32 val; val = I40E_PFINT_DYN_CTL0_INTENA_MASK | - (clearpba ? I40E_PFINT_DYN_CTL0_CLEARPBA_MASK : 0) | + I40E_PFINT_DYN_CTL0_CLEARPBA_MASK | (I40E_ITR_NONE << I40E_PFINT_DYN_CTL0_ITR_INDX_SHIFT); wr32(hw, I40E_PFINT_DYN_CTL0, val); @@ -3482,6 +3655,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) int tx_int_idx = 0; int vector, err; int irq_num; + int cpu; for (vector = 0; vector < q_vectors; vector++) { struct i40e_q_vector *q_vector = vsi->q_vectors[vector]; @@ -3517,10 +3691,14 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) q_vector->affinity_notify.notify = i40e_irq_affinity_notify; q_vector->affinity_notify.release = i40e_irq_affinity_release; irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); - /* get_cpu_mask returns a static constant mask with - * a permanent lifetime so it's ok to use here. + /* Spread affinity hints out across online CPUs. + * + * get_cpu_mask returns a static constant mask with + * a permanent lifetime so it's ok to pass to + * irq_set_affinity_hint without making a copy. */ - irq_set_affinity_hint(irq_num, get_cpu_mask(q_vector->v_idx)); + cpu = cpumask_local_spread(q_vector->v_idx, -1); + irq_set_affinity_hint(irq_num, get_cpu_mask(cpu)); } vsi->irqs_ready = true; @@ -3596,7 +3774,7 @@ static int i40e_vsi_enable_irq(struct i40e_vsi *vsi) for (i = 0; i < vsi->num_q_vectors; i++) i40e_irq_dynamic_enable(vsi, i); } else { - i40e_irq_dynamic_enable_icr0(pf, true); + i40e_irq_dynamic_enable_icr0(pf); } i40e_flush(&pf->hw); @@ -3745,7 +3923,7 @@ enable_intr: wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask); if (!test_bit(__I40E_DOWN, pf->state)) { i40e_service_event_schedule(pf); - i40e_irq_dynamic_enable_icr0(pf, false); + i40e_irq_dynamic_enable_icr0(pf); } return ret; @@ -4861,6 +5039,24 @@ static u8 i40e_dcb_get_enabled_tc(struct i40e_dcbx_config *dcbcfg) } /** + * i40e_mqprio_get_enabled_tc - Get enabled traffic classes + * @pf: PF being queried + * + * Query the current MQPRIO configuration and return the number of + * traffic classes enabled. + **/ +static u8 i40e_mqprio_get_enabled_tc(struct i40e_pf *pf) +{ + struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + u8 num_tc = vsi->mqprio_qopt.qopt.num_tc; + u8 enabled_tc = 1, i; + + for (i = 1; i < num_tc; i++) + enabled_tc |= BIT(i); + return enabled_tc; +} + +/** * i40e_pf_get_num_tc - Get enabled traffic classes for PF * @pf: PF being queried * @@ -4873,7 +5069,10 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) u8 num_tc = 0; struct i40e_dcbx_config *dcbcfg = &hw->local_dcbx_config; - /* If DCB is not enabled then always in single TC */ + if (pf->flags & I40E_FLAG_TC_MQPRIO) + return pf->vsi[pf->lan_vsi]->mqprio_qopt.qopt.num_tc; + + /* If neither MQPRIO nor DCB is enabled, then always use single TC */ if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) return 1; @@ -4902,7 +5101,12 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) **/ static u8 i40e_pf_get_tc_map(struct i40e_pf *pf) { - /* If DCB is not enabled for this PF then just return default TC */ + if (pf->flags & I40E_FLAG_TC_MQPRIO) + return i40e_mqprio_get_enabled_tc(pf); + + /* If neither MQPRIO nor DCB is enabled for this PF then just return + * default TC + */ if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) return I40E_DEFAULT_TRAFFIC_CLASS; @@ -4992,6 +5196,16 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, i40e_status ret; int i; + if (vsi->back->flags & I40E_FLAG_TC_MQPRIO) + return 0; + if (!vsi->mqprio_qopt.qopt.hw) { + ret = i40e_set_bw_limit(vsi, vsi->seid, 0); + if (ret) + dev_info(&vsi->back->pdev->dev, + "Failed to reset tx rate for vsi->seid %u\n", + vsi->seid); + return ret; + } bw_data.tc_valid_bits = enabled_tc; for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) bw_data.tc_bw_credits[i] = bw_share[i]; @@ -5054,6 +5268,9 @@ static void i40e_vsi_config_netdev_tc(struct i40e_vsi *vsi, u8 enabled_tc) vsi->tc_config.tc_info[i].qoffset); } + if (pf->flags & I40E_FLAG_TC_MQPRIO) + return; + /* Assign UP2TC map for the VSI */ for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) { /* Get the actual TC# for the UP */ @@ -5104,7 +5321,8 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) int i; /* Check if enabled_tc is same as existing or new TCs */ - if (vsi->tc_config.enabled_tc == enabled_tc) + if (vsi->tc_config.enabled_tc == enabled_tc && + vsi->mqprio_qopt.mode != TC_MQPRIO_MODE_CHANNEL) return ret; /* Enable ETS TCs with equal BW Share for now across all VSIs */ @@ -5127,15 +5345,37 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) ctxt.vf_num = 0; ctxt.uplink_seid = vsi->uplink_seid; ctxt.info = vsi->info; - i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, false); + if (vsi->back->flags & I40E_FLAG_TC_MQPRIO) { + ret = i40e_vsi_setup_queue_map_mqprio(vsi, &ctxt, enabled_tc); + if (ret) + goto out; + } else { + i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, false); + } + /* On destroying the qdisc, reset vsi->rss_size, as number of enabled + * queues changed. + */ + if (!vsi->mqprio_qopt.qopt.hw && vsi->reconfig_rss) { + vsi->rss_size = min_t(int, vsi->back->alloc_rss_size, + vsi->num_queue_pairs); + ret = i40e_vsi_config_rss(vsi); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Failed to reconfig rss for num_queues\n"); + return ret; + } + vsi->reconfig_rss = false; + } if (vsi->back->flags & I40E_FLAG_IWARP_ENABLED) { ctxt.info.valid_sections |= cpu_to_le16(I40E_AQ_VSI_PROP_QUEUE_OPT_VALID); ctxt.info.queueing_opt_flags |= I40E_AQ_VSI_QUE_OPT_TCP_ENA; } - /* Update the VSI after updating the VSI queue-mapping information */ + /* Update the VSI after updating the VSI queue-mapping + * information + */ ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL); if (ret) { dev_info(&vsi->back->pdev->dev, @@ -5167,6 +5407,739 @@ out: } /** + * i40e_get_link_speed - Returns link speed for the interface + * @vsi: VSI to be configured + * + **/ +int i40e_get_link_speed(struct i40e_vsi *vsi) +{ + struct i40e_pf *pf = vsi->back; + + switch (pf->hw.phy.link_info.link_speed) { + case I40E_LINK_SPEED_40GB: + return 40000; + case I40E_LINK_SPEED_25GB: + return 25000; + case I40E_LINK_SPEED_20GB: + return 20000; + case I40E_LINK_SPEED_10GB: + return 10000; + case I40E_LINK_SPEED_1GB: + return 1000; + default: + return -EINVAL; + } +} + +/** + * i40e_set_bw_limit - setup BW limit for Tx traffic based on max_tx_rate + * @vsi: VSI to be configured + * @seid: seid of the channel/VSI + * @max_tx_rate: max TX rate to be configured as BW limit + * + * Helper function to set BW limit for a given VSI + **/ +int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate) +{ + struct i40e_pf *pf = vsi->back; + u64 credits = 0; + int speed = 0; + int ret = 0; + + speed = i40e_get_link_speed(vsi); + if (max_tx_rate > speed) { + dev_err(&pf->pdev->dev, + "Invalid max tx rate %llu specified for VSI seid %d.", + max_tx_rate, seid); + return -EINVAL; + } + if (max_tx_rate && max_tx_rate < 50) { + dev_warn(&pf->pdev->dev, + "Setting max tx rate to minimum usable value of 50Mbps.\n"); + max_tx_rate = 50; + } + + /* Tx rate credits are in values of 50Mbps, 0 is disabled */ + credits = max_tx_rate; + do_div(credits, I40E_BW_CREDIT_DIVISOR); + ret = i40e_aq_config_vsi_bw_limit(&pf->hw, seid, credits, + I40E_MAX_BW_INACTIVE_ACCUM, NULL); + if (ret) + dev_err(&pf->pdev->dev, + "Failed set tx rate (%llu Mbps) for vsi->seid %u, err %s aq_err %s\n", + max_tx_rate, seid, i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + return ret; +} + +/** + * i40e_remove_queue_channels - Remove queue channels for the TCs + * @vsi: VSI to be configured + * + * Remove queue channels for the TCs + **/ +static void i40e_remove_queue_channels(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch, *ch_tmp; + int ret, i; + + /* Reset rss size that was stored when reconfiguring rss for + * channel VSIs with non-power-of-2 queue count. + */ + vsi->current_rss_size = 0; + + /* perform cleanup for channels if they exist */ + if (list_empty(&vsi->ch_list)) + return; + + list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { + struct i40e_vsi *p_vsi; + + list_del(&ch->list); + p_vsi = ch->parent_vsi; + if (!p_vsi || !ch->initialized) { + kfree(ch); + continue; + } + /* Reset queue contexts */ + for (i = 0; i < ch->num_queue_pairs; i++) { + struct i40e_ring *tx_ring, *rx_ring; + u16 pf_q; + + pf_q = ch->base_queue + i; + tx_ring = vsi->tx_rings[pf_q]; + tx_ring->ch = NULL; + + rx_ring = vsi->rx_rings[pf_q]; + rx_ring->ch = NULL; + } + + /* Reset BW configured for this VSI via mqprio */ + ret = i40e_set_bw_limit(vsi, ch->seid, 0); + if (ret) + dev_info(&vsi->back->pdev->dev, + "Failed to reset tx rate for ch->seid %u\n", + ch->seid); + + /* delete VSI from FW */ + ret = i40e_aq_delete_element(&vsi->back->hw, ch->seid, + NULL); + if (ret) + dev_err(&vsi->back->pdev->dev, + "unable to remove channel (%d) for parent VSI(%d)\n", + ch->seid, p_vsi->seid); + kfree(ch); + } + INIT_LIST_HEAD(&vsi->ch_list); +} + +/** + * i40e_is_any_channel - channel exist or not + * @vsi: ptr to VSI to which channels are associated with + * + * Returns true or false if channel(s) exist for associated VSI or not + **/ +static bool i40e_is_any_channel(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch, *ch_tmp; + + list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { + if (ch->initialized) + return true; + } + + return false; +} + +/** + * i40e_get_max_queues_for_channel + * @vsi: ptr to VSI to which channels are associated with + * + * Helper function which returns max value among the queue counts set on the + * channels/TCs created. + **/ +static int i40e_get_max_queues_for_channel(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch, *ch_tmp; + int max = 0; + + list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { + if (!ch->initialized) + continue; + if (ch->num_queue_pairs > max) + max = ch->num_queue_pairs; + } + + return max; +} + +/** + * i40e_validate_num_queues - validate num_queues w.r.t channel + * @pf: ptr to PF device + * @num_queues: number of queues + * @vsi: the parent VSI + * @reconfig_rss: indicates should the RSS be reconfigured or not + * + * This function validates number of queues in the context of new channel + * which is being established and determines if RSS should be reconfigured + * or not for parent VSI. + **/ +static int i40e_validate_num_queues(struct i40e_pf *pf, int num_queues, + struct i40e_vsi *vsi, bool *reconfig_rss) +{ + int max_ch_queues; + + if (!reconfig_rss) + return -EINVAL; + + *reconfig_rss = false; + + if (num_queues > I40E_MAX_QUEUES_PER_CH) { + dev_err(&pf->pdev->dev, + "Failed to create VMDq VSI. User requested num_queues (%d) > I40E_MAX_QUEUES_PER_VSI (%u)\n", + num_queues, I40E_MAX_QUEUES_PER_CH); + return -EINVAL; + } + + if (vsi->current_rss_size) { + if (num_queues > vsi->current_rss_size) { + dev_dbg(&pf->pdev->dev, + "Error: num_queues (%d) > vsi's current_size(%d)\n", + num_queues, vsi->current_rss_size); + return -EINVAL; + } else if ((num_queues < vsi->current_rss_size) && + (!is_power_of_2(num_queues))) { + dev_dbg(&pf->pdev->dev, + "Error: num_queues (%d) < vsi's current_size(%d), but not power of 2\n", + num_queues, vsi->current_rss_size); + return -EINVAL; + } + } + + if (!is_power_of_2(num_queues)) { + /* Find the max num_queues configured for channel if channel + * exist. + * if channel exist, then enforce 'num_queues' to be more than + * max ever queues configured for channel. + */ + max_ch_queues = i40e_get_max_queues_for_channel(vsi); + if (num_queues < max_ch_queues) { + dev_dbg(&pf->pdev->dev, + "Error: num_queues (%d) < max queues configured for channel(%d)\n", + num_queues, max_ch_queues); + return -EINVAL; + } + *reconfig_rss = true; + } + + return 0; +} + +/** + * i40e_vsi_reconfig_rss - reconfig RSS based on specified rss_size + * @vsi: the VSI being setup + * @rss_size: size of RSS, accordingly LUT gets reprogrammed + * + * This function reconfigures RSS by reprogramming LUTs using 'rss_size' + **/ +static int i40e_vsi_reconfig_rss(struct i40e_vsi *vsi, u16 rss_size) +{ + struct i40e_pf *pf = vsi->back; + u8 seed[I40E_HKEY_ARRAY_SIZE]; + struct i40e_hw *hw = &pf->hw; + int local_rss_size; + u8 *lut; + int ret; + + if (!vsi->rss_size) + return -EINVAL; + + if (rss_size > vsi->rss_size) + return -EINVAL; + + local_rss_size = min_t(int, vsi->rss_size, rss_size); + lut = kzalloc(vsi->rss_table_size, GFP_KERNEL); + if (!lut) + return -ENOMEM; + + /* Ignoring user configured lut if there is one */ + i40e_fill_rss_lut(pf, lut, vsi->rss_table_size, local_rss_size); + + /* Use user configured hash key if there is one, otherwise + * use default. + */ + if (vsi->rss_hkey_user) + memcpy(seed, vsi->rss_hkey_user, I40E_HKEY_ARRAY_SIZE); + else + netdev_rss_key_fill((void *)seed, I40E_HKEY_ARRAY_SIZE); + + ret = i40e_config_rss(vsi, seed, lut, vsi->rss_table_size); + if (ret) { + dev_info(&pf->pdev->dev, + "Cannot set RSS lut, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + kfree(lut); + return ret; + } + kfree(lut); + + /* Do the update w.r.t. storing rss_size */ + if (!vsi->orig_rss_size) + vsi->orig_rss_size = vsi->rss_size; + vsi->current_rss_size = local_rss_size; + + return ret; +} + +/** + * i40e_channel_setup_queue_map - Setup a channel queue map + * @pf: ptr to PF device + * @vsi: the VSI being setup + * @ctxt: VSI context structure + * @ch: ptr to channel structure + * + * Setup queue map for a specific channel + **/ +static void i40e_channel_setup_queue_map(struct i40e_pf *pf, + struct i40e_vsi_context *ctxt, + struct i40e_channel *ch) +{ + u16 qcount, qmap, sections = 0; + u8 offset = 0; + int pow; + + sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID; + sections |= I40E_AQ_VSI_PROP_SCHED_VALID; + + qcount = min_t(int, ch->num_queue_pairs, pf->num_lan_msix); + ch->num_queue_pairs = qcount; + + /* find the next higher power-of-2 of num queue pairs */ + pow = ilog2(qcount); + if (!is_power_of_2(qcount)) + pow++; + + qmap = (offset << I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) | + (pow << I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT); + + /* Setup queue TC[0].qmap for given VSI context */ + ctxt->info.tc_mapping[0] = cpu_to_le16(qmap); + + ctxt->info.up_enable_bits = 0x1; /* TC0 enabled */ + ctxt->info.mapping_flags |= cpu_to_le16(I40E_AQ_VSI_QUE_MAP_CONTIG); + ctxt->info.queue_mapping[0] = cpu_to_le16(ch->base_queue); + ctxt->info.valid_sections |= cpu_to_le16(sections); +} + +/** + * i40e_add_channel - add a channel by adding VSI + * @pf: ptr to PF device + * @uplink_seid: underlying HW switching element (VEB) ID + * @ch: ptr to channel structure + * + * Add a channel (VSI) using add_vsi and queue_map + **/ +static int i40e_add_channel(struct i40e_pf *pf, u16 uplink_seid, + struct i40e_channel *ch) +{ + struct i40e_hw *hw = &pf->hw; + struct i40e_vsi_context ctxt; + u8 enabled_tc = 0x1; /* TC0 enabled */ + int ret; + + if (ch->type != I40E_VSI_VMDQ2) { + dev_info(&pf->pdev->dev, + "add new vsi failed, ch->type %d\n", ch->type); + return -EINVAL; + } + + memset(&ctxt, 0, sizeof(ctxt)); + ctxt.pf_num = hw->pf_id; + ctxt.vf_num = 0; + ctxt.uplink_seid = uplink_seid; + ctxt.connection_type = I40E_AQ_VSI_CONN_TYPE_NORMAL; + if (ch->type == I40E_VSI_VMDQ2) + ctxt.flags = I40E_AQ_VSI_TYPE_VMDQ2; + + if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED) { + ctxt.info.valid_sections |= + cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID); + ctxt.info.switch_id = + cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB); + } + + /* Set queue map for a given VSI context */ + i40e_channel_setup_queue_map(pf, &ctxt, ch); + + /* Now time to create VSI */ + ret = i40e_aq_add_vsi(hw, &ctxt, NULL); + if (ret) { + dev_info(&pf->pdev->dev, + "add new vsi failed, err %s aq_err %s\n", + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, + pf->hw.aq.asq_last_status)); + return -ENOENT; + } + + /* Success, update channel */ + ch->enabled_tc = enabled_tc; + ch->seid = ctxt.seid; + ch->vsi_number = ctxt.vsi_number; + ch->stat_counter_idx = cpu_to_le16(ctxt.info.stat_counter_idx); + + /* copy just the sections touched not the entire info + * since not all sections are valid as returned by + * update vsi params + */ + ch->info.mapping_flags = ctxt.info.mapping_flags; + memcpy(&ch->info.queue_mapping, + &ctxt.info.queue_mapping, sizeof(ctxt.info.queue_mapping)); + memcpy(&ch->info.tc_mapping, ctxt.info.tc_mapping, + sizeof(ctxt.info.tc_mapping)); + + return 0; +} + +static int i40e_channel_config_bw(struct i40e_vsi *vsi, struct i40e_channel *ch, + u8 *bw_share) +{ + struct i40e_aqc_configure_vsi_tc_bw_data bw_data; + i40e_status ret; + int i; + + bw_data.tc_valid_bits = ch->enabled_tc; + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) + bw_data.tc_bw_credits[i] = bw_share[i]; + + ret = i40e_aq_config_vsi_tc_bw(&vsi->back->hw, ch->seid, + &bw_data, NULL); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Config VSI BW allocation per TC failed, aq_err: %d for new_vsi->seid %u\n", + vsi->back->hw.aq.asq_last_status, ch->seid); + return -EINVAL; + } + + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) + ch->info.qs_handle[i] = bw_data.qs_handles[i]; + + return 0; +} + +/** + * i40e_channel_config_tx_ring - config TX ring associated with new channel + * @pf: ptr to PF device + * @vsi: the VSI being setup + * @ch: ptr to channel structure + * + * Configure TX rings associated with channel (VSI) since queues are being + * from parent VSI. + **/ +static int i40e_channel_config_tx_ring(struct i40e_pf *pf, + struct i40e_vsi *vsi, + struct i40e_channel *ch) +{ + i40e_status ret; + int i; + u8 bw_share[I40E_MAX_TRAFFIC_CLASS] = {0}; + + /* Enable ETS TCs with equal BW Share for now across all VSIs */ + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { + if (ch->enabled_tc & BIT(i)) + bw_share[i] = 1; + } + + /* configure BW for new VSI */ + ret = i40e_channel_config_bw(vsi, ch, bw_share); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Failed configuring TC map %d for channel (seid %u)\n", + ch->enabled_tc, ch->seid); + return ret; + } + + for (i = 0; i < ch->num_queue_pairs; i++) { + struct i40e_ring *tx_ring, *rx_ring; + u16 pf_q; + + pf_q = ch->base_queue + i; + + /* Get to TX ring ptr of main VSI, for re-setup TX queue + * context + */ + tx_ring = vsi->tx_rings[pf_q]; + tx_ring->ch = ch; + + /* Get the RX ring ptr */ + rx_ring = vsi->rx_rings[pf_q]; + rx_ring->ch = ch; + } + + return 0; +} + +/** + * i40e_setup_hw_channel - setup new channel + * @pf: ptr to PF device + * @vsi: the VSI being setup + * @ch: ptr to channel structure + * @uplink_seid: underlying HW switching element (VEB) ID + * @type: type of channel to be created (VMDq2/VF) + * + * Setup new channel (VSI) based on specified type (VMDq2/VF) + * and configures TX rings accordingly + **/ +static inline int i40e_setup_hw_channel(struct i40e_pf *pf, + struct i40e_vsi *vsi, + struct i40e_channel *ch, + u16 uplink_seid, u8 type) +{ + int ret; + + ch->initialized = false; + ch->base_queue = vsi->next_base_queue; + ch->type = type; + + /* Proceed with creation of channel (VMDq2) VSI */ + ret = i40e_add_channel(pf, uplink_seid, ch); + if (ret) { + dev_info(&pf->pdev->dev, + "failed to add_channel using uplink_seid %u\n", + uplink_seid); + return ret; + } + + /* Mark the successful creation of channel */ + ch->initialized = true; + + /* Reconfigure TX queues using QTX_CTL register */ + ret = i40e_channel_config_tx_ring(pf, vsi, ch); + if (ret) { + dev_info(&pf->pdev->dev, + "failed to configure TX rings for channel %u\n", + ch->seid); + return ret; + } + + /* update 'next_base_queue' */ + vsi->next_base_queue = vsi->next_base_queue + ch->num_queue_pairs; + dev_dbg(&pf->pdev->dev, + "Added channel: vsi_seid %u, vsi_number %u, stat_counter_idx %u, num_queue_pairs %u, pf->next_base_queue %d\n", + ch->seid, ch->vsi_number, ch->stat_counter_idx, + ch->num_queue_pairs, + vsi->next_base_queue); + return ret; +} + +/** + * i40e_setup_channel - setup new channel using uplink element + * @pf: ptr to PF device + * @type: type of channel to be created (VMDq2/VF) + * @uplink_seid: underlying HW switching element (VEB) ID + * @ch: ptr to channel structure + * + * Setup new channel (VSI) based on specified type (VMDq2/VF) + * and uplink switching element (uplink_seid) + **/ +static bool i40e_setup_channel(struct i40e_pf *pf, struct i40e_vsi *vsi, + struct i40e_channel *ch) +{ + u8 vsi_type; + u16 seid; + int ret; + + if (vsi->type == I40E_VSI_MAIN) { + vsi_type = I40E_VSI_VMDQ2; + } else { + dev_err(&pf->pdev->dev, "unsupported parent vsi type(%d)\n", + vsi->type); + return false; + } + + /* underlying switching element */ + seid = pf->vsi[pf->lan_vsi]->uplink_seid; + + /* create channel (VSI), configure TX rings */ + ret = i40e_setup_hw_channel(pf, vsi, ch, seid, vsi_type); + if (ret) { + dev_err(&pf->pdev->dev, "failed to setup hw_channel\n"); + return false; + } + + return ch->initialized ? true : false; +} + +/** + * i40e_create_queue_channel - function to create channel + * @vsi: VSI to be configured + * @ch: ptr to channel (it contains channel specific params) + * + * This function creates channel (VSI) using num_queues specified by user, + * reconfigs RSS if needed. + **/ +int i40e_create_queue_channel(struct i40e_vsi *vsi, + struct i40e_channel *ch) +{ + struct i40e_pf *pf = vsi->back; + bool reconfig_rss; + int err; + + if (!ch) + return -EINVAL; + + if (!ch->num_queue_pairs) { + dev_err(&pf->pdev->dev, "Invalid num_queues requested: %d\n", + ch->num_queue_pairs); + return -EINVAL; + } + + /* validate user requested num_queues for channel */ + err = i40e_validate_num_queues(pf, ch->num_queue_pairs, vsi, + &reconfig_rss); + if (err) { + dev_info(&pf->pdev->dev, "Failed to validate num_queues (%d)\n", + ch->num_queue_pairs); + return -EINVAL; + } + + /* By default we are in VEPA mode, if this is the first VF/VMDq + * VSI to be added switch to VEB mode. + */ + if ((!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) || + (!i40e_is_any_channel(vsi))) { + if (!is_power_of_2(vsi->tc_config.tc_info[0].qcount)) { + dev_dbg(&pf->pdev->dev, + "Failed to create channel. Override queues (%u) not power of 2\n", + vsi->tc_config.tc_info[0].qcount); + return -EINVAL; + } + + if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { + pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; + + if (vsi->type == I40E_VSI_MAIN) { + if (pf->flags & I40E_FLAG_TC_MQPRIO) + i40e_do_reset(pf, I40E_PF_RESET_FLAG, + true); + else + i40e_do_reset_safe(pf, + I40E_PF_RESET_FLAG); + } + } + /* now onwards for main VSI, number of queues will be value + * of TC0's queue count + */ + } + + /* By this time, vsi->cnt_q_avail shall be set to non-zero and + * it should be more than num_queues + */ + if (!vsi->cnt_q_avail || vsi->cnt_q_avail < ch->num_queue_pairs) { + dev_dbg(&pf->pdev->dev, + "Error: cnt_q_avail (%u) less than num_queues %d\n", + vsi->cnt_q_avail, ch->num_queue_pairs); + return -EINVAL; + } + + /* reconfig_rss only if vsi type is MAIN_VSI */ + if (reconfig_rss && (vsi->type == I40E_VSI_MAIN)) { + err = i40e_vsi_reconfig_rss(vsi, ch->num_queue_pairs); + if (err) { + dev_info(&pf->pdev->dev, + "Error: unable to reconfig rss for num_queues (%u)\n", + ch->num_queue_pairs); + return -EINVAL; + } + } + + if (!i40e_setup_channel(pf, vsi, ch)) { + dev_info(&pf->pdev->dev, "Failed to setup channel\n"); + return -EINVAL; + } + + dev_info(&pf->pdev->dev, + "Setup channel (id:%u) utilizing num_queues %d\n", + ch->seid, ch->num_queue_pairs); + + /* configure VSI for BW limit */ + if (ch->max_tx_rate) { + u64 credits = ch->max_tx_rate; + + if (i40e_set_bw_limit(vsi, ch->seid, ch->max_tx_rate)) + return -EINVAL; + + do_div(credits, I40E_BW_CREDIT_DIVISOR); + dev_dbg(&pf->pdev->dev, + "Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n", + ch->max_tx_rate, + credits, + ch->seid); + } + + /* in case of VF, this will be main SRIOV VSI */ + ch->parent_vsi = vsi; + + /* and update main_vsi's count for queue_available to use */ + vsi->cnt_q_avail -= ch->num_queue_pairs; + + return 0; +} + +/** + * i40e_configure_queue_channels - Add queue channel for the given TCs + * @vsi: VSI to be configured + * + * Configures queue channel mapping to the given TCs + **/ +static int i40e_configure_queue_channels(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch; + u64 max_rate = 0; + int ret = 0, i; + + /* Create app vsi with the TCs. Main VSI with TC0 is already set up */ + for (i = 1; i < I40E_MAX_TRAFFIC_CLASS; i++) { + if (vsi->tc_config.enabled_tc & BIT(i)) { + ch = kzalloc(sizeof(*ch), GFP_KERNEL); + if (!ch) { + ret = -ENOMEM; + goto err_free; + } + + INIT_LIST_HEAD(&ch->list); + ch->num_queue_pairs = + vsi->tc_config.tc_info[i].qcount; + ch->base_queue = + vsi->tc_config.tc_info[i].qoffset; + + /* Bandwidth limit through tc interface is in bytes/s, + * change to Mbit/s + */ + max_rate = vsi->mqprio_qopt.max_rate[i]; + do_div(max_rate, I40E_BW_MBPS_DIVISOR); + ch->max_tx_rate = max_rate; + + list_add_tail(&ch->list, &vsi->ch_list); + + ret = i40e_create_queue_channel(vsi, ch); + if (ret) { + dev_err(&vsi->back->pdev->dev, + "Failed creating queue channel with TC%d: queues %d\n", + i, ch->num_queue_pairs); + goto err_free; + } + } + } + return ret; + +err_free: + i40e_remove_queue_channels(vsi); + return ret; +} + +/** * i40e_veb_config_tc - Configure TCs for given VEB * @veb: given VEB * @enabled_tc: TC bitmap @@ -5567,74 +6540,221 @@ void i40e_down(struct i40e_vsi *vsi) } /** + * i40e_validate_mqprio_qopt- validate queue mapping info + * @vsi: the VSI being configured + * @mqprio_qopt: queue parametrs + **/ +static int i40e_validate_mqprio_qopt(struct i40e_vsi *vsi, + struct tc_mqprio_qopt_offload *mqprio_qopt) +{ + u64 sum_max_rate = 0; + u64 max_rate = 0; + int i; + + if (mqprio_qopt->qopt.offset[0] != 0 || + mqprio_qopt->qopt.num_tc < 1 || + mqprio_qopt->qopt.num_tc > I40E_MAX_TRAFFIC_CLASS) + return -EINVAL; + for (i = 0; ; i++) { + if (!mqprio_qopt->qopt.count[i]) + return -EINVAL; + if (mqprio_qopt->min_rate[i]) { + dev_err(&vsi->back->pdev->dev, + "Invalid min tx rate (greater than 0) specified\n"); + return -EINVAL; + } + max_rate = mqprio_qopt->max_rate[i]; + do_div(max_rate, I40E_BW_MBPS_DIVISOR); + sum_max_rate += max_rate; + + if (i >= mqprio_qopt->qopt.num_tc - 1) + break; + if (mqprio_qopt->qopt.offset[i + 1] != + (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) + return -EINVAL; + } + if (vsi->num_queue_pairs < + (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) { + return -EINVAL; + } + if (sum_max_rate > i40e_get_link_speed(vsi)) { + dev_err(&vsi->back->pdev->dev, + "Invalid max tx rate specified\n"); + return -EINVAL; + } + return 0; +} + +/** + * i40e_vsi_set_default_tc_config - set default values for tc configuration + * @vsi: the VSI being configured + **/ +static void i40e_vsi_set_default_tc_config(struct i40e_vsi *vsi) +{ + u16 qcount; + int i; + + /* Only TC0 is enabled */ + vsi->tc_config.numtc = 1; + vsi->tc_config.enabled_tc = 1; + qcount = min_t(int, vsi->alloc_queue_pairs, + i40e_pf_get_max_q_per_tc(vsi->back)); + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { + /* For the TC that is not enabled set the offset to to default + * queue and allocate one queue for the given TC. + */ + vsi->tc_config.tc_info[i].qoffset = 0; + if (i == 0) + vsi->tc_config.tc_info[i].qcount = qcount; + else + vsi->tc_config.tc_info[i].qcount = 1; + vsi->tc_config.tc_info[i].netdev_tc = 0; + } +} + +/** * i40e_setup_tc - configure multiple traffic classes * @netdev: net device to configure - * @tc: number of traffic classes to enable + * @type_data: tc offload data **/ -static int i40e_setup_tc(struct net_device *netdev, u8 tc) +static int i40e_setup_tc(struct net_device *netdev, void *type_data) { + struct tc_mqprio_qopt_offload *mqprio_qopt = type_data; struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - u8 enabled_tc = 0; + u8 enabled_tc = 0, num_tc, hw; + bool need_reset = false; int ret = -EINVAL; + u16 mode; int i; - /* Check if DCB enabled to continue */ - if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) { - netdev_info(netdev, "DCB is not enabled for adapter\n"); - goto exit; + num_tc = mqprio_qopt->qopt.num_tc; + hw = mqprio_qopt->qopt.hw; + mode = mqprio_qopt->mode; + if (!hw) { + pf->flags &= ~I40E_FLAG_TC_MQPRIO; + memcpy(&vsi->mqprio_qopt, mqprio_qopt, sizeof(*mqprio_qopt)); + goto config_tc; } /* Check if MFP enabled */ if (pf->flags & I40E_FLAG_MFP_ENABLED) { - netdev_info(netdev, "Configuring TC not supported in MFP mode\n"); - goto exit; + netdev_info(netdev, + "Configuring TC not supported in MFP mode\n"); + return ret; } + switch (mode) { + case TC_MQPRIO_MODE_DCB: + pf->flags &= ~I40E_FLAG_TC_MQPRIO; - /* Check whether tc count is within enabled limit */ - if (tc > i40e_pf_get_num_tc(pf)) { - netdev_info(netdev, "TC count greater than enabled on link for adapter\n"); - goto exit; + /* Check if DCB enabled to continue */ + if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) { + netdev_info(netdev, + "DCB is not enabled for adapter\n"); + return ret; + } + + /* Check whether tc count is within enabled limit */ + if (num_tc > i40e_pf_get_num_tc(pf)) { + netdev_info(netdev, + "TC count greater than enabled on link for adapter\n"); + return ret; + } + break; + case TC_MQPRIO_MODE_CHANNEL: + if (pf->flags & I40E_FLAG_DCB_ENABLED) { + netdev_info(netdev, + "Full offload of TC Mqprio options is not supported when DCB is enabled\n"); + return ret; + } + if (!(pf->flags & I40E_FLAG_MSIX_ENABLED)) + return ret; + ret = i40e_validate_mqprio_qopt(vsi, mqprio_qopt); + if (ret) + return ret; + memcpy(&vsi->mqprio_qopt, mqprio_qopt, + sizeof(*mqprio_qopt)); + pf->flags |= I40E_FLAG_TC_MQPRIO; + pf->flags &= ~I40E_FLAG_DCB_ENABLED; + break; + default: + return -EINVAL; } +config_tc: /* Generate TC map for number of tc requested */ - for (i = 0; i < tc; i++) + for (i = 0; i < num_tc; i++) enabled_tc |= BIT(i); /* Requesting same TC configuration as already enabled */ - if (enabled_tc == vsi->tc_config.enabled_tc) + if (enabled_tc == vsi->tc_config.enabled_tc && + mode != TC_MQPRIO_MODE_CHANNEL) return 0; /* Quiesce VSI queues */ i40e_quiesce_vsi(vsi); + if (!hw && !(pf->flags & I40E_FLAG_TC_MQPRIO)) + i40e_remove_queue_channels(vsi); + /* Configure VSI for enabled TCs */ ret = i40e_vsi_config_tc(vsi, enabled_tc); if (ret) { netdev_info(netdev, "Failed configuring TC for VSI seid=%d\n", vsi->seid); + need_reset = true; goto exit; } - /* Unquiesce VSI */ - i40e_unquiesce_vsi(vsi); + if (pf->flags & I40E_FLAG_TC_MQPRIO) { + if (vsi->mqprio_qopt.max_rate[0]) { + u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0]; + + do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR); + ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); + if (!ret) { + u64 credits = max_tx_rate; + + do_div(credits, I40E_BW_CREDIT_DIVISOR); + dev_dbg(&vsi->back->pdev->dev, + "Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n", + max_tx_rate, + credits, + vsi->seid); + } else { + need_reset = true; + goto exit; + } + } + ret = i40e_configure_queue_channels(vsi); + if (ret) { + netdev_info(netdev, + "Failed configuring queue channels\n"); + need_reset = true; + goto exit; + } + } exit: + /* Reset the configuration data to defaults, only TC0 is enabled */ + if (need_reset) { + i40e_vsi_set_default_tc_config(vsi); + need_reset = false; + } + + /* Unquiesce VSI */ + i40e_unquiesce_vsi(vsi); return ret; } static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type, void *type_data) { - struct tc_mqprio_qopt *mqprio = type_data; - if (type != TC_SETUP_MQPRIO) return -EOPNOTSUPP; - mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - - return i40e_setup_tc(netdev, mqprio->num_tc); + return i40e_setup_tc(netdev, type_data); } /** @@ -5752,7 +6872,7 @@ err_setup_rx: err_setup_tx: i40e_vsi_free_tx_resources(vsi); if (vsi == pf->vsi[pf->lan_vsi]) - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true); + i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); return err; } @@ -5880,7 +7000,7 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired) wr32(&pf->hw, I40E_GLGEN_RTRIG, val); i40e_flush(&pf->hw); - } else if (reset_flags & BIT_ULL(__I40E_PF_RESET_REQUESTED)) { + } else if (reset_flags & I40E_PF_RESET_FLAG) { /* Request a PF Reset * @@ -6231,6 +7351,7 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf) hlist_del(&filter->fdir_node); kfree(filter); pf->fdir_pf_active_filters--; + pf->fd_inv = 0; } } } @@ -6557,12 +7678,26 @@ static void i40e_handle_link_event(struct i40e_pf *pf, */ i40e_link_event(pf); - /* check for unqualified module, if link is down */ - if ((status->link_info & I40E_AQ_MEDIA_AVAILABLE) && - (!(status->an_info & I40E_AQ_QUALIFIED_MODULE)) && - (!(status->link_info & I40E_AQ_LINK_UP))) + /* Check if module meets thermal requirements */ + if (status->phy_type == I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP) { dev_err(&pf->pdev->dev, - "The driver failed to link because an unqualified module was detected.\n"); + "Rx/Tx is disabled on this device because the module does not meet thermal requirements.\n"); + dev_err(&pf->pdev->dev, + "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n"); + } else { + /* check for unqualified module, if link is down, suppress + * the message if link was forced to be down. + */ + if ((status->link_info & I40E_AQ_MEDIA_AVAILABLE) && + (!(status->an_info & I40E_AQ_QUALIFIED_MODULE)) && + (!(status->link_info & I40E_AQ_LINK_UP)) && + (!(pf->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED))) { + dev_err(&pf->pdev->dev, + "Rx/Tx is disabled on this device because an unsupported SFP module type was detected.\n"); + dev_err(&pf->pdev->dev, + "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n"); + } + } } /** @@ -7021,6 +8156,49 @@ static void i40e_fdir_teardown(struct i40e_pf *pf) } /** + * i40e_rebuild_channels - Rebuilds channel VSIs if they existed before reset + * @vsi: PF main vsi + * + * Rebuilds channel VSIs if they existed before reset + **/ +static int i40e_rebuild_channels(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch, *ch_tmp; + i40e_status ret; + + if (list_empty(&vsi->ch_list)) + return 0; + + list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { + if (!ch->initialized) + break; + /* Proceed with creation of channel (VMDq2) VSI */ + ret = i40e_add_channel(vsi->back, vsi->uplink_seid, ch); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "failed to rebuild channels using uplink_seid %u\n", + vsi->uplink_seid); + return ret; + } + if (ch->max_tx_rate) { + u64 credits = ch->max_tx_rate; + + if (i40e_set_bw_limit(vsi, ch->seid, + ch->max_tx_rate)) + return -EINVAL; + + do_div(credits, I40E_BW_CREDIT_DIVISOR); + dev_dbg(&vsi->back->pdev->dev, + "Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n", + ch->max_tx_rate, + credits, + ch->seid); + } + } + return 0; +} + +/** * i40e_prep_for_reset - prep for the core to reset * @pf: board private structure * @lock_acquired: indicates whether or not the lock has been acquired @@ -7156,6 +8334,7 @@ static int i40e_reset(struct i40e_pf *pf) **/ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) { + struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; struct i40e_hw *hw = &pf->hw; u8 set_fc_aq_fail = 0; i40e_status ret; @@ -7238,7 +8417,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) * If there were VEBs but the reconstitution failed, we'll try * try to recover minimal use by getting the basic PF VSI working. */ - if (pf->vsi[pf->lan_vsi]->uplink_seid != pf->mac_seid) { + if (vsi->uplink_seid != pf->mac_seid) { dev_dbg(&pf->pdev->dev, "attempting to rebuild switch\n"); /* find the one VEB connected to the MAC, and find orphans */ for (v = 0; v < I40E_MAX_VEB; v++) { @@ -7262,8 +8441,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) dev_info(&pf->pdev->dev, "rebuild of switch failed: %d, will try to set up simple PF connection\n", ret); - pf->vsi[pf->lan_vsi]->uplink_seid - = pf->mac_seid; + vsi->uplink_seid = pf->mac_seid; break; } else if (pf->veb[v]->uplink_seid == 0) { dev_info(&pf->pdev->dev, @@ -7274,10 +8452,10 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } } - if (pf->vsi[pf->lan_vsi]->uplink_seid == pf->mac_seid) { + if (vsi->uplink_seid == pf->mac_seid) { dev_dbg(&pf->pdev->dev, "attempting to rebuild PF VSI\n"); /* no VEB, so rebuild only the Main VSI */ - ret = i40e_add_vsi(pf->vsi[pf->lan_vsi]); + ret = i40e_add_vsi(vsi); if (ret) { dev_info(&pf->pdev->dev, "rebuild of Main VSI failed: %d\n", ret); @@ -7285,6 +8463,31 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } } + if (vsi->mqprio_qopt.max_rate[0]) { + u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0]; + u64 credits = 0; + + do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR); + ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); + if (ret) + goto end_unlock; + + credits = max_tx_rate; + do_div(credits, I40E_BW_CREDIT_DIVISOR); + dev_dbg(&vsi->back->pdev->dev, + "Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n", + max_tx_rate, + credits, + vsi->seid); + } + + /* PF Main VSI is rebuild by now, go ahead and rebuild channel VSIs + * for this main VSI if they exist + */ + ret = i40e_rebuild_channels(vsi); + if (ret) + goto end_unlock; + /* Reconfigure hardware for allowing smaller MSS in the case * of TSO, so that we avoid the MDD being fired and causing * a reset in the case of small MSS+TSO. @@ -7619,9 +8822,9 @@ static void i40e_service_task(struct work_struct *work) * i40e_service_timer - timer callback * @data: pointer to PF struct **/ -static void i40e_service_timer(unsigned long data) +static void i40e_service_timer(struct timer_list *t) { - struct i40e_pf *pf = (struct i40e_pf *)data; + struct i40e_pf *pf = from_timer(pf, t, service_timer); mod_timer(&pf->service_timer, round_jiffies(jiffies + pf->service_timer_period)); @@ -7678,7 +8881,7 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi) /** * i40e_vsi_alloc_arrays - Allocate queue and vector pointer arrays for the vsi - * @type: VSI pointer + * @vsi: VSI pointer * @alloc_qvectors: a bool to specify if q_vectors need to be allocated. * * On error: returns error code (negative) @@ -8439,51 +9642,12 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf) i40e_flush(hw); - i40e_irq_dynamic_enable_icr0(pf, true); + i40e_irq_dynamic_enable_icr0(pf); return err; } /** - * i40e_config_rss_aq - Prepare for RSS using AQ commands - * @vsi: vsi structure - * @seed: RSS hash seed - **/ -static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed, - u8 *lut, u16 lut_size) -{ - struct i40e_pf *pf = vsi->back; - struct i40e_hw *hw = &pf->hw; - int ret = 0; - - if (seed) { - struct i40e_aqc_get_set_rss_key_data *seed_dw = - (struct i40e_aqc_get_set_rss_key_data *)seed; - ret = i40e_aq_set_rss_key(hw, vsi->id, seed_dw); - if (ret) { - dev_info(&pf->pdev->dev, - "Cannot set RSS key, err %s aq_err %s\n", - i40e_stat_str(hw, ret), - i40e_aq_str(hw, hw->aq.asq_last_status)); - return ret; - } - } - if (lut) { - bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false; - - ret = i40e_aq_set_rss_lut(hw, vsi->id, pf_lut, lut, lut_size); - if (ret) { - dev_info(&pf->pdev->dev, - "Cannot set RSS lut, err %s aq_err %s\n", - i40e_stat_str(hw, ret), - i40e_aq_str(hw, hw->aq.asq_last_status)); - return ret; - } - } - return ret; -} - -/** * i40e_get_rss_aq - Get RSS keys and lut by using AQ commands * @vsi: Pointer to vsi structure * @seed: Buffter to store the hash keys @@ -8530,46 +9694,6 @@ static int i40e_get_rss_aq(struct i40e_vsi *vsi, const u8 *seed, } /** - * i40e_vsi_config_rss - Prepare for VSI(VMDq) RSS if used - * @vsi: VSI structure - **/ -static int i40e_vsi_config_rss(struct i40e_vsi *vsi) -{ - u8 seed[I40E_HKEY_ARRAY_SIZE]; - struct i40e_pf *pf = vsi->back; - u8 *lut; - int ret; - - if (!(pf->hw_features & I40E_HW_RSS_AQ_CAPABLE)) - return 0; - - if (!vsi->rss_size) - vsi->rss_size = min_t(int, pf->alloc_rss_size, - vsi->num_queue_pairs); - if (!vsi->rss_size) - return -EINVAL; - - lut = kzalloc(vsi->rss_table_size, GFP_KERNEL); - if (!lut) - return -ENOMEM; - /* Use the user configured hash keys and lookup table if there is one, - * otherwise use default - */ - if (vsi->rss_lut_user) - memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size); - else - i40e_fill_rss_lut(pf, lut, vsi->rss_table_size, vsi->rss_size); - if (vsi->rss_hkey_user) - memcpy(seed, vsi->rss_hkey_user, I40E_HKEY_ARRAY_SIZE); - else - netdev_rss_key_fill((void *)seed, I40E_HKEY_ARRAY_SIZE); - ret = i40e_config_rss_aq(vsi, seed, lut, vsi->rss_table_size); - kfree(lut); - - return ret; -} - -/** * i40e_config_rss_reg - Configure RSS keys and lut by writing registers * @vsi: Pointer to vsi structure * @seed: RSS hash seed @@ -8967,8 +10091,8 @@ static int i40e_sw_init(struct i40e_pf *pf) I40E_FLAG_MSIX_ENABLED; /* Set default ITR */ - pf->rx_itr_default = I40E_ITR_DYNAMIC | I40E_ITR_RX_DEF; - pf->tx_itr_default = I40E_ITR_DYNAMIC | I40E_ITR_TX_DEF; + pf->rx_itr_default = I40E_ITR_RX_DEF; + pf->tx_itr_default = I40E_ITR_TX_DEF; /* Depending on PF configurations, it is possible that the RSS * maximum might end up larger than the available queues @@ -9068,6 +10192,11 @@ static int i40e_sw_init(struct i40e_pf *pf) (pf->hw.aq.fw_maj_ver >= 5))) pf->hw_features |= I40E_HW_USE_SET_LLDP_MIB; + /* Enable PTP L4 if FW > v6.0 */ + if (pf->hw.mac.type == I40E_MAC_XL710 && + pf->hw.aq.fw_maj_ver >= 6) + pf->hw_features |= I40E_HW_PTP_L4_CAPABLE; + if (pf->hw.func_caps.vmdq) { pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI; pf->flags |= I40E_FLAG_VMDQ_ENABLED; @@ -9208,7 +10337,7 @@ static int i40e_set_features(struct net_device *netdev, need_reset = i40e_set_ntuple(pf, features); if (need_reset) - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true); + i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); return 0; } @@ -9460,8 +10589,7 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; else pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED; - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), - true); + i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); break; } } @@ -9903,6 +11031,31 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) enabled_tc = i40e_pf_get_tc_map(pf); + /* Source pruning is enabled by default, so the flag is + * negative logic - if it's set, we need to fiddle with + * the VSI to disable source pruning. + */ + if (pf->flags & I40E_FLAG_SOURCE_PRUNING_DISABLED) { + memset(&ctxt, 0, sizeof(ctxt)); + ctxt.seid = pf->main_vsi_seid; + ctxt.pf_num = pf->hw.pf_id; + ctxt.vf_num = 0; + ctxt.info.valid_sections |= + cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID); + ctxt.info.switch_id = + cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_LOCAL_LB); + ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL); + if (ret) { + dev_info(&pf->pdev->dev, + "update vsi failed, err %s aq_err %s\n", + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, + pf->hw.aq.asq_last_status)); + ret = -ENOENT; + goto err; + } + } + /* MFP mode setup queue map and update VSI */ if ((pf->flags & I40E_FLAG_MFP_ENABLED) && !(pf->hw.func_caps.iscsi)) { /* NIC type PF */ @@ -11517,7 +12670,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) #endif /* CONFIG_I40E_DCB */ /* set up periodic task facility */ - setup_timer(&pf->service_timer, i40e_service_timer, (unsigned long)pf); + timer_setup(&pf->service_timer, i40e_service_timer, 0); pf->service_timer_period = HZ; INIT_WORK(&pf->service_task, i40e_service_task); @@ -11569,6 +12722,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_info(&pdev->dev, "setup_pf_switch failed: %d\n", err); goto err_vsis; } + INIT_LIST_HEAD(&pf->vsi[pf->lan_vsi]->ch_list); /* Make sure flow control is set according to current settings */ err = i40e_set_fc(hw, &set_fc_aq_fail, true); @@ -11840,7 +12994,7 @@ static void i40e_remove(struct pci_dev *pdev) /* no more scheduling of any task */ set_bit(__I40E_SUSPENDED, pf->state); set_bit(__I40E_DOWN, pf->state); - if (pf->service_timer.data) + if (pf->service_timer.function) del_timer_sync(&pf->service_timer); if (pf->service_task.func) cancel_work_sync(&pf->service_task); @@ -12000,6 +13154,28 @@ static pci_ers_result_t i40e_pci_error_slot_reset(struct pci_dev *pdev) } /** + * i40e_pci_error_reset_prepare - prepare device driver for pci reset + * @pdev: PCI device information struct + */ +static void i40e_pci_error_reset_prepare(struct pci_dev *pdev) +{ + struct i40e_pf *pf = pci_get_drvdata(pdev); + + i40e_prep_for_reset(pf, false); +} + +/** + * i40e_pci_error_reset_done - pci reset done, device driver reset can begin + * @pdev: PCI device information struct + */ +static void i40e_pci_error_reset_done(struct pci_dev *pdev) +{ + struct i40e_pf *pf = pci_get_drvdata(pdev); + + i40e_reset_and_rebuild(pf, false, false); +} + +/** * i40e_pci_error_resume - restart operations after PCI error recovery * @pdev: PCI device information struct * @@ -12189,6 +13365,8 @@ static int i40e_resume(struct device *dev) static const struct pci_error_handlers i40e_err_handler = { .error_detected = i40e_pci_error_detected, .slot_reset = i40e_pci_error_slot_reset, + .reset_prepare = i40e_pci_error_reset_prepare, + .reset_done = i40e_pci_error_reset_done, .resume = i40e_pci_error_resume, }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 57505b1df98d..151d9cfb6ea4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -311,13 +311,10 @@ static i40e_status i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset, static i40e_status __i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, u16 *data) { - i40e_status ret_code = 0; - if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) - ret_code = i40e_read_nvm_word_aq(hw, offset, data); - else - ret_code = i40e_read_nvm_word_srctl(hw, offset, data); - return ret_code; + return i40e_read_nvm_word_aq(hw, offset, data); + + return i40e_read_nvm_word_srctl(hw, offset, data); } /** @@ -331,7 +328,7 @@ static i40e_status __i40e_read_nvm_word(struct i40e_hw *hw, i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, u16 *data) { - i40e_status ret_code = 0; + i40e_status ret_code; ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); if (ret_code) @@ -446,13 +443,10 @@ static i40e_status __i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, u16 *words, u16 *data) { - i40e_status ret_code = 0; - if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) - ret_code = i40e_read_nvm_buffer_aq(hw, offset, words, data); - else - ret_code = i40e_read_nvm_buffer_srctl(hw, offset, words, data); - return ret_code; + return i40e_read_nvm_buffer_aq(hw, offset, words, data); + + return i40e_read_nvm_buffer_srctl(hw, offset, words, data); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h index 86ca27f72f02..c234758dad15 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_register.h +++ b/drivers/net/ethernet/intel/i40e/i40e_register.h @@ -2794,7 +2794,7 @@ #define I40E_GLV_RUPP_MAX_INDEX 383 #define I40E_GLV_RUPP_RUPP_SHIFT 0 #define I40E_GLV_RUPP_RUPP_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_RUPP_RUPP_SHIFT) -#define I40E_GLV_TEPC(_VSI) (0x00344000 + ((_VSI) * 4)) /* _i=0...383 */ /* Reset: CORER */ +#define I40E_GLV_TEPC(_i) (0x00344000 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */ #define I40E_GLV_TEPC_MAX_INDEX 383 #define I40E_GLV_TEPC_TEPC_SHIFT 0 #define I40E_GLV_TEPC_TEPC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_TEPC_TEPC_SHIFT) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index d9fdf69bbc6e..a23306f04e00 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1372,6 +1372,15 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) union i40e_rx_desc *rx_desc; struct i40e_rx_buffer *bi; + /* Hardware only fetches new descriptors in cache lines of 8, + * essentially ignoring the lower 3 bits of the tail register. We want + * to ensure our tail writes are aligned to avoid unnecessary work. We + * can't simply round down the cleaned count, since we might fail to + * allocate some buffers. What we really want is to ensure that + * next_to_used + cleaned_count produces an aligned value. + */ + cleaned_count -= (ntu + cleaned_count) & 0x7; + /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) return false; @@ -2202,9 +2211,7 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr) u32 val; val = I40E_PFINT_DYN_CTLN_INTENA_MASK | - /* Don't clear PBA because that can cause lost interrupts that - * came in while we were cleaning/polling - */ + I40E_PFINT_DYN_CTLN_CLEARPBA_MASK | (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) | (itr << I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT); @@ -2241,7 +2248,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, /* If we don't have MSIX, then we only need to re-enable icr0 */ if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) { - i40e_irq_dynamic_enable_icr0(vsi->back, false); + i40e_irq_dynamic_enable_icr0(vsi->back); return; } @@ -3167,38 +3174,12 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, /* write last descriptor with EOP bit */ td_cmd |= I40E_TX_DESC_CMD_EOP; - /* We can OR these values together as they both are checked against - * 4 below and at this point desc_count will be used as a boolean value - * after this if/else block. + /* We OR these values together to check both against 4 (WB_STRIDE) + * below. This is safe since we don't re-use desc_count afterwards. */ desc_count |= ++tx_ring->packet_stride; - /* Algorithm to optimize tail and RS bit setting: - * if queue is stopped - * mark RS bit - * reset packet counter - * else if xmit_more is supported and is true - * advance packet counter to 4 - * reset desc_count to 0 - * - * if desc_count >= 4 - * mark RS bit - * reset packet counter - * if desc_count > 0 - * update tail - * - * Note: If there are less than 4 descriptors - * pending and interrupts were disabled the service task will - * trigger a force WB. - */ - if (netif_xmit_stopped(txring_txq(tx_ring))) { - goto do_rs; - } else if (skb->xmit_more) { - /* set stride to arm on next packet and reset desc_count */ - tx_ring->packet_stride = WB_STRIDE; - desc_count = 0; - } else if (desc_count >= WB_STRIDE) { -do_rs: + if (desc_count >= WB_STRIDE) { /* write last descriptor with RS bit set */ td_cmd |= I40E_TX_DESC_CMD_RS; tx_ring->packet_stride = 0; @@ -3219,7 +3200,7 @@ do_rs: first->next_to_watch = tx_desc; /* notify HW of packet */ - if (desc_count) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { writel(i, tx_ring->tail); /* we need this if more than one processor can write to our tail diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 2f848bc5e391..fbae1182e2ea 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -38,8 +38,10 @@ #define I40E_ITR_8K 0x003E #define I40E_ITR_4K 0x007A #define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ -#define I40E_ITR_RX_DEF I40E_ITR_20K -#define I40E_ITR_TX_DEF I40E_ITR_20K +#define I40E_ITR_RX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ + I40E_ITR_DYNAMIC) +#define I40E_ITR_TX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ + I40E_ITR_DYNAMIC) #define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ #define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */ #define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */ @@ -206,7 +208,7 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, } /* How many Rx Buffers do we bundle into one write to the hardware ? */ -#define I40E_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define I40E_RX_BUFFER_WRITE 32 /* Must be power of 2 */ #define I40E_RX_INCREMENT(r, i) \ do { \ (i)++; \ @@ -342,6 +344,7 @@ struct i40e_rx_queue_stats { enum i40e_ring_state_t { __I40E_TX_FDIR_INIT_DONE, __I40E_TX_XPS_INIT_DONE, + __I40E_RING_STATE_NBITS /* must be last */ }; /* some useful defines for virtchannel interface, which @@ -366,7 +369,7 @@ struct i40e_ring { struct i40e_tx_buffer *tx_bi; struct i40e_rx_buffer *rx_bi; }; - unsigned long state; + DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS); u16 queue_index; /* Queue number of ring */ u8 dcb_tc; /* Traffic class of ring */ u8 __iomem *tail; @@ -423,6 +426,8 @@ struct i40e_ring { * i40e_clean_rx_ring_irq() is called * for this ring. */ + + struct i40e_channel *ch; } ____cacheline_internodealigned_in_smp; static inline bool ring_uses_build_skb(struct i40e_ring *ring) diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 4b32b1d38a66..17a99b53acd9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -46,6 +46,9 @@ /* Max default timeout in ms, */ #define I40E_MAX_NVM_TIMEOUT 18000 +/* Max timeout in ms for the phy to respond */ +#define I40E_MAX_PHY_TIMEOUT 500 + /* Switch from ms to the 1usec global time (this is the GTIME resolution) */ #define I40E_MS_TO_GTIME(time) ((time) * 1000) @@ -268,6 +271,10 @@ struct i40e_phy_info { I40E_PHY_TYPE_OFFSET) #define I40E_CAP_PHY_TYPE_25GBASE_LR BIT_ULL(I40E_PHY_TYPE_25GBASE_LR + \ I40E_PHY_TYPE_OFFSET) +#define I40E_CAP_PHY_TYPE_25GBASE_AOC BIT_ULL(I40E_PHY_TYPE_25GBASE_AOC + \ + I40E_PHY_TYPE_OFFSET) +#define I40E_CAP_PHY_TYPE_25GBASE_ACC BIT_ULL(I40E_PHY_TYPE_25GBASE_ACC + \ + I40E_PHY_TYPE_OFFSET) #define I40E_HW_CAP_MAX_GPIO 30 /* Capabilities of a PF or a VF or the whole device */ struct i40e_hw_capabilities { diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 04568137e029..f8a794b72462 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -273,7 +273,7 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, struct i40e_hw *hw = &pf->hw; u16 vsi_queue_id, pf_queue_id; enum i40e_queue_type qtype; - u16 next_q, vector_id; + u16 next_q, vector_id, size; u32 reg, reg_idx; u16 itr_idx = 0; @@ -303,9 +303,11 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, vsi_queue_id + 1)); } - next_q = find_first_bit(&linklistmap, - (I40E_MAX_VSI_QP * - I40E_VIRTCHNL_SUPPORTED_QTYPES)); + size = I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES; + next_q = find_first_bit(&linklistmap, size); + if (unlikely(next_q == size)) + goto irq_list_done; + vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES; qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES; pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id); @@ -313,7 +315,7 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, wr32(hw, reg_idx, reg); - while (next_q < (I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES)) { + while (next_q < size) { switch (qtype) { case I40E_QUEUE_TYPE_RX: reg_idx = I40E_QINT_RQCTL(pf_queue_id); @@ -327,12 +329,8 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, break; } - next_q = find_next_bit(&linklistmap, - (I40E_MAX_VSI_QP * - I40E_VIRTCHNL_SUPPORTED_QTYPES), - next_q + 1); - if (next_q < - (I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES)) { + next_q = find_next_bit(&linklistmap, size, next_q + 1); + if (next_q < size) { vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES; qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES; pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, @@ -639,7 +637,7 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id, rx_ctx.dsize = 1; /* default values */ - rx_ctx.lrxqthresh = 2; + rx_ctx.lrxqthresh = 1; rx_ctx.crcstrip = 1; rx_ctx.prefena = 1; rx_ctx.l2tsel = 1; @@ -1358,7 +1356,7 @@ err_alloc: i40e_free_vfs(pf); err_iov: /* Re-enable interrupt 0. */ - i40e_irq_dynamic_enable_icr0(pf, false); + i40e_irq_dynamic_enable_icr0(pf); return ret; } @@ -1427,8 +1425,7 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs) if (num_vfs) { if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; - i40e_do_reset_safe(pf, - BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } return i40e_pci_sriov_enable(pdev, num_vfs); } @@ -1436,7 +1433,7 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs) if (!pci_vfs_assigned(pf->pdev)) { i40e_free_vfs(pf); pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED; - i40e_do_reset_safe(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } else { dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs.\n"); return -EINVAL; @@ -2048,8 +2045,9 @@ error_param: * @msglen: msg length * * VFs get a default number of queues but can use this message to request a - * different number. Will respond with either the number requested or the - * maximum we can support. + * different number. If the request is successful, PF will reset the VF and + * return 0. If unsuccessful, PF will send message informing VF of number of + * available queues and return result of sending VF a message. **/ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg, int msglen) { @@ -2080,7 +2078,11 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg, int msglen) pf->queues_left); vfres->num_queue_pairs = pf->queues_left + cur_pairs; } else { + /* successful request */ vf->num_req_queues = req_pairs; + i40e_vc_notify_vf_reset(vf); + i40e_reset_vf(vf, false); + return 0; } return i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES, 0, @@ -2883,6 +2885,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) struct i40e_mac_filter *f; struct i40e_vf *vf; int ret = 0; + struct hlist_node *h; int bkt; /* validate the request */ @@ -2921,7 +2924,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) /* Delete all the filters for this VSI - we're going to kill it * anyway. */ - hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) __i40e_del_filter(vsi, f); spin_unlock_bh(&vsi->mac_filter_hash_lock); @@ -3119,8 +3122,6 @@ error_pvid: return ret; } -#define I40E_BW_CREDIT_DIVISOR 50 /* 50Mbps per BW credit */ -#define I40E_MAX_BW_INACTIVE_ACCUM 4 /* device can accumulate 4 credits max */ /** * i40e_ndo_set_vf_bw * @netdev: network interface device structure @@ -3136,7 +3137,6 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, struct i40e_pf *pf = np->vsi->back; struct i40e_vsi *vsi; struct i40e_vf *vf; - int speed = 0; int ret = 0; /* validate the request */ @@ -3161,48 +3161,10 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, goto error; } - switch (pf->hw.phy.link_info.link_speed) { - case I40E_LINK_SPEED_40GB: - speed = 40000; - break; - case I40E_LINK_SPEED_25GB: - speed = 25000; - break; - case I40E_LINK_SPEED_20GB: - speed = 20000; - break; - case I40E_LINK_SPEED_10GB: - speed = 10000; - break; - case I40E_LINK_SPEED_1GB: - speed = 1000; - break; - default: - break; - } - - if (max_tx_rate > speed) { - dev_err(&pf->pdev->dev, "Invalid max tx rate %d specified for VF %d.\n", - max_tx_rate, vf->vf_id); - ret = -EINVAL; + ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); + if (ret) goto error; - } - - if ((max_tx_rate < 50) && (max_tx_rate > 0)) { - dev_warn(&pf->pdev->dev, "Setting max Tx rate to minimum usable value of 50Mbps.\n"); - max_tx_rate = 50; - } - /* Tx rate credits are in values of 50Mbps, 0 is disabled*/ - ret = i40e_aq_config_vsi_bw_limit(&pf->hw, vsi->seid, - max_tx_rate / I40E_BW_CREDIT_DIVISOR, - I40E_MAX_BW_INACTIVE_ACCUM, NULL); - if (ret) { - dev_err(&pf->pdev->dev, "Unable to set max tx rate, error code %d.\n", - ret); - ret = -EIO; - goto error; - } vf->tx_rate = max_tx_rate; error: return ret; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index ed5602f4bbcd..463e331a70a9 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -1767,9 +1767,12 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_25GBASE_CR = 0x20, I40E_PHY_TYPE_25GBASE_SR = 0x21, I40E_PHY_TYPE_25GBASE_LR = 0x22, + I40E_PHY_TYPE_25GBASE_AOC = 0x23, + I40E_PHY_TYPE_25GBASE_ACC = 0x24, + I40E_PHY_TYPE_MAX, + I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD, I40E_PHY_TYPE_EMPTY = 0xFE, I40E_PHY_TYPE_DEFAULT = 0xFF, - I40E_PHY_TYPE_MAX }; #define I40E_LINK_SPEED_100MB_SHIFT 0x1 @@ -1826,6 +1829,8 @@ struct i40e_aq_get_phy_abilities_resp { #define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02 #define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04 #define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08 +#define I40E_AQ_PHY_TYPE_EXT_25G_AOC 0x10 +#define I40E_AQ_PHY_TYPE_EXT_25G_ACC 0x20 u8 fec_cfg_curr_mod_ext_info; #define I40E_AQ_ENABLE_FEC_KR 0x01 #define I40E_AQ_ENABLE_FEC_RS 0x02 diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 37e1de886d48..6806ada11490 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -711,6 +711,15 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) union i40e_rx_desc *rx_desc; struct i40e_rx_buffer *bi; + /* Hardware only fetches new descriptors in cache lines of 8, + * essentially ignoring the lower 3 bits of the tail register. We want + * to ensure our tail writes are aligned to avoid unnecessary work. We + * can't simply round down the cleaned count, since we might fail to + * allocate some buffers. What we really want is to ensure that + * next_to_used + cleaned_count produces an aligned value. + */ + cleaned_count -= (ntu + cleaned_count) & 0x7; + /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) return false; @@ -1409,9 +1418,7 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr) u32 val; val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - /* Don't clear PBA because that can cause lost interrupts that - * came in while we were cleaning/polling - */ + I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK | (type << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | (itr << I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 0d9f98bc07bd..8d26c85d12e1 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -38,8 +38,10 @@ #define I40E_ITR_8K 0x003E #define I40E_ITR_4K 0x007A #define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ -#define I40E_ITR_RX_DEF I40E_ITR_20K -#define I40E_ITR_TX_DEF I40E_ITR_20K +#define I40E_ITR_RX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ + I40E_ITR_DYNAMIC) +#define I40E_ITR_TX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ + I40E_ITR_DYNAMIC) #define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ #define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */ #define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */ @@ -189,7 +191,7 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, } /* How many Rx Buffers do we bundle into one write to the hardware ? */ -#define I40E_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define I40E_RX_BUFFER_WRITE 32 /* Must be power of 2 */ #define I40E_RX_INCREMENT(r, i) \ do { \ (i)++; \ @@ -325,6 +327,7 @@ struct i40e_rx_queue_stats { enum i40e_ring_state_t { __I40E_TX_FDIR_INIT_DONE, __I40E_TX_XPS_INIT_DONE, + __I40E_RING_STATE_NBITS /* must be last */ }; /* some useful defines for virtchannel interface, which @@ -348,7 +351,7 @@ struct i40e_ring { struct i40e_tx_buffer *tx_bi; struct i40e_rx_buffer *rx_bi; }; - unsigned long state; + DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS); u16 queue_index; /* Queue number of ring */ u8 dcb_tc; /* Traffic class of ring */ u8 __iomem *tail; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index 9364b67fff9c..213b773dfad6 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -46,6 +46,9 @@ /* Max default timeout in ms, */ #define I40E_MAX_NVM_TIMEOUT 18000 +/* Max timeout in ms for the phy to respond */ +#define I40E_MAX_PHY_TIMEOUT 500 + /* Switch from ms to the 1usec global time (this is the GTIME resolution) */ #define I40E_MS_TO_GTIME(time) ((time) * 1000) diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 5982362c5643..de0af521d602 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -222,22 +222,22 @@ struct i40evf_adapter { u32 flags; #define I40EVF_FLAG_RX_CSUM_ENABLED BIT(0) -#define I40EVF_FLAG_IMIR_ENABLED BIT(5) -#define I40EVF_FLAG_MQ_CAPABLE BIT(6) -#define I40EVF_FLAG_PF_COMMS_FAILED BIT(8) -#define I40EVF_FLAG_RESET_PENDING BIT(9) -#define I40EVF_FLAG_RESET_NEEDED BIT(10) -#define I40EVF_FLAG_WB_ON_ITR_CAPABLE BIT(11) -#define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE BIT(12) -#define I40EVF_FLAG_ADDR_SET_BY_PF BIT(13) -#define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(14) -#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(15) -#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(16) -#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(17) -#define I40EVF_FLAG_PROMISC_ON BIT(18) -#define I40EVF_FLAG_ALLMULTI_ON BIT(19) -#define I40EVF_FLAG_LEGACY_RX BIT(20) -#define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(21) +#define I40EVF_FLAG_IMIR_ENABLED BIT(1) +#define I40EVF_FLAG_MQ_CAPABLE BIT(2) +#define I40EVF_FLAG_PF_COMMS_FAILED BIT(3) +#define I40EVF_FLAG_RESET_PENDING BIT(4) +#define I40EVF_FLAG_RESET_NEEDED BIT(5) +#define I40EVF_FLAG_WB_ON_ITR_CAPABLE BIT(6) +#define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE BIT(7) +#define I40EVF_FLAG_ADDR_SET_BY_PF BIT(8) +#define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(9) +#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(10) +#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(11) +#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(12) +#define I40EVF_FLAG_PROMISC_ON BIT(13) +#define I40EVF_FLAG_ALLMULTI_ON BIT(14) +#define I40EVF_FLAG_LEGACY_RX BIT(15) +#define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(16) /* duplicates for common code */ #define I40E_FLAG_DCB_ENABLED 0 #define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index f2f1e754c2ce..ca2ebdbd24d7 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -515,6 +515,7 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) unsigned int vector, q_vectors; unsigned int rx_int_idx = 0, tx_int_idx = 0; int irq_num, err; + int cpu; i40evf_irq_disable(adapter); /* Decrement for Other and TCP Timer vectors */ @@ -553,10 +554,12 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) q_vector->affinity_notify.release = i40evf_irq_affinity_release; irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); - /* get_cpu_mask returns a static constant mask with - * a permanent lifetime so it's ok to use here. + /* Spread the IRQ affinity hints across online CPUs. Note that + * get_cpu_mask returns a mask with a permanent lifetime so + * it's safe to use as a hint for irq_set_affinity_hint. */ - irq_set_affinity_hint(irq_num, get_cpu_mask(q_vector->v_idx)); + cpu = cpumask_local_spread(q_vector->v_idx, -1); + irq_set_affinity_hint(irq_num, get_cpu_mask(cpu)); } return 0; @@ -877,6 +880,8 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, list_add_tail(&f->list, &adapter->mac_filter_list); f->add = true; adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER; + } else { + f->remove = false; } clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); @@ -1218,7 +1223,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) tx_ring->netdev = adapter->netdev; tx_ring->dev = &adapter->pdev->dev; tx_ring->count = adapter->tx_desc_count; - tx_ring->tx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_TX_DEF); + tx_ring->tx_itr_setting = I40E_ITR_TX_DEF; if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE) tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR; @@ -1227,7 +1232,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) rx_ring->netdev = adapter->netdev; rx_ring->dev = &adapter->pdev->dev; rx_ring->count = adapter->rx_desc_count; - rx_ring->rx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_RX_DEF); + rx_ring->rx_itr_setting = I40E_ITR_RX_DEF; } adapter->num_active_queues = num_active_queues; @@ -1589,9 +1594,10 @@ err: * i40evf_watchdog_timer - Periodic call-back timer * @data: pointer to adapter disguised as unsigned long **/ -static void i40evf_watchdog_timer(unsigned long data) +static void i40evf_watchdog_timer(struct timer_list *t) { - struct i40evf_adapter *adapter = (struct i40evf_adapter *)data; + struct i40evf_adapter *adapter = from_timer(adapter, t, + watchdog_timer); schedule_work(&adapter->watchdog_task); /* timer will be rescheduled in watchdog task */ @@ -2420,10 +2426,6 @@ out_err: return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } -#define I40EVF_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_TX |\ - NETIF_F_HW_VLAN_CTAG_RX |\ - NETIF_F_HW_VLAN_CTAG_FILTER) - /** * i40evf_fix_features - fix up the netdev feature bits * @netdev: our net device @@ -2436,9 +2438,11 @@ static netdev_features_t i40evf_fix_features(struct net_device *netdev, { struct i40evf_adapter *adapter = netdev_priv(netdev); - features &= ~I40EVF_VLAN_FEATURES; - if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) - features |= I40EVF_VLAN_FEATURES; + if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)) + features &= ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER); + return features; } @@ -2569,9 +2573,17 @@ int i40evf_process_config(struct i40evf_adapter *adapter) */ hw_features = hw_enc_features; + /* Enable VLAN features if supported */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) + hw_features |= (NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX); + netdev->hw_features |= hw_features; - netdev->features |= hw_features | I40EVF_VLAN_FEATURES; + netdev->features |= hw_features; + + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) + netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; adapter->vsi.id = adapter->vsi_res->vsi_id; @@ -2737,8 +2749,7 @@ static void i40evf_init_task(struct work_struct *work) ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } - setup_timer(&adapter->watchdog_timer, &i40evf_watchdog_timer, - (unsigned long)adapter); + timer_setup(&adapter->watchdog_timer, i40evf_watchdog_timer, 0); mod_timer(&adapter->watchdog_timer, jiffies + 1); adapter->tx_desc_count = I40EVF_DEFAULT_TXD; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index 2bb81c39d85f..46c8b8a3907c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -407,6 +407,7 @@ int i40evf_request_queues(struct i40evf_adapter *adapter, int num) vfres.num_queue_pairs = num; adapter->current_op = VIRTCHNL_OP_REQUEST_QUEUES; + adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; return i40evf_send_pf_msg(adapter, VIRTCHNL_OP_REQUEST_QUEUES, (u8 *)&vfres, sizeof(vfres)); } @@ -1098,15 +1099,13 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, case VIRTCHNL_OP_REQUEST_QUEUES: { struct virtchnl_vf_res_request *vfres = (struct virtchnl_vf_res_request *)msg; - if (vfres->num_queue_pairs == adapter->num_req_queues) { - adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; - i40evf_schedule_reset(adapter); - } else { + if (vfres->num_queue_pairs != adapter->num_req_queues) { dev_info(&adapter->pdev->dev, "Requested %d queues, PF can support %d\n", adapter->num_req_queues, vfres->num_queue_pairs); adapter->num_req_queues = 0; + adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; } } break; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index fd4a46b03cc8..58d01a211367 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -133,8 +133,8 @@ static void igb_clean_all_rx_rings(struct igb_adapter *); static void igb_clean_tx_ring(struct igb_ring *); static void igb_clean_rx_ring(struct igb_ring *); static void igb_set_rx_mode(struct net_device *); -static void igb_update_phy_info(unsigned long); -static void igb_watchdog(unsigned long); +static void igb_update_phy_info(struct timer_list *); +static void igb_watchdog(struct timer_list *); static void igb_watchdog_task(struct work_struct *); static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, struct net_device *); static void igb_get_stats64(struct net_device *dev, @@ -2538,10 +2538,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) wr32(E1000_TXPBS, I210_TXPBSIZE_DEFAULT); } - setup_timer(&adapter->watchdog_timer, igb_watchdog, - (unsigned long) adapter); - setup_timer(&adapter->phy_info_timer, igb_update_phy_info, - (unsigned long) adapter); + timer_setup(&adapter->watchdog_timer, igb_watchdog, 0); + timer_setup(&adapter->phy_info_timer, igb_update_phy_info, 0); INIT_WORK(&adapter->reset_task, igb_reset_task); INIT_WORK(&adapter->watchdog_task, igb_watchdog_task); @@ -3162,6 +3160,8 @@ static int igb_sw_init(struct igb_adapter *adapter) /* Setup and initialize a copy of the hw vlan table array */ adapter->shadow_vfta = kcalloc(E1000_VLAN_FILTER_TBL_SIZE, sizeof(u32), GFP_ATOMIC); + if (!adapter->shadow_vfta) + return -ENOMEM; /* This call may decrease the number of queues */ if (igb_init_interrupt_scheme(adapter, true)) { @@ -4423,9 +4423,9 @@ static void igb_spoof_check(struct igb_adapter *adapter) /* Need to wait a few seconds after link up to get diagnostic information from * the phy */ -static void igb_update_phy_info(unsigned long data) +static void igb_update_phy_info(struct timer_list *t) { - struct igb_adapter *adapter = (struct igb_adapter *) data; + struct igb_adapter *adapter = from_timer(adapter, t, phy_info_timer); igb_get_phy_info(&adapter->hw); } @@ -4512,9 +4512,9 @@ static void igb_check_lvmmc(struct igb_adapter *adapter) * igb_watchdog - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void igb_watchdog(unsigned long data) +static void igb_watchdog(struct timer_list *t) { - struct igb_adapter *adapter = (struct igb_adapter *)data; + struct igb_adapter *adapter = from_timer(adapter, t, watchdog_timer); /* Do the rest outside of interrupt context */ schedule_work(&adapter->watchdog_task); } diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 1ed556911b14..713e8df23744 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1915,9 +1915,9 @@ static bool igbvf_has_link(struct igbvf_adapter *adapter) * igbvf_watchdog - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void igbvf_watchdog(unsigned long data) +static void igbvf_watchdog(struct timer_list *t) { - struct igbvf_adapter *adapter = (struct igbvf_adapter *)data; + struct igbvf_adapter *adapter = from_timer(adapter, t, watchdog_timer); /* Do the rest outside of interrupt context */ schedule_work(&adapter->watchdog_task); @@ -2878,8 +2878,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->addr_len); } - setup_timer(&adapter->watchdog_timer, &igbvf_watchdog, - (unsigned long)adapter); + timer_setup(&adapter->watchdog_timer, igbvf_watchdog, 0); INIT_WORK(&adapter->reset_task, igbvf_reset_task); INIT_WORK(&adapter->watchdog_task, igbvf_watchdog_task); diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 1e6ec2277d54..2353c383f0a7 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -83,7 +83,7 @@ static void ixgb_setup_rctl(struct ixgb_adapter *adapter); static void ixgb_clean_tx_ring(struct ixgb_adapter *adapter); static void ixgb_clean_rx_ring(struct ixgb_adapter *adapter); static void ixgb_set_multi(struct net_device *netdev); -static void ixgb_watchdog(unsigned long data); +static void ixgb_watchdog(struct timer_list *t); static netdev_tx_t ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev); static int ixgb_change_mtu(struct net_device *netdev, int new_mtu); @@ -508,8 +508,7 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->part_num = ixgb_get_ee_pba_number(&adapter->hw); - setup_timer(&adapter->watchdog_timer, ixgb_watchdog, - (unsigned long)adapter); + timer_setup(&adapter->watchdog_timer, ixgb_watchdog, 0); INIT_WORK(&adapter->tx_timeout_task, ixgb_tx_timeout_task); @@ -1151,9 +1150,9 @@ alloc_failed: **/ static void -ixgb_watchdog(unsigned long data) +ixgb_watchdog(struct timer_list *t) { - struct ixgb_adapter *adapter = (struct ixgb_adapter *)data; + struct ixgb_adapter *adapter = from_timer(adapter, t, watchdog_timer); struct net_device *netdev = adapter->netdev; struct ixgb_desc_ring *txdr = &adapter->tx_ring; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index dd5578756ae0..468c3555a629 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -275,6 +275,7 @@ struct ixgbe_rx_queue_stats { u64 rsc_count; u64 rsc_flush; u64 non_eop_descs; + u64 alloc_rx_page; u64 alloc_rx_page_failed; u64 alloc_rx_buff_failed; u64 csum_err; @@ -434,8 +435,15 @@ static inline unsigned int ixgbe_rx_pg_order(struct ixgbe_ring *ring) } #define ixgbe_rx_pg_size(_ring) (PAGE_SIZE << ixgbe_rx_pg_order(_ring)) +#define IXGBE_ITR_ADAPTIVE_MIN_INC 2 +#define IXGBE_ITR_ADAPTIVE_MIN_USECS 10 +#define IXGBE_ITR_ADAPTIVE_MAX_USECS 126 +#define IXGBE_ITR_ADAPTIVE_LATENCY 0x80 +#define IXGBE_ITR_ADAPTIVE_BULK 0x00 + struct ixgbe_ring_container { struct ixgbe_ring *ring; /* pointer to linked list of rings */ + unsigned long next_update; /* jiffies value of last update */ unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_packets; /* total packets processed this int */ u16 work_limit; /* total work allowed per interrupt */ @@ -655,6 +663,7 @@ struct ixgbe_adapter { u64 rsc_total_count; u64 rsc_total_flush; u64 non_eop_descs; + u32 alloc_rx_page; u32 alloc_rx_page_failed; u32 alloc_rx_buff_failed; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index 523f9d05a810..8a32eb7d47b9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -175,31 +175,9 @@ static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw) **/ static s32 ixgbe_start_hw_82598(struct ixgbe_hw *hw) { -#ifndef CONFIG_SPARC - u32 regval; - u32 i; -#endif s32 ret_val; ret_val = ixgbe_start_hw_generic(hw); - -#ifndef CONFIG_SPARC - /* Disable relaxed ordering */ - for (i = 0; ((i < hw->mac.max_tx_queues) && - (i < IXGBE_DCA_MAX_QUEUES_82598)); i++) { - regval = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL(i)); - regval &= ~IXGBE_DCA_TXCTRL_DESC_WRO_EN; - IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL(i), regval); - } - - for (i = 0; ((i < hw->mac.max_rx_queues) && - (i < IXGBE_DCA_MAX_QUEUES_82598)); i++) { - regval = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i)); - regval &= ~(IXGBE_DCA_RXCTRL_DATA_WRO_EN | - IXGBE_DCA_RXCTRL_HEAD_WRO_EN); - IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(i), regval); - } -#endif if (ret_val) return ret_val; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 2c19070d2a0b..9bef255f6a18 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -366,25 +366,6 @@ s32 ixgbe_start_hw_gen2(struct ixgbe_hw *hw) } IXGBE_WRITE_FLUSH(hw); -#ifndef CONFIG_ARCH_WANT_RELAX_ORDER - /* Disable relaxed ordering */ - for (i = 0; i < hw->mac.max_tx_queues; i++) { - u32 regval; - - regval = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL_82599(i)); - regval &= ~IXGBE_DCA_TXCTRL_DESC_WRO_EN; - IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL_82599(i), regval); - } - - for (i = 0; i < hw->mac.max_rx_queues; i++) { - u32 regval; - - regval = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i)); - regval &= ~(IXGBE_DCA_RXCTRL_DATA_WRO_EN | - IXGBE_DCA_RXCTRL_HEAD_WRO_EN); - IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(i), regval); - } -#endif return 0; } @@ -3800,10 +3781,10 @@ s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min, fw_cmd.ver_build = build; fw_cmd.ver_sub = sub; fw_cmd.hdr.checksum = 0; - fw_cmd.hdr.checksum = ixgbe_calculate_checksum((u8 *)&fw_cmd, - (FW_CEM_HDR_LEN + fw_cmd.hdr.buf_len)); fw_cmd.pad = 0; fw_cmd.pad2 = 0; + fw_cmd.hdr.checksum = ixgbe_calculate_checksum((u8 *)&fw_cmd, + (FW_CEM_HDR_LEN + fw_cmd.hdr.buf_len)); for (i = 0; i <= FW_CEM_MAX_RETRIES; i++) { ret_val = ixgbe_host_interface_command(hw, &fw_cmd, @@ -4100,8 +4081,8 @@ bool ixgbe_mng_present(struct ixgbe_hw *hw) return false; fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw)); - fwsm &= IXGBE_FWSM_MODE_MASK; - return fwsm == IXGBE_FWSM_FW_MODE_PT; + + return !!(fwsm & IXGBE_FWSM_FW_MODE_PT); } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 72c565712a5f..0aad1c2a3667 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -104,6 +104,7 @@ static const struct ixgbe_stats ixgbe_gstrings_stats[] = { {"tx_flow_control_xoff", IXGBE_STAT(stats.lxofftxc)}, {"rx_flow_control_xoff", IXGBE_STAT(stats.lxoffrxc)}, {"rx_csum_offload_errors", IXGBE_STAT(hw_csum_rx_error)}, + {"alloc_rx_page", IXGBE_STAT(alloc_rx_page)}, {"alloc_rx_page_failed", IXGBE_STAT(alloc_rx_page_failed)}, {"alloc_rx_buff_failed", IXGBE_STAT(alloc_rx_buff_failed)}, {"rx_no_dma_resources", IXGBE_STAT(hw_rx_no_dma_resources)}, @@ -1048,7 +1049,7 @@ static int ixgbe_set_ringparam(struct net_device *netdev, { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_ring *temp_ring; - int i, err = 0; + int i, j, err = 0; u32 new_rx_count, new_tx_count; if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) @@ -1085,8 +1086,8 @@ static int ixgbe_set_ringparam(struct net_device *netdev, } /* allocate temporary buffer to store rings in */ - i = max_t(int, adapter->num_tx_queues, adapter->num_rx_queues); - i = max_t(int, i, adapter->num_xdp_queues); + i = max_t(int, adapter->num_tx_queues + adapter->num_xdp_queues, + adapter->num_rx_queues); temp_ring = vmalloc(i * sizeof(struct ixgbe_ring)); if (!temp_ring) { @@ -1118,8 +1119,8 @@ static int ixgbe_set_ringparam(struct net_device *netdev, } } - for (i = 0; i < adapter->num_xdp_queues; i++) { - memcpy(&temp_ring[i], adapter->xdp_ring[i], + for (j = 0; j < adapter->num_xdp_queues; j++, i++) { + memcpy(&temp_ring[i], adapter->xdp_ring[j], sizeof(struct ixgbe_ring)); temp_ring[i].count = new_tx_count; @@ -1139,10 +1140,10 @@ static int ixgbe_set_ringparam(struct net_device *netdev, memcpy(adapter->tx_ring[i], &temp_ring[i], sizeof(struct ixgbe_ring)); } - for (i = 0; i < adapter->num_xdp_queues; i++) { - ixgbe_free_tx_resources(adapter->xdp_ring[i]); + for (j = 0; j < adapter->num_xdp_queues; j++, i++) { + ixgbe_free_tx_resources(adapter->xdp_ring[j]); - memcpy(adapter->xdp_ring[i], &temp_ring[i], + memcpy(adapter->xdp_ring[j], &temp_ring[i], sizeof(struct ixgbe_ring)); } @@ -1916,8 +1917,6 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, unsigned int size) { union ixgbe_adv_rx_desc *rx_desc; - struct ixgbe_rx_buffer *rx_buffer; - struct ixgbe_tx_buffer *tx_buffer; u16 rx_ntc, tx_ntc, count = 0; /* initialize next to clean and descriptor values */ @@ -1925,7 +1924,38 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, tx_ntc = tx_ring->next_to_clean; rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc); + while (tx_ntc != tx_ring->next_to_use) { + union ixgbe_adv_tx_desc *tx_desc; + struct ixgbe_tx_buffer *tx_buffer; + + tx_desc = IXGBE_TX_DESC(tx_ring, tx_ntc); + + /* if DD is not set transmit has not completed */ + if (!(tx_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD))) + return count; + + /* unmap buffer on Tx side */ + tx_buffer = &tx_ring->tx_buffer_info[tx_ntc]; + + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + /* increment Tx next to clean counter */ + tx_ntc++; + if (tx_ntc == tx_ring->count) + tx_ntc = 0; + } + while (rx_desc->wb.upper.length) { + struct ixgbe_rx_buffer *rx_buffer; + /* check Rx buffer */ rx_buffer = &rx_ring->rx_buffer_info[rx_ntc]; @@ -1938,6 +1968,8 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, /* verify contents of skb */ if (ixgbe_check_lbtest_frame(rx_buffer, size)) count++; + else + break; /* sync Rx buffer for device write */ dma_sync_single_for_device(rx_ring->dev, @@ -1945,26 +1977,10 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, ixgbe_rx_bufsz(rx_ring), DMA_FROM_DEVICE); - /* unmap buffer on Tx side */ - tx_buffer = &tx_ring->tx_buffer_info[tx_ntc]; - - /* Free all the Tx ring sk_buffs */ - dev_kfree_skb_any(tx_buffer->skb); - - /* unmap skb header data */ - dma_unmap_single(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - dma_unmap_len_set(tx_buffer, len, 0); - - /* increment Rx/Tx next to clean counters */ + /* increment Rx next to clean counter */ rx_ntc++; if (rx_ntc == rx_ring->count) rx_ntc = 0; - tx_ntc++; - if (tx_ntc == tx_ring->count) - tx_ntc = 0; /* fetch next descriptor */ rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index f1bfae0c41d0..8e2a957aca18 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -806,6 +806,7 @@ static void ixgbe_add_ring(struct ixgbe_ring *ring, ring->next = head->ring; head->ring = ring; head->count++; + head->next_update = jiffies + 1; } /** @@ -879,8 +880,11 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, /* initialize work limits */ q_vector->tx.work_limit = adapter->tx_work_limit; - /* initialize pointer to rings */ - ring = q_vector->ring; + /* Initialize setting for adaptive ITR */ + q_vector->tx.itr = IXGBE_ITR_ADAPTIVE_MAX_USECS | + IXGBE_ITR_ADAPTIVE_LATENCY; + q_vector->rx.itr = IXGBE_ITR_ADAPTIVE_MAX_USECS | + IXGBE_ITR_ADAPTIVE_LATENCY; /* intialize ITR */ if (txr_count && !rxr_count) { @@ -897,6 +901,9 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, q_vector->itr = adapter->rx_itr_setting; } + /* initialize pointer to rings */ + ring = q_vector->ring; + while (txr_count) { /* assign generic ring traits */ ring->dev = &adapter->pdev->dev; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 3942c6208745..3e83edd10e23 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1620,6 +1620,7 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring, bi->page = page; bi->page_offset = ixgbe_rx_offset(rx_ring); bi->pagecnt_bias = 1; + rx_ring->rx_stats.alloc_rx_page++; return true; } @@ -2539,50 +2540,174 @@ enum latency_range { static void ixgbe_update_itr(struct ixgbe_q_vector *q_vector, struct ixgbe_ring_container *ring_container) { - int bytes = ring_container->total_bytes; - int packets = ring_container->total_packets; - u32 timepassed_us; - u64 bytes_perint; - u8 itr_setting = ring_container->itr; + unsigned int itr = IXGBE_ITR_ADAPTIVE_MIN_USECS | + IXGBE_ITR_ADAPTIVE_LATENCY; + unsigned int avg_wire_size, packets, bytes; + unsigned long next_update = jiffies; - if (packets == 0) + /* If we don't have any rings just leave ourselves set for maximum + * possible latency so we take ourselves out of the equation. + */ + if (!ring_container->ring) return; - /* simple throttlerate management - * 0-10MB/s lowest (100000 ints/s) - * 10-20MB/s low (20000 ints/s) - * 20-1249MB/s bulk (12000 ints/s) + /* If we didn't update within up to 1 - 2 jiffies we can assume + * that either packets are coming in so slow there hasn't been + * any work, or that there is so much work that NAPI is dealing + * with interrupt moderation and we don't need to do anything. */ - /* what was last interrupt timeslice? */ - timepassed_us = q_vector->itr >> 2; - if (timepassed_us == 0) - return; + if (time_after(next_update, ring_container->next_update)) + goto clear_counts; - bytes_perint = bytes / timepassed_us; /* bytes/usec */ + packets = ring_container->total_packets; - switch (itr_setting) { - case lowest_latency: - if (bytes_perint > 10) - itr_setting = low_latency; - break; - case low_latency: - if (bytes_perint > 20) - itr_setting = bulk_latency; - else if (bytes_perint <= 10) - itr_setting = lowest_latency; + /* We have no packets to actually measure against. This means + * either one of the other queues on this vector is active or + * we are a Tx queue doing TSO with too high of an interrupt rate. + * + * When this occurs just tick up our delay by the minimum value + * and hope that this extra delay will prevent us from being called + * without any work on our queue. + */ + if (!packets) { + itr = (q_vector->itr >> 2) + IXGBE_ITR_ADAPTIVE_MIN_INC; + if (itr > IXGBE_ITR_ADAPTIVE_MAX_USECS) + itr = IXGBE_ITR_ADAPTIVE_MAX_USECS; + itr += ring_container->itr & IXGBE_ITR_ADAPTIVE_LATENCY; + goto clear_counts; + } + + bytes = ring_container->total_bytes; + + /* If packets are less than 4 or bytes are less than 9000 assume + * insufficient data to use bulk rate limiting approach. We are + * likely latency driven. + */ + if (packets < 4 && bytes < 9000) { + itr = IXGBE_ITR_ADAPTIVE_LATENCY; + goto adjust_by_size; + } + + /* Between 4 and 48 we can assume that our current interrupt delay + * is only slightly too low. As such we should increase it by a small + * fixed amount. + */ + if (packets < 48) { + itr = (q_vector->itr >> 2) + IXGBE_ITR_ADAPTIVE_MIN_INC; + if (itr > IXGBE_ITR_ADAPTIVE_MAX_USECS) + itr = IXGBE_ITR_ADAPTIVE_MAX_USECS; + goto clear_counts; + } + + /* Between 48 and 96 is our "goldilocks" zone where we are working + * out "just right". Just report that our current ITR is good for us. + */ + if (packets < 96) { + itr = q_vector->itr >> 2; + goto clear_counts; + } + + /* If packet count is 96 or greater we are likely looking at a slight + * overrun of the delay we want. Try halving our delay to see if that + * will cut the number of packets in half per interrupt. + */ + if (packets < 256) { + itr = q_vector->itr >> 3; + if (itr < IXGBE_ITR_ADAPTIVE_MIN_USECS) + itr = IXGBE_ITR_ADAPTIVE_MIN_USECS; + goto clear_counts; + } + + /* The paths below assume we are dealing with a bulk ITR since number + * of packets is 256 or greater. We are just going to have to compute + * a value and try to bring the count under control, though for smaller + * packet sizes there isn't much we can do as NAPI polling will likely + * be kicking in sooner rather than later. + */ + itr = IXGBE_ITR_ADAPTIVE_BULK; + +adjust_by_size: + /* If packet counts are 256 or greater we can assume we have a gross + * overestimation of what the rate should be. Instead of trying to fine + * tune it just use the formula below to try and dial in an exact value + * give the current packet size of the frame. + */ + avg_wire_size = bytes / packets; + + /* The following is a crude approximation of: + * wmem_default / (size + overhead) = desired_pkts_per_int + * rate / bits_per_byte / (size + ethernet overhead) = pkt_rate + * (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value + * + * Assuming wmem_default is 212992 and overhead is 640 bytes per + * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the + * formula down to + * + * (170 * (size + 24)) / (size + 640) = ITR + * + * We first do some math on the packet size and then finally bitshift + * by 8 after rounding up. We also have to account for PCIe link speed + * difference as ITR scales based on this. + */ + if (avg_wire_size <= 60) { + /* Start at 50k ints/sec */ + avg_wire_size = 5120; + } else if (avg_wire_size <= 316) { + /* 50K ints/sec to 16K ints/sec */ + avg_wire_size *= 40; + avg_wire_size += 2720; + } else if (avg_wire_size <= 1084) { + /* 16K ints/sec to 9.2K ints/sec */ + avg_wire_size *= 15; + avg_wire_size += 11452; + } else if (avg_wire_size <= 1980) { + /* 9.2K ints/sec to 8K ints/sec */ + avg_wire_size *= 5; + avg_wire_size += 22420; + } else { + /* plateau at a limit of 8K ints/sec */ + avg_wire_size = 32256; + } + + /* If we are in low latency mode half our delay which doubles the rate + * to somewhere between 100K to 16K ints/sec + */ + if (itr & IXGBE_ITR_ADAPTIVE_LATENCY) + avg_wire_size >>= 1; + + /* Resultant value is 256 times larger than it needs to be. This + * gives us room to adjust the value as needed to either increase + * or decrease the value based on link speeds of 10G, 2.5G, 1G, etc. + * + * Use addition as we have already recorded the new latency flag + * for the ITR value. + */ + switch (q_vector->adapter->link_speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + case IXGBE_LINK_SPEED_100_FULL: + default: + itr += DIV_ROUND_UP(avg_wire_size, + IXGBE_ITR_ADAPTIVE_MIN_INC * 256) * + IXGBE_ITR_ADAPTIVE_MIN_INC; break; - case bulk_latency: - if (bytes_perint <= 20) - itr_setting = low_latency; + case IXGBE_LINK_SPEED_2_5GB_FULL: + case IXGBE_LINK_SPEED_1GB_FULL: + case IXGBE_LINK_SPEED_10_FULL: + itr += DIV_ROUND_UP(avg_wire_size, + IXGBE_ITR_ADAPTIVE_MIN_INC * 64) * + IXGBE_ITR_ADAPTIVE_MIN_INC; break; } - /* clear work counters since we have the values we need */ +clear_counts: + /* write back value */ + ring_container->itr = itr; + + /* next update should occur within next jiffy */ + ring_container->next_update = next_update + 1; + ring_container->total_bytes = 0; ring_container->total_packets = 0; - - /* write updated itr to ring container */ - ring_container->itr = itr_setting; } /** @@ -2624,34 +2749,19 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector) static void ixgbe_set_itr(struct ixgbe_q_vector *q_vector) { - u32 new_itr = q_vector->itr; - u8 current_itr; + u32 new_itr; ixgbe_update_itr(q_vector, &q_vector->tx); ixgbe_update_itr(q_vector, &q_vector->rx); - current_itr = max(q_vector->rx.itr, q_vector->tx.itr); + /* use the smallest value of new ITR delay calculations */ + new_itr = min(q_vector->rx.itr, q_vector->tx.itr); - switch (current_itr) { - /* counts and packets in update_itr are dependent on these numbers */ - case lowest_latency: - new_itr = IXGBE_100K_ITR; - break; - case low_latency: - new_itr = IXGBE_20K_ITR; - break; - case bulk_latency: - new_itr = IXGBE_12K_ITR; - break; - default: - break; - } + /* Clear latency flag if set, shift into correct position */ + new_itr &= ~IXGBE_ITR_ADAPTIVE_LATENCY; + new_itr <<= 2; if (new_itr != q_vector->itr) { - /* do an exponential smoothing */ - new_itr = (10 * new_itr * q_vector->itr) / - ((9 * new_itr) + q_vector->itr); - /* save the algorithm value here */ q_vector->itr = new_itr; @@ -4904,7 +5014,7 @@ static void ixgbe_clear_udp_tunnel_port(struct ixgbe_adapter *adapter, u32 mask) IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE))) return; - vxlanctrl = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) && ~mask; + vxlanctrl = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) & ~mask; IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, vxlanctrl); if (mask & IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK) @@ -6794,6 +6904,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) u32 i, missed_rx = 0, mpc, bprc, lxon, lxoff, xon_off_tot; u64 non_eop_descs = 0, restart_queue = 0, tx_busy = 0; u64 alloc_rx_page_failed = 0, alloc_rx_buff_failed = 0; + u64 alloc_rx_page = 0; u64 bytes = 0, packets = 0, hw_csum_rx_error = 0; if (test_bit(__IXGBE_DOWN, &adapter->state) || @@ -6814,6 +6925,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_rx_queues; i++) { struct ixgbe_ring *rx_ring = adapter->rx_ring[i]; non_eop_descs += rx_ring->rx_stats.non_eop_descs; + alloc_rx_page += rx_ring->rx_stats.alloc_rx_page; alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed; alloc_rx_buff_failed += rx_ring->rx_stats.alloc_rx_buff_failed; hw_csum_rx_error += rx_ring->rx_stats.csum_err; @@ -6821,6 +6933,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) packets += rx_ring->stats.packets; } adapter->non_eop_descs = non_eop_descs; + adapter->alloc_rx_page = alloc_rx_page; adapter->alloc_rx_page_failed = alloc_rx_page_failed; adapter->alloc_rx_buff_failed = alloc_rx_buff_failed; adapter->hw_csum_rx_error = hw_csum_rx_error; @@ -7577,9 +7690,9 @@ static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter) * ixgbe_service_timer - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void ixgbe_service_timer(unsigned long data) +static void ixgbe_service_timer(struct timer_list *t) { - struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)data; + struct ixgbe_adapter *adapter = from_timer(adapter, t, service_timer); unsigned long next_event_offset; /* poll faster when waiting for link */ @@ -8552,6 +8665,10 @@ static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) return ixgbe_ptp_set_ts_config(adapter, req); case SIOCGHWTSTAMP: return ixgbe_ptp_get_ts_config(adapter, req); + case SIOCGMIIPHY: + if (!adapter->hw.phy.ops.read_reg) + return -EOPNOTSUPP; + /* fall through */ default: return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd); } @@ -9758,6 +9875,17 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv) limit = find_last_bit(&adapter->fwd_bitmask, 32); adapter->ring_feature[RING_F_VMDQ].limit = limit + 1; ixgbe_fwd_ring_down(fwd_adapter->netdev, fwd_adapter); + + /* go back to full RSS if we're done with our VMQs */ + if (adapter->ring_feature[RING_F_VMDQ].limit == 1) { + int rss = min_t(int, ixgbe_max_rss_indices(adapter), + num_online_cpus()); + + adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED; + adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; + adapter->ring_feature[RING_F_RSS].limit = rss; + } + ixgbe_setup_tc(pdev, netdev_get_num_tc(pdev)); netdev_dbg(pdev, "pool %i:%i queues %i:%i VSI bitmask %lx\n", fwd_adapter->pool, adapter->num_rx_pools, @@ -10380,8 +10508,7 @@ skip_sriov: ether_addr_copy(hw->mac.addr, hw->mac.perm_addr); ixgbe_mac_set_default_filter(adapter); - setup_timer(&adapter->service_timer, &ixgbe_service_timer, - (unsigned long) adapter); + timer_setup(&adapter->service_timer, ixgbe_service_timer, 0); if (ixgbe_removed(hw->hw_addr)) { err = -EIO; @@ -10737,6 +10864,9 @@ skip_bad_vf_detection: if (!test_bit(__IXGBE_SERVICE_INITED, &adapter->state)) return PCI_ERS_RESULT_DISCONNECT; + if (!netif_device_present(netdev)) + return PCI_ERS_RESULT_DISCONNECT; + rtnl_lock(); netif_device_detach(netdev); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index 6ea0d6a5fb90..b8c5fd2a2115 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -619,12 +619,6 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) usleep_range(5000, 10000); } - /* Failed to get SW only semaphore */ - if (swmask == IXGBE_GSSR_SW_MNG_SM) { - hw_dbg(hw, "Failed to get SW only semaphore\n"); - return IXGBE_ERR_SWFW_SYNC; - } - /* If the resource is not released by the FW/HW the SW can assume that * the FW/HW malfunctions. In that case the SW should set the SW bit(s) * of the requested resource(s) while ignoring the corresponding FW/HW @@ -647,7 +641,8 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) */ if (swfw_sync & swmask) { u32 rmask = IXGBE_GSSR_EEP_SM | IXGBE_GSSR_PHY0_SM | - IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM; + IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM | + IXGBE_GSSR_SW_MNG_SM; if (swi2c_mask) rmask |= IXGBE_GSSR_I2C_MASK; @@ -763,6 +758,8 @@ static void ixgbe_release_swfw_sync_semaphore(struct ixgbe_hw *hw) **/ void ixgbe_init_swfw_sync_X540(struct ixgbe_hw *hw) { + u32 rmask; + /* First try to grab the semaphore but we don't need to bother * looking to see whether we got the lock or not since we do * the same thing regardless of whether we got the lock or not. @@ -771,6 +768,14 @@ void ixgbe_init_swfw_sync_X540(struct ixgbe_hw *hw) */ ixgbe_get_swfw_sync_semaphore(hw); ixgbe_release_swfw_sync_semaphore(hw); + + /* Acquire and release all software resources. */ + rmask = IXGBE_GSSR_EEP_SM | IXGBE_GSSR_PHY0_SM | + IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM | + IXGBE_GSSR_SW_MNG_SM | IXGBE_GSSR_I2C_MASK; + + ixgbe_acquire_swfw_sync_X540(hw, rmask); + ixgbe_release_swfw_sync_X540(hw, rmask); } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 19fbb2f28ea4..cb7da5f9c4da 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -900,6 +900,8 @@ static s32 ixgbe_read_ee_hostif_buffer_X550(struct ixgbe_hw *hw, /* convert offset from words to bytes */ buffer.address = cpu_to_be32((offset + current_word) * 2); buffer.length = cpu_to_be16(words_to_read * 2); + buffer.pad2 = 0; + buffer.pad3 = 0; status = ixgbe_hic_unlocked(hw, (u32 *)&buffer, sizeof(buffer), IXGBE_HI_COMMAND_TIMEOUT); @@ -3192,6 +3194,9 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) /* Identify the PHY or SFP module */ ret_val = phy->ops.identify(hw); + if (ret_val == IXGBE_ERR_SFP_NOT_SUPPORTED || + ret_val == IXGBE_ERR_PHY_ADDR_INVALID) + return ret_val; /* Setup function pointers based on detected hardware */ ixgbe_init_mac_link_ops_X550em(hw); @@ -3394,9 +3399,10 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) ixgbe_clear_tx_pending(hw); /* PHY ops must be identified and initialized prior to reset */ - - /* Identify PHY and related function pointers */ status = hw->phy.ops.init(hw); + if (status == IXGBE_ERR_SFP_NOT_SUPPORTED || + status == IXGBE_ERR_PHY_ADDR_INVALID) + return status; /* start the external PHY */ if (hw->phy.type == ixgbe_phy_x550em_ext_t) { @@ -3884,7 +3890,7 @@ static const struct ixgbe_mac_operations mac_ops_X550EM_x_fw = { .write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550, }; -static struct ixgbe_mac_operations mac_ops_x550em_a = { +static const struct ixgbe_mac_operations mac_ops_x550em_a = { X550_COMMON_MAC .led_on = ixgbe_led_on_t_x550em, .led_off = ixgbe_led_off_t_x550em, @@ -3905,7 +3911,7 @@ static struct ixgbe_mac_operations mac_ops_x550em_a = { .write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550a, }; -static struct ixgbe_mac_operations mac_ops_x550em_a_fw = { +static const struct ixgbe_mac_operations mac_ops_x550em_a_fw = { X550_COMMON_MAC .led_on = ixgbe_led_on_generic, .led_off = ixgbe_led_off_generic, diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 032f8ac06357..12d3601b1d57 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -2747,9 +2747,10 @@ void ixgbevf_update_stats(struct ixgbevf_adapter *adapter) * ixgbevf_service_timer - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void ixgbevf_service_timer(unsigned long data) +static void ixgbevf_service_timer(struct timer_list *t) { - struct ixgbevf_adapter *adapter = (struct ixgbevf_adapter *)data; + struct ixgbevf_adapter *adapter = from_timer(adapter, t, + service_timer); /* Reset the timer */ mod_timer(&adapter->service_timer, (HZ * 2) + jiffies); @@ -4120,8 +4121,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_sw_init; } - setup_timer(&adapter->service_timer, &ixgbevf_service_timer, - (unsigned long)adapter); + timer_setup(&adapter->service_timer, ixgbevf_service_timer, 0); INIT_WORK(&adapter->service_task, ixgbevf_service_task); set_bit(__IXGBEVF_SERVICE_INITED, &adapter->state); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 3d4e4a5d00d1..bf1f04164885 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1742,13 +1742,18 @@ static int mlx4_en_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return err; } +static int mlx4_en_get_max_num_rx_rings(struct net_device *dev) +{ + return min_t(int, num_online_cpus(), MAX_RX_RINGS); +} + static void mlx4_en_get_channels(struct net_device *dev, struct ethtool_channels *channel) { struct mlx4_en_priv *priv = netdev_priv(dev); - channel->max_rx = MAX_RX_RINGS; - channel->max_tx = MLX4_EN_MAX_TX_RING_P_UP; + channel->max_rx = mlx4_en_get_max_num_rx_rings(dev); + channel->max_tx = priv->mdev->profile.max_num_tx_rings_p_up; channel->rx_count = priv->rx_ring_num; channel->tx_count = priv->tx_ring_num[TX] / @@ -1777,7 +1782,7 @@ static int mlx4_en_set_channels(struct net_device *dev, mutex_lock(&mdev->state_lock); xdp_count = priv->tx_ring_num[TX_XDP] ? channel->rx_count : 0; if (channel->tx_count * priv->prof->num_up + xdp_count > - MAX_TX_RINGS) { + priv->mdev->profile.max_num_tx_rings_p_up * priv->prof->num_up) { err = -EINVAL; en_err(priv, "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n", diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index 686e18de9a97..2c2965497ed3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -153,7 +153,7 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev) int i; params->udp_rss = udp_rss; - params->num_tx_rings_p_up = mlx4_low_memory_profile() ? + params->max_num_tx_rings_p_up = mlx4_low_memory_profile() ? MLX4_EN_MIN_TX_RING_P_UP : min_t(int, num_online_cpus(), MLX4_EN_MAX_TX_RING_P_UP); @@ -170,8 +170,8 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev) params->prof[i].tx_ring_size = MLX4_EN_DEF_TX_RING_SIZE; params->prof[i].rx_ring_size = MLX4_EN_DEF_RX_RING_SIZE; params->prof[i].num_up = MLX4_EN_NUM_UP_LOW; - params->prof[i].num_tx_rings_p_up = params->num_tx_rings_p_up; - params->prof[i].tx_ring_num[TX] = params->num_tx_rings_p_up * + params->prof[i].num_tx_rings_p_up = params->max_num_tx_rings_p_up; + params->prof[i].tx_ring_num[TX] = params->max_num_tx_rings_p_up * params->prof[i].num_up; params->prof[i].rss_rings = 0; params->prof[i].inline_thold = inline_thold; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 9c218f1cfc6c..d611df2f274d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1752,6 +1752,7 @@ int mlx4_en_start_port(struct net_device *dev) mlx4_en_arm_cq(priv, cq); } else { + mlx4_en_init_tx_xdp_ring_descs(priv, tx_ring); mlx4_en_init_recycle_ring(priv, i); /* XDP TX CQ should never be armed */ } @@ -3305,7 +3306,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, priv->pflags = MLX4_EN_PRIV_FLAGS_BLUEFLAME; priv->ctrl_flags = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE | MLX4_WQE_CTRL_SOLICITED); - priv->num_tx_rings_p_up = mdev->profile.num_tx_rings_p_up; + priv->num_tx_rings_p_up = mdev->profile.max_num_tx_rings_p_up; priv->tx_work_limit = MLX4_EN_DEFAULT_TX_WORK; netdev_rss_key_fill(priv->rss_key, sizeof(priv->rss_key)); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c index 5a47f9669621..6883ac75d37f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c @@ -53,7 +53,7 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride, if (is_tx) { context->sq_size_stride = ilog2(size) << 3 | (ilog2(stride) - 4); if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP) - context->params2 |= MLX4_QP_BIT_FPP; + context->params2 |= cpu_to_be32(MLX4_QP_BIT_FPP); } else { context->sq_size_stride = ilog2(TXBB_SIZE) - 4; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 8f9cb8abc497..92aec17f4b4d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -254,8 +254,7 @@ void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev) DEF_RX_RINGS)); num_rx_rings = mlx4_low_memory_profile() ? MIN_RX_RINGS : - min_t(int, num_of_eqs, - netif_get_num_default_rss_queues()); + min_t(int, num_of_eqs, num_online_cpus()); mdev->profile.prof[i].rx_ring_num = rounddown_pow_of_two(num_rx_rings); } @@ -779,7 +778,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud case XDP_PASS: break; case XDP_TX: - if (likely(!mlx4_en_xmit_frame(ring, frags, dev, + if (likely(!mlx4_en_xmit_frame(ring, frags, priv, length, cq_ring, &doorbell_pending))) { frags[0].page = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 8a32a8f7f9c0..596445a4a241 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -718,7 +718,7 @@ void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring) #else iowrite32be( #endif - ring->doorbell_qpn, + (__force u32)ring->doorbell_qpn, ring->bf.uar->map + MLX4_SEND_DOORBELL); } @@ -1085,13 +1085,35 @@ tx_drop: #define MLX4_EN_XDP_TX_REAL_SZ (((CTRL_SIZE + MLX4_EN_XDP_TX_NRTXBB * DS_SIZE) \ / 16) & 0x3f) +void mlx4_en_init_tx_xdp_ring_descs(struct mlx4_en_priv *priv, + struct mlx4_en_tx_ring *ring) +{ + int i; + + for (i = 0; i < ring->size; i++) { + struct mlx4_en_tx_info *tx_info = &ring->tx_info[i]; + struct mlx4_en_tx_desc *tx_desc = ring->buf + + (i << LOG_TXBB_SIZE); + + tx_info->map0_byte_count = PAGE_SIZE; + tx_info->nr_txbb = MLX4_EN_XDP_TX_NRTXBB; + tx_info->data_offset = offsetof(struct mlx4_en_tx_desc, data); + tx_info->ts_requested = 0; + tx_info->nr_maps = 1; + tx_info->linear = 1; + tx_info->inl = 0; + + tx_desc->data.lkey = ring->mr_key; + tx_desc->ctrl.qpn_vlan.fence_size = MLX4_EN_XDP_TX_REAL_SZ; + tx_desc->ctrl.srcrb_flags = priv->ctrl_flags; + } +} + netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, struct mlx4_en_rx_alloc *frame, - struct net_device *dev, unsigned int length, + struct mlx4_en_priv *priv, unsigned int length, int tx_ind, bool *doorbell_pending) { - struct mlx4_en_priv *priv = netdev_priv(dev); - union mlx4_wqe_qpn_vlan qpn_vlan = {}; struct mlx4_en_tx_desc *tx_desc; struct mlx4_en_tx_info *tx_info; struct mlx4_wqe_data_seg *data; @@ -1123,25 +1145,16 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, tx_info->page = frame->page; frame->page = NULL; tx_info->map0_dma = dma; - tx_info->map0_byte_count = PAGE_SIZE; - tx_info->nr_txbb = MLX4_EN_XDP_TX_NRTXBB; tx_info->nr_bytes = max_t(unsigned int, length, ETH_ZLEN); - tx_info->data_offset = offsetof(struct mlx4_en_tx_desc, data); - tx_info->ts_requested = 0; - tx_info->nr_maps = 1; - tx_info->linear = 1; - tx_info->inl = 0; dma_sync_single_range_for_device(priv->ddev, dma, frame->page_offset, length, PCI_DMA_TODEVICE); data->addr = cpu_to_be64(dma + frame->page_offset); - data->lkey = ring->mr_key; dma_wmb(); data->byte_count = cpu_to_be32(length); /* tx completion can avoid cache line miss for common cases */ - tx_desc->ctrl.srcrb_flags = priv->ctrl_flags; op_own = cpu_to_be32(MLX4_OPCODE_SEND) | ((ring->prod & ring->size) ? @@ -1152,10 +1165,13 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, ring->prod += MLX4_EN_XDP_TX_NRTXBB; - qpn_vlan.fence_size = MLX4_EN_XDP_TX_REAL_SZ; + /* Ensure new descriptor hits memory + * before setting ownership of this descriptor to HW + */ + dma_wmb(); + tx_desc->ctrl.owner_opcode = op_own; + ring->xmit_more++; - mlx4_en_tx_write_desc(ring, tx_desc, qpn_vlan, TXBB_SIZE, 0, - op_own, false, false); *doorbell_pending = true; return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 16c09949afd5..634f603f941c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -57,12 +57,12 @@ MODULE_PARM_DESC(enable_qos, "Enable Enhanced QoS support (default: off)"); #define MLX4_GET(dest, source, offset) \ do { \ void *__p = (char *) (source) + (offset); \ - u64 val; \ - switch (sizeof(dest)) { \ + __be64 val; \ + switch (sizeof(dest)) { \ case 1: (dest) = *(u8 *) __p; break; \ case 2: (dest) = be16_to_cpup(__p); break; \ case 4: (dest) = be32_to_cpup(__p); break; \ - case 8: val = get_unaligned((u64 *)__p); \ + case 8: val = get_unaligned((__be64 *)__p); \ (dest) = be64_to_cpu(val); break; \ default: __buggy_use_of_MLX4_GET(); \ } \ diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index fdb3ad0cbe54..1856e279a7e0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -399,7 +399,7 @@ struct mlx4_en_profile { u32 active_ports; u32 small_pkt_int; u8 no_reset; - u8 num_tx_rings_p_up; + u8 max_num_tx_rings_p_up; struct mlx4_en_port_profile prof[MLX4_MAX_PORTS + 1]; }; @@ -693,7 +693,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev); netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, struct mlx4_en_rx_alloc *frame, - struct net_device *dev, unsigned int length, + struct mlx4_en_priv *priv, unsigned int length, int tx_ind, bool *doorbell_pending); void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring); bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring, @@ -705,6 +705,8 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, int node, int queue_index); void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring **pring); +void mlx4_en_init_tx_xdp_ring_descs(struct mlx4_en_priv *priv, + struct mlx4_en_tx_ring *ring); int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring, int cq, int user_prio); diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index 728a2fb1f5c0..203320923340 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -925,7 +925,7 @@ int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt, context->flags &= cpu_to_be32(~(0xf << 28)); context->flags |= cpu_to_be32(states[i + 1] << 28); if (states[i + 1] != MLX4_QP_STATE_RTR) - context->params2 &= ~MLX4_QP_BIT_FPP; + context->params2 &= ~cpu_to_be32(MLX4_QP_BIT_FPP); err = mlx4_qp_modify(dev, mtt, states[i], states[i + 1], context, 0, 0, qp); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index fabb53379727..04304dd894c6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -3185,7 +3185,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev, optpar = be32_to_cpu(*(__be32 *) inbox->buf); if (slave != mlx4_master_func_num(dev)) { - qp_ctx->params2 &= ~MLX4_QP_BIT_FPP; + qp_ctx->params2 &= ~cpu_to_be32(MLX4_QP_BIT_FPP); /* setting QP rate-limit is disallowed for VFs */ if (qp_ctx->rate_limit_params) return -EPERM; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index fdaef00465d7..25deaa5a534c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -6,6 +6,7 @@ config MLX5_CORE tristate "Mellanox Technologies ConnectX-4 and Connect-IB core driver" depends on MAY_USE_DEVLINK depends on PCI + imply PTP_1588_CLOCK default n ---help--- Core driver for low level functionality of the ConnectX-4 and @@ -29,7 +30,6 @@ config MLX5_CORE_EN bool "Mellanox Technologies ConnectX-4 Ethernet support" depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE depends on IPV6=y || IPV6=n || MLX5_CORE=m - imply PTP_1588_CLOCK default n ---help--- Ethernet support in Mellanox Technologies ConnectX-4 NIC. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 87a3099808f3..100fe4ecad9b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -4,7 +4,7 @@ subdir-ccflags-y += -I$(src) mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \ mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \ - fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o \ + fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o lib/clock.o \ diag/fs_tracepoint.o mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o @@ -13,7 +13,7 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \ fpga/ipsec.o mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ - en_tx.o en_rx.o en_rx_am.o en_txrx.o en_clock.o vxlan.o \ + en_tx.o en_rx.o en_rx_am.o en_txrx.o vxlan.o \ en_arfs.o en_fs_ethtool.o en_selftest.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o @@ -22,7 +22,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o en_rep.o en_tc. mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o -mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o +mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib_vlan.o mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \ en_accel/ipsec_stats.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index cc13d3dbd366..ca8845b641c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -267,28 +267,6 @@ struct mlx5e_dcbx { }; #endif -#define MAX_PIN_NUM 8 -struct mlx5e_pps { - u8 pin_caps[MAX_PIN_NUM]; - struct work_struct out_work; - u64 start[MAX_PIN_NUM]; - u8 enabled; -}; - -struct mlx5e_tstamp { - rwlock_t lock; - struct cyclecounter cycles; - struct timecounter clock; - struct hwtstamp_config hwtstamp_config; - u32 nominal_c_mult; - unsigned long overflow_period; - struct delayed_work overflow_work; - struct mlx5_core_dev *mdev; - struct ptp_clock *ptp; - struct ptp_clock_info ptp_info; - struct mlx5e_pps pps_info; -}; - enum { MLX5E_RQ_STATE_ENABLED, MLX5E_RQ_STATE_AM, @@ -375,9 +353,10 @@ struct mlx5e_txqsq { u8 min_inline_mode; u16 edge; struct device *pdev; - struct mlx5e_tstamp *tstamp; __be32 mkey_be; unsigned long state; + struct hwtstamp_config *tstamp; + struct mlx5_clock *clock; /* control path */ struct mlx5_wq_ctrl wq_ctrl; @@ -543,10 +522,11 @@ struct mlx5e_rq { struct mlx5e_channel *channel; struct device *pdev; struct net_device *netdev; - struct mlx5e_tstamp *tstamp; struct mlx5e_rq_stats stats; struct mlx5e_cq cq; struct mlx5e_page_cache page_cache; + struct hwtstamp_config *tstamp; + struct mlx5_clock *clock; mlx5e_fp_handle_rx_cqe handle_rx_cqe; mlx5e_fp_post_rx_wqes post_wqes; @@ -588,7 +568,7 @@ struct mlx5e_channel { /* control */ struct mlx5e_priv *priv; struct mlx5_core_dev *mdev; - struct mlx5e_tstamp *tstamp; + struct hwtstamp_config *tstamp; int ix; }; @@ -789,7 +769,7 @@ struct mlx5e_priv { struct mlx5_core_dev *mdev; struct net_device *netdev; struct mlx5e_stats stats; - struct mlx5e_tstamp tstamp; + struct hwtstamp_config tstamp; u16 q_counter; #ifdef CONFIG_MLX5_CORE_EN_DCB struct mlx5e_dcbx dcbx; @@ -873,12 +853,6 @@ void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv); void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv); void mlx5e_set_rx_mode_work(struct work_struct *work); -void mlx5e_fill_hwstamp(struct mlx5e_tstamp *clock, u64 timestamp, - struct skb_shared_hwtstamps *hwts); -void mlx5e_timestamp_init(struct mlx5e_priv *priv); -void mlx5e_timestamp_cleanup(struct mlx5e_priv *priv); -void mlx5e_pps_event_handler(struct mlx5e_priv *priv, - struct ptp_clock_event *event); int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr); int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr); int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val); @@ -889,6 +863,7 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto, u16 vid); void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv); void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv); +void mlx5e_timestamp_set(struct mlx5e_priv *priv); struct mlx5e_redirect_rqt_param { bool is_rss; @@ -1081,6 +1056,9 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv, int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv, struct ethtool_flash *flash); +int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data); + /* mlx5e generic netdev management API */ struct net_device* mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c deleted file mode 100644 index 84dd63e74041..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c +++ /dev/null @@ -1,619 +0,0 @@ -/* - * Copyright (c) 2015, Mellanox Technologies. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#include <linux/clocksource.h> -#include "en.h" - -enum { - MLX5E_CYCLES_SHIFT = 23 -}; - -enum { - MLX5E_PIN_MODE_IN = 0x0, - MLX5E_PIN_MODE_OUT = 0x1, -}; - -enum { - MLX5E_OUT_PATTERN_PULSE = 0x0, - MLX5E_OUT_PATTERN_PERIODIC = 0x1, -}; - -enum { - MLX5E_EVENT_MODE_DISABLE = 0x0, - MLX5E_EVENT_MODE_REPETETIVE = 0x1, - MLX5E_EVENT_MODE_ONCE_TILL_ARM = 0x2, -}; - -enum { - MLX5E_MTPPS_FS_ENABLE = BIT(0x0), - MLX5E_MTPPS_FS_PATTERN = BIT(0x2), - MLX5E_MTPPS_FS_PIN_MODE = BIT(0x3), - MLX5E_MTPPS_FS_TIME_STAMP = BIT(0x4), - MLX5E_MTPPS_FS_OUT_PULSE_DURATION = BIT(0x5), - MLX5E_MTPPS_FS_ENH_OUT_PER_ADJ = BIT(0x7), -}; - -void mlx5e_fill_hwstamp(struct mlx5e_tstamp *tstamp, u64 timestamp, - struct skb_shared_hwtstamps *hwts) -{ - u64 nsec; - - read_lock(&tstamp->lock); - nsec = timecounter_cyc2time(&tstamp->clock, timestamp); - read_unlock(&tstamp->lock); - - hwts->hwtstamp = ns_to_ktime(nsec); -} - -static u64 mlx5e_read_internal_timer(const struct cyclecounter *cc) -{ - struct mlx5e_tstamp *tstamp = container_of(cc, struct mlx5e_tstamp, - cycles); - - return mlx5_read_internal_timer(tstamp->mdev) & cc->mask; -} - -static void mlx5e_pps_out(struct work_struct *work) -{ - struct mlx5e_pps *pps_info = container_of(work, struct mlx5e_pps, - out_work); - struct mlx5e_tstamp *tstamp = container_of(pps_info, struct mlx5e_tstamp, - pps_info); - u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; - unsigned long flags; - int i; - - for (i = 0; i < tstamp->ptp_info.n_pins; i++) { - u64 tstart; - - write_lock_irqsave(&tstamp->lock, flags); - tstart = tstamp->pps_info.start[i]; - tstamp->pps_info.start[i] = 0; - write_unlock_irqrestore(&tstamp->lock, flags); - if (!tstart) - continue; - - MLX5_SET(mtpps_reg, in, pin, i); - MLX5_SET64(mtpps_reg, in, time_stamp, tstart); - MLX5_SET(mtpps_reg, in, field_select, MLX5E_MTPPS_FS_TIME_STAMP); - mlx5_set_mtpps(tstamp->mdev, in, sizeof(in)); - } -} - -static void mlx5e_timestamp_overflow(struct work_struct *work) -{ - struct delayed_work *dwork = to_delayed_work(work); - struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp, - overflow_work); - struct mlx5e_priv *priv = container_of(tstamp, struct mlx5e_priv, tstamp); - unsigned long flags; - - write_lock_irqsave(&tstamp->lock, flags); - timecounter_read(&tstamp->clock); - write_unlock_irqrestore(&tstamp->lock, flags); - queue_delayed_work(priv->wq, &tstamp->overflow_work, - msecs_to_jiffies(tstamp->overflow_period * 1000)); -} - -int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) -{ - struct hwtstamp_config config; - int err; - - if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) - return -EOPNOTSUPP; - - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; - - /* TX HW timestamp */ - switch (config.tx_type) { - case HWTSTAMP_TX_OFF: - case HWTSTAMP_TX_ON: - break; - default: - return -ERANGE; - } - - mutex_lock(&priv->state_lock); - /* RX HW timestamp */ - switch (config.rx_filter) { - case HWTSTAMP_FILTER_NONE: - /* Reset CQE compression to Admin default */ - mlx5e_modify_rx_cqe_compression_locked(priv, priv->channels.params.rx_cqe_compress_def); - break; - case HWTSTAMP_FILTER_ALL: - case HWTSTAMP_FILTER_SOME: - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - case HWTSTAMP_FILTER_NTP_ALL: - /* Disable CQE compression */ - netdev_warn(priv->netdev, "Disabling cqe compression"); - err = mlx5e_modify_rx_cqe_compression_locked(priv, false); - if (err) { - netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err); - mutex_unlock(&priv->state_lock); - return err; - } - config.rx_filter = HWTSTAMP_FILTER_ALL; - break; - default: - mutex_unlock(&priv->state_lock); - return -ERANGE; - } - - memcpy(&priv->tstamp.hwtstamp_config, &config, sizeof(config)); - mutex_unlock(&priv->state_lock); - - return copy_to_user(ifr->ifr_data, &config, - sizeof(config)) ? -EFAULT : 0; -} - -int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr) -{ - struct hwtstamp_config *cfg = &priv->tstamp.hwtstamp_config; - - if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) - return -EOPNOTSUPP; - - return copy_to_user(ifr->ifr_data, cfg, sizeof(*cfg)) ? -EFAULT : 0; -} - -static int mlx5e_ptp_settime(struct ptp_clock_info *ptp, - const struct timespec64 *ts) -{ - struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, - ptp_info); - u64 ns = timespec64_to_ns(ts); - unsigned long flags; - - write_lock_irqsave(&tstamp->lock, flags); - timecounter_init(&tstamp->clock, &tstamp->cycles, ns); - write_unlock_irqrestore(&tstamp->lock, flags); - - return 0; -} - -static int mlx5e_ptp_gettime(struct ptp_clock_info *ptp, - struct timespec64 *ts) -{ - struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, - ptp_info); - u64 ns; - unsigned long flags; - - write_lock_irqsave(&tstamp->lock, flags); - ns = timecounter_read(&tstamp->clock); - write_unlock_irqrestore(&tstamp->lock, flags); - - *ts = ns_to_timespec64(ns); - - return 0; -} - -static int mlx5e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) -{ - struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, - ptp_info); - unsigned long flags; - - write_lock_irqsave(&tstamp->lock, flags); - timecounter_adjtime(&tstamp->clock, delta); - write_unlock_irqrestore(&tstamp->lock, flags); - - return 0; -} - -static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) -{ - u64 adj; - u32 diff; - unsigned long flags; - int neg_adj = 0; - struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, - ptp_info); - - if (delta < 0) { - neg_adj = 1; - delta = -delta; - } - - adj = tstamp->nominal_c_mult; - adj *= delta; - diff = div_u64(adj, 1000000000ULL); - - write_lock_irqsave(&tstamp->lock, flags); - timecounter_read(&tstamp->clock); - tstamp->cycles.mult = neg_adj ? tstamp->nominal_c_mult - diff : - tstamp->nominal_c_mult + diff; - write_unlock_irqrestore(&tstamp->lock, flags); - - return 0; -} - -static int mlx5e_extts_configure(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, - int on) -{ - struct mlx5e_tstamp *tstamp = - container_of(ptp, struct mlx5e_tstamp, ptp_info); - struct mlx5e_priv *priv = - container_of(tstamp, struct mlx5e_priv, tstamp); - u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; - u32 field_select = 0; - u8 pin_mode = 0; - u8 pattern = 0; - int pin = -1; - int err = 0; - - if (!MLX5_PPS_CAP(priv->mdev)) - return -EOPNOTSUPP; - - if (rq->extts.index >= tstamp->ptp_info.n_pins) - return -EINVAL; - - if (on) { - pin = ptp_find_pin(tstamp->ptp, PTP_PF_EXTTS, rq->extts.index); - if (pin < 0) - return -EBUSY; - pin_mode = MLX5E_PIN_MODE_IN; - pattern = !!(rq->extts.flags & PTP_FALLING_EDGE); - field_select = MLX5E_MTPPS_FS_PIN_MODE | - MLX5E_MTPPS_FS_PATTERN | - MLX5E_MTPPS_FS_ENABLE; - } else { - pin = rq->extts.index; - field_select = MLX5E_MTPPS_FS_ENABLE; - } - - MLX5_SET(mtpps_reg, in, pin, pin); - MLX5_SET(mtpps_reg, in, pin_mode, pin_mode); - MLX5_SET(mtpps_reg, in, pattern, pattern); - MLX5_SET(mtpps_reg, in, enable, on); - MLX5_SET(mtpps_reg, in, field_select, field_select); - - err = mlx5_set_mtpps(priv->mdev, in, sizeof(in)); - if (err) - return err; - - return mlx5_set_mtppse(priv->mdev, pin, 0, - MLX5E_EVENT_MODE_REPETETIVE & on); -} - -static int mlx5e_perout_configure(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, - int on) -{ - struct mlx5e_tstamp *tstamp = - container_of(ptp, struct mlx5e_tstamp, ptp_info); - struct mlx5e_priv *priv = - container_of(tstamp, struct mlx5e_priv, tstamp); - u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; - u64 nsec_now, nsec_delta, time_stamp = 0; - u64 cycles_now, cycles_delta; - struct timespec64 ts; - unsigned long flags; - u32 field_select = 0; - u8 pin_mode = 0; - u8 pattern = 0; - int pin = -1; - int err = 0; - s64 ns; - - if (!MLX5_PPS_CAP(priv->mdev)) - return -EOPNOTSUPP; - - if (rq->perout.index >= tstamp->ptp_info.n_pins) - return -EINVAL; - - if (on) { - pin = ptp_find_pin(tstamp->ptp, PTP_PF_PEROUT, - rq->perout.index); - if (pin < 0) - return -EBUSY; - - pin_mode = MLX5E_PIN_MODE_OUT; - pattern = MLX5E_OUT_PATTERN_PERIODIC; - ts.tv_sec = rq->perout.period.sec; - ts.tv_nsec = rq->perout.period.nsec; - ns = timespec64_to_ns(&ts); - - if ((ns >> 1) != 500000000LL) - return -EINVAL; - - ts.tv_sec = rq->perout.start.sec; - ts.tv_nsec = rq->perout.start.nsec; - ns = timespec64_to_ns(&ts); - cycles_now = mlx5_read_internal_timer(tstamp->mdev); - write_lock_irqsave(&tstamp->lock, flags); - nsec_now = timecounter_cyc2time(&tstamp->clock, cycles_now); - nsec_delta = ns - nsec_now; - cycles_delta = div64_u64(nsec_delta << tstamp->cycles.shift, - tstamp->cycles.mult); - write_unlock_irqrestore(&tstamp->lock, flags); - time_stamp = cycles_now + cycles_delta; - field_select = MLX5E_MTPPS_FS_PIN_MODE | - MLX5E_MTPPS_FS_PATTERN | - MLX5E_MTPPS_FS_ENABLE | - MLX5E_MTPPS_FS_TIME_STAMP; - } else { - pin = rq->perout.index; - field_select = MLX5E_MTPPS_FS_ENABLE; - } - - MLX5_SET(mtpps_reg, in, pin, pin); - MLX5_SET(mtpps_reg, in, pin_mode, pin_mode); - MLX5_SET(mtpps_reg, in, pattern, pattern); - MLX5_SET(mtpps_reg, in, enable, on); - MLX5_SET64(mtpps_reg, in, time_stamp, time_stamp); - MLX5_SET(mtpps_reg, in, field_select, field_select); - - err = mlx5_set_mtpps(priv->mdev, in, sizeof(in)); - if (err) - return err; - - return mlx5_set_mtppse(priv->mdev, pin, 0, - MLX5E_EVENT_MODE_REPETETIVE & on); -} - -static int mlx5e_pps_configure(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, - int on) -{ - struct mlx5e_tstamp *tstamp = - container_of(ptp, struct mlx5e_tstamp, ptp_info); - - tstamp->pps_info.enabled = !!on; - return 0; -} - -static int mlx5e_ptp_enable(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, - int on) -{ - switch (rq->type) { - case PTP_CLK_REQ_EXTTS: - return mlx5e_extts_configure(ptp, rq, on); - case PTP_CLK_REQ_PEROUT: - return mlx5e_perout_configure(ptp, rq, on); - case PTP_CLK_REQ_PPS: - return mlx5e_pps_configure(ptp, rq, on); - default: - return -EOPNOTSUPP; - } - return 0; -} - -static int mlx5e_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, - enum ptp_pin_function func, unsigned int chan) -{ - return (func == PTP_PF_PHYSYNC) ? -EOPNOTSUPP : 0; -} - -static const struct ptp_clock_info mlx5e_ptp_clock_info = { - .owner = THIS_MODULE, - .max_adj = 100000000, - .n_alarm = 0, - .n_ext_ts = 0, - .n_per_out = 0, - .n_pins = 0, - .pps = 0, - .adjfreq = mlx5e_ptp_adjfreq, - .adjtime = mlx5e_ptp_adjtime, - .gettime64 = mlx5e_ptp_gettime, - .settime64 = mlx5e_ptp_settime, - .enable = NULL, - .verify = NULL, -}; - -static void mlx5e_timestamp_init_config(struct mlx5e_tstamp *tstamp) -{ - tstamp->hwtstamp_config.tx_type = HWTSTAMP_TX_OFF; - tstamp->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; -} - -static int mlx5e_init_pin_config(struct mlx5e_tstamp *tstamp) -{ - int i; - - tstamp->ptp_info.pin_config = - kzalloc(sizeof(*tstamp->ptp_info.pin_config) * - tstamp->ptp_info.n_pins, GFP_KERNEL); - if (!tstamp->ptp_info.pin_config) - return -ENOMEM; - tstamp->ptp_info.enable = mlx5e_ptp_enable; - tstamp->ptp_info.verify = mlx5e_ptp_verify; - tstamp->ptp_info.pps = 1; - - for (i = 0; i < tstamp->ptp_info.n_pins; i++) { - snprintf(tstamp->ptp_info.pin_config[i].name, - sizeof(tstamp->ptp_info.pin_config[i].name), - "mlx5_pps%d", i); - tstamp->ptp_info.pin_config[i].index = i; - tstamp->ptp_info.pin_config[i].func = PTP_PF_NONE; - tstamp->ptp_info.pin_config[i].chan = i; - } - - return 0; -} - -static void mlx5e_get_pps_caps(struct mlx5e_priv *priv, - struct mlx5e_tstamp *tstamp) -{ - u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; - - mlx5_query_mtpps(priv->mdev, out, sizeof(out)); - - tstamp->ptp_info.n_pins = MLX5_GET(mtpps_reg, out, - cap_number_of_pps_pins); - tstamp->ptp_info.n_ext_ts = MLX5_GET(mtpps_reg, out, - cap_max_num_of_pps_in_pins); - tstamp->ptp_info.n_per_out = MLX5_GET(mtpps_reg, out, - cap_max_num_of_pps_out_pins); - - tstamp->pps_info.pin_caps[0] = MLX5_GET(mtpps_reg, out, cap_pin_0_mode); - tstamp->pps_info.pin_caps[1] = MLX5_GET(mtpps_reg, out, cap_pin_1_mode); - tstamp->pps_info.pin_caps[2] = MLX5_GET(mtpps_reg, out, cap_pin_2_mode); - tstamp->pps_info.pin_caps[3] = MLX5_GET(mtpps_reg, out, cap_pin_3_mode); - tstamp->pps_info.pin_caps[4] = MLX5_GET(mtpps_reg, out, cap_pin_4_mode); - tstamp->pps_info.pin_caps[5] = MLX5_GET(mtpps_reg, out, cap_pin_5_mode); - tstamp->pps_info.pin_caps[6] = MLX5_GET(mtpps_reg, out, cap_pin_6_mode); - tstamp->pps_info.pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode); -} - -void mlx5e_pps_event_handler(struct mlx5e_priv *priv, - struct ptp_clock_event *event) -{ - struct net_device *netdev = priv->netdev; - struct mlx5e_tstamp *tstamp = &priv->tstamp; - struct timespec64 ts; - u64 nsec_now, nsec_delta; - u64 cycles_now, cycles_delta; - int pin = event->index; - s64 ns; - unsigned long flags; - - switch (tstamp->ptp_info.pin_config[pin].func) { - case PTP_PF_EXTTS: - if (tstamp->pps_info.enabled) { - event->type = PTP_CLOCK_PPSUSR; - event->pps_times.ts_real = ns_to_timespec64(event->timestamp); - } else { - event->type = PTP_CLOCK_EXTTS; - } - ptp_clock_event(tstamp->ptp, event); - break; - case PTP_PF_PEROUT: - mlx5e_ptp_gettime(&tstamp->ptp_info, &ts); - cycles_now = mlx5_read_internal_timer(tstamp->mdev); - ts.tv_sec += 1; - ts.tv_nsec = 0; - ns = timespec64_to_ns(&ts); - write_lock_irqsave(&tstamp->lock, flags); - nsec_now = timecounter_cyc2time(&tstamp->clock, cycles_now); - nsec_delta = ns - nsec_now; - cycles_delta = div64_u64(nsec_delta << tstamp->cycles.shift, - tstamp->cycles.mult); - tstamp->pps_info.start[pin] = cycles_now + cycles_delta; - queue_work(priv->wq, &tstamp->pps_info.out_work); - write_unlock_irqrestore(&tstamp->lock, flags); - break; - default: - netdev_err(netdev, "%s: Unhandled event\n", __func__); - } -} - -void mlx5e_timestamp_init(struct mlx5e_priv *priv) -{ - struct mlx5e_tstamp *tstamp = &priv->tstamp; - u64 ns; - u64 frac = 0; - u32 dev_freq; - - mlx5e_timestamp_init_config(tstamp); - dev_freq = MLX5_CAP_GEN(priv->mdev, device_frequency_khz); - if (!dev_freq) { - mlx5_core_warn(priv->mdev, "invalid device_frequency_khz, aborting HW clock init\n"); - return; - } - rwlock_init(&tstamp->lock); - tstamp->cycles.read = mlx5e_read_internal_timer; - tstamp->cycles.shift = MLX5E_CYCLES_SHIFT; - tstamp->cycles.mult = clocksource_khz2mult(dev_freq, - tstamp->cycles.shift); - tstamp->nominal_c_mult = tstamp->cycles.mult; - tstamp->cycles.mask = CLOCKSOURCE_MASK(41); - tstamp->mdev = priv->mdev; - - timecounter_init(&tstamp->clock, &tstamp->cycles, - ktime_to_ns(ktime_get_real())); - - /* Calculate period in seconds to call the overflow watchdog - to make - * sure counter is checked at least once every wrap around. - */ - ns = cyclecounter_cyc2ns(&tstamp->cycles, tstamp->cycles.mask, - frac, &frac); - do_div(ns, NSEC_PER_SEC / 2 / HZ); - tstamp->overflow_period = ns; - - INIT_WORK(&tstamp->pps_info.out_work, mlx5e_pps_out); - INIT_DELAYED_WORK(&tstamp->overflow_work, mlx5e_timestamp_overflow); - if (tstamp->overflow_period) - queue_delayed_work(priv->wq, &tstamp->overflow_work, 0); - else - mlx5_core_warn(priv->mdev, "invalid overflow period, overflow_work is not scheduled\n"); - - /* Configure the PHC */ - tstamp->ptp_info = mlx5e_ptp_clock_info; - snprintf(tstamp->ptp_info.name, 16, "mlx5 ptp"); - - /* Initialize 1PPS data structures */ - if (MLX5_PPS_CAP(priv->mdev)) - mlx5e_get_pps_caps(priv, tstamp); - if (tstamp->ptp_info.n_pins) - mlx5e_init_pin_config(tstamp); - - tstamp->ptp = ptp_clock_register(&tstamp->ptp_info, - &priv->mdev->pdev->dev); - if (IS_ERR(tstamp->ptp)) { - mlx5_core_warn(priv->mdev, "ptp_clock_register failed %ld\n", - PTR_ERR(tstamp->ptp)); - tstamp->ptp = NULL; - } -} - -void mlx5e_timestamp_cleanup(struct mlx5e_priv *priv) -{ - struct mlx5e_tstamp *tstamp = &priv->tstamp; - - if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) - return; - - if (priv->tstamp.ptp) { - ptp_clock_unregister(priv->tstamp.ptp); - priv->tstamp.ptp = NULL; - } - - cancel_work_sync(&tstamp->pps_info.out_work); - cancel_delayed_work_sync(&tstamp->overflow_work); - kfree(tstamp->ptp_info.pin_config); -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index ece3fb147e3e..157d02917237 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -134,6 +134,7 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev) mlx5_core_destroy_mkey(mdev, &res->mkey); mlx5_core_dealloc_transport_domain(mdev, res->td.tdn); mlx5_core_dealloc_pd(mdev, res->pdn); + memset(res, 0, sizeof(*res)); } int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index d12e9fc0d76b..81a112e40fe3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1417,14 +1417,15 @@ static int mlx5e_set_pauseparam(struct net_device *netdev, int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv, struct ethtool_ts_info *info) { + struct mlx5_core_dev *mdev = priv->mdev; int ret; ret = ethtool_op_get_ts_info(priv->netdev, info); if (ret) return ret; - info->phc_index = priv->tstamp.ptp ? - ptp_clock_index(priv->tstamp.ptp) : -1; + info->phc_index = mdev->clock.ptp ? + ptp_clock_index(mdev->clock.ptp) : -1; if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) return 0; @@ -1754,7 +1755,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, if (!MLX5_CAP_GEN(mdev, cqe_compression)) return -EOPNOTSUPP; - if (enable && priv->tstamp.hwtstamp_config.rx_filter != HWTSTAMP_FILTER_NONE) { + if (enable && priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE) { netdev_err(netdev, "Can't enable cqe compression while timestamping is enabled.\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index cc11bbbd0309..3a1969a6d509 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -373,8 +373,6 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv, enum mlx5_dev_event event, unsigned long param) { struct mlx5e_priv *priv = vpriv; - struct ptp_clock_event ptp_event; - struct mlx5_eqe *eqe = NULL; if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state)) return; @@ -384,14 +382,6 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv, case MLX5_DEV_EVENT_PORT_DOWN: queue_work(priv->wq, &priv->update_carrier_work); break; - case MLX5_DEV_EVENT_PPS: - eqe = (struct mlx5_eqe *)param; - ptp_event.index = eqe->data.pps.pin; - ptp_event.timestamp = - timecounter_cyc2time(&priv->tstamp.clock, - be64_to_cpu(eqe->data.pps.time_stamp)); - mlx5e_pps_event_handler(vpriv, &ptp_event); - break; default: break; } @@ -585,6 +575,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->pdev = c->pdev; rq->netdev = c->netdev; rq->tstamp = c->tstamp; + rq->clock = &mdev->clock; rq->channel = c; rq->ix = c->ix; rq->mdev = mdev; @@ -1123,6 +1114,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->pdev = c->pdev; sq->tstamp = c->tstamp; + sq->clock = &mdev->clock; sq->mkey_be = c->mkey_be; sq->channel = c; sq->txq_ix = txq_ix; @@ -2678,6 +2670,12 @@ void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, netif_carrier_on(netdev); } +void mlx5e_timestamp_set(struct mlx5e_priv *priv) +{ + priv->tstamp.tx_type = HWTSTAMP_TX_OFF; + priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE; +} + int mlx5e_open_locked(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -2693,7 +2691,7 @@ int mlx5e_open_locked(struct net_device *netdev) mlx5e_activate_priv_channels(priv); if (priv->profile->update_carrier) priv->profile->update_carrier(priv); - mlx5e_timestamp_init(priv); + mlx5e_timestamp_set(priv); if (priv->profile->update_stats) queue_delayed_work(priv->wq, &priv->update_stats_work, 0); @@ -2731,7 +2729,6 @@ int mlx5e_close_locked(struct net_device *netdev) clear_bit(MLX5E_STATE_OPENED, &priv->state); - mlx5e_timestamp_cleanup(priv); netif_carrier_off(priv->netdev); mlx5e_deactivate_priv_channels(priv); mlx5e_close_channels(&priv->channels); @@ -3108,8 +3105,8 @@ static int mlx5e_setup_tc_cls_flower(struct net_device *dev, } #endif -static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type, - void *type_data) +int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) { switch (type) { #ifdef CONFIG_MLX5_ESWITCH @@ -3403,6 +3400,80 @@ out: return err; } +int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) +{ + struct hwtstamp_config config; + int err; + + if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) + return -EOPNOTSUPP; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + /* TX HW timestamp */ + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; + } + + mutex_lock(&priv->state_lock); + /* RX HW timestamp */ + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + /* Reset CQE compression to Admin default */ + mlx5e_modify_rx_cqe_compression_locked(priv, priv->channels.params.rx_cqe_compress_def); + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_NTP_ALL: + /* Disable CQE compression */ + netdev_warn(priv->netdev, "Disabling cqe compression"); + err = mlx5e_modify_rx_cqe_compression_locked(priv, false); + if (err) { + netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err); + mutex_unlock(&priv->state_lock); + return err; + } + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + mutex_unlock(&priv->state_lock); + return -ERANGE; + } + + memcpy(&priv->tstamp, &config, sizeof(config)); + mutex_unlock(&priv->state_lock); + + return copy_to_user(ifr->ifr_data, &config, + sizeof(config)) ? -EFAULT : 0; +} + +int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr) +{ + struct hwtstamp_config *cfg = &priv->tstamp; + + if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) + return -EOPNOTSUPP; + + return copy_to_user(ifr->ifr_data, cfg, sizeof(*cfg)) ? -EFAULT : 0; +} + static int mlx5e_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct mlx5e_priv *priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 45e03c427faf..765fc74fbb1b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -34,6 +34,7 @@ #include <linux/mlx5/fs.h> #include <net/switchdev.h> #include <net/pkt_cls.h> +#include <net/act_api.h> #include <net/netevent.h> #include <net/arp.h> @@ -667,14 +668,6 @@ mlx5e_rep_setup_tc_cls_flower(struct net_device *dev, cls_flower->common.chain_index) return -EOPNOTSUPP; - if (cls_flower->egress_dev) { - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - - dev = mlx5_eswitch_get_uplink_netdev(esw); - return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, - cls_flower); - } - switch (cls_flower->command) { case TC_CLSFLOWER_REPLACE: return mlx5e_configure_flower(priv, cls_flower); @@ -698,6 +691,14 @@ static int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type, } } +static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct net_device *dev = cb_priv; + + return mlx5e_setup_tc(dev, type, type_data); +} + bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; @@ -1017,15 +1018,24 @@ mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) goto err_detach_netdev; } + err = tc_setup_cb_egdev_register(netdev, mlx5e_rep_setup_tc_cb, + mlx5_eswitch_get_uplink_netdev(esw)); + if (err) + goto err_neigh_cleanup; + err = register_netdev(netdev); if (err) { pr_warn("Failed to register representor netdev for vport %d\n", rep->vport); - goto err_neigh_cleanup; + goto err_egdev_cleanup; } return 0; +err_egdev_cleanup: + tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb, + mlx5_eswitch_get_uplink_netdev(esw)); + err_neigh_cleanup: mlx5e_rep_neigh_cleanup(rpriv); @@ -1047,7 +1057,8 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) void *ppriv = priv->ppriv; unregister_netdev(rep->netdev); - + tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb, + mlx5_eswitch_get_uplink_netdev(esw)); mlx5e_rep_neigh_cleanup(rpriv); mlx5e_detach_netdev(priv); mlx5e_destroy_netdev(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index bc654aeae5d4..6d7df4750e0f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -42,10 +42,11 @@ #include "en_rep.h" #include "ipoib/ipoib.h" #include "en_accel/ipsec_rxtx.h" +#include "lib/clock.h" -static inline bool mlx5e_rx_hw_stamp(struct mlx5e_tstamp *tstamp) +static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config) { - return tstamp->hwtstamp_config.rx_filter == HWTSTAMP_FILTER_ALL; + return config->rx_filter == HWTSTAMP_FILTER_ALL; } static inline void mlx5e_read_cqe_slot(struct mlx5e_cq *cq, u32 cqcc, @@ -661,7 +662,6 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb) { struct net_device *netdev = rq->netdev; - struct mlx5e_tstamp *tstamp = rq->tstamp; int lro_num_seg; lro_num_seg = be32_to_cpu(cqe->srqn) >> 24; @@ -676,8 +676,9 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, rq->stats.lro_bytes += cqe_bcnt; } - if (unlikely(mlx5e_rx_hw_stamp(tstamp))) - mlx5e_fill_hwstamp(tstamp, get_cqe_ts(cqe), skb_hwtstamps(skb)); + if (unlikely(mlx5e_rx_hw_stamp(rq->tstamp))) + skb_hwtstamps(skb)->hwtstamp = + mlx5_timecounter_cyc2time(rq->clock, get_cqe_ts(cqe)); skb_record_rx_queue(skb, rq->ix); @@ -1163,12 +1164,25 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, u32 cqe_bcnt, struct sk_buff *skb) { - struct net_device *netdev = rq->netdev; - struct mlx5e_tstamp *tstamp = rq->tstamp; + struct net_device *netdev; char *pseudo_header; + u32 qpn; u8 *dgid; u8 g; + qpn = be32_to_cpu(cqe->sop_drop_qpn) & 0xffffff; + netdev = mlx5i_pkey_get_netdev(rq->netdev, qpn); + + /* No mapping present, cannot process SKB. This might happen if a child + * interface is going down while having unprocessed CQEs on parent RQ + */ + if (unlikely(!netdev)) { + /* TODO: add drop counters support */ + skb->dev = NULL; + pr_warn_once("Unable to map QPN %u to dev - dropping skb\n", qpn); + return; + } + g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3; dgid = skb->data + MLX5_IB_GRH_DGID_OFFSET; if ((!g) || dgid[0] != 0xff) @@ -1189,8 +1203,9 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, skb->ip_summed = CHECKSUM_COMPLETE; skb->csum = csum_unfold((__force __sum16)cqe->check_sum); - if (unlikely(mlx5e_rx_hw_stamp(tstamp))) - mlx5e_fill_hwstamp(tstamp, get_cqe_ts(cqe), skb_hwtstamps(skb)); + if (unlikely(mlx5e_rx_hw_stamp(rq->tstamp))) + skb_hwtstamps(skb)->hwtstamp = + mlx5_timecounter_cyc2time(rq->clock, get_cqe_ts(cqe)); skb_record_rx_queue(skb, rq->ix); @@ -1230,6 +1245,10 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) goto wq_free_wqe; mlx5i_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); + if (unlikely(!skb->dev)) { + dev_kfree_skb_any(skb); + goto wq_free_wqe; + } napi_gro_receive(rq->cq.napi, skb); wq_free_wqe: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 1d6925d4369a..a7c208a1ad83 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -35,6 +35,7 @@ #include "en.h" #include "ipoib/ipoib.h" #include "en_accel/ipsec_rxtx.h" +#include "lib/clock.h" #define MLX5E_SQ_NOPS_ROOM MLX5_SEND_WQE_MAX_WQEBBS #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\ @@ -452,8 +453,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) SKBTX_HW_TSTAMP)) { struct skb_shared_hwtstamps hwts = {}; - mlx5e_fill_hwstamp(sq->tstamp, - get_cqe_ts(cqe), &hwts); + hwts.hwtstamp = + mlx5_timecounter_cyc2time(sq->clock, + get_cqe_ts(cqe)); skb_tstamp_tx(skb, &hwts); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index fc606bfd1d6e..60771865c99c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -491,8 +491,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr) break; case MLX5_EVENT_TYPE_PPS_EVENT: - if (dev->event) - dev->event(dev, MLX5_DEV_EVENT_PPS, (unsigned long)eqe); + mlx5_pps_event(dev, eqe); break; case MLX5_EVENT_TYPE_FPGA_ERROR: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 36ecc2b2e187..881e2e55840c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -40,7 +40,8 @@ #include "eswitch.h" int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, - struct mlx5_flow_table *ft, u32 underlay_qpn) + struct mlx5_flow_table *ft, u32 underlay_qpn, + bool disconnect) { u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {0}; u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {0}; @@ -52,7 +53,15 @@ int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, MLX5_SET(set_flow_table_root_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ROOT); MLX5_SET(set_flow_table_root_in, in, table_type, ft->type); - MLX5_SET(set_flow_table_root_in, in, table_id, ft->id); + + if (disconnect) { + MLX5_SET(set_flow_table_root_in, in, op_mod, 1); + MLX5_SET(set_flow_table_root_in, in, table_id, 0); + } else { + MLX5_SET(set_flow_table_root_in, in, op_mod, 0); + MLX5_SET(set_flow_table_root_in, in, table_id, ft->id); + } + MLX5_SET(set_flow_table_root_in, in, underlay_qpn, underlay_qpn); if (ft->vport) { MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index c6d7bdf255b6..71e2d0f37ad9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -71,8 +71,8 @@ int mlx5_cmd_delete_fte(struct mlx5_core_dev *dev, unsigned int index); int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, - struct mlx5_flow_table *ft, - u32 underlay_qpn); + struct mlx5_flow_table *ft, u32 underlay_qpn, + bool disconnect); int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 5a7bea688ec8..f77e496f7053 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -145,10 +145,10 @@ static struct init_tree_node { } }; -enum fs_i_mutex_lock_class { - FS_MUTEX_GRANDPARENT, - FS_MUTEX_PARENT, - FS_MUTEX_CHILD +enum fs_i_lock_class { + FS_LOCK_GRANDPARENT, + FS_LOCK_PARENT, + FS_LOCK_CHILD }; static const struct rhashtable_params rhash_fte = { @@ -168,10 +168,16 @@ static const struct rhashtable_params rhash_fg = { }; -static void del_rule(struct fs_node *node); -static void del_flow_table(struct fs_node *node); -static void del_flow_group(struct fs_node *node); -static void del_fte(struct fs_node *node); +static void del_hw_flow_table(struct fs_node *node); +static void del_hw_flow_group(struct fs_node *node); +static void del_hw_fte(struct fs_node *node); +static void del_sw_flow_table(struct fs_node *node); +static void del_sw_flow_group(struct fs_node *node); +static void del_sw_fte(struct fs_node *node); +/* Delete rule (destination) is special case that + * requires to lock the FTE for all the deletion process. + */ +static void del_sw_hw_rule(struct fs_node *node); static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, struct mlx5_flow_destination *d2); static struct mlx5_flow_rule * @@ -179,14 +185,16 @@ find_flow_rule(struct fs_fte *fte, struct mlx5_flow_destination *dest); static void tree_init_node(struct fs_node *node, - unsigned int refcount, - void (*remove_func)(struct fs_node *)) + void (*del_hw_func)(struct fs_node *), + void (*del_sw_func)(struct fs_node *)) { - atomic_set(&node->refcount, refcount); + atomic_set(&node->refcount, 1); INIT_LIST_HEAD(&node->list); INIT_LIST_HEAD(&node->children); - mutex_init(&node->lock); - node->remove_func = remove_func; + init_rwsem(&node->lock); + node->del_hw_func = del_hw_func; + node->del_sw_func = del_sw_func; + node->active = false; } static void tree_add_node(struct fs_node *node, struct fs_node *parent) @@ -202,50 +210,70 @@ static void tree_add_node(struct fs_node *node, struct fs_node *parent) node->root = parent->root; } -static void tree_get_node(struct fs_node *node) +static int tree_get_node(struct fs_node *node) { - atomic_inc(&node->refcount); + return atomic_add_unless(&node->refcount, 1, 0); } -static void nested_lock_ref_node(struct fs_node *node, - enum fs_i_mutex_lock_class class) +static void nested_down_read_ref_node(struct fs_node *node, + enum fs_i_lock_class class) { if (node) { - mutex_lock_nested(&node->lock, class); + down_read_nested(&node->lock, class); atomic_inc(&node->refcount); } } -static void lock_ref_node(struct fs_node *node) +static void nested_down_write_ref_node(struct fs_node *node, + enum fs_i_lock_class class) { if (node) { - mutex_lock(&node->lock); + down_write_nested(&node->lock, class); atomic_inc(&node->refcount); } } -static void unlock_ref_node(struct fs_node *node) +static void down_write_ref_node(struct fs_node *node) { if (node) { - atomic_dec(&node->refcount); - mutex_unlock(&node->lock); + down_write(&node->lock); + atomic_inc(&node->refcount); } } +static void up_read_ref_node(struct fs_node *node) +{ + atomic_dec(&node->refcount); + up_read(&node->lock); +} + +static void up_write_ref_node(struct fs_node *node) +{ + atomic_dec(&node->refcount); + up_write(&node->lock); +} + static void tree_put_node(struct fs_node *node) { struct fs_node *parent_node = node->parent; - lock_ref_node(parent_node); if (atomic_dec_and_test(&node->refcount)) { - if (parent_node) + if (node->del_hw_func) + node->del_hw_func(node); + if (parent_node) { + /* Only root namespace doesn't have parent and we just + * need to free its node. + */ + down_write_ref_node(parent_node); list_del_init(&node->list); - if (node->remove_func) - node->remove_func(node); - kfree(node); + if (node->del_sw_func) + node->del_sw_func(node); + up_write_ref_node(parent_node); + } else { + kfree(node); + } node = NULL; } - unlock_ref_node(parent_node); if (!node && parent_node) tree_put_node(parent_node); } @@ -362,6 +390,15 @@ static struct mlx5_flow_root_namespace *find_root(struct fs_node *node) return container_of(ns, struct mlx5_flow_root_namespace, ns); } +static inline struct mlx5_flow_steering *get_steering(struct fs_node *node) +{ + struct mlx5_flow_root_namespace *root = find_root(node); + + if (root) + return root->dev->priv.steering; + return NULL; +} + static inline struct mlx5_core_dev *get_dev(struct fs_node *node) { struct mlx5_flow_root_namespace *root = find_root(node); @@ -371,26 +408,36 @@ static inline struct mlx5_core_dev *get_dev(struct fs_node *node) return NULL; } -static void del_flow_table(struct fs_node *node) +static void del_hw_flow_table(struct fs_node *node) { struct mlx5_flow_table *ft; struct mlx5_core_dev *dev; - struct fs_prio *prio; int err; fs_get_obj(ft, node); dev = get_dev(&ft->node); - err = mlx5_cmd_destroy_flow_table(dev, ft); - if (err) - mlx5_core_warn(dev, "flow steering can't destroy ft\n"); - ida_destroy(&ft->fte_allocator); + if (node->active) { + err = mlx5_cmd_destroy_flow_table(dev, ft); + if (err) + mlx5_core_warn(dev, "flow steering can't destroy ft\n"); + } +} + +static void del_sw_flow_table(struct fs_node *node) +{ + struct mlx5_flow_table *ft; + struct fs_prio *prio; + + fs_get_obj(ft, node); + rhltable_destroy(&ft->fgs_hash); fs_get_obj(prio, ft->node.parent); prio->num_ft--; + kfree(ft); } -static void del_rule(struct fs_node *node) +static void del_sw_hw_rule(struct fs_node *node) { struct mlx5_flow_rule *rule; struct mlx5_flow_table *ft; @@ -406,7 +453,6 @@ static void del_rule(struct fs_node *node) fs_get_obj(fg, fte->node.parent); fs_get_obj(ft, fg->node.parent); trace_mlx5_fs_del_rule(rule); - list_del(&rule->node.list); if (rule->sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { mutex_lock(&rule->dest_attr.ft->lock); list_del(&rule->next_ft); @@ -434,117 +480,203 @@ out: "%s can't del rule fg id=%d fte_index=%d\n", __func__, fg->id, fte->index); } + kfree(rule); } -static void destroy_fte(struct fs_fte *fte, struct mlx5_flow_group *fg) +static void del_hw_fte(struct fs_node *node) { struct mlx5_flow_table *ft; - int ret; + struct mlx5_flow_group *fg; + struct mlx5_core_dev *dev; + struct fs_fte *fte; + int err; - ret = rhashtable_remove_fast(&fg->ftes_hash, &fte->hash, rhash_fte); - WARN_ON(ret); - fte->status = 0; + fs_get_obj(fte, node); + fs_get_obj(fg, fte->node.parent); fs_get_obj(ft, fg->node.parent); - ida_simple_remove(&ft->fte_allocator, fte->index); + + trace_mlx5_fs_del_fte(fte); + dev = get_dev(&ft->node); + if (node->active) { + err = mlx5_cmd_delete_fte(dev, ft, + fte->index); + if (err) + mlx5_core_warn(dev, + "flow steering can't delete fte in index %d of flow group id %d\n", + fte->index, fg->id); + } } -static void del_fte(struct fs_node *node) +static void del_sw_fte(struct fs_node *node) { - struct mlx5_flow_table *ft; + struct mlx5_flow_steering *steering = get_steering(node); struct mlx5_flow_group *fg; - struct mlx5_core_dev *dev; struct fs_fte *fte; int err; fs_get_obj(fte, node); fs_get_obj(fg, fte->node.parent); - fs_get_obj(ft, fg->node.parent); - trace_mlx5_fs_del_fte(fte); - - dev = get_dev(&ft->node); - err = mlx5_cmd_delete_fte(dev, ft, - fte->index); - if (err) - mlx5_core_warn(dev, - "flow steering can't delete fte in index %d of flow group id %d\n", - fte->index, fg->id); - destroy_fte(fte, fg); + err = rhashtable_remove_fast(&fg->ftes_hash, + &fte->hash, + rhash_fte); + WARN_ON(err); + ida_simple_remove(&fg->fte_allocator, fte->index - fg->start_index); + kmem_cache_free(steering->ftes_cache, fte); } -static void del_flow_group(struct fs_node *node) +static void del_hw_flow_group(struct fs_node *node) { struct mlx5_flow_group *fg; struct mlx5_flow_table *ft; struct mlx5_core_dev *dev; - int err; fs_get_obj(fg, node); fs_get_obj(ft, fg->node.parent); dev = get_dev(&ft->node); trace_mlx5_fs_del_fg(fg); - if (ft->autogroup.active) - ft->autogroup.num_groups--; + if (fg->node.active && mlx5_cmd_destroy_flow_group(dev, ft, fg->id)) + mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n", + fg->id, ft->id); +} + +static void del_sw_flow_group(struct fs_node *node) +{ + struct mlx5_flow_steering *steering = get_steering(node); + struct mlx5_flow_group *fg; + struct mlx5_flow_table *ft; + int err; + + fs_get_obj(fg, node); + fs_get_obj(ft, fg->node.parent); rhashtable_destroy(&fg->ftes_hash); + ida_destroy(&fg->fte_allocator); + if (ft->autogroup.active) + ft->autogroup.num_groups--; err = rhltable_remove(&ft->fgs_hash, &fg->hash, rhash_fg); WARN_ON(err); - if (mlx5_cmd_destroy_flow_group(dev, ft, fg->id)) - mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n", - fg->id, ft->id); + kmem_cache_free(steering->fgs_cache, fg); } -static struct fs_fte *alloc_fte(struct mlx5_flow_act *flow_act, +static int insert_fte(struct mlx5_flow_group *fg, struct fs_fte *fte) +{ + int index; + int ret; + + index = ida_simple_get(&fg->fte_allocator, 0, fg->max_ftes, GFP_KERNEL); + if (index < 0) + return index; + + fte->index = index + fg->start_index; + ret = rhashtable_insert_fast(&fg->ftes_hash, + &fte->hash, + rhash_fte); + if (ret) + goto err_ida_remove; + + tree_add_node(&fte->node, &fg->node); + list_add_tail(&fte->node.list, &fg->node.children); + return 0; + +err_ida_remove: + ida_simple_remove(&fg->fte_allocator, index); + return ret; +} + +static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft, u32 *match_value, - unsigned int index) + struct mlx5_flow_act *flow_act) { + struct mlx5_flow_steering *steering = get_steering(&ft->node); struct fs_fte *fte; - fte = kzalloc(sizeof(*fte), GFP_KERNEL); + fte = kmem_cache_zalloc(steering->ftes_cache, GFP_KERNEL); if (!fte) return ERR_PTR(-ENOMEM); memcpy(fte->val, match_value, sizeof(fte->val)); fte->node.type = FS_TYPE_FLOW_ENTRY; fte->flow_tag = flow_act->flow_tag; - fte->index = index; fte->action = flow_act->action; fte->encap_id = flow_act->encap_id; fte->modify_id = flow_act->modify_id; + tree_init_node(&fte->node, del_hw_fte, del_sw_fte); + return fte; } -static struct mlx5_flow_group *alloc_flow_group(u32 *create_fg_in) +static void dealloc_flow_group(struct mlx5_flow_steering *steering, + struct mlx5_flow_group *fg) +{ + rhashtable_destroy(&fg->ftes_hash); + kmem_cache_free(steering->fgs_cache, fg); +} + +static struct mlx5_flow_group *alloc_flow_group(struct mlx5_flow_steering *steering, + u8 match_criteria_enable, + void *match_criteria, + int start_index, + int end_index) { struct mlx5_flow_group *fg; - void *match_criteria = MLX5_ADDR_OF(create_flow_group_in, - create_fg_in, match_criteria); - u8 match_criteria_enable = MLX5_GET(create_flow_group_in, - create_fg_in, - match_criteria_enable); int ret; - fg = kzalloc(sizeof(*fg), GFP_KERNEL); + fg = kmem_cache_zalloc(steering->fgs_cache, GFP_KERNEL); if (!fg) return ERR_PTR(-ENOMEM); ret = rhashtable_init(&fg->ftes_hash, &rhash_fte); if (ret) { - kfree(fg); + kmem_cache_free(steering->fgs_cache, fg); return ERR_PTR(ret); - } +} + ida_init(&fg->fte_allocator); fg->mask.match_criteria_enable = match_criteria_enable; memcpy(&fg->mask.match_criteria, match_criteria, sizeof(fg->mask.match_criteria)); fg->node.type = FS_TYPE_FLOW_GROUP; - fg->start_index = MLX5_GET(create_flow_group_in, create_fg_in, - start_flow_index); - fg->max_ftes = MLX5_GET(create_flow_group_in, create_fg_in, - end_flow_index) - fg->start_index + 1; + fg->start_index = start_index; + fg->max_ftes = end_index - start_index + 1; + + return fg; +} + +static struct mlx5_flow_group *alloc_insert_flow_group(struct mlx5_flow_table *ft, + u8 match_criteria_enable, + void *match_criteria, + int start_index, + int end_index, + struct list_head *prev) +{ + struct mlx5_flow_steering *steering = get_steering(&ft->node); + struct mlx5_flow_group *fg; + int ret; + + fg = alloc_flow_group(steering, match_criteria_enable, match_criteria, + start_index, end_index); + if (IS_ERR(fg)) + return fg; + + /* initialize refcnt, add to parent list */ + ret = rhltable_insert(&ft->fgs_hash, + &fg->hash, + rhash_fg); + if (ret) { + dealloc_flow_group(steering, fg); + return ERR_PTR(ret); + } + + tree_init_node(&fg->node, del_hw_flow_group, del_sw_flow_group); + tree_add_node(&fg->node, &ft->node); + /* Add node to group list */ + list_add(&fg->node.list, prev); + atomic_inc(&ft->node.version); + return fg; } @@ -575,7 +707,6 @@ static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_ft ft->flags = flags; INIT_LIST_HEAD(&ft->fwd_rules); mutex_init(&ft->lock); - ida_init(&ft->fte_allocator); return ft; } @@ -693,8 +824,10 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio *prio) { struct mlx5_flow_root_namespace *root = find_root(&prio->node); + struct mlx5_ft_underlay_qp *uqp; int min_level = INT_MAX; int err; + u32 qpn; if (root->root_ft) min_level = root->root_ft->level; @@ -702,10 +835,24 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio if (ft->level >= min_level) return 0; - err = mlx5_cmd_update_root_ft(root->dev, ft, root->underlay_qpn); + if (list_empty(&root->underlay_qpns)) { + /* Don't set any QPN (zero) in case QPN list is empty */ + qpn = 0; + err = mlx5_cmd_update_root_ft(root->dev, ft, qpn, false); + } else { + list_for_each_entry(uqp, &root->underlay_qpns, list) { + qpn = uqp->qpn; + err = mlx5_cmd_update_root_ft(root->dev, ft, qpn, + false); + if (err) + break; + } + } + if (err) - mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n", - ft->id); + mlx5_core_warn(root->dev, + "Update root flow table of id(%u) qpn(%d) failed\n", + ft->id, qpn); else root->root_ft = ft; @@ -724,7 +871,7 @@ static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule, fs_get_obj(fte, rule->node.parent); if (!(fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST)) return -EINVAL; - lock_ref_node(&fte->node); + down_write_ref_node(&fte->node); fs_get_obj(fg, fte->node.parent); fs_get_obj(ft, fg->node.parent); @@ -733,7 +880,7 @@ static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule, ft, fg->id, modify_mask, fte); - unlock_ref_node(&fte->node); + up_write_ref_node(&fte->node); return err; } @@ -870,7 +1017,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa goto unlock_root; } - tree_init_node(&ft->node, 1, del_flow_table); + tree_init_node(&ft->node, del_hw_flow_table, del_sw_flow_table); log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0; next_ft = find_next_chained_ft(fs_prio); err = mlx5_cmd_create_flow_table(root->dev, ft->vport, ft->op_mod, ft->type, @@ -882,17 +1029,17 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa err = connect_flow_table(root->dev, ft, fs_prio); if (err) goto destroy_ft; - lock_ref_node(&fs_prio->node); + ft->node.active = true; + down_write_ref_node(&fs_prio->node); tree_add_node(&ft->node, &fs_prio->node); list_add_flow_table(ft, fs_prio); fs_prio->num_ft++; - unlock_ref_node(&fs_prio->node); + up_write_ref_node(&fs_prio->node); mutex_unlock(&root->chain_lock); return ft; destroy_ft: mlx5_cmd_destroy_flow_table(root->dev, ft); free_ft: - ida_destroy(&ft->fte_allocator); kfree(ft); unlock_root: mutex_unlock(&root->chain_lock); @@ -960,54 +1107,6 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, } EXPORT_SYMBOL(mlx5_create_auto_grouped_flow_table); -/* Flow table should be locked */ -static struct mlx5_flow_group *create_flow_group_common(struct mlx5_flow_table *ft, - u32 *fg_in, - struct list_head - *prev_fg, - bool is_auto_fg) -{ - struct mlx5_flow_group *fg; - struct mlx5_core_dev *dev = get_dev(&ft->node); - int err; - - if (!dev) - return ERR_PTR(-ENODEV); - - fg = alloc_flow_group(fg_in); - if (IS_ERR(fg)) - return fg; - - err = rhltable_insert(&ft->fgs_hash, &fg->hash, rhash_fg); - if (err) - goto err_free_fg; - - err = mlx5_cmd_create_flow_group(dev, ft, fg_in, &fg->id); - if (err) - goto err_remove_fg; - - if (ft->autogroup.active) - ft->autogroup.num_groups++; - /* Add node to tree */ - tree_init_node(&fg->node, !is_auto_fg, del_flow_group); - tree_add_node(&fg->node, &ft->node); - /* Add node to group list */ - list_add(&fg->node.list, prev_fg); - - trace_mlx5_fs_add_fg(fg); - return fg; - -err_remove_fg: - WARN_ON(rhltable_remove(&ft->fgs_hash, - &fg->hash, - rhash_fg)); -err_free_fg: - rhashtable_destroy(&fg->ftes_hash); - kfree(fg); - - return ERR_PTR(err); -} - struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft, u32 *fg_in) { @@ -1016,7 +1115,13 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft, u8 match_criteria_enable = MLX5_GET(create_flow_group_in, fg_in, match_criteria_enable); + int start_index = MLX5_GET(create_flow_group_in, fg_in, + start_flow_index); + int end_index = MLX5_GET(create_flow_group_in, fg_in, + end_flow_index); + struct mlx5_core_dev *dev = get_dev(&ft->node); struct mlx5_flow_group *fg; + int err; if (!check_valid_mask(match_criteria_enable, match_criteria)) return ERR_PTR(-EINVAL); @@ -1024,9 +1129,21 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft, if (ft->autogroup.active) return ERR_PTR(-EPERM); - lock_ref_node(&ft->node); - fg = create_flow_group_common(ft, fg_in, ft->node.children.prev, false); - unlock_ref_node(&ft->node); + down_write_ref_node(&ft->node); + fg = alloc_insert_flow_group(ft, match_criteria_enable, match_criteria, + start_index, end_index, + ft->node.children.prev); + up_write_ref_node(&ft->node); + if (IS_ERR(fg)) + return fg; + + err = mlx5_cmd_create_flow_group(dev, ft, fg_in, &fg->id); + if (err) { + tree_put_node(&fg->node); + return ERR_PTR(err); + } + trace_mlx5_fs_add_fg(fg); + fg->node.active = true; return fg; } @@ -1111,7 +1228,7 @@ create_flow_handle(struct fs_fte *fte, /* Add dest to dests list- we need flow tables to be in the * end of the list for forward to next prio rules. */ - tree_init_node(&rule->node, 1, del_rule); + tree_init_node(&rule->node, NULL, del_sw_hw_rule); if (dest && dest[i].type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) list_add(&rule->node.list, &fte->node.children); @@ -1167,7 +1284,9 @@ add_rule_fte(struct fs_fte *fte, if (err) goto free_handle; + fte->node.active = true; fte->status |= FS_FTE_STATUS_EXISTING; + atomic_inc(&fte->node.version); out: return handle; @@ -1177,59 +1296,17 @@ free_handle: return ERR_PTR(err); } -static struct fs_fte *create_fte(struct mlx5_flow_group *fg, - u32 *match_value, - struct mlx5_flow_act *flow_act) -{ - struct mlx5_flow_table *ft; - struct fs_fte *fte; - int index; - int ret; - - fs_get_obj(ft, fg->node.parent); - index = ida_simple_get(&ft->fte_allocator, fg->start_index, - fg->start_index + fg->max_ftes, - GFP_KERNEL); - if (index < 0) - return ERR_PTR(index); - - fte = alloc_fte(flow_act, match_value, index); - if (IS_ERR(fte)) { - ret = PTR_ERR(fte); - goto err_alloc; - } - ret = rhashtable_insert_fast(&fg->ftes_hash, &fte->hash, rhash_fte); - if (ret) - goto err_hash; - - return fte; - -err_hash: - kfree(fte); -err_alloc: - ida_simple_remove(&ft->fte_allocator, index); - return ERR_PTR(ret); -} - -static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft, - u8 match_criteria_enable, - u32 *match_criteria) +static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table *ft, + struct mlx5_flow_spec *spec) { - int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct list_head *prev = &ft->node.children; - unsigned int candidate_index = 0; struct mlx5_flow_group *fg; - void *match_criteria_addr; + unsigned int candidate_index = 0; unsigned int group_size = 0; - u32 *in; if (!ft->autogroup.active) return ERR_PTR(-ENOENT); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) - return ERR_PTR(-ENOMEM); - if (ft->autogroup.num_groups < ft->autogroup.required_groups) /* We save place for flow groups in addition to max types */ group_size = ft->max_fte / (ft->autogroup.required_groups + 1); @@ -1247,25 +1324,55 @@ static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft, prev = &fg->node.list; } - if (candidate_index + group_size > ft->max_fte) { - fg = ERR_PTR(-ENOSPC); + if (candidate_index + group_size > ft->max_fte) + return ERR_PTR(-ENOSPC); + + fg = alloc_insert_flow_group(ft, + spec->match_criteria_enable, + spec->match_criteria, + candidate_index, + candidate_index + group_size - 1, + prev); + if (IS_ERR(fg)) goto out; - } + + ft->autogroup.num_groups++; + +out: + return fg; +} + +static int create_auto_flow_group(struct mlx5_flow_table *ft, + struct mlx5_flow_group *fg) +{ + struct mlx5_core_dev *dev = get_dev(&ft->node); + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + void *match_criteria_addr; + int err; + u32 *in; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; MLX5_SET(create_flow_group_in, in, match_criteria_enable, - match_criteria_enable); - MLX5_SET(create_flow_group_in, in, start_flow_index, candidate_index); - MLX5_SET(create_flow_group_in, in, end_flow_index, candidate_index + - group_size - 1); + fg->mask.match_criteria_enable); + MLX5_SET(create_flow_group_in, in, start_flow_index, fg->start_index); + MLX5_SET(create_flow_group_in, in, end_flow_index, fg->start_index + + fg->max_ftes - 1); match_criteria_addr = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); - memcpy(match_criteria_addr, match_criteria, - MLX5_ST_SZ_BYTES(fte_match_param)); + memcpy(match_criteria_addr, fg->mask.match_criteria, + sizeof(fg->mask.match_criteria)); + + err = mlx5_cmd_create_flow_group(dev, ft, in, &fg->id); + if (!err) { + fg->node.active = true; + trace_mlx5_fs_add_fg(fg); + } - fg = create_flow_group_common(ft, in, prev, true); -out: kvfree(in); - return fg; + return err; } static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, @@ -1340,60 +1447,30 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, struct fs_fte *fte) { struct mlx5_flow_handle *handle; - struct mlx5_flow_table *ft; + int old_action; int i; + int ret; - if (fte) { - int old_action; - int ret; - - nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD); - ret = check_conflicting_ftes(fte, flow_act); - if (ret) { - handle = ERR_PTR(ret); - goto unlock_fte; - } - - old_action = fte->action; - fte->action |= flow_act->action; - handle = add_rule_fte(fte, fg, dest, dest_num, - old_action != flow_act->action); - if (IS_ERR(handle)) { - fte->action = old_action; - goto unlock_fte; - } else { - trace_mlx5_fs_set_fte(fte, false); - goto add_rules; - } - } - fs_get_obj(ft, fg->node.parent); + ret = check_conflicting_ftes(fte, flow_act); + if (ret) + return ERR_PTR(ret); - fte = create_fte(fg, match_value, flow_act); - if (IS_ERR(fte)) - return (void *)fte; - tree_init_node(&fte->node, 0, del_fte); - nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD); - handle = add_rule_fte(fte, fg, dest, dest_num, false); + old_action = fte->action; + fte->action |= flow_act->action; + handle = add_rule_fte(fte, fg, dest, dest_num, + old_action != flow_act->action); if (IS_ERR(handle)) { - unlock_ref_node(&fte->node); - destroy_fte(fte, fg); - kfree(fte); + fte->action = old_action; return handle; } + trace_mlx5_fs_set_fte(fte, false); - tree_add_node(&fte->node, &fg->node); - /* fte list isn't sorted */ - list_add_tail(&fte->node.list, &fg->node.children); - trace_mlx5_fs_set_fte(fte, true); -add_rules: for (i = 0; i < handle->num_rules; i++) { if (atomic_read(&handle->rule[i]->node.refcount) == 1) { tree_add_node(&handle->rule[i]->node, &fte->node); trace_mlx5_fs_add_rule(handle->rule[i]); } } -unlock_fte: - unlock_ref_node(&fte->node); return handle; } @@ -1441,93 +1518,197 @@ static bool dest_is_valid(struct mlx5_flow_destination *dest, return true; } -static struct mlx5_flow_handle * -try_add_to_existing_fg(struct mlx5_flow_table *ft, - struct mlx5_flow_spec *spec, - struct mlx5_flow_act *flow_act, - struct mlx5_flow_destination *dest, - int dest_num) -{ +struct match_list { + struct list_head list; struct mlx5_flow_group *g; - struct mlx5_flow_handle *rule = ERR_PTR(-ENOENT); +}; + +struct match_list_head { + struct list_head list; + struct match_list first; +}; + +static void free_match_list(struct match_list_head *head) +{ + if (!list_empty(&head->list)) { + struct match_list *iter, *match_tmp; + + list_del(&head->first.list); + tree_put_node(&head->first.g->node); + list_for_each_entry_safe(iter, match_tmp, &head->list, + list) { + tree_put_node(&iter->g->node); + list_del(&iter->list); + kfree(iter); + } + } +} + +static int build_match_list(struct match_list_head *match_head, + struct mlx5_flow_table *ft, + struct mlx5_flow_spec *spec) +{ struct rhlist_head *tmp, *list; - struct match_list { - struct list_head list; - struct mlx5_flow_group *g; - } match_list, *iter; - LIST_HEAD(match_head); + struct mlx5_flow_group *g; + int err = 0; rcu_read_lock(); + INIT_LIST_HEAD(&match_head->list); /* Collect all fgs which has a matching match_criteria */ list = rhltable_lookup(&ft->fgs_hash, spec, rhash_fg); + /* RCU is atomic, we can't execute FW commands here */ rhl_for_each_entry_rcu(g, tmp, list, hash) { struct match_list *curr_match; - if (likely(list_empty(&match_head))) { - match_list.g = g; - list_add_tail(&match_list.list, &match_head); + if (likely(list_empty(&match_head->list))) { + if (!tree_get_node(&g->node)) + continue; + match_head->first.g = g; + list_add_tail(&match_head->first.list, + &match_head->list); continue; } - curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC); + curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC); if (!curr_match) { - rcu_read_unlock(); - rule = ERR_PTR(-ENOMEM); - goto free_list; + free_match_list(match_head); + err = -ENOMEM; + goto out; + } + if (!tree_get_node(&g->node)) { + kfree(curr_match); + continue; } curr_match->g = g; - list_add_tail(&curr_match->list, &match_head); + list_add_tail(&curr_match->list, &match_head->list); } +out: rcu_read_unlock(); + return err; +} + +static u64 matched_fgs_get_version(struct list_head *match_head) +{ + struct match_list *iter; + u64 version = 0; + + list_for_each_entry(iter, match_head, list) + version += (u64)atomic_read(&iter->g->node.version); + return version; +} +static struct mlx5_flow_handle * +try_add_to_existing_fg(struct mlx5_flow_table *ft, + struct list_head *match_head, + struct mlx5_flow_spec *spec, + struct mlx5_flow_act *flow_act, + struct mlx5_flow_destination *dest, + int dest_num, + int ft_version) +{ + struct mlx5_flow_steering *steering = get_steering(&ft->node); + struct mlx5_flow_group *g; + struct mlx5_flow_handle *rule; + struct match_list *iter; + bool take_write = false; + struct fs_fte *fte; + u64 version; + int err; + + fte = alloc_fte(ft, spec->match_value, flow_act); + if (IS_ERR(fte)) + return ERR_PTR(-ENOMEM); + + list_for_each_entry(iter, match_head, list) { + nested_down_read_ref_node(&iter->g->node, FS_LOCK_PARENT); + ida_pre_get(&iter->g->fte_allocator, GFP_KERNEL); + } + +search_again_locked: + version = matched_fgs_get_version(match_head); /* Try to find a fg that already contains a matching fte */ - list_for_each_entry(iter, &match_head, list) { - struct fs_fte *fte; + list_for_each_entry(iter, match_head, list) { + struct fs_fte *fte_tmp; g = iter->g; - nested_lock_ref_node(&g->node, FS_MUTEX_PARENT); - fte = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value, - rhash_fte); - if (fte) { - rule = add_rule_fg(g, spec->match_value, - flow_act, dest, dest_num, fte); - unlock_ref_node(&g->node); - goto free_list; + fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value, + rhash_fte); + if (!fte_tmp || !tree_get_node(&fte_tmp->node)) + continue; + + nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); + if (!take_write) { + list_for_each_entry(iter, match_head, list) + up_read_ref_node(&iter->g->node); + } else { + list_for_each_entry(iter, match_head, list) + up_write_ref_node(&iter->g->node); } - unlock_ref_node(&g->node); + + rule = add_rule_fg(g, spec->match_value, + flow_act, dest, dest_num, fte_tmp); + up_write_ref_node(&fte_tmp->node); + tree_put_node(&fte_tmp->node); + kmem_cache_free(steering->ftes_cache, fte); + return rule; } /* No group with matching fte found. Try to add a new fte to any * matching fg. */ - list_for_each_entry(iter, &match_head, list) { - g = iter->g; - nested_lock_ref_node(&g->node, FS_MUTEX_PARENT); - rule = add_rule_fg(g, spec->match_value, - flow_act, dest, dest_num, NULL); - if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOSPC) { - unlock_ref_node(&g->node); - goto free_list; - } - unlock_ref_node(&g->node); + if (!take_write) { + list_for_each_entry(iter, match_head, list) + up_read_ref_node(&iter->g->node); + list_for_each_entry(iter, match_head, list) + nested_down_write_ref_node(&iter->g->node, + FS_LOCK_PARENT); + take_write = true; } -free_list: - if (!list_empty(&match_head)) { - struct match_list *match_tmp; + /* Check the ft version, for case that new flow group + * was added while the fgs weren't locked + */ + if (atomic_read(&ft->node.version) != ft_version) { + rule = ERR_PTR(-EAGAIN); + goto out; + } - /* The most common case is having one FG. Since we want to - * optimize this case, we save the first on the stack. - * Therefore, no need to free it. - */ - list_del(&list_first_entry(&match_head, typeof(*iter), list)->list); - list_for_each_entry_safe(iter, match_tmp, &match_head, list) { - list_del(&iter->list); - kfree(iter); + /* Check the fgs version, for case the new FTE with the + * same values was added while the fgs weren't locked + */ + if (version != matched_fgs_get_version(match_head)) + goto search_again_locked; + + list_for_each_entry(iter, match_head, list) { + g = iter->g; + + if (!g->node.active) + continue; + err = insert_fte(g, fte); + if (err) { + if (err == -ENOSPC) + continue; + list_for_each_entry(iter, match_head, list) + up_write_ref_node(&iter->g->node); + kmem_cache_free(steering->ftes_cache, fte); + return ERR_PTR(err); } - } + nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD); + list_for_each_entry(iter, match_head, list) + up_write_ref_node(&iter->g->node); + rule = add_rule_fg(g, spec->match_value, + flow_act, dest, dest_num, fte); + up_write_ref_node(&fte->node); + tree_put_node(&fte->node); + return rule; + } + rule = ERR_PTR(-ENOENT); +out: + list_for_each_entry(iter, match_head, list) + up_write_ref_node(&iter->g->node); + kmem_cache_free(steering->ftes_cache, fte); return rule; } @@ -1539,8 +1720,14 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, int dest_num) { + struct mlx5_flow_steering *steering = get_steering(&ft->node); struct mlx5_flow_group *g; struct mlx5_flow_handle *rule; + struct match_list_head match_head; + bool take_write = false; + struct fs_fte *fte; + int version; + int err; int i; if (!check_valid_spec(spec)) @@ -1550,33 +1737,73 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, if (!dest_is_valid(&dest[i], flow_act->action, ft)) return ERR_PTR(-EINVAL); } + nested_down_read_ref_node(&ft->node, FS_LOCK_GRANDPARENT); +search_again_locked: + version = atomic_read(&ft->node.version); + + /* Collect all fgs which has a matching match_criteria */ + err = build_match_list(&match_head, ft, spec); + if (err) + return ERR_PTR(err); - nested_lock_ref_node(&ft->node, FS_MUTEX_GRANDPARENT); - rule = try_add_to_existing_fg(ft, spec, flow_act, dest, dest_num); - if (!IS_ERR(rule)) - goto unlock; + if (!take_write) + up_read_ref_node(&ft->node); - g = create_autogroup(ft, spec->match_criteria_enable, - spec->match_criteria); + rule = try_add_to_existing_fg(ft, &match_head.list, spec, flow_act, dest, + dest_num, version); + free_match_list(&match_head); + if (!IS_ERR(rule) || + (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) + return rule; + + if (!take_write) { + nested_down_write_ref_node(&ft->node, FS_LOCK_GRANDPARENT); + take_write = true; + } + + if (PTR_ERR(rule) == -EAGAIN || + version != atomic_read(&ft->node.version)) + goto search_again_locked; + + g = alloc_auto_flow_group(ft, spec); if (IS_ERR(g)) { rule = (void *)g; - goto unlock; + up_write_ref_node(&ft->node); + return rule; } - rule = add_rule_fg(g, spec->match_value, flow_act, dest, - dest_num, NULL); - if (IS_ERR(rule)) { - /* Remove assumes refcount > 0 and autogroup creates a group - * with a refcount = 0. - */ - unlock_ref_node(&ft->node); - tree_get_node(&g->node); - tree_remove_node(&g->node); - return rule; + nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); + up_write_ref_node(&ft->node); + + err = create_auto_flow_group(ft, g); + if (err) + goto err_release_fg; + + fte = alloc_fte(ft, spec->match_value, flow_act); + if (IS_ERR(fte)) { + err = PTR_ERR(fte); + goto err_release_fg; } -unlock: - unlock_ref_node(&ft->node); + + err = insert_fte(g, fte); + if (err) { + kmem_cache_free(steering->ftes_cache, fte); + goto err_release_fg; + } + + nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD); + up_write_ref_node(&g->node); + rule = add_rule_fg(g, spec->match_value, flow_act, dest, + dest_num, fte); + up_write_ref_node(&fte->node); + tree_put_node(&fte->node); + tree_put_node(&g->node); return rule; + +err_release_fg: + up_write_ref_node(&g->node); + tree_put_node(&g->node); + return ERR_PTR(err); } static bool fwd_next_prio_supported(struct mlx5_flow_table *ft) @@ -1661,23 +1888,43 @@ static struct mlx5_flow_table *find_next_ft(struct mlx5_flow_table *ft) static int update_root_ft_destroy(struct mlx5_flow_table *ft) { struct mlx5_flow_root_namespace *root = find_root(&ft->node); + struct mlx5_ft_underlay_qp *uqp; struct mlx5_flow_table *new_root_ft = NULL; + int err = 0; + u32 qpn; if (root->root_ft != ft) return 0; new_root_ft = find_next_ft(ft); - if (new_root_ft) { - int err = mlx5_cmd_update_root_ft(root->dev, new_root_ft, - root->underlay_qpn); - if (err) { - mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n", - ft->id); - return err; + if (!new_root_ft) { + root->root_ft = NULL; + return 0; + } + + if (list_empty(&root->underlay_qpns)) { + /* Don't set any QPN (zero) in case QPN list is empty */ + qpn = 0; + err = mlx5_cmd_update_root_ft(root->dev, new_root_ft, qpn, + false); + } else { + list_for_each_entry(uqp, &root->underlay_qpns, list) { + qpn = uqp->qpn; + err = mlx5_cmd_update_root_ft(root->dev, new_root_ft, + qpn, false); + if (err) + break; } } - root->root_ft = new_root_ft; + + if (err) + mlx5_core_warn(root->dev, + "Update root flow table of id(%u) qpn(%d) failed\n", + ft->id, qpn); + else + root->root_ft = new_root_ft; + return 0; } @@ -1817,7 +2064,7 @@ static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns, return ERR_PTR(-ENOMEM); fs_prio->node.type = FS_TYPE_PRIO; - tree_init_node(&fs_prio->node, 1, NULL); + tree_init_node(&fs_prio->node, NULL, NULL); tree_add_node(&fs_prio->node, &ns->node); fs_prio->num_levels = num_levels; fs_prio->prio = prio; @@ -1843,7 +2090,7 @@ static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio) return ERR_PTR(-ENOMEM); fs_init_namespace(ns); - tree_init_node(&ns->node, 1, NULL); + tree_init_node(&ns->node, NULL, NULL); tree_add_node(&ns->node, &prio->node); list_add_tail(&ns->node.list, &prio->node.children); @@ -1965,10 +2212,12 @@ static struct mlx5_flow_root_namespace *create_root_ns(struct mlx5_flow_steering root_ns->dev = steering->dev; root_ns->table_type = table_type; + INIT_LIST_HEAD(&root_ns->underlay_qpns); + ns = &root_ns->ns; fs_init_namespace(ns); mutex_init(&root_ns->chain_lock); - tree_init_node(&ns->node, 1, NULL); + tree_init_node(&ns->node, NULL, NULL); tree_add_node(&ns->node, NULL); return root_ns; @@ -2066,8 +2315,10 @@ static void clean_tree(struct fs_node *node) struct fs_node *iter; struct fs_node *temp; + tree_get_node(node); list_for_each_entry_safe(iter, temp, &node->children, list) clean_tree(iter); + tree_put_node(node); tree_remove_node(node); } } @@ -2091,6 +2342,8 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev) cleanup_root_ns(steering->sniffer_rx_root_ns); cleanup_root_ns(steering->sniffer_tx_root_ns); mlx5_cleanup_fc_stats(dev); + kmem_cache_destroy(steering->ftes_cache); + kmem_cache_destroy(steering->fgs_cache); kfree(steering); } @@ -2196,6 +2449,16 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) steering->dev = dev; dev->priv.steering = steering; + steering->fgs_cache = kmem_cache_create("mlx5_fs_fgs", + sizeof(struct mlx5_flow_group), 0, + 0, NULL); + steering->ftes_cache = kmem_cache_create("mlx5_fs_ftes", sizeof(struct fs_fte), 0, + 0, NULL); + if (!steering->ftes_cache || !steering->fgs_cache) { + err = -ENOMEM; + goto err; + } + if ((((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && (MLX5_CAP_GEN(dev, nic_flow_table))) || ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) && @@ -2245,17 +2508,76 @@ err: int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn) { struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns; + struct mlx5_ft_underlay_qp *new_uqp; + int err = 0; + + new_uqp = kzalloc(sizeof(*new_uqp), GFP_KERNEL); + if (!new_uqp) + return -ENOMEM; + + mutex_lock(&root->chain_lock); + + if (!root->root_ft) { + err = -EINVAL; + goto update_ft_fail; + } + + err = mlx5_cmd_update_root_ft(dev, root->root_ft, underlay_qpn, false); + if (err) { + mlx5_core_warn(dev, "Failed adding underlay QPN (%u) to root FT err(%d)\n", + underlay_qpn, err); + goto update_ft_fail; + } + + new_uqp->qpn = underlay_qpn; + list_add_tail(&new_uqp->list, &root->underlay_qpns); + + mutex_unlock(&root->chain_lock); - root->underlay_qpn = underlay_qpn; return 0; + +update_ft_fail: + mutex_unlock(&root->chain_lock); + kfree(new_uqp); + return err; } EXPORT_SYMBOL(mlx5_fs_add_rx_underlay_qpn); int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn) { struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns; + struct mlx5_ft_underlay_qp *uqp; + bool found = false; + int err = 0; + + mutex_lock(&root->chain_lock); + list_for_each_entry(uqp, &root->underlay_qpns, list) { + if (uqp->qpn == underlay_qpn) { + found = true; + break; + } + } + + if (!found) { + mlx5_core_warn(dev, "Failed finding underlay qp (%u) in qpn list\n", + underlay_qpn); + err = -EINVAL; + goto out; + } + + err = mlx5_cmd_update_root_ft(dev, root->root_ft, underlay_qpn, true); + if (err) + mlx5_core_warn(dev, "Failed removing underlay QPN (%u) from root FT err(%d)\n", + underlay_qpn, err); + + list_del(&uqp->list); + mutex_unlock(&root->chain_lock); + kfree(uqp); - root->underlay_qpn = 0; return 0; + +out: + mutex_unlock(&root->chain_lock); + return err; } EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 48dd78975062..80f6f3c714c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -66,6 +66,8 @@ enum fs_fte_status { struct mlx5_flow_steering { struct mlx5_core_dev *dev; + struct kmem_cache *fgs_cache; + struct kmem_cache *ftes_cache; struct mlx5_flow_root_namespace *root_ns; struct mlx5_flow_root_namespace *fdb_root_ns; struct mlx5_flow_root_namespace *esw_egress_root_ns; @@ -81,9 +83,12 @@ struct fs_node { struct fs_node *parent; struct fs_node *root; /* lock the node for writing and traversing */ - struct mutex lock; + struct rw_semaphore lock; atomic_t refcount; - void (*remove_func)(struct fs_node *); + bool active; + void (*del_hw_func)(struct fs_node *); + void (*del_sw_func)(struct fs_node *); + atomic_t version; }; struct mlx5_flow_rule { @@ -120,7 +125,6 @@ struct mlx5_flow_table { /* FWD rules that point on this flow table */ struct list_head fwd_rules; u32 flags; - struct ida fte_allocator; struct rhltable fgs_hash; }; @@ -147,6 +151,11 @@ struct mlx5_fc { struct mlx5_fc_cache cache ____cacheline_aligned_in_smp; }; +struct mlx5_ft_underlay_qp { + struct list_head list; + u32 qpn; +}; + #define MLX5_FTE_MATCH_PARAM_RESERVED reserved_at_600 /* Calculate the fte_match_param length and without the reserved length. * Make sure the reserved field is the last. @@ -200,6 +209,7 @@ struct mlx5_flow_group { struct mlx5_flow_group_mask mask; u32 start_index; u32 max_ftes; + struct ida fte_allocator; u32 id; struct rhashtable ftes_hash; struct rhlist_head hash; @@ -212,7 +222,7 @@ struct mlx5_flow_root_namespace { struct mlx5_flow_table *root_ft; /* Should be held when chaining flow tables */ struct mutex chain_lock; - u32 underlay_qpn; + struct list_head underlay_qpns; }; int mlx5_init_fc_stats(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index 43c126c63955..6f338a9219c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -250,3 +250,8 @@ const struct ethtool_ops mlx5i_ethtool_ops = { .get_link_ksettings = mlx5i_get_link_ksettings, .get_link = ethtool_op_get_link, }; + +const struct ethtool_ops mlx5i_pkey_ethtool_ops = { + .get_drvinfo = mlx5i_get_drvinfo, + .get_link = ethtool_op_get_link, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 145e392ab849..abf270d7f556 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -40,8 +40,6 @@ static int mlx5i_open(struct net_device *netdev); static int mlx5i_close(struct net_device *netdev); -static int mlx5i_dev_init(struct net_device *dev); -static void mlx5i_dev_cleanup(struct net_device *dev); static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu); static int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); @@ -70,10 +68,10 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev, } /* Called directly after IPoIB netdevice was created to initialize SW structs */ -static void mlx5i_init(struct mlx5_core_dev *mdev, - struct net_device *netdev, - const struct mlx5e_profile *profile, - void *ppriv) +void mlx5i_init(struct mlx5_core_dev *mdev, + struct net_device *netdev, + const struct mlx5e_profile *profile, + void *ppriv) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); @@ -108,11 +106,69 @@ static void mlx5i_cleanup(struct mlx5e_priv *priv) /* Do nothing .. */ } +int mlx5i_init_underlay_qp(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5i_priv *ipriv = priv->ppriv; + struct mlx5_core_qp *qp = &ipriv->qp; + struct mlx5_qp_context *context; + int ret; + + /* QP states */ + context = kzalloc(sizeof(*context), GFP_KERNEL); + if (!context) + return -ENOMEM; + + context->flags = cpu_to_be32(MLX5_QP_PM_MIGRATED << 11); + context->pri_path.port = 1; + context->pri_path.pkey_index = cpu_to_be16(ipriv->pkey_index); + context->qkey = cpu_to_be32(IB_DEFAULT_Q_KEY); + + ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, context, qp); + if (ret) { + mlx5_core_err(mdev, "Failed to modify qp RST2INIT, err: %d\n", ret); + goto err_qp_modify_to_err; + } + memset(context, 0, sizeof(*context)); + + ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, context, qp); + if (ret) { + mlx5_core_err(mdev, "Failed to modify qp INIT2RTR, err: %d\n", ret); + goto err_qp_modify_to_err; + } + + ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, context, qp); + if (ret) { + mlx5_core_err(mdev, "Failed to modify qp RTR2RTS, err: %d\n", ret); + goto err_qp_modify_to_err; + } + + kfree(context); + return 0; + +err_qp_modify_to_err: + mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2ERR_QP, 0, &context, qp); + kfree(context); + return ret; +} + +void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv) +{ + struct mlx5i_priv *ipriv = priv->ppriv; + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_qp_context context; + int err; + + err = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2RST_QP, 0, &context, + &ipriv->qp); + if (err) + mlx5_core_err(mdev, "Failed to modify qp 2RST, err: %d\n", err); +} + #define MLX5_QP_ENHANCED_ULP_STATELESS_MODE 2 -static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) +int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) { - struct mlx5_qp_context *context = NULL; u32 *in = NULL; void *addr_path; int ret = 0; @@ -140,43 +196,12 @@ static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core goto out; } - /* QP states */ - context = kzalloc(sizeof(*context), GFP_KERNEL); - if (!context) { - ret = -ENOMEM; - goto out; - } - - context->flags = cpu_to_be32(MLX5_QP_PM_MIGRATED << 11); - context->pri_path.port = 1; - context->qkey = cpu_to_be32(IB_DEFAULT_Q_KEY); - - ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, context, qp); - if (ret) { - mlx5_core_err(mdev, "Failed to modify qp RST2INIT, err: %d\n", ret); - goto out; - } - memset(context, 0, sizeof(*context)); - - ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, context, qp); - if (ret) { - mlx5_core_err(mdev, "Failed to modify qp INIT2RTR, err: %d\n", ret); - goto out; - } - - ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, context, qp); - if (ret) { - mlx5_core_err(mdev, "Failed to modify qp RTR2RTS, err: %d\n", ret); - goto out; - } - out: - kfree(context); kvfree(in); return ret; } -static void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) +void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) { mlx5_core_destroy_qp(mdev, qp); } @@ -195,10 +220,14 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv) err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]); if (err) { mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err); - return err; + goto err_destroy_underlay_qp; } return 0; + +err_destroy_underlay_qp: + mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp); + return err; } static void mlx5i_cleanup_tx(struct mlx5e_priv *priv) @@ -249,7 +278,6 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv) static int mlx5i_init_rx(struct mlx5e_priv *priv) { - struct mlx5i_priv *ipriv = priv->ppriv; int err; err = mlx5e_create_indirect_rqt(priv); @@ -268,18 +296,12 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) if (err) goto err_destroy_indirect_tirs; - err = mlx5_fs_add_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn); - if (err) - goto err_destroy_direct_tirs; - err = mlx5i_create_flow_steering(priv); if (err) - goto err_remove_rx_underlay_qpn; + goto err_destroy_direct_tirs; return 0; -err_remove_rx_underlay_qpn: - mlx5_fs_remove_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn); err_destroy_direct_tirs: mlx5e_destroy_direct_tirs(priv); err_destroy_indirect_tirs: @@ -293,9 +315,6 @@ err_destroy_indirect_rqts: static void mlx5i_cleanup_rx(struct mlx5e_priv *priv) { - struct mlx5i_priv *ipriv = priv->ppriv; - - mlx5_fs_remove_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn); mlx5i_destroy_flow_steering(priv); mlx5e_destroy_direct_tirs(priv); mlx5e_destroy_indirect_tirs(priv); @@ -351,7 +370,7 @@ out: return err; } -static int mlx5i_dev_init(struct net_device *dev) +int mlx5i_dev_init(struct net_device *dev) { struct mlx5e_priv *priv = mlx5i_epriv(dev); struct mlx5i_priv *ipriv = priv->ppriv; @@ -361,6 +380,9 @@ static int mlx5i_dev_init(struct net_device *dev) dev->dev_addr[2] = (ipriv->qp.qpn >> 8) & 0xff; dev->dev_addr[3] = (ipriv->qp.qpn) & 0xff; + /* Add QPN to net-device mapping to HT */ + mlx5i_pkey_add_qpn(dev ,ipriv->qp.qpn); + return 0; } @@ -378,63 +400,84 @@ static int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } } -static void mlx5i_dev_cleanup(struct net_device *dev) +void mlx5i_dev_cleanup(struct net_device *dev) { struct mlx5e_priv *priv = mlx5i_epriv(dev); - struct mlx5_core_dev *mdev = priv->mdev; - struct mlx5i_priv *ipriv = priv->ppriv; - struct mlx5_qp_context context; + struct mlx5i_priv *ipriv = priv->ppriv; + + mlx5i_uninit_underlay_qp(priv); - /* detach qp from flow-steering by reset it */ - mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2RST_QP, 0, &context, &ipriv->qp); + /* Delete QPN to net-device mapping from HT */ + mlx5i_pkey_del_qpn(dev, ipriv->qp.qpn); } static int mlx5i_open(struct net_device *netdev) { - struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5e_priv *epriv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = epriv->ppriv; + struct mlx5_core_dev *mdev = epriv->mdev; int err; - mutex_lock(&priv->state_lock); + mutex_lock(&epriv->state_lock); - set_bit(MLX5E_STATE_OPENED, &priv->state); + set_bit(MLX5E_STATE_OPENED, &epriv->state); - err = mlx5e_open_channels(priv, &priv->channels); - if (err) + err = mlx5i_init_underlay_qp(epriv); + if (err) { + mlx5_core_warn(mdev, "prepare underlay qp state failed, %d\n", err); goto err_clear_state_opened_flag; + } - mlx5e_refresh_tirs(priv, false); - mlx5e_activate_priv_channels(priv); - mlx5e_timestamp_init(priv); + err = mlx5_fs_add_rx_underlay_qpn(mdev, ipriv->qp.qpn); + if (err) { + mlx5_core_warn(mdev, "attach underlay qp to ft failed, %d\n", err); + goto err_reset_qp; + } - mutex_unlock(&priv->state_lock); + err = mlx5e_open_channels(epriv, &epriv->channels); + if (err) + goto err_remove_fs_underlay_qp; + + mlx5e_refresh_tirs(epriv, false); + mlx5e_activate_priv_channels(epriv); + mlx5e_timestamp_set(epriv); + + mutex_unlock(&epriv->state_lock); return 0; +err_remove_fs_underlay_qp: + mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn); +err_reset_qp: + mlx5i_uninit_underlay_qp(epriv); err_clear_state_opened_flag: - clear_bit(MLX5E_STATE_OPENED, &priv->state); - mutex_unlock(&priv->state_lock); + clear_bit(MLX5E_STATE_OPENED, &epriv->state); + mutex_unlock(&epriv->state_lock); return err; } static int mlx5i_close(struct net_device *netdev) { - struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5e_priv *epriv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = epriv->ppriv; + struct mlx5_core_dev *mdev = epriv->mdev; /* May already be CLOSED in case a previous configuration operation * (e.g RX/TX queue size change) that involves close&open failed. */ - mutex_lock(&priv->state_lock); + mutex_lock(&epriv->state_lock); - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + if (!test_bit(MLX5E_STATE_OPENED, &epriv->state)) goto unlock; - clear_bit(MLX5E_STATE_OPENED, &priv->state); + clear_bit(MLX5E_STATE_OPENED, &epriv->state); - mlx5e_timestamp_cleanup(priv); - netif_carrier_off(priv->netdev); - mlx5e_deactivate_priv_channels(priv); - mlx5e_close_channels(&priv->channels); + netif_carrier_off(epriv->netdev); + mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn); + mlx5i_uninit_underlay_qp(epriv); + mlx5e_deactivate_priv_channels(epriv); + mlx5e_close_channels(&epriv->channels);; unlock: - mutex_unlock(&priv->state_lock); + mutex_unlock(&epriv->state_lock); return 0; } @@ -492,6 +535,13 @@ static int mlx5i_xmit(struct net_device *dev, struct sk_buff *skb, return mlx5i_sq_xmit(sq, skb, &mah->av, dqpn, ipriv->qkey); } +static void mlx5i_set_pkey_index(struct net_device *netdev, int id) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + + ipriv->pkey_index = (u16)id; +} + static int mlx5i_check_required_hca_cap(struct mlx5_core_dev *mdev) { if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_IB) @@ -510,12 +560,13 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, const char *name, void (*setup)(struct net_device *)) { - const struct mlx5e_profile *profile = &mlx5i_nic_profile; - int nch = profile->max_nch(mdev); + const struct mlx5e_profile *profile; struct net_device *netdev; struct mlx5i_priv *ipriv; struct mlx5e_priv *epriv; struct rdma_netdev *rn; + bool sub_interface; + int nch; int err; if (mlx5i_check_required_hca_cap(mdev)) { @@ -523,10 +574,15 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, return ERR_PTR(-EOPNOTSUPP); } - /* This function should only be called once per mdev */ - err = mlx5e_create_mdev_resources(mdev); - if (err) - return NULL; + /* TODO: Need to find a better way to check if child device*/ + sub_interface = (mdev->mlx5e_res.pdn != 0); + + if (sub_interface) + profile = mlx5i_pkey_get_profile(); + else + profile = &mlx5i_nic_profile; + + nch = profile->max_nch(mdev); netdev = alloc_netdev_mqs(sizeof(struct mlx5i_priv) + sizeof(struct mlx5e_priv), name, NET_NAME_UNKNOWN, @@ -535,7 +591,7 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, nch); if (!netdev) { mlx5_core_warn(mdev, "alloc_netdev_mqs failed\n"); - goto free_mdev_resources; + return NULL; } ipriv = netdev_priv(netdev); @@ -545,6 +601,20 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, if (!epriv->wq) goto err_free_netdev; + ipriv->sub_interface = sub_interface; + if (!ipriv->sub_interface) { + err = mlx5i_pkey_qpn_ht_init(netdev); + if (err) { + mlx5_core_warn(mdev, "allocate qpn_to_netdev ht failed\n"); + goto destroy_wq; + } + + /* This should only be called once per mdev */ + err = mlx5e_create_mdev_resources(mdev); + if (err) + goto destroy_ht; + } + profile->init(mdev, netdev, profile, ipriv); mlx5e_attach_netdev(epriv); @@ -556,13 +626,16 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, rn->send = mlx5i_xmit; rn->attach_mcast = mlx5i_attach_mcast; rn->detach_mcast = mlx5i_detach_mcast; + rn->set_id = mlx5i_set_pkey_index; return netdev; +destroy_ht: + mlx5i_pkey_qpn_ht_cleanup(netdev); +destroy_wq: + destroy_workqueue(epriv->wq); err_free_netdev: free_netdev(netdev); -free_mdev_resources: - mlx5e_destroy_mdev_resources(mdev); return NULL; } @@ -570,15 +643,18 @@ EXPORT_SYMBOL(mlx5_rdma_netdev_alloc); void mlx5_rdma_netdev_free(struct net_device *netdev) { - struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = priv->ppriv; const struct mlx5e_profile *profile = priv->profile; - struct mlx5_core_dev *mdev = priv->mdev; mlx5e_detach_netdev(priv); profile->cleanup(priv); destroy_workqueue(priv->wq); - free_netdev(netdev); - mlx5e_destroy_mdev_resources(mdev); + if (!ipriv->sub_interface) { + mlx5i_pkey_qpn_ht_cleanup(netdev); + mlx5e_destroy_mdev_resources(priv->mdev); + } + free_netdev(netdev); } EXPORT_SYMBOL(mlx5_rdma_netdev_free); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index a0f405f520f7..49008022c306 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -39,6 +39,7 @@ #define MLX5I_MAX_NUM_TC 1 extern const struct ethtool_ops mlx5i_ethtool_ops; +extern const struct ethtool_ops mlx5i_pkey_ethtool_ops; #define MLX5_IB_GRH_BYTES 40 #define MLX5_IPOIB_ENCAP_LEN 4 @@ -49,10 +50,45 @@ extern const struct ethtool_ops mlx5i_ethtool_ops; struct mlx5i_priv { struct rdma_netdev rn; /* keep this first */ struct mlx5_core_qp qp; + bool sub_interface; u32 qkey; + u16 pkey_index; + struct mlx5i_pkey_qpn_ht *qpn_htbl; char *mlx5e_priv[0]; }; +/* Underlay QP create/destroy functions */ +int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp); +void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp); + +/* Underlay QP state modification init/uninit functions */ +int mlx5i_init_underlay_qp(struct mlx5e_priv *priv); +void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv); + +/* Allocate/Free underlay QPN to net-device hash table */ +int mlx5i_pkey_qpn_ht_init(struct net_device *netdev); +void mlx5i_pkey_qpn_ht_cleanup(struct net_device *netdev); + +/* Add/Remove an underlay QPN to net-device mapping to/from the hash table */ +int mlx5i_pkey_add_qpn(struct net_device *netdev, u32 qpn); +int mlx5i_pkey_del_qpn(struct net_device *netdev, u32 qpn); + +/* Get the net-device corresponding to the given underlay QPN */ +struct net_device *mlx5i_pkey_get_netdev(struct net_device *netdev, u32 qpn); + +/* Shared ndo functionts */ +int mlx5i_dev_init(struct net_device *dev); +void mlx5i_dev_cleanup(struct net_device *dev); + +/* Parent profile functions */ +void mlx5i_init(struct mlx5_core_dev *mdev, + struct net_device *netdev, + const struct mlx5e_profile *profile, + void *ppriv); + +/* Get child interface nic profile */ +const struct mlx5e_profile *mlx5i_pkey_get_profile(void); + /* Extract mlx5e_priv from IPoIB netdev */ #define mlx5i_epriv(netdev) ((void *)(((struct mlx5i_priv *)netdev_priv(netdev))->mlx5e_priv)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c new file mode 100644 index 000000000000..531b02cc979b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -0,0 +1,350 @@ +/* + * Copyright (c) 2017, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/hash.h> +#include "ipoib.h" + +#define MLX5I_MAX_LOG_PKEY_SUP 7 + +struct qpn_to_netdev { + struct net_device *netdev; + struct hlist_node hlist; + u32 underlay_qpn; +}; + +struct mlx5i_pkey_qpn_ht { + struct hlist_head buckets[1 << MLX5I_MAX_LOG_PKEY_SUP]; + spinlock_t ht_lock; /* Synchronise with NAPI */ +}; + +int mlx5i_pkey_qpn_ht_init(struct net_device *netdev) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + struct mlx5i_pkey_qpn_ht *qpn_htbl; + + qpn_htbl = kzalloc(sizeof(*qpn_htbl), GFP_KERNEL); + if (!qpn_htbl) + return -ENOMEM; + + ipriv->qpn_htbl = qpn_htbl; + spin_lock_init(&qpn_htbl->ht_lock); + + return 0; +} + +void mlx5i_pkey_qpn_ht_cleanup(struct net_device *netdev) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + + kfree(ipriv->qpn_htbl); +} + +static struct qpn_to_netdev *mlx5i_find_qpn_to_netdev_node(struct hlist_head *buckets, + u32 qpn) +{ + struct hlist_head *h = &buckets[hash_32(qpn, MLX5I_MAX_LOG_PKEY_SUP)]; + struct qpn_to_netdev *node; + + hlist_for_each_entry(node, h, hlist) { + if (node->underlay_qpn == qpn) + return node; + } + + return NULL; +} + +int mlx5i_pkey_add_qpn(struct net_device *netdev, u32 qpn) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + struct mlx5i_pkey_qpn_ht *ht = ipriv->qpn_htbl; + u8 key = hash_32(qpn, MLX5I_MAX_LOG_PKEY_SUP); + struct qpn_to_netdev *new_node; + + new_node = kzalloc(sizeof(*new_node), GFP_KERNEL); + if (!new_node) + return -ENOMEM; + + new_node->netdev = netdev; + new_node->underlay_qpn = qpn; + spin_lock_bh(&ht->ht_lock); + hlist_add_head(&new_node->hlist, &ht->buckets[key]); + spin_unlock_bh(&ht->ht_lock); + + return 0; +} + +int mlx5i_pkey_del_qpn(struct net_device *netdev, u32 qpn) +{ + struct mlx5e_priv *epriv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = epriv->ppriv; + struct mlx5i_pkey_qpn_ht *ht = ipriv->qpn_htbl; + struct qpn_to_netdev *node; + + node = mlx5i_find_qpn_to_netdev_node(ht->buckets, qpn); + if (!node) { + mlx5_core_warn(epriv->mdev, "QPN to netdev delete from HT failed\n"); + return -EINVAL; + } + + spin_lock_bh(&ht->ht_lock); + hlist_del_init(&node->hlist); + spin_unlock_bh(&ht->ht_lock); + kfree(node); + + return 0; +} + +struct net_device *mlx5i_pkey_get_netdev(struct net_device *netdev, u32 qpn) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + struct qpn_to_netdev *node; + + node = mlx5i_find_qpn_to_netdev_node(ipriv->qpn_htbl->buckets, qpn); + if (!node) + return NULL; + + return node->netdev; +} + +static int mlx5i_pkey_open(struct net_device *netdev); +static int mlx5i_pkey_close(struct net_device *netdev); +static int mlx5i_pkey_dev_init(struct net_device *dev); +static void mlx5i_pkey_dev_cleanup(struct net_device *netdev); +static int mlx5i_pkey_change_mtu(struct net_device *netdev, int new_mtu); + +static const struct net_device_ops mlx5i_pkey_netdev_ops = { + .ndo_open = mlx5i_pkey_open, + .ndo_stop = mlx5i_pkey_close, + .ndo_init = mlx5i_pkey_dev_init, + .ndo_uninit = mlx5i_pkey_dev_cleanup, + .ndo_change_mtu = mlx5i_pkey_change_mtu, +}; + +/* Child NDOs */ +static int mlx5i_pkey_dev_init(struct net_device *dev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(dev); + struct mlx5i_priv *ipriv, *parent_ipriv; + struct net_device *parent_dev; + int parent_ifindex; + + ipriv = priv->ppriv; + + /* Get QPN to netdevice hash table from parent */ + parent_ifindex = dev->netdev_ops->ndo_get_iflink(dev); + parent_dev = dev_get_by_index(dev_net(dev), parent_ifindex); + if (!parent_dev) { + mlx5_core_warn(priv->mdev, "failed to get parent device\n"); + return -EINVAL; + } + + parent_ipriv = netdev_priv(parent_dev); + ipriv->qpn_htbl = parent_ipriv->qpn_htbl; + dev_put(parent_dev); + + return mlx5i_dev_init(dev); +} + +static void mlx5i_pkey_dev_cleanup(struct net_device *netdev) +{ + return mlx5i_dev_cleanup(netdev); +} + +static int mlx5i_pkey_open(struct net_device *netdev) +{ + struct mlx5e_priv *epriv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = epriv->ppriv; + struct mlx5_core_dev *mdev = epriv->mdev; + int err; + + mutex_lock(&epriv->state_lock); + + set_bit(MLX5E_STATE_OPENED, &epriv->state); + + err = mlx5i_init_underlay_qp(epriv); + if (err) { + mlx5_core_warn(mdev, "prepare child underlay qp state failed, %d\n", err); + goto err_release_lock; + } + + err = mlx5_fs_add_rx_underlay_qpn(mdev, ipriv->qp.qpn); + if (err) { + mlx5_core_warn(mdev, "attach child underlay qp to ft failed, %d\n", err); + goto err_unint_underlay_qp; + } + + err = mlx5e_create_tis(mdev, 0 /* tc */, ipriv->qp.qpn, &epriv->tisn[0]); + if (err) { + mlx5_core_warn(mdev, "create child tis failed, %d\n", err); + goto err_remove_rx_uderlay_qp; + } + + err = mlx5e_open_channels(epriv, &epriv->channels); + if (err) { + mlx5_core_warn(mdev, "opening child channels failed, %d\n", err); + goto err_clear_state_opened_flag; + } + mlx5e_refresh_tirs(epriv, false); + mlx5e_activate_priv_channels(epriv); + mutex_unlock(&epriv->state_lock); + + return 0; + +err_clear_state_opened_flag: + mlx5e_destroy_tis(mdev, epriv->tisn[0]); +err_remove_rx_uderlay_qp: + mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn); +err_unint_underlay_qp: + mlx5i_uninit_underlay_qp(epriv); +err_release_lock: + clear_bit(MLX5E_STATE_OPENED, &epriv->state); + mutex_unlock(&epriv->state_lock); + return err; +} + +static int mlx5i_pkey_close(struct net_device *netdev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = priv->ppriv; + struct mlx5_core_dev *mdev = priv->mdev; + + mutex_lock(&priv->state_lock); + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + goto unlock; + + clear_bit(MLX5E_STATE_OPENED, &priv->state); + + netif_carrier_off(priv->netdev); + mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn); + mlx5i_uninit_underlay_qp(priv); + mlx5e_deactivate_priv_channels(priv); + mlx5e_close_channels(&priv->channels); + mlx5e_destroy_tis(mdev, priv->tisn[0]); +unlock: + mutex_unlock(&priv->state_lock); + return 0; +} + +static int mlx5i_pkey_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + + mutex_lock(&priv->state_lock); + netdev->mtu = new_mtu; + mutex_unlock(&priv->state_lock); + + return 0; +} + +/* Called directly after IPoIB netdevice was created to initialize SW structs */ +static void mlx5i_pkey_init(struct mlx5_core_dev *mdev, + struct net_device *netdev, + const struct mlx5e_profile *profile, + void *ppriv) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + + mlx5i_init(mdev, netdev, profile, ppriv); + + /* Override parent ndo */ + netdev->netdev_ops = &mlx5i_pkey_netdev_ops; + + /* Set child limited ethtool support */ + netdev->ethtool_ops = &mlx5i_pkey_ethtool_ops; + + /* Use dummy rqs */ + priv->channels.params.log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE; +} + +/* Called directly before IPoIB netdevice is destroyed to cleanup SW structs */ +static void mlx5i_pkey_cleanup(struct mlx5e_priv *priv) +{ + /* Do nothing .. */ +} + +static int mlx5i_pkey_init_tx(struct mlx5e_priv *priv) +{ + struct mlx5i_priv *ipriv = priv->ppriv; + int err; + + err = mlx5i_create_underlay_qp(priv->mdev, &ipriv->qp); + if (err) { + mlx5_core_warn(priv->mdev, "create child underlay QP failed, %d\n", err); + return err; + } + + return 0; +} + +static void mlx5i_pkey_cleanup_tx(struct mlx5e_priv *priv) +{ + struct mlx5i_priv *ipriv = priv->ppriv; + + mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp); +} + +static int mlx5i_pkey_init_rx(struct mlx5e_priv *priv) +{ + /* Since the rx resources are shared between child and parent, the + * parent interface is taking care of rx resource allocation and init + */ + return 0; +} + +static void mlx5i_pkey_cleanup_rx(struct mlx5e_priv *priv) +{ + /* Since the rx resources are shared between child and parent, the + * parent interface is taking care of rx resource free and de-init + */ +} + +static const struct mlx5e_profile mlx5i_pkey_nic_profile = { + .init = mlx5i_pkey_init, + .cleanup = mlx5i_pkey_cleanup, + .init_tx = mlx5i_pkey_init_tx, + .cleanup_tx = mlx5i_pkey_cleanup_tx, + .init_rx = mlx5i_pkey_init_rx, + .cleanup_rx = mlx5i_pkey_cleanup_rx, + .enable = NULL, + .disable = NULL, + .update_stats = NULL, + .max_nch = mlx5e_get_max_num_channels, + .rx_handlers.handle_rx_cqe = mlx5i_handle_rx_cqe, + .rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */ + .max_tc = MLX5I_MAX_NUM_TC, +}; + +const struct mlx5e_profile *mlx5i_pkey_get_profile(void) +{ + return &mlx5i_pkey_nic_profile; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c new file mode 100644 index 000000000000..fa8aed62b231 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -0,0 +1,525 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/clocksource.h> +#include "en.h" + +enum { + MLX5_CYCLES_SHIFT = 23 +}; + +enum { + MLX5_PIN_MODE_IN = 0x0, + MLX5_PIN_MODE_OUT = 0x1, +}; + +enum { + MLX5_OUT_PATTERN_PULSE = 0x0, + MLX5_OUT_PATTERN_PERIODIC = 0x1, +}; + +enum { + MLX5_EVENT_MODE_DISABLE = 0x0, + MLX5_EVENT_MODE_REPETETIVE = 0x1, + MLX5_EVENT_MODE_ONCE_TILL_ARM = 0x2, +}; + +enum { + MLX5_MTPPS_FS_ENABLE = BIT(0x0), + MLX5_MTPPS_FS_PATTERN = BIT(0x2), + MLX5_MTPPS_FS_PIN_MODE = BIT(0x3), + MLX5_MTPPS_FS_TIME_STAMP = BIT(0x4), + MLX5_MTPPS_FS_OUT_PULSE_DURATION = BIT(0x5), + MLX5_MTPPS_FS_ENH_OUT_PER_ADJ = BIT(0x7), +}; + +static u64 read_internal_timer(const struct cyclecounter *cc) +{ + struct mlx5_clock *clock = container_of(cc, struct mlx5_clock, cycles); + struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, + clock); + + return mlx5_read_internal_timer(mdev) & cc->mask; +} + +static void mlx5_pps_out(struct work_struct *work) +{ + struct mlx5_pps *pps_info = container_of(work, struct mlx5_pps, + out_work); + struct mlx5_clock *clock = container_of(pps_info, struct mlx5_clock, + pps_info); + struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, + clock); + u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; + unsigned long flags; + int i; + + for (i = 0; i < clock->ptp_info.n_pins; i++) { + u64 tstart; + + write_lock_irqsave(&clock->lock, flags); + tstart = clock->pps_info.start[i]; + clock->pps_info.start[i] = 0; + write_unlock_irqrestore(&clock->lock, flags); + if (!tstart) + continue; + + MLX5_SET(mtpps_reg, in, pin, i); + MLX5_SET64(mtpps_reg, in, time_stamp, tstart); + MLX5_SET(mtpps_reg, in, field_select, MLX5_MTPPS_FS_TIME_STAMP); + mlx5_set_mtpps(mdev, in, sizeof(in)); + } +} + +static void mlx5_timestamp_overflow(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct mlx5_clock *clock = container_of(dwork, struct mlx5_clock, + overflow_work); + unsigned long flags; + + write_lock_irqsave(&clock->lock, flags); + timecounter_read(&clock->tc); + write_unlock_irqrestore(&clock->lock, flags); + schedule_delayed_work(&clock->overflow_work, clock->overflow_period); +} + +static int mlx5_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); + u64 ns = timespec64_to_ns(ts); + unsigned long flags; + + write_lock_irqsave(&clock->lock, flags); + timecounter_init(&clock->tc, &clock->cycles, ns); + write_unlock_irqrestore(&clock->lock, flags); + + return 0; +} + +static int mlx5_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) +{ + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); + u64 ns; + unsigned long flags; + + write_lock_irqsave(&clock->lock, flags); + ns = timecounter_read(&clock->tc); + write_unlock_irqrestore(&clock->lock, flags); + + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); + unsigned long flags; + + write_lock_irqsave(&clock->lock, flags); + timecounter_adjtime(&clock->tc, delta); + write_unlock_irqrestore(&clock->lock, flags); + + return 0; +} + +static int mlx5_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) +{ + u64 adj; + u32 diff; + unsigned long flags; + int neg_adj = 0; + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); + + if (delta < 0) { + neg_adj = 1; + delta = -delta; + } + + adj = clock->nominal_c_mult; + adj *= delta; + diff = div_u64(adj, 1000000000ULL); + + write_lock_irqsave(&clock->lock, flags); + timecounter_read(&clock->tc); + clock->cycles.mult = neg_adj ? clock->nominal_c_mult - diff : + clock->nominal_c_mult + diff; + write_unlock_irqrestore(&clock->lock, flags); + + return 0; +} + +static int mlx5_extts_configure(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, + int on) +{ + struct mlx5_clock *clock = + container_of(ptp, struct mlx5_clock, ptp_info); + struct mlx5_core_dev *mdev = + container_of(clock, struct mlx5_core_dev, clock); + u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; + u32 field_select = 0; + u8 pin_mode = 0; + u8 pattern = 0; + int pin = -1; + int err = 0; + + if (!MLX5_PPS_CAP(mdev)) + return -EOPNOTSUPP; + + if (rq->extts.index >= clock->ptp_info.n_pins) + return -EINVAL; + + if (on) { + pin = ptp_find_pin(clock->ptp, PTP_PF_EXTTS, rq->extts.index); + if (pin < 0) + return -EBUSY; + pin_mode = MLX5_PIN_MODE_IN; + pattern = !!(rq->extts.flags & PTP_FALLING_EDGE); + field_select = MLX5_MTPPS_FS_PIN_MODE | + MLX5_MTPPS_FS_PATTERN | + MLX5_MTPPS_FS_ENABLE; + } else { + pin = rq->extts.index; + field_select = MLX5_MTPPS_FS_ENABLE; + } + + MLX5_SET(mtpps_reg, in, pin, pin); + MLX5_SET(mtpps_reg, in, pin_mode, pin_mode); + MLX5_SET(mtpps_reg, in, pattern, pattern); + MLX5_SET(mtpps_reg, in, enable, on); + MLX5_SET(mtpps_reg, in, field_select, field_select); + + err = mlx5_set_mtpps(mdev, in, sizeof(in)); + if (err) + return err; + + return mlx5_set_mtppse(mdev, pin, 0, + MLX5_EVENT_MODE_REPETETIVE & on); +} + +static int mlx5_perout_configure(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, + int on) +{ + struct mlx5_clock *clock = + container_of(ptp, struct mlx5_clock, ptp_info); + struct mlx5_core_dev *mdev = + container_of(clock, struct mlx5_core_dev, clock); + u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; + u64 nsec_now, nsec_delta, time_stamp = 0; + u64 cycles_now, cycles_delta; + struct timespec64 ts; + unsigned long flags; + u32 field_select = 0; + u8 pin_mode = 0; + u8 pattern = 0; + int pin = -1; + int err = 0; + s64 ns; + + if (!MLX5_PPS_CAP(mdev)) + return -EOPNOTSUPP; + + if (rq->perout.index >= clock->ptp_info.n_pins) + return -EINVAL; + + if (on) { + pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, + rq->perout.index); + if (pin < 0) + return -EBUSY; + + pin_mode = MLX5_PIN_MODE_OUT; + pattern = MLX5_OUT_PATTERN_PERIODIC; + ts.tv_sec = rq->perout.period.sec; + ts.tv_nsec = rq->perout.period.nsec; + ns = timespec64_to_ns(&ts); + + if ((ns >> 1) != 500000000LL) + return -EINVAL; + + ts.tv_sec = rq->perout.start.sec; + ts.tv_nsec = rq->perout.start.nsec; + ns = timespec64_to_ns(&ts); + cycles_now = mlx5_read_internal_timer(mdev); + write_lock_irqsave(&clock->lock, flags); + nsec_now = timecounter_cyc2time(&clock->tc, cycles_now); + nsec_delta = ns - nsec_now; + cycles_delta = div64_u64(nsec_delta << clock->cycles.shift, + clock->cycles.mult); + write_unlock_irqrestore(&clock->lock, flags); + time_stamp = cycles_now + cycles_delta; + field_select = MLX5_MTPPS_FS_PIN_MODE | + MLX5_MTPPS_FS_PATTERN | + MLX5_MTPPS_FS_ENABLE | + MLX5_MTPPS_FS_TIME_STAMP; + } else { + pin = rq->perout.index; + field_select = MLX5_MTPPS_FS_ENABLE; + } + + MLX5_SET(mtpps_reg, in, pin, pin); + MLX5_SET(mtpps_reg, in, pin_mode, pin_mode); + MLX5_SET(mtpps_reg, in, pattern, pattern); + MLX5_SET(mtpps_reg, in, enable, on); + MLX5_SET64(mtpps_reg, in, time_stamp, time_stamp); + MLX5_SET(mtpps_reg, in, field_select, field_select); + + err = mlx5_set_mtpps(mdev, in, sizeof(in)); + if (err) + return err; + + return mlx5_set_mtppse(mdev, pin, 0, + MLX5_EVENT_MODE_REPETETIVE & on); +} + +static int mlx5_pps_configure(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, + int on) +{ + struct mlx5_clock *clock = + container_of(ptp, struct mlx5_clock, ptp_info); + + clock->pps_info.enabled = !!on; + return 0; +} + +static int mlx5_ptp_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, + int on) +{ + switch (rq->type) { + case PTP_CLK_REQ_EXTTS: + return mlx5_extts_configure(ptp, rq, on); + case PTP_CLK_REQ_PEROUT: + return mlx5_perout_configure(ptp, rq, on); + case PTP_CLK_REQ_PPS: + return mlx5_pps_configure(ptp, rq, on); + default: + return -EOPNOTSUPP; + } + return 0; +} + +static int mlx5_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + return (func == PTP_PF_PHYSYNC) ? -EOPNOTSUPP : 0; +} + +static const struct ptp_clock_info mlx5_ptp_clock_info = { + .owner = THIS_MODULE, + .name = "mlx5_p2p", + .max_adj = 100000000, + .n_alarm = 0, + .n_ext_ts = 0, + .n_per_out = 0, + .n_pins = 0, + .pps = 0, + .adjfreq = mlx5_ptp_adjfreq, + .adjtime = mlx5_ptp_adjtime, + .gettime64 = mlx5_ptp_gettime, + .settime64 = mlx5_ptp_settime, + .enable = NULL, + .verify = NULL, +}; + +static int mlx5_init_pin_config(struct mlx5_clock *clock) +{ + int i; + + clock->ptp_info.pin_config = + kzalloc(sizeof(*clock->ptp_info.pin_config) * + clock->ptp_info.n_pins, GFP_KERNEL); + if (!clock->ptp_info.pin_config) + return -ENOMEM; + clock->ptp_info.enable = mlx5_ptp_enable; + clock->ptp_info.verify = mlx5_ptp_verify; + clock->ptp_info.pps = 1; + + for (i = 0; i < clock->ptp_info.n_pins; i++) { + snprintf(clock->ptp_info.pin_config[i].name, + sizeof(clock->ptp_info.pin_config[i].name), + "mlx5_pps%d", i); + clock->ptp_info.pin_config[i].index = i; + clock->ptp_info.pin_config[i].func = PTP_PF_NONE; + clock->ptp_info.pin_config[i].chan = i; + } + + return 0; +} + +static void mlx5_get_pps_caps(struct mlx5_core_dev *mdev) +{ + struct mlx5_clock *clock = &mdev->clock; + u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; + + mlx5_query_mtpps(mdev, out, sizeof(out)); + + clock->ptp_info.n_pins = MLX5_GET(mtpps_reg, out, + cap_number_of_pps_pins); + clock->ptp_info.n_ext_ts = MLX5_GET(mtpps_reg, out, + cap_max_num_of_pps_in_pins); + clock->ptp_info.n_per_out = MLX5_GET(mtpps_reg, out, + cap_max_num_of_pps_out_pins); + + clock->pps_info.pin_caps[0] = MLX5_GET(mtpps_reg, out, cap_pin_0_mode); + clock->pps_info.pin_caps[1] = MLX5_GET(mtpps_reg, out, cap_pin_1_mode); + clock->pps_info.pin_caps[2] = MLX5_GET(mtpps_reg, out, cap_pin_2_mode); + clock->pps_info.pin_caps[3] = MLX5_GET(mtpps_reg, out, cap_pin_3_mode); + clock->pps_info.pin_caps[4] = MLX5_GET(mtpps_reg, out, cap_pin_4_mode); + clock->pps_info.pin_caps[5] = MLX5_GET(mtpps_reg, out, cap_pin_5_mode); + clock->pps_info.pin_caps[6] = MLX5_GET(mtpps_reg, out, cap_pin_6_mode); + clock->pps_info.pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode); +} + +void mlx5_pps_event(struct mlx5_core_dev *mdev, + struct mlx5_eqe *eqe) +{ + struct mlx5_clock *clock = &mdev->clock; + struct ptp_clock_event ptp_event; + struct timespec64 ts; + u64 nsec_now, nsec_delta; + u64 cycles_now, cycles_delta; + int pin = eqe->data.pps.pin; + s64 ns; + unsigned long flags; + + switch (clock->ptp_info.pin_config[pin].func) { + case PTP_PF_EXTTS: + if (clock->pps_info.enabled) { + ptp_event.type = PTP_CLOCK_PPSUSR; + ptp_event.pps_times.ts_real = ns_to_timespec64(eqe->data.pps.time_stamp); + } else { + ptp_event.type = PTP_CLOCK_EXTTS; + } + ptp_clock_event(clock->ptp, &ptp_event); + break; + case PTP_PF_PEROUT: + mlx5_ptp_gettime(&clock->ptp_info, &ts); + cycles_now = mlx5_read_internal_timer(mdev); + ts.tv_sec += 1; + ts.tv_nsec = 0; + ns = timespec64_to_ns(&ts); + write_lock_irqsave(&clock->lock, flags); + nsec_now = timecounter_cyc2time(&clock->tc, cycles_now); + nsec_delta = ns - nsec_now; + cycles_delta = div64_u64(nsec_delta << clock->cycles.shift, + clock->cycles.mult); + clock->pps_info.start[pin] = cycles_now + cycles_delta; + schedule_work(&clock->pps_info.out_work); + write_unlock_irqrestore(&clock->lock, flags); + break; + default: + mlx5_core_err(mdev, " Unhandled event\n"); + } +} + +void mlx5_init_clock(struct mlx5_core_dev *mdev) +{ + struct mlx5_clock *clock = &mdev->clock; + u64 ns; + u64 frac = 0; + u32 dev_freq; + + dev_freq = MLX5_CAP_GEN(mdev, device_frequency_khz); + if (!dev_freq) { + mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n"); + return; + } + rwlock_init(&clock->lock); + clock->cycles.read = read_internal_timer; + clock->cycles.shift = MLX5_CYCLES_SHIFT; + clock->cycles.mult = clocksource_khz2mult(dev_freq, + clock->cycles.shift); + clock->nominal_c_mult = clock->cycles.mult; + clock->cycles.mask = CLOCKSOURCE_MASK(41); + + timecounter_init(&clock->tc, &clock->cycles, + ktime_to_ns(ktime_get_real())); + + /* Calculate period in seconds to call the overflow watchdog - to make + * sure counter is checked at least once every wrap around. + */ + ns = cyclecounter_cyc2ns(&clock->cycles, clock->cycles.mask, + frac, &frac); + do_div(ns, NSEC_PER_SEC / 2 / HZ); + clock->overflow_period = ns; + + INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out); + INIT_DELAYED_WORK(&clock->overflow_work, mlx5_timestamp_overflow); + if (clock->overflow_period) + schedule_delayed_work(&clock->overflow_work, 0); + else + mlx5_core_warn(mdev, "invalid overflow period, overflow_work is not scheduled\n"); + + /* Configure the PHC */ + clock->ptp_info = mlx5_ptp_clock_info; + + /* Initialize 1PPS data structures */ + if (MLX5_PPS_CAP(mdev)) + mlx5_get_pps_caps(mdev); + if (clock->ptp_info.n_pins) + mlx5_init_pin_config(clock); + + clock->ptp = ptp_clock_register(&clock->ptp_info, + &mdev->pdev->dev); + if (IS_ERR(clock->ptp)) { + mlx5_core_warn(mdev, "ptp_clock_register failed %ld\n", + PTR_ERR(clock->ptp)); + clock->ptp = NULL; + } +} + +void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) +{ + struct mlx5_clock *clock = &mdev->clock; + + if (!MLX5_CAP_GEN(mdev, device_frequency_khz)) + return; + + if (clock->ptp) { + ptp_clock_unregister(clock->ptp); + clock->ptp = NULL; + } + + cancel_work_sync(&clock->pps_info.out_work); + cancel_delayed_work_sync(&clock->overflow_work); + kfree(clock->ptp_info.pin_config); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h new file mode 100644 index 000000000000..a8eecedd46c2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h @@ -0,0 +1,51 @@ +/* + * Copyright (c) 2017, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __LIB_CLOCK_H__ +#define __LIB_CLOCK_H__ + +void mlx5_init_clock(struct mlx5_core_dev *mdev); +void mlx5_cleanup_clock(struct mlx5_core_dev *mdev); + +static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock, + u64 timestamp) +{ + u64 nsec; + + read_lock(&clock->lock); + nsec = timecounter_cyc2time(&clock->tc, timestamp); + read_unlock(&clock->lock); + + return ns_to_ktime(nsec); +} + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 0d2c8dcd6eae..ecbe9fad22d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -59,6 +59,7 @@ #include "lib/mlx5.h" #include "fpga/core.h" #include "accel/ipsec.h" +#include "lib/clock.h" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox Connect-IB, ConnectX-4 core driver"); @@ -889,6 +890,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_init_reserved_gids(dev); + mlx5_init_clock(dev); + err = mlx5_init_rl_table(dev); if (err) { dev_err(&pdev->dev, "Failed to init rate limiting\n"); @@ -949,6 +952,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_eswitch_cleanup(dev->priv.eswitch); mlx5_mpfs_cleanup(dev); mlx5_cleanup_rl_table(dev); + mlx5_cleanup_clock(dev); mlx5_cleanup_reserved_gids(dev); mlx5_cleanup_mkey_table(dev); mlx5_cleanup_srq_table(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index b7c2900b75f9..8f00de2fe283 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -93,6 +93,7 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); void mlx5_core_page_fault(struct mlx5_core_dev *dev, struct mlx5_pagefault *pfault); +void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe); void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe); void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force); void mlx5_disable_device(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 5cd4df08ce97..e6519f2906a4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -53,6 +53,7 @@ #include <linux/notifier.h> #include <linux/dcbnl.h> #include <linux/inetdevice.h> +#include <linux/netlink.h> #include <net/switchdev.h> #include <net/pkt_cls.h> #include <net/tc_act/tc_mirred.h> @@ -3666,6 +3667,9 @@ static int mlxsw_sp_basic_trap_groups_set(struct mlxsw_core *mlxsw_core) return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); } +static int mlxsw_sp_netdevice_event(struct notifier_block *unused, + unsigned long event, void *ptr); + static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, const struct mlxsw_bus_info *mlxsw_bus_info) { @@ -3735,6 +3739,16 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_router_init; } + /* Initialize netdevice notifier after router is initialized, so that + * the event handler can use router structures. + */ + mlxsw_sp->netdevice_nb.notifier_call = mlxsw_sp_netdevice_event; + err = register_netdevice_notifier(&mlxsw_sp->netdevice_nb); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to register netdev notifier\n"); + goto err_netdev_notifier; + } + err = mlxsw_sp_span_init(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n"); @@ -3768,6 +3782,8 @@ err_dpipe_init: err_acl_init: mlxsw_sp_span_fini(mlxsw_sp); err_span_init: + unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb); +err_netdev_notifier: mlxsw_sp_router_fini(mlxsw_sp); err_router_init: mlxsw_sp_afa_fini(mlxsw_sp); @@ -3794,6 +3810,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) mlxsw_sp_dpipe_fini(mlxsw_sp); mlxsw_sp_acl_fini(mlxsw_sp); mlxsw_sp_span_fini(mlxsw_sp); + unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb); mlxsw_sp_router_fini(mlxsw_sp); mlxsw_sp_afa_fini(mlxsw_sp); mlxsw_sp_counter_pool_fini(mlxsw_sp); @@ -4298,7 +4315,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, if (info->linking) err = mlxsw_sp_port_bridge_join(mlxsw_sp_port, lower_dev, - upper_dev); + upper_dev, + extack); else mlxsw_sp_port_bridge_leave(mlxsw_sp_port, lower_dev, @@ -4389,18 +4407,25 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev, { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct netdev_notifier_changeupper_info *info = ptr; + struct netlink_ext_ack *extack; struct net_device *upper_dev; int err = 0; + extack = netdev_notifier_info_to_extack(&info->info); + switch (event) { case NETDEV_PRECHANGEUPPER: upper_dev = info->upper_dev; - if (!netif_is_bridge_master(upper_dev)) + if (!netif_is_bridge_master(upper_dev)) { + NL_SET_ERR_MSG(extack, "spectrum: VLAN devices only support bridge and VRF uppers"); return -EINVAL; + } if (!info->linking) break; - if (netdev_has_any_upper_dev(upper_dev)) + if (netdev_has_any_upper_dev(upper_dev)) { + NL_SET_ERR_MSG(extack, "spectrum: Enslaving a port to a device that already has an upper device is not supported"); return -EINVAL; + } break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; @@ -4408,7 +4433,8 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev, if (info->linking) err = mlxsw_sp_port_bridge_join(mlxsw_sp_port, vlan_dev, - upper_dev); + upper_dev, + extack); else mlxsw_sp_port_bridge_leave(mlxsw_sp_port, vlan_dev, @@ -4471,13 +4497,17 @@ static bool mlxsw_sp_is_vrf_event(unsigned long event, void *ptr) return netif_is_l3_master(info->upper_dev); } -static int mlxsw_sp_netdevice_event(struct notifier_block *unused, +static int mlxsw_sp_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct mlxsw_sp *mlxsw_sp; int err = 0; - if (event == NETDEV_CHANGEADDR || event == NETDEV_CHANGEMTU) + mlxsw_sp = container_of(nb, struct mlxsw_sp, netdevice_nb); + if (mlxsw_sp_netdev_is_ipip(mlxsw_sp, dev)) + err = mlxsw_sp_netdevice_ipip_event(mlxsw_sp, dev, event, ptr); + else if (event == NETDEV_CHANGEADDR || event == NETDEV_CHANGEMTU) err = mlxsw_sp_netdevice_router_port_event(dev); else if (mlxsw_sp_is_vrf_event(event, ptr)) err = mlxsw_sp_netdevice_vrf_event(dev, event, ptr); @@ -4491,13 +4521,16 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *unused, return notifier_from_errno(err); } -static struct notifier_block mlxsw_sp_netdevice_nb __read_mostly = { - .notifier_call = mlxsw_sp_netdevice_event, +static struct notifier_block mlxsw_sp_inetaddr_valid_nb __read_mostly = { + .notifier_call = mlxsw_sp_inetaddr_valid_event, }; static struct notifier_block mlxsw_sp_inetaddr_nb __read_mostly = { .notifier_call = mlxsw_sp_inetaddr_event, - .priority = 10, /* Must be called before FIB notifier block */ +}; + +static struct notifier_block mlxsw_sp_inet6addr_valid_nb __read_mostly = { + .notifier_call = mlxsw_sp_inet6addr_valid_event, }; static struct notifier_block mlxsw_sp_inet6addr_nb __read_mostly = { @@ -4522,8 +4555,9 @@ static int __init mlxsw_sp_module_init(void) { int err; - register_netdevice_notifier(&mlxsw_sp_netdevice_nb); + register_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb); register_inetaddr_notifier(&mlxsw_sp_inetaddr_nb); + register_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb); register_inet6addr_notifier(&mlxsw_sp_inet6addr_nb); register_netevent_notifier(&mlxsw_sp_router_netevent_nb); @@ -4542,8 +4576,9 @@ err_pci_driver_register: err_core_driver_register: unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb); unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb); + unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb); unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb); - unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb); + unregister_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb); return err; } @@ -4553,8 +4588,9 @@ static void __exit mlxsw_sp_module_exit(void) mlxsw_core_driver_unregister(&mlxsw_sp_driver); unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb); unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb); + unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb); unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb); - unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb); + unregister_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb); } module_init(mlxsw_sp_module_init); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index ae67e6046098..2a2472a09d8c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -161,6 +161,7 @@ struct mlxsw_sp { struct { DECLARE_BITMAP(usage, MLXSW_SP_KVD_LINEAR_SIZE); } kvdl; + struct notifier_block netdevice_nb; struct mlxsw_sp_counter_pool *counter_pool; struct { @@ -326,7 +327,8 @@ void mlxsw_sp_port_vlan_bridge_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan); int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *brport_dev, - struct net_device *br_dev); + struct net_device *br_dev, + struct netlink_ext_ack *extack); void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *brport_dev, struct net_device *br_dev); @@ -389,10 +391,21 @@ int mlxsw_sp_router_netevent_event(struct notifier_block *unused, int mlxsw_sp_netdevice_router_port_event(struct net_device *dev); int mlxsw_sp_inetaddr_event(struct notifier_block *unused, unsigned long event, void *ptr); +int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused, + unsigned long event, void *ptr); int mlxsw_sp_inet6addr_event(struct notifier_block *unused, unsigned long event, void *ptr); +int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused, + unsigned long event, void *ptr); int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, struct netdev_notifier_changeupper_info *info); +bool mlxsw_sp_netdev_is_ipip(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev); +int +mlxsw_sp_netdevice_ipip_event(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev, + unsigned long event, + struct netdev_notifier_changeupper_info *info); void mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan); void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h index 1c2db831d83b..6fb49129ce87 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h @@ -47,7 +47,6 @@ struct mlxsw_sp_ipip_entry { enum mlxsw_sp_ipip_type ipipt; struct net_device *ol_dev; /* Overlay. */ struct mlxsw_sp_rif_ipip_lb *ol_lb; - unsigned int ref_count; /* Number of next hops using the tunnel. */ struct mlxsw_sp_fib_entry *decap_fib_entry; struct list_head ipip_list_node; }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index e0f8ea4ed7af..12d471d2a90b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -731,14 +731,17 @@ static struct mlxsw_sp_fib *mlxsw_sp_vr_fib(const struct mlxsw_sp_vr *vr, } static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, - u32 tb_id) + u32 tb_id, + struct netlink_ext_ack *extack) { struct mlxsw_sp_vr *vr; int err; vr = mlxsw_sp_vr_find_unused(mlxsw_sp); - if (!vr) + if (!vr) { + NL_SET_ERR_MSG(extack, "spectrum: Exceeded number of supported virtual routers"); return ERR_PTR(-EBUSY); + } vr->fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4); if (IS_ERR(vr->fib4)) return ERR_CAST(vr->fib4); @@ -775,14 +778,15 @@ static void mlxsw_sp_vr_destroy(struct mlxsw_sp_vr *vr) vr->fib4 = NULL; } -static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id) +static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id, + struct netlink_ext_ack *extack) { struct mlxsw_sp_vr *vr; tb_id = mlxsw_sp_fix_tb_id(tb_id); vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id); if (!vr) - vr = mlxsw_sp_vr_create(mlxsw_sp, tb_id); + vr = mlxsw_sp_vr_create(mlxsw_sp, tb_id, extack); return vr; } @@ -948,7 +952,8 @@ static u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev) static struct mlxsw_sp_rif * mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_rif_params *params); + const struct mlxsw_sp_rif_params *params, + struct netlink_ext_ack *extack); static struct mlxsw_sp_rif_ipip_lb * mlxsw_sp_ipip_ol_ipip_lb_create(struct mlxsw_sp *mlxsw_sp, @@ -966,7 +971,7 @@ mlxsw_sp_ipip_ol_ipip_lb_create(struct mlxsw_sp *mlxsw_sp, .lb_config = ipip_ops->ol_loopback_config(mlxsw_sp, ol_dev), }; - rif = mlxsw_sp_rif_create(mlxsw_sp, &lb_params.common); + rif = mlxsw_sp_rif_create(mlxsw_sp, &lb_params.common, NULL); if (IS_ERR(rif)) return ERR_CAST(rif); return container_of(rif, struct mlxsw_sp_rif_ipip_lb, common); @@ -1002,9 +1007,8 @@ err_ol_ipip_lb_create: } static void -mlxsw_sp_ipip_entry_destroy(struct mlxsw_sp_ipip_entry *ipip_entry) +mlxsw_sp_ipip_entry_dealloc(struct mlxsw_sp_ipip_entry *ipip_entry) { - WARN_ON(ipip_entry->ref_count > 0); mlxsw_sp_rif_destroy(&ipip_entry->ol_lb->common); kfree(ipip_entry); } @@ -1200,26 +1204,22 @@ mlxsw_sp_ipip_entry_find_decap(struct mlxsw_sp *mlxsw_sp, } static struct mlxsw_sp_ipip_entry * -mlxsw_sp_ipip_entry_get(struct mlxsw_sp *mlxsw_sp, - enum mlxsw_sp_ipip_type ipipt, - struct net_device *ol_dev) +mlxsw_sp_ipip_entry_create(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_ipip_type ipipt, + struct net_device *ol_dev) { u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev); struct mlxsw_sp_router *router = mlxsw_sp->router; - struct mlxsw_sp_fib_entry *decap_fib_entry; struct mlxsw_sp_ipip_entry *ipip_entry; enum mlxsw_sp_l3proto ul_proto; union mlxsw_sp_l3addr saddr; + /* The configuration where several tunnels have the same local address + * in the same underlay table needs special treatment in the HW. That is + * currently not implemented in the driver. + */ list_for_each_entry(ipip_entry, &mlxsw_sp->router->ipip_list, ipip_list_node) { - if (ipip_entry->ol_dev == ol_dev) - goto inc_ref_count; - - /* The configuration where several tunnels have the same local - * address in the same underlay table needs special treatment in - * the HW. That is currently not implemented in the driver. - */ ul_proto = router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto; saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ol_dev); if (mlxsw_sp_ipip_entry_saddr_matches(mlxsw_sp, ul_proto, saddr, @@ -1231,29 +1231,18 @@ mlxsw_sp_ipip_entry_get(struct mlxsw_sp *mlxsw_sp, if (IS_ERR(ipip_entry)) return ipip_entry; - decap_fib_entry = mlxsw_sp_ipip_entry_find_decap(mlxsw_sp, ipip_entry); - if (decap_fib_entry) - mlxsw_sp_ipip_entry_promote_decap(mlxsw_sp, ipip_entry, - decap_fib_entry); - list_add_tail(&ipip_entry->ipip_list_node, &mlxsw_sp->router->ipip_list); -inc_ref_count: - ++ipip_entry->ref_count; return ipip_entry; } static void -mlxsw_sp_ipip_entry_put(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_ipip_entry *ipip_entry) +mlxsw_sp_ipip_entry_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry) { - if (--ipip_entry->ref_count == 0) { - list_del(&ipip_entry->ipip_list_node); - if (ipip_entry->decap_fib_entry) - mlxsw_sp_ipip_entry_demote_decap(mlxsw_sp, ipip_entry); - mlxsw_sp_ipip_entry_destroy(ipip_entry); - } + list_del(&ipip_entry->ipip_list_node); + mlxsw_sp_ipip_entry_dealloc(ipip_entry); } static bool @@ -1295,6 +1284,168 @@ mlxsw_sp_ipip_entry_find_by_decap(struct mlxsw_sp *mlxsw_sp, return NULL; } +static bool mlxsw_sp_netdev_ipip_type(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev, + enum mlxsw_sp_ipip_type *p_type) +{ + struct mlxsw_sp_router *router = mlxsw_sp->router; + const struct mlxsw_sp_ipip_ops *ipip_ops; + enum mlxsw_sp_ipip_type ipipt; + + for (ipipt = 0; ipipt < MLXSW_SP_IPIP_TYPE_MAX; ++ipipt) { + ipip_ops = router->ipip_ops_arr[ipipt]; + if (dev->type == ipip_ops->dev_type) { + if (p_type) + *p_type = ipipt; + return true; + } + } + return false; +} + +bool mlxsw_sp_netdev_is_ipip(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev) +{ + return mlxsw_sp_netdev_ipip_type(mlxsw_sp, dev, NULL); +} + +static struct mlxsw_sp_ipip_entry * +mlxsw_sp_ipip_entry_find_by_ol_dev(struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev) +{ + struct mlxsw_sp_ipip_entry *ipip_entry; + + list_for_each_entry(ipip_entry, &mlxsw_sp->router->ipip_list, + ipip_list_node) + if (ipip_entry->ol_dev == ol_dev) + return ipip_entry; + + return NULL; +} + +static int mlxsw_sp_netdevice_ipip_reg_event(struct mlxsw_sp *mlxsw_sp, + struct net_device *ol_dev) +{ + struct mlxsw_sp_router *router = mlxsw_sp->router; + struct mlxsw_sp_ipip_entry *ipip_entry; + enum mlxsw_sp_ipip_type ipipt; + + mlxsw_sp_netdev_ipip_type(mlxsw_sp, ol_dev, &ipipt); + if (router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, ol_dev, + MLXSW_SP_L3_PROTO_IPV4) || + router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, ol_dev, + MLXSW_SP_L3_PROTO_IPV6)) { + ipip_entry = mlxsw_sp_ipip_entry_create(mlxsw_sp, ipipt, + ol_dev); + if (IS_ERR(ipip_entry)) + return PTR_ERR(ipip_entry); + } + + return 0; +} + +static void mlxsw_sp_netdevice_ipip_unreg_event(struct mlxsw_sp *mlxsw_sp, + struct net_device *ol_dev) +{ + struct mlxsw_sp_ipip_entry *ipip_entry; + + ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); + if (ipip_entry) + mlxsw_sp_ipip_entry_destroy(mlxsw_sp, ipip_entry); +} + +static int mlxsw_sp_netdevice_ipip_up_event(struct mlxsw_sp *mlxsw_sp, + struct net_device *ol_dev) +{ + struct mlxsw_sp_fib_entry *decap_fib_entry; + struct mlxsw_sp_ipip_entry *ipip_entry; + + ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); + if (ipip_entry) { + decap_fib_entry = mlxsw_sp_ipip_entry_find_decap(mlxsw_sp, + ipip_entry); + if (decap_fib_entry) + mlxsw_sp_ipip_entry_promote_decap(mlxsw_sp, ipip_entry, + decap_fib_entry); + } + + return 0; +} + +static void mlxsw_sp_netdevice_ipip_down_event(struct mlxsw_sp *mlxsw_sp, + struct net_device *ol_dev) +{ + struct mlxsw_sp_ipip_entry *ipip_entry; + + ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); + if (ipip_entry && ipip_entry->decap_fib_entry) + mlxsw_sp_ipip_entry_demote_decap(mlxsw_sp, ipip_entry); +} + +static int mlxsw_sp_netdevice_ipip_vrf_event(struct mlxsw_sp *mlxsw_sp, + struct net_device *ol_dev) +{ + struct mlxsw_sp_fib_entry *decap_fib_entry; + struct mlxsw_sp_ipip_entry *ipip_entry; + struct mlxsw_sp_rif_ipip_lb *lb_rif; + + ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); + if (!ipip_entry) + return 0; + + /* When a tunneling device is moved to a different VRF, we need to + * update the backing loopback. Since RIFs can't be edited, we need to + * destroy and recreate it. That might create a window of opportunity + * where RALUE and RATR registers end up referencing a RIF that's + * already gone. RATRs are handled by the RIF destroy, and to take care + * of RALUE, demote the decap route back. + */ + if (ipip_entry->decap_fib_entry) + mlxsw_sp_ipip_entry_demote_decap(mlxsw_sp, ipip_entry); + + lb_rif = mlxsw_sp_ipip_ol_ipip_lb_create(mlxsw_sp, ipip_entry->ipipt, + ol_dev); + if (IS_ERR(lb_rif)) + return PTR_ERR(lb_rif); + mlxsw_sp_rif_destroy(&ipip_entry->ol_lb->common); + ipip_entry->ol_lb = lb_rif; + + if (ol_dev->flags & IFF_UP) { + decap_fib_entry = mlxsw_sp_ipip_entry_find_decap(mlxsw_sp, + ipip_entry); + if (decap_fib_entry) + mlxsw_sp_ipip_entry_promote_decap(mlxsw_sp, ipip_entry, + decap_fib_entry); + } + + return 0; +} + +int mlxsw_sp_netdevice_ipip_event(struct mlxsw_sp *mlxsw_sp, + struct net_device *ol_dev, + unsigned long event, + struct netdev_notifier_changeupper_info *info) +{ + switch (event) { + case NETDEV_REGISTER: + return mlxsw_sp_netdevice_ipip_reg_event(mlxsw_sp, ol_dev); + case NETDEV_UNREGISTER: + mlxsw_sp_netdevice_ipip_unreg_event(mlxsw_sp, ol_dev); + return 0; + case NETDEV_UP: + return mlxsw_sp_netdevice_ipip_up_event(mlxsw_sp, ol_dev); + case NETDEV_DOWN: + mlxsw_sp_netdevice_ipip_down_event(mlxsw_sp, ol_dev); + return 0; + case NETDEV_CHANGEUPPER: + if (netif_is_l3_master(info->upper_dev)) + return mlxsw_sp_netdevice_ipip_vrf_event(mlxsw_sp, + ol_dev); + return 0; + } + return 0; +} + struct mlxsw_sp_neigh_key { struct neighbour *n; }; @@ -2785,36 +2936,16 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp, neigh_release(n); } -static bool mlxsw_sp_netdev_ipip_type(const struct mlxsw_sp *mlxsw_sp, - const struct net_device *dev, - enum mlxsw_sp_ipip_type *p_type) -{ - struct mlxsw_sp_router *router = mlxsw_sp->router; - const struct mlxsw_sp_ipip_ops *ipip_ops; - enum mlxsw_sp_ipip_type ipipt; - - for (ipipt = 0; ipipt < MLXSW_SP_IPIP_TYPE_MAX; ++ipipt) { - ipip_ops = router->ipip_ops_arr[ipipt]; - if (dev->type == ipip_ops->dev_type) { - if (p_type) - *p_type = ipipt; - return true; - } - } - return false; -} - static int mlxsw_sp_nexthop_ipip_init(struct mlxsw_sp *mlxsw_sp, - enum mlxsw_sp_ipip_type ipipt, struct mlxsw_sp_nexthop *nh, struct net_device *ol_dev) { if (!nh->nh_grp->gateway || nh->ipip_entry) return 0; - nh->ipip_entry = mlxsw_sp_ipip_entry_get(mlxsw_sp, ipipt, ol_dev); - if (IS_ERR(nh->ipip_entry)) - return PTR_ERR(nh->ipip_entry); + nh->ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); + if (!nh->ipip_entry) + return -ENOENT; __mlxsw_sp_nexthop_neigh_update(nh, false); return 0; @@ -2829,7 +2960,6 @@ static void mlxsw_sp_nexthop_ipip_fini(struct mlxsw_sp *mlxsw_sp, return; __mlxsw_sp_nexthop_neigh_update(nh, true); - mlxsw_sp_ipip_entry_put(mlxsw_sp, ipip_entry); nh->ipip_entry = NULL; } @@ -2873,7 +3003,7 @@ static int mlxsw_sp_nexthop4_type_init(struct mlxsw_sp *mlxsw_sp, router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev, MLXSW_SP_L3_PROTO_IPV4)) { nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP; - err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev); + err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, nh, dev); if (err) return err; mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common); @@ -3640,20 +3770,6 @@ static int mlxsw_sp_fib_lpm_tree_link(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_fib_lpm_tree_unlink(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib *fib) { - struct mlxsw_sp_prefix_usage req_prefix_usage = {{ 0 } }; - struct mlxsw_sp_lpm_tree *lpm_tree; - - /* Aggregate prefix lengths across all virtual routers to make - * sure we only have used prefix lengths in the LPM tree. - */ - mlxsw_sp_vrs_prefixes(mlxsw_sp, fib->proto, &req_prefix_usage); - lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, - fib->proto); - if (IS_ERR(lpm_tree)) - goto err_tree_get; - mlxsw_sp_vrs_lpm_tree_replace(mlxsw_sp, fib, lpm_tree); - -err_tree_get: if (!mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) return; mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, fib); @@ -3725,7 +3841,7 @@ mlxsw_sp_fib_node_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id, const void *addr, struct mlxsw_sp_vr *vr; int err; - vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id); + vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id, NULL); if (IS_ERR(vr)) return ERR_CAST(vr); fib = mlxsw_sp_vr_fib(vr, proto); @@ -4149,7 +4265,7 @@ static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp, router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev, MLXSW_SP_L3_PROTO_IPV6)) { nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP; - err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev); + err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, nh, dev); if (err) return err; mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common); @@ -4764,7 +4880,7 @@ static int mlxsw_sp_router_fibmr_add(struct mlxsw_sp *mlxsw_sp, if (mlxsw_sp->router->aborted) return 0; - vr = mlxsw_sp_vr_get(mlxsw_sp, men_info->tb_id); + vr = mlxsw_sp_vr_get(mlxsw_sp, men_info->tb_id, NULL); if (IS_ERR(vr)) return PTR_ERR(vr); @@ -4797,7 +4913,7 @@ mlxsw_sp_router_fibmr_vif_add(struct mlxsw_sp *mlxsw_sp, if (mlxsw_sp->router->aborted) return 0; - vr = mlxsw_sp_vr_get(mlxsw_sp, ven_info->tb_id); + vr = mlxsw_sp_vr_get(mlxsw_sp, ven_info->tb_id, NULL); if (IS_ERR(vr)) return PTR_ERR(vr); @@ -5093,25 +5209,35 @@ static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work) static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work, struct fib_notifier_info *info) { + struct fib_entry_notifier_info *fen_info; + struct fib_rule_notifier_info *fr_info; + struct fib_nh_notifier_info *fnh_info; + switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: /* fall through */ case FIB_EVENT_ENTRY_APPEND: /* fall through */ case FIB_EVENT_ENTRY_ADD: /* fall through */ case FIB_EVENT_ENTRY_DEL: - memcpy(&fib_work->fen_info, info, sizeof(fib_work->fen_info)); - /* Take referece on fib_info to prevent it from being + fen_info = container_of(info, struct fib_entry_notifier_info, + info); + fib_work->fen_info = *fen_info; + /* Take reference on fib_info to prevent it from being * freed while work is queued. Release it afterwards. */ fib_info_hold(fib_work->fen_info.fi); break; case FIB_EVENT_RULE_ADD: /* fall through */ case FIB_EVENT_RULE_DEL: - memcpy(&fib_work->fr_info, info, sizeof(fib_work->fr_info)); + fr_info = container_of(info, struct fib_rule_notifier_info, + info); + fib_work->fr_info = *fr_info; fib_rule_get(fib_work->fr_info.rule); break; case FIB_EVENT_NH_ADD: /* fall through */ case FIB_EVENT_NH_DEL: - memcpy(&fib_work->fnh_info, info, sizeof(fib_work->fnh_info)); + fnh_info = container_of(info, struct fib_nh_notifier_info, + info); + fib_work->fnh_info = *fnh_info; fib_info_hold(fib_work->fnh_info.fib_nh->nh_parent); break; } @@ -5120,16 +5246,23 @@ static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work, static void mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work, struct fib_notifier_info *info) { + struct fib6_entry_notifier_info *fen6_info; + struct fib_rule_notifier_info *fr_info; + switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: /* fall through */ case FIB_EVENT_ENTRY_ADD: /* fall through */ case FIB_EVENT_ENTRY_DEL: - memcpy(&fib_work->fen6_info, info, sizeof(fib_work->fen6_info)); + fen6_info = container_of(info, struct fib6_entry_notifier_info, + info); + fib_work->fen6_info = *fen6_info; rt6_hold(fib_work->fen6_info.rt); break; case FIB_EVENT_RULE_ADD: /* fall through */ case FIB_EVENT_RULE_DEL: - memcpy(&fib_work->fr_info, info, sizeof(fib_work->fr_info)); + fr_info = container_of(info, struct fib_rule_notifier_info, + info); + fib_work->fr_info = *fr_info; fib_rule_get(fib_work->fr_info.rule); break; } @@ -5360,7 +5493,8 @@ const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif) static struct mlxsw_sp_rif * mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_rif_params *params) + const struct mlxsw_sp_rif_params *params, + struct netlink_ext_ack *extack) { u32 tb_id = l3mdev_fib_table(params->dev); const struct mlxsw_sp_rif_ops *ops; @@ -5374,14 +5508,16 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, type = mlxsw_sp_dev_rif_type(mlxsw_sp, params->dev); ops = mlxsw_sp->router->rif_ops_arr[type]; - vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN); + vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN, extack); if (IS_ERR(vr)) return ERR_CAST(vr); vr->rif_count++; err = mlxsw_sp_rif_index_alloc(mlxsw_sp, &rif_index); - if (err) + if (err) { + NL_SET_ERR_MSG(extack, "spectrum: Exceeded number of supported router interfaces"); goto err_rif_index_alloc; + } rif = mlxsw_sp_rif_alloc(ops->rif_size, rif_index, vr->id, params->dev); if (!rif) { @@ -5468,7 +5604,8 @@ mlxsw_sp_rif_subport_params_init(struct mlxsw_sp_rif_params *params, static int mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan, - struct net_device *l3_dev) + struct net_device *l3_dev, + struct netlink_ext_ack *extack) { struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port; struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; @@ -5484,7 +5621,7 @@ mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan, }; mlxsw_sp_rif_subport_params_init(¶ms, mlxsw_sp_port_vlan); - rif = mlxsw_sp_rif_create(mlxsw_sp, ¶ms); + rif = mlxsw_sp_rif_create(mlxsw_sp, ¶ms, extack); if (IS_ERR(rif)) return PTR_ERR(rif); } @@ -5539,7 +5676,8 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan) static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev, struct net_device *port_dev, - unsigned long event, u16 vid) + unsigned long event, u16 vid, + struct netlink_ext_ack *extack) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev); struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; @@ -5551,7 +5689,7 @@ static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev, switch (event) { case NETDEV_UP: return mlxsw_sp_port_vlan_router_join(mlxsw_sp_port_vlan, - l3_dev); + l3_dev, extack); case NETDEV_DOWN: mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan); break; @@ -5561,19 +5699,22 @@ static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev, } static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev, - unsigned long event) + unsigned long event, + struct netlink_ext_ack *extack) { if (netif_is_bridge_port(port_dev) || netif_is_lag_port(port_dev) || netif_is_ovs_port(port_dev)) return 0; - return mlxsw_sp_inetaddr_port_vlan_event(port_dev, port_dev, event, 1); + return mlxsw_sp_inetaddr_port_vlan_event(port_dev, port_dev, event, 1, + extack); } static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev, struct net_device *lag_dev, - unsigned long event, u16 vid) + unsigned long event, u16 vid, + struct netlink_ext_ack *extack) { struct net_device *port_dev; struct list_head *iter; @@ -5583,7 +5724,8 @@ static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev, if (mlxsw_sp_port_dev_check(port_dev)) { err = mlxsw_sp_inetaddr_port_vlan_event(l3_dev, port_dev, - event, vid); + event, vid, + extack); if (err) return err; } @@ -5593,16 +5735,19 @@ static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev, } static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev, - unsigned long event) + unsigned long event, + struct netlink_ext_ack *extack) { if (netif_is_bridge_port(lag_dev)) return 0; - return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1); + return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1, + extack); } static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev, - unsigned long event) + unsigned long event, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev); struct mlxsw_sp_rif_params params = { @@ -5612,7 +5757,7 @@ static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev, switch (event) { case NETDEV_UP: - rif = mlxsw_sp_rif_create(mlxsw_sp, ¶ms); + rif = mlxsw_sp_rif_create(mlxsw_sp, ¶ms, extack); if (IS_ERR(rif)) return PTR_ERR(rif); break; @@ -5626,7 +5771,8 @@ static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev, } static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev, - unsigned long event) + unsigned long event, + struct netlink_ext_ack *extack) { struct net_device *real_dev = vlan_dev_real_dev(vlan_dev); u16 vid = vlan_dev_vlan_id(vlan_dev); @@ -5636,27 +5782,28 @@ static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev, if (mlxsw_sp_port_dev_check(real_dev)) return mlxsw_sp_inetaddr_port_vlan_event(vlan_dev, real_dev, - event, vid); + event, vid, extack); else if (netif_is_lag_master(real_dev)) return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event, - vid); + vid, extack); else if (netif_is_bridge_master(real_dev) && br_vlan_enabled(real_dev)) - return mlxsw_sp_inetaddr_bridge_event(vlan_dev, event); + return mlxsw_sp_inetaddr_bridge_event(vlan_dev, event, extack); return 0; } static int __mlxsw_sp_inetaddr_event(struct net_device *dev, - unsigned long event) + unsigned long event, + struct netlink_ext_ack *extack) { if (mlxsw_sp_port_dev_check(dev)) - return mlxsw_sp_inetaddr_port_event(dev, event); + return mlxsw_sp_inetaddr_port_event(dev, event, extack); else if (netif_is_lag_master(dev)) - return mlxsw_sp_inetaddr_lag_event(dev, event); + return mlxsw_sp_inetaddr_lag_event(dev, event, extack); else if (netif_is_bridge_master(dev)) - return mlxsw_sp_inetaddr_bridge_event(dev, event); + return mlxsw_sp_inetaddr_bridge_event(dev, event, extack); else if (is_vlan_dev(dev)) - return mlxsw_sp_inetaddr_vlan_event(dev, event); + return mlxsw_sp_inetaddr_vlan_event(dev, event, extack); else return 0; } @@ -5670,6 +5817,32 @@ int mlxsw_sp_inetaddr_event(struct notifier_block *unused, struct mlxsw_sp_rif *rif; int err = 0; + /* NETDEV_UP event is handled by mlxsw_sp_inetaddr_valid_event */ + if (event == NETDEV_UP) + goto out; + + mlxsw_sp = mlxsw_sp_lower_get(dev); + if (!mlxsw_sp) + goto out; + + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!mlxsw_sp_rif_should_config(rif, dev, event)) + goto out; + + err = __mlxsw_sp_inetaddr_event(dev, event, NULL); +out: + return notifier_from_errno(err); +} + +int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct in_validator_info *ivi = (struct in_validator_info *) ptr; + struct net_device *dev = ivi->ivi_dev->dev; + struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_rif *rif; + int err = 0; + mlxsw_sp = mlxsw_sp_lower_get(dev); if (!mlxsw_sp) goto out; @@ -5678,7 +5851,7 @@ int mlxsw_sp_inetaddr_event(struct notifier_block *unused, if (!mlxsw_sp_rif_should_config(rif, dev, event)) goto out; - err = __mlxsw_sp_inetaddr_event(dev, event); + err = __mlxsw_sp_inetaddr_event(dev, event, ivi->extack); out: return notifier_from_errno(err); } @@ -5707,7 +5880,7 @@ static void mlxsw_sp_inet6addr_event_work(struct work_struct *work) if (!mlxsw_sp_rif_should_config(rif, dev, event)) goto out; - __mlxsw_sp_inetaddr_event(dev, event); + __mlxsw_sp_inetaddr_event(dev, event, NULL); out: rtnl_unlock(); dev_put(dev); @@ -5722,6 +5895,10 @@ int mlxsw_sp_inet6addr_event(struct notifier_block *unused, struct mlxsw_sp_inet6addr_event_work *inet6addr_work; struct net_device *dev = if6->idev->dev; + /* NETDEV_UP event is handled by mlxsw_sp_inet6addr_valid_event */ + if (event == NETDEV_UP) + return NOTIFY_DONE; + if (!mlxsw_sp_port_dev_lower_find_rcu(dev)) return NOTIFY_DONE; @@ -5738,6 +5915,28 @@ int mlxsw_sp_inet6addr_event(struct notifier_block *unused, return NOTIFY_DONE; } +int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct in6_validator_info *i6vi = (struct in6_validator_info *) ptr; + struct net_device *dev = i6vi->i6vi_dev->dev; + struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_rif *rif; + int err = 0; + + mlxsw_sp = mlxsw_sp_lower_get(dev); + if (!mlxsw_sp) + goto out; + + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!mlxsw_sp_rif_should_config(rif, dev, event)) + goto out; + + err = __mlxsw_sp_inetaddr_event(dev, event, i6vi->extack); +out: + return notifier_from_errno(err); +} + static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index, const char *mac, int mtu) { @@ -5810,7 +6009,8 @@ err_rif_edit: } static int mlxsw_sp_port_vrf_join(struct mlxsw_sp *mlxsw_sp, - struct net_device *l3_dev) + struct net_device *l3_dev, + struct netlink_ext_ack *extack) { struct mlxsw_sp_rif *rif; @@ -5819,9 +6019,9 @@ static int mlxsw_sp_port_vrf_join(struct mlxsw_sp *mlxsw_sp, */ rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev); if (rif) - __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN); + __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN, extack); - return __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_UP); + return __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_UP, extack); } static void mlxsw_sp_port_vrf_leave(struct mlxsw_sp *mlxsw_sp, @@ -5832,7 +6032,7 @@ static void mlxsw_sp_port_vrf_leave(struct mlxsw_sp *mlxsw_sp, rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev); if (!rif) return; - __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN); + __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN, NULL); } int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, @@ -5848,10 +6048,14 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, case NETDEV_PRECHANGEUPPER: return 0; case NETDEV_CHANGEUPPER: - if (info->linking) - err = mlxsw_sp_port_vrf_join(mlxsw_sp, l3_dev); - else + if (info->linking) { + struct netlink_ext_ack *extack; + + extack = netdev_notifier_info_to_extack(&info->info); + err = mlxsw_sp_port_vrf_join(mlxsw_sp, l3_dev, extack); + } else { mlxsw_sp_port_vrf_leave(mlxsw_sp, l3_dev); + } break; } @@ -5957,7 +6161,7 @@ static int mlxsw_sp_rif_vlan_fid_op(struct mlxsw_sp_rif *rif, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); } -static u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp) +u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp) { return mlxsw_core_max_ports(mlxsw_sp->core) + 1; } @@ -6158,7 +6362,7 @@ mlxsw_sp_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif) struct mlxsw_sp_vr *ul_vr; int err; - ul_vr = mlxsw_sp_vr_get(mlxsw_sp, ul_tb_id); + ul_vr = mlxsw_sp_vr_get(mlxsw_sp, ul_tb_id, NULL); if (IS_ERR(ul_vr)) return PTR_ERR(ul_vr); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index 3d449180b035..3f2d840cb285 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -70,6 +70,7 @@ u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif); u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *rif); u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *rif); int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif); +u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp); const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif); int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 0f9eac5f4ebf..7b8548e25ae7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -46,8 +46,10 @@ #include <linux/workqueue.h> #include <linux/jiffies.h> #include <linux/rtnetlink.h> +#include <linux/netlink.h> #include <net/switchdev.h> +#include "spectrum_router.h" #include "spectrum.h" #include "core.h" #include "reg.h" @@ -78,7 +80,8 @@ struct mlxsw_sp_bridge_device { struct list_head ports_list; struct list_head mids_list; u8 vlan_enabled:1, - multicast_enabled:1; + multicast_enabled:1, + mrouter:1; const struct mlxsw_sp_bridge_ops *ops; }; @@ -107,7 +110,8 @@ struct mlxsw_sp_bridge_vlan { struct mlxsw_sp_bridge_ops { int (*port_join)(struct mlxsw_sp_bridge_device *bridge_device, struct mlxsw_sp_bridge_port *bridge_port, - struct mlxsw_sp_port *mlxsw_sp_port); + struct mlxsw_sp_port *mlxsw_sp_port, + struct netlink_ext_ack *extack); void (*port_leave)(struct mlxsw_sp_bridge_device *bridge_device, struct mlxsw_sp_bridge_port *bridge_port, struct mlxsw_sp_port *mlxsw_sp_port); @@ -168,6 +172,7 @@ mlxsw_sp_bridge_device_create(struct mlxsw_sp_bridge *bridge, bridge_device->dev = br_dev; bridge_device->vlan_enabled = vlan_enabled; bridge_device->multicast_enabled = br_multicast_enabled(br_dev); + bridge_device->mrouter = br_multicast_router(br_dev); INIT_LIST_HEAD(&bridge_device->ports_list); if (vlan_enabled) { bridge->vlan_enabled_exists = true; @@ -810,6 +815,60 @@ static int mlxsw_sp_port_mc_disabled_set(struct mlxsw_sp_port *mlxsw_sp_port, return 0; } +static int mlxsw_sp_smid_router_port_set(struct mlxsw_sp *mlxsw_sp, + u16 mid_idx, bool add) +{ + char *smid_pl; + int err; + + smid_pl = kmalloc(MLXSW_REG_SMID_LEN, GFP_KERNEL); + if (!smid_pl) + return -ENOMEM; + + mlxsw_reg_smid_pack(smid_pl, mid_idx, + mlxsw_sp_router_port(mlxsw_sp), add); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(smid), smid_pl); + kfree(smid_pl); + return err; +} + +static void +mlxsw_sp_bridge_mrouter_update_mdb(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_bridge_device *bridge_device, + bool add) +{ + struct mlxsw_sp_mid *mid; + + list_for_each_entry(mid, &bridge_device->mids_list, list) + mlxsw_sp_smid_router_port_set(mlxsw_sp, mid->mid, add); +} + +static int +mlxsw_sp_port_attr_br_mrouter_set(struct mlxsw_sp_port *mlxsw_sp_port, + struct switchdev_trans *trans, + struct net_device *orig_dev, + bool is_mrouter) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_bridge_device *bridge_device; + + if (switchdev_trans_ph_prepare(trans)) + return 0; + + /* It's possible we failed to enslave the port, yet this + * operation is executed due to it being deferred. + */ + bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, orig_dev); + if (!bridge_device) + return 0; + + if (bridge_device->mrouter != is_mrouter) + mlxsw_sp_bridge_mrouter_update_mdb(mlxsw_sp, bridge_device, + is_mrouter); + bridge_device->mrouter = is_mrouter; + return 0; +} + static int mlxsw_sp_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct switchdev_trans *trans) @@ -847,6 +906,11 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev, attr->orig_dev, attr->u.mc_disabled); break; + case SWITCHDEV_ATTR_ID_BRIDGE_MROUTER: + err = mlxsw_sp_port_attr_br_mrouter_set(mlxsw_sp_port, trans, + attr->orig_dev, + attr->u.mrouter); + break; default: err = -EOPNOTSUPP; break; @@ -1241,7 +1305,8 @@ static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr, } static int mlxsw_sp_port_smid_full_entry(struct mlxsw_sp *mlxsw_sp, u16 mid_idx, - long *ports_bitmap) + long *ports_bitmap, + bool set_router_port) { char *smid_pl; int err, i; @@ -1256,9 +1321,15 @@ static int mlxsw_sp_port_smid_full_entry(struct mlxsw_sp *mlxsw_sp, u16 mid_idx, mlxsw_reg_smid_port_mask_set(smid_pl, i, 1); } + mlxsw_reg_smid_port_mask_set(smid_pl, + mlxsw_sp_router_port(mlxsw_sp), 1); + for_each_set_bit(i, ports_bitmap, mlxsw_core_max_ports(mlxsw_sp->core)) mlxsw_reg_smid_port_set(smid_pl, i, 1); + mlxsw_reg_smid_port_set(smid_pl, mlxsw_sp_router_port(mlxsw_sp), + set_router_port); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(smid), smid_pl); kfree(smid_pl); return err; @@ -1362,7 +1433,8 @@ mlxsw_sp_mc_write_mdb_entry(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_mc_get_mrouters_bitmap(flood_bitmap, bridge_device, mlxsw_sp); mid->mid = mid_idx; - err = mlxsw_sp_port_smid_full_entry(mlxsw_sp, mid_idx, flood_bitmap); + err = mlxsw_sp_port_smid_full_entry(mlxsw_sp, mid_idx, flood_bitmap, + bridge_device->mrouter); kfree(flood_bitmap); if (err) return false; @@ -1735,12 +1807,15 @@ static const struct switchdev_ops mlxsw_sp_port_switchdev_ops = { static int mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device, struct mlxsw_sp_bridge_port *bridge_port, - struct mlxsw_sp_port *mlxsw_sp_port) + struct mlxsw_sp_port *mlxsw_sp_port, + struct netlink_ext_ack *extack) { struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; - if (is_vlan_dev(bridge_port->dev)) + if (is_vlan_dev(bridge_port->dev)) { + NL_SET_ERR_MSG(extack, "spectrum: Can not enslave a VLAN device to a VLAN-aware bridge"); return -EINVAL; + } mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, 1); if (WARN_ON(!mlxsw_sp_port_vlan)) @@ -1797,13 +1872,16 @@ mlxsw_sp_port_is_br_member(const struct mlxsw_sp_port *mlxsw_sp_port, static int mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device, struct mlxsw_sp_bridge_port *bridge_port, - struct mlxsw_sp_port *mlxsw_sp_port) + struct mlxsw_sp_port *mlxsw_sp_port, + struct netlink_ext_ack *extack) { struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; u16 vid; - if (!is_vlan_dev(bridge_port->dev)) + if (!is_vlan_dev(bridge_port->dev)) { + NL_SET_ERR_MSG(extack, "spectrum: Only VLAN devices can be enslaved to a VLAN-unaware bridge"); return -EINVAL; + } vid = vlan_dev_vlan_id(bridge_port->dev); mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid); @@ -1811,7 +1889,7 @@ mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device, return -EINVAL; if (mlxsw_sp_port_is_br_member(mlxsw_sp_port, bridge_device->dev)) { - netdev_err(mlxsw_sp_port->dev, "Can't bridge VLAN uppers of the same port\n"); + NL_SET_ERR_MSG(extack, "spectrum: Can not bridge VLAN uppers of the same port"); return -EINVAL; } @@ -1854,7 +1932,8 @@ static const struct mlxsw_sp_bridge_ops mlxsw_sp_bridge_8021d_ops = { int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *brport_dev, - struct net_device *br_dev) + struct net_device *br_dev, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_bridge_device *bridge_device; @@ -1867,7 +1946,7 @@ int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port, bridge_device = bridge_port->bridge_device; err = bridge_device->ops->port_join(bridge_device, bridge_port, - mlxsw_sp_port); + mlxsw_sp_port, extack); if (err) goto err_port_join; diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c index e798fbe08600..52207508744c 100644 --- a/drivers/net/ethernet/micrel/ksz884x.c +++ b/drivers/net/ethernet/micrel/ksz884x.c @@ -4338,11 +4338,11 @@ static void ksz_stop_timer(struct ksz_timer_info *info) } static void ksz_init_timer(struct ksz_timer_info *info, int period, - void (*function)(unsigned long), void *data) + void (*function)(struct timer_list *)) { info->max = 0; info->period = period; - setup_timer(&info->timer, function, (unsigned long)data); + timer_setup(&info->timer, function, 0); } static void ksz_update_timer(struct ksz_timer_info *info) @@ -6689,9 +6689,9 @@ static void mib_read_work(struct work_struct *work) } } -static void mib_monitor(unsigned long ptr) +static void mib_monitor(struct timer_list *t) { - struct dev_info *hw_priv = (struct dev_info *) ptr; + struct dev_info *hw_priv = from_timer(hw_priv, t, mib_timer_info.timer); mib_read_work(&hw_priv->mib_read); @@ -6716,10 +6716,10 @@ static void mib_monitor(unsigned long ptr) * * This routine is run in a kernel timer to monitor the network device. */ -static void dev_monitor(unsigned long ptr) +static void dev_monitor(struct timer_list *t) { - struct net_device *dev = (struct net_device *) ptr; - struct dev_priv *priv = netdev_priv(dev); + struct dev_priv *priv = from_timer(priv, t, monitor_timer_info.timer); + struct net_device *dev = priv->mii_if.dev; struct dev_info *hw_priv = priv->adapter; struct ksz_hw *hw = &hw_priv->hw; struct ksz_port *port = &priv->port; @@ -6789,7 +6789,7 @@ static int __init netdev_init(struct net_device *dev) /* 500 ms timeout */ ksz_init_timer(&priv->monitor_timer_info, 500 * HZ / 1000, - dev_monitor, dev); + dev_monitor); /* 500 ms timeout */ dev->watchdog_timeo = HZ / 2; @@ -7065,7 +7065,7 @@ static int pcidev_init(struct pci_dev *pdev, const struct pci_device_id *id) /* 500 ms timeout */ ksz_init_timer(&hw_priv->mib_timer_info, 500 * HZ / 1000, - mib_monitor, hw_priv); + mib_monitor); for (i = 0; i < hw->dev_count; i++) { dev = alloc_etherdev(sizeof(struct dev_priv)); diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 462eda926b1c..b8983e73265a 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -337,12 +337,6 @@ static const char ethtool_driver_stats_keys[][ETH_GSTRING_LEN] = { #define S2IO_TEST_LEN ARRAY_SIZE(s2io_gstrings) #define S2IO_STRINGS_LEN (S2IO_TEST_LEN * ETH_GSTRING_LEN) -#define S2IO_TIMER_CONF(timer, handle, arg, exp) \ - init_timer(&timer); \ - timer.function = handle; \ - timer.data = (unsigned long)arg; \ - mod_timer(&timer, (jiffies + exp)) \ - /* copy mac addr to def_mac_addr array */ static void do_s2io_copy_mac_addr(struct s2io_nic *sp, int offset, u64 mac_addr) { @@ -4193,9 +4187,9 @@ pci_map_failed: } static void -s2io_alarm_handle(unsigned long data) +s2io_alarm_handle(struct timer_list *t) { - struct s2io_nic *sp = (struct s2io_nic *)data; + struct s2io_nic *sp = from_timer(sp, t, alarm_timer); struct net_device *dev = sp->dev; s2io_handle_errors(dev); @@ -7186,7 +7180,8 @@ static int s2io_card_up(struct s2io_nic *sp) return -ENODEV; } - S2IO_TIMER_CONF(sp->alarm_timer, s2io_alarm_handle, sp, (HZ/2)); + timer_setup(&sp->alarm_timer, s2io_alarm_handle, 0); + mod_timer(&sp->alarm_timer, jiffies + HZ / 2); set_bit(__S2IO_STATE_CARD_UP, &sp->state); diff --git a/drivers/net/ethernet/neterion/s2io.h b/drivers/net/ethernet/neterion/s2io.h index 6c5997dc8afc..1a24a7218794 100644 --- a/drivers/net/ethernet/neterion/s2io.h +++ b/drivers/net/ethernet/neterion/s2io.h @@ -1094,7 +1094,7 @@ static int s2io_poll_msix(struct napi_struct *napi, int budget); static int s2io_poll_inta(struct napi_struct *napi, int budget); static void s2io_init_pci(struct s2io_nic * sp); static int do_s2io_prog_unicast(struct net_device *dev, u8 *addr); -static void s2io_alarm_handle(unsigned long data); +static void s2io_alarm_handle(struct timer_list *t); static irqreturn_t s2io_msix_ring_handle(int irq, void *dev_id); static irqreturn_t diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 50ea69d88480..5d5b9855e24e 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -2597,9 +2597,9 @@ INTA_MODE: return VXGE_HW_OK; } -static void vxge_poll_vp_reset(unsigned long data) +static void vxge_poll_vp_reset(struct timer_list *t) { - struct vxgedev *vdev = (struct vxgedev *)data; + struct vxgedev *vdev = from_timer(vdev, t, vp_reset_timer); int i, j = 0; for (i = 0; i < vdev->no_of_vpath; i++) { @@ -2616,9 +2616,9 @@ static void vxge_poll_vp_reset(unsigned long data) mod_timer(&vdev->vp_reset_timer, jiffies + HZ / 2); } -static void vxge_poll_vp_lockup(unsigned long data) +static void vxge_poll_vp_lockup(struct timer_list *t) { - struct vxgedev *vdev = (struct vxgedev *)data; + struct vxgedev *vdev = from_timer(vdev, t, vp_lockup_timer); enum vxge_hw_status status = VXGE_HW_OK; struct vxge_vpath *vpath; struct vxge_ring *ring; @@ -2858,12 +2858,12 @@ static int vxge_open(struct net_device *dev) vdev->config.rx_pause_enable); if (vdev->vp_reset_timer.function == NULL) - vxge_os_timer(&vdev->vp_reset_timer, vxge_poll_vp_reset, vdev, + vxge_os_timer(&vdev->vp_reset_timer, vxge_poll_vp_reset, HZ / 2); /* There is no need to check for RxD leak and RxD lookup on Titan1A */ if (vdev->titan1 && vdev->vp_lockup_timer.function == NULL) - vxge_os_timer(&vdev->vp_lockup_timer, vxge_poll_vp_lockup, vdev, + vxge_os_timer(&vdev->vp_lockup_timer, vxge_poll_vp_lockup, HZ / 2); set_bit(__VXGE_STATE_CARD_UP, &vdev->state); diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.h b/drivers/net/ethernet/neterion/vxge/vxge-main.h index 3a79d93b8445..59a57ff5e96a 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.h +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.h @@ -417,12 +417,10 @@ struct vxge_tx_priv { module_param(p, int, 0) static inline -void vxge_os_timer(struct timer_list *timer, void (*func)(unsigned long data), - struct vxgedev *vdev, unsigned long timeout) +void vxge_os_timer(struct timer_list *timer, void (*func)(struct timer_list *), + unsigned long timeout) { - init_timer(timer); - timer->function = func; - timer->data = (unsigned long)vdev; + timer_setup(timer, func, 0); mod_timer(timer, jiffies + timeout); } diff --git a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c index 5f630a24e491..0c3b5dea2858 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c @@ -1209,9 +1209,6 @@ void vxge_hw_ring_rxd_pre_post(struct __vxge_hw_ring *ring, void *rxdh) void vxge_hw_ring_rxd_post_post(struct __vxge_hw_ring *ring, void *rxdh) { struct vxge_hw_ring_rxd_1 *rxdp = (struct vxge_hw_ring_rxd_1 *)rxdh; - struct __vxge_hw_channel *channel; - - channel = &ring->channel; rxdp->control_0 = VXGE_HW_RING_RXD_LIST_OWN_ADAPTER; @@ -1359,11 +1356,8 @@ exit: enum vxge_hw_status vxge_hw_ring_handle_tcode( struct __vxge_hw_ring *ring, void *rxdh, u8 t_code) { - struct __vxge_hw_channel *channel; enum vxge_hw_status status = VXGE_HW_OK; - channel = &ring->channel; - /* If the t_code is not supported and if the * t_code is other than 0x5 (unparseable packet * such as unknown UPV6 header), Drop it !!! @@ -1399,10 +1393,6 @@ exit: static void __vxge_hw_non_offload_db_post(struct __vxge_hw_fifo *fifo, u64 txdl_ptr, u32 num_txds, u32 no_snoop) { - struct __vxge_hw_channel *channel; - - channel = &fifo->channel; - writeq(VXGE_HW_NODBW_TYPE(VXGE_HW_NODBW_TYPE_NODBW) | VXGE_HW_NODBW_LAST_TXD_NUMBER(num_txds) | VXGE_HW_NODBW_GET_NO_SNOOP(no_snoop), @@ -1506,9 +1496,6 @@ void vxge_hw_fifo_txdl_buffer_set(struct __vxge_hw_fifo *fifo, { struct __vxge_hw_fifo_txdl_priv *txdl_priv; struct vxge_hw_fifo_txd *txdp, *txdp_last; - struct __vxge_hw_channel *channel; - - channel = &fifo->channel; txdl_priv = __vxge_hw_fifo_txdl_priv(fifo, txdlh); txdp = (struct vxge_hw_fifo_txd *)txdlh + txdl_priv->frags; @@ -1554,9 +1541,6 @@ void vxge_hw_fifo_txdl_post(struct __vxge_hw_fifo *fifo, void *txdlh) struct __vxge_hw_fifo_txdl_priv *txdl_priv; struct vxge_hw_fifo_txd *txdp_last; struct vxge_hw_fifo_txd *txdp_first; - struct __vxge_hw_channel *channel; - - channel = &fifo->channel; txdl_priv = __vxge_hw_fifo_txdl_priv(fifo, txdlh); txdp_first = txdlh; @@ -1672,10 +1656,7 @@ enum vxge_hw_status vxge_hw_fifo_handle_tcode(struct __vxge_hw_fifo *fifo, void *txdlh, enum vxge_hw_fifo_tcode t_code) { - struct __vxge_hw_channel *channel; - enum vxge_hw_status status = VXGE_HW_OK; - channel = &fifo->channel; if (((t_code & 0x7) < 0) || ((t_code & 0x7) > 0x4)) { status = VXGE_HW_ERR_INVALID_TCODE; diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile index becaacf1554d..bd3b2bd408bc 100644 --- a/drivers/net/ethernet/netronome/nfp/Makefile +++ b/drivers/net/ethernet/netronome/nfp/Makefile @@ -14,6 +14,7 @@ nfp-objs := \ nfpcore/nfp_resource.o \ nfpcore/nfp_rtsym.o \ nfpcore/nfp_target.o \ + nfp_asm.o \ nfp_app.o \ nfp_app_nic.o \ nfp_devlink.o \ diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 239dfbe8a0a1..23fb11a41cc4 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -110,150 +110,7 @@ nfp_prog_offset_to_index(struct nfp_prog *nfp_prog, unsigned int offset) return offset - nfp_prog->start_off; } -/* --- SW reg --- */ -struct nfp_insn_ur_regs { - enum alu_dst_ab dst_ab; - u16 dst; - u16 areg, breg; - bool swap; - bool wr_both; -}; - -struct nfp_insn_re_regs { - enum alu_dst_ab dst_ab; - u8 dst; - u8 areg, breg; - bool swap; - bool wr_both; - bool i8; -}; - -static u16 nfp_swreg_to_unreg(u32 swreg, bool is_dst) -{ - u16 val = FIELD_GET(NN_REG_VAL, swreg); - - switch (FIELD_GET(NN_REG_TYPE, swreg)) { - case NN_REG_GPR_A: - case NN_REG_GPR_B: - case NN_REG_GPR_BOTH: - return val; - case NN_REG_NNR: - return UR_REG_NN | val; - case NN_REG_XFER: - return UR_REG_XFR | val; - case NN_REG_IMM: - if (val & ~0xff) { - pr_err("immediate too large\n"); - return 0; - } - return UR_REG_IMM_encode(val); - case NN_REG_NONE: - return is_dst ? UR_REG_NO_DST : REG_NONE; - default: - pr_err("unrecognized reg encoding %08x\n", swreg); - return 0; - } -} - -static int -swreg_to_unrestricted(u32 dst, u32 lreg, u32 rreg, struct nfp_insn_ur_regs *reg) -{ - memset(reg, 0, sizeof(*reg)); - - /* Decode destination */ - if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_IMM) - return -EFAULT; - - if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_GPR_B) - reg->dst_ab = ALU_DST_B; - if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_GPR_BOTH) - reg->wr_both = true; - reg->dst = nfp_swreg_to_unreg(dst, true); - - /* Decode source operands */ - if (FIELD_GET(NN_REG_TYPE, lreg) == FIELD_GET(NN_REG_TYPE, rreg)) - return -EFAULT; - - if (FIELD_GET(NN_REG_TYPE, lreg) == NN_REG_GPR_B || - FIELD_GET(NN_REG_TYPE, rreg) == NN_REG_GPR_A) { - reg->areg = nfp_swreg_to_unreg(rreg, false); - reg->breg = nfp_swreg_to_unreg(lreg, false); - reg->swap = true; - } else { - reg->areg = nfp_swreg_to_unreg(lreg, false); - reg->breg = nfp_swreg_to_unreg(rreg, false); - } - - return 0; -} - -static u16 nfp_swreg_to_rereg(u32 swreg, bool is_dst, bool has_imm8, bool *i8) -{ - u16 val = FIELD_GET(NN_REG_VAL, swreg); - - switch (FIELD_GET(NN_REG_TYPE, swreg)) { - case NN_REG_GPR_A: - case NN_REG_GPR_B: - case NN_REG_GPR_BOTH: - return val; - case NN_REG_XFER: - return RE_REG_XFR | val; - case NN_REG_IMM: - if (val & ~(0x7f | has_imm8 << 7)) { - pr_err("immediate too large\n"); - return 0; - } - *i8 = val & 0x80; - return RE_REG_IMM_encode(val & 0x7f); - case NN_REG_NONE: - return is_dst ? RE_REG_NO_DST : REG_NONE; - default: - pr_err("unrecognized reg encoding\n"); - return 0; - } -} - -static int -swreg_to_restricted(u32 dst, u32 lreg, u32 rreg, struct nfp_insn_re_regs *reg, - bool has_imm8) -{ - memset(reg, 0, sizeof(*reg)); - - /* Decode destination */ - if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_IMM) - return -EFAULT; - - if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_GPR_B) - reg->dst_ab = ALU_DST_B; - if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_GPR_BOTH) - reg->wr_both = true; - reg->dst = nfp_swreg_to_rereg(dst, true, false, NULL); - - /* Decode source operands */ - if (FIELD_GET(NN_REG_TYPE, lreg) == FIELD_GET(NN_REG_TYPE, rreg)) - return -EFAULT; - - if (FIELD_GET(NN_REG_TYPE, lreg) == NN_REG_GPR_B || - FIELD_GET(NN_REG_TYPE, rreg) == NN_REG_GPR_A) { - reg->areg = nfp_swreg_to_rereg(rreg, false, has_imm8, ®->i8); - reg->breg = nfp_swreg_to_rereg(lreg, false, has_imm8, ®->i8); - reg->swap = true; - } else { - reg->areg = nfp_swreg_to_rereg(lreg, false, has_imm8, ®->i8); - reg->breg = nfp_swreg_to_rereg(rreg, false, has_imm8, ®->i8); - } - - return 0; -} - /* --- Emitters --- */ -static const struct cmd_tgt_act cmd_tgt_act[__CMD_TGT_MAP_SIZE] = { - [CMD_TGT_WRITE8] = { 0x00, 0x42 }, - [CMD_TGT_READ8] = { 0x01, 0x43 }, - [CMD_TGT_READ_LE] = { 0x01, 0x40 }, - [CMD_TGT_READ_SWAP_LE] = { 0x03, 0x40 }, -}; - static void __emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op, u8 mode, u8 xfer, u8 areg, u8 breg, u8 size, bool sync) @@ -281,7 +138,7 @@ __emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op, static void emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op, - u8 mode, u8 xfer, u32 lreg, u32 rreg, u8 size, bool sync) + u8 mode, u8 xfer, swreg lreg, swreg rreg, u8 size, bool sync) { struct nfp_insn_re_regs reg; int err; @@ -296,6 +153,11 @@ emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op, nfp_prog->error = -EFAULT; return; } + if (reg.dst_lmextn || reg.src_lmextn) { + pr_err("cmd can't use LMextn\n"); + nfp_prog->error = -EFAULT; + return; + } __emit_cmd(nfp_prog, op, mode, xfer, reg.areg, reg.breg, size, sync); } @@ -341,7 +203,7 @@ emit_br(struct nfp_prog *nfp_prog, enum br_mask mask, u16 addr, u8 defer) static void __emit_br_byte(struct nfp_prog *nfp_prog, u8 areg, u8 breg, bool imm8, - u8 byte, bool equal, u16 addr, u8 defer) + u8 byte, bool equal, u16 addr, u8 defer, bool src_lmextn) { u16 addr_lo, addr_hi; u64 insn; @@ -357,32 +219,34 @@ __emit_br_byte(struct nfp_prog *nfp_prog, u8 areg, u8 breg, bool imm8, FIELD_PREP(OP_BB_EQ, equal) | FIELD_PREP(OP_BB_DEFBR, defer) | FIELD_PREP(OP_BB_ADDR_LO, addr_lo) | - FIELD_PREP(OP_BB_ADDR_HI, addr_hi); + FIELD_PREP(OP_BB_ADDR_HI, addr_hi) | + FIELD_PREP(OP_BB_SRC_LMEXTN, src_lmextn); nfp_prog_push(nfp_prog, insn); } static void emit_br_byte_neq(struct nfp_prog *nfp_prog, - u32 dst, u8 imm, u8 byte, u16 addr, u8 defer) + swreg src, u8 imm, u8 byte, u16 addr, u8 defer) { struct nfp_insn_re_regs reg; int err; - err = swreg_to_restricted(reg_none(), dst, reg_imm(imm), ®, true); + err = swreg_to_restricted(reg_none(), src, reg_imm(imm), ®, true); if (err) { nfp_prog->error = err; return; } __emit_br_byte(nfp_prog, reg.areg, reg.breg, reg.i8, byte, false, addr, - defer); + defer, reg.src_lmextn); } static void __emit_immed(struct nfp_prog *nfp_prog, u16 areg, u16 breg, u16 imm_hi, enum immed_width width, bool invert, - enum immed_shift shift, bool wr_both) + enum immed_shift shift, bool wr_both, + bool dst_lmextn, bool src_lmextn) { u64 insn; @@ -393,19 +257,21 @@ __emit_immed(struct nfp_prog *nfp_prog, u16 areg, u16 breg, u16 imm_hi, FIELD_PREP(OP_IMMED_WIDTH, width) | FIELD_PREP(OP_IMMED_INV, invert) | FIELD_PREP(OP_IMMED_SHIFT, shift) | - FIELD_PREP(OP_IMMED_WR_AB, wr_both); + FIELD_PREP(OP_IMMED_WR_AB, wr_both) | + FIELD_PREP(OP_IMMED_SRC_LMEXTN, src_lmextn) | + FIELD_PREP(OP_IMMED_DST_LMEXTN, dst_lmextn); nfp_prog_push(nfp_prog, insn); } static void -emit_immed(struct nfp_prog *nfp_prog, u32 dst, u16 imm, +emit_immed(struct nfp_prog *nfp_prog, swreg dst, u16 imm, enum immed_width width, bool invert, enum immed_shift shift) { struct nfp_insn_ur_regs reg; int err; - if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_IMM) { + if (swreg_type(dst) == NN_REG_IMM) { nfp_prog->error = -EFAULT; return; } @@ -417,13 +283,15 @@ emit_immed(struct nfp_prog *nfp_prog, u32 dst, u16 imm, } __emit_immed(nfp_prog, reg.areg, reg.breg, imm >> 8, width, - invert, shift, reg.wr_both); + invert, shift, reg.wr_both, + reg.dst_lmextn, reg.src_lmextn); } static void __emit_shf(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab, enum shf_sc sc, u8 shift, - u16 areg, enum shf_op op, u16 breg, bool i8, bool sw, bool wr_both) + u16 areg, enum shf_op op, u16 breg, bool i8, bool sw, bool wr_both, + bool dst_lmextn, bool src_lmextn) { u64 insn; @@ -445,14 +313,16 @@ __emit_shf(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab, FIELD_PREP(OP_SHF_SHIFT, shift) | FIELD_PREP(OP_SHF_OP, op) | FIELD_PREP(OP_SHF_DST_AB, dst_ab) | - FIELD_PREP(OP_SHF_WR_AB, wr_both); + FIELD_PREP(OP_SHF_WR_AB, wr_both) | + FIELD_PREP(OP_SHF_SRC_LMEXTN, src_lmextn) | + FIELD_PREP(OP_SHF_DST_LMEXTN, dst_lmextn); nfp_prog_push(nfp_prog, insn); } static void -emit_shf(struct nfp_prog *nfp_prog, u32 dst, u32 lreg, enum shf_op op, u32 rreg, - enum shf_sc sc, u8 shift) +emit_shf(struct nfp_prog *nfp_prog, swreg dst, + swreg lreg, enum shf_op op, swreg rreg, enum shf_sc sc, u8 shift) { struct nfp_insn_re_regs reg; int err; @@ -464,12 +334,14 @@ emit_shf(struct nfp_prog *nfp_prog, u32 dst, u32 lreg, enum shf_op op, u32 rreg, } __emit_shf(nfp_prog, reg.dst, reg.dst_ab, sc, shift, - reg.areg, op, reg.breg, reg.i8, reg.swap, reg.wr_both); + reg.areg, op, reg.breg, reg.i8, reg.swap, reg.wr_both, + reg.dst_lmextn, reg.src_lmextn); } static void __emit_alu(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab, - u16 areg, enum alu_op op, u16 breg, bool swap, bool wr_both) + u16 areg, enum alu_op op, u16 breg, bool swap, bool wr_both, + bool dst_lmextn, bool src_lmextn) { u64 insn; @@ -480,13 +352,16 @@ __emit_alu(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab, FIELD_PREP(OP_ALU_SW, swap) | FIELD_PREP(OP_ALU_OP, op) | FIELD_PREP(OP_ALU_DST_AB, dst_ab) | - FIELD_PREP(OP_ALU_WR_AB, wr_both); + FIELD_PREP(OP_ALU_WR_AB, wr_both) | + FIELD_PREP(OP_ALU_SRC_LMEXTN, src_lmextn) | + FIELD_PREP(OP_ALU_DST_LMEXTN, dst_lmextn); nfp_prog_push(nfp_prog, insn); } static void -emit_alu(struct nfp_prog *nfp_prog, u32 dst, u32 lreg, enum alu_op op, u32 rreg) +emit_alu(struct nfp_prog *nfp_prog, swreg dst, + swreg lreg, enum alu_op op, swreg rreg) { struct nfp_insn_ur_regs reg; int err; @@ -498,13 +373,15 @@ emit_alu(struct nfp_prog *nfp_prog, u32 dst, u32 lreg, enum alu_op op, u32 rreg) } __emit_alu(nfp_prog, reg.dst, reg.dst_ab, - reg.areg, op, reg.breg, reg.swap, reg.wr_both); + reg.areg, op, reg.breg, reg.swap, reg.wr_both, + reg.dst_lmextn, reg.src_lmextn); } static void __emit_ld_field(struct nfp_prog *nfp_prog, enum shf_sc sc, u8 areg, u8 bmask, u8 breg, u8 shift, bool imm8, - bool zero, bool swap, bool wr_both) + bool zero, bool swap, bool wr_both, + bool dst_lmextn, bool src_lmextn) { u64 insn; @@ -517,33 +394,42 @@ __emit_ld_field(struct nfp_prog *nfp_prog, enum shf_sc sc, FIELD_PREP(OP_LDF_ZF, zero) | FIELD_PREP(OP_LDF_BMASK, bmask) | FIELD_PREP(OP_LDF_SHF, shift) | - FIELD_PREP(OP_LDF_WR_AB, wr_both); + FIELD_PREP(OP_LDF_WR_AB, wr_both) | + FIELD_PREP(OP_LDF_SRC_LMEXTN, src_lmextn) | + FIELD_PREP(OP_LDF_DST_LMEXTN, dst_lmextn); nfp_prog_push(nfp_prog, insn); } static void -emit_ld_field_any(struct nfp_prog *nfp_prog, enum shf_sc sc, u8 shift, - u32 dst, u8 bmask, u32 src, bool zero) +emit_ld_field_any(struct nfp_prog *nfp_prog, swreg dst, u8 bmask, swreg src, + enum shf_sc sc, u8 shift, bool zero) { struct nfp_insn_re_regs reg; int err; - err = swreg_to_restricted(reg_none(), dst, src, ®, true); + /* Note: ld_field is special as it uses one of the src regs as dst */ + err = swreg_to_restricted(dst, dst, src, ®, true); if (err) { nfp_prog->error = err; return; } __emit_ld_field(nfp_prog, sc, reg.areg, bmask, reg.breg, shift, - reg.i8, zero, reg.swap, reg.wr_both); + reg.i8, zero, reg.swap, reg.wr_both, + reg.dst_lmextn, reg.src_lmextn); } static void -emit_ld_field(struct nfp_prog *nfp_prog, u32 dst, u8 bmask, u32 src, +emit_ld_field(struct nfp_prog *nfp_prog, swreg dst, u8 bmask, swreg src, enum shf_sc sc, u8 shift) { - emit_ld_field_any(nfp_prog, sc, shift, dst, bmask, src, false); + emit_ld_field_any(nfp_prog, dst, bmask, src, sc, shift, false); +} + +static void emit_nop(struct nfp_prog *nfp_prog) +{ + __emit_immed(nfp_prog, UR_REG_IMM, UR_REG_IMM, 0, 0, 0, 0, 0, 0, 0); } /* --- Wrappers --- */ @@ -565,7 +451,7 @@ static bool pack_immed(u32 imm, u16 *val, enum immed_shift *shift) return true; } -static void wrp_immed(struct nfp_prog *nfp_prog, u32 dst, u32 imm) +static void wrp_immed(struct nfp_prog *nfp_prog, swreg dst, u32 imm) { enum immed_shift shift; u16 val; @@ -586,7 +472,7 @@ static void wrp_immed(struct nfp_prog *nfp_prog, u32 dst, u32 imm) * If the @imm is small enough encode it directly in operand and return * otherwise load @imm to a spare register and return its encoding. */ -static u32 ur_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, u32 tmp_reg) +static swreg ur_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, swreg tmp_reg) { if (FIELD_FIT(UR_REG_IMM_MAX, imm)) return reg_imm(imm); @@ -599,7 +485,7 @@ static u32 ur_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, u32 tmp_reg) * If the @imm is small enough encode it directly in operand and return * otherwise load @imm to a spare register and return its encoding. */ -static u32 re_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, u32 tmp_reg) +static swreg re_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, swreg tmp_reg) { if (FIELD_FIT(RE_REG_IMM_MAX, imm)) return reg_imm(imm); @@ -618,78 +504,134 @@ wrp_br_special(struct nfp_prog *nfp_prog, enum br_mask mask, FIELD_PREP(OP_BR_SPECIAL, special); } +static void wrp_mov(struct nfp_prog *nfp_prog, swreg dst, swreg src) +{ + emit_alu(nfp_prog, dst, reg_none(), ALU_OP_NONE, src); +} + static void wrp_reg_mov(struct nfp_prog *nfp_prog, u16 dst, u16 src) { - emit_alu(nfp_prog, reg_both(dst), reg_none(), ALU_OP_NONE, reg_b(src)); + wrp_mov(nfp_prog, reg_both(dst), reg_b(src)); } static int -construct_data_ind_ld(struct nfp_prog *nfp_prog, u16 offset, - u16 src, bool src_valid, u8 size) +data_ld(struct nfp_prog *nfp_prog, swreg offset, u8 dst_gpr, int size) { unsigned int i; u16 shift, sz; - u32 tmp_reg; /* We load the value from the address indicated in @offset and then * shift out the data we don't need. Note: this is big endian! */ - sz = size < 4 ? 4 : size; + sz = max(size, 4); shift = size < 4 ? 4 - size : 0; - if (src_valid) { - /* Calculate the true offset (src_reg + imm) */ - tmp_reg = ur_load_imm_any(nfp_prog, offset, imm_b(nfp_prog)); - emit_alu(nfp_prog, imm_both(nfp_prog), - reg_a(src), ALU_OP_ADD, tmp_reg); - /* Check packet length (size guaranteed to fit b/c it's u8) */ - emit_alu(nfp_prog, imm_a(nfp_prog), - imm_a(nfp_prog), ALU_OP_ADD, reg_imm(size)); - emit_alu(nfp_prog, reg_none(), - NFP_BPF_ABI_LEN, ALU_OP_SUB, imm_a(nfp_prog)); - wrp_br_special(nfp_prog, BR_BLO, OP_BR_GO_ABORT); - /* Load data */ - emit_cmd(nfp_prog, CMD_TGT_READ8, CMD_MODE_32b, 0, - pkt_reg(nfp_prog), imm_b(nfp_prog), sz - 1, true); - } else { - /* Check packet length */ - tmp_reg = ur_load_imm_any(nfp_prog, offset + size, - imm_a(nfp_prog)); - emit_alu(nfp_prog, reg_none(), - NFP_BPF_ABI_LEN, ALU_OP_SUB, tmp_reg); - wrp_br_special(nfp_prog, BR_BLO, OP_BR_GO_ABORT); - /* Load data */ - tmp_reg = re_load_imm_any(nfp_prog, offset, imm_b(nfp_prog)); - emit_cmd(nfp_prog, CMD_TGT_READ8, CMD_MODE_32b, 0, - pkt_reg(nfp_prog), tmp_reg, sz - 1, true); - } + emit_cmd(nfp_prog, CMD_TGT_READ8, CMD_MODE_32b, 0, + pptr_reg(nfp_prog), offset, sz - 1, true); i = 0; if (shift) - emit_shf(nfp_prog, reg_both(0), reg_none(), SHF_OP_NONE, + emit_shf(nfp_prog, reg_both(dst_gpr), reg_none(), SHF_OP_NONE, reg_xfer(0), SHF_SC_R_SHF, shift * 8); else for (; i * 4 < size; i++) - emit_alu(nfp_prog, reg_both(i), - reg_none(), ALU_OP_NONE, reg_xfer(i)); + wrp_mov(nfp_prog, reg_both(dst_gpr + i), reg_xfer(i)); + + if (i < 2) + wrp_immed(nfp_prog, reg_both(dst_gpr + 1), 0); + + return 0; +} + +static int +data_ld_host_order(struct nfp_prog *nfp_prog, u8 src_gpr, swreg offset, + u8 dst_gpr, int size) +{ + unsigned int i; + u8 mask, sz; + + /* We load the value from the address indicated in @offset and then + * mask out the data we don't need. Note: this is little endian! + */ + sz = max(size, 4); + mask = size < 4 ? GENMASK(size - 1, 0) : 0; + + emit_cmd(nfp_prog, CMD_TGT_READ32_SWAP, CMD_MODE_32b, 0, + reg_a(src_gpr), offset, sz / 4 - 1, true); + + i = 0; + if (mask) + emit_ld_field_any(nfp_prog, reg_both(dst_gpr), mask, + reg_xfer(0), SHF_SC_NONE, 0, true); + else + for (; i * 4 < size; i++) + wrp_mov(nfp_prog, reg_both(dst_gpr + i), reg_xfer(i)); if (i < 2) - wrp_immed(nfp_prog, reg_both(1), 0); + wrp_immed(nfp_prog, reg_both(dst_gpr + 1), 0); return 0; } +static int +construct_data_ind_ld(struct nfp_prog *nfp_prog, u16 offset, u16 src, u8 size) +{ + swreg tmp_reg; + + /* Calculate the true offset (src_reg + imm) */ + tmp_reg = ur_load_imm_any(nfp_prog, offset, imm_b(nfp_prog)); + emit_alu(nfp_prog, imm_both(nfp_prog), reg_a(src), ALU_OP_ADD, tmp_reg); + + /* Check packet length (size guaranteed to fit b/c it's u8) */ + emit_alu(nfp_prog, imm_a(nfp_prog), + imm_a(nfp_prog), ALU_OP_ADD, reg_imm(size)); + emit_alu(nfp_prog, reg_none(), + plen_reg(nfp_prog), ALU_OP_SUB, imm_a(nfp_prog)); + wrp_br_special(nfp_prog, BR_BLO, OP_BR_GO_ABORT); + + /* Load data */ + return data_ld(nfp_prog, imm_b(nfp_prog), 0, size); +} + static int construct_data_ld(struct nfp_prog *nfp_prog, u16 offset, u8 size) { - return construct_data_ind_ld(nfp_prog, offset, 0, false, size); + swreg tmp_reg; + + /* Check packet length */ + tmp_reg = ur_load_imm_any(nfp_prog, offset + size, imm_a(nfp_prog)); + emit_alu(nfp_prog, reg_none(), plen_reg(nfp_prog), ALU_OP_SUB, tmp_reg); + wrp_br_special(nfp_prog, BR_BLO, OP_BR_GO_ABORT); + + /* Load data */ + tmp_reg = re_load_imm_any(nfp_prog, offset, imm_b(nfp_prog)); + return data_ld(nfp_prog, tmp_reg, 0, size); +} + +static int +data_stx_host_order(struct nfp_prog *nfp_prog, u8 dst_gpr, swreg offset, + u8 src_gpr, u8 size) +{ + unsigned int i; + + for (i = 0; i * 4 < size; i++) + wrp_mov(nfp_prog, reg_xfer(i), reg_a(src_gpr + i)); + + emit_cmd(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b, 0, + reg_a(dst_gpr), offset, size - 1, true); + + return 0; } -static int wrp_set_mark(struct nfp_prog *nfp_prog, u8 src) +static int +data_st_host_order(struct nfp_prog *nfp_prog, u8 dst_gpr, swreg offset, + u64 imm, u8 size) { - emit_alu(nfp_prog, NFP_BPF_ABI_MARK, - reg_none(), ALU_OP_NONE, reg_b(src)); - emit_alu(nfp_prog, NFP_BPF_ABI_FLAGS, - NFP_BPF_ABI_FLAGS, ALU_OP_OR, reg_imm(NFP_BPF_ABI_FLAG_MARK)); + wrp_immed(nfp_prog, reg_xfer(0), imm); + if (size == 8) + wrp_immed(nfp_prog, reg_xfer(1), imm >> 32); + + emit_cmd(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b, 0, + reg_a(dst_gpr), offset, size - 1, true); return 0; } @@ -697,7 +639,7 @@ static int wrp_set_mark(struct nfp_prog *nfp_prog, u8 src) static void wrp_alu_imm(struct nfp_prog *nfp_prog, u8 dst, enum alu_op alu_op, u32 imm) { - u32 tmp_reg; + swreg tmp_reg; if (alu_op == ALU_OP_AND) { if (!imm) @@ -815,7 +757,7 @@ wrp_cmp_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, const struct bpf_insn *insn = &meta->insn; u64 imm = insn->imm; /* sign extend */ u8 reg = insn->dst_reg * 2; - u32 tmp_reg; + swreg tmp_reg; if (insn->off < 0) /* TODO */ return -EOPNOTSUPP; @@ -844,7 +786,10 @@ wrp_cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, enum br_mask br_mask, bool swap) { const struct bpf_insn *insn = &meta->insn; - u8 areg = insn->src_reg * 2, breg = insn->dst_reg * 2; + u8 areg, breg; + + areg = insn->dst_reg * 2; + breg = insn->src_reg * 2; if (insn->off < 0) /* TODO */ return -EOPNOTSUPP; @@ -863,6 +808,14 @@ wrp_cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, return 0; } +static void wrp_end32(struct nfp_prog *nfp_prog, swreg reg_in, u8 gpr_out) +{ + emit_ld_field(nfp_prog, reg_both(gpr_out), 0xf, reg_in, + SHF_SC_R_ROT, 8); + emit_ld_field(nfp_prog, reg_both(gpr_out), 0x5, reg_a(gpr_out), + SHF_SC_R_ROT, 16); +} + /* --- Callbacks --- */ static int mov_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { @@ -967,12 +920,24 @@ static int sub_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int shl_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; - - if (insn->imm != 32) - return 1; /* TODO */ - - wrp_reg_mov(nfp_prog, insn->dst_reg * 2 + 1, insn->dst_reg * 2); - wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2), 0); + u8 dst = insn->dst_reg * 2; + + if (insn->imm < 32) { + emit_shf(nfp_prog, reg_both(dst + 1), + reg_a(dst + 1), SHF_OP_NONE, reg_b(dst), + SHF_SC_R_DSHF, 32 - insn->imm); + emit_shf(nfp_prog, reg_both(dst), + reg_none(), SHF_OP_NONE, reg_b(dst), + SHF_SC_L_SHF, insn->imm); + } else if (insn->imm == 32) { + wrp_reg_mov(nfp_prog, dst + 1, dst); + wrp_immed(nfp_prog, reg_both(dst), 0); + } else if (insn->imm > 32) { + emit_shf(nfp_prog, reg_both(dst + 1), + reg_none(), SHF_OP_NONE, reg_b(dst), + SHF_SC_L_SHF, insn->imm - 32); + wrp_immed(nfp_prog, reg_both(dst), 0); + } return 0; } @@ -980,12 +945,24 @@ static int shl_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int shr_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; - - if (insn->imm != 32) - return 1; /* TODO */ - - wrp_reg_mov(nfp_prog, insn->dst_reg * 2, insn->dst_reg * 2 + 1); - wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2 + 1), 0); + u8 dst = insn->dst_reg * 2; + + if (insn->imm < 32) { + emit_shf(nfp_prog, reg_both(dst), + reg_a(dst + 1), SHF_OP_NONE, reg_b(dst), + SHF_SC_R_DSHF, insn->imm); + emit_shf(nfp_prog, reg_both(dst + 1), + reg_none(), SHF_OP_NONE, reg_b(dst + 1), + SHF_SC_R_SHF, insn->imm); + } else if (insn->imm == 32) { + wrp_reg_mov(nfp_prog, dst, dst + 1); + wrp_immed(nfp_prog, reg_both(dst + 1), 0); + } else if (insn->imm > 32) { + emit_shf(nfp_prog, reg_both(dst), + reg_none(), SHF_OP_NONE, reg_b(dst + 1), + SHF_SC_R_SHF, insn->imm - 32); + wrp_immed(nfp_prog, reg_both(dst + 1), 0); + } return 0; } @@ -1075,6 +1052,35 @@ static int shl_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) return 0; } +static int end_reg32(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + const struct bpf_insn *insn = &meta->insn; + u8 gpr = insn->dst_reg * 2; + + switch (insn->imm) { + case 16: + emit_ld_field(nfp_prog, reg_both(gpr), 0x9, reg_b(gpr), + SHF_SC_R_ROT, 8); + emit_ld_field(nfp_prog, reg_both(gpr), 0xe, reg_a(gpr), + SHF_SC_R_SHF, 16); + + wrp_immed(nfp_prog, reg_both(gpr + 1), 0); + break; + case 32: + wrp_end32(nfp_prog, reg_a(gpr), gpr); + wrp_immed(nfp_prog, reg_both(gpr + 1), 0); + break; + case 64: + wrp_mov(nfp_prog, imm_a(nfp_prog), reg_b(gpr + 1)); + + wrp_end32(nfp_prog, reg_a(gpr), gpr + 1); + wrp_end32(nfp_prog, imm_a(nfp_prog), gpr); + break; + } + + return 0; +} + static int imm_ld8_part2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { wrp_immed(nfp_prog, reg_both(nfp_meta_prev(meta)->insn.dst_reg * 2 + 1), @@ -1111,82 +1117,209 @@ static int data_ld4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int data_ind_ld1(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { return construct_data_ind_ld(nfp_prog, meta->insn.imm, - meta->insn.src_reg * 2, true, 1); + meta->insn.src_reg * 2, 1); } static int data_ind_ld2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { return construct_data_ind_ld(nfp_prog, meta->insn.imm, - meta->insn.src_reg * 2, true, 2); + meta->insn.src_reg * 2, 2); } static int data_ind_ld4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { return construct_data_ind_ld(nfp_prog, meta->insn.imm, - meta->insn.src_reg * 2, true, 4); + meta->insn.src_reg * 2, 4); } -static int mem_ldx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +static int mem_ldx_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + u8 size) { - if (meta->insn.off == offsetof(struct sk_buff, len)) - emit_alu(nfp_prog, reg_both(meta->insn.dst_reg * 2), - reg_none(), ALU_OP_NONE, NFP_BPF_ABI_LEN); - else + swreg dst = reg_both(meta->insn.dst_reg * 2); + + switch (meta->insn.off) { + case offsetof(struct sk_buff, len): + if (size != FIELD_SIZEOF(struct sk_buff, len)) + return -EOPNOTSUPP; + wrp_mov(nfp_prog, dst, plen_reg(nfp_prog)); + break; + case offsetof(struct sk_buff, data): + if (size != sizeof(void *)) + return -EOPNOTSUPP; + wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog)); + break; + case offsetof(struct sk_buff, cb) + + offsetof(struct bpf_skb_data_end, data_end): + if (size != sizeof(void *)) + return -EOPNOTSUPP; + emit_alu(nfp_prog, dst, + plen_reg(nfp_prog), ALU_OP_ADD, pptr_reg(nfp_prog)); + break; + default: return -EOPNOTSUPP; + } + + wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0); return 0; } -static int mem_ldx4_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +static int mem_ldx_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + u8 size) { - u32 dst = reg_both(meta->insn.dst_reg * 2); + swreg dst = reg_both(meta->insn.dst_reg * 2); - if (meta->insn.off != offsetof(struct xdp_md, data) && - meta->insn.off != offsetof(struct xdp_md, data_end)) + if (size != sizeof(void *)) + return -EINVAL; + + switch (meta->insn.off) { + case offsetof(struct xdp_buff, data): + wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog)); + break; + case offsetof(struct xdp_buff, data_end): + emit_alu(nfp_prog, dst, + plen_reg(nfp_prog), ALU_OP_ADD, pptr_reg(nfp_prog)); + break; + default: return -EOPNOTSUPP; + } - emit_alu(nfp_prog, dst, reg_none(), ALU_OP_NONE, NFP_BPF_ABI_PKT); + wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0); - if (meta->insn.off == offsetof(struct xdp_md, data)) - return 0; + return 0; +} - emit_alu(nfp_prog, dst, dst, ALU_OP_ADD, NFP_BPF_ABI_LEN); +static int +mem_ldx_data(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + unsigned int size) +{ + swreg tmp_reg; - return 0; + tmp_reg = re_load_imm_any(nfp_prog, meta->insn.off, imm_b(nfp_prog)); + + return data_ld_host_order(nfp_prog, meta->insn.src_reg * 2, tmp_reg, + meta->insn.dst_reg * 2, size); +} + +static int +mem_ldx(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + unsigned int size) +{ + if (meta->ptr.type == PTR_TO_CTX) { + if (nfp_prog->act == NN_ACT_XDP) + return mem_ldx_xdp(nfp_prog, meta, size); + else + return mem_ldx_skb(nfp_prog, meta, size); + } + + if (meta->ptr.type == PTR_TO_PACKET) + return mem_ldx_data(nfp_prog, meta, size); + + return -EOPNOTSUPP; +} + +static int mem_ldx1(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_ldx(nfp_prog, meta, 1); +} + +static int mem_ldx2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_ldx(nfp_prog, meta, 2); } static int mem_ldx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - int ret; + return mem_ldx(nfp_prog, meta, 4); +} - if (nfp_prog->act == NN_ACT_XDP) - ret = mem_ldx4_xdp(nfp_prog, meta); - else - ret = mem_ldx4_skb(nfp_prog, meta); +static int mem_ldx8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_ldx(nfp_prog, meta, 8); +} - wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0); +static int +mem_st_data(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + unsigned int size) +{ + u64 imm = meta->insn.imm; /* sign extend */ + swreg off_reg; - return ret; + off_reg = re_load_imm_any(nfp_prog, meta->insn.off, imm_b(nfp_prog)); + + return data_st_host_order(nfp_prog, meta->insn.dst_reg * 2, off_reg, + imm, size); } -static int mem_stx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +static int mem_st(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + unsigned int size) { - if (meta->insn.off == offsetof(struct sk_buff, mark)) - return wrp_set_mark(nfp_prog, meta->insn.src_reg * 2); + if (meta->ptr.type == PTR_TO_PACKET) + return mem_st_data(nfp_prog, meta, size); return -EOPNOTSUPP; } -static int mem_stx4_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +static int mem_st1(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_st(nfp_prog, meta, 1); +} + +static int mem_st2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { + return mem_st(nfp_prog, meta, 2); +} + +static int mem_st4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_st(nfp_prog, meta, 4); +} + +static int mem_st8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_st(nfp_prog, meta, 8); +} + +static int +mem_stx_data(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + unsigned int size) +{ + swreg off_reg; + + off_reg = re_load_imm_any(nfp_prog, meta->insn.off, imm_b(nfp_prog)); + + return data_stx_host_order(nfp_prog, meta->insn.dst_reg * 2, off_reg, + meta->insn.src_reg * 2, size); +} + +static int +mem_stx(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + unsigned int size) +{ + if (meta->ptr.type == PTR_TO_PACKET) + return mem_stx_data(nfp_prog, meta, size); + return -EOPNOTSUPP; } +static int mem_stx1(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_stx(nfp_prog, meta, 1); +} + +static int mem_stx2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_stx(nfp_prog, meta, 2); +} + static int mem_stx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - if (nfp_prog->act == NN_ACT_XDP) - return mem_stx4_xdp(nfp_prog, meta); - return mem_stx4_skb(nfp_prog, meta); + return mem_stx(nfp_prog, meta, 4); +} + +static int mem_stx8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_stx(nfp_prog, meta, 8); } static int jump(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) @@ -1202,8 +1335,10 @@ static int jeq_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; u64 imm = insn->imm; /* sign extend */ - u32 or1 = reg_a(insn->dst_reg * 2), or2 = reg_b(insn->dst_reg * 2 + 1); - u32 tmp_reg; + swreg or1, or2, tmp_reg; + + or1 = reg_a(insn->dst_reg * 2); + or2 = reg_b(insn->dst_reg * 2 + 1); if (insn->off < 0) /* TODO */ return -EOPNOTSUPP; @@ -1230,29 +1365,29 @@ static int jeq_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int jgt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_imm(nfp_prog, meta, BR_BLO, false); + return wrp_cmp_imm(nfp_prog, meta, BR_BLO, true); } static int jge_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_imm(nfp_prog, meta, BR_BHS, true); + return wrp_cmp_imm(nfp_prog, meta, BR_BHS, false); } static int jlt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_imm(nfp_prog, meta, BR_BHS, false); + return wrp_cmp_imm(nfp_prog, meta, BR_BLO, false); } static int jle_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_imm(nfp_prog, meta, BR_BLO, true); + return wrp_cmp_imm(nfp_prog, meta, BR_BHS, true); } static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; u64 imm = insn->imm; /* sign extend */ - u32 tmp_reg; + swreg tmp_reg; if (insn->off < 0) /* TODO */ return -EOPNOTSUPP; @@ -1283,7 +1418,7 @@ static int jne_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; u64 imm = insn->imm; /* sign extend */ - u32 tmp_reg; + swreg tmp_reg; if (insn->off < 0) /* TODO */ return -EOPNOTSUPP; @@ -1292,6 +1427,7 @@ static int jne_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) emit_alu(nfp_prog, reg_none(), reg_a(insn->dst_reg * 2), ALU_OP_OR, reg_b(insn->dst_reg * 2 + 1)); emit_br(nfp_prog, BR_BNE, insn->off, 0); + return 0; } tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog)); @@ -1327,22 +1463,22 @@ static int jeq_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int jgt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_reg(nfp_prog, meta, BR_BLO, false); + return wrp_cmp_reg(nfp_prog, meta, BR_BLO, true); } static int jge_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_reg(nfp_prog, meta, BR_BHS, true); + return wrp_cmp_reg(nfp_prog, meta, BR_BHS, false); } static int jlt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_reg(nfp_prog, meta, BR_BHS, false); + return wrp_cmp_reg(nfp_prog, meta, BR_BLO, false); } static int jle_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_reg(nfp_prog, meta, BR_BLO, true); + return wrp_cmp_reg(nfp_prog, meta, BR_BHS, true); } static int jset_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) @@ -1390,6 +1526,7 @@ static const instr_cb_t instr_cb[256] = { [BPF_ALU | BPF_SUB | BPF_X] = sub_reg, [BPF_ALU | BPF_SUB | BPF_K] = sub_imm, [BPF_ALU | BPF_LSH | BPF_K] = shl_imm, + [BPF_ALU | BPF_END | BPF_X] = end_reg32, [BPF_LD | BPF_IMM | BPF_DW] = imm_ld8, [BPF_LD | BPF_ABS | BPF_B] = data_ld1, [BPF_LD | BPF_ABS | BPF_H] = data_ld2, @@ -1397,8 +1534,18 @@ static const instr_cb_t instr_cb[256] = { [BPF_LD | BPF_IND | BPF_B] = data_ind_ld1, [BPF_LD | BPF_IND | BPF_H] = data_ind_ld2, [BPF_LD | BPF_IND | BPF_W] = data_ind_ld4, + [BPF_LDX | BPF_MEM | BPF_B] = mem_ldx1, + [BPF_LDX | BPF_MEM | BPF_H] = mem_ldx2, [BPF_LDX | BPF_MEM | BPF_W] = mem_ldx4, + [BPF_LDX | BPF_MEM | BPF_DW] = mem_ldx8, + [BPF_STX | BPF_MEM | BPF_B] = mem_stx1, + [BPF_STX | BPF_MEM | BPF_H] = mem_stx2, [BPF_STX | BPF_MEM | BPF_W] = mem_stx4, + [BPF_STX | BPF_MEM | BPF_DW] = mem_stx8, + [BPF_ST | BPF_MEM | BPF_B] = mem_st1, + [BPF_ST | BPF_MEM | BPF_H] = mem_st2, + [BPF_ST | BPF_MEM | BPF_W] = mem_st4, + [BPF_ST | BPF_MEM | BPF_DW] = mem_st8, [BPF_JMP | BPF_JA | BPF_K] = jump, [BPF_JMP | BPF_JEQ | BPF_K] = jeq_imm, [BPF_JMP | BPF_JGT | BPF_K] = jgt_imm, @@ -1510,8 +1657,9 @@ static int nfp_fixup_branches(struct nfp_prog *nfp_prog) static void nfp_intro(struct nfp_prog *nfp_prog) { - emit_alu(nfp_prog, pkt_reg(nfp_prog), - reg_none(), ALU_OP_NONE, NFP_BPF_ABI_PKT); + wrp_immed(nfp_prog, plen_reg(nfp_prog), GENMASK(13, 0)); + emit_alu(nfp_prog, plen_reg(nfp_prog), + plen_reg(nfp_prog), ALU_OP_AND, pv_len(nfp_prog)); } static void nfp_outro_tc_legacy(struct nfp_prog *nfp_prog) @@ -1534,8 +1682,7 @@ static void nfp_outro_tc_legacy(struct nfp_prog *nfp_prog) * ife + tx 0x24 -> redir, count as stat1 */ emit_br_byte_neq(nfp_prog, reg_b(0), 0xff, 0, nfp_prog->tgt_done, 2); - emit_alu(nfp_prog, reg_a(0), - reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS); + wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS); emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_imm(0x11), SHF_SC_L_SHF, 16); emit_br(nfp_prog, BR_UNC, nfp_prog->tgt_done, 1); @@ -1562,8 +1709,7 @@ static void nfp_outro_tc_da(struct nfp_prog *nfp_prog) emit_br_def(nfp_prog, nfp_prog->tgt_done, 2); - emit_alu(nfp_prog, reg_a(0), - reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS); + wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS); emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_imm(0x11), SHF_SC_L_SHF, 16); /* Target for normal exits */ @@ -1572,8 +1718,7 @@ static void nfp_outro_tc_da(struct nfp_prog *nfp_prog) /* if R0 > 7 jump to abort */ emit_alu(nfp_prog, reg_none(), reg_imm(7), ALU_OP_SUB, reg_b(0)); emit_br(nfp_prog, BR_BLO, nfp_prog->tgt_abort, 0); - emit_alu(nfp_prog, reg_a(0), - reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS); + wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS); wrp_immed(nfp_prog, reg_b(2), 0x41221211); wrp_immed(nfp_prog, reg_b(3), 0x41001211); @@ -1610,8 +1755,7 @@ static void nfp_outro_xdp(struct nfp_prog *nfp_prog) emit_br_def(nfp_prog, nfp_prog->tgt_done, 2); - emit_alu(nfp_prog, reg_a(0), - reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS); + wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS); emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_imm(0x82), SHF_SC_L_SHF, 16); /* Target for normal exits */ @@ -1632,8 +1776,7 @@ static void nfp_outro_xdp(struct nfp_prog *nfp_prog) emit_br_def(nfp_prog, nfp_prog->tgt_done, 2); - emit_alu(nfp_prog, reg_a(0), - reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS); + wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS); emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_b(2), SHF_SC_L_SHF, 16); } @@ -1656,7 +1799,7 @@ static void nfp_outro(struct nfp_prog *nfp_prog) static int nfp_translate(struct nfp_prog *nfp_prog) { struct nfp_insn_meta *meta; - int err; + int i, err; nfp_intro(nfp_prog); if (nfp_prog->error) @@ -1688,6 +1831,11 @@ static int nfp_translate(struct nfp_prog *nfp_prog) if (nfp_prog->error) return nfp_prog->error; + for (i = 0; i < NFP_USTORE_PREFETCH_WINDOW; i++) + emit_nop(nfp_prog); + if (nfp_prog->error) + return nfp_prog->error; + return nfp_fixup_branches(nfp_prog); } @@ -1737,38 +1885,6 @@ static void nfp_bpf_opt_reg_init(struct nfp_prog *nfp_prog) } } -/* Try to rename registers so that program uses only low ones */ -static int nfp_bpf_opt_reg_rename(struct nfp_prog *nfp_prog) -{ - bool reg_used[MAX_BPF_REG] = {}; - u8 tgt_reg[MAX_BPF_REG] = {}; - struct nfp_insn_meta *meta; - unsigned int i, j; - - list_for_each_entry(meta, &nfp_prog->insns, l) { - if (meta->skip) - continue; - - reg_used[meta->insn.src_reg] = true; - reg_used[meta->insn.dst_reg] = true; - } - - for (i = 0, j = 0; i < ARRAY_SIZE(tgt_reg); i++) { - if (!reg_used[i]) - continue; - - tgt_reg[i] = j++; - } - nfp_prog->num_regs = j; - - list_for_each_entry(meta, &nfp_prog->insns, l) { - meta->insn.src_reg = tgt_reg[meta->insn.src_reg]; - meta->insn.dst_reg = tgt_reg[meta->insn.dst_reg]; - } - - return 0; -} - /* Remove masking after load since our load guarantees this is not needed */ static void nfp_bpf_opt_ld_mask(struct nfp_prog *nfp_prog) { @@ -1845,20 +1961,33 @@ static void nfp_bpf_opt_ld_shift(struct nfp_prog *nfp_prog) static int nfp_bpf_optimize(struct nfp_prog *nfp_prog) { - int ret; - nfp_bpf_opt_reg_init(nfp_prog); - ret = nfp_bpf_opt_reg_rename(nfp_prog); - if (ret) - return ret; - nfp_bpf_opt_ld_mask(nfp_prog); nfp_bpf_opt_ld_shift(nfp_prog); return 0; } +static int nfp_bpf_ustore_calc(struct nfp_prog *nfp_prog, __le64 *ustore) +{ + int i; + + for (i = 0; i < nfp_prog->prog_len; i++) { + int err; + + err = nfp_ustore_check_valid_no_ecc(nfp_prog->prog[i]); + if (err) + return err; + + nfp_prog->prog[i] = nfp_ustore_calc_ecc_insn(nfp_prog->prog[i]); + + ustore[i] = cpu_to_le64(nfp_prog->prog[i]); + } + + return 0; +} + /** * nfp_bpf_jit() - translate BPF code into NFP assembly * @filter: kernel BPF filter struct @@ -1899,10 +2028,8 @@ nfp_bpf_jit(struct bpf_prog *filter, void *prog_mem, if (ret) goto out; - if (nfp_prog->num_regs <= 7) - nfp_prog->regs_per_thread = 16; - else - nfp_prog->regs_per_thread = 32; + nfp_prog->num_regs = MAX_BPF_REG; + nfp_prog->regs_per_thread = 32; nfp_prog->prog = prog_mem; nfp_prog->__prog_alloc_len = prog_sz; @@ -1912,10 +2039,13 @@ nfp_bpf_jit(struct bpf_prog *filter, void *prog_mem, pr_err("Translation failed with error %d (translated: %u)\n", ret, nfp_prog->n_translated); ret = -EINVAL; + goto out; } + ret = nfp_bpf_ustore_calc(nfp_prog, (__force __le64 *)prog_mem); + res->n_instr = nfp_prog->prog_len; - res->dense_mode = nfp_prog->num_regs <= 7; + res->dense_mode = false; out: nfp_prog_free(nfp_prog); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index be2cf10a2cd7..6e74f8db1cc1 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -42,9 +42,11 @@ static bool nfp_net_ebpf_capable(struct nfp_net *nn) { +#ifdef __LITTLE_ENDIAN if (nn->cap & NFP_NET_CFG_CTRL_BPF && nn_readb(nn, NFP_NET_CFG_BPF_ABI) == NFP_NET_BPF_ABI) return true; +#endif return false; } @@ -89,14 +91,6 @@ nfp_bpf_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id) struct nfp_net_bpf_priv *priv; int ret; - /* Limit to single port, otherwise it's just a NIC */ - if (id > 0) { - nfp_warn(app->cpp, - "BPF NIC doesn't support more than one port right now\n"); - nn->port = nfp_port_alloc(app, NFP_PORT_INVALID, nn->dp.netdev); - return PTR_ERR_OR_ZERO(nn->port); - } - priv = kmalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index 4051e943f363..d77e88a45409 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -36,9 +36,11 @@ #include <linux/bitfield.h> #include <linux/bpf.h> +#include <linux/bpf_verifier.h> #include <linux/list.h> #include <linux/types.h> +#include "../nfp_asm.h" #include "../nfp_net.h" /* For branch fixup logic use up-most byte of branch instruction as scratch @@ -53,9 +55,13 @@ enum br_special { }; enum static_regs { - STATIC_REG_PKT = 1, -#define REG_PKT_BANK ALU_DST_A - STATIC_REG_IMM = 2, /* Bank AB */ + STATIC_REG_IMM = 21, /* Bank AB */ + STATIC_REG_PKT_LEN = 22, /* Bank B */ +}; + +enum pkt_vec { + PKT_VEC_PKT_LEN = 0, + PKT_VEC_PKT_PTR = 2, }; enum nfp_bpf_action_type { @@ -65,39 +71,17 @@ enum nfp_bpf_action_type { NN_ACT_XDP, }; -/* Software register representation, hardware encoding in asm.h */ -#define NN_REG_TYPE GENMASK(31, 24) -#define NN_REG_VAL GENMASK(7, 0) - -enum nfp_bpf_reg_type { - NN_REG_GPR_A = BIT(0), - NN_REG_GPR_B = BIT(1), - NN_REG_NNR = BIT(2), - NN_REG_XFER = BIT(3), - NN_REG_IMM = BIT(4), - NN_REG_NONE = BIT(5), -}; - -#define NN_REG_GPR_BOTH (NN_REG_GPR_A | NN_REG_GPR_B) - -#define reg_both(x) ((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_GPR_BOTH)) -#define reg_a(x) ((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_GPR_A)) -#define reg_b(x) ((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_GPR_B)) -#define reg_nnr(x) ((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_NNR)) -#define reg_xfer(x) ((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_XFER)) -#define reg_imm(x) ((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_IMM)) -#define reg_none() (FIELD_PREP(NN_REG_TYPE, NN_REG_NONE)) +#define pv_len(np) reg_lm(1, PKT_VEC_PKT_LEN) +#define pv_ctm_ptr(np) reg_lm(1, PKT_VEC_PKT_PTR) -#define pkt_reg(np) reg_a((np)->regs_per_thread - STATIC_REG_PKT) -#define imm_a(np) reg_a((np)->regs_per_thread - STATIC_REG_IMM) -#define imm_b(np) reg_b((np)->regs_per_thread - STATIC_REG_IMM) -#define imm_both(np) reg_both((np)->regs_per_thread - STATIC_REG_IMM) +#define plen_reg(np) reg_b(STATIC_REG_PKT_LEN) +#define pptr_reg(np) pv_ctm_ptr(np) +#define imm_a(np) reg_a(STATIC_REG_IMM) +#define imm_b(np) reg_b(STATIC_REG_IMM) +#define imm_both(np) reg_both(STATIC_REG_IMM) -#define NFP_BPF_ABI_FLAGS reg_nnr(0) +#define NFP_BPF_ABI_FLAGS reg_imm(0) #define NFP_BPF_ABI_FLAG_MARK 1 -#define NFP_BPF_ABI_MARK reg_nnr(1) -#define NFP_BPF_ABI_PKT reg_nnr(2) -#define NFP_BPF_ABI_LEN reg_nnr(3) struct nfp_prog; struct nfp_insn_meta; @@ -113,6 +97,7 @@ typedef int (*instr_cb_t)(struct nfp_prog *, struct nfp_insn_meta *); /** * struct nfp_insn_meta - BPF instruction wrapper * @insn: BPF instruction + * @ptr: pointer type for memory operations * @off: index of first generated machine instruction (in nfp_prog.prog) * @n: eBPF instruction number * @skip: skip this instruction (optimized out) @@ -121,6 +106,7 @@ typedef int (*instr_cb_t)(struct nfp_prog *, struct nfp_insn_meta *); */ struct nfp_insn_meta { struct bpf_insn insn; + struct bpf_reg_state ptr; unsigned int off; unsigned short n; bool skip; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c index 5b783a91b115..e361c0e3b788 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c @@ -112,12 +112,19 @@ nfp_bpf_check_exit(struct nfp_prog *nfp_prog, } static int -nfp_bpf_check_ctx_ptr(struct nfp_prog *nfp_prog, - const struct bpf_verifier_env *env, u8 reg) +nfp_bpf_check_ptr(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + const struct bpf_verifier_env *env, u8 reg) { - if (env->cur_state.regs[reg].type != PTR_TO_CTX) + if (env->cur_state.regs[reg].type != PTR_TO_CTX && + env->cur_state.regs[reg].type != PTR_TO_PACKET) return -EINVAL; + if (meta->ptr.type != NOT_INIT && + meta->ptr.type != env->cur_state.regs[reg].type) + return -EINVAL; + + meta->ptr = env->cur_state.regs[reg]; + return 0; } @@ -145,11 +152,11 @@ nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx) return nfp_bpf_check_exit(priv->prog, env); if ((meta->insn.code & ~BPF_SIZE_MASK) == (BPF_LDX | BPF_MEM)) - return nfp_bpf_check_ctx_ptr(priv->prog, env, - meta->insn.src_reg); + return nfp_bpf_check_ptr(priv->prog, meta, env, + meta->insn.src_reg); if ((meta->insn.code & ~BPF_SIZE_MASK) == (BPF_STX | BPF_MEM)) - return nfp_bpf_check_ctx_ptr(priv->prog, env, - meta->insn.dst_reg); + return nfp_bpf_check_ptr(priv->prog, meta, env, + meta->insn.dst_reg); return 0; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.c b/drivers/net/ethernet/netronome/nfp/nfp_app.c index 82c290763529..5d9e2eba5b49 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.c @@ -31,6 +31,7 @@ * SOFTWARE. */ +#include <linux/bug.h> #include <linux/skbuff.h> #include <linux/slab.h> diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h index af640b5c2108..857bb33020ba 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h @@ -36,6 +36,8 @@ #include <net/devlink.h> +#include <trace/events/devlink.h> + #include "nfp_net_repr.h" struct bpf_prog; @@ -271,11 +273,17 @@ static inline int nfp_app_xdp_offload(struct nfp_app *app, struct nfp_net *nn, static inline bool nfp_app_ctrl_tx(struct nfp_app *app, struct sk_buff *skb) { + trace_devlink_hwmsg(priv_to_devlink(app->pf), false, 0, + skb->data, skb->len); + return nfp_ctrl_tx(app->ctrl, skb); } static inline void nfp_app_ctrl_rx(struct nfp_app *app, struct sk_buff *skb) { + trace_devlink_hwmsg(priv_to_devlink(app->pf), true, 0, + skb->data, skb->len); + app->type->ctrl_msg_rx(app, skb); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.c b/drivers/net/ethernet/netronome/nfp/nfp_asm.c new file mode 100644 index 000000000000..830f6de25f47 --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.c @@ -0,0 +1,257 @@ +/* + * Copyright (C) 2016-2017 Netronome Systems, Inc. + * + * This software is dual licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree or the BSD 2-Clause License provided below. You have the + * option to license this software under the complete terms of either license. + * + * The BSD 2-Clause License: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * 1. Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * 2. Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/bitops.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/types.h> + +#include "nfp_asm.h" + +const struct cmd_tgt_act cmd_tgt_act[__CMD_TGT_MAP_SIZE] = { + [CMD_TGT_WRITE8_SWAP] = { 0x02, 0x42 }, + [CMD_TGT_READ8] = { 0x01, 0x43 }, + [CMD_TGT_READ32] = { 0x00, 0x5c }, + [CMD_TGT_READ32_LE] = { 0x01, 0x5c }, + [CMD_TGT_READ32_SWAP] = { 0x02, 0x5c }, + [CMD_TGT_READ_LE] = { 0x01, 0x40 }, + [CMD_TGT_READ_SWAP_LE] = { 0x03, 0x40 }, +}; + +static u16 nfp_swreg_to_unreg(swreg reg, bool is_dst) +{ + bool lm_id, lm_dec = false; + u16 val = swreg_value(reg); + + switch (swreg_type(reg)) { + case NN_REG_GPR_A: + case NN_REG_GPR_B: + case NN_REG_GPR_BOTH: + return val; + case NN_REG_NNR: + return UR_REG_NN | val; + case NN_REG_XFER: + return UR_REG_XFR | val; + case NN_REG_LMEM: + lm_id = swreg_lm_idx(reg); + + switch (swreg_lm_mode(reg)) { + case NN_LM_MOD_NONE: + if (val & ~UR_REG_LM_IDX_MAX) { + pr_err("LM offset too large\n"); + return 0; + } + return UR_REG_LM | FIELD_PREP(UR_REG_LM_IDX, lm_id) | + val; + case NN_LM_MOD_DEC: + lm_dec = true; + /* fall through */ + case NN_LM_MOD_INC: + if (val) { + pr_err("LM offset in inc/dev mode\n"); + return 0; + } + return UR_REG_LM | UR_REG_LM_POST_MOD | + FIELD_PREP(UR_REG_LM_IDX, lm_id) | + FIELD_PREP(UR_REG_LM_POST_MOD_DEC, lm_dec); + default: + pr_err("bad LM mode for unrestricted operands %d\n", + swreg_lm_mode(reg)); + return 0; + } + case NN_REG_IMM: + if (val & ~0xff) { + pr_err("immediate too large\n"); + return 0; + } + return UR_REG_IMM_encode(val); + case NN_REG_NONE: + return is_dst ? UR_REG_NO_DST : REG_NONE; + } + + pr_err("unrecognized reg encoding %08x\n", reg); + return 0; +} + +int swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg, + struct nfp_insn_ur_regs *reg) +{ + memset(reg, 0, sizeof(*reg)); + + /* Decode destination */ + if (swreg_type(dst) == NN_REG_IMM) + return -EFAULT; + + if (swreg_type(dst) == NN_REG_GPR_B) + reg->dst_ab = ALU_DST_B; + if (swreg_type(dst) == NN_REG_GPR_BOTH) + reg->wr_both = true; + reg->dst = nfp_swreg_to_unreg(dst, true); + + /* Decode source operands */ + if (swreg_type(lreg) == swreg_type(rreg)) + return -EFAULT; + + if (swreg_type(lreg) == NN_REG_GPR_B || + swreg_type(rreg) == NN_REG_GPR_A) { + reg->areg = nfp_swreg_to_unreg(rreg, false); + reg->breg = nfp_swreg_to_unreg(lreg, false); + reg->swap = true; + } else { + reg->areg = nfp_swreg_to_unreg(lreg, false); + reg->breg = nfp_swreg_to_unreg(rreg, false); + } + + reg->dst_lmextn = swreg_lmextn(dst); + reg->src_lmextn = swreg_lmextn(lreg) | swreg_lmextn(rreg); + + return 0; +} + +static u16 nfp_swreg_to_rereg(swreg reg, bool is_dst, bool has_imm8, bool *i8) +{ + u16 val = swreg_value(reg); + bool lm_id; + + switch (swreg_type(reg)) { + case NN_REG_GPR_A: + case NN_REG_GPR_B: + case NN_REG_GPR_BOTH: + return val; + case NN_REG_XFER: + return RE_REG_XFR | val; + case NN_REG_LMEM: + lm_id = swreg_lm_idx(reg); + + if (swreg_lm_mode(reg) != NN_LM_MOD_NONE) { + pr_err("bad LM mode for restricted operands %d\n", + swreg_lm_mode(reg)); + return 0; + } + + if (val & ~RE_REG_LM_IDX_MAX) { + pr_err("LM offset too large\n"); + return 0; + } + + return RE_REG_LM | FIELD_PREP(RE_REG_LM_IDX, lm_id) | val; + case NN_REG_IMM: + if (val & ~(0x7f | has_imm8 << 7)) { + pr_err("immediate too large\n"); + return 0; + } + *i8 = val & 0x80; + return RE_REG_IMM_encode(val & 0x7f); + case NN_REG_NONE: + return is_dst ? RE_REG_NO_DST : REG_NONE; + case NN_REG_NNR: + pr_err("NNRs used with restricted encoding\n"); + return 0; + } + + pr_err("unrecognized reg encoding\n"); + return 0; +} + +int swreg_to_restricted(swreg dst, swreg lreg, swreg rreg, + struct nfp_insn_re_regs *reg, bool has_imm8) +{ + memset(reg, 0, sizeof(*reg)); + + /* Decode destination */ + if (swreg_type(dst) == NN_REG_IMM) + return -EFAULT; + + if (swreg_type(dst) == NN_REG_GPR_B) + reg->dst_ab = ALU_DST_B; + if (swreg_type(dst) == NN_REG_GPR_BOTH) + reg->wr_both = true; + reg->dst = nfp_swreg_to_rereg(dst, true, false, NULL); + + /* Decode source operands */ + if (swreg_type(lreg) == swreg_type(rreg)) + return -EFAULT; + + if (swreg_type(lreg) == NN_REG_GPR_B || + swreg_type(rreg) == NN_REG_GPR_A) { + reg->areg = nfp_swreg_to_rereg(rreg, false, has_imm8, ®->i8); + reg->breg = nfp_swreg_to_rereg(lreg, false, has_imm8, ®->i8); + reg->swap = true; + } else { + reg->areg = nfp_swreg_to_rereg(lreg, false, has_imm8, ®->i8); + reg->breg = nfp_swreg_to_rereg(rreg, false, has_imm8, ®->i8); + } + + reg->dst_lmextn = swreg_lmextn(dst); + reg->src_lmextn = swreg_lmextn(lreg) | swreg_lmextn(rreg); + + return 0; +} + +#define NFP_USTORE_ECC_POLY_WORDS 7 +#define NFP_USTORE_OP_BITS 45 + +static const u64 nfp_ustore_ecc_polynomials[NFP_USTORE_ECC_POLY_WORDS] = { + 0x0ff800007fffULL, + 0x11f801ff801fULL, + 0x1e387e0781e1ULL, + 0x17cb8e388e22ULL, + 0x1af5b2c93244ULL, + 0x1f56d5525488ULL, + 0x0daf69a46910ULL, +}; + +static bool parity(u64 value) +{ + return hweight64(value) & 1; +} + +int nfp_ustore_check_valid_no_ecc(u64 insn) +{ + if (insn & ~GENMASK_ULL(NFP_USTORE_OP_BITS, 0)) + return -EINVAL; + + return 0; +} + +u64 nfp_ustore_calc_ecc_insn(u64 insn) +{ + u8 ecc = 0; + int i; + + for (i = 0; i < NFP_USTORE_ECC_POLY_WORDS; i++) + ecc |= parity(nfp_ustore_ecc_polynomials[i] & insn) << i; + + return insn | (u64)ecc << NFP_USTORE_OP_BITS; +} diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h index d2b535739d2b..86e7daee6099 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h @@ -34,6 +34,8 @@ #ifndef __NFP_ASM_H__ #define __NFP_ASM_H__ 1 +#include <linux/bitfield.h> +#include <linux/bug.h> #include <linux/types.h> #define REG_NONE 0 @@ -43,23 +45,31 @@ #define RE_REG_IMM_encode(x) \ (RE_REG_IMM | ((x) & 0x1f) | (((x) & 0x60) << 1)) #define RE_REG_IMM_MAX 0x07fULL +#define RE_REG_LM 0x050 +#define RE_REG_LM_IDX 0x008 +#define RE_REG_LM_IDX_MAX 0x7 #define RE_REG_XFR 0x080 #define UR_REG_XFR 0x180 +#define UR_REG_LM 0x200 +#define UR_REG_LM_IDX 0x020 +#define UR_REG_LM_POST_MOD 0x010 +#define UR_REG_LM_POST_MOD_DEC 0x001 +#define UR_REG_LM_IDX_MAX 0xf #define UR_REG_NN 0x280 #define UR_REG_NO_DST 0x300 #define UR_REG_IMM UR_REG_NO_DST #define UR_REG_IMM_encode(x) (UR_REG_IMM | (x)) #define UR_REG_IMM_MAX 0x0ffULL -#define OP_BR_BASE 0x0d800000020ULL -#define OP_BR_BASE_MASK 0x0f8000c3ce0ULL -#define OP_BR_MASK 0x0000000001fULL -#define OP_BR_EV_PIP 0x00000000300ULL -#define OP_BR_CSS 0x0000003c000ULL -#define OP_BR_DEFBR 0x00000300000ULL -#define OP_BR_ADDR_LO 0x007ffc00000ULL -#define OP_BR_ADDR_HI 0x10000000000ULL +#define OP_BR_BASE 0x0d800000020ULL +#define OP_BR_BASE_MASK 0x0f8000c3ce0ULL +#define OP_BR_MASK 0x0000000001fULL +#define OP_BR_EV_PIP 0x00000000300ULL +#define OP_BR_CSS 0x0000003c000ULL +#define OP_BR_DEFBR 0x00000300000ULL +#define OP_BR_ADDR_LO 0x007ffc00000ULL +#define OP_BR_ADDR_HI 0x10000000000ULL #define nfp_is_br(_insn) \ (((_insn) & OP_BR_BASE_MASK) == OP_BR_BASE) @@ -82,30 +92,33 @@ enum br_ctx_signal_state { BR_CSS_NONE = 2, }; -#define OP_BBYTE_BASE 0x0c800000000ULL -#define OP_BB_A_SRC 0x000000000ffULL -#define OP_BB_BYTE 0x00000000300ULL -#define OP_BB_B_SRC 0x0000003fc00ULL -#define OP_BB_I8 0x00000040000ULL -#define OP_BB_EQ 0x00000080000ULL -#define OP_BB_DEFBR 0x00000300000ULL -#define OP_BB_ADDR_LO 0x007ffc00000ULL -#define OP_BB_ADDR_HI 0x10000000000ULL - -#define OP_BALU_BASE 0x0e800000000ULL -#define OP_BA_A_SRC 0x000000003ffULL -#define OP_BA_B_SRC 0x000000ffc00ULL -#define OP_BA_DEFBR 0x00000300000ULL -#define OP_BA_ADDR_HI 0x0007fc00000ULL - -#define OP_IMMED_A_SRC 0x000000003ffULL -#define OP_IMMED_B_SRC 0x000000ffc00ULL -#define OP_IMMED_IMM 0x0000ff00000ULL -#define OP_IMMED_WIDTH 0x00060000000ULL -#define OP_IMMED_INV 0x00080000000ULL -#define OP_IMMED_SHIFT 0x00600000000ULL -#define OP_IMMED_BASE 0x0f000000000ULL -#define OP_IMMED_WR_AB 0x20000000000ULL +#define OP_BBYTE_BASE 0x0c800000000ULL +#define OP_BB_A_SRC 0x000000000ffULL +#define OP_BB_BYTE 0x00000000300ULL +#define OP_BB_B_SRC 0x0000003fc00ULL +#define OP_BB_I8 0x00000040000ULL +#define OP_BB_EQ 0x00000080000ULL +#define OP_BB_DEFBR 0x00000300000ULL +#define OP_BB_ADDR_LO 0x007ffc00000ULL +#define OP_BB_ADDR_HI 0x10000000000ULL +#define OP_BB_SRC_LMEXTN 0x40000000000ULL + +#define OP_BALU_BASE 0x0e800000000ULL +#define OP_BA_A_SRC 0x000000003ffULL +#define OP_BA_B_SRC 0x000000ffc00ULL +#define OP_BA_DEFBR 0x00000300000ULL +#define OP_BA_ADDR_HI 0x0007fc00000ULL + +#define OP_IMMED_A_SRC 0x000000003ffULL +#define OP_IMMED_B_SRC 0x000000ffc00ULL +#define OP_IMMED_IMM 0x0000ff00000ULL +#define OP_IMMED_WIDTH 0x00060000000ULL +#define OP_IMMED_INV 0x00080000000ULL +#define OP_IMMED_SHIFT 0x00600000000ULL +#define OP_IMMED_BASE 0x0f000000000ULL +#define OP_IMMED_WR_AB 0x20000000000ULL +#define OP_IMMED_SRC_LMEXTN 0x40000000000ULL +#define OP_IMMED_DST_LMEXTN 0x80000000000ULL enum immed_width { IMMED_WIDTH_ALL = 0, @@ -119,17 +132,19 @@ enum immed_shift { IMMED_SHIFT_2B = 2, }; -#define OP_SHF_BASE 0x08000000000ULL -#define OP_SHF_A_SRC 0x000000000ffULL -#define OP_SHF_SC 0x00000000300ULL -#define OP_SHF_B_SRC 0x0000003fc00ULL -#define OP_SHF_I8 0x00000040000ULL -#define OP_SHF_SW 0x00000080000ULL -#define OP_SHF_DST 0x0000ff00000ULL -#define OP_SHF_SHIFT 0x001f0000000ULL -#define OP_SHF_OP 0x00e00000000ULL -#define OP_SHF_DST_AB 0x01000000000ULL -#define OP_SHF_WR_AB 0x20000000000ULL +#define OP_SHF_BASE 0x08000000000ULL +#define OP_SHF_A_SRC 0x000000000ffULL +#define OP_SHF_SC 0x00000000300ULL +#define OP_SHF_B_SRC 0x0000003fc00ULL +#define OP_SHF_I8 0x00000040000ULL +#define OP_SHF_SW 0x00000080000ULL +#define OP_SHF_DST 0x0000ff00000ULL +#define OP_SHF_SHIFT 0x001f0000000ULL +#define OP_SHF_OP 0x00e00000000ULL +#define OP_SHF_DST_AB 0x01000000000ULL +#define OP_SHF_WR_AB 0x20000000000ULL +#define OP_SHF_SRC_LMEXTN 0x40000000000ULL +#define OP_SHF_DST_LMEXTN 0x80000000000ULL enum shf_op { SHF_OP_NONE = 0, @@ -139,19 +154,22 @@ enum shf_op { enum shf_sc { SHF_SC_R_ROT = 0, + SHF_SC_NONE = SHF_SC_R_ROT, SHF_SC_R_SHF = 1, SHF_SC_L_SHF = 2, SHF_SC_R_DSHF = 3, }; -#define OP_ALU_A_SRC 0x000000003ffULL -#define OP_ALU_B_SRC 0x000000ffc00ULL -#define OP_ALU_DST 0x0003ff00000ULL -#define OP_ALU_SW 0x00040000000ULL -#define OP_ALU_OP 0x00f80000000ULL -#define OP_ALU_DST_AB 0x01000000000ULL -#define OP_ALU_BASE 0x0a000000000ULL -#define OP_ALU_WR_AB 0x20000000000ULL +#define OP_ALU_A_SRC 0x000000003ffULL +#define OP_ALU_B_SRC 0x000000ffc00ULL +#define OP_ALU_DST 0x0003ff00000ULL +#define OP_ALU_SW 0x00040000000ULL +#define OP_ALU_OP 0x00f80000000ULL +#define OP_ALU_DST_AB 0x01000000000ULL +#define OP_ALU_BASE 0x0a000000000ULL +#define OP_ALU_WR_AB 0x20000000000ULL +#define OP_ALU_SRC_LMEXTN 0x40000000000ULL +#define OP_ALU_DST_LMEXTN 0x80000000000ULL enum alu_op { ALU_OP_NONE = 0x00, @@ -170,26 +188,28 @@ enum alu_dst_ab { ALU_DST_B = 1, }; -#define OP_LDF_BASE 0x0c000000000ULL -#define OP_LDF_A_SRC 0x000000000ffULL -#define OP_LDF_SC 0x00000000300ULL -#define OP_LDF_B_SRC 0x0000003fc00ULL -#define OP_LDF_I8 0x00000040000ULL -#define OP_LDF_SW 0x00000080000ULL -#define OP_LDF_ZF 0x00000100000ULL -#define OP_LDF_BMASK 0x0000f000000ULL -#define OP_LDF_SHF 0x001f0000000ULL -#define OP_LDF_WR_AB 0x20000000000ULL - -#define OP_CMD_A_SRC 0x000000000ffULL -#define OP_CMD_CTX 0x00000000300ULL -#define OP_CMD_B_SRC 0x0000003fc00ULL -#define OP_CMD_TOKEN 0x000000c0000ULL -#define OP_CMD_XFER 0x00001f00000ULL -#define OP_CMD_CNT 0x0000e000000ULL -#define OP_CMD_SIG 0x000f0000000ULL -#define OP_CMD_TGT_CMD 0x07f00000000ULL -#define OP_CMD_MODE 0x1c0000000000ULL +#define OP_LDF_BASE 0x0c000000000ULL +#define OP_LDF_A_SRC 0x000000000ffULL +#define OP_LDF_SC 0x00000000300ULL +#define OP_LDF_B_SRC 0x0000003fc00ULL +#define OP_LDF_I8 0x00000040000ULL +#define OP_LDF_SW 0x00000080000ULL +#define OP_LDF_ZF 0x00000100000ULL +#define OP_LDF_BMASK 0x0000f000000ULL +#define OP_LDF_SHF 0x001f0000000ULL +#define OP_LDF_WR_AB 0x20000000000ULL +#define OP_LDF_SRC_LMEXTN 0x40000000000ULL +#define OP_LDF_DST_LMEXTN 0x80000000000ULL + +#define OP_CMD_A_SRC 0x000000000ffULL +#define OP_CMD_CTX 0x00000000300ULL +#define OP_CMD_B_SRC 0x0000003fc00ULL +#define OP_CMD_TOKEN 0x000000c0000ULL +#define OP_CMD_XFER 0x00001f00000ULL +#define OP_CMD_CNT 0x0000e000000ULL +#define OP_CMD_SIG 0x000f0000000ULL +#define OP_CMD_TGT_CMD 0x07f00000000ULL +#define OP_CMD_MODE 0x1c0000000000ULL struct cmd_tgt_act { u8 token; @@ -198,12 +218,17 @@ struct cmd_tgt_act { enum cmd_tgt_map { CMD_TGT_READ8, - CMD_TGT_WRITE8, + CMD_TGT_WRITE8_SWAP, + CMD_TGT_READ32, + CMD_TGT_READ32_LE, + CMD_TGT_READ32_SWAP, CMD_TGT_READ_LE, CMD_TGT_READ_SWAP_LE, __CMD_TGT_MAP_SIZE, }; +extern const struct cmd_tgt_act cmd_tgt_act[__CMD_TGT_MAP_SIZE]; + enum cmd_mode { CMD_MODE_40b_AB = 0, CMD_MODE_40b_BA = 1, @@ -215,11 +240,13 @@ enum cmd_ctx_swap { CMD_CTX_NO_SWAP = 3, }; -#define OP_LCSR_BASE 0x0fc00000000ULL -#define OP_LCSR_A_SRC 0x000000003ffULL -#define OP_LCSR_B_SRC 0x000000ffc00ULL -#define OP_LCSR_WRITE 0x00000200000ULL -#define OP_LCSR_ADDR 0x001ffc00000ULL +#define OP_LCSR_BASE 0x0fc00000000ULL +#define OP_LCSR_A_SRC 0x000000003ffULL +#define OP_LCSR_B_SRC 0x000000ffc00ULL +#define OP_LCSR_WRITE 0x00000200000ULL +#define OP_LCSR_ADDR 0x001ffc00000ULL +#define OP_LCSR_SRC_LMEXTN 0x40000000000ULL +#define OP_LCSR_DST_LMEXTN 0x80000000000ULL enum lcsr_wr_src { LCSR_WR_AREG, @@ -227,7 +254,122 @@ enum lcsr_wr_src { LCSR_WR_IMM, }; -#define OP_CARB_BASE 0x0e000000000ULL -#define OP_CARB_OR 0x00000010000ULL +#define OP_CARB_BASE 0x0e000000000ULL +#define OP_CARB_OR 0x00000010000ULL + +/* Software register representation, independent of operand type */ +#define NN_REG_TYPE GENMASK(31, 24) +#define NN_REG_LM_IDX GENMASK(23, 22) +#define NN_REG_LM_IDX_HI BIT(23) +#define NN_REG_LM_IDX_LO BIT(22) +#define NN_REG_LM_MOD GENMASK(21, 20) +#define NN_REG_VAL GENMASK(7, 0) + +enum nfp_bpf_reg_type { + NN_REG_GPR_A = BIT(0), + NN_REG_GPR_B = BIT(1), + NN_REG_GPR_BOTH = NN_REG_GPR_A | NN_REG_GPR_B, + NN_REG_NNR = BIT(2), + NN_REG_XFER = BIT(3), + NN_REG_IMM = BIT(4), + NN_REG_NONE = BIT(5), + NN_REG_LMEM = BIT(6), +}; + +enum nfp_bpf_lm_mode { + NN_LM_MOD_NONE = 0, + NN_LM_MOD_INC, + NN_LM_MOD_DEC, +}; + +#define reg_both(x) __enc_swreg((x), NN_REG_GPR_BOTH) +#define reg_a(x) __enc_swreg((x), NN_REG_GPR_A) +#define reg_b(x) __enc_swreg((x), NN_REG_GPR_B) +#define reg_nnr(x) __enc_swreg((x), NN_REG_NNR) +#define reg_xfer(x) __enc_swreg((x), NN_REG_XFER) +#define reg_imm(x) __enc_swreg((x), NN_REG_IMM) +#define reg_none() __enc_swreg(0, NN_REG_NONE) +#define reg_lm(x, off) __enc_swreg_lm((x), NN_LM_MOD_NONE, (off)) +#define reg_lm_inc(x) __enc_swreg_lm((x), NN_LM_MOD_INC, 0) +#define reg_lm_dec(x) __enc_swreg_lm((x), NN_LM_MOD_DEC, 0) +#define __reg_lm(x, mod, off) __enc_swreg_lm((x), (mod), (off)) + +typedef __u32 __bitwise swreg; + +static inline swreg __enc_swreg(u16 id, u8 type) +{ + return (__force swreg)(id | FIELD_PREP(NN_REG_TYPE, type)); +} + +static inline swreg __enc_swreg_lm(u8 id, enum nfp_bpf_lm_mode mode, u8 off) +{ + WARN_ON(id > 3 || (off && mode != NN_LM_MOD_NONE)); + + return (__force swreg)(FIELD_PREP(NN_REG_TYPE, NN_REG_LMEM) | + FIELD_PREP(NN_REG_LM_IDX, id) | + FIELD_PREP(NN_REG_LM_MOD, mode) | + off); +} + +static inline u32 swreg_raw(swreg reg) +{ + return (__force u32)reg; +} + +static inline enum nfp_bpf_reg_type swreg_type(swreg reg) +{ + return FIELD_GET(NN_REG_TYPE, swreg_raw(reg)); +} + +static inline u16 swreg_value(swreg reg) +{ + return FIELD_GET(NN_REG_VAL, swreg_raw(reg)); +} + +static inline bool swreg_lm_idx(swreg reg) +{ + return FIELD_GET(NN_REG_LM_IDX_LO, swreg_raw(reg)); +} + +static inline bool swreg_lmextn(swreg reg) +{ + return FIELD_GET(NN_REG_LM_IDX_HI, swreg_raw(reg)); +} + +static inline enum nfp_bpf_lm_mode swreg_lm_mode(swreg reg) +{ + return FIELD_GET(NN_REG_LM_MOD, swreg_raw(reg)); +} + +struct nfp_insn_ur_regs { + enum alu_dst_ab dst_ab; + u16 dst; + u16 areg, breg; + bool swap; + bool wr_both; + bool dst_lmextn; + bool src_lmextn; +}; + +struct nfp_insn_re_regs { + enum alu_dst_ab dst_ab; + u8 dst; + u8 areg, breg; + bool swap; + bool wr_both; + bool i8; + bool dst_lmextn; + bool src_lmextn; +}; + +int swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg, + struct nfp_insn_ur_regs *reg); +int swreg_to_restricted(swreg dst, swreg lreg, swreg rreg, + struct nfp_insn_re_regs *reg, bool has_imm8); + +#define NFP_USTORE_PREFETCH_WINDOW 8 + +int nfp_ustore_check_valid_no_ecc(u64 insn); +u64 nfp_ustore_calc_ecc_insn(u64 insn); #endif diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index b0a452ba9039..782d452e0fc2 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -255,7 +255,7 @@ * @NFP_NET_CFG_BPF_ADDR: DMA address of the buffer with JITed BPF code */ #define NFP_NET_CFG_BPF_ABI 0x0080 -#define NFP_NET_BPF_ABI 1 +#define NFP_NET_BPF_ABI 2 #define NFP_NET_CFG_BPF_CAP 0x0081 #define NFP_NET_BPF_CAP_RELO (1 << 0) /* seamless reload */ #define NFP_NET_CFG_BPF_MAX_LEN 0x0082 diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index a235e8881af9..88128ce61471 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -1884,10 +1884,9 @@ packet_dropped: } /* If rx bufs are exhausted called after 50ms to attempt to refresh */ -static void nv_do_rx_refill(unsigned long data) +static void nv_do_rx_refill(struct timer_list *t) { - struct net_device *dev = (struct net_device *) data; - struct fe_priv *np = netdev_priv(dev); + struct fe_priv *np = from_timer(np, t, oom_kick); /* Just reschedule NAPI rx processing */ napi_schedule(&np->napi); @@ -4065,10 +4064,10 @@ static void nv_free_irq(struct net_device *dev) } } -static void nv_do_nic_poll(unsigned long data) +static void nv_do_nic_poll(struct timer_list *t) { - struct net_device *dev = (struct net_device *) data; - struct fe_priv *np = netdev_priv(dev); + struct fe_priv *np = from_timer(np, t, nic_poll); + struct net_device *dev = np->dev; u8 __iomem *base = get_hwbase(dev); u32 mask = 0; unsigned long flags; @@ -4176,16 +4175,18 @@ static void nv_do_nic_poll(unsigned long data) #ifdef CONFIG_NET_POLL_CONTROLLER static void nv_poll_controller(struct net_device *dev) { - nv_do_nic_poll((unsigned long) dev); + struct fe_priv *np = netdev_priv(dev); + + nv_do_nic_poll(&np->nic_poll); } #endif -static void nv_do_stats_poll(unsigned long data) +static void nv_do_stats_poll(struct timer_list *t) __acquires(&netdev_priv(dev)->hwstats_lock) __releases(&netdev_priv(dev)->hwstats_lock) { - struct net_device *dev = (struct net_device *) data; - struct fe_priv *np = netdev_priv(dev); + struct fe_priv *np = from_timer(np, t, stats_poll); + struct net_device *dev = np->dev; /* If lock is currently taken, the stats are being refreshed * and hence fresh enough */ @@ -5631,10 +5632,9 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) u64_stats_init(&np->swstats_rx_syncp); u64_stats_init(&np->swstats_tx_syncp); - setup_timer(&np->oom_kick, nv_do_rx_refill, (unsigned long)dev); - setup_timer(&np->nic_poll, nv_do_nic_poll, (unsigned long)dev); - setup_deferrable_timer(&np->stats_poll, nv_do_stats_poll, - (unsigned long)dev); + timer_setup(&np->oom_kick, nv_do_rx_refill, 0); + timer_setup(&np->nic_poll, nv_do_nic_poll, 0); + timer_setup(&np->stats_poll, nv_do_stats_poll, TIMER_DEFERRABLE); err = pci_enable_device(pci_dev); if (err) diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h index 8d710a3b4db0..697e29dd4bd3 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h @@ -613,7 +613,6 @@ struct pch_gbe_privdata { * @rx_ring: Pointer of Rx descriptor ring structure * @rx_buffer_len: Receive buffer length * @tx_queue_len: Transmit queue length - * @have_msi: PCI MSI mode flag * @pch_gbe_privdata: PCI Device ID driver_data */ @@ -623,6 +622,7 @@ struct pch_gbe_adapter { atomic_t irq_sem; struct net_device *netdev; struct pci_dev *pdev; + int irq; struct net_device *polling_netdev; struct napi_struct napi; struct pch_gbe_hw hw; @@ -637,7 +637,6 @@ struct pch_gbe_adapter { struct pch_gbe_rx_ring *rx_ring; unsigned long rx_buffer_len; unsigned long tx_queue_len; - bool have_msi; bool rx_stop_flag; int hwts_tx_en; int hwts_rx_en; diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index 5ae9681a2da7..457ee80307ea 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -781,11 +781,8 @@ static void pch_gbe_free_irq(struct pch_gbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; - free_irq(adapter->pdev->irq, netdev); - if (adapter->have_msi) { - pci_disable_msi(adapter->pdev); - netdev_dbg(netdev, "call pci_disable_msi\n"); - } + free_irq(adapter->irq, netdev); + pci_free_irq_vectors(adapter->pdev); } /** @@ -799,7 +796,7 @@ static void pch_gbe_irq_disable(struct pch_gbe_adapter *adapter) atomic_inc(&adapter->irq_sem); iowrite32(0, &hw->reg->INT_EN); ioread32(&hw->reg->INT_ST); - synchronize_irq(adapter->pdev->irq); + synchronize_irq(adapter->irq); netdev_dbg(adapter->netdev, "INT_EN reg : 0x%08x\n", ioread32(&hw->reg->INT_EN)); @@ -1903,30 +1900,23 @@ static int pch_gbe_request_irq(struct pch_gbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; int err; - int flags; - flags = IRQF_SHARED; - adapter->have_msi = false; - err = pci_enable_msi(adapter->pdev); - netdev_dbg(netdev, "call pci_enable_msi\n"); - if (err) { - netdev_dbg(netdev, "call pci_enable_msi - Error: %d\n", err); - } else { - flags = 0; - adapter->have_msi = true; - } - err = request_irq(adapter->pdev->irq, &pch_gbe_intr, - flags, netdev->name, netdev); + err = pci_alloc_irq_vectors(adapter->pdev, 1, 1, PCI_IRQ_ALL_TYPES); + if (err < 0) + return err; + + adapter->irq = pci_irq_vector(adapter->pdev, 0); + + err = request_irq(adapter->irq, &pch_gbe_intr, IRQF_SHARED, + netdev->name, netdev); if (err) netdev_err(netdev, "Unable to allocate interrupt Error: %d\n", err); - netdev_dbg(netdev, - "adapter->have_msi : %d flags : 0x%04x return : 0x%04x\n", - adapter->have_msi, flags, err); + netdev_dbg(netdev, "have_msi : %d return : 0x%04x\n", + pci_dev_msi_enabled(adapter->pdev), err); return err; } - /** * pch_gbe_up - Up GbE network device * @adapter: Board private structure @@ -2399,9 +2389,9 @@ static void pch_gbe_netpoll(struct net_device *netdev) { struct pch_gbe_adapter *adapter = netdev_priv(netdev); - disable_irq(adapter->pdev->irq); - pch_gbe_intr(adapter->pdev->irq, netdev); - enable_irq(adapter->pdev->irq); + disable_irq(adapter->irq); + pch_gbe_intr(adapter->irq, netdev); + enable_irq(adapter->irq); } #endif diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig index c2e24afbaeb2..26ddf092e3ec 100644 --- a/drivers/net/ethernet/qlogic/Kconfig +++ b/drivers/net/ethernet/qlogic/Kconfig @@ -117,4 +117,7 @@ config QED_ISCSI config QED_FCOE bool +config QED_OOO + bool + endif # NET_VENDOR_QLOGIC diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile index 82dd47068e18..c3c599950574 100644 --- a/drivers/net/ethernet/qlogic/qed/Makefile +++ b/drivers/net/ethernet/qlogic/qed/Makefile @@ -6,5 +6,6 @@ qed-y := qed_cxt.o qed_dev.o qed_hw.o qed_init_fw_funcs.o qed_init_ops.o \ qed-$(CONFIG_QED_SRIOV) += qed_sriov.o qed_vf.o qed-$(CONFIG_QED_LL2) += qed_ll2.o qed-$(CONFIG_QED_RDMA) += qed_roce.o qed_rdma.o qed_iwarp.o -qed-$(CONFIG_QED_ISCSI) += qed_iscsi.o qed_ooo.o +qed-$(CONFIG_QED_ISCSI) += qed_iscsi.o qed-$(CONFIG_QED_FCOE) += qed_fcoe.o +qed-$(CONFIG_QED_OOO) += qed_ooo.o diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 8f6ccc0c39e5..6e15d3c10ebf 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -2308,7 +2308,7 @@ static int qed_dcbnl_ieee_setapp(struct qed_dev *cdev, struct dcb_app *app) DP_VERBOSE(hwfn, QED_MSG_DCB, "selector = %d protocol = %d pri = %d\n", app->selector, app->protocol, app->priority); - if (app->priority < 0 || app->priority >= QED_MAX_PFC_PRIORITIES) { + if (app->priority >= QED_MAX_PFC_PRIORITIES) { DP_INFO(hwfn, "Invalid priority %d\n", app->priority); return -EINVAL; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index 8fc9c811f6e3..409041eab189 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1410,12 +1410,22 @@ int qed_iwarp_alloc(struct qed_hwfn *p_hwfn) INIT_LIST_HEAD(&p_hwfn->p_rdma_info->iwarp.ep_free_list); spin_lock_init(&p_hwfn->p_rdma_info->iwarp.iw_lock); - return qed_iwarp_prealloc_ep(p_hwfn, true); + rc = qed_iwarp_prealloc_ep(p_hwfn, true); + if (rc) + return rc; + + return qed_ooo_alloc(p_hwfn); } void qed_iwarp_resc_free(struct qed_hwfn *p_hwfn) { + struct qed_iwarp_info *iwarp_info = &p_hwfn->p_rdma_info->iwarp; + + qed_ooo_free(p_hwfn); qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->tcp_cid_map, 1); + kfree(iwarp_info->mpa_bufs); + kfree(iwarp_info->partial_fpdus); + kfree(iwarp_info->mpa_intermediate_buf); } int qed_iwarp_accept(void *rdma_cxt, struct qed_iwarp_accept_in *iparams) @@ -1713,6 +1723,569 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn, return 0; } +static struct qed_iwarp_fpdu *qed_iwarp_get_curr_fpdu(struct qed_hwfn *p_hwfn, + u16 cid) +{ + struct qed_iwarp_info *iwarp_info = &p_hwfn->p_rdma_info->iwarp; + struct qed_iwarp_fpdu *partial_fpdu; + u32 idx; + + idx = cid - qed_cxt_get_proto_cid_start(p_hwfn, PROTOCOLID_IWARP); + if (idx >= iwarp_info->max_num_partial_fpdus) { + DP_ERR(p_hwfn, "Invalid cid %x max_num_partial_fpdus=%x\n", cid, + iwarp_info->max_num_partial_fpdus); + return NULL; + } + + partial_fpdu = &iwarp_info->partial_fpdus[idx]; + + return partial_fpdu; +} + +enum qed_iwarp_mpa_pkt_type { + QED_IWARP_MPA_PKT_PACKED, + QED_IWARP_MPA_PKT_PARTIAL, + QED_IWARP_MPA_PKT_UNALIGNED +}; + +#define QED_IWARP_INVALID_FPDU_LENGTH 0xffff +#define QED_IWARP_MPA_FPDU_LENGTH_SIZE (2) +#define QED_IWARP_MPA_CRC32_DIGEST_SIZE (4) + +/* Pad to multiple of 4 */ +#define QED_IWARP_PDU_DATA_LEN_WITH_PAD(data_len) ALIGN(data_len, 4) +#define QED_IWARP_FPDU_LEN_WITH_PAD(_mpa_len) \ + (QED_IWARP_PDU_DATA_LEN_WITH_PAD((_mpa_len) + \ + QED_IWARP_MPA_FPDU_LENGTH_SIZE) + \ + QED_IWARP_MPA_CRC32_DIGEST_SIZE) + +/* fpdu can be fragmented over maximum 3 bds: header, partial mpa, unaligned */ +#define QED_IWARP_MAX_BDS_PER_FPDU 3 + +char *pkt_type_str[] = { + "QED_IWARP_MPA_PKT_PACKED", + "QED_IWARP_MPA_PKT_PARTIAL", + "QED_IWARP_MPA_PKT_UNALIGNED" +}; + +static int +qed_iwarp_recycle_pkt(struct qed_hwfn *p_hwfn, + struct qed_iwarp_fpdu *fpdu, + struct qed_iwarp_ll2_buff *buf); + +static enum qed_iwarp_mpa_pkt_type +qed_iwarp_mpa_classify(struct qed_hwfn *p_hwfn, + struct qed_iwarp_fpdu *fpdu, + u16 tcp_payload_len, u8 *mpa_data) +{ + enum qed_iwarp_mpa_pkt_type pkt_type; + u16 mpa_len; + + if (fpdu->incomplete_bytes) { + pkt_type = QED_IWARP_MPA_PKT_UNALIGNED; + goto out; + } + + /* special case of one byte remaining... + * lower byte will be read next packet + */ + if (tcp_payload_len == 1) { + fpdu->fpdu_length = *mpa_data << BITS_PER_BYTE; + pkt_type = QED_IWARP_MPA_PKT_PARTIAL; + goto out; + } + + mpa_len = ntohs(*((u16 *)(mpa_data))); + fpdu->fpdu_length = QED_IWARP_FPDU_LEN_WITH_PAD(mpa_len); + + if (fpdu->fpdu_length <= tcp_payload_len) + pkt_type = QED_IWARP_MPA_PKT_PACKED; + else + pkt_type = QED_IWARP_MPA_PKT_PARTIAL; + +out: + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "MPA_ALIGN: %s: fpdu_length=0x%x tcp_payload_len:0x%x\n", + pkt_type_str[pkt_type], fpdu->fpdu_length, tcp_payload_len); + + return pkt_type; +} + +static void +qed_iwarp_init_fpdu(struct qed_iwarp_ll2_buff *buf, + struct qed_iwarp_fpdu *fpdu, + struct unaligned_opaque_data *pkt_data, + u16 tcp_payload_size, u8 placement_offset) +{ + fpdu->mpa_buf = buf; + fpdu->pkt_hdr = buf->data_phys_addr + placement_offset; + fpdu->pkt_hdr_size = pkt_data->tcp_payload_offset; + fpdu->mpa_frag = buf->data_phys_addr + pkt_data->first_mpa_offset; + fpdu->mpa_frag_virt = (u8 *)(buf->data) + pkt_data->first_mpa_offset; + + if (tcp_payload_size == 1) + fpdu->incomplete_bytes = QED_IWARP_INVALID_FPDU_LENGTH; + else if (tcp_payload_size < fpdu->fpdu_length) + fpdu->incomplete_bytes = fpdu->fpdu_length - tcp_payload_size; + else + fpdu->incomplete_bytes = 0; /* complete fpdu */ + + fpdu->mpa_frag_len = fpdu->fpdu_length - fpdu->incomplete_bytes; +} + +static int +qed_iwarp_cp_pkt(struct qed_hwfn *p_hwfn, + struct qed_iwarp_fpdu *fpdu, + struct unaligned_opaque_data *pkt_data, + struct qed_iwarp_ll2_buff *buf, u16 tcp_payload_size) +{ + u8 *tmp_buf = p_hwfn->p_rdma_info->iwarp.mpa_intermediate_buf; + int rc; + + /* need to copy the data from the partial packet stored in fpdu + * to the new buf, for this we also need to move the data currently + * placed on the buf. The assumption is that the buffer is big enough + * since fpdu_length <= mss, we use an intermediate buffer since + * we may need to copy the new data to an overlapping location + */ + if ((fpdu->mpa_frag_len + tcp_payload_size) > (u16)buf->buff_size) { + DP_ERR(p_hwfn, + "MPA ALIGN: Unexpected: buffer is not large enough for split fpdu buff_size = %d mpa_frag_len = %d, tcp_payload_size = %d, incomplete_bytes = %d\n", + buf->buff_size, fpdu->mpa_frag_len, + tcp_payload_size, fpdu->incomplete_bytes); + return -EINVAL; + } + + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "MPA ALIGN Copying fpdu: [%p, %d] [%p, %d]\n", + fpdu->mpa_frag_virt, fpdu->mpa_frag_len, + (u8 *)(buf->data) + pkt_data->first_mpa_offset, + tcp_payload_size); + + memcpy(tmp_buf, fpdu->mpa_frag_virt, fpdu->mpa_frag_len); + memcpy(tmp_buf + fpdu->mpa_frag_len, + (u8 *)(buf->data) + pkt_data->first_mpa_offset, + tcp_payload_size); + + rc = qed_iwarp_recycle_pkt(p_hwfn, fpdu, fpdu->mpa_buf); + if (rc) + return rc; + + /* If we managed to post the buffer copy the data to the new buffer + * o/w this will occur in the next round... + */ + memcpy((u8 *)(buf->data), tmp_buf, + fpdu->mpa_frag_len + tcp_payload_size); + + fpdu->mpa_buf = buf; + /* fpdu->pkt_hdr remains as is */ + /* fpdu->mpa_frag is overridden with new buf */ + fpdu->mpa_frag = buf->data_phys_addr; + fpdu->mpa_frag_virt = buf->data; + fpdu->mpa_frag_len += tcp_payload_size; + + fpdu->incomplete_bytes -= tcp_payload_size; + + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "MPA ALIGN: split fpdu buff_size = %d mpa_frag_len = %d, tcp_payload_size = %d, incomplete_bytes = %d\n", + buf->buff_size, fpdu->mpa_frag_len, tcp_payload_size, + fpdu->incomplete_bytes); + + return 0; +} + +static void +qed_iwarp_update_fpdu_length(struct qed_hwfn *p_hwfn, + struct qed_iwarp_fpdu *fpdu, u8 *mpa_data) +{ + u16 mpa_len; + + /* Update incomplete packets if needed */ + if (fpdu->incomplete_bytes == QED_IWARP_INVALID_FPDU_LENGTH) { + /* Missing lower byte is now available */ + mpa_len = fpdu->fpdu_length | *mpa_data; + fpdu->fpdu_length = QED_IWARP_FPDU_LEN_WITH_PAD(mpa_len); + fpdu->mpa_frag_len = fpdu->fpdu_length; + /* one byte of hdr */ + fpdu->incomplete_bytes = fpdu->fpdu_length - 1; + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "MPA_ALIGN: Partial header mpa_len=%x fpdu_length=%x incomplete_bytes=%x\n", + mpa_len, fpdu->fpdu_length, fpdu->incomplete_bytes); + } +} + +#define QED_IWARP_IS_RIGHT_EDGE(_curr_pkt) \ + (GET_FIELD((_curr_pkt)->flags, \ + UNALIGNED_OPAQUE_DATA_PKT_REACHED_WIN_RIGHT_EDGE)) + +/* This function is used to recycle a buffer using the ll2 drop option. It + * uses the mechanism to ensure that all buffers posted to tx before this one + * were completed. The buffer sent here will be sent as a cookie in the tx + * completion function and can then be reposted to rx chain when done. The flow + * that requires this is the flow where a FPDU splits over more than 3 tcp + * segments. In this case the driver needs to re-post a rx buffer instead of + * the one received, but driver can't simply repost a buffer it copied from + * as there is a case where the buffer was originally a packed FPDU, and is + * partially posted to FW. Driver needs to ensure FW is done with it. + */ +static int +qed_iwarp_recycle_pkt(struct qed_hwfn *p_hwfn, + struct qed_iwarp_fpdu *fpdu, + struct qed_iwarp_ll2_buff *buf) +{ + struct qed_ll2_tx_pkt_info tx_pkt; + u8 ll2_handle; + int rc; + + memset(&tx_pkt, 0, sizeof(tx_pkt)); + tx_pkt.num_of_bds = 1; + tx_pkt.tx_dest = QED_LL2_TX_DEST_DROP; + tx_pkt.l4_hdr_offset_w = fpdu->pkt_hdr_size >> 2; + tx_pkt.first_frag = fpdu->pkt_hdr; + tx_pkt.first_frag_len = fpdu->pkt_hdr_size; + buf->piggy_buf = NULL; + tx_pkt.cookie = buf; + + ll2_handle = p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle; + + rc = qed_ll2_prepare_tx_packet(p_hwfn, ll2_handle, &tx_pkt, true); + if (rc) + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "Can't drop packet rc=%d\n", rc); + + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "MPA_ALIGN: send drop tx packet [%lx, 0x%x], buf=%p, rc=%d\n", + (unsigned long int)tx_pkt.first_frag, + tx_pkt.first_frag_len, buf, rc); + + return rc; +} + +static int +qed_iwarp_win_right_edge(struct qed_hwfn *p_hwfn, struct qed_iwarp_fpdu *fpdu) +{ + struct qed_ll2_tx_pkt_info tx_pkt; + u8 ll2_handle; + int rc; + + memset(&tx_pkt, 0, sizeof(tx_pkt)); + tx_pkt.num_of_bds = 1; + tx_pkt.tx_dest = QED_LL2_TX_DEST_LB; + tx_pkt.l4_hdr_offset_w = fpdu->pkt_hdr_size >> 2; + + tx_pkt.first_frag = fpdu->pkt_hdr; + tx_pkt.first_frag_len = fpdu->pkt_hdr_size; + tx_pkt.enable_ip_cksum = true; + tx_pkt.enable_l4_cksum = true; + tx_pkt.calc_ip_len = true; + /* vlan overload with enum iwarp_ll2_tx_queues */ + tx_pkt.vlan = IWARP_LL2_ALIGNED_RIGHT_TRIMMED_TX_QUEUE; + + ll2_handle = p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle; + + rc = qed_ll2_prepare_tx_packet(p_hwfn, ll2_handle, &tx_pkt, true); + if (rc) + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "Can't send right edge rc=%d\n", rc); + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "MPA_ALIGN: Sent right edge FPDU num_bds=%d [%lx, 0x%x], rc=%d\n", + tx_pkt.num_of_bds, + (unsigned long int)tx_pkt.first_frag, + tx_pkt.first_frag_len, rc); + + return rc; +} + +static int +qed_iwarp_send_fpdu(struct qed_hwfn *p_hwfn, + struct qed_iwarp_fpdu *fpdu, + struct unaligned_opaque_data *curr_pkt, + struct qed_iwarp_ll2_buff *buf, + u16 tcp_payload_size, enum qed_iwarp_mpa_pkt_type pkt_type) +{ + struct qed_ll2_tx_pkt_info tx_pkt; + u8 ll2_handle; + int rc; + + memset(&tx_pkt, 0, sizeof(tx_pkt)); + + /* An unaligned packet means it's split over two tcp segments. So the + * complete packet requires 3 bds, one for the header, one for the + * part of the fpdu of the first tcp segment, and the last fragment + * will point to the remainder of the fpdu. A packed pdu, requires only + * two bds, one for the header and one for the data. + */ + tx_pkt.num_of_bds = (pkt_type == QED_IWARP_MPA_PKT_UNALIGNED) ? 3 : 2; + tx_pkt.tx_dest = QED_LL2_TX_DEST_LB; + tx_pkt.l4_hdr_offset_w = fpdu->pkt_hdr_size >> 2; /* offset in words */ + + /* Send the mpa_buf only with the last fpdu (in case of packed) */ + if (pkt_type == QED_IWARP_MPA_PKT_UNALIGNED || + tcp_payload_size <= fpdu->fpdu_length) + tx_pkt.cookie = fpdu->mpa_buf; + + tx_pkt.first_frag = fpdu->pkt_hdr; + tx_pkt.first_frag_len = fpdu->pkt_hdr_size; + tx_pkt.enable_ip_cksum = true; + tx_pkt.enable_l4_cksum = true; + tx_pkt.calc_ip_len = true; + /* vlan overload with enum iwarp_ll2_tx_queues */ + tx_pkt.vlan = IWARP_LL2_ALIGNED_TX_QUEUE; + + /* special case of unaligned packet and not packed, need to send + * both buffers as cookie to release. + */ + if (tcp_payload_size == fpdu->incomplete_bytes) + fpdu->mpa_buf->piggy_buf = buf; + + ll2_handle = p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle; + + /* Set first fragment to header */ + rc = qed_ll2_prepare_tx_packet(p_hwfn, ll2_handle, &tx_pkt, true); + if (rc) + goto out; + + /* Set second fragment to first part of packet */ + rc = qed_ll2_set_fragment_of_tx_packet(p_hwfn, ll2_handle, + fpdu->mpa_frag, + fpdu->mpa_frag_len); + if (rc) + goto out; + + if (!fpdu->incomplete_bytes) + goto out; + + /* Set third fragment to second part of the packet */ + rc = qed_ll2_set_fragment_of_tx_packet(p_hwfn, + ll2_handle, + buf->data_phys_addr + + curr_pkt->first_mpa_offset, + fpdu->incomplete_bytes); +out: + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "MPA_ALIGN: Sent FPDU num_bds=%d first_frag_len=%x, mpa_frag_len=0x%x, incomplete_bytes:0x%x rc=%d\n", + tx_pkt.num_of_bds, + tx_pkt.first_frag_len, + fpdu->mpa_frag_len, + fpdu->incomplete_bytes, rc); + + return rc; +} + +static void +qed_iwarp_mpa_get_data(struct qed_hwfn *p_hwfn, + struct unaligned_opaque_data *curr_pkt, + u32 opaque_data0, u32 opaque_data1) +{ + u64 opaque_data; + + opaque_data = HILO_64(opaque_data1, opaque_data0); + *curr_pkt = *((struct unaligned_opaque_data *)&opaque_data); + + curr_pkt->first_mpa_offset = curr_pkt->tcp_payload_offset + + le16_to_cpu(curr_pkt->first_mpa_offset); + curr_pkt->cid = le32_to_cpu(curr_pkt->cid); +} + +/* This function is called when an unaligned or incomplete MPA packet arrives + * driver needs to align the packet, perhaps using previous data and send + * it down to FW once it is aligned. + */ +static int +qed_iwarp_process_mpa_pkt(struct qed_hwfn *p_hwfn, + struct qed_iwarp_ll2_mpa_buf *mpa_buf) +{ + struct unaligned_opaque_data *curr_pkt = &mpa_buf->data; + struct qed_iwarp_ll2_buff *buf = mpa_buf->ll2_buf; + enum qed_iwarp_mpa_pkt_type pkt_type; + struct qed_iwarp_fpdu *fpdu; + int rc = -EINVAL; + u8 *mpa_data; + + fpdu = qed_iwarp_get_curr_fpdu(p_hwfn, curr_pkt->cid & 0xffff); + if (!fpdu) { /* something corrupt with cid, post rx back */ + DP_ERR(p_hwfn, "Invalid cid, drop and post back to rx cid=%x\n", + curr_pkt->cid); + goto err; + } + + do { + mpa_data = ((u8 *)(buf->data) + curr_pkt->first_mpa_offset); + + pkt_type = qed_iwarp_mpa_classify(p_hwfn, fpdu, + mpa_buf->tcp_payload_len, + mpa_data); + + switch (pkt_type) { + case QED_IWARP_MPA_PKT_PARTIAL: + qed_iwarp_init_fpdu(buf, fpdu, + curr_pkt, + mpa_buf->tcp_payload_len, + mpa_buf->placement_offset); + + if (!QED_IWARP_IS_RIGHT_EDGE(curr_pkt)) { + mpa_buf->tcp_payload_len = 0; + break; + } + + rc = qed_iwarp_win_right_edge(p_hwfn, fpdu); + + if (rc) { + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "Can't send FPDU:reset rc=%d\n", rc); + memset(fpdu, 0, sizeof(*fpdu)); + break; + } + + mpa_buf->tcp_payload_len = 0; + break; + case QED_IWARP_MPA_PKT_PACKED: + qed_iwarp_init_fpdu(buf, fpdu, + curr_pkt, + mpa_buf->tcp_payload_len, + mpa_buf->placement_offset); + + rc = qed_iwarp_send_fpdu(p_hwfn, fpdu, curr_pkt, buf, + mpa_buf->tcp_payload_len, + pkt_type); + if (rc) { + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "Can't send FPDU:reset rc=%d\n", rc); + memset(fpdu, 0, sizeof(*fpdu)); + break; + } + + mpa_buf->tcp_payload_len -= fpdu->fpdu_length; + curr_pkt->first_mpa_offset += fpdu->fpdu_length; + break; + case QED_IWARP_MPA_PKT_UNALIGNED: + qed_iwarp_update_fpdu_length(p_hwfn, fpdu, mpa_data); + if (mpa_buf->tcp_payload_len < fpdu->incomplete_bytes) { + /* special handling of fpdu split over more + * than 2 segments + */ + if (QED_IWARP_IS_RIGHT_EDGE(curr_pkt)) { + rc = qed_iwarp_win_right_edge(p_hwfn, + fpdu); + /* packet will be re-processed later */ + if (rc) + return rc; + } + + rc = qed_iwarp_cp_pkt(p_hwfn, fpdu, curr_pkt, + buf, + mpa_buf->tcp_payload_len); + if (rc) /* packet will be re-processed later */ + return rc; + + mpa_buf->tcp_payload_len = 0; + break; + } + + rc = qed_iwarp_send_fpdu(p_hwfn, fpdu, curr_pkt, buf, + mpa_buf->tcp_payload_len, + pkt_type); + if (rc) { + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "Can't send FPDU:delay rc=%d\n", rc); + /* don't reset fpdu -> we need it for next + * classify + */ + break; + } + + mpa_buf->tcp_payload_len -= fpdu->incomplete_bytes; + curr_pkt->first_mpa_offset += fpdu->incomplete_bytes; + /* The framed PDU was sent - no more incomplete bytes */ + fpdu->incomplete_bytes = 0; + break; + } + } while (mpa_buf->tcp_payload_len && !rc); + + return rc; + +err: + qed_iwarp_ll2_post_rx(p_hwfn, + buf, + p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle); + return rc; +} + +static void qed_iwarp_process_pending_pkts(struct qed_hwfn *p_hwfn) +{ + struct qed_iwarp_info *iwarp_info = &p_hwfn->p_rdma_info->iwarp; + struct qed_iwarp_ll2_mpa_buf *mpa_buf = NULL; + int rc; + + while (!list_empty(&iwarp_info->mpa_buf_pending_list)) { + mpa_buf = list_first_entry(&iwarp_info->mpa_buf_pending_list, + struct qed_iwarp_ll2_mpa_buf, + list_entry); + + rc = qed_iwarp_process_mpa_pkt(p_hwfn, mpa_buf); + + /* busy means break and continue processing later, don't + * remove the buf from the pending list. + */ + if (rc == -EBUSY) + break; + + list_del(&mpa_buf->list_entry); + list_add_tail(&mpa_buf->list_entry, &iwarp_info->mpa_buf_list); + + if (rc) { /* different error, don't continue */ + DP_NOTICE(p_hwfn, "process pkts failed rc=%d\n", rc); + break; + } + } +} + +static void +qed_iwarp_ll2_comp_mpa_pkt(void *cxt, struct qed_ll2_comp_rx_data *data) +{ + struct qed_iwarp_ll2_mpa_buf *mpa_buf; + struct qed_iwarp_info *iwarp_info; + struct qed_hwfn *p_hwfn = cxt; + + iwarp_info = &p_hwfn->p_rdma_info->iwarp; + mpa_buf = list_first_entry(&iwarp_info->mpa_buf_list, + struct qed_iwarp_ll2_mpa_buf, list_entry); + if (!mpa_buf) { + DP_ERR(p_hwfn, "No free mpa buf\n"); + goto err; + } + + list_del(&mpa_buf->list_entry); + qed_iwarp_mpa_get_data(p_hwfn, &mpa_buf->data, + data->opaque_data_0, data->opaque_data_1); + + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "LL2 MPA CompRx payload_len:0x%x\tfirst_mpa_offset:0x%x\ttcp_payload_offset:0x%x\tflags:0x%x\tcid:0x%x\n", + data->length.packet_length, mpa_buf->data.first_mpa_offset, + mpa_buf->data.tcp_payload_offset, mpa_buf->data.flags, + mpa_buf->data.cid); + + mpa_buf->ll2_buf = data->cookie; + mpa_buf->tcp_payload_len = data->length.packet_length - + mpa_buf->data.first_mpa_offset; + mpa_buf->data.first_mpa_offset += data->u.placement_offset; + mpa_buf->placement_offset = data->u.placement_offset; + + list_add_tail(&mpa_buf->list_entry, &iwarp_info->mpa_buf_pending_list); + + qed_iwarp_process_pending_pkts(p_hwfn); + return; +err: + qed_iwarp_ll2_post_rx(p_hwfn, data->cookie, + iwarp_info->ll2_mpa_handle); +} + static void qed_iwarp_ll2_comp_syn_pkt(void *cxt, struct qed_ll2_comp_rx_data *data) { @@ -1855,10 +2428,25 @@ static void qed_iwarp_ll2_comp_tx_pkt(void *cxt, u8 connection_handle, bool b_last_fragment, bool b_last_packet) { struct qed_iwarp_ll2_buff *buffer = cookie; + struct qed_iwarp_ll2_buff *piggy; struct qed_hwfn *p_hwfn = cxt; + if (!buffer) /* can happen in packed mpa unaligned... */ + return; + /* this was originally an rx packet, post it back */ + piggy = buffer->piggy_buf; + if (piggy) { + buffer->piggy_buf = NULL; + qed_iwarp_ll2_post_rx(p_hwfn, piggy, connection_handle); + } + qed_iwarp_ll2_post_rx(p_hwfn, buffer, connection_handle); + + if (connection_handle == p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle) + qed_iwarp_process_pending_pkts(p_hwfn); + + return; } static void qed_iwarp_ll2_rel_tx_pkt(void *cxt, u8 connection_handle, @@ -1871,12 +2459,44 @@ static void qed_iwarp_ll2_rel_tx_pkt(void *cxt, u8 connection_handle, if (!buffer) return; + if (buffer->piggy_buf) { + dma_free_coherent(&p_hwfn->cdev->pdev->dev, + buffer->piggy_buf->buff_size, + buffer->piggy_buf->data, + buffer->piggy_buf->data_phys_addr); + + kfree(buffer->piggy_buf); + } + dma_free_coherent(&p_hwfn->cdev->pdev->dev, buffer->buff_size, buffer->data, buffer->data_phys_addr); kfree(buffer); } +/* The only slowpath for iwarp ll2 is unalign flush. When this completion + * is received, need to reset the FPDU. + */ +void +qed_iwarp_ll2_slowpath(void *cxt, + u8 connection_handle, + u32 opaque_data_0, u32 opaque_data_1) +{ + struct unaligned_opaque_data unalign_data; + struct qed_hwfn *p_hwfn = cxt; + struct qed_iwarp_fpdu *fpdu; + + qed_iwarp_mpa_get_data(p_hwfn, &unalign_data, + opaque_data_0, opaque_data_1); + + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "(0x%x) Flush fpdu\n", + unalign_data.cid); + + fpdu = qed_iwarp_get_curr_fpdu(p_hwfn, (u16)unalign_data.cid); + if (fpdu) + memset(fpdu, 0, sizeof(*fpdu)); +} + static int qed_iwarp_ll2_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { struct qed_iwarp_info *iwarp_info = &p_hwfn->p_rdma_info->iwarp; @@ -1902,6 +2522,16 @@ static int qed_iwarp_ll2_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) iwarp_info->ll2_ooo_handle = QED_IWARP_HANDLE_INVAL; } + if (iwarp_info->ll2_mpa_handle != QED_IWARP_HANDLE_INVAL) { + rc = qed_ll2_terminate_connection(p_hwfn, + iwarp_info->ll2_mpa_handle); + if (rc) + DP_INFO(p_hwfn, "Failed to terminate mpa connection\n"); + + qed_ll2_release_connection(p_hwfn, iwarp_info->ll2_mpa_handle); + iwarp_info->ll2_mpa_handle = QED_IWARP_HANDLE_INVAL; + } + qed_llh_remove_mac_filter(p_hwfn, p_ptt, p_hwfn->p_rdma_info->iwarp.mac_addr); return rc; @@ -1953,12 +2583,15 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, struct qed_iwarp_info *iwarp_info; struct qed_ll2_acquire_data data; struct qed_ll2_cbs cbs; + u32 mpa_buff_size; u16 n_ooo_bufs; int rc = 0; + int i; iwarp_info = &p_hwfn->p_rdma_info->iwarp; iwarp_info->ll2_syn_handle = QED_IWARP_HANDLE_INVAL; iwarp_info->ll2_ooo_handle = QED_IWARP_HANDLE_INVAL; + iwarp_info->ll2_mpa_handle = QED_IWARP_HANDLE_INVAL; iwarp_info->max_mtu = params->max_mtu; @@ -2029,6 +2662,68 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, if (rc) goto err; + /* Start Unaligned MPA connection */ + cbs.rx_comp_cb = qed_iwarp_ll2_comp_mpa_pkt; + cbs.slowpath_cb = qed_iwarp_ll2_slowpath; + + memset(&data, 0, sizeof(data)); + data.input.conn_type = QED_LL2_TYPE_IWARP; + data.input.mtu = params->max_mtu; + /* FW requires that once a packet arrives OOO, it must have at + * least 2 rx buffers available on the unaligned connection + * for handling the case that it is a partial fpdu. + */ + data.input.rx_num_desc = n_ooo_bufs * 2; + data.input.tx_num_desc = data.input.rx_num_desc; + data.input.tx_max_bds_per_packet = QED_IWARP_MAX_BDS_PER_FPDU; + data.p_connection_handle = &iwarp_info->ll2_mpa_handle; + data.input.secondary_queue = true; + data.cbs = &cbs; + + rc = qed_ll2_acquire_connection(p_hwfn, &data); + if (rc) + goto err; + + rc = qed_ll2_establish_connection(p_hwfn, iwarp_info->ll2_mpa_handle); + if (rc) + goto err; + + mpa_buff_size = QED_IWARP_MAX_BUF_SIZE(params->max_mtu); + rc = qed_iwarp_ll2_alloc_buffers(p_hwfn, + data.input.rx_num_desc, + mpa_buff_size, + iwarp_info->ll2_mpa_handle); + if (rc) + goto err; + + iwarp_info->partial_fpdus = kcalloc((u16)p_hwfn->p_rdma_info->num_qps, + sizeof(*iwarp_info->partial_fpdus), + GFP_KERNEL); + if (!iwarp_info->partial_fpdus) + goto err; + + iwarp_info->max_num_partial_fpdus = (u16)p_hwfn->p_rdma_info->num_qps; + + iwarp_info->mpa_intermediate_buf = kzalloc(mpa_buff_size, GFP_KERNEL); + if (!iwarp_info->mpa_intermediate_buf) + goto err; + + /* The mpa_bufs array serves for pending RX packets received on the + * mpa ll2 that don't have place on the tx ring and require later + * processing. We can't fail on allocation of such a struct therefore + * we allocate enough to take care of all rx packets + */ + iwarp_info->mpa_bufs = kcalloc(data.input.rx_num_desc, + sizeof(*iwarp_info->mpa_bufs), + GFP_KERNEL); + if (!iwarp_info->mpa_bufs) + goto err; + + INIT_LIST_HEAD(&iwarp_info->mpa_buf_pending_list); + INIT_LIST_HEAD(&iwarp_info->mpa_buf_list); + for (i = 0; i < data.input.rx_num_desc; i++) + list_add_tail(&iwarp_info->mpa_bufs[i].list_entry, + &iwarp_info->mpa_buf_list); return rc; err: qed_iwarp_ll2_stop(p_hwfn, p_ptt); diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h index 9e2bfde894df..c1ecd743305f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h @@ -55,15 +55,43 @@ enum qed_iwarp_qp_state qed_roce2iwarp_state(enum qed_roce_qp_state state); #define QED_IWARP_HANDLE_INVAL (0xff) struct qed_iwarp_ll2_buff { + struct qed_iwarp_ll2_buff *piggy_buf; void *data; dma_addr_t data_phys_addr; u32 buff_size; }; +struct qed_iwarp_ll2_mpa_buf { + struct list_head list_entry; + struct qed_iwarp_ll2_buff *ll2_buf; + struct unaligned_opaque_data data; + u16 tcp_payload_len; + u8 placement_offset; +}; + +/* In some cases a fpdu will arrive with only one byte of the header, in this + * case the fpdu_length will be partial (contain only higher byte and + * incomplete bytes will contain the invalid value + */ +#define QED_IWARP_INVALID_INCOMPLETE_BYTES 0xffff + +struct qed_iwarp_fpdu { + struct qed_iwarp_ll2_buff *mpa_buf; + void *mpa_frag_virt; + dma_addr_t mpa_frag; + dma_addr_t pkt_hdr; + u16 mpa_frag_len; + u16 fpdu_length; + u16 incomplete_bytes; + u8 pkt_hdr_size; +}; + struct qed_iwarp_info { struct list_head listen_list; /* qed_iwarp_listener */ struct list_head ep_list; /* qed_iwarp_ep */ struct list_head ep_free_list; /* pre-allocated ep's */ + struct list_head mpa_buf_list; /* list of mpa_bufs */ + struct list_head mpa_buf_pending_list; spinlock_t iw_lock; /* for iwarp resources */ spinlock_t qp_lock; /* for teardown races */ u32 rcv_wnd_scale; @@ -73,9 +101,14 @@ struct qed_iwarp_info { u8 tcp_flags; u8 ll2_syn_handle; u8 ll2_ooo_handle; + u8 ll2_mpa_handle; u8 peer2peer; enum mpa_negotiation_mode mpa_rev; enum mpa_rtr_type rtr_type; + struct qed_iwarp_fpdu *partial_fpdus; + struct qed_iwarp_ll2_mpa_buf *mpa_bufs; + u8 *mpa_intermediate_buf; + u16 max_num_partial_fpdus; }; enum qed_iwarp_ep_state { diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 250afa5486cf..047f556ca62e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -423,6 +423,41 @@ static void qed_ll2_rxq_parse_reg(struct qed_hwfn *p_hwfn, } static int +qed_ll2_handle_slowpath(struct qed_hwfn *p_hwfn, + struct qed_ll2_info *p_ll2_conn, + union core_rx_cqe_union *p_cqe, + unsigned long *p_lock_flags) +{ + struct qed_ll2_rx_queue *p_rx = &p_ll2_conn->rx_queue; + struct core_rx_slow_path_cqe *sp_cqe; + + sp_cqe = &p_cqe->rx_cqe_sp; + if (sp_cqe->ramrod_cmd_id != CORE_RAMROD_RX_QUEUE_FLUSH) { + DP_NOTICE(p_hwfn, + "LL2 - unexpected Rx CQE slowpath ramrod_cmd_id:%d\n", + sp_cqe->ramrod_cmd_id); + return -EINVAL; + } + + if (!p_ll2_conn->cbs.slowpath_cb) { + DP_NOTICE(p_hwfn, + "LL2 - received RX_QUEUE_FLUSH but no callback was provided\n"); + return -EINVAL; + } + + spin_unlock_irqrestore(&p_rx->lock, *p_lock_flags); + + p_ll2_conn->cbs.slowpath_cb(p_ll2_conn->cbs.cookie, + p_ll2_conn->my_id, + le32_to_cpu(sp_cqe->opaque_data.data[0]), + le32_to_cpu(sp_cqe->opaque_data.data[1])); + + spin_lock_irqsave(&p_rx->lock, *p_lock_flags); + + return 0; +} + +static int qed_ll2_rxq_handle_completion(struct qed_hwfn *p_hwfn, struct qed_ll2_info *p_ll2_conn, union core_rx_cqe_union *p_cqe, @@ -495,8 +530,8 @@ static int qed_ll2_rxq_completion(struct qed_hwfn *p_hwfn, void *cookie) switch (cqe->rx_cqe_sp.type) { case CORE_RX_CQE_TYPE_SLOW_PATH: - DP_NOTICE(p_hwfn, "LL2 - unexpected Rx CQE slowpath\n"); - rc = -EINVAL; + rc = qed_ll2_handle_slowpath(p_hwfn, p_ll2_conn, + cqe, &flags); break; case CORE_RX_CQE_TYPE_GSI_OFFLOAD: case CORE_RX_CQE_TYPE_REGULAR: @@ -894,7 +929,7 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn, p_ramrod->drop_ttl0_flg = p_ll2_conn->input.rx_drop_ttl0_flg; p_ramrod->inner_vlan_removal_en = p_ll2_conn->input.rx_vlan_removal_en; p_ramrod->queue_id = p_ll2_conn->queue_id; - p_ramrod->main_func_queue = (conn_type == QED_LL2_TYPE_OOO) ? 0 : 1; + p_ramrod->main_func_queue = p_ll2_conn->main_func_queue ? 1 : 0; if ((IS_MF_DEFAULT(p_hwfn) || IS_MF_SI(p_hwfn)) && p_ramrod->main_func_queue && (conn_type != QED_LL2_TYPE_ROCE) && @@ -1105,6 +1140,7 @@ static int qed_ll2_acquire_connection_tx(struct qed_hwfn *p_hwfn, struct qed_ll2_info *p_ll2_info) { struct qed_ll2_tx_packet *p_descq; + u32 desc_size; u32 capacity; int rc = 0; @@ -1122,13 +1158,17 @@ static int qed_ll2_acquire_connection_tx(struct qed_hwfn *p_hwfn, goto out; capacity = qed_chain_get_capacity(&p_ll2_info->tx_queue.txq_chain); - p_descq = kcalloc(capacity, sizeof(struct qed_ll2_tx_packet), - GFP_KERNEL); + /* First element is part of the packet, rest are flexibly added */ + desc_size = (sizeof(*p_descq) + + (p_ll2_info->input.tx_max_bds_per_packet - 1) * + sizeof(p_descq->bds_set)); + + p_descq = kcalloc(capacity, desc_size, GFP_KERNEL); if (!p_descq) { rc = -ENOMEM; goto out; } - p_ll2_info->tx_queue.descq_array = p_descq; + p_ll2_info->tx_queue.descq_mem = p_descq; DP_VERBOSE(p_hwfn, QED_MSG_LL2, "Allocated LL2 Txq [Type %08x] with 0x%08x buffers\n", @@ -1209,6 +1249,7 @@ qed_ll2_set_cbs(struct qed_ll2_info *p_ll2_info, const struct qed_ll2_cbs *cbs) p_ll2_info->cbs.rx_release_cb = cbs->rx_release_cb; p_ll2_info->cbs.tx_comp_cb = cbs->tx_comp_cb; p_ll2_info->cbs.tx_release_cb = cbs->tx_release_cb; + p_ll2_info->cbs.slowpath_cb = cbs->slowpath_cb; p_ll2_info->cbs.cookie = cbs->cookie; return 0; @@ -1260,6 +1301,11 @@ int qed_ll2_acquire_connection(void *cxt, struct qed_ll2_acquire_data *data) p_ll2_info->tx_dest = (data->input.tx_dest == QED_LL2_TX_DEST_NW) ? CORE_TX_DEST_NW : CORE_TX_DEST_LB; + if (data->input.conn_type == QED_LL2_TYPE_OOO || + data->input.secondary_queue) + p_ll2_info->main_func_queue = false; + else + p_ll2_info->main_func_queue = true; /* Correct maximum number of Tx BDs */ p_tx_max = &p_ll2_info->input.tx_max_bds_per_packet; @@ -1359,11 +1405,13 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle) { struct qed_hwfn *p_hwfn = cxt; struct qed_ll2_info *p_ll2_conn; + struct qed_ll2_tx_packet *p_pkt; struct qed_ll2_rx_queue *p_rx; struct qed_ll2_tx_queue *p_tx; struct qed_ptt *p_ptt; int rc = -EINVAL; u32 i, capacity; + u32 desc_size; u8 qid; p_ptt = qed_ptt_acquire(p_hwfn); @@ -1397,9 +1445,15 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle) INIT_LIST_HEAD(&p_tx->sending_descq); spin_lock_init(&p_tx->lock); capacity = qed_chain_get_capacity(&p_tx->txq_chain); - for (i = 0; i < capacity; i++) - list_add_tail(&p_tx->descq_array[i].list_entry, - &p_tx->free_descq); + /* First element is part of the packet, rest are flexibly added */ + desc_size = (sizeof(*p_pkt) + + (p_ll2_conn->input.tx_max_bds_per_packet - 1) * + sizeof(p_pkt->bds_set)); + + for (i = 0; i < capacity; i++) { + p_pkt = p_tx->descq_mem + desc_size * i; + list_add_tail(&p_pkt->list_entry, &p_tx->free_descq); + } p_tx->cur_completing_bd_idx = 0; p_tx->bds_idx = 0; p_tx->b_completing_packet = false; @@ -1579,11 +1633,28 @@ qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, roce_flavor = (pkt->qed_roce_flavor == QED_LL2_ROCE) ? CORE_ROCE : CORE_RROCE; - tx_dest = (pkt->tx_dest == QED_LL2_TX_DEST_NW) ? CORE_TX_DEST_NW - : CORE_TX_DEST_LB; + switch (pkt->tx_dest) { + case QED_LL2_TX_DEST_NW: + tx_dest = CORE_TX_DEST_NW; + break; + case QED_LL2_TX_DEST_LB: + tx_dest = CORE_TX_DEST_LB; + break; + case QED_LL2_TX_DEST_DROP: + tx_dest = CORE_TX_DEST_DROP; + break; + default: + tx_dest = CORE_TX_DEST_LB; + break; + } start_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain); - start_bd->nw_vlan_or_lb_echo = cpu_to_le16(pkt->vlan); + if (QED_IS_IWARP_PERSONALITY(p_hwfn) && + p_ll2->input.conn_type == QED_LL2_TYPE_OOO) + start_bd->nw_vlan_or_lb_echo = + cpu_to_le16(IWARP_LL2_IN_ORDER_TX_QUEUE); + else + start_bd->nw_vlan_or_lb_echo = cpu_to_le16(pkt->vlan); SET_FIELD(start_bd->bitfield1, CORE_TX_BD_L4_HDR_OFFSET_W, cpu_to_le16(pkt->l4_hdr_offset_w)); SET_FIELD(start_bd->bitfield1, CORE_TX_BD_TX_DST, tx_dest); @@ -1591,6 +1662,9 @@ qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, SET_FIELD(bd_data, CORE_TX_BD_DATA_START_BD, 0x1); SET_FIELD(bd_data, CORE_TX_BD_DATA_NBDS, pkt->num_of_bds); SET_FIELD(bd_data, CORE_TX_BD_DATA_ROCE_FLAV, roce_flavor); + SET_FIELD(bd_data, CORE_TX_BD_DATA_IP_CSUM, !!(pkt->enable_ip_cksum)); + SET_FIELD(bd_data, CORE_TX_BD_DATA_L4_CSUM, !!(pkt->enable_l4_cksum)); + SET_FIELD(bd_data, CORE_TX_BD_DATA_IP_LEN, !!(pkt->calc_ip_len)); start_bd->bd_data.as_bitfield = cpu_to_le16(bd_data); DMA_REGPAIR_LE(start_bd->addr, pkt->first_frag); start_bd->nbytes = cpu_to_le16(pkt->first_frag_len); @@ -1698,7 +1772,7 @@ int qed_ll2_prepare_tx_packet(void *cxt, p_tx = &p_ll2_conn->tx_queue; p_tx_chain = &p_tx->txq_chain; - if (pkt->num_of_bds > CORE_LL2_TX_MAX_BDS_PER_PACKET) + if (pkt->num_of_bds > p_ll2_conn->input.tx_max_bds_per_packet) return -EIO; spin_lock_irqsave(&p_tx->lock, flags); @@ -1858,7 +1932,7 @@ void qed_ll2_release_connection(void *cxt, u8 connection_handle) qed_int_unregister_cb(p_hwfn, p_ll2_conn->tx_queue.tx_sb_index); } - kfree(p_ll2_conn->tx_queue.descq_array); + kfree(p_ll2_conn->tx_queue.descq_mem); qed_chain_free(p_hwfn->cdev, &p_ll2_conn->tx_queue.txq_chain); kfree(p_ll2_conn->rx_queue.descq_array); diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h index a822528e9c63..f65817012e97 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h @@ -63,17 +63,14 @@ struct qed_ll2_rx_packet { struct qed_ll2_tx_packet { struct list_head list_entry; u16 bd_used; - u16 vlan; - u16 l4_hdr_offset_w; - u8 bd_flags; bool notify_fw; void *cookie; - + /* Flexible Array of bds_set determined by max_bds_per_packet */ struct { struct core_tx_bd *txq_bd; dma_addr_t tx_frag; u16 frag_len; - } bds_set[ETH_TX_MAX_BDS_PER_NON_LSO_PACKET]; + } bds_set[1]; }; struct qed_ll2_rx_queue { @@ -101,7 +98,7 @@ struct qed_ll2_tx_queue { struct list_head active_descq; struct list_head free_descq; struct list_head sending_descq; - struct qed_ll2_tx_packet *descq_array; + void *descq_mem; /* memory for variable sized qed_ll2_tx_packet*/ struct qed_ll2_tx_packet *cur_send_packet; struct qed_ll2_tx_packet cur_completing_packet; u16 cur_completing_bd_idx; @@ -124,6 +121,7 @@ struct qed_ll2_info { bool b_active; enum core_tx_dest tx_dest; u8 tx_stats_en; + bool main_func_queue; struct qed_ll2_rx_queue rx_queue; struct qed_ll2_tx_queue tx_queue; struct qed_ll2_cbs cbs; diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c index 000636530111..6172354b451c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c @@ -103,18 +103,28 @@ int qed_ooo_alloc(struct qed_hwfn *p_hwfn) { u16 max_num_archipelagos = 0, cid_base; struct qed_ooo_info *p_ooo_info; + enum protocol_type proto; u16 max_num_isles = 0; u32 i; - if (p_hwfn->hw_info.personality != QED_PCI_ISCSI) { + switch (p_hwfn->hw_info.personality) { + case QED_PCI_ISCSI: + proto = PROTOCOLID_ISCSI; + break; + case QED_PCI_ETH_RDMA: + case QED_PCI_ETH_IWARP: + proto = PROTOCOLID_IWARP; + break; + default: DP_NOTICE(p_hwfn, "Failed to allocate qed_ooo_info: unknown personality\n"); return -EINVAL; } - max_num_archipelagos = p_hwfn->pf_params.iscsi_pf_params.num_cons; + max_num_archipelagos = (u16)qed_cxt_get_proto_cid_count(p_hwfn, proto, + NULL); max_num_isles = QED_MAX_NUM_ISLES + max_num_archipelagos; - cid_base = (u16)qed_cxt_get_proto_cid_start(p_hwfn, PROTOCOLID_ISCSI); + cid_base = (u16)qed_cxt_get_proto_cid_start(p_hwfn, proto); if (!max_num_archipelagos) { DP_NOTICE(p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.h b/drivers/net/ethernet/qlogic/qed/qed_ooo.h index e8ed40b848f5..49c4e75b15b1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ooo.h +++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.h @@ -83,7 +83,7 @@ struct qed_ooo_info { u16 cid_base; }; -#if IS_ENABLED(CONFIG_QED_ISCSI) +#if IS_ENABLED(CONFIG_QED_OOO) void qed_ooo_save_history_entry(struct qed_hwfn *p_hwfn, struct qed_ooo_info *p_ooo_info, struct ooo_opaque *p_cqe); diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 3ed9033e56db..9cbb27263742 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -309,22 +309,12 @@ void emac_mac_mode_config(struct emac_adapter *adpt) /* Config descriptor rings */ static void emac_mac_dma_rings_config(struct emac_adapter *adpt) { - static const unsigned short tpd_q_offset[] = { - EMAC_DESC_CTRL_8, EMAC_H1TPD_BASE_ADDR_LO, - EMAC_H2TPD_BASE_ADDR_LO, EMAC_H3TPD_BASE_ADDR_LO}; - static const unsigned short rfd_q_offset[] = { - EMAC_DESC_CTRL_2, EMAC_DESC_CTRL_10, - EMAC_DESC_CTRL_12, EMAC_DESC_CTRL_13}; - static const unsigned short rrd_q_offset[] = { - EMAC_DESC_CTRL_5, EMAC_DESC_CTRL_14, - EMAC_DESC_CTRL_15, EMAC_DESC_CTRL_16}; - /* TPD (Transmit Packet Descriptor) */ writel(upper_32_bits(adpt->tx_q.tpd.dma_addr), adpt->base + EMAC_DESC_CTRL_1); writel(lower_32_bits(adpt->tx_q.tpd.dma_addr), - adpt->base + tpd_q_offset[0]); + adpt->base + EMAC_DESC_CTRL_8); writel(adpt->tx_q.tpd.count & TPD_RING_SIZE_BMSK, adpt->base + EMAC_DESC_CTRL_9); @@ -334,9 +324,9 @@ static void emac_mac_dma_rings_config(struct emac_adapter *adpt) adpt->base + EMAC_DESC_CTRL_0); writel(lower_32_bits(adpt->rx_q.rfd.dma_addr), - adpt->base + rfd_q_offset[0]); + adpt->base + EMAC_DESC_CTRL_2); writel(lower_32_bits(adpt->rx_q.rrd.dma_addr), - adpt->base + rrd_q_offset[0]); + adpt->base + EMAC_DESC_CTRL_5); writel(adpt->rx_q.rfd.count & RFD_RING_SIZE_BMSK, adpt->base + EMAC_DESC_CTRL_3); diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c index 29ba37a08372..e8ab512ee7e3 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c @@ -68,10 +68,10 @@ static void emac_sgmii_link_init(struct emac_adapter *adpt) writel(val, phy->base + EMAC_SGMII_PHY_AUTONEG_CFG2); } -static int emac_sgmii_irq_clear(struct emac_adapter *adpt, u32 irq_bits) +static int emac_sgmii_irq_clear(struct emac_adapter *adpt, u8 irq_bits) { struct emac_sgmii *phy = &adpt->phy; - u32 status; + u8 status; writel_relaxed(irq_bits, phy->base + EMAC_SGMII_PHY_INTERRUPT_CLEAR); writel_relaxed(IRQ_GLOBAL_CLEAR, phy->base + EMAC_SGMII_PHY_IRQ_CMD); @@ -86,9 +86,8 @@ static int emac_sgmii_irq_clear(struct emac_adapter *adpt, u32 irq_bits) EMAC_SGMII_PHY_INTERRUPT_STATUS, status, !(status & irq_bits), 1, SGMII_PHY_IRQ_CLR_WAIT_TIME)) { - netdev_err(adpt->netdev, - "error: failed clear SGMII irq: status:0x%x bits:0x%x\n", - status, irq_bits); + net_err_ratelimited("%s: failed to clear SGMII irq: status:0x%x bits:0x%x\n", + adpt->netdev->name, status, irq_bits); return -EIO; } @@ -109,7 +108,7 @@ static irqreturn_t emac_sgmii_interrupt(int irq, void *data) { struct emac_adapter *adpt = data; struct emac_sgmii *phy = &adpt->phy; - u32 status; + u8 status; status = readl(phy->base + EMAC_SGMII_PHY_INTERRUPT_STATUS); status &= SGMII_ISR_MASK; @@ -139,10 +138,8 @@ static irqreturn_t emac_sgmii_interrupt(int irq, void *data) atomic_set(&phy->decode_error_count, 0); } - if (emac_sgmii_irq_clear(adpt, status)) { - netdev_warn(adpt->netdev, "failed to clear SGMII interrupt\n"); + if (emac_sgmii_irq_clear(adpt, status)) schedule_work(&adpt->work_thread); - } return IRQ_HANDLED; } diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index f477ba29c569..70c92b649b29 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -148,9 +148,8 @@ static irqreturn_t emac_isr(int _irq, void *data) goto exit; if (status & ISR_ERROR) { - netif_warn(adpt, intr, adpt->netdev, - "warning: error irq status 0x%lx\n", - status & ISR_ERROR); + net_err_ratelimited("%s: error interrupt 0x%lx\n", + adpt->netdev->name, status & ISR_ERROR); /* reset MAC */ schedule_work(&adpt->work_thread); } @@ -169,7 +168,8 @@ static irqreturn_t emac_isr(int _irq, void *data) emac_mac_tx_process(adpt, &adpt->tx_q); if (status & ISR_OVER) - net_warn_ratelimited("warning: TX/RX overflow\n"); + net_warn_ratelimited("%s: TX/RX overflow interrupt\n", + adpt->netdev->name); exit: /* enable the interrupt */ @@ -615,20 +615,11 @@ static int emac_probe(struct platform_device *pdev) u32 reg; int ret; - /* The EMAC itself is capable of 64-bit DMA, so try that first. */ - ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + /* The TPD buffer address is limited to 45 bits. */ + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(45)); if (ret) { - /* Some platforms may restrict the EMAC's address bus to less - * then the size of DDR. In this case, we need to try a - * smaller mask. We could try every possible smaller mask, - * but that's overkill. Instead, just fall to 32-bit, which - * should always work. - */ - ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (ret) { - dev_err(&pdev->dev, "could not set DMA mask\n"); - return ret; - } + dev_err(&pdev->dev, "could not set DMA mask\n"); + return ret; } netdev = alloc_etherdev(sizeof(struct emac_adapter)); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 8403eea08d0e..71bee1af71ef 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -61,23 +61,6 @@ rmnet_get_port_rtnl(const struct net_device *real_dev) return rtnl_dereference(real_dev->rx_handler_data); } -static struct rmnet_endpoint* -rmnet_get_endpoint(struct net_device *dev, int config_id) -{ - struct rmnet_endpoint *ep; - struct rmnet_port *port; - - if (!rmnet_is_real_dev_registered(dev)) { - ep = rmnet_vnd_get_endpoint(dev); - } else { - port = rmnet_get_port_rtnl(dev); - - ep = &port->muxed_ep[config_id]; - } - - return ep; -} - static int rmnet_unregister_real_device(struct net_device *real_dev, struct rmnet_port *port) { @@ -98,7 +81,7 @@ static int rmnet_unregister_real_device(struct net_device *real_dev, static int rmnet_register_real_device(struct net_device *real_dev) { struct rmnet_port *port; - int rc; + int rc, entry; ASSERT_RTNL(); @@ -119,27 +102,41 @@ static int rmnet_register_real_device(struct net_device *real_dev) /* hold on to real dev for MAP data */ dev_hold(real_dev); + for (entry = 0; entry < RMNET_MAX_LOGICAL_EP; entry++) + INIT_HLIST_HEAD(&port->muxed_ep[entry]); + netdev_dbg(real_dev, "registered with rmnet\n"); return 0; } -static void rmnet_set_endpoint_config(struct net_device *dev, - u8 mux_id, u8 rmnet_mode, - struct net_device *egress_dev) +static void rmnet_unregister_bridge(struct net_device *dev, + struct rmnet_port *port) { - struct rmnet_endpoint *ep; + struct net_device *rmnet_dev, *bridge_dev; + struct rmnet_port *bridge_port; + + if (port->rmnet_mode != RMNET_EPMODE_BRIDGE) + return; - netdev_dbg(dev, "id %d mode %d dev %s\n", - mux_id, rmnet_mode, egress_dev->name); + /* bridge slave handling */ + if (!port->nr_rmnet_devs) { + rmnet_dev = netdev_master_upper_dev_get_rcu(dev); + netdev_upper_dev_unlink(dev, rmnet_dev); - ep = rmnet_get_endpoint(dev, mux_id); - /* This config is cleared on every set, so its ok to not - * clear it on a device delete. - */ - memset(ep, 0, sizeof(struct rmnet_endpoint)); - ep->rmnet_mode = rmnet_mode; - ep->egress_dev = egress_dev; - ep->mux_id = mux_id; + bridge_dev = port->bridge_ep; + + bridge_port = rmnet_get_port_rtnl(bridge_dev); + bridge_port->bridge_ep = NULL; + bridge_port->rmnet_mode = RMNET_EPMODE_VND; + } else { + bridge_dev = port->bridge_ep; + + bridge_port = rmnet_get_port_rtnl(bridge_dev); + rmnet_dev = netdev_master_upper_dev_get_rcu(bridge_dev); + netdev_upper_dev_unlink(bridge_dev, rmnet_dev); + + rmnet_unregister_real_device(bridge_dev, bridge_port); + } } static int rmnet_newlink(struct net *src_net, struct net_device *dev, @@ -153,6 +150,7 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, RMNET_EGRESS_FORMAT_MAP; struct net_device *real_dev; int mode = RMNET_EPMODE_VND; + struct rmnet_endpoint *ep; struct rmnet_port *port; int err = 0; u16 mux_id; @@ -164,6 +162,10 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, if (!data[IFLA_VLAN_ID]) return -EINVAL; + ep = kzalloc(sizeof(*ep), GFP_ATOMIC); + if (!ep) + return -ENOMEM; + mux_id = nla_get_u16(data[IFLA_VLAN_ID]); err = rmnet_register_real_device(real_dev); @@ -171,7 +173,7 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, goto err0; port = rmnet_get_port_rtnl(real_dev); - err = rmnet_vnd_newlink(mux_id, dev, port, real_dev); + err = rmnet_vnd_newlink(mux_id, dev, port, real_dev, ep); if (err) goto err1; @@ -183,13 +185,13 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, ingress_format, egress_format); port->egress_data_format = egress_format; port->ingress_data_format = ingress_format; + port->rmnet_mode = mode; - rmnet_set_endpoint_config(real_dev, mux_id, mode, dev); - rmnet_set_endpoint_config(dev, mux_id, mode, real_dev); + hlist_add_head_rcu(&ep->hlnode, &port->muxed_ep[mux_id]); return 0; err2: - rmnet_vnd_dellink(mux_id, port); + rmnet_vnd_dellink(mux_id, port, ep); err1: rmnet_unregister_real_device(real_dev, port); err0: @@ -199,6 +201,7 @@ err0: static void rmnet_dellink(struct net_device *dev, struct list_head *head) { struct net_device *real_dev; + struct rmnet_endpoint *ep; struct rmnet_port *port; u8 mux_id; @@ -212,8 +215,15 @@ static void rmnet_dellink(struct net_device *dev, struct list_head *head) port = rmnet_get_port_rtnl(real_dev); mux_id = rmnet_vnd_get_mux(dev); - rmnet_vnd_dellink(mux_id, port); netdev_upper_dev_unlink(dev, real_dev); + + ep = rmnet_get_endpoint(port, mux_id); + if (ep) { + hlist_del_init_rcu(&ep->hlnode); + rmnet_unregister_bridge(dev, port); + rmnet_vnd_dellink(mux_id, port, ep); + kfree(ep); + } rmnet_unregister_real_device(real_dev, port); unregister_netdevice_queue(dev, head); @@ -222,11 +232,16 @@ static void rmnet_dellink(struct net_device *dev, struct list_head *head) static int rmnet_dev_walk_unreg(struct net_device *rmnet_dev, void *data) { struct rmnet_walk_data *d = data; + struct rmnet_endpoint *ep; u8 mux_id; mux_id = rmnet_vnd_get_mux(rmnet_dev); - - rmnet_vnd_dellink(mux_id, d->port); + ep = rmnet_get_endpoint(d->port, mux_id); + if (ep) { + hlist_del_init_rcu(&ep->hlnode); + rmnet_vnd_dellink(mux_id, d->port, ep); + kfree(ep); + } netdev_upper_dev_unlink(rmnet_dev, d->real_dev); unregister_netdevice_queue(rmnet_dev, d->head); @@ -252,6 +267,8 @@ static void rmnet_force_unassociate_device(struct net_device *dev) d.port = port; rcu_read_lock(); + rmnet_unregister_bridge(dev, port); + netdev_walk_all_lower_dev_rcu(real_dev, rmnet_dev_walk_unreg, &d); rcu_read_unlock(); unregister_netdevice_many(&list); @@ -324,6 +341,77 @@ struct rmnet_port *rmnet_get_port(struct net_device *real_dev) return NULL; } +struct rmnet_endpoint *rmnet_get_endpoint(struct rmnet_port *port, u8 mux_id) +{ + struct rmnet_endpoint *ep; + + hlist_for_each_entry_rcu(ep, &port->muxed_ep[mux_id], hlnode) { + if (ep->mux_id == mux_id) + return ep; + } + + return NULL; +} + +int rmnet_add_bridge(struct net_device *rmnet_dev, + struct net_device *slave_dev, + struct netlink_ext_ack *extack) +{ + struct rmnet_priv *priv = netdev_priv(rmnet_dev); + struct net_device *real_dev = priv->real_dev; + struct rmnet_port *port, *slave_port; + int err; + + port = rmnet_get_port(real_dev); + + /* If there is more than one rmnet dev attached, its probably being + * used for muxing. Skip the briding in that case + */ + if (port->nr_rmnet_devs > 1) + return -EINVAL; + + if (rmnet_is_real_dev_registered(slave_dev)) + return -EBUSY; + + err = rmnet_register_real_device(slave_dev); + if (err) + return -EBUSY; + + err = netdev_master_upper_dev_link(slave_dev, rmnet_dev, NULL, NULL, + extack); + if (err) + return -EINVAL; + + slave_port = rmnet_get_port(slave_dev); + slave_port->rmnet_mode = RMNET_EPMODE_BRIDGE; + slave_port->bridge_ep = real_dev; + + port->rmnet_mode = RMNET_EPMODE_BRIDGE; + port->bridge_ep = slave_dev; + + netdev_dbg(slave_dev, "registered with rmnet as slave\n"); + return 0; +} + +int rmnet_del_bridge(struct net_device *rmnet_dev, + struct net_device *slave_dev) +{ + struct rmnet_priv *priv = netdev_priv(rmnet_dev); + struct net_device *real_dev = priv->real_dev; + struct rmnet_port *port, *slave_port; + + port = rmnet_get_port(real_dev); + port->rmnet_mode = RMNET_EPMODE_VND; + port->bridge_ep = NULL; + + netdev_upper_dev_unlink(slave_dev, rmnet_dev); + slave_port = rmnet_get_port(slave_dev); + rmnet_unregister_real_device(slave_dev, slave_port); + + netdev_dbg(slave_dev, "removed from rmnet as slave\n"); + return 0; +} + /* Startup/Shutdown */ static int __init rmnet_init(void) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h index dde4e9f14f4a..60115e69e415 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h @@ -20,13 +20,10 @@ #define RMNET_MAX_LOGICAL_EP 255 -/* Information about the next device to deliver the packet to. - * Exact usage of this parameter depends on the rmnet_mode. - */ struct rmnet_endpoint { - u8 rmnet_mode; u8 mux_id; struct net_device *egress_dev; + struct hlist_node hlnode; }; /* One instance of this structure is instantiated for each real_dev associated @@ -34,22 +31,26 @@ struct rmnet_endpoint { */ struct rmnet_port { struct net_device *dev; - struct rmnet_endpoint local_ep; - struct rmnet_endpoint muxed_ep[RMNET_MAX_LOGICAL_EP]; u32 ingress_data_format; u32 egress_data_format; - struct net_device *rmnet_devices[RMNET_MAX_LOGICAL_EP]; u8 nr_rmnet_devs; + u8 rmnet_mode; + struct hlist_head muxed_ep[RMNET_MAX_LOGICAL_EP]; + struct net_device *bridge_ep; }; extern struct rtnl_link_ops rmnet_link_ops; struct rmnet_priv { - struct rmnet_endpoint local_ep; u8 mux_id; struct net_device *real_dev; }; struct rmnet_port *rmnet_get_port(struct net_device *real_dev); - +struct rmnet_endpoint *rmnet_get_endpoint(struct rmnet_port *port, u8 mux_id); +int rmnet_add_bridge(struct net_device *rmnet_dev, + struct net_device *slave_dev, + struct netlink_ext_ack *extack); +int rmnet_del_bridge(struct net_device *rmnet_dev, + struct net_device *slave_dev); #endif /* _RMNET_CONFIG_H_ */ diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 540c7622dcb1..df3d2d16ce55 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -44,56 +44,18 @@ static void rmnet_set_skb_proto(struct sk_buff *skb) /* Generic handler */ static rx_handler_result_t -rmnet_bridge_handler(struct sk_buff *skb, struct rmnet_endpoint *ep) +rmnet_deliver_skb(struct sk_buff *skb) { - if (!ep->egress_dev) - kfree_skb(skb); - else - rmnet_egress_handler(skb, ep); + skb_reset_transport_header(skb); + skb_reset_network_header(skb); + rmnet_vnd_rx_fixup(skb, skb->dev); + skb->pkt_type = PACKET_HOST; + skb_set_mac_header(skb, 0); + netif_receive_skb(skb); return RX_HANDLER_CONSUMED; } -static rx_handler_result_t -rmnet_deliver_skb(struct sk_buff *skb, struct rmnet_endpoint *ep) -{ - switch (ep->rmnet_mode) { - case RMNET_EPMODE_NONE: - return RX_HANDLER_PASS; - - case RMNET_EPMODE_BRIDGE: - return rmnet_bridge_handler(skb, ep); - - case RMNET_EPMODE_VND: - skb_reset_transport_header(skb); - skb_reset_network_header(skb); - rmnet_vnd_rx_fixup(skb, skb->dev); - - skb->pkt_type = PACKET_HOST; - skb_set_mac_header(skb, 0); - netif_receive_skb(skb); - return RX_HANDLER_CONSUMED; - - default: - kfree_skb(skb); - return RX_HANDLER_CONSUMED; - } -} - -static rx_handler_result_t -rmnet_ingress_deliver_packet(struct sk_buff *skb, - struct rmnet_port *port) -{ - if (!port) { - kfree_skb(skb); - return RX_HANDLER_CONSUMED; - } - - skb->dev = port->local_ep.egress_dev; - - return rmnet_deliver_skb(skb, &port->local_ep); -} - /* MAP handler */ static rx_handler_result_t @@ -109,19 +71,18 @@ __rmnet_map_ingress_handler(struct sk_buff *skb, & RMNET_INGRESS_FORMAT_MAP_COMMANDS) return rmnet_map_command(skb, port); - kfree_skb(skb); - return RX_HANDLER_CONSUMED; + goto free_skb; } mux_id = RMNET_MAP_GET_MUX_ID(skb); len = RMNET_MAP_GET_LENGTH(skb) - RMNET_MAP_GET_PAD(skb); - if (mux_id >= RMNET_MAX_LOGICAL_EP) { - kfree_skb(skb); - return RX_HANDLER_CONSUMED; - } + if (mux_id >= RMNET_MAX_LOGICAL_EP) + goto free_skb; - ep = &port->muxed_ep[mux_id]; + ep = rmnet_get_endpoint(port, mux_id); + if (!ep) + goto free_skb; if (port->ingress_data_format & RMNET_INGRESS_FORMAT_DEMUXING) skb->dev = ep->egress_dev; @@ -130,7 +91,11 @@ __rmnet_map_ingress_handler(struct sk_buff *skb, skb_pull(skb, sizeof(struct rmnet_map_header)); skb_trim(skb, len); rmnet_set_skb_proto(skb); - return rmnet_deliver_skb(skb, ep); + return rmnet_deliver_skb(skb); + +free_skb: + kfree_skb(skb); + return RX_HANDLER_CONSUMED; } static rx_handler_result_t @@ -154,8 +119,7 @@ rmnet_map_ingress_handler(struct sk_buff *skb, } static int rmnet_map_egress_handler(struct sk_buff *skb, - struct rmnet_port *port, - struct rmnet_endpoint *ep, + struct rmnet_port *port, u8 mux_id, struct net_device *orig_dev) { int required_headroom, additional_header_len; @@ -174,10 +138,10 @@ static int rmnet_map_egress_handler(struct sk_buff *skb, return RMNET_MAP_CONSUMED; if (port->egress_data_format & RMNET_EGRESS_FORMAT_MUXING) { - if (ep->mux_id == 0xff) + if (mux_id == 0xff) map_header->mux_id = 0; else - map_header->mux_id = ep->mux_id; + map_header->mux_id = mux_id; } skb->protocol = htons(ETH_P_MAP); @@ -185,6 +149,17 @@ static int rmnet_map_egress_handler(struct sk_buff *skb, return RMNET_MAP_SUCCESS; } +static rx_handler_result_t +rmnet_bridge_handler(struct sk_buff *skb, struct net_device *bridge_dev) +{ + if (bridge_dev) { + skb->dev = bridge_dev; + dev_queue_xmit(skb); + } + + return RX_HANDLER_CONSUMED; +} + /* Ingress / Egress Entry Points */ /* Processes packet as per ingress data format for receiving device. Logical @@ -193,10 +168,10 @@ static int rmnet_map_egress_handler(struct sk_buff *skb, */ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) { - struct rmnet_port *port; + int rc = RX_HANDLER_CONSUMED; struct sk_buff *skb = *pskb; + struct rmnet_port *port; struct net_device *dev; - int rc; if (!skb) return RX_HANDLER_CONSUMED; @@ -204,28 +179,14 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) dev = skb->dev; port = rmnet_get_port(dev); - if (port->ingress_data_format & RMNET_INGRESS_FORMAT_MAP) { - rc = rmnet_map_ingress_handler(skb, port); - } else { - switch (ntohs(skb->protocol)) { - case ETH_P_MAP: - if (port->local_ep.rmnet_mode == - RMNET_EPMODE_BRIDGE) { - rc = rmnet_ingress_deliver_packet(skb, port); - } else { - kfree_skb(skb); - rc = RX_HANDLER_CONSUMED; - } - break; - - case ETH_P_IP: - case ETH_P_IPV6: - rc = rmnet_ingress_deliver_packet(skb, port); - break; - - default: - rc = RX_HANDLER_PASS; - } + switch (port->rmnet_mode) { + case RMNET_EPMODE_VND: + if (port->ingress_data_format & RMNET_INGRESS_FORMAT_MAP) + rc = rmnet_map_ingress_handler(skb, port); + break; + case RMNET_EPMODE_BRIDGE: + rc = rmnet_bridge_handler(skb, port->bridge_ep); + break; } return rc; @@ -235,14 +196,17 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) * for egress device configured in logical endpoint. Packet is then transmitted * on the egress device. */ -void rmnet_egress_handler(struct sk_buff *skb, - struct rmnet_endpoint *ep) +void rmnet_egress_handler(struct sk_buff *skb) { struct net_device *orig_dev; struct rmnet_port *port; + struct rmnet_priv *priv; + u8 mux_id; orig_dev = skb->dev; - skb->dev = ep->egress_dev; + priv = netdev_priv(orig_dev); + skb->dev = priv->real_dev; + mux_id = priv->mux_id; port = rmnet_get_port(skb->dev); if (!port) { @@ -251,7 +215,7 @@ void rmnet_egress_handler(struct sk_buff *skb, } if (port->egress_data_format & RMNET_EGRESS_FORMAT_MAP) { - switch (rmnet_map_egress_handler(skb, port, ep, orig_dev)) { + switch (rmnet_map_egress_handler(skb, port, mux_id, orig_dev)) { case RMNET_MAP_CONSUMED: return; @@ -264,8 +228,7 @@ void rmnet_egress_handler(struct sk_buff *skb, } } - if (ep->rmnet_mode == RMNET_EPMODE_VND) - rmnet_vnd_tx_fixup(skb, orig_dev); + rmnet_vnd_tx_fixup(skb, orig_dev); dev_queue_xmit(skb); } diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h index f2638cf5693c..3537e4ceedb3 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h @@ -18,8 +18,7 @@ #include "rmnet_config.h" -void rmnet_egress_handler(struct sk_buff *skb, - struct rmnet_endpoint *ep); +void rmnet_egress_handler(struct sk_buff *skb); rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c index d1ea5e21b982..74d362f71cce 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c @@ -17,7 +17,7 @@ #include "rmnet_vnd.h" static u8 rmnet_map_do_flow_control(struct sk_buff *skb, - struct rmnet_port *rdinfo, + struct rmnet_port *port, int enable) { struct rmnet_map_control_command *cmd; @@ -37,7 +37,7 @@ static u8 rmnet_map_do_flow_control(struct sk_buff *skb, return RX_HANDLER_CONSUMED; } - ep = &rdinfo->muxed_ep[mux_id]; + ep = rmnet_get_endpoint(port, mux_id); vnd = ep->egress_dev; ip_family = cmd->flow_control.ip_family; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h index 7967198fdd90..49102f922b31 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h @@ -19,23 +19,15 @@ #define RMNET_TX_QUEUE_LEN 1000 /* Constants */ -#define RMNET_EGRESS_FORMAT__RESERVED__ BIT(0) #define RMNET_EGRESS_FORMAT_MAP BIT(1) #define RMNET_EGRESS_FORMAT_AGGREGATION BIT(2) #define RMNET_EGRESS_FORMAT_MUXING BIT(3) -#define RMNET_EGRESS_FORMAT_MAP_CKSUMV3 BIT(4) -#define RMNET_EGRESS_FORMAT_MAP_CKSUMV4 BIT(5) -#define RMNET_INGRESS_FIX_ETHERNET BIT(0) #define RMNET_INGRESS_FORMAT_MAP BIT(1) #define RMNET_INGRESS_FORMAT_DEAGGREGATION BIT(2) #define RMNET_INGRESS_FORMAT_DEMUXING BIT(3) #define RMNET_INGRESS_FORMAT_MAP_COMMANDS BIT(4) -#define RMNET_INGRESS_FORMAT_MAP_CKSUMV3 BIT(5) -#define RMNET_INGRESS_FORMAT_MAP_CKSUMV4 BIT(6) -/* Pass the frame up the stack with no modifications to skb->dev */ -#define RMNET_EPMODE_NONE (0) /* Replace skb->dev to a virtual rmnet device and pass up the stack */ #define RMNET_EPMODE_VND (1) /* Pass the frame directly to another device with dev_queue_xmit() */ diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 7f90d5587653..12bd0bbd5235 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -45,8 +45,8 @@ static netdev_tx_t rmnet_vnd_start_xmit(struct sk_buff *skb, struct rmnet_priv *priv; priv = netdev_priv(dev); - if (priv->local_ep.egress_dev) { - rmnet_egress_handler(skb, &priv->local_ep); + if (priv->real_dev) { + rmnet_egress_handler(skb); } else { dev->stats.tx_dropped++; kfree_skb(skb); @@ -74,6 +74,8 @@ static const struct net_device_ops rmnet_vnd_ops = { .ndo_start_xmit = rmnet_vnd_start_xmit, .ndo_change_mtu = rmnet_vnd_change_mtu, .ndo_get_iflink = rmnet_vnd_get_iflink, + .ndo_add_slave = rmnet_add_bridge, + .ndo_del_slave = rmnet_del_bridge, }; /* Called by kernel whenever a new rmnet<n> device is created. Sets MTU, @@ -100,17 +102,19 @@ void rmnet_vnd_setup(struct net_device *rmnet_dev) int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, struct rmnet_port *port, - struct net_device *real_dev) + struct net_device *real_dev, + struct rmnet_endpoint *ep) { struct rmnet_priv *priv; int rc; - if (port->rmnet_devices[id]) + if (ep->egress_dev) return -EINVAL; rc = register_netdevice(rmnet_dev); if (!rc) { - port->rmnet_devices[id] = rmnet_dev; + ep->egress_dev = rmnet_dev; + ep->mux_id = id; port->nr_rmnet_devs++; rmnet_dev->rtnl_link_ops = &rmnet_link_ops; @@ -125,12 +129,13 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, return rc; } -int rmnet_vnd_dellink(u8 id, struct rmnet_port *port) +int rmnet_vnd_dellink(u8 id, struct rmnet_port *port, + struct rmnet_endpoint *ep) { - if (id >= RMNET_MAX_LOGICAL_EP || !port->rmnet_devices[id]) + if (id >= RMNET_MAX_LOGICAL_EP || !ep->egress_dev) return -EINVAL; - port->rmnet_devices[id] = NULL; + ep->egress_dev = NULL; port->nr_rmnet_devs--; return 0; } @@ -143,21 +148,6 @@ u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev) return priv->mux_id; } -/* Gets the logical endpoint configuration for a RmNet virtual network device - * node. Caller should confirm that devices is a RmNet VND before calling. - */ -struct rmnet_endpoint *rmnet_vnd_get_endpoint(struct net_device *rmnet_dev) -{ - struct rmnet_priv *priv; - - if (!rmnet_dev) - return NULL; - - priv = netdev_priv(rmnet_dev); - - return &priv->local_ep; -} - int rmnet_vnd_do_flow_control(struct net_device *rmnet_dev, int enable) { netdev_dbg(rmnet_dev, "Setting VND TX queue state to %d\n", enable); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h index 8a4042f0f6bf..71e4c3286951 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h @@ -17,11 +17,12 @@ #define _RMNET_VND_H_ int rmnet_vnd_do_flow_control(struct net_device *dev, int enable); -struct rmnet_endpoint *rmnet_vnd_get_endpoint(struct net_device *dev); int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, struct rmnet_port *port, - struct net_device *real_dev); -int rmnet_vnd_dellink(u8 id, struct rmnet_port *port); + struct net_device *real_dev, + struct rmnet_endpoint *ep); +int rmnet_vnd_dellink(u8 id, struct rmnet_port *port, + struct rmnet_endpoint *ep); void rmnet_vnd_rx_fixup(struct sk_buff *skb, struct net_device *dev); void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev); u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index a8822a756e08..2b962d349f5f 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1354,20 +1354,15 @@ static void ravb_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) { struct ravb_private *priv = netdev_priv(ndev); - wol->supported = 0; - wol->wolopts = 0; - - if (priv->clk) { - wol->supported = WAKE_MAGIC; - wol->wolopts = priv->wol_enabled ? WAKE_MAGIC : 0; - } + wol->supported = WAKE_MAGIC; + wol->wolopts = priv->wol_enabled ? WAKE_MAGIC : 0; } static int ravb_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) { struct ravb_private *priv = netdev_priv(ndev); - if (!priv->clk || wol->wolopts & ~WAKE_MAGIC) + if (wol->wolopts & ~WAKE_MAGIC) return -EOPNOTSUPP; priv->wol_enabled = !!(wol->wolopts & WAKE_MAGIC); @@ -1962,22 +1957,12 @@ MODULE_DEVICE_TABLE(of, ravb_match_table); static int ravb_set_gti(struct net_device *ndev) { - + struct ravb_private *priv = netdev_priv(ndev); struct device *dev = ndev->dev.parent; - struct device_node *np = dev->of_node; unsigned long rate; - struct clk *clk; uint64_t inc; - clk = of_clk_get(np, 0); - if (IS_ERR(clk)) { - dev_err(dev, "could not get clock\n"); - return PTR_ERR(clk); - } - - rate = clk_get_rate(clk); - clk_put(clk); - + rate = clk_get_rate(priv->clk); if (!rate) return -EINVAL; @@ -2126,10 +2111,11 @@ static int ravb_probe(struct platform_device *pdev) priv->chip_id = chip_id; - /* Get clock, if not found that's OK but Wake-On-Lan is unavailable */ priv->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(priv->clk)) - priv->clk = NULL; + if (IS_ERR(priv->clk)) { + error = PTR_ERR(priv->clk); + goto out_release; + } /* Set function */ ndev->netdev_ops = &ravb_netdev_ops; @@ -2197,8 +2183,7 @@ static int ravb_probe(struct platform_device *pdev) if (error) goto out_napi_del; - if (priv->clk) - device_set_wakeup_capable(&pdev->dev, 1); + device_set_wakeup_capable(&pdev->dev, 1); /* Print device information */ netdev_info(ndev, "Base address at %#x, %pM, IRQ %d.\n", diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index d2e88a30f57b..7e060aa9fbed 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -594,7 +594,7 @@ static struct sh_eth_cpu_data r8a7740_data = { }; /* There is CPU dependent code */ -static void sh_eth_set_rate_r8a777x(struct net_device *ndev) +static void sh_eth_set_rate_rcar(struct net_device *ndev) { struct sh_eth_private *mdp = netdev_priv(ndev); @@ -608,10 +608,10 @@ static void sh_eth_set_rate_r8a777x(struct net_device *ndev) } } -/* R8A7778/9 */ -static struct sh_eth_cpu_data r8a777x_data = { +/* R-Car Gen1 */ +static struct sh_eth_cpu_data rcar_gen1_data = { .set_duplex = sh_eth_set_duplex, - .set_rate = sh_eth_set_rate_r8a777x, + .set_rate = sh_eth_set_rate_rcar, .register_type = SH_ETH_REG_FAST_RCAR, @@ -635,10 +635,10 @@ static struct sh_eth_cpu_data r8a777x_data = { .hw_swap = 1, }; -/* R8A7790/1 */ -static struct sh_eth_cpu_data r8a779x_data = { +/* R-Car Gen2 and RZ/G1 */ +static struct sh_eth_cpu_data rcar_gen2_data = { .set_duplex = sh_eth_set_duplex, - .set_rate = sh_eth_set_rate_r8a777x, + .set_rate = sh_eth_set_rate_rcar, .register_type = SH_ETH_REG_FAST_RCAR, @@ -3086,15 +3086,17 @@ static struct sh_eth_plat_data *sh_eth_parse_dt(struct device *dev) static const struct of_device_id sh_eth_match_table[] = { { .compatible = "renesas,gether-r8a7740", .data = &r8a7740_data }, - { .compatible = "renesas,ether-r8a7743", .data = &r8a779x_data }, - { .compatible = "renesas,ether-r8a7745", .data = &r8a779x_data }, - { .compatible = "renesas,ether-r8a7778", .data = &r8a777x_data }, - { .compatible = "renesas,ether-r8a7779", .data = &r8a777x_data }, - { .compatible = "renesas,ether-r8a7790", .data = &r8a779x_data }, - { .compatible = "renesas,ether-r8a7791", .data = &r8a779x_data }, - { .compatible = "renesas,ether-r8a7793", .data = &r8a779x_data }, - { .compatible = "renesas,ether-r8a7794", .data = &r8a779x_data }, + { .compatible = "renesas,ether-r8a7743", .data = &rcar_gen2_data }, + { .compatible = "renesas,ether-r8a7745", .data = &rcar_gen2_data }, + { .compatible = "renesas,ether-r8a7778", .data = &rcar_gen1_data }, + { .compatible = "renesas,ether-r8a7779", .data = &rcar_gen1_data }, + { .compatible = "renesas,ether-r8a7790", .data = &rcar_gen2_data }, + { .compatible = "renesas,ether-r8a7791", .data = &rcar_gen2_data }, + { .compatible = "renesas,ether-r8a7793", .data = &rcar_gen2_data }, + { .compatible = "renesas,ether-r8a7794", .data = &rcar_gen2_data }, { .compatible = "renesas,ether-r7s72100", .data = &r7s72100_data }, + { .compatible = "renesas,rcar-gen1-ether", .data = &rcar_gen1_data }, + { .compatible = "renesas,rcar-gen2-ether", .data = &rcar_gen2_data }, { } }; MODULE_DEVICE_TABLE(of, sh_eth_match_table); diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c index 244c1e171017..da4807723a06 100644 --- a/drivers/net/ethernet/seeq/ether3.c +++ b/drivers/net/ethernet/seeq/ether3.c @@ -170,9 +170,11 @@ ether3_setbuffer(struct net_device *dev, buffer_rw_t read, int start) /* * Switch LED off... */ -static void ether3_ledoff(unsigned long data) +static void ether3_ledoff(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; + struct dev_priv *private = from_timer(priv, t, timer); + struct net_device *dev = private->dev; + ether3_outw(priv(dev)->regs.config2 |= CFG2_CTRLO, REG_CONFIG2); } @@ -183,8 +185,6 @@ static inline void ether3_ledon(struct net_device *dev) { del_timer(&priv(dev)->timer); priv(dev)->timer.expires = jiffies + HZ / 50; /* leave on for 1/50th second */ - priv(dev)->timer.data = (unsigned long)dev; - priv(dev)->timer.function = ether3_ledoff; add_timer(&priv(dev)->timer); if (priv(dev)->regs.config2 & CFG2_CTRLO) ether3_outw(priv(dev)->regs.config2 &= ~CFG2_CTRLO, REG_CONFIG2); @@ -783,7 +783,8 @@ ether3_probe(struct expansion_card *ec, const struct ecard_id *id) ether3_addr(dev->dev_addr, ec); - init_timer(&priv(dev)->timer); + priv(dev)->dev = dev; + timer_setup(&priv(dev)->timer, ether3_ledoff, 0); /* Reset card... */ diff --git a/drivers/net/ethernet/seeq/ether3.h b/drivers/net/ethernet/seeq/ether3.h index 2db63b08bdf3..ea2ba286e665 100644 --- a/drivers/net/ethernet/seeq/ether3.h +++ b/drivers/net/ethernet/seeq/ether3.h @@ -165,6 +165,7 @@ struct dev_priv { unsigned char tx_tail; /* buffer nr of transmitting packet */ unsigned int rx_head; /* address to fetch next packet from */ struct timer_list timer; + net_device *dev; int broken; /* 0 = ok, 1 = something went wrong */ }; diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index 9c0488e0f08e..18d533fdf14c 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -764,9 +764,9 @@ static inline void ioc3_setup_duplex(struct ioc3_private *ip) ioc3_w_emcr(ip->emcr); } -static void ioc3_timer(unsigned long data) +static void ioc3_timer(struct timer_list *t) { - struct ioc3_private *ip = (struct ioc3_private *) data; + struct ioc3_private *ip = from_timer(ip, t, ioc3_timer); /* Print the link status if it has changed */ mii_check_media(&ip->mii, 1, 0); @@ -818,8 +818,6 @@ out: static void ioc3_mii_start(struct ioc3_private *ip) { ip->ioc3_timer.expires = jiffies + (12 * HZ)/10; /* 1.2 sec. */ - ip->ioc3_timer.data = (unsigned long) ip; - ip->ioc3_timer.function = ioc3_timer; add_timer(&ip->ioc3_timer); } @@ -1291,7 +1289,7 @@ static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) #endif spin_lock_init(&ip->ioc3_lock); - init_timer(&ip->ioc3_timer); + timer_setup(&ip->ioc3_timer, ioc3_timer, 0); ioc3_stop(ip); ioc3_init(dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c index 6a9c954492f2..8b50afcdb52d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c +++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c @@ -118,10 +118,9 @@ int tse_pcs_init(void __iomem *base, struct tse_pcs *pcs) return ret; } -static void pcs_link_timer_callback(unsigned long data) +static void pcs_link_timer_callback(struct tse_pcs *pcs) { u16 val = 0; - struct tse_pcs *pcs = (struct tse_pcs *)data; void __iomem *tse_pcs_base = pcs->tse_pcs_base; void __iomem *sgmii_adapter_base = pcs->sgmii_adapter_base; @@ -138,12 +137,11 @@ static void pcs_link_timer_callback(unsigned long data) } } -static void auto_nego_timer_callback(unsigned long data) +static void auto_nego_timer_callback(struct tse_pcs *pcs) { u16 val = 0; u16 speed = 0; u16 duplex = 0; - struct tse_pcs *pcs = (struct tse_pcs *)data; void __iomem *tse_pcs_base = pcs->tse_pcs_base; void __iomem *sgmii_adapter_base = pcs->sgmii_adapter_base; @@ -201,14 +199,14 @@ static void auto_nego_timer_callback(unsigned long data) } } -static void aneg_link_timer_callback(unsigned long data) +static void aneg_link_timer_callback(struct timer_list *t) { - struct tse_pcs *pcs = (struct tse_pcs *)data; + struct tse_pcs *pcs = from_timer(pcs, t, aneg_link_timer); if (pcs->autoneg == AUTONEG_ENABLE) - auto_nego_timer_callback(data); + auto_nego_timer_callback(pcs); else if (pcs->autoneg == AUTONEG_DISABLE) - pcs_link_timer_callback(data); + pcs_link_timer_callback(pcs); } void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev, @@ -237,8 +235,8 @@ void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev, tse_pcs_reset(tse_pcs_base, pcs); - setup_timer(&pcs->aneg_link_timer, - aneg_link_timer_callback, (unsigned long)pcs); + timer_setup(&pcs->aneg_link_timer, aneg_link_timer_callback, + 0); mod_timer(&pcs->aneg_link_timer, jiffies + msecs_to_jiffies(AUTONEGO_LINK_TIMER)); } else if (phy_dev->autoneg == AUTONEG_DISABLE) { @@ -270,8 +268,8 @@ void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev, tse_pcs_reset(tse_pcs_base, pcs); - setup_timer(&pcs->aneg_link_timer, - aneg_link_timer_callback, (unsigned long)pcs); + timer_setup(&pcs->aneg_link_timer, aneg_link_timer_callback, + 0); mod_timer(&pcs->aneg_link_timer, jiffies + msecs_to_jiffies(AUTONEGO_LINK_TIMER)); } diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index e82b4b70b7be..e1e5ac053760 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -442,8 +442,9 @@ struct stmmac_dma_ops { void (*dma_mode)(void __iomem *ioaddr, int txmode, int rxmode, int rxfifosz); void (*dma_rx_mode)(void __iomem *ioaddr, int mode, u32 channel, - int fifosz); - void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel); + int fifosz, u8 qmode); + void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel, + int fifosz, u8 qmode); /* To track extra statistic (if supported) */ void (*dma_diagnostic_fr) (void *data, struct stmmac_extra_stats *x, void __iomem *ioaddr); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index 866444b6c82f..2c6d7c69c8f7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -51,15 +51,11 @@ #define NSS_COMMON_CLK_SRC_CTRL_RGMII(x) 1 #define NSS_COMMON_CLK_SRC_CTRL_SGMII(x) ((x >= 2) ? 1 : 0) -#define NSS_COMMON_MACSEC_CTL 0x28 -#define NSS_COMMON_MACSEC_CTL_EXT_BYPASS_EN(x) (1 << x) - #define NSS_COMMON_GMAC_CTL(x) (0x30 + (x * 4)) #define NSS_COMMON_GMAC_CTL_CSYS_REQ BIT(19) #define NSS_COMMON_GMAC_CTL_PHY_IFACE_SEL BIT(16) #define NSS_COMMON_GMAC_CTL_IFG_LIMIT_OFFSET 8 #define NSS_COMMON_GMAC_CTL_IFG_OFFSET 0 -#define NSS_COMMON_GMAC_CTL_IFG_MASK 0x3f #define NSS_COMMON_CLK_DIV_RGMII_1000 1 #define NSS_COMMON_CLK_DIV_RGMII_100 9 @@ -68,9 +64,6 @@ #define NSS_COMMON_CLK_DIV_SGMII_100 4 #define NSS_COMMON_CLK_DIV_SGMII_10 49 -#define QSGMII_PCS_MODE_CTL 0x68 -#define QSGMII_PCS_MODE_CTL_AUTONEG_EN(x) BIT((x * 8) + 7) - #define QSGMII_PCS_CAL_LCKDT_CTL 0x120 #define QSGMII_PCS_CAL_LCKDT_CTL_RST BIT(19) @@ -83,15 +76,10 @@ #define QSGMII_PHY_TX_DRIVER_EN BIT(3) #define QSGMII_PHY_QSGMII_EN BIT(7) #define QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET 12 -#define QSGMII_PHY_PHASE_LOOP_GAIN_MASK 0x7 #define QSGMII_PHY_RX_DC_BIAS_OFFSET 18 -#define QSGMII_PHY_RX_DC_BIAS_MASK 0x3 #define QSGMII_PHY_RX_INPUT_EQU_OFFSET 20 -#define QSGMII_PHY_RX_INPUT_EQU_MASK 0x3 #define QSGMII_PHY_CDR_PI_SLEW_OFFSET 22 -#define QSGMII_PHY_CDR_PI_SLEW_MASK 0x3 #define QSGMII_PHY_TX_DRV_AMP_OFFSET 28 -#define QSGMII_PHY_TX_DRV_AMP_MASK 0xf struct ipq806x_gmac { struct platform_device *pdev; @@ -217,7 +205,7 @@ static int ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac) * code and keep it consistent with the Linux convention, we'll number * them from 0 to 3 here. */ - if (gmac->id < 0 || gmac->id > 3) { + if (gmac->id > 3) { dev_err(dev, "invalid gmac id\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index d74cedf2a397..aeda3ab2d761 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -225,6 +225,8 @@ enum power_event { #define MTL_CHAN_RX_DEBUG(x) (MTL_CHANX_BASE_ADDR(x) + 0x38) #define MTL_OP_MODE_RSF BIT(5) +#define MTL_OP_MODE_TXQEN_MASK GENMASK(3, 2) +#define MTL_OP_MODE_TXQEN_AV BIT(2) #define MTL_OP_MODE_TXQEN BIT(3) #define MTL_OP_MODE_TSF BIT(1) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index e84831e1b63b..c110f6850ffa 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -191,7 +191,7 @@ static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 number_chan) } static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode, - u32 channel, int fifosz) + u32 channel, int fifosz, u8 qmode) { unsigned int rqs = fifosz / 256 - 1; u32 mtl_rx_op, mtl_rx_int; @@ -218,8 +218,10 @@ static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode, mtl_rx_op &= ~MTL_OP_MODE_RQS_MASK; mtl_rx_op |= rqs << MTL_OP_MODE_RQS_SHIFT; - /* enable flow control only if each channel gets 4 KiB or more FIFO */ - if (fifosz >= 4096) { + /* Enable flow control only if each channel gets 4 KiB or more FIFO and + * only if channel is not an AVB channel. + */ + if ((fifosz >= 4096) && (qmode != MTL_QUEUE_AVB)) { unsigned int rfd, rfa; mtl_rx_op |= MTL_OP_MODE_EHFC; @@ -271,9 +273,10 @@ static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode, } static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode, - u32 channel) + u32 channel, int fifosz, u8 qmode) { u32 mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel)); + unsigned int tqs = fifosz / 256 - 1; if (mode == SF_DMA_MODE) { pr_debug("GMAC: enable TX store and forward mode\n"); @@ -306,12 +309,18 @@ static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode, * For an IP with DWC_EQOS_NUM_TXQ > 1, the fields TXQEN and TQS are R/W * with reset values: TXQEN off, TQS 256 bytes. * - * Write the bits in both cases, since it will have no effect when RO. - * For DWC_EQOS_NUM_TXQ > 1, the top bits in MTL_OP_MODE_TQS_MASK might - * be RO, however, writing the whole TQS field will result in a value - * equal to DWC_EQOS_TXFIFO_SIZE, just like for DWC_EQOS_NUM_TXQ == 1. + * TXQEN must be written for multi-channel operation and TQS must + * reflect the available fifo size per queue (total fifo size / number + * of enabled queues). */ - mtl_tx_op |= MTL_OP_MODE_TXQEN | MTL_OP_MODE_TQS_MASK; + mtl_tx_op &= ~MTL_OP_MODE_TXQEN_MASK; + if (qmode != MTL_QUEUE_AVB) + mtl_tx_op |= MTL_OP_MODE_TXQEN; + else + mtl_tx_op |= MTL_OP_MODE_TXQEN_AV; + mtl_tx_op &= ~MTL_OP_MODE_TQS_MASK; + mtl_tx_op |= tqs << MTL_OP_MODE_TQS_SHIFT; + writel(mtl_tx_op, ioaddr + MTL_CHAN_TX_OP_MODE(channel)); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f41661a04f23..0e1b0a3d7b76 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1750,12 +1750,20 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) u32 rx_channels_count = priv->plat->rx_queues_to_use; u32 tx_channels_count = priv->plat->tx_queues_to_use; int rxfifosz = priv->plat->rx_fifo_size; + int txfifosz = priv->plat->tx_fifo_size; u32 txmode = 0; u32 rxmode = 0; u32 chan = 0; + u8 qmode = 0; if (rxfifosz == 0) rxfifosz = priv->dma_cap.rx_fifo_size; + if (txfifosz == 0) + txfifosz = priv->dma_cap.tx_fifo_size; + + /* Adjust for real per queue fifo size */ + rxfifosz /= rx_channels_count; + txfifosz /= tx_channels_count; if (priv->plat->force_thresh_dma_mode) { txmode = tc; @@ -1778,12 +1786,19 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) /* configure all channels */ if (priv->synopsys_id >= DWMAC_CORE_4_00) { - for (chan = 0; chan < rx_channels_count; chan++) + for (chan = 0; chan < rx_channels_count; chan++) { + qmode = priv->plat->rx_queues_cfg[chan].mode_to_use; + priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan, - rxfifosz); + rxfifosz, qmode); + } - for (chan = 0; chan < tx_channels_count; chan++) - priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan); + for (chan = 0; chan < tx_channels_count; chan++) { + qmode = priv->plat->tx_queues_cfg[chan].mode_to_use; + + priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan, + txfifosz, qmode); + } } else { priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode, rxfifosz); @@ -1946,15 +1961,27 @@ static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan) static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, u32 rxmode, u32 chan) { + u8 rxqmode = priv->plat->rx_queues_cfg[chan].mode_to_use; + u8 txqmode = priv->plat->tx_queues_cfg[chan].mode_to_use; + u32 rx_channels_count = priv->plat->rx_queues_to_use; + u32 tx_channels_count = priv->plat->tx_queues_to_use; int rxfifosz = priv->plat->rx_fifo_size; + int txfifosz = priv->plat->tx_fifo_size; if (rxfifosz == 0) rxfifosz = priv->dma_cap.rx_fifo_size; + if (txfifosz == 0) + txfifosz = priv->dma_cap.tx_fifo_size; + + /* Adjust for real per queue fifo size */ + rxfifosz /= rx_channels_count; + txfifosz /= tx_channels_count; if (priv->synopsys_id >= DWMAC_CORE_4_00) { priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan, - rxfifosz); - priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan); + rxfifosz, rxqmode); + priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan, + txfifosz, txqmode); } else { priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode, rxfifosz); diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index a74d78f64af9..113bd57e2ea0 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -4079,9 +4079,9 @@ done: #endif } -static void cas_link_timer(unsigned long data) +static void cas_link_timer(struct timer_list *t) { - struct cas *cp = (struct cas *) data; + struct cas *cp = from_timer(cp, t, link_timer); int mask, pending = 0, reset = 0; unsigned long flags; @@ -5039,7 +5039,8 @@ static int cas_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) spin_lock_init(&cp->stat_lock[N_TX_RINGS]); mutex_init(&cp->pm_mutex); - setup_timer(&cp->link_timer, cas_link_timer, (unsigned long)cp); + timer_setup(&cp->link_timer, cas_link_timer, 0); + #if 1 /* Just in case the implementation of atomic operations * change so that an explicit initialization is necessary. diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index 5feeaa9f0a9e..5ea037672e6f 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -363,8 +363,7 @@ static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) list_add_rcu(&port->list, &vp->port_list); spin_unlock_irqrestore(&vp->lock, flags); - setup_timer(&port->clean_timer, sunvnet_clean_timer_expire_common, - (unsigned long)port); + timer_setup(&port->clean_timer, sunvnet_clean_timer_expire_common, 0); err = register_netdev(dev); if (err) { diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index bde19b307d0d..ab502ee35fb2 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -2221,9 +2221,9 @@ static int niu_link_status(struct niu *np, int *link_up_p) return err; } -static void niu_timer(unsigned long __opaque) +static void niu_timer(struct timer_list *t) { - struct niu *np = (struct niu *) __opaque; + struct niu *np = from_timer(np, t, timer); unsigned long off; int err, link_up; @@ -6123,7 +6123,7 @@ static int niu_open(struct net_device *dev) err = niu_init_hw(np); if (!err) { - setup_timer(&np->timer, niu_timer, (unsigned long)np); + timer_setup(&np->timer, niu_timer, 0); np->timer.expires = jiffies + HZ; err = niu_enable_interrupts(np, 1); @@ -6773,10 +6773,8 @@ static int niu_change_mtu(struct net_device *dev, int new_mtu) err = niu_init_hw(np); if (!err) { - init_timer(&np->timer); + timer_setup(&np->timer, niu_timer, 0); np->timer.expires = jiffies + HZ; - np->timer.data = (unsigned long) np; - np->timer.function = niu_timer; err = niu_enable_interrupts(np, 1); if (err) diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index 3189722110c2..0b1f41f6bceb 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -523,9 +523,9 @@ static int try_next_permutation(struct bigmac *bp, void __iomem *tregs) return -1; } -static void bigmac_timer(unsigned long data) +static void bigmac_timer(struct timer_list *t) { - struct bigmac *bp = (struct bigmac *) data; + struct bigmac *bp = from_timer(bp, t, bigmac_timer); void __iomem *tregs = bp->tregs; int restart_timer = 0; @@ -613,8 +613,6 @@ static void bigmac_begin_auto_negotiation(struct bigmac *bp) bp->timer_state = ltrywait; bp->timer_ticks = 0; bp->bigmac_timer.expires = jiffies + (12 * HZ) / 10; - bp->bigmac_timer.data = (unsigned long) bp; - bp->bigmac_timer.function = bigmac_timer; add_timer(&bp->bigmac_timer); } @@ -921,7 +919,7 @@ static int bigmac_open(struct net_device *dev) printk(KERN_ERR "BIGMAC: Can't order irq %d to go.\n", dev->irq); return ret; } - init_timer(&bp->bigmac_timer); + timer_setup(&bp->bigmac_timer, bigmac_timer, 0); ret = bigmac_init_hw(bp, 0); if (ret) free_irq(dev->irq, bp); @@ -1172,7 +1170,7 @@ static int bigmac_ether_init(struct platform_device *op, "board-version", 1); /* Init auto-negotiation timer state. */ - init_timer(&bp->bigmac_timer); + timer_setup(&bp->bigmac_timer, bigmac_timer, 0); bp->timer_state = asleep; bp->timer_ticks = 0; diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index b75ab8f44968..a7afcee3c5ae 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -1496,9 +1496,9 @@ static int gem_mdio_link_not_up(struct gem *gp) } } -static void gem_link_timer(unsigned long data) +static void gem_link_timer(struct timer_list *t) { - struct gem *gp = (struct gem *) data; + struct gem *gp = from_timer(gp, t, link_timer); struct net_device *dev = gp->dev; int restart_aneg = 0; @@ -2910,7 +2910,7 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) gp->msg_enable = DEFAULT_MSG; - setup_timer(&gp->link_timer, gem_link_timer, (unsigned long)gp); + timer_setup(&gp->link_timer, gem_link_timer, 0); INIT_WORK(&gp->reset_task, gem_reset_task); diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 9e983e1d8249..0431f1e5f511 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -685,9 +685,9 @@ static int is_lucent_phy(struct happy_meal *hp) return ret; } -static void happy_meal_timer(unsigned long data) +static void happy_meal_timer(struct timer_list *t) { - struct happy_meal *hp = (struct happy_meal *) data; + struct happy_meal *hp = from_timer(hp, t, happy_timer); void __iomem *tregs = hp->tcvregs; int restart_timer = 0; @@ -1413,8 +1413,6 @@ force_link: hp->timer_ticks = 0; hp->happy_timer.expires = jiffies + (12 * HZ)/10; /* 1.2 sec. */ - hp->happy_timer.data = (unsigned long) hp; - hp->happy_timer.function = happy_meal_timer; add_timer(&hp->happy_timer); } @@ -2819,7 +2817,7 @@ static int happy_meal_sbus_probe_one(struct platform_device *op, int is_qfe) hp->timer_state = asleep; hp->timer_ticks = 0; - init_timer(&hp->happy_timer); + timer_setup(&hp->happy_timer, happy_meal_timer, 0); hp->dev = dev; dev->netdev_ops = &hme_netdev_ops; @@ -3133,7 +3131,7 @@ static int happy_meal_pci_probe(struct pci_dev *pdev, hp->timer_state = asleep; hp->timer_ticks = 0; - init_timer(&hp->happy_timer); + timer_setup(&hp->happy_timer, happy_meal_timer, 0); hp->irq = pdev->irq; hp->dev = dev; diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 0b95105f7060..27fb22638885 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -492,8 +492,7 @@ static int vnet_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) pr_info("%s: PORT ( remote-mac %pM%s )\n", vp->dev->name, port->raddr, switch_port ? " switch-port" : ""); - setup_timer(&port->clean_timer, sunvnet_clean_timer_expire_common, - (unsigned long)port); + timer_setup(&port->clean_timer, sunvnet_clean_timer_expire_common, 0); napi_enable(&port->napi); vio_port_up(&port->vio); diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index ecf456c7b6d1..8aa3ce46bb81 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -1040,9 +1040,9 @@ static inline void vnet_free_skbs(struct sk_buff *skb) } } -void sunvnet_clean_timer_expire_common(unsigned long port0) +void sunvnet_clean_timer_expire_common(struct timer_list *t) { - struct vnet_port *port = (struct vnet_port *)port0; + struct vnet_port *port = from_timer(port, t, clean_timer); struct sk_buff *freeskbs; unsigned pending; diff --git a/drivers/net/ethernet/sun/sunvnet_common.h b/drivers/net/ethernet/sun/sunvnet_common.h index b20d6fa7ef25..656673c31066 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.h +++ b/drivers/net/ethernet/sun/sunvnet_common.h @@ -129,7 +129,7 @@ struct vnet { ((__port)->vsw ? (__port)->dev : (__port)->vp->dev) /* Common funcs */ -void sunvnet_clean_timer_expire_common(unsigned long port0); +void sunvnet_clean_timer_expire_common(struct timer_list *t); int sunvnet_open_common(struct net_device *dev); int sunvnet_close_common(struct net_device *dev); void sunvnet_set_rx_mode_common(struct net_device *dev, struct vnet *vp); diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index c8d53d8c83ee..8f53d762fbc4 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -172,7 +172,8 @@ static u32 tlan_handle_tx_eoc(struct net_device *, u16); static u32 tlan_handle_status_check(struct net_device *, u16); static u32 tlan_handle_rx_eoc(struct net_device *, u16); -static void tlan_timer(unsigned long); +static void tlan_timer(struct timer_list *t); +static void tlan_phy_monitor(struct timer_list *t); static void tlan_reset_lists(struct net_device *); static void tlan_free_lists(struct net_device *); @@ -190,7 +191,6 @@ static void tlan_phy_power_up(struct net_device *); static void tlan_phy_reset(struct net_device *); static void tlan_phy_start_link(struct net_device *); static void tlan_phy_finish_auto_neg(struct net_device *); -static void tlan_phy_monitor(unsigned long); /* static int tlan_phy_nop(struct net_device *); @@ -254,11 +254,10 @@ tlan_set_timer(struct net_device *dev, u32 ticks, u32 type) spin_unlock_irqrestore(&priv->lock, flags); return; } - priv->timer.function = tlan_timer; + priv->timer.function = (TIMER_FUNC_TYPE)tlan_timer; if (!in_irq()) spin_unlock_irqrestore(&priv->lock, flags); - priv->timer.data = (unsigned long) dev; priv->timer_set_at = jiffies; priv->timer_type = type; mod_timer(&priv->timer, jiffies + ticks); @@ -926,8 +925,8 @@ static int tlan_open(struct net_device *dev) return err; } - init_timer(&priv->timer); - init_timer(&priv->media_timer); + timer_setup(&priv->timer, NULL, 0); + timer_setup(&priv->media_timer, tlan_phy_monitor, 0); tlan_start(dev); @@ -1426,8 +1425,7 @@ static u32 tlan_handle_tx_eof(struct net_device *dev, u16 host_int) tlan_dio_write8(dev->base_addr, TLAN_LED_REG, TLAN_LED_LINK | TLAN_LED_ACT); if (priv->timer.function == NULL) { - priv->timer.function = tlan_timer; - priv->timer.data = (unsigned long) dev; + priv->timer.function = (TIMER_FUNC_TYPE)tlan_timer; priv->timer.expires = jiffies + TLAN_TIMER_ACT_DELAY; priv->timer_set_at = jiffies; priv->timer_type = TLAN_TIMER_ACTIVITY; @@ -1578,8 +1576,7 @@ drop_and_reuse: tlan_dio_write8(dev->base_addr, TLAN_LED_REG, TLAN_LED_LINK | TLAN_LED_ACT); if (priv->timer.function == NULL) { - priv->timer.function = tlan_timer; - priv->timer.data = (unsigned long) dev; + priv->timer.function = (TIMER_FUNC_TYPE)tlan_timer; priv->timer.expires = jiffies + TLAN_TIMER_ACT_DELAY; priv->timer_set_at = jiffies; priv->timer_type = TLAN_TIMER_ACTIVITY; @@ -1836,10 +1833,10 @@ ThunderLAN driver timer function * **************************************************************/ -static void tlan_timer(unsigned long data) +static void tlan_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *) data; - struct tlan_priv *priv = netdev_priv(dev); + struct tlan_priv *priv = from_timer(priv, t, timer); + struct net_device *dev = priv->dev; u32 elapsed; unsigned long flags = 0; @@ -1872,7 +1869,6 @@ static void tlan_timer(unsigned long data) tlan_dio_write8(dev->base_addr, TLAN_LED_REG, TLAN_LED_LINK); } else { - priv->timer.function = tlan_timer; priv->timer.expires = priv->timer_set_at + TLAN_TIMER_ACT_DELAY; spin_unlock_irqrestore(&priv->lock, flags); @@ -2317,8 +2313,6 @@ tlan_finish_reset(struct net_device *dev) } else netdev_info(dev, "Link active\n"); /* Enabling link beat monitoring */ - priv->media_timer.function = tlan_phy_monitor; - priv->media_timer.data = (unsigned long) dev; priv->media_timer.expires = jiffies + HZ; add_timer(&priv->media_timer); } @@ -2763,10 +2757,10 @@ static void tlan_phy_finish_auto_neg(struct net_device *dev) * *******************************************************************/ -static void tlan_phy_monitor(unsigned long data) +static void tlan_phy_monitor(struct timer_list *t) { - struct net_device *dev = (struct net_device *) data; - struct tlan_priv *priv = netdev_priv(dev); + struct tlan_priv *priv = from_timer(priv, t, media_timer); + struct net_device *dev = priv->dev; u16 phy; u16 phy_status; diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 97fe8dfb602d..bbc7b7808a31 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -136,9 +136,9 @@ static int encode_sixpack(unsigned char *, unsigned char *, int, unsigned char); * Note that in case of DAMA operation, the data is not sent here. */ -static void sp_xmit_on_air(unsigned long channel) +static void sp_xmit_on_air(struct timer_list *t) { - struct sixpack *sp = (struct sixpack *) channel; + struct sixpack *sp = from_timer(sp, t, tx_t); int actual, when = sp->slottime; static unsigned char random; @@ -229,7 +229,7 @@ static void sp_encaps(struct sixpack *sp, unsigned char *icp, int len) sp->xleft = count; sp->xhead = sp->xbuff; sp->status2 = count; - sp_xmit_on_air((unsigned long)sp); + sp_xmit_on_air(&sp->tx_t); } return; @@ -500,9 +500,9 @@ static inline void tnc_set_sync_state(struct sixpack *sp, int new_tnc_state) __tnc_set_sync_state(sp, new_tnc_state); } -static void resync_tnc(unsigned long channel) +static void resync_tnc(struct timer_list *t) { - struct sixpack *sp = (struct sixpack *) channel; + struct sixpack *sp = from_timer(sp, t, resync_t); static char resync_cmd = 0xe8; /* clear any data that might have been received */ @@ -526,8 +526,6 @@ static void resync_tnc(unsigned long channel) /* Start resync timer again -- the TNC might be still absent */ del_timer(&sp->resync_t); - sp->resync_t.data = (unsigned long) sp; - sp->resync_t.function = resync_tnc; sp->resync_t.expires = jiffies + SIXP_RESYNC_TIMEOUT; add_timer(&sp->resync_t); } @@ -541,8 +539,6 @@ static inline int tnc_init(struct sixpack *sp) sp->tty->ops->write(sp->tty, &inbyte, 1); del_timer(&sp->resync_t); - sp->resync_t.data = (unsigned long) sp; - sp->resync_t.function = resync_tnc; sp->resync_t.expires = jiffies + SIXP_RESYNC_TIMEOUT; add_timer(&sp->resync_t); @@ -623,9 +619,9 @@ static int sixpack_open(struct tty_struct *tty) netif_start_queue(dev); - setup_timer(&sp->tx_t, sp_xmit_on_air, (unsigned long)sp); + timer_setup(&sp->tx_t, sp_xmit_on_air, 0); - init_timer(&sp->resync_t); + timer_setup(&sp->resync_t, resync_tnc, 0); spin_unlock_bh(&sp->lock); @@ -926,8 +922,6 @@ static void decode_prio_command(struct sixpack *sp, unsigned char cmd) if (sp->tnc_state == TNC_IN_SYNC) { del_timer(&sp->resync_t); - sp->resync_t.data = (unsigned long) sp; - sp->resync_t.function = resync_tnc; sp->resync_t.expires = jiffies + SIXP_INIT_RESYNC_TIMEOUT; add_timer(&sp->resync_t); } diff --git a/drivers/net/hamradio/baycom_par.c b/drivers/net/hamradio/baycom_par.c index e1783832d304..1f7ceafd61ff 100644 --- a/drivers/net/hamradio/baycom_par.c +++ b/drivers/net/hamradio/baycom_par.c @@ -311,7 +311,9 @@ static void par96_wakeup(void *handle) static int par96_open(struct net_device *dev) { struct baycom_state *bc = netdev_priv(dev); + struct pardev_cb par_cb; struct parport *pp; + int i; if (!dev || !bc) return -ENXIO; @@ -332,8 +334,21 @@ static int par96_open(struct net_device *dev) } memset(&bc->modem, 0, sizeof(bc->modem)); bc->hdrv.par.bitrate = 9600; - bc->pdev = parport_register_device(pp, dev->name, NULL, par96_wakeup, - par96_interrupt, PARPORT_DEV_EXCL, dev); + memset(&par_cb, 0, sizeof(par_cb)); + par_cb.wakeup = par96_wakeup; + par_cb.irq_func = par96_interrupt; + par_cb.private = (void *)dev; + par_cb.flags = PARPORT_DEV_EXCL; + for (i = 0; i < NR_PORTS; i++) + if (baycom_device[i] == dev) + break; + + if (i == NR_PORTS) { + pr_err("%s: no device found\n", bc_drvname); + parport_put_port(pp); + return -ENODEV; + } + bc->pdev = parport_register_dev_model(pp, dev->name, &par_cb, i); parport_put_port(pp); if (!bc->pdev) { printk(KERN_ERR "baycom_par: cannot register parport at 0x%lx\n", dev->base_addr); @@ -490,12 +505,34 @@ MODULE_LICENSE("GPL"); /* --------------------------------------------------------------------- */ +static int baycom_par_probe(struct pardevice *par_dev) +{ + struct device_driver *drv = par_dev->dev.driver; + int len = strlen(drv->name); + + if (strncmp(par_dev->name, drv->name, len)) + return -ENODEV; + + return 0; +} + +static struct parport_driver baycom_par_driver = { + .name = "bcp", + .probe = baycom_par_probe, + .devmodel = true, +}; + static int __init init_baycompar(void) { - int i, found = 0; + int i, found = 0, ret; char set_hw = 1; printk(bc_drvinfo); + + ret = parport_register_driver(&baycom_par_driver); + if (ret) + return ret; + /* * register net devices */ @@ -524,8 +561,10 @@ static int __init init_baycompar(void) baycom_device[i] = dev; } - if (!found) + if (!found) { + parport_unregister_driver(&baycom_par_driver); return -ENXIO; + } return 0; } @@ -539,6 +578,7 @@ static void __exit cleanup_baycompar(void) if (dev) hdlcdrv_unregister(dev); } + parport_unregister_driver(&baycom_par_driver); } module_init(init_baycompar); diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c index 295f267b73ea..c9f7215c5dc2 100644 --- a/drivers/net/hamradio/scc.c +++ b/drivers/net/hamradio/scc.c @@ -185,14 +185,15 @@ static const char banner[] __initconst = KERN_INFO \ "AX.25: Z8530 SCC driver version "VERSION".dl1bke\n"; -static void t_dwait(unsigned long); -static void t_txdelay(unsigned long); -static void t_tail(unsigned long); -static void t_busy(unsigned long); -static void t_maxkeyup(unsigned long); -static void t_idle(unsigned long); +static void t_dwait(struct timer_list *t); +static void t_txdelay(struct timer_list *t); +static void t_tail(struct timer_list *t); +static void t_busy(struct timer_list *); +static void t_maxkeyup(struct timer_list *); +static void t_idle(struct timer_list *t); static void scc_tx_done(struct scc_channel *); -static void scc_start_tx_timer(struct scc_channel *, void (*)(unsigned long), unsigned long); +static void scc_start_tx_timer(struct scc_channel *, + void (*)(struct timer_list *), unsigned long); static void scc_start_maxkeyup(struct scc_channel *); static void scc_start_defer(struct scc_channel *); @@ -992,24 +993,27 @@ static void scc_key_trx(struct scc_channel *scc, char tx) /* ----> SCC timer interrupt handler and friends. <---- */ -static void __scc_start_tx_timer(struct scc_channel *scc, void (*handler)(unsigned long), unsigned long when) +static void __scc_start_tx_timer(struct scc_channel *scc, + void (*handler)(struct timer_list *t), + unsigned long when) { del_timer(&scc->tx_t); if (when == 0) { - handler((unsigned long) scc); + handler(&scc->tx_t); } else if (when != TIMER_OFF) { - scc->tx_t.data = (unsigned long) scc; - scc->tx_t.function = handler; + scc->tx_t.function = (TIMER_FUNC_TYPE)handler; scc->tx_t.expires = jiffies + (when*HZ)/100; add_timer(&scc->tx_t); } } -static void scc_start_tx_timer(struct scc_channel *scc, void (*handler)(unsigned long), unsigned long when) +static void scc_start_tx_timer(struct scc_channel *scc, + void (*handler)(struct timer_list *t), + unsigned long when) { unsigned long flags; @@ -1027,8 +1031,7 @@ static void scc_start_defer(struct scc_channel *scc) if (scc->kiss.maxdefer != 0 && scc->kiss.maxdefer != TIMER_OFF) { - scc->tx_wdog.data = (unsigned long) scc; - scc->tx_wdog.function = t_busy; + scc->tx_wdog.function = (TIMER_FUNC_TYPE)t_busy; scc->tx_wdog.expires = jiffies + HZ*scc->kiss.maxdefer; add_timer(&scc->tx_wdog); } @@ -1044,8 +1047,7 @@ static void scc_start_maxkeyup(struct scc_channel *scc) if (scc->kiss.maxkeyup != 0 && scc->kiss.maxkeyup != TIMER_OFF) { - scc->tx_wdog.data = (unsigned long) scc; - scc->tx_wdog.function = t_maxkeyup; + scc->tx_wdog.function = (TIMER_FUNC_TYPE)t_maxkeyup; scc->tx_wdog.expires = jiffies + HZ*scc->kiss.maxkeyup; add_timer(&scc->tx_wdog); } @@ -1121,9 +1123,9 @@ static inline int is_grouped(struct scc_channel *scc) * fulldup == 2: mintime expired, reset status or key trx and start txdelay */ -static void t_dwait(unsigned long channel) +static void t_dwait(struct timer_list *t) { - struct scc_channel *scc = (struct scc_channel *) channel; + struct scc_channel *scc = from_timer(scc, t, tx_t); if (scc->stat.tx_state == TXS_WAIT) /* maxkeyup or idle timeout */ { @@ -1163,9 +1165,9 @@ static void t_dwait(unsigned long channel) * kick transmission by a fake scc_txint(scc), start 'maxkeyup' watchdog. */ -static void t_txdelay(unsigned long channel) +static void t_txdelay(struct timer_list *t) { - struct scc_channel *scc = (struct scc_channel *) channel; + struct scc_channel *scc = from_timer(scc, t, tx_t); scc_start_maxkeyup(scc); @@ -1184,9 +1186,9 @@ static void t_txdelay(unsigned long channel) * transmission after 'mintime' seconds */ -static void t_tail(unsigned long channel) +static void t_tail(struct timer_list *t) { - struct scc_channel *scc = (struct scc_channel *) channel; + struct scc_channel *scc = from_timer(scc, t, tx_t); unsigned long flags; spin_lock_irqsave(&scc->lock, flags); @@ -1211,9 +1213,9 @@ static void t_tail(unsigned long channel) * throw away send buffers if DCD remains active too long. */ -static void t_busy(unsigned long channel) +static void t_busy(struct timer_list *t) { - struct scc_channel *scc = (struct scc_channel *) channel; + struct scc_channel *scc = from_timer(scc, t, tx_wdog); del_timer(&scc->tx_t); netif_stop_queue(scc->dev); /* don't pile on the wabbit! */ @@ -1230,9 +1232,9 @@ static void t_busy(unsigned long channel) * this is our watchdog. */ -static void t_maxkeyup(unsigned long channel) +static void t_maxkeyup(struct timer_list *t) { - struct scc_channel *scc = (struct scc_channel *) channel; + struct scc_channel *scc = from_timer(scc, t, tx_wdog); unsigned long flags; spin_lock_irqsave(&scc->lock, flags); @@ -1264,9 +1266,9 @@ static void t_maxkeyup(unsigned long channel) * expires. */ -static void t_idle(unsigned long channel) +static void t_idle(struct timer_list *t) { - struct scc_channel *scc = (struct scc_channel *) channel; + struct scc_channel *scc = from_timer(scc, t, tx_t); del_timer(&scc->tx_wdog); @@ -1397,9 +1399,9 @@ static unsigned long scc_get_param(struct scc_channel *scc, unsigned int cmd) /* * Send calibration pattern * */ /* ******************************************************************* */ -static void scc_stop_calibrate(unsigned long channel) +static void scc_stop_calibrate(struct timer_list *t) { - struct scc_channel *scc = (struct scc_channel *) channel; + struct scc_channel *scc = from_timer(scc, t, tx_wdog); unsigned long flags; spin_lock_irqsave(&scc->lock, flags); @@ -1426,8 +1428,7 @@ scc_start_calibrate(struct scc_channel *scc, int duration, unsigned char pattern del_timer(&scc->tx_wdog); - scc->tx_wdog.data = (unsigned long) scc; - scc->tx_wdog.function = scc_stop_calibrate; + scc->tx_wdog.function = (TIMER_FUNC_TYPE)scc_stop_calibrate; scc->tx_wdog.expires = jiffies + HZ*duration; add_timer(&scc->tx_wdog); @@ -1522,8 +1523,8 @@ static int scc_net_alloc(const char *name, struct scc_channel *scc) dev->ml_priv = scc; scc->dev = dev; spin_lock_init(&scc->lock); - init_timer(&scc->tx_t); - init_timer(&scc->tx_wdog); + timer_setup(&scc->tx_t, NULL, 0); + timer_setup(&scc->tx_wdog, NULL, 0); err = register_netdevice(dev); if (err) { diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 6f550e15a41c..4958bb6b7376 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -179,7 +179,7 @@ struct rndis_device { u8 hw_mac_adr[ETH_ALEN]; u8 rss_key[NETVSC_HASH_KEYLEN]; - u16 ind_table[ITAB_NUM]; + u16 rx_table[ITAB_NUM]; }; @@ -704,6 +704,14 @@ struct netvsc_reconfig { u32 event; }; +/* L4 hash bits for different protocols */ +#define HV_TCP4_L4HASH 1 +#define HV_TCP6_L4HASH 2 +#define HV_UDP4_L4HASH 4 +#define HV_UDP6_L4HASH 8 +#define HV_DEFAULT_L4HASH (HV_TCP4_L4HASH | HV_TCP6_L4HASH | HV_UDP4_L4HASH | \ + HV_UDP6_L4HASH) + /* The context of the netvsc device */ struct net_device_context { /* point back to our device context */ @@ -723,13 +731,12 @@ struct net_device_context { u32 tx_checksum_mask; - u32 tx_send_table[VRSS_SEND_TAB_SIZE]; + u32 tx_table[VRSS_SEND_TAB_SIZE]; /* Ethtool settings */ - bool udp4_l4_hash; - bool udp6_l4_hash; u8 duplex; u32 speed; + u32 l4_hash; /* L4 hash settings */ struct netvsc_ethtool_stats eth_stats; /* State to manage the associated VF interface. */ diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 6e5194916bbe..5bb6a20072dd 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1110,7 +1110,7 @@ static void netvsc_send_table(struct hv_device *hdev, nvmsg->msg.v5_msg.send_table.offset); for (i = 0; i < count; i++) - net_device_ctx->tx_send_table[i] = tab[i]; + net_device_ctx->tx_table[i] = tab[i]; } static void netvsc_send_vf(struct net_device_context *net_device_ctx, @@ -1255,6 +1255,9 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device, if (!net_device) return ERR_PTR(-ENOMEM); + for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) + net_device_ctx->tx_table[i] = 0; + net_device->ring_size = ring_size; /* Because the device uses NAPI, all the interrupt batching and diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index dfb986421ec6..da216ca4f2b2 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -203,7 +203,7 @@ static inline u32 netvsc_get_hash( const struct net_device_context *ndc) { struct flow_keys flow; - u32 hash; + u32 hash, pkt_proto = 0; static u32 hashrnd __read_mostly; net_get_random_once(&hashrnd, sizeof(hashrnd)); @@ -211,11 +211,25 @@ static inline u32 netvsc_get_hash( if (!skb_flow_dissect_flow_keys(skb, &flow, 0)) return 0; - if (flow.basic.ip_proto == IPPROTO_TCP || - (flow.basic.ip_proto == IPPROTO_UDP && - ((flow.basic.n_proto == htons(ETH_P_IP) && ndc->udp4_l4_hash) || - (flow.basic.n_proto == htons(ETH_P_IPV6) && - ndc->udp6_l4_hash)))) { + switch (flow.basic.ip_proto) { + case IPPROTO_TCP: + if (flow.basic.n_proto == htons(ETH_P_IP)) + pkt_proto = HV_TCP4_L4HASH; + else if (flow.basic.n_proto == htons(ETH_P_IPV6)) + pkt_proto = HV_TCP6_L4HASH; + + break; + + case IPPROTO_UDP: + if (flow.basic.n_proto == htons(ETH_P_IP)) + pkt_proto = HV_UDP4_L4HASH; + else if (flow.basic.n_proto == htons(ETH_P_IPV6)) + pkt_proto = HV_UDP6_L4HASH; + + break; + } + + if (pkt_proto & ndc->l4_hash) { return skb_get_hash(skb); } else { if (flow.basic.n_proto == htons(ETH_P_IP)) @@ -238,8 +252,8 @@ static inline int netvsc_get_tx_queue(struct net_device *ndev, struct sock *sk = skb->sk; int q_idx; - q_idx = ndc->tx_send_table[netvsc_get_hash(skb, ndc) & - (VRSS_SEND_TAB_SIZE - 1)]; + q_idx = ndc->tx_table[netvsc_get_hash(skb, ndc) & + (VRSS_SEND_TAB_SIZE - 1)]; /* If queue index changed record the new value */ if (q_idx != old_idx && @@ -898,8 +912,7 @@ static void netvsc_init_settings(struct net_device *dev) { struct net_device_context *ndc = netdev_priv(dev); - ndc->udp4_l4_hash = true; - ndc->udp6_l4_hash = true; + ndc->l4_hash = HV_DEFAULT_L4HASH; ndc->speed = SPEED_UNKNOWN; ndc->duplex = DUPLEX_FULL; @@ -1245,23 +1258,32 @@ static int netvsc_get_rss_hash_opts(struct net_device_context *ndc, struct ethtool_rxnfc *info) { + const u32 l4_flag = RXH_L4_B_0_1 | RXH_L4_B_2_3; + info->data = RXH_IP_SRC | RXH_IP_DST; switch (info->flow_type) { case TCP_V4_FLOW: + if (ndc->l4_hash & HV_TCP4_L4HASH) + info->data |= l4_flag; + + break; + case TCP_V6_FLOW: - info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + if (ndc->l4_hash & HV_TCP6_L4HASH) + info->data |= l4_flag; + break; case UDP_V4_FLOW: - if (ndc->udp4_l4_hash) - info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + if (ndc->l4_hash & HV_UDP4_L4HASH) + info->data |= l4_flag; break; case UDP_V6_FLOW: - if (ndc->udp6_l4_hash) - info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + if (ndc->l4_hash & HV_UDP6_L4HASH) + info->data |= l4_flag; break; @@ -1302,23 +1324,51 @@ static int netvsc_set_rss_hash_opts(struct net_device_context *ndc, { if (info->data == (RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3)) { - if (info->flow_type == UDP_V4_FLOW) - ndc->udp4_l4_hash = true; - else if (info->flow_type == UDP_V6_FLOW) - ndc->udp6_l4_hash = true; - else + switch (info->flow_type) { + case TCP_V4_FLOW: + ndc->l4_hash |= HV_TCP4_L4HASH; + break; + + case TCP_V6_FLOW: + ndc->l4_hash |= HV_TCP6_L4HASH; + break; + + case UDP_V4_FLOW: + ndc->l4_hash |= HV_UDP4_L4HASH; + break; + + case UDP_V6_FLOW: + ndc->l4_hash |= HV_UDP6_L4HASH; + break; + + default: return -EOPNOTSUPP; + } return 0; } if (info->data == (RXH_IP_SRC | RXH_IP_DST)) { - if (info->flow_type == UDP_V4_FLOW) - ndc->udp4_l4_hash = false; - else if (info->flow_type == UDP_V6_FLOW) - ndc->udp6_l4_hash = false; - else + switch (info->flow_type) { + case TCP_V4_FLOW: + ndc->l4_hash &= ~HV_TCP4_L4HASH; + break; + + case TCP_V6_FLOW: + ndc->l4_hash &= ~HV_TCP6_L4HASH; + break; + + case UDP_V4_FLOW: + ndc->l4_hash &= ~HV_UDP4_L4HASH; + break; + + case UDP_V6_FLOW: + ndc->l4_hash &= ~HV_UDP6_L4HASH; + break; + + default: return -EOPNOTSUPP; + } return 0; } @@ -1384,7 +1434,7 @@ static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, rndis_dev = ndev->extension; if (indir) { for (i = 0; i < ITAB_NUM; i++) - indir[i] = rndis_dev->ind_table[i]; + indir[i] = rndis_dev->rx_table[i]; } if (key) @@ -1414,7 +1464,7 @@ static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir, return -EINVAL; for (i = 0; i < ITAB_NUM; i++) - rndis_dev->ind_table[i] = indir[i]; + rndis_dev->rx_table[i] = indir[i]; } if (!key) { diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 065b204d8e17..addf9f69c58c 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -759,7 +759,7 @@ int rndis_filter_set_rss_param(struct rndis_device *rdev, /* Set indirection table entries */ itab = (u32 *)(rssp + 1); for (i = 0; i < ITAB_NUM; i++) - itab[i] = rdev->ind_table[i]; + itab[i] = rdev->rx_table[i]; /* Set hask key values */ keyp = (u8 *)((unsigned long)rssp + rssp->kashkey_offset); @@ -1284,8 +1284,8 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, net_device->num_chn = min(net_device->max_chn, device_info->num_chn); for (i = 0; i < ITAB_NUM; i++) - rndis_device->ind_table[i] = ethtool_rxfh_indir_default(i, - net_device->num_chn); + rndis_device->rx_table[i] = ethtool_rxfh_indir_default( + i, net_device->num_chn); atomic_set(&net_device->open_chn, 1); vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open); diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c index 115fa3f37a86..d5584063049f 100644 --- a/drivers/net/ieee802154/atusb.c +++ b/drivers/net/ieee802154/atusb.c @@ -45,8 +45,6 @@ #define ATUSB_ALLOC_DELAY_MS 100 /* delay after failed allocation */ #define ATUSB_TX_TIMEOUT_MS 200 /* on the air timeout */ -struct atusb_chip_data; - struct atusb { struct ieee802154_hw *hw; struct usb_device *usb_dev; @@ -767,14 +765,14 @@ atusb_set_promiscuous_mode(struct ieee802154_hw *hw, const bool on) return 0; } -struct atusb_chip_data atusb_chip_data = { +static struct atusb_chip_data atusb_chip_data = { .t_channel_switch = 1, .rssi_base_val = -91, .set_txpower = atusb_set_txpower, .set_channel = atusb_set_channel, }; -struct atusb_chip_data hulusb_chip_data = { +static struct atusb_chip_data hulusb_chip_data = { .t_channel_switch = 11, .rssi_base_val = -100, .set_txpower = hulusb_set_txpower, @@ -1060,7 +1058,7 @@ static int atusb_probe(struct usb_interface *interface, atusb_get_and_show_build(atusb); atusb_set_extended_addr(atusb); - if (atusb->fw_ver_maj >= 0 && atusb->fw_ver_min >= 3) + if ((atusb->fw_ver_maj == 0 && atusb->fw_ver_min >= 3) || atusb->fw_ver_maj > 0) hw->flags |= IEEE802154_HW_FRAME_RETRIES; ret = atusb_get_and_clear_error(atusb); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 57c3856bab05..f0ab55df57f1 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -407,7 +407,7 @@ static int ipvlan_hard_header(struct sk_buff *skb, struct net_device *dev, * while the packets use the mac-addr on the physical device. */ return dev_hard_header(skb, phy_dev, type, daddr, - saddr ? : dev->dev_addr, len); + saddr ? : phy_dev->dev_addr, len); } static const struct header_ops ipvlan_header_ops = { @@ -730,6 +730,11 @@ static int ipvlan_device_event(struct notifier_block *unused, ipvlan_adjust_mtu(ipvlan, dev); break; + case NETDEV_CHANGEADDR: + list_for_each_entry(ipvlan, &port->ipvlans, pnode) + ether_addr_copy(ipvlan->dev->dev_addr, dev->dev_addr); + break; + case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; @@ -803,10 +808,6 @@ static int ipvlan_addr6_event(struct notifier_block *unused, struct net_device *dev = (struct net_device *)if6->idev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); - /* FIXME IPv6 autoconf calls us from bh without RTNL */ - if (in_softirq()) - return NOTIFY_DONE; - if (!netif_is_ipvlan(dev)) return NOTIFY_DONE; @@ -846,8 +847,11 @@ static int ipvlan_addr6_validator_event(struct notifier_block *unused, switch (event) { case NETDEV_UP: - if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true)) + if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true)) { + NL_SET_ERR_MSG(i6vi->extack, + "Address already assigned to an ipvlan device"); return notifier_from_errno(-EADDRINUSE); + } break; } @@ -916,8 +920,11 @@ static int ipvlan_addr4_validator_event(struct notifier_block *unused, switch (event) { case NETDEV_UP: - if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false)) + if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false)) { + NL_SET_ERR_MSG(ivi->extack, + "Address already assigned to an ipvlan device"); return notifier_from_errno(-EADDRINUSE); + } break; } diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 858bd66511a2..a178c5efd33e 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -413,7 +413,9 @@ static void macvlan_forward_source_one(struct sk_buff *skb, len = nskb->len + ETH_HLEN; nskb->dev = dev; - nskb->pkt_type = PACKET_HOST; + + if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, dev->dev_addr)) + nskb->pkt_type = PACKET_HOST; ret = netif_rx(nskb); macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false); @@ -480,7 +482,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) struct macvlan_dev, list); else vlan = macvlan_hash_lookup(port, eth->h_dest); - if (vlan == NULL) + if (!vlan || vlan->mode == MACVLAN_MODE_SOURCE) return RX_HANDLER_PASS; dev = vlan->dev; @@ -596,8 +598,6 @@ static const struct header_ops macvlan_hard_header_ops = { .cache_update = eth_header_cache_update, }; -static struct rtnl_link_ops macvlan_link_ops; - static int macvlan_open(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); @@ -613,8 +613,7 @@ static int macvlan_open(struct net_device *dev) goto hash_add; } - if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD && - dev->rtnl_link_ops == &macvlan_link_ops) { + if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) { vlan->fwd_priv = lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev); diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index cd931cf9dcc2..8125412c8814 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -277,6 +277,11 @@ config DAVICOM_PHY ---help--- Currently supports dm9161e and dm9131 +config DP83822_PHY + tristate "Texas Instruments DP83822 PHY" + ---help--- + Supports the DP83822 PHY. + config DP83848_PHY tristate "Texas Instruments DP83848 PHY" ---help--- @@ -366,6 +371,11 @@ config REALTEK_PHY ---help--- Supports the Realtek 821x PHY. +config RENESAS_PHY + tristate "Driver for Renesas PHYs" + ---help--- + Supports the Renesas PHYs uPD60620 and uPD60620A. + config ROCKCHIP_PHY tristate "Driver for Rockchip Ethernet PHYs" ---help--- diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 416df92fbf4f..4b983be83566 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -55,6 +55,7 @@ obj-$(CONFIG_CICADA_PHY) += cicada.o obj-$(CONFIG_CORTINA_PHY) += cortina.o obj-$(CONFIG_DAVICOM_PHY) += davicom.o obj-$(CONFIG_DP83640_PHY) += dp83640.o +obj-$(CONFIG_DP83822_PHY) += dp83822.o obj-$(CONFIG_DP83848_PHY) += dp83848.o obj-$(CONFIG_DP83867_PHY) += dp83867.o obj-$(CONFIG_FIXED_PHY) += fixed_phy.o @@ -72,6 +73,7 @@ obj-$(CONFIG_MICROSEMI_PHY) += mscc.o obj-$(CONFIG_NATIONAL_PHY) += national.o obj-$(CONFIG_QSEMI_PHY) += qsemi.o obj-$(CONFIG_REALTEK_PHY) += realtek.o +obj-$(CONFIG_RENESAS_PHY) += uPD60620.o obj-$(CONFIG_ROCKCHIP_PHY) += rockchip.o obj-$(CONFIG_SMSC_PHY) += smsc.o obj-$(CONFIG_STE10XP) += ste10Xp.o diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index c1e52b9dc58d..5f93e6add563 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -167,7 +167,7 @@ static int at803x_set_wol(struct phy_device *phydev, mac = (const u8 *) ndev->dev_addr; if (!is_valid_ether_addr(mac)) - return -EFAULT; + return -EINVAL; for (i = 0; i < 3; i++) { phy_write(phydev, AT803X_MMD_ACCESS_CONTROL, diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 1e9ad30a35c8..d7ed69deabfb 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -43,6 +43,12 @@ static int bcm54210e_config_init(struct phy_device *phydev) val &= ~BCM54810_SHD_CLK_CTL_GTXCLK_EN; bcm_phy_write_shadow(phydev, BCM54810_SHD_CLK_CTL, val); + if (phydev->dev_flags & PHY_BRCM_EN_MASTER_MODE) { + val = phy_read(phydev, MII_CTRL1000); + val |= CTL1000_AS_MASTER | CTL1000_ENABLE_MASTER; + phy_write(phydev, MII_CTRL1000, val); + } + return 0; } diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c new file mode 100644 index 000000000000..14335d14e9e4 --- /dev/null +++ b/drivers/net/phy/dp83822.c @@ -0,0 +1,344 @@ +/* + * Driver for the Texas Instruments DP83822 PHY + * + * Copyright (C) 2017 Texas Instruments Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/ethtool.h> +#include <linux/etherdevice.h> +#include <linux/kernel.h> +#include <linux/mii.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/phy.h> +#include <linux/netdevice.h> + +#define DP83822_PHY_ID 0x2000a240 +#define DP83822_DEVADDR 0x1f + +#define MII_DP83822_PHYSCR 0x11 +#define MII_DP83822_MISR1 0x12 +#define MII_DP83822_MISR2 0x13 +#define MII_DP83822_RESET_CTRL 0x1f + +#define DP83822_HW_RESET BIT(15) +#define DP83822_SW_RESET BIT(14) + +/* PHYSCR Register Fields */ +#define DP83822_PHYSCR_INT_OE BIT(0) /* Interrupt Output Enable */ +#define DP83822_PHYSCR_INTEN BIT(1) /* Interrupt Enable */ + +/* MISR1 bits */ +#define DP83822_RX_ERR_HF_INT_EN BIT(0) +#define DP83822_FALSE_CARRIER_HF_INT_EN BIT(1) +#define DP83822_ANEG_COMPLETE_INT_EN BIT(2) +#define DP83822_DUP_MODE_CHANGE_INT_EN BIT(3) +#define DP83822_SPEED_CHANGED_INT_EN BIT(4) +#define DP83822_LINK_STAT_INT_EN BIT(5) +#define DP83822_ENERGY_DET_INT_EN BIT(6) +#define DP83822_LINK_QUAL_INT_EN BIT(7) + +/* MISR2 bits */ +#define DP83822_JABBER_DET_INT_EN BIT(0) +#define DP83822_WOL_PKT_INT_EN BIT(1) +#define DP83822_SLEEP_MODE_INT_EN BIT(2) +#define DP83822_MDI_XOVER_INT_EN BIT(3) +#define DP83822_LB_FIFO_INT_EN BIT(4) +#define DP83822_PAGE_RX_INT_EN BIT(5) +#define DP83822_ANEG_ERR_INT_EN BIT(6) +#define DP83822_EEE_ERROR_CHANGE_INT_EN BIT(7) + +/* INT_STAT1 bits */ +#define DP83822_WOL_INT_EN BIT(4) +#define DP83822_WOL_INT_STAT BIT(12) + +#define MII_DP83822_RXSOP1 0x04a5 +#define MII_DP83822_RXSOP2 0x04a6 +#define MII_DP83822_RXSOP3 0x04a7 + +/* WoL Registers */ +#define MII_DP83822_WOL_CFG 0x04a0 +#define MII_DP83822_WOL_STAT 0x04a1 +#define MII_DP83822_WOL_DA1 0x04a2 +#define MII_DP83822_WOL_DA2 0x04a3 +#define MII_DP83822_WOL_DA3 0x04a4 + +/* WoL bits */ +#define DP83822_WOL_MAGIC_EN BIT(0) +#define DP83822_WOL_SECURE_ON BIT(5) +#define DP83822_WOL_EN BIT(7) +#define DP83822_WOL_INDICATION_SEL BIT(8) +#define DP83822_WOL_CLR_INDICATION BIT(11) + +static int dp83822_ack_interrupt(struct phy_device *phydev) +{ + int err; + + err = phy_read(phydev, MII_DP83822_MISR1); + if (err < 0) + return err; + + err = phy_read(phydev, MII_DP83822_MISR2); + if (err < 0) + return err; + + return 0; +} + +static int dp83822_set_wol(struct phy_device *phydev, + struct ethtool_wolinfo *wol) +{ + struct net_device *ndev = phydev->attached_dev; + u16 value; + const u8 *mac; + + if (wol->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) { + mac = (const u8 *)ndev->dev_addr; + + if (!is_valid_ether_addr(mac)) + return -EINVAL; + + /* MAC addresses start with byte 5, but stored in mac[0]. + * 822 PHYs store bytes 4|5, 2|3, 0|1 + */ + phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_DA1, + (mac[1] << 8) | mac[0]); + phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_DA2, + (mac[3] << 8) | mac[2]); + phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_DA3, + (mac[5] << 8) | mac[4]); + + value = phy_read_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_WOL_CFG); + if (wol->wolopts & WAKE_MAGIC) + value |= DP83822_WOL_MAGIC_EN; + else + value &= ~DP83822_WOL_MAGIC_EN; + + if (wol->wolopts & WAKE_MAGICSECURE) { + phy_write_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RXSOP1, + (wol->sopass[1] << 8) | wol->sopass[0]); + phy_write_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RXSOP2, + (wol->sopass[3] << 8) | wol->sopass[2]); + phy_write_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RXSOP3, + (wol->sopass[5] << 8) | wol->sopass[4]); + value |= DP83822_WOL_SECURE_ON; + } else { + value &= ~DP83822_WOL_SECURE_ON; + } + + value |= (DP83822_WOL_EN | DP83822_WOL_INDICATION_SEL | + DP83822_WOL_CLR_INDICATION); + phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, + value); + } else { + value = phy_read_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_WOL_CFG); + value &= ~DP83822_WOL_EN; + phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, + value); + } + + return 0; +} + +static void dp83822_get_wol(struct phy_device *phydev, + struct ethtool_wolinfo *wol) +{ + int value; + u16 sopass_val; + + wol->supported = (WAKE_MAGIC | WAKE_MAGICSECURE); + wol->wolopts = 0; + + value = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG); + + if (value & DP83822_WOL_MAGIC_EN) + wol->wolopts |= WAKE_MAGIC; + + if (value & DP83822_WOL_SECURE_ON) { + sopass_val = phy_read_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RXSOP1); + wol->sopass[0] = (sopass_val & 0xff); + wol->sopass[1] = (sopass_val >> 8); + + sopass_val = phy_read_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RXSOP2); + wol->sopass[2] = (sopass_val & 0xff); + wol->sopass[3] = (sopass_val >> 8); + + sopass_val = phy_read_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RXSOP3); + wol->sopass[4] = (sopass_val & 0xff); + wol->sopass[5] = (sopass_val >> 8); + + wol->wolopts |= WAKE_MAGICSECURE; + } + + /* WoL is not enabled so set wolopts to 0 */ + if (!(value & DP83822_WOL_EN)) + wol->wolopts = 0; +} + +static int dp83822_config_intr(struct phy_device *phydev) +{ + int misr_status; + int physcr_status; + int err; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + misr_status = phy_read(phydev, MII_DP83822_MISR1); + if (misr_status < 0) + return misr_status; + + misr_status |= (DP83822_RX_ERR_HF_INT_EN | + DP83822_FALSE_CARRIER_HF_INT_EN | + DP83822_ANEG_COMPLETE_INT_EN | + DP83822_DUP_MODE_CHANGE_INT_EN | + DP83822_SPEED_CHANGED_INT_EN | + DP83822_LINK_STAT_INT_EN | + DP83822_ENERGY_DET_INT_EN | + DP83822_LINK_QUAL_INT_EN); + + err = phy_write(phydev, MII_DP83822_MISR1, misr_status); + if (err < 0) + return err; + + misr_status = phy_read(phydev, MII_DP83822_MISR2); + if (misr_status < 0) + return misr_status; + + misr_status |= (DP83822_JABBER_DET_INT_EN | + DP83822_WOL_PKT_INT_EN | + DP83822_SLEEP_MODE_INT_EN | + DP83822_MDI_XOVER_INT_EN | + DP83822_LB_FIFO_INT_EN | + DP83822_PAGE_RX_INT_EN | + DP83822_ANEG_ERR_INT_EN | + DP83822_EEE_ERROR_CHANGE_INT_EN); + + err = phy_write(phydev, MII_DP83822_MISR2, misr_status); + if (err < 0) + return err; + + physcr_status = phy_read(phydev, MII_DP83822_PHYSCR); + if (physcr_status < 0) + return physcr_status; + + physcr_status |= DP83822_PHYSCR_INT_OE | DP83822_PHYSCR_INTEN; + + } else { + err = phy_write(phydev, MII_DP83822_MISR1, 0); + if (err < 0) + return err; + + err = phy_write(phydev, MII_DP83822_MISR1, 0); + if (err < 0) + return err; + + physcr_status = phy_read(phydev, MII_DP83822_PHYSCR); + if (physcr_status < 0) + return physcr_status; + + physcr_status &= ~DP83822_PHYSCR_INTEN; + } + + return phy_write(phydev, MII_DP83822_PHYSCR, physcr_status); +} + +static int dp83822_config_init(struct phy_device *phydev) +{ + int err; + int value; + + err = genphy_config_init(phydev); + if (err < 0) + return err; + + value = DP83822_WOL_MAGIC_EN | DP83822_WOL_SECURE_ON | DP83822_WOL_EN; + + return phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, + value); +} + +static int dp83822_phy_reset(struct phy_device *phydev) +{ + int err; + + err = phy_write(phydev, MII_DP83822_RESET_CTRL, DP83822_HW_RESET); + if (err < 0) + return err; + + dp83822_config_init(phydev); + + return 0; +} + +static int dp83822_suspend(struct phy_device *phydev) +{ + int value; + + value = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG); + + if (!(value & DP83822_WOL_EN)) + genphy_suspend(phydev); + + return 0; +} + +static int dp83822_resume(struct phy_device *phydev) +{ + int value; + + genphy_resume(phydev); + + value = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG); + + phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, value | + DP83822_WOL_CLR_INDICATION); + + return 0; +} + +static struct phy_driver dp83822_driver[] = { + { + .phy_id = DP83822_PHY_ID, + .phy_id_mask = 0xfffffff0, + .name = "TI DP83822", + .features = PHY_BASIC_FEATURES, + .flags = PHY_HAS_INTERRUPT, + .config_init = dp83822_config_init, + .soft_reset = dp83822_phy_reset, + .get_wol = dp83822_get_wol, + .set_wol = dp83822_set_wol, + .ack_interrupt = dp83822_ack_interrupt, + .config_intr = dp83822_config_intr, + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + .suspend = dp83822_suspend, + .resume = dp83822_resume, + }, +}; +module_phy_driver(dp83822_driver); + +static struct mdio_device_id __maybe_unused dp83822_tbl[] = { + { DP83822_PHY_ID, 0xfffffff0 }, + { }, +}; +MODULE_DEVICE_TABLE(mdio, dp83822_tbl); + +MODULE_DESCRIPTION("Texas Instruments DP83822 PHY driver"); +MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c index 3de4fe4dda77..3966d43c5146 100644 --- a/drivers/net/phy/dp83848.c +++ b/drivers/net/phy/dp83848.c @@ -20,7 +20,6 @@ #define TI_DP83620_PHY_ID 0x20005ce0 #define NS_DP83848C_PHY_ID 0x20005c90 #define TLK10X_PHY_ID 0x2000a210 -#define TI_DP83822_PHY_ID 0x2000a240 /* Registers */ #define DP83848_MICR 0x11 /* MII Interrupt Control Register */ @@ -80,7 +79,6 @@ static struct mdio_device_id __maybe_unused dp83848_tbl[] = { { NS_DP83848C_PHY_ID, 0xfffffff0 }, { TI_DP83620_PHY_ID, 0xfffffff0 }, { TLK10X_PHY_ID, 0xfffffff0 }, - { TI_DP83822_PHY_ID, 0xfffffff0 }, { } }; MODULE_DEVICE_TABLE(mdio, dp83848_tbl); @@ -110,7 +108,6 @@ static struct phy_driver dp83848_driver[] = { DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY"), DP83848_PHY_DRIVER(TI_DP83620_PHY_ID, "TI DP83620 10/100 Mbps PHY"), DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY"), - DP83848_PHY_DRIVER(TI_DP83822_PHY_ID, "TI DP83822 10/100 Mbps PHY"), }; module_phy_driver(dp83848_driver); diff --git a/drivers/net/phy/uPD60620.c b/drivers/net/phy/uPD60620.c new file mode 100644 index 000000000000..96b33475ea5e --- /dev/null +++ b/drivers/net/phy/uPD60620.c @@ -0,0 +1,109 @@ +/* + * Driver for the Renesas PHY uPD60620. + * + * Copyright (C) 2015 Softing Industrial Automation GmbH + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/phy.h> + +#define UPD60620_PHY_ID 0xb8242824 + +/* Extended Registers and values */ +/* PHY Special Control/Status */ +#define PHY_PHYSCR 0x1F /* PHY.31 */ +#define PHY_PHYSCR_10MB 0x0004 /* PHY speed = 10mb */ +#define PHY_PHYSCR_100MB 0x0008 /* PHY speed = 100mb */ +#define PHY_PHYSCR_DUPLEX 0x0010 /* PHY Duplex */ + +/* PHY Special Modes */ +#define PHY_SPM 0x12 /* PHY.18 */ + +/* Init PHY */ + +static int upd60620_config_init(struct phy_device *phydev) +{ + /* Enable support for passive HUBs (could be a strap option) */ + /* PHYMODE: All speeds, HD in parallel detect */ + return phy_write(phydev, PHY_SPM, 0x0180 | phydev->mdio.addr); +} + +/* Get PHY status from common registers */ + +static int upd60620_read_status(struct phy_device *phydev) +{ + int phy_state; + + /* Read negotiated state */ + phy_state = phy_read(phydev, MII_BMSR); + if (phy_state < 0) + return phy_state; + + phydev->link = 0; + phydev->lp_advertising = 0; + phydev->pause = 0; + phydev->asym_pause = 0; + + if (phy_state & (BMSR_ANEGCOMPLETE | BMSR_LSTATUS)) { + phy_state = phy_read(phydev, PHY_PHYSCR); + if (phy_state < 0) + return phy_state; + + if (phy_state & (PHY_PHYSCR_10MB | PHY_PHYSCR_100MB)) { + phydev->link = 1; + phydev->speed = SPEED_10; + phydev->duplex = DUPLEX_HALF; + + if (phy_state & PHY_PHYSCR_100MB) + phydev->speed = SPEED_100; + if (phy_state & PHY_PHYSCR_DUPLEX) + phydev->duplex = DUPLEX_FULL; + + phy_state = phy_read(phydev, MII_LPA); + if (phy_state < 0) + return phy_state; + + phydev->lp_advertising + = mii_lpa_to_ethtool_lpa_t(phy_state); + + if (phydev->duplex == DUPLEX_FULL) { + if (phy_state & LPA_PAUSE_CAP) + phydev->pause = 1; + if (phy_state & LPA_PAUSE_ASYM) + phydev->asym_pause = 1; + } + } + } + return 0; +} + +MODULE_DESCRIPTION("Renesas uPD60620 PHY driver"); +MODULE_AUTHOR("Bernd Edlinger <bernd.edlinger@hotmail.de>"); +MODULE_LICENSE("GPL"); + +static struct phy_driver upd60620_driver[1] = { { + .phy_id = UPD60620_PHY_ID, + .phy_id_mask = 0xfffffffe, + .name = "Renesas uPD60620", + .features = PHY_BASIC_FEATURES, + .flags = 0, + .config_init = upd60620_config_init, + .config_aneg = genphy_config_aneg, + .read_status = upd60620_read_status, +} }; + +module_phy_driver(upd60620_driver); + +static struct mdio_device_id __maybe_unused upd60620_tbl[] = { + { UPD60620_PHY_ID, 0xfffffffe }, + { } +}; + +MODULE_DEVICE_TABLE(mdio, upd60620_tbl); diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index c3f77e3b7819..e365866600ba 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1339,7 +1339,17 @@ ppp_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats64) static int ppp_dev_init(struct net_device *dev) { + struct ppp *ppp; + netdev_lockdep_set_classes(dev); + + ppp = netdev_priv(dev); + /* Let the netdevice take a reference on the ppp file. This ensures + * that ppp_destroy_interface() won't run before the device gets + * unregistered. + */ + atomic_inc(&ppp->file.refcnt); + return 0; } @@ -1362,6 +1372,15 @@ static void ppp_dev_uninit(struct net_device *dev) wake_up_interruptible(&ppp->file.rwait); } +static void ppp_dev_priv_destructor(struct net_device *dev) +{ + struct ppp *ppp; + + ppp = netdev_priv(dev); + if (atomic_dec_and_test(&ppp->file.refcnt)) + ppp_destroy_interface(ppp); +} + static const struct net_device_ops ppp_netdev_ops = { .ndo_init = ppp_dev_init, .ndo_uninit = ppp_dev_uninit, @@ -1387,6 +1406,7 @@ static void ppp_setup(struct net_device *dev) dev->tx_queue_len = 3; dev->type = ARPHRD_PPP; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; + dev->priv_destructor = ppp_dev_priv_destructor; netif_keep_dst(dev); } diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c index 1a7bc0bf4598..435854688a7a 100644 --- a/drivers/net/thunderbolt.c +++ b/drivers/net/thunderbolt.c @@ -394,7 +394,7 @@ static int tbnet_handle_packet(const void *buf, size_t size, void *data) struct tbnet *net = data; u32 command_id; int ret = 0; - u8 sequence; + u32 sequence; u64 route; /* Make sure the packet is for us */ diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 57e4c31fa84a..3b41c36eae90 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -175,6 +175,7 @@ struct tun_file { unsigned int ifindex; }; struct napi_struct napi; + bool napi_enabled; struct mutex napi_mutex; /* Protects access to the above napi */ struct list_head next; struct tun_struct *detached; @@ -276,6 +277,7 @@ static int tun_napi_poll(struct napi_struct *napi, int budget) static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile, bool napi_en) { + tfile->napi_enabled = napi_en; if (napi_en) { netif_napi_add(tun->dev, &tfile->napi, tun_napi_poll, NAPI_POLL_WEIGHT); @@ -286,13 +288,13 @@ static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile, static void tun_napi_disable(struct tun_struct *tun, struct tun_file *tfile) { - if (tun->flags & IFF_NAPI) + if (tfile->napi_enabled) napi_disable(&tfile->napi); } static void tun_napi_del(struct tun_struct *tun, struct tun_file *tfile) { - if (tun->flags & IFF_NAPI) + if (tfile->napi_enabled) netif_napi_del(&tfile->napi); } @@ -1055,7 +1057,8 @@ static void tun_poll_controller(struct net_device *dev) rcu_read_lock(); for (i = 0; i < tun->numqueues; i++) { tfile = rcu_dereference(tun->tfiles[i]); - napi_schedule(&tfile->napi); + if (tfile->napi_enabled) + napi_schedule(&tfile->napi); } rcu_read_unlock(); } @@ -1737,7 +1740,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, /* Exercise flow dissector code path. */ u32 headlen = eth_get_headlen(skb->data, skb_headlen(skb)); - if (headlen > skb_headlen(skb) || headlen < ETH_HLEN) { + if (unlikely(headlen > skb_headlen(skb))) { this_cpu_inc(tun->pcpu_stats->rx_dropped); napi_free_frags(&tfile->napi); mutex_unlock(&tfile->napi_mutex); @@ -1749,7 +1752,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, napi_gro_frags(&tfile->napi); local_bh_enable(); mutex_unlock(&tfile->napi_mutex); - } else if (tun->flags & IFF_NAPI) { + } else if (tfile->napi_enabled) { struct sk_buff_head *queue = &tfile->sk.sk_write_queue; int queue_len; diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index aeb62e17d19d..18d36dff97ea 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -611,9 +611,9 @@ static void catc_stats_done(struct catc *catc, struct ctrl_queue *q) catc->stats_vals[index >> 1] = data; } -static void catc_stats_timer(unsigned long data) +static void catc_stats_timer(struct timer_list *t) { - struct catc *catc = (void *) data; + struct catc *catc = from_timer(catc, t, timer); int i; for (i = 0; i < 8; i++) @@ -805,7 +805,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id spin_lock_init(&catc->tx_lock); spin_lock_init(&catc->ctrl_lock); - setup_timer(&catc->timer, catc_stats_timer, (long)catc); + timer_setup(&catc->timer, catc_stats_timer, 0); catc->ctrl_urb = usb_alloc_urb(0, GFP_KERNEL); catc->tx_urb = usb_alloc_urb(0, GFP_KERNEL); diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 29c7e2ec0dcb..52ea80bcd639 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -560,6 +560,7 @@ static const struct driver_info wwan_info = { #define NVIDIA_VENDOR_ID 0x0955 #define HP_VENDOR_ID 0x03f0 #define MICROSOFT_VENDOR_ID 0x045e +#define UBLOX_VENDOR_ID 0x1546 static const struct usb_device_id products[] = { /* BLACKLIST !! @@ -869,6 +870,18 @@ static const struct usb_device_id products[] = { USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&zte_cdc_info, }, { + /* U-blox TOBY-L2 */ + USB_DEVICE_AND_INTERFACE_INFO(UBLOX_VENDOR_ID, 0x1143, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, +}, { + /* U-blox SARA-U2 */ + USB_DEVICE_AND_INTERFACE_INFO(UBLOX_VENDOR_ID, 0x1104, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, +}, { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (unsigned long) &cdc_info, diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 0161f77641fa..94c7804903c4 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3516,11 +3516,9 @@ static const struct net_device_ops lan78xx_netdev_ops = { .ndo_vlan_rx_kill_vid = lan78xx_vlan_rx_kill_vid, }; -static void lan78xx_stat_monitor(unsigned long param) +static void lan78xx_stat_monitor(struct timer_list *t) { - struct lan78xx_net *dev; - - dev = (struct lan78xx_net *)param; + struct lan78xx_net *dev = from_timer(dev, t, stat_monitor); lan78xx_defer_kevent(dev, EVENT_STAT_UPDATE); } @@ -3571,10 +3569,8 @@ static int lan78xx_probe(struct usb_interface *intf, netdev->watchdog_timeo = TX_TIMEOUT_JIFFIES; netdev->ethtool_ops = &lan78xx_ethtool_ops; - dev->stat_monitor.function = lan78xx_stat_monitor; - dev->stat_monitor.data = (unsigned long)dev; dev->delta = 1; - init_timer(&dev->stat_monitor); + timer_setup(&dev->stat_monitor, lan78xx_stat_monitor, 0); mutex_init(&dev->stats.access_lock); diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c index 2110ab3513f0..c43087e06696 100644 --- a/drivers/net/usb/sierra_net.c +++ b/drivers/net/usb/sierra_net.c @@ -189,9 +189,6 @@ struct lsi_umts_dual { #define SIERRA_NET_LSI_UMTS_DS_STATUS_LEN \ (SIERRA_NET_LSI_UMTS_DS_LEN - SIERRA_NET_LSI_COMMON_LEN) -/* Forward definitions */ -static void sierra_sync_timer(unsigned long syncdata); - /* Our own net device operations structure */ static const struct net_device_ops sierra_net_device_ops = { .ndo_open = usbnet_open, @@ -475,8 +472,6 @@ static void sierra_net_dosync(struct usbnet *dev) "Send SYNC failed, status %d\n", status); /* Now, start a timer and make sure we get the Restart Indication */ - priv->sync_timer.function = sierra_sync_timer; - priv->sync_timer.data = (unsigned long) dev; priv->sync_timer.expires = jiffies + SIERRA_NET_SYNCDELAY; add_timer(&priv->sync_timer); } @@ -593,9 +588,10 @@ static void sierra_net_defer_kevent(struct usbnet *dev, int work) /* * Sync Retransmit Timer Handler. On expiry, kick the work queue */ -static void sierra_sync_timer(unsigned long syncdata) +static void sierra_sync_timer(struct timer_list *t) { - struct usbnet *dev = (struct usbnet *)syncdata; + struct sierra_net_data *priv = from_timer(priv, t, sync_timer); + struct usbnet *dev = priv->usbnet; dev_dbg(&dev->udev->dev, "%s", __func__); /* Kick the tasklet */ @@ -752,7 +748,7 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf) INIT_WORK(&priv->sierra_net_kevent, sierra_net_kevent); /* Only need to do this once */ - init_timer(&priv->sync_timer); + timer_setup(&priv->sync_timer, sierra_sync_timer, 0); /* verify fw attributes */ status = sierra_net_get_fw_attr(dev, &fwattr); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 6510e5cc1817..80348b6a8646 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1509,9 +1509,9 @@ err: // tasklet (work deferred from completions, in_irq) or timer -static void usbnet_bh (unsigned long param) +static void usbnet_bh (struct timer_list *t) { - struct usbnet *dev = (struct usbnet *) param; + struct usbnet *dev = from_timer(dev, t, delay); struct sk_buff *skb; struct skb_data *entry; @@ -1694,13 +1694,11 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) skb_queue_head_init (&dev->txq); skb_queue_head_init (&dev->done); skb_queue_head_init(&dev->rxq_pause); - dev->bh.func = usbnet_bh; - dev->bh.data = (unsigned long) dev; + dev->bh.func = (void (*)(unsigned long))usbnet_bh; + dev->bh.data = (unsigned long)&dev->delay; INIT_WORK (&dev->kevent, usbnet_deferred_kevent); init_usb_anchor(&dev->deferred); - dev->delay.function = usbnet_bh; - dev->delay.data = (unsigned long) dev; - init_timer (&dev->delay); + timer_setup(&dev->delay, usbnet_bh, 0); mutex_init (&dev->phy_mutex); mutex_init(&dev->interrupt_mutex); dev->interrupt_count = 0; diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c index c696d42f4502..320039d329c7 100644 --- a/drivers/net/wan/hdlc_cisco.c +++ b/drivers/net/wan/hdlc_cisco.c @@ -54,6 +54,7 @@ struct cisco_state { cisco_proto settings; struct timer_list timer; + struct net_device *dev; spinlock_t lock; unsigned long last_poll; int up; @@ -257,11 +258,10 @@ rx_error: -static void cisco_timer(unsigned long arg) +static void cisco_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)arg; - hdlc_device *hdlc = dev_to_hdlc(dev); - struct cisco_state *st = state(hdlc); + struct cisco_state *st = from_timer(st, t, timer); + struct net_device *dev = st->dev; spin_lock(&st->lock); if (st->up && @@ -276,8 +276,6 @@ static void cisco_timer(unsigned long arg) spin_unlock(&st->lock); st->timer.expires = jiffies + st->settings.interval * HZ; - st->timer.function = cisco_timer; - st->timer.data = arg; add_timer(&st->timer); } @@ -293,7 +291,8 @@ static void cisco_start(struct net_device *dev) st->up = st->txseq = st->rxseq = 0; spin_unlock_irqrestore(&st->lock, flags); - setup_timer(&st->timer, cisco_timer, (unsigned long)dev); + st->dev = dev; + timer_setup(&st->timer, cisco_timer, 0); st->timer.expires = jiffies + HZ; /* First poll after 1 s */ add_timer(&st->timer); } diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 425a47ffed25..038236a9c60e 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -140,6 +140,7 @@ struct frad_state { int dce_pvc_count; struct timer_list timer; + struct net_device *dev; unsigned long last_poll; int reliable; int dce_changed; @@ -597,9 +598,10 @@ static void fr_set_link_state(int reliable, struct net_device *dev) } -static void fr_timer(unsigned long arg) +static void fr_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)arg; + struct frad_state *st = from_timer(st, t, timer); + struct net_device *dev = st->dev; hdlc_device *hdlc = dev_to_hdlc(dev); int i, cnt = 0, reliable; u32 list; @@ -644,8 +646,6 @@ static void fr_timer(unsigned long arg) state(hdlc)->settings.t391 * HZ; } - state(hdlc)->timer.function = fr_timer; - state(hdlc)->timer.data = arg; add_timer(&state(hdlc)->timer); } @@ -1003,8 +1003,8 @@ static void fr_start(struct net_device *dev) state(hdlc)->n391cnt = 0; state(hdlc)->txseq = state(hdlc)->rxseq = 0; - setup_timer(&state(hdlc)->timer, fr_timer, - (unsigned long)dev); + state(hdlc)->dev = dev; + timer_setup(&state(hdlc)->timer, fr_timer, 0); /* First poll after 1 s */ state(hdlc)->timer.expires = jiffies + HZ; add_timer(&state(hdlc)->timer); diff --git a/drivers/net/wireless/broadcom/b43/phy_g.c b/drivers/net/wireless/broadcom/b43/phy_g.c index 822dcaa8ace6..f59c02166462 100644 --- a/drivers/net/wireless/broadcom/b43/phy_g.c +++ b/drivers/net/wireless/broadcom/b43/phy_g.c @@ -2297,7 +2297,7 @@ static u8 b43_gphy_aci_detect(struct b43_wldev *dev, u8 channel) static u8 b43_gphy_aci_scan(struct b43_wldev *dev) { struct b43_phy *phy = &dev->phy; - u8 ret[13]; + u8 ret[13] = { 0 }; unsigned int channel = phy->channel; unsigned int i, j, start, end; diff --git a/drivers/net/wireless/broadcom/b43/phy_ht.c b/drivers/net/wireless/broadcom/b43/phy_ht.c index 718c90e81696..c3158d085c2b 100644 --- a/drivers/net/wireless/broadcom/b43/phy_ht.c +++ b/drivers/net/wireless/broadcom/b43/phy_ht.c @@ -119,7 +119,7 @@ static void b43_radio_2059_rcal(struct b43_wldev *dev) /* Calibrate the internal RC oscillator? */ static void b43_radio_2057_rccal(struct b43_wldev *dev) { - const u16 radio_values[3][2] = { + static const u16 radio_values[3][2] = { { 0x61, 0xE9 }, { 0x69, 0xD5 }, { 0x73, 0x99 }, }; int i; @@ -154,7 +154,7 @@ static void b43_radio_2059_init_pre(struct b43_wldev *dev) static void b43_radio_2059_init(struct b43_wldev *dev) { - const u16 routing[] = { R2059_C1, R2059_C2, R2059_C3 }; + static const u16 routing[] = { R2059_C1, R2059_C2, R2059_C3 }; int i; /* Prepare (reset?) radio */ @@ -263,7 +263,7 @@ static void b43_phy_ht_reset_cca(struct b43_wldev *dev) static void b43_phy_ht_zero_extg(struct b43_wldev *dev) { u8 i, j; - u16 base[] = { 0x40, 0x60, 0x80 }; + static const u16 base[] = { 0x40, 0x60, 0x80 }; for (i = 0; i < ARRAY_SIZE(base); i++) { for (j = 0; j < 4; j++) diff --git a/drivers/net/wireless/broadcom/b43legacy/radio.c b/drivers/net/wireless/broadcom/b43legacy/radio.c index 9501420340a9..eab1c9387846 100644 --- a/drivers/net/wireless/broadcom/b43legacy/radio.c +++ b/drivers/net/wireless/broadcom/b43legacy/radio.c @@ -280,7 +280,7 @@ u8 b43legacy_radio_aci_detect(struct b43legacy_wldev *dev, u8 channel) u8 b43legacy_radio_aci_scan(struct b43legacy_wldev *dev) { struct b43legacy_phy *phy = &dev->phy; - u8 ret[13]; + u8 ret[13] = { 0 }; unsigned int channel = phy->channel; unsigned int i; unsigned int j; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c index 4eb1e1ce9ace..e7eaa57d11d9 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c @@ -257,11 +257,6 @@ static void brcmf_fweh_event_worker(struct work_struct *work) brcmf_dbg_hex_dump(BRCMF_EVENT_ON(), event->data, min_t(u32, emsg.datalen, 64), "event payload, len=%d\n", emsg.datalen); - if (emsg.datalen > event->datalen) { - brcmf_err("event invalid length header=%d, msg=%d\n", - event->datalen, emsg.datalen); - goto event_free; - } /* special handling of interface event */ if (event->code == BRCMF_E_IF) { @@ -429,7 +424,8 @@ void brcmf_fweh_process_event(struct brcmf_pub *drvr, if (code != BRCMF_E_IF && !fweh->evt_handler[code]) return; - if (datalen > BRCMF_DCMD_MAXLEN) + if (datalen > BRCMF_DCMD_MAXLEN || + datalen + sizeof(*event_packet) > packet_len) return; if (in_interrupt()) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c index 2ce675ab40ef..1c450c0727cb 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c @@ -1853,7 +1853,6 @@ s32 brcmf_p2p_notify_rx_mgmt_p2p_probereq(struct brcmf_if *ifp, struct afx_hdl *afx_hdl = &p2p->afx_hdl; struct brcmf_cfg80211_vif *vif = ifp->vif; struct brcmf_rx_mgmt_data *rxframe = (struct brcmf_rx_mgmt_data *)data; - u16 chanspec = be16_to_cpu(rxframe->chanspec); struct brcmu_chan ch; u8 *mgmt_frame; u32 mgmt_frame_len; @@ -1906,7 +1905,7 @@ s32 brcmf_p2p_notify_rx_mgmt_p2p_probereq(struct brcmf_if *ifp, cfg80211_rx_mgmt(&vif->wdev, freq, 0, mgmt_frame, mgmt_frame_len, 0); brcmf_dbg(INFO, "mgmt_frame_len (%d) , e->datalen (%d), chanspec (%04x), freq (%d)\n", - mgmt_frame_len, e->datalen, chanspec, freq); + mgmt_frame_len, e->datalen, ch.chspec, freq); return 0; } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index 613caca7dc02..5adce0e36fe5 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -4144,10 +4144,8 @@ struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev) init_waitqueue_head(&bus->dcmd_resp_wait); /* Set up the watchdog timer */ - init_timer(&bus->timer); - bus->timer.data = (unsigned long)bus; - bus->timer.function = brcmf_sdio_watchdog; - + setup_timer(&bus->timer, brcmf_sdio_watchdog, + (unsigned long)bus); /* Initialize watchdog thread */ init_completion(&bus->watchdog_wait); bus->watchdog_tsk = kthread_run(brcmf_sdio_watchdog_thread, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c index 1c4e9dd57960..3a13d176b221 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c @@ -1916,7 +1916,7 @@ void wlc_phy_txpower_update_shm(struct brcms_phy *pi) pi->hwpwr_txcur); for (j = TXP_FIRST_OFDM; j <= TXP_LAST_OFDM; j++) { - const u8 ucode_ofdm_rates[] = { + static const u8 ucode_ofdm_rates[] = { 0x0c, 0x12, 0x18, 0x24, 0x30, 0x48, 0x60, 0x6c }; offset = wlapi_bmac_rate_shm_offset( diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c index b3aab2fe96eb..ef685465f80a 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c @@ -14764,8 +14764,8 @@ static void wlc_phy_ipa_restore_tx_digi_filts_nphy(struct brcms_phy *pi) } static void -wlc_phy_set_rfseq_nphy(struct brcms_phy *pi, u8 cmd, u8 *events, u8 *dlys, - u8 len) +wlc_phy_set_rfseq_nphy(struct brcms_phy *pi, u8 cmd, const u8 *events, + const u8 *dlys, u8 len) { u32 t1_offset, t2_offset; u8 ctr; @@ -15240,16 +15240,16 @@ static void wlc_phy_workarounds_nphy_gainctrl_2057_rev5(struct brcms_phy *pi) static void wlc_phy_workarounds_nphy_gainctrl_2057_rev6(struct brcms_phy *pi) { u16 currband; - s8 lna1G_gain_db_rev7[] = { 9, 14, 19, 24 }; - s8 *lna1_gain_db = NULL; - s8 *lna1_gain_db_2 = NULL; - s8 *lna2_gain_db = NULL; - s8 tiaA_gain_db_rev7[] = { -9, -6, -3, 0, 3, 3, 3, 3, 3, 3 }; - s8 *tia_gain_db; - s8 tiaA_gainbits_rev7[] = { 0, 1, 2, 3, 4, 4, 4, 4, 4, 4 }; - s8 *tia_gainbits; - u16 rfseqA_init_gain_rev7[] = { 0x624f, 0x624f }; - u16 *rfseq_init_gain; + static const s8 lna1G_gain_db_rev7[] = { 9, 14, 19, 24 }; + const s8 *lna1_gain_db = NULL; + const s8 *lna1_gain_db_2 = NULL; + const s8 *lna2_gain_db = NULL; + static const s8 tiaA_gain_db_rev7[] = { -9, -6, -3, 0, 3, 3, 3, 3, 3, 3 }; + const s8 *tia_gain_db; + static const s8 tiaA_gainbits_rev7[] = { 0, 1, 2, 3, 4, 4, 4, 4, 4, 4 }; + const s8 *tia_gainbits; + static const u16 rfseqA_init_gain_rev7[] = { 0x624f, 0x624f }; + const u16 *rfseq_init_gain; u16 init_gaincode; u16 clip1hi_gaincode; u16 clip1md_gaincode = 0; @@ -15310,10 +15310,9 @@ static void wlc_phy_workarounds_nphy_gainctrl_2057_rev6(struct brcms_phy *pi) if ((freq <= 5080) || (freq == 5825)) { - s8 lna1A_gain_db_rev7[] = { 11, 16, 20, 24 }; - s8 lna1A_gain_db_2_rev7[] = { - 11, 17, 22, 25}; - s8 lna2A_gain_db_rev7[] = { -1, 6, 10, 14 }; + static const s8 lna1A_gain_db_rev7[] = { 11, 16, 20, 24 }; + static const s8 lna1A_gain_db_2_rev7[] = { 11, 17, 22, 25}; + static const s8 lna2A_gain_db_rev7[] = { -1, 6, 10, 14 }; crsminu_th = 0x3e; lna1_gain_db = lna1A_gain_db_rev7; @@ -15321,10 +15320,9 @@ static void wlc_phy_workarounds_nphy_gainctrl_2057_rev6(struct brcms_phy *pi) lna2_gain_db = lna2A_gain_db_rev7; } else if ((freq >= 5500) && (freq <= 5700)) { - s8 lna1A_gain_db_rev7[] = { 11, 17, 21, 25 }; - s8 lna1A_gain_db_2_rev7[] = { - 12, 18, 22, 26}; - s8 lna2A_gain_db_rev7[] = { 1, 8, 12, 16 }; + static const s8 lna1A_gain_db_rev7[] = { 11, 17, 21, 25 }; + static const s8 lna1A_gain_db_2_rev7[] = { 12, 18, 22, 26}; + static const s8 lna2A_gain_db_rev7[] = { 1, 8, 12, 16 }; crsminu_th = 0x45; clip1md_gaincode_B = 0x14; @@ -15335,10 +15333,9 @@ static void wlc_phy_workarounds_nphy_gainctrl_2057_rev6(struct brcms_phy *pi) lna2_gain_db = lna2A_gain_db_rev7; } else { - s8 lna1A_gain_db_rev7[] = { 12, 18, 22, 26 }; - s8 lna1A_gain_db_2_rev7[] = { - 12, 18, 22, 26}; - s8 lna2A_gain_db_rev7[] = { -1, 6, 10, 14 }; + static const s8 lna1A_gain_db_rev7[] = { 12, 18, 22, 26 }; + static const s8 lna1A_gain_db_2_rev7[] = { 12, 18, 22, 26}; + static const s8 lna2A_gain_db_rev7[] = { -1, 6, 10, 14 }; crsminu_th = 0x41; lna1_gain_db = lna1A_gain_db_rev7; @@ -15450,65 +15447,65 @@ static void wlc_phy_workarounds_nphy_gainctrl(struct brcms_phy *pi) NPHY_RFSEQ_CMD_CLR_HIQ_DIS, NPHY_RFSEQ_CMD_SET_HPF_BW }; - u8 rfseq_updategainu_dlys[] = { 10, 30, 1 }; - s8 lna1G_gain_db[] = { 7, 11, 16, 23 }; - s8 lna1G_gain_db_rev4[] = { 8, 12, 17, 25 }; - s8 lna1G_gain_db_rev5[] = { 9, 13, 18, 26 }; - s8 lna1G_gain_db_rev6[] = { 8, 13, 18, 25 }; - s8 lna1G_gain_db_rev6_224B0[] = { 10, 14, 19, 27 }; - s8 lna1A_gain_db[] = { 7, 11, 17, 23 }; - s8 lna1A_gain_db_rev4[] = { 8, 12, 18, 23 }; - s8 lna1A_gain_db_rev5[] = { 6, 10, 16, 21 }; - s8 lna1A_gain_db_rev6[] = { 6, 10, 16, 21 }; - s8 *lna1_gain_db = NULL; - s8 lna2G_gain_db[] = { -5, 6, 10, 14 }; - s8 lna2G_gain_db_rev5[] = { -3, 7, 11, 16 }; - s8 lna2G_gain_db_rev6[] = { -5, 6, 10, 14 }; - s8 lna2G_gain_db_rev6_224B0[] = { -5, 6, 10, 15 }; - s8 lna2A_gain_db[] = { -6, 2, 6, 10 }; - s8 lna2A_gain_db_rev4[] = { -5, 2, 6, 10 }; - s8 lna2A_gain_db_rev5[] = { -7, 0, 4, 8 }; - s8 lna2A_gain_db_rev6[] = { -7, 0, 4, 8 }; - s8 *lna2_gain_db = NULL; - s8 tiaG_gain_db[] = { + static const u8 rfseq_updategainu_dlys[] = { 10, 30, 1 }; + static const s8 lna1G_gain_db[] = { 7, 11, 16, 23 }; + static const s8 lna1G_gain_db_rev4[] = { 8, 12, 17, 25 }; + static const s8 lna1G_gain_db_rev5[] = { 9, 13, 18, 26 }; + static const s8 lna1G_gain_db_rev6[] = { 8, 13, 18, 25 }; + static const s8 lna1G_gain_db_rev6_224B0[] = { 10, 14, 19, 27 }; + static const s8 lna1A_gain_db[] = { 7, 11, 17, 23 }; + static const s8 lna1A_gain_db_rev4[] = { 8, 12, 18, 23 }; + static const s8 lna1A_gain_db_rev5[] = { 6, 10, 16, 21 }; + static const s8 lna1A_gain_db_rev6[] = { 6, 10, 16, 21 }; + const s8 *lna1_gain_db = NULL; + static const s8 lna2G_gain_db[] = { -5, 6, 10, 14 }; + static const s8 lna2G_gain_db_rev5[] = { -3, 7, 11, 16 }; + static const s8 lna2G_gain_db_rev6[] = { -5, 6, 10, 14 }; + static const s8 lna2G_gain_db_rev6_224B0[] = { -5, 6, 10, 15 }; + static const s8 lna2A_gain_db[] = { -6, 2, 6, 10 }; + static const s8 lna2A_gain_db_rev4[] = { -5, 2, 6, 10 }; + static const s8 lna2A_gain_db_rev5[] = { -7, 0, 4, 8 }; + static const s8 lna2A_gain_db_rev6[] = { -7, 0, 4, 8 }; + const s8 *lna2_gain_db = NULL; + static const s8 tiaG_gain_db[] = { 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A }; - s8 tiaA_gain_db[] = { + static const s8 tiaA_gain_db[] = { 0x13, 0x13, 0x13, 0x13, 0x13, 0x13, 0x13, 0x13, 0x13, 0x13 }; - s8 tiaA_gain_db_rev4[] = { + static const s8 tiaA_gain_db_rev4[] = { 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d }; - s8 tiaA_gain_db_rev5[] = { + static const s8 tiaA_gain_db_rev5[] = { 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d }; - s8 tiaA_gain_db_rev6[] = { + static const s8 tiaA_gain_db_rev6[] = { 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d, 0x0d }; - s8 *tia_gain_db; - s8 tiaG_gainbits[] = { + const s8 *tia_gain_db; + static const s8 tiaG_gainbits[] = { 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03 }; - s8 tiaA_gainbits[] = { + static const s8 tiaA_gainbits[] = { 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06 }; - s8 tiaA_gainbits_rev4[] = { + static const s8 tiaA_gainbits_rev4[] = { 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04 }; - s8 tiaA_gainbits_rev5[] = { + static const s8 tiaA_gainbits_rev5[] = { 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04 }; - s8 tiaA_gainbits_rev6[] = { + static const s8 tiaA_gainbits_rev6[] = { 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04 }; - s8 *tia_gainbits; - s8 lpf_gain_db[] = { 0x00, 0x06, 0x0c, 0x12, 0x12, 0x12 }; - s8 lpf_gainbits[] = { 0x00, 0x01, 0x02, 0x03, 0x03, 0x03 }; - u16 rfseqG_init_gain[] = { 0x613f, 0x613f, 0x613f, 0x613f }; - u16 rfseqG_init_gain_rev4[] = { 0x513f, 0x513f, 0x513f, 0x513f }; - u16 rfseqG_init_gain_rev5[] = { 0x413f, 0x413f, 0x413f, 0x413f }; - u16 rfseqG_init_gain_rev5_elna[] = { + const s8 *tia_gainbits; + static const s8 lpf_gain_db[] = { 0x00, 0x06, 0x0c, 0x12, 0x12, 0x12 }; + static const s8 lpf_gainbits[] = { 0x00, 0x01, 0x02, 0x03, 0x03, 0x03 }; + static const u16 rfseqG_init_gain[] = { 0x613f, 0x613f, 0x613f, 0x613f }; + static const u16 rfseqG_init_gain_rev4[] = { 0x513f, 0x513f, 0x513f, 0x513f }; + static const u16 rfseqG_init_gain_rev5[] = { 0x413f, 0x413f, 0x413f, 0x413f }; + static const u16 rfseqG_init_gain_rev5_elna[] = { 0x013f, 0x013f, 0x013f, 0x013f }; - u16 rfseqG_init_gain_rev6[] = { 0x513f, 0x513f }; - u16 rfseqG_init_gain_rev6_224B0[] = { 0x413f, 0x413f }; - u16 rfseqG_init_gain_rev6_elna[] = { 0x113f, 0x113f }; - u16 rfseqA_init_gain[] = { 0x516f, 0x516f, 0x516f, 0x516f }; - u16 rfseqA_init_gain_rev4[] = { 0x614f, 0x614f, 0x614f, 0x614f }; - u16 rfseqA_init_gain_rev4_elna[] = { + static const u16 rfseqG_init_gain_rev6[] = { 0x513f, 0x513f }; + static const u16 rfseqG_init_gain_rev6_224B0[] = { 0x413f, 0x413f }; + static const u16 rfseqG_init_gain_rev6_elna[] = { 0x113f, 0x113f }; + static const u16 rfseqA_init_gain[] = { 0x516f, 0x516f, 0x516f, 0x516f }; + static const u16 rfseqA_init_gain_rev4[] = { 0x614f, 0x614f, 0x614f, 0x614f }; + static const u16 rfseqA_init_gain_rev4_elna[] = { 0x314f, 0x314f, 0x314f, 0x314f }; - u16 rfseqA_init_gain_rev5[] = { 0x714f, 0x714f, 0x714f, 0x714f }; - u16 rfseqA_init_gain_rev6[] = { 0x714f, 0x714f }; - u16 *rfseq_init_gain; + static const u16 rfseqA_init_gain_rev5[] = { 0x714f, 0x714f, 0x714f, 0x714f }; + static const u16 rfseqA_init_gain_rev6[] = { 0x714f, 0x714f }; + const u16 *rfseq_init_gain; u16 initG_gaincode = 0x627e; u16 initG_gaincode_rev4 = 0x527e; u16 initG_gaincode_rev5 = 0x427e; @@ -15538,10 +15535,10 @@ static void wlc_phy_workarounds_nphy_gainctrl(struct brcms_phy *pi) u16 clip1mdA_gaincode_rev6 = 0x2084; u16 clip1md_gaincode = 0; u16 clip1loG_gaincode = 0x0074; - u16 clip1loG_gaincode_rev5[] = { + static const u16 clip1loG_gaincode_rev5[] = { 0x0062, 0x0064, 0x006a, 0x106a, 0x106c, 0x1074, 0x107c, 0x207c }; - u16 clip1loG_gaincode_rev6[] = { + static const u16 clip1loG_gaincode_rev6[] = { 0x106a, 0x106c, 0x1074, 0x107c, 0x007e, 0x107e, 0x207e, 0x307e }; u16 clip1loG_gaincode_rev6_224B0 = 0x1074; @@ -16066,7 +16063,7 @@ static void wlc_phy_workarounds_nphy_gainctrl(struct brcms_phy *pi) static void wlc_phy_workarounds_nphy(struct brcms_phy *pi) { - u8 rfseq_rx2tx_events[] = { + static const u8 rfseq_rx2tx_events[] = { NPHY_RFSEQ_CMD_NOP, NPHY_RFSEQ_CMD_RXG_FBW, NPHY_RFSEQ_CMD_TR_SWITCH, @@ -16076,7 +16073,7 @@ static void wlc_phy_workarounds_nphy(struct brcms_phy *pi) NPHY_RFSEQ_CMD_EXT_PA }; u8 rfseq_rx2tx_dlys[] = { 8, 6, 6, 2, 4, 60, 1 }; - u8 rfseq_tx2rx_events[] = { + static const u8 rfseq_tx2rx_events[] = { NPHY_RFSEQ_CMD_NOP, NPHY_RFSEQ_CMD_EXT_PA, NPHY_RFSEQ_CMD_TX_GAIN, @@ -16085,8 +16082,8 @@ static void wlc_phy_workarounds_nphy(struct brcms_phy *pi) NPHY_RFSEQ_CMD_RXG_FBW, NPHY_RFSEQ_CMD_CLR_HIQ_DIS }; - u8 rfseq_tx2rx_dlys[] = { 8, 6, 2, 4, 4, 6, 1 }; - u8 rfseq_tx2rx_events_rev3[] = { + static const u8 rfseq_tx2rx_dlys[] = { 8, 6, 2, 4, 4, 6, 1 }; + static const u8 rfseq_tx2rx_events_rev3[] = { NPHY_REV3_RFSEQ_CMD_EXT_PA, NPHY_REV3_RFSEQ_CMD_INT_PA_PU, NPHY_REV3_RFSEQ_CMD_TX_GAIN, @@ -16096,7 +16093,7 @@ static void wlc_phy_workarounds_nphy(struct brcms_phy *pi) NPHY_REV3_RFSEQ_CMD_CLR_HIQ_DIS, NPHY_REV3_RFSEQ_CMD_END }; - u8 rfseq_tx2rx_dlys_rev3[] = { 8, 4, 2, 2, 4, 4, 6, 1 }; + static const u8 rfseq_tx2rx_dlys_rev3[] = { 8, 4, 2, 2, 4, 4, 6, 1 }; u8 rfseq_rx2tx_events_rev3[] = { NPHY_REV3_RFSEQ_CMD_NOP, NPHY_REV3_RFSEQ_CMD_RXG_FBW, @@ -16110,7 +16107,7 @@ static void wlc_phy_workarounds_nphy(struct brcms_phy *pi) }; u8 rfseq_rx2tx_dlys_rev3[] = { 8, 6, 6, 4, 4, 18, 42, 1, 1 }; - u8 rfseq_rx2tx_events_rev3_ipa[] = { + static const u8 rfseq_rx2tx_events_rev3_ipa[] = { NPHY_REV3_RFSEQ_CMD_NOP, NPHY_REV3_RFSEQ_CMD_RXG_FBW, NPHY_REV3_RFSEQ_CMD_TR_SWITCH, @@ -16121,15 +16118,15 @@ static void wlc_phy_workarounds_nphy(struct brcms_phy *pi) NPHY_REV3_RFSEQ_CMD_INT_PA_PU, NPHY_REV3_RFSEQ_CMD_END }; - u8 rfseq_rx2tx_dlys_rev3_ipa[] = { 8, 6, 6, 4, 4, 16, 43, 1, 1 }; - u16 rfseq_rx2tx_dacbufpu_rev7[] = { 0x10f, 0x10f }; + static const u8 rfseq_rx2tx_dlys_rev3_ipa[] = { 8, 6, 6, 4, 4, 16, 43, 1, 1 }; + static const u16 rfseq_rx2tx_dacbufpu_rev7[] = { 0x10f, 0x10f }; s16 alpha0, alpha1, alpha2; s16 beta0, beta1, beta2; u32 leg_data_weights, ht_data_weights, nss1_data_weights, stbc_data_weights; u8 chan_freq_range = 0; - u16 dac_control = 0x0002; + static const u16 dac_control = 0x0002; u16 aux_adc_vmid_rev7_core0[] = { 0x8e, 0x96, 0x96, 0x96 }; u16 aux_adc_vmid_rev7_core1[] = { 0x8f, 0x9f, 0x9f, 0x96 }; u16 aux_adc_vmid_rev4[] = { 0xa2, 0xb4, 0xb4, 0x89 }; @@ -16139,8 +16136,8 @@ static void wlc_phy_workarounds_nphy(struct brcms_phy *pi) u16 aux_adc_gain_rev4[] = { 0x02, 0x02, 0x02, 0x00 }; u16 aux_adc_gain_rev3[] = { 0x02, 0x02, 0x02, 0x00 }; u16 *aux_adc_gain; - u16 sk_adc_vmid[] = { 0xb4, 0xb4, 0xb4, 0x24 }; - u16 sk_adc_gain[] = { 0x02, 0x02, 0x02, 0x02 }; + static const u16 sk_adc_vmid[] = { 0xb4, 0xb4, 0xb4, 0x24 }; + static const u16 sk_adc_gain[] = { 0x02, 0x02, 0x02, 0x02 }; s32 min_nvar_val = 0x18d; s32 min_nvar_offset_6mbps = 20; u8 pdetrange; @@ -16151,9 +16148,9 @@ static void wlc_phy_workarounds_nphy(struct brcms_phy *pi) u16 rfseq_rx2tx_lpf_h_hpc_rev7 = 0x77; u16 rfseq_tx2rx_lpf_h_hpc_rev7 = 0x77; u16 rfseq_pktgn_lpf_h_hpc_rev7 = 0x77; - u16 rfseq_htpktgn_lpf_hpc_rev7[] = { 0x77, 0x11, 0x11 }; - u16 rfseq_pktgn_lpf_hpc_rev7[] = { 0x11, 0x11 }; - u16 rfseq_cckpktgn_lpf_hpc_rev7[] = { 0x11, 0x11 }; + static const u16 rfseq_htpktgn_lpf_hpc_rev7[] = { 0x77, 0x11, 0x11 }; + static const u16 rfseq_pktgn_lpf_hpc_rev7[] = { 0x11, 0x11 }; + static const u16 rfseq_cckpktgn_lpf_hpc_rev7[] = { 0x11, 0x11 }; u16 ipalvlshift_3p3_war_en = 0; u16 rccal_bcap_val, rccal_scap_val; u16 rccal_tx20_11b_bcap = 0; @@ -24291,13 +24288,13 @@ static void wlc_phy_update_txcal_ladder_nphy(struct brcms_phy *pi, u16 core) u16 bbmult; u16 tblentry; - struct nphy_txiqcal_ladder ladder_lo[] = { + static const struct nphy_txiqcal_ladder ladder_lo[] = { {3, 0}, {4, 0}, {6, 0}, {9, 0}, {13, 0}, {18, 0}, {25, 0}, {25, 1}, {25, 2}, {25, 3}, {25, 4}, {25, 5}, {25, 6}, {25, 7}, {35, 7}, {50, 7}, {71, 7}, {100, 7} }; - struct nphy_txiqcal_ladder ladder_iq[] = { + static const struct nphy_txiqcal_ladder ladder_iq[] = { {3, 0}, {4, 0}, {6, 0}, {9, 0}, {13, 0}, {18, 0}, {25, 0}, {35, 0}, {50, 0}, {71, 0}, {100, 0}, {100, 1}, {100, 2}, {100, 3}, {100, 4}, {100, 5}, {100, 6}, {100, 7} @@ -25773,67 +25770,67 @@ wlc_phy_cal_txiqlo_nphy(struct brcms_phy *pi, struct nphy_txgains target_gain, u16 cal_gain[2]; struct nphy_iqcal_params cal_params[2]; u32 tbl_len; - void *tbl_ptr; + const void *tbl_ptr; bool ladder_updated[2]; u8 mphase_cal_lastphase = 0; int bcmerror = 0; bool phyhang_avoid_state = false; - u16 tbl_tx_iqlo_cal_loft_ladder_20[] = { + static const u16 tbl_tx_iqlo_cal_loft_ladder_20[] = { 0x0300, 0x0500, 0x0700, 0x0900, 0x0d00, 0x1100, 0x1900, 0x1901, 0x1902, 0x1903, 0x1904, 0x1905, 0x1906, 0x1907, 0x2407, 0x3207, 0x4607, 0x6407 }; - u16 tbl_tx_iqlo_cal_iqimb_ladder_20[] = { + static const u16 tbl_tx_iqlo_cal_iqimb_ladder_20[] = { 0x0200, 0x0300, 0x0600, 0x0900, 0x0d00, 0x1100, 0x1900, 0x2400, 0x3200, 0x4600, 0x6400, 0x6401, 0x6402, 0x6403, 0x6404, 0x6405, 0x6406, 0x6407 }; - u16 tbl_tx_iqlo_cal_loft_ladder_40[] = { + static const u16 tbl_tx_iqlo_cal_loft_ladder_40[] = { 0x0200, 0x0300, 0x0400, 0x0700, 0x0900, 0x0c00, 0x1200, 0x1201, 0x1202, 0x1203, 0x1204, 0x1205, 0x1206, 0x1207, 0x1907, 0x2307, 0x3207, 0x4707 }; - u16 tbl_tx_iqlo_cal_iqimb_ladder_40[] = { + static const u16 tbl_tx_iqlo_cal_iqimb_ladder_40[] = { 0x0100, 0x0200, 0x0400, 0x0700, 0x0900, 0x0c00, 0x1200, 0x1900, 0x2300, 0x3200, 0x4700, 0x4701, 0x4702, 0x4703, 0x4704, 0x4705, 0x4706, 0x4707 }; - u16 tbl_tx_iqlo_cal_startcoefs[] = { + static const u16 tbl_tx_iqlo_cal_startcoefs[] = { 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000 }; - u16 tbl_tx_iqlo_cal_cmds_fullcal[] = { + static const u16 tbl_tx_iqlo_cal_cmds_fullcal[] = { 0x8123, 0x8264, 0x8086, 0x8245, 0x8056, 0x9123, 0x9264, 0x9086, 0x9245, 0x9056 }; - u16 tbl_tx_iqlo_cal_cmds_recal[] = { + static const u16 tbl_tx_iqlo_cal_cmds_recal[] = { 0x8101, 0x8253, 0x8053, 0x8234, 0x8034, 0x9101, 0x9253, 0x9053, 0x9234, 0x9034 }; - u16 tbl_tx_iqlo_cal_startcoefs_nphyrev3[] = { + static const u16 tbl_tx_iqlo_cal_startcoefs_nphyrev3[] = { 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000 }; - u16 tbl_tx_iqlo_cal_cmds_fullcal_nphyrev3[] = { + static const u16 tbl_tx_iqlo_cal_cmds_fullcal_nphyrev3[] = { 0x8434, 0x8334, 0x8084, 0x8267, 0x8056, 0x8234, 0x9434, 0x9334, 0x9084, 0x9267, 0x9056, 0x9234 }; - u16 tbl_tx_iqlo_cal_cmds_recal_nphyrev3[] = { + static const u16 tbl_tx_iqlo_cal_cmds_recal_nphyrev3[] = { 0x8423, 0x8323, 0x8073, 0x8256, 0x8045, 0x8223, 0x9423, 0x9323, 0x9073, 0x9256, 0x9045, 0x9223 }; diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c index de9b6522c43f..65eba2c24292 100644 --- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c +++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c @@ -1480,7 +1480,7 @@ il4965_get_ac_from_tid(u16 tid) static inline int il4965_get_fifo_from_tid(u16 tid) { - const u8 ac_to_fifo[] = { + static const u8 ac_to_fifo[] = { IL_TX_FIFO_VO, IL_TX_FIFO_VI, IL_TX_FIFO_BE, diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile index 35a32a3ec882..91b90e77d6d9 100644 --- a/drivers/net/wireless/intel/iwlwifi/Makefile +++ b/drivers/net/wireless/intel/iwlwifi/Makefile @@ -13,6 +13,7 @@ iwlwifi-objs += iwl-trans.o iwlwifi-objs += fw/notif-wait.o iwlwifi-$(CONFIG_IWLMVM) += fw/paging.o fw/smem.o fw/init.o fw/dbg.o iwlwifi-$(CONFIG_IWLMVM) += fw/common_rx.o fw/nvm.o +iwlwifi-$(CONFIG_ACPI) += fw/acpi.o iwlwifi-objs += $(iwlwifi-m) diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/7000.c b/drivers/net/wireless/intel/iwlwifi/cfg/7000.c index 45e2efc70d19..ce741beec1fc 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/7000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/7000.c @@ -309,6 +309,7 @@ const struct iwl_cfg iwl3168_2ac_cfg = { .nvm_calib_ver = IWL3168_TX_POWER_VERSION, .pwr_tx_backoffs = iwl7265_pwr_tx_backoffs, .dccm_len = IWL7265_DCCM_LEN, + .nvm_type = IWL_NVM_SDP, }; const struct iwl_cfg iwl7265_2ac_cfg = { diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c index 2e6c52664cee..c2a5936ccede 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c @@ -164,7 +164,7 @@ static const struct iwl_tt_params iwl8000_tt_params = { .default_nvm_file_C_step = DEFAULT_NVM_FILE_FAMILY_8000C, \ .thermal_params = &iwl8000_tt_params, \ .apmg_not_supported = true, \ - .ext_nvm = true, \ + .nvm_type = IWL_NVM_EXT, \ .dbgc_supported = true #define IWL_DEVICE_8000 \ diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c index 2babe0a1f18b..e8b5ff42f5a8 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c @@ -148,7 +148,7 @@ static const struct iwl_tt_params iwl9000_tt_params = { .vht_mu_mimo_supported = true, \ .mac_addr_from_csr = true, \ .rf_id = true, \ - .ext_nvm = true, \ + .nvm_type = IWL_NVM_EXT, \ .dbgc_supported = true const struct iwl_cfg iwl9160_2ac_cfg = { diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/a000.c b/drivers/net/wireless/intel/iwlwifi/cfg/a000.c index 76ba1f8bc72f..c911d55fde49 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/a000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/a000.c @@ -133,78 +133,79 @@ static const struct iwl_ht_params iwl_a000_ht_params = { .use_tfh = true, \ .rf_id = true, \ .gen2 = true, \ - .ext_nvm = true, \ - .dbgc_supported = true + .nvm_type = IWL_NVM_EXT, \ + .dbgc_supported = true, \ + .tx_cmd_queue_size = 32 const struct iwl_cfg iwla000_2ac_cfg_hr = { - .name = "Intel(R) Dual Band Wireless AC a000", - .fw_name_pre = IWL_A000_HR_FW_PRE, - IWL_DEVICE_A000, - .ht_params = &iwl_a000_ht_params, - .nvm_ver = IWL_A000_NVM_VERSION, - .nvm_calib_ver = IWL_A000_TX_POWER_VERSION, - .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .name = "Intel(R) Dual Band Wireless AC a000", + .fw_name_pre = IWL_A000_HR_FW_PRE, + IWL_DEVICE_A000, + .ht_params = &iwl_a000_ht_params, + .nvm_ver = IWL_A000_NVM_VERSION, + .nvm_calib_ver = IWL_A000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, }; const struct iwl_cfg iwla000_2ac_cfg_hr_cdb = { - .name = "Intel(R) Dual Band Wireless AC a000", - .fw_name_pre = IWL_A000_HR_CDB_FW_PRE, - IWL_DEVICE_A000, - .ht_params = &iwl_a000_ht_params, - .nvm_ver = IWL_A000_NVM_VERSION, - .nvm_calib_ver = IWL_A000_TX_POWER_VERSION, - .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, - .cdb = true, + .name = "Intel(R) Dual Band Wireless AC a000", + .fw_name_pre = IWL_A000_HR_CDB_FW_PRE, + IWL_DEVICE_A000, + .ht_params = &iwl_a000_ht_params, + .nvm_ver = IWL_A000_NVM_VERSION, + .nvm_calib_ver = IWL_A000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .cdb = true, }; const struct iwl_cfg iwla000_2ac_cfg_jf = { - .name = "Intel(R) Dual Band Wireless AC a000", - .fw_name_pre = IWL_A000_JF_FW_PRE, - IWL_DEVICE_A000, - .ht_params = &iwl_a000_ht_params, - .nvm_ver = IWL_A000_NVM_VERSION, - .nvm_calib_ver = IWL_A000_TX_POWER_VERSION, - .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .name = "Intel(R) Dual Band Wireless AC a000", + .fw_name_pre = IWL_A000_JF_FW_PRE, + IWL_DEVICE_A000, + .ht_params = &iwl_a000_ht_params, + .nvm_ver = IWL_A000_NVM_VERSION, + .nvm_calib_ver = IWL_A000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, }; const struct iwl_cfg iwla000_2ax_cfg_hr = { - .name = "Intel(R) Dual Band Wireless AX a000", - .fw_name_pre = IWL_A000_HR_FW_PRE, - IWL_DEVICE_A000, - .ht_params = &iwl_a000_ht_params, - .nvm_ver = IWL_A000_NVM_VERSION, - .nvm_calib_ver = IWL_A000_TX_POWER_VERSION, - .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .name = "Intel(R) Dual Band Wireless AX a000", + .fw_name_pre = IWL_A000_HR_FW_PRE, + IWL_DEVICE_A000, + .ht_params = &iwl_a000_ht_params, + .nvm_ver = IWL_A000_NVM_VERSION, + .nvm_calib_ver = IWL_A000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, }; const struct iwl_cfg iwla000_2ax_cfg_qnj_hr_f0 = { - .name = "Intel(R) Dual Band Wireless AX a000", - .fw_name_pre = IWL_A000_HR_F0_FW_PRE, - IWL_DEVICE_A000, - .ht_params = &iwl_a000_ht_params, - .nvm_ver = IWL_A000_NVM_VERSION, - .nvm_calib_ver = IWL_A000_TX_POWER_VERSION, - .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .name = "Intel(R) Dual Band Wireless AX a000", + .fw_name_pre = IWL_A000_HR_F0_FW_PRE, + IWL_DEVICE_A000, + .ht_params = &iwl_a000_ht_params, + .nvm_ver = IWL_A000_NVM_VERSION, + .nvm_calib_ver = IWL_A000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, }; const struct iwl_cfg iwla000_2ax_cfg_qnj_jf_b0 = { - .name = "Intel(R) Dual Band Wireless AX a000", - .fw_name_pre = IWL_A000_JF_B0_FW_PRE, - IWL_DEVICE_A000, - .ht_params = &iwl_a000_ht_params, - .nvm_ver = IWL_A000_NVM_VERSION, - .nvm_calib_ver = IWL_A000_TX_POWER_VERSION, - .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .name = "Intel(R) Dual Band Wireless AX a000", + .fw_name_pre = IWL_A000_JF_B0_FW_PRE, + IWL_DEVICE_A000, + .ht_params = &iwl_a000_ht_params, + .nvm_ver = IWL_A000_NVM_VERSION, + .nvm_calib_ver = IWL_A000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, }; const struct iwl_cfg iwla000_2ax_cfg_qnj_hr_a0 = { - .name = "Intel(R) Dual Band Wireless AX a000", - .fw_name_pre = IWL_A000_HR_A0_FW_PRE, - IWL_DEVICE_A000, - .ht_params = &iwl_a000_ht_params, - .nvm_ver = IWL_A000_NVM_VERSION, - .nvm_calib_ver = IWL_A000_TX_POWER_VERSION, - .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .name = "Intel(R) Dual Band Wireless AX a000", + .fw_name_pre = IWL_A000_HR_A0_FW_PRE, + IWL_DEVICE_A000, + .ht_params = &iwl_a000_ht_params, + .nvm_ver = IWL_A000_NVM_VERSION, + .nvm_calib_ver = IWL_A000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, }; MODULE_FIRMWARE(IWL_A000_HR_MODULE_FIRMWARE(IWL_A000_UCODE_API_MAX)); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c new file mode 100644 index 000000000000..75cae54ea7de --- /dev/null +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -0,0 +1,210 @@ +/****************************************************************************** + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2017 Intel Deutschland GmbH + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; + * + * The full GNU General Public License is included in this distribution + * in the file called COPYING. + * + * Contact Information: + * Intel Linux Wireless <linuxwifi@intel.com> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + * + * BSD LICENSE + * + * Copyright(c) 2017 Intel Deutschland GmbH + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + *****************************************************************************/ + +#include "iwl-drv.h" +#include "iwl-debug.h" +#include "acpi.h" + +void *iwl_acpi_get_object(struct device *dev, acpi_string method) +{ + acpi_handle root_handle; + acpi_handle handle; + struct acpi_buffer buf = {ACPI_ALLOCATE_BUFFER, NULL}; + acpi_status status; + + root_handle = ACPI_HANDLE(dev); + if (!root_handle) { + IWL_DEBUG_DEV_RADIO(dev, + "Could not retrieve root port ACPI handle\n"); + return ERR_PTR(-ENOENT); + } + + /* Get the method's handle */ + status = acpi_get_handle(root_handle, method, &handle); + if (ACPI_FAILURE(status)) { + IWL_DEBUG_DEV_RADIO(dev, "%s method not found\n", method); + return ERR_PTR(-ENOENT); + } + + /* Call the method with no arguments */ + status = acpi_evaluate_object(handle, NULL, NULL, &buf); + if (ACPI_FAILURE(status)) { + IWL_DEBUG_DEV_RADIO(dev, "%s invocation failed (0x%x)\n", + method, status); + return ERR_PTR(-ENOENT); + } + + return buf.pointer; +} +IWL_EXPORT_SYMBOL(iwl_acpi_get_object); + +union acpi_object *iwl_acpi_get_wifi_pkg(struct device *dev, + union acpi_object *data, + int data_size) +{ + int i; + union acpi_object *wifi_pkg; + + /* + * We need at least one entry in the wifi package that + * describes the domain, and one more entry, otherwise there's + * no point in reading it. + */ + if (WARN_ON_ONCE(data_size < 2)) + return ERR_PTR(-EINVAL); + + /* + * We need at least two packages, one for the revision and one + * for the data itself. Also check that the revision is valid + * (i.e. it is an integer set to 0). + */ + if (data->type != ACPI_TYPE_PACKAGE || + data->package.count < 2 || + data->package.elements[0].type != ACPI_TYPE_INTEGER || + data->package.elements[0].integer.value != 0) { + IWL_DEBUG_DEV_RADIO(dev, "Unsupported packages structure\n"); + return ERR_PTR(-EINVAL); + } + + /* loop through all the packages to find the one for WiFi */ + for (i = 1; i < data->package.count; i++) { + union acpi_object *domain; + + wifi_pkg = &data->package.elements[i]; + + /* skip entries that are not a package with the right size */ + if (wifi_pkg->type != ACPI_TYPE_PACKAGE || + wifi_pkg->package.count != data_size) + continue; + + domain = &wifi_pkg->package.elements[0]; + if (domain->type == ACPI_TYPE_INTEGER && + domain->integer.value == ACPI_WIFI_DOMAIN) + goto found; + } + + return ERR_PTR(-ENOENT); + +found: + return wifi_pkg; +} +IWL_EXPORT_SYMBOL(iwl_acpi_get_wifi_pkg); + +int iwl_acpi_get_mcc(struct device *dev, char *mcc) +{ + union acpi_object *wifi_pkg, *data; + u32 mcc_val; + int ret; + + data = iwl_acpi_get_object(dev, ACPI_WRDD_METHOD); + if (IS_ERR(data)) + return PTR_ERR(data); + + wifi_pkg = iwl_acpi_get_wifi_pkg(dev, data, ACPI_WRDD_WIFI_DATA_SIZE); + if (IS_ERR(wifi_pkg)) { + ret = PTR_ERR(wifi_pkg); + goto out_free; + } + + if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) { + ret = -EINVAL; + goto out_free; + } + + mcc_val = wifi_pkg->package.elements[1].integer.value; + + mcc[0] = (mcc_val >> 8) & 0xff; + mcc[1] = mcc_val & 0xff; + mcc[2] = '\0'; + + ret = 0; +out_free: + kfree(data); + return ret; +} +IWL_EXPORT_SYMBOL(iwl_acpi_get_mcc); + +u64 iwl_acpi_get_pwr_limit(struct device *dev) +{ + union acpi_object *data, *wifi_pkg; + u64 dflt_pwr_limit; + + data = iwl_acpi_get_object(dev, ACPI_SPLC_METHOD); + if (IS_ERR(data)) { + dflt_pwr_limit = 0; + goto out; + } + + wifi_pkg = iwl_acpi_get_wifi_pkg(dev, data, + ACPI_SPLC_WIFI_DATA_SIZE); + if (IS_ERR(wifi_pkg) || + wifi_pkg->package.elements[1].integer.value != ACPI_TYPE_INTEGER) { + dflt_pwr_limit = 0; + goto out_free; + } + + dflt_pwr_limit = wifi_pkg->package.elements[1].integer.value; +out_free: + kfree(data); +out: + return dflt_pwr_limit; +} +IWL_EXPORT_SYMBOL(iwl_acpi_get_pwr_limit); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h new file mode 100644 index 000000000000..cb5f32c1d705 --- /dev/null +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h @@ -0,0 +1,138 @@ +/****************************************************************************** + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2017 Intel Deutschland GmbH + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; + * + * The full GNU General Public License is included in this distribution + * in the file called COPYING. + * + * Contact Information: + * Intel Linux Wireless <linuxwifi@intel.com> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + * + * BSD LICENSE + * + * Copyright(c) 2017 Intel Deutschland GmbH + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + *****************************************************************************/ +#ifndef __iwl_fw_acpi__ +#define __iwl_fw_acpi__ + +#include <linux/acpi.h> + +#define ACPI_WRDS_METHOD "WRDS" +#define ACPI_EWRD_METHOD "EWRD" +#define ACPI_WGDS_METHOD "WGDS" +#define ACPI_WRDD_METHOD "WRDD" +#define ACPI_SPLC_METHOD "SPLC" + +#define ACPI_WIFI_DOMAIN (0x07) + +#define ACPI_SAR_TABLE_SIZE 10 +#define ACPI_SAR_PROFILE_NUM 4 + +#define ACPI_GEO_TABLE_SIZE 6 +#define ACPI_NUM_GEO_PROFILES 3 +#define ACPI_GEO_PER_CHAIN_SIZE 3 + +#define ACPI_SAR_NUM_CHAIN_LIMITS 2 +#define ACPI_SAR_NUM_SUB_BANDS 5 + +#define ACPI_WRDS_WIFI_DATA_SIZE (ACPI_SAR_TABLE_SIZE + 2) +#define ACPI_EWRD_WIFI_DATA_SIZE ((ACPI_SAR_PROFILE_NUM - 1) * \ + ACPI_SAR_TABLE_SIZE + 3) +#define ACPI_WGDS_WIFI_DATA_SIZE 18 +#define ACPI_WRDD_WIFI_DATA_SIZE 2 +#define ACPI_SPLC_WIFI_DATA_SIZE 2 + +#define ACPI_WGDS_NUM_BANDS 2 +#define ACPI_WGDS_TABLE_SIZE 3 + +#ifdef CONFIG_ACPI + +void *iwl_acpi_get_object(struct device *dev, acpi_string method); +union acpi_object *iwl_acpi_get_wifi_pkg(struct device *dev, + union acpi_object *data, + int data_size); + +/** + * iwl_acpi_get_mcc - read MCC from ACPI, if available + * + * @dev: the struct device + * @mcc: output buffer (3 bytes) that will get the MCC + * + * This function tries to read the current MCC from ACPI if available. + */ +int iwl_acpi_get_mcc(struct device *dev, char *mcc); + +u64 iwl_acpi_get_pwr_limit(struct device *dev); + +#else /* CONFIG_ACPI */ + +static inline void *iwl_acpi_get_object(struct device *dev, acpi_string method) +{ + return ERR_PTR(-ENOENT); +} + +static inline union acpi_object *iwl_acpi_get_wifi_pkg(struct device *dev, + union acpi_object *data, + int data_size) +{ + return ERR_PTR(-ENOENT); +} + +static inline int iwl_acpi_get_mcc(struct device *dev, char *mcc) +{ + return -ENOENT; +} + +static inline u64 iwl_acpi_get_pwr_limit(struct device *dev) +{ + return 0; +} + +#endif /* CONFIG_ACPI */ +#endif /* __iwl_fw_acpi__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/binding.h b/drivers/net/wireless/intel/iwlwifi/fw/api/binding.h index d2717fafdf5b..570f19026c91 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/binding.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/binding.h @@ -116,14 +116,14 @@ struct iwl_binding_cmd { #define IWL_MVM_MAX_QUOTA 128 /** - * struct iwl_time_quota_data - configuration of time quota per binding + * struct iwl_time_quota_data_v1 - configuration of time quota per binding * @id_and_color: ID and color of the relevant Binding, * &enum iwl_ctxt_id_and_color * @quota: absolute time quota in TU. The scheduler will try to divide the * remainig quota (after Time Events) according to this quota. * @max_duration: max uninterrupted context duration in TU */ -struct iwl_time_quota_data { +struct iwl_time_quota_data_v1 { __le32 id_and_color; __le32 quota; __le32 max_duration; @@ -137,8 +137,43 @@ struct iwl_time_quota_data { * essentially zero. * On CDB the fourth one is a regular binding. */ +struct iwl_time_quota_cmd_v1 { + struct iwl_time_quota_data_v1 quotas[MAX_BINDINGS]; +} __packed; /* TIME_QUOTA_ALLOCATION_CMD_API_S_VER_1 */ + +enum iwl_quota_low_latency { + IWL_QUOTA_LOW_LATENCY_NONE = 0, + IWL_QUOTA_LOW_LATENCY_TX = BIT(0), + IWL_QUOTA_LOW_LATENCY_RX = BIT(1), + IWL_QUOTA_LOW_LATENCY_TX_RX = + IWL_QUOTA_LOW_LATENCY_TX | IWL_QUOTA_LOW_LATENCY_RX, +}; + +/** + * struct iwl_time_quota_data - configuration of time quota per binding + * @id_and_color: ID and color of the relevant Binding. + * @quota: absolute time quota in TU. The scheduler will try to divide the + * remainig quota (after Time Events) according to this quota. + * @max_duration: max uninterrupted context duration in TU + * @low_latency: low latency status, &enum iwl_quota_low_latency + */ +struct iwl_time_quota_data { + __le32 id_and_color; + __le32 quota; + __le32 max_duration; + __le32 low_latency; +} __packed; /* TIME_QUOTA_DATA_API_S_VER_2 */ + +/** + * struct iwl_time_quota_cmd - configuration of time quota between bindings + * ( TIME_QUOTA_CMD = 0x2c ) + * Note: on non-CDB the fourth one is the auxilary mac and is essentially zero. + * On CDB the fourth one is a regular binding. + * + * @quotas: allocations per binding + */ struct iwl_time_quota_cmd { struct iwl_time_quota_data quotas[MAX_BINDINGS]; -} __packed; /* TIME_QUOTA_ALLOCATION_CMD_API_S_VER_1 */ +} __packed; /* TIME_QUOTA_ALLOCATION_CMD_API_S_VER_2 */ #endif /* __iwl_fw_api_binding_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h index 074868394427..7ebbf097488b 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h @@ -504,6 +504,7 @@ enum iwl_legacy_cmds { /** * @MARKER_CMD: trace marker command, uses &struct iwl_mvm_marker + * with &struct iwl_mvm_marker_rsp */ MARKER_CMD = 0xcb, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h index 9f88b61536bc..0a81fb1b6ed4 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h @@ -278,6 +278,15 @@ struct iwl_mvm_marker { __le32 metadata[0]; } __packed; /* MARKER_API_S_VER_1 */ +/** + * struct iwl_mvm_marker_rsp - Response to marker cmd + * + * @gp2: The gp2 clock value in the FW + */ +struct iwl_mvm_marker_rsp { + __le32 gp2; +} __packed; + /* Operation types for the debug mem access */ enum { DEBUG_MEM_OP_READ = 0, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h index 39c89e85fd2f..ec42c84e5df2 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h @@ -68,78 +68,11 @@ */ enum iwl_mac_conf_subcmd_ids { /** - * @LINK_QUALITY_MEASUREMENT_CMD: &struct iwl_link_qual_msrmnt_cmd - */ - LINK_QUALITY_MEASUREMENT_CMD = 0x1, - - /** - * @LINK_QUALITY_MEASUREMENT_COMPLETE_NOTIF: - * &struct iwl_link_qual_msrmnt_notif - */ - LINK_QUALITY_MEASUREMENT_COMPLETE_NOTIF = 0xFE, - - /** * @CHANNEL_SWITCH_NOA_NOTIF: &struct iwl_channel_switch_noa_notif */ CHANNEL_SWITCH_NOA_NOTIF = 0xFF, }; -#define LQM_NUMBER_OF_STATIONS_IN_REPORT 16 - -enum iwl_lqm_cmd_operatrions { - LQM_CMD_OPERATION_START_MEASUREMENT = 0x01, - LQM_CMD_OPERATION_STOP_MEASUREMENT = 0x02, -}; - -enum iwl_lqm_status { - LQM_STATUS_SUCCESS = 0, - LQM_STATUS_TIMEOUT = 1, - LQM_STATUS_ABORT = 2, -}; - -/** - * struct iwl_link_qual_msrmnt_cmd - Link Quality Measurement command - * @cmd_operation: command operation to be performed (start or stop) - * as defined above. - * @mac_id: MAC ID the measurement applies to. - * @measurement_time: time of the total measurement to be performed, in uSec. - * @timeout: maximum time allowed until a response is sent, in uSec. - */ -struct iwl_link_qual_msrmnt_cmd { - __le32 cmd_operation; - __le32 mac_id; - __le32 measurement_time; - __le32 timeout; -} __packed /* LQM_CMD_API_S_VER_1 */; - -/** - * struct iwl_link_qual_msrmnt_notif - Link Quality Measurement notification - * - * @frequent_stations_air_time: an array containing the total air time - * (in uSec) used by the most frequently transmitting stations. - * @number_of_stations: the number of uniqe stations included in the array - * (a number between 0 to 16) - * @total_air_time_other_stations: the total air time (uSec) used by all the - * stations which are not included in the above report. - * @time_in_measurement_window: the total time in uSec in which a measurement - * took place. - * @tx_frame_dropped: the number of TX frames dropped due to retry limit during - * measurement - * @mac_id: MAC ID the measurement applies to. - * @status: return status. may be one of the LQM_STATUS_* defined above. - * @reserved: reserved. - */ -struct iwl_link_qual_msrmnt_notif { - __le32 frequent_stations_air_time[LQM_NUMBER_OF_STATIONS_IN_REPORT]; - __le32 number_of_stations; - __le32 total_air_time_other_stations; - __le32 time_in_measurement_window; - __le32 tx_frame_dropped; - __le32 mac_id; - __le32 status; - u8 reserved[12]; -} __packed; /* LQM_MEASUREMENT_COMPLETE_NTF_API_S_VER1 */ - /** * struct iwl_channel_switch_noa_notif - Channel switch NOA notification * diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h index 00bc7a25dece..3fd07bc80f54 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h @@ -108,6 +108,7 @@ enum iwl_nvm_access_target { * @NVM_SECTION_TYPE_REGULATORY: regulatory section * @NVM_SECTION_TYPE_CALIBRATION: calibration section * @NVM_SECTION_TYPE_PRODUCTION: production section + * @NVM_SECTION_TYPE_REGULATORY_SDP: regulatory section used by 3168 series * @NVM_SECTION_TYPE_MAC_OVERRIDE: MAC override section * @NVM_SECTION_TYPE_PHY_SKU: PHY SKU section * @NVM_MAX_NUM_SECTIONS: number of sections @@ -117,6 +118,7 @@ enum iwl_nvm_section_type { NVM_SECTION_TYPE_REGULATORY = 3, NVM_SECTION_TYPE_CALIBRATION = 4, NVM_SECTION_TYPE_PRODUCTION = 5, + NVM_SECTION_TYPE_REGULATORY_SDP = 8, NVM_SECTION_TYPE_MAC_OVERRIDE = 11, NVM_SECTION_TYPE_PHY_SKU = 12, NVM_MAX_NUM_SECTIONS = 13, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h index a06afb5605d2..a3c77e01863b 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h @@ -357,8 +357,7 @@ struct iwl_dev_tx_power_cmd { u8 reserved[3]; } __packed; /* TX_REDUCED_POWER_API_S_VER_4 */ -#define IWL_NUM_GEO_PROFILES 3 -#define IWL_GEO_PER_CHAIN_SIZE 3 +#define IWL_NUM_GEO_PROFILES 3 /** * enum iwl_geo_per_chain_offset_operation - type of operation diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h b/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h index af369eba3795..dc40cbd52f92 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h @@ -68,9 +68,6 @@ * @STA_FLG_REDUCED_TX_PWR_DATA: reduced TX power (data frames) * @STA_FLG_DISABLE_TX: set if TX should be disabled * @STA_FLG_PS: set if STA is in Power Save - * @STA_FLG_INVALID: set if STA is invalid - * @STA_FLG_DLP_EN: Direct Link Protocol is enabled - * @STA_FLG_SET_ALL_KEYS: the current key applies to all key IDs * @STA_FLG_DRAIN_FLOW: drain flow * @STA_FLG_PAN: STA is for PAN interface * @STA_FLG_CLASS_AUTH: station is authenticated @@ -100,7 +97,6 @@ * @STA_FLG_MIMO_EN_SISO: no support for MIMO * @STA_FLG_MIMO_EN_MIMO2: 2 streams supported * @STA_FLG_MIMO_EN_MIMO3: 3 streams supported - * @STA_FLG_MFP_EN: Management Frame Protection * @STA_FLG_AGG_MPDU_DENS_MSK: A-MPDU density (mask) * @STA_FLG_AGG_MPDU_DENS_SHIFT: A-MPDU density (bit shift) * @STA_FLG_AGG_MPDU_DENS_2US: A-MPDU density (2 usec gap) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index 6afc7a799892..8106fd4be996 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -93,6 +93,8 @@ static void iwl_read_radio_regs(struct iwl_fw_runtime *fwrt, unsigned long flags; int i; + IWL_DEBUG_INFO(fwrt, "WRT radio registers dump\n"); + if (!iwl_trans_grab_nic_access(fwrt->trans, &flags)) return; @@ -233,6 +235,8 @@ static void iwl_fw_dump_fifos(struct iwl_fw_runtime *fwrt, unsigned long flags; int i, j; + IWL_DEBUG_INFO(fwrt, "WRT FIFO dump\n"); + if (!iwl_trans_grab_nic_access(fwrt->trans, &flags)) return; @@ -476,6 +480,8 @@ static void iwl_dump_prph(struct iwl_trans *trans, unsigned long flags; u32 i; + IWL_DEBUG_INFO(trans, "WRT PRPH dump\n"); + if (!iwl_trans_grab_nic_access(trans, &flags)) return; @@ -559,6 +565,8 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt) bool monitor_dump_only = false; int i; + IWL_DEBUG_INFO(fwrt, "WRT dump start\n"); + /* there's no point in fw dump if the bus is dead */ if (test_bit(STATUS_TRANS_DEAD, &fwrt->trans->status)) { IWL_ERR(fwrt, "Skip fw error dump since bus is dead\n"); @@ -816,6 +824,9 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt) dump_mem->type = fw_dbg_mem[i].data_type; dump_mem->offset = cpu_to_le32(ofs); + IWL_DEBUG_INFO(fwrt, "WRT memory dump. Type=%u\n", + dump_mem->type); + switch (dump_mem->type & cpu_to_le32(FW_DBG_MEM_TYPE_MASK)) { case cpu_to_le32(FW_DBG_MEM_TYPE_REGULAR): iwl_trans_read_mem_bytes(fwrt->trans, ofs, @@ -841,6 +852,7 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt) } if (smem_len) { + IWL_DEBUG_INFO(fwrt, "WRT SMEM dump\n"); dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM); dump_data->len = cpu_to_le32(smem_len + sizeof(*dump_mem)); dump_mem = (void *)dump_data->data; @@ -853,6 +865,7 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt) } if (sram2_len) { + IWL_DEBUG_INFO(fwrt, "WRT SRAM dump\n"); dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM); dump_data->len = cpu_to_le32(sram2_len + sizeof(*dump_mem)); dump_mem = (void *)dump_data->data; @@ -868,6 +881,7 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt) if (!fwrt->trans->cfg->gen2 && fwrt->fw->img[fwrt->cur_fw_img].paging_mem_size && fwrt->fw_paging_db[0].fw_paging_block) { + IWL_DEBUG_INFO(fwrt, "WRT paging dump\n"); for (i = 1; i < fwrt->num_of_paging_blk + 1; i++) { struct iwl_fw_error_dump_paging *paging; struct page *pages = @@ -930,6 +944,7 @@ out: iwl_fw_free_dump_desc(fwrt); fwrt->dump.trig = NULL; clear_bit(IWL_FWRT_STATUS_DUMPING, &fwrt->status); + IWL_DEBUG_INFO(fwrt, "WRT dump done\n"); } IWL_EXPORT_SYMBOL(iwl_fw_error_dump); @@ -1086,7 +1101,7 @@ void iwl_fw_error_dump_wk(struct work_struct *work) if (fwrt->trans->cfg->device_family == IWL_DEVICE_FAMILY_7000) { /* stop recording */ - iwl_set_bits_prph(fwrt->trans, MON_BUFF_SAMPLE_CTL, 0x100); + iwl_fw_dbg_stop_recording(fwrt); iwl_fw_error_dump(fwrt); @@ -1104,10 +1119,7 @@ void iwl_fw_error_dump_wk(struct work_struct *work) u32 in_sample = iwl_read_prph(fwrt->trans, DBGC_IN_SAMPLE); u32 out_ctrl = iwl_read_prph(fwrt->trans, DBGC_OUT_CTRL); - /* stop recording */ - iwl_write_prph(fwrt->trans, DBGC_IN_SAMPLE, 0); - udelay(100); - iwl_write_prph(fwrt->trans, DBGC_OUT_CTRL, 0); + iwl_fw_dbg_stop_recording(fwrt); /* wait before we collect the data till the DBGC stop */ udelay(500); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h index 0f810ea89d31..9c889a32fe24 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h @@ -68,6 +68,8 @@ #include <linux/workqueue.h> #include <net/cfg80211.h> #include "runtime.h" +#include "iwl-prph.h" +#include "iwl-io.h" #include "file.h" #include "error-dump.h" @@ -194,8 +196,21 @@ _iwl_fw_dbg_trigger_simple_stop(struct iwl_fw_runtime *fwrt, iwl_fw_dbg_get_trigger((fwrt)->fw,\ (trig))) +static inline void iwl_fw_dbg_stop_recording(struct iwl_fw_runtime *fwrt) +{ + if (fwrt->trans->cfg->device_family == IWL_DEVICE_FAMILY_7000) { + iwl_set_bits_prph(fwrt->trans, MON_BUFF_SAMPLE_CTL, 0x100); + } else { + iwl_write_prph(fwrt->trans, DBGC_IN_SAMPLE, 0); + udelay(100); + iwl_write_prph(fwrt->trans, DBGC_OUT_CTRL, 0); + } +} + static inline void iwl_fw_dump_conf_clear(struct iwl_fw_runtime *fwrt) { + iwl_fw_dbg_stop_recording(fwrt); + fwrt->dump.conf = FW_DBG_INVALID; } diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h index 279248cd9cfb..efd7fb65de8b 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/file.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h @@ -248,6 +248,8 @@ typedef unsigned int __bitwise iwl_ucode_tlv_api_t; * @IWL_UCODE_TLV_API_NEW_RX_STATS: should new RX STATISTICS API be used * @IWL_UCODE_TLV_API_ATS_COEX_EXTERNAL: the coex notification is enlared to * include information about ACL time sharing. + * @IWL_UCODE_TLV_API_QUOTA_LOW_LATENCY: Quota command includes a field + * indicating low latency direction. * * @NUM_IWL_UCODE_TLV_API: number of bits used */ @@ -265,6 +267,7 @@ enum iwl_ucode_tlv_api { IWL_UCODE_TLV_API_NEW_BEACON_TEMPLATE = (__force iwl_ucode_tlv_api_t)34, IWL_UCODE_TLV_API_NEW_RX_STATS = (__force iwl_ucode_tlv_api_t)35, IWL_UCODE_TLV_API_COEX_ATS_EXTERNAL = (__force iwl_ucode_tlv_api_t)37, + IWL_UCODE_TLV_API_QUOTA_LOW_LATENCY = (__force iwl_ucode_tlv_api_t)38, NUM_IWL_UCODE_TLV_API #ifdef __CHECKER__ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index 3e057b539d5b..0347a03b6f1b 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -108,6 +108,18 @@ enum iwl_led_mode { IWL_LED_DISABLE, }; +/** + * enum iwl_nvm_type - nvm formats + * @IWL_NVM: the regular format + * @IWL_NVM_EXT: extended NVM format + * @IWL_NVM_SDP: NVM format used by 3168 series + */ +enum iwl_nvm_type { + IWL_NVM, + IWL_NVM_EXT, + IWL_NVM_SDP, +}; + /* * This is the threshold value of plcp error rate per 100mSecs. It is * used to set and check for the validity of plcp_delta. @@ -320,7 +332,9 @@ struct iwl_pwr_tx_backoff { * @integrated: discrete or integrated * @gen2: a000 and on transport operation * @cdb: CDB support - * @ext_nvm: extended NVM format + * @nvm_type: see &enum iwl_nvm_type + * @tx_cmd_queue_size: size of the cmd queue. If zero, use the same value as + * the regular queues * * We enable the driver to be backward compatible wrt. hardware features. * API differences in uCode shouldn't be handled here but through TLVs @@ -342,6 +356,7 @@ struct iwl_cfg { const struct iwl_tt_params *thermal_params; enum iwl_device_family device_family; enum iwl_led_mode led_mode; + enum iwl_nvm_type nvm_type; u32 max_data_size; u32 max_inst_size; netdev_features_t features; @@ -369,8 +384,8 @@ struct iwl_cfg { use_tfh:1, gen2:1, cdb:1, - ext_nvm:1, dbgc_supported:1; + u16 tx_cmd_queue_size; u8 valid_tx_ant; u8 valid_rx_ant; u8 non_shared_ant; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-debug.h b/drivers/net/wireless/intel/iwlwifi/iwl-debug.h index cd77c6971753..c023fcf5d452 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-debug.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-debug.h @@ -216,6 +216,7 @@ do { \ #define IWL_DEBUG_TX_REPLY(p, f, a...) IWL_DEBUG(p, IWL_DL_TX_REPLY, f, ## a) #define IWL_DEBUG_TX_QUEUES(p, f, a...) IWL_DEBUG(p, IWL_DL_TX_QUEUES, f, ## a) #define IWL_DEBUG_RADIO(p, f, a...) IWL_DEBUG(p, IWL_DL_RADIO, f, ## a) +#define IWL_DEBUG_DEV_RADIO(p, f, a...) IWL_DEBUG_DEV(p, IWL_DL_RADIO, f, ## a) #define IWL_DEBUG_POWER(p, f, a...) IWL_DEBUG(p, IWL_DL_POWER, f, ## a) #define IWL_DEBUG_11H(p, f, a...) IWL_DEBUG(p, IWL_DL_11H, f, ## a) #define IWL_DEBUG_RPM(p, f, a...) IWL_DEBUG(p, IWL_DL_RPM, f, ## a) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index 99676d6c4713..ccdb247d68c5 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -832,7 +832,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv, capa->standard_phy_calibration_size = le32_to_cpup((__le32 *)tlv_data); break; - case IWL_UCODE_TLV_SEC_RT: + case IWL_UCODE_TLV_SEC_RT: iwl_store_ucode_sec(pieces, tlv_data, IWL_UCODE_REGULAR, tlv_len); drv->fw.type = IWL_FW_MVM; @@ -864,7 +864,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv, FW_PHY_CFG_RX_CHAIN) >> FW_PHY_CFG_RX_CHAIN_POS; break; - case IWL_UCODE_TLV_SECURE_SEC_RT: + case IWL_UCODE_TLV_SECURE_SEC_RT: iwl_store_ucode_sec(pieces, tlv_data, IWL_UCODE_REGULAR, tlv_len); drv->fw.type = IWL_FW_MVM; @@ -1335,7 +1335,8 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context) /* Runtime instructions and 2 copies of data: * 1) unmodified from disk - * 2) backup cache for save/restore during power-downs */ + * 2) backup cache for save/restore during power-downs + */ for (i = 0; i < IWL_UCODE_TYPE_MAX; i++) if (iwl_alloc_ucode(drv, pieces, i)) goto out_free_fw; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index 3014beef4873..8928613e033e 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -68,16 +68,17 @@ #include <linux/export.h> #include <linux/etherdevice.h> #include <linux/pci.h> -#include <linux/acpi.h> + #include "iwl-drv.h" #include "iwl-modparams.h" #include "iwl-nvm-parse.h" #include "iwl-prph.h" #include "iwl-io.h" #include "iwl-csr.h" +#include "fw/acpi.h" /* NVM offsets (in words) definitions */ -enum wkp_nvm_offsets { +enum nvm_offsets { /* NVM HW-Section offset (in words) definitions */ SUBSYSTEM_ID = 0x0A, HW_ADDR = 0x15, @@ -92,7 +93,10 @@ enum wkp_nvm_offsets { /* NVM calibration section offset (in words) definitions */ NVM_CALIB_SECTION = 0x2B8, - XTAL_CALIB = 0x316 - NVM_CALIB_SECTION + XTAL_CALIB = 0x316 - NVM_CALIB_SECTION, + + /* NVM REGULATORY -Section offset (in words) definitions */ + NVM_CHANNELS_SDP = 0, }; enum ext_nvm_offsets { @@ -206,8 +210,36 @@ enum iwl_nvm_channel_flags { NVM_CHANNEL_DC_HIGH = BIT(12), }; +static inline void iwl_nvm_print_channel_flags(struct device *dev, u32 level, + int chan, u16 flags) +{ #define CHECK_AND_PRINT_I(x) \ - ((ch_flags & NVM_CHANNEL_##x) ? # x " " : "") + ((flags & NVM_CHANNEL_##x) ? " " #x : "") + + if (!(flags & NVM_CHANNEL_VALID)) { + IWL_DEBUG_DEV(dev, level, "Ch. %d: 0x%x: No traffic\n", + chan, flags); + return; + } + + /* Note: already can print up to 101 characters, 110 is the limit! */ + IWL_DEBUG_DEV(dev, level, + "Ch. %d: 0x%x:%s%s%s%s%s%s%s%s%s%s%s%s\n", + chan, flags, + CHECK_AND_PRINT_I(VALID), + CHECK_AND_PRINT_I(IBSS), + CHECK_AND_PRINT_I(ACTIVE), + CHECK_AND_PRINT_I(RADAR), + CHECK_AND_PRINT_I(INDOOR_ONLY), + CHECK_AND_PRINT_I(GO_CONCURRENT), + CHECK_AND_PRINT_I(UNIFORM), + CHECK_AND_PRINT_I(20MHZ), + CHECK_AND_PRINT_I(40MHZ), + CHECK_AND_PRINT_I(80MHZ), + CHECK_AND_PRINT_I(160MHZ), + CHECK_AND_PRINT_I(DC_HIGH)); +#undef CHECK_AND_PRINT_I +} static u32 iwl_get_channel_flags(u8 ch_num, int ch_idx, bool is_5ghz, u16 nvm_flags, const struct iwl_cfg *cfg) @@ -215,7 +247,7 @@ static u32 iwl_get_channel_flags(u8 ch_num, int ch_idx, bool is_5ghz, u32 flags = IEEE80211_CHAN_NO_HT40; u32 last_5ghz_ht = LAST_5GHZ_HT; - if (cfg->ext_nvm) + if (cfg->nvm_type == IWL_NVM_EXT) last_5ghz_ht = LAST_5GHZ_HT_FAMILY_8000; if (!is_5ghz && (nvm_flags & NVM_CHANNEL_40MHZ)) { @@ -268,7 +300,7 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg, int num_of_ch, num_2ghz_channels; const u8 *nvm_chan; - if (!cfg->ext_nvm) { + if (cfg->nvm_type != IWL_NVM_EXT) { num_of_ch = IWL_NUM_CHANNELS; nvm_chan = &iwl_nvm_channels[0]; num_2ghz_channels = NUM_2GHZ_CHANNELS; @@ -302,12 +334,8 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg, * supported, hence we still want to add them to * the list of supported channels to cfg80211. */ - IWL_DEBUG_EEPROM(dev, - "Ch. %d Flags %x [%sGHz] - No traffic\n", - nvm_chan[ch_idx], - ch_flags, - (ch_idx >= num_2ghz_channels) ? - "5.2" : "2.4"); + iwl_nvm_print_channel_flags(dev, IWL_DL_EEPROM, + nvm_chan[ch_idx], ch_flags); continue; } @@ -337,27 +365,10 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg, else channel->flags = 0; - IWL_DEBUG_EEPROM(dev, - "Ch. %d [%sGHz] flags 0x%x %s%s%s%s%s%s%s%s%s%s%s%s(%ddBm): Ad-Hoc %ssupported\n", - channel->hw_value, - is_5ghz ? "5.2" : "2.4", - ch_flags, - CHECK_AND_PRINT_I(VALID), - CHECK_AND_PRINT_I(IBSS), - CHECK_AND_PRINT_I(ACTIVE), - CHECK_AND_PRINT_I(RADAR), - CHECK_AND_PRINT_I(INDOOR_ONLY), - CHECK_AND_PRINT_I(GO_CONCURRENT), - CHECK_AND_PRINT_I(UNIFORM), - CHECK_AND_PRINT_I(20MHZ), - CHECK_AND_PRINT_I(40MHZ), - CHECK_AND_PRINT_I(80MHZ), - CHECK_AND_PRINT_I(160MHZ), - CHECK_AND_PRINT_I(DC_HIGH), - channel->max_power, - ((ch_flags & NVM_CHANNEL_IBSS) && - !(ch_flags & NVM_CHANNEL_RADAR)) - ? "" : "not "); + iwl_nvm_print_channel_flags(dev, IWL_DL_EEPROM, + channel->hw_value, ch_flags); + IWL_DEBUG_EEPROM(dev, "Ch. %d: %ddBm\n", + channel->hw_value, channel->max_power); } return n_channels; @@ -484,7 +495,7 @@ IWL_EXPORT_SYMBOL(iwl_init_sbands); static int iwl_get_sku(const struct iwl_cfg *cfg, const __le16 *nvm_sw, const __le16 *phy_sku) { - if (!cfg->ext_nvm) + if (cfg->nvm_type != IWL_NVM_EXT) return le16_to_cpup(nvm_sw + SKU); return le32_to_cpup((__le32 *)(phy_sku + SKU_FAMILY_8000)); @@ -492,7 +503,7 @@ static int iwl_get_sku(const struct iwl_cfg *cfg, const __le16 *nvm_sw, static int iwl_get_nvm_version(const struct iwl_cfg *cfg, const __le16 *nvm_sw) { - if (!cfg->ext_nvm) + if (cfg->nvm_type != IWL_NVM_EXT) return le16_to_cpup(nvm_sw + NVM_VERSION); else return le32_to_cpup((__le32 *)(nvm_sw + @@ -502,7 +513,7 @@ static int iwl_get_nvm_version(const struct iwl_cfg *cfg, const __le16 *nvm_sw) static int iwl_get_radio_cfg(const struct iwl_cfg *cfg, const __le16 *nvm_sw, const __le16 *phy_sku) { - if (!cfg->ext_nvm) + if (cfg->nvm_type != IWL_NVM_EXT) return le16_to_cpup(nvm_sw + RADIO_CFG); return le32_to_cpup((__le32 *)(phy_sku + RADIO_CFG_FAMILY_EXT_NVM)); @@ -513,7 +524,7 @@ static int iwl_get_n_hw_addrs(const struct iwl_cfg *cfg, const __le16 *nvm_sw) { int n_hw_addr; - if (!cfg->ext_nvm) + if (cfg->nvm_type != IWL_NVM_EXT) return le16_to_cpup(nvm_sw + N_HW_ADDRS); n_hw_addr = le32_to_cpup((__le32 *)(nvm_sw + N_HW_ADDRS_FAMILY_8000)); @@ -525,7 +536,7 @@ static void iwl_set_radio_cfg(const struct iwl_cfg *cfg, struct iwl_nvm_data *data, u32 radio_cfg) { - if (!cfg->ext_nvm) { + if (cfg->nvm_type != IWL_NVM_EXT) { data->radio_cfg_type = NVM_RF_CFG_TYPE_MSK(radio_cfg); data->radio_cfg_step = NVM_RF_CFG_STEP_MSK(radio_cfg); data->radio_cfg_dash = NVM_RF_CFG_DASH_MSK(radio_cfg); @@ -634,7 +645,7 @@ static int iwl_set_hw_address(struct iwl_trans *trans, { if (cfg->mac_addr_from_csr) { iwl_set_hw_address_from_csr(trans, data); - } else if (!cfg->ext_nvm) { + } else if (cfg->nvm_type != IWL_NVM_EXT) { const u8 *hw_addr = (const u8 *)(nvm_hw + HW_ADDR); /* The byte order is little endian 16 bit, meaning 214365 */ @@ -706,7 +717,7 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg, u16 lar_config; const __le16 *ch_section; - if (!cfg->ext_nvm) + if (cfg->nvm_type != IWL_NVM_EXT) data = kzalloc(sizeof(*data) + sizeof(struct ieee80211_channel) * IWL_NUM_CHANNELS, @@ -740,7 +751,7 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg, data->n_hw_addrs = iwl_get_n_hw_addrs(cfg, nvm_sw); - if (!cfg->ext_nvm) { + if (cfg->nvm_type != IWL_NVM_EXT) { /* Checking for required sections */ if (!nvm_calib) { IWL_ERR(trans, @@ -748,11 +759,15 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg, kfree(data); return NULL; } + + ch_section = cfg->nvm_type == IWL_NVM_SDP ? + ®ulatory[NVM_CHANNELS_SDP] : + &nvm_sw[NVM_CHANNELS]; + /* in family 8000 Xtal calibration values moved to OTP */ data->xtal_calib[0] = *(nvm_calib + XTAL_CALIB); data->xtal_calib[1] = *(nvm_calib + XTAL_CALIB + 1); lar_enabled = true; - ch_section = &nvm_sw[NVM_CHANNELS]; } else { u16 lar_offset = data->nvm_version < 0xE39 ? NVM_LAR_OFFSET_OLD : @@ -786,7 +801,7 @@ static u32 iwl_nvm_get_regdom_bw_flags(const u8 *nvm_chan, u32 flags = NL80211_RRF_NO_HT40; u32 last_5ghz_ht = LAST_5GHZ_HT; - if (cfg->ext_nvm) + if (cfg->nvm_type == IWL_NVM_EXT) last_5ghz_ht = LAST_5GHZ_HT_FAMILY_8000; if (ch_idx < NUM_2GHZ_CHANNELS && @@ -834,7 +849,7 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, int ch_idx; u16 ch_flags; u32 reg_rule_flags, prev_reg_rule_flags = 0; - const u8 *nvm_chan = cfg->ext_nvm ? + const u8 *nvm_chan = cfg->nvm_type == IWL_NVM_EXT ? iwl_ext_nvm_channels : iwl_nvm_channels; struct ieee80211_regdomain *regd; int size_of_regd; @@ -843,7 +858,7 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, int center_freq, prev_center_freq = 0; int valid_rules = 0; bool new_rule; - int max_num_ch = cfg->ext_nvm ? + int max_num_ch = cfg->nvm_type == IWL_NVM_EXT ? IWL_NUM_CHANNELS_EXT : IWL_NUM_CHANNELS; if (WARN_ON_ONCE(num_of_ch > NL80211_MAX_SUPP_REG_RULES)) @@ -873,12 +888,8 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, new_rule = false; if (!(ch_flags & NVM_CHANNEL_VALID)) { - IWL_DEBUG_DEV(dev, IWL_DL_LAR, - "Ch. %d Flags %x [%sGHz] - No traffic\n", - nvm_chan[ch_idx], - ch_flags, - (ch_idx >= NUM_2GHZ_CHANNELS) ? - "5.2" : "2.4"); + iwl_nvm_print_channel_flags(dev, IWL_DL_LAR, + nvm_chan[ch_idx], ch_flags); continue; } @@ -914,31 +925,8 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, prev_center_freq = center_freq; prev_reg_rule_flags = reg_rule_flags; - IWL_DEBUG_DEV(dev, IWL_DL_LAR, - "Ch. %d [%sGHz] %s%s%s%s%s%s%s%s%s%s%s%s(0x%02x)\n", - center_freq, - band == NL80211_BAND_5GHZ ? "5.2" : "2.4", - CHECK_AND_PRINT_I(VALID), - CHECK_AND_PRINT_I(IBSS), - CHECK_AND_PRINT_I(ACTIVE), - CHECK_AND_PRINT_I(RADAR), - CHECK_AND_PRINT_I(INDOOR_ONLY), - CHECK_AND_PRINT_I(GO_CONCURRENT), - CHECK_AND_PRINT_I(UNIFORM), - CHECK_AND_PRINT_I(20MHZ), - CHECK_AND_PRINT_I(40MHZ), - CHECK_AND_PRINT_I(80MHZ), - CHECK_AND_PRINT_I(160MHZ), - CHECK_AND_PRINT_I(DC_HIGH), - ch_flags); - IWL_DEBUG_DEV(dev, IWL_DL_LAR, - "Ch. %d [%sGHz] reg_flags 0x%x: %s\n", - center_freq, - band == NL80211_BAND_5GHZ ? "5.2" : "2.4", - reg_rule_flags, - ((ch_flags & NVM_CHANNEL_ACTIVE) && - !(ch_flags & NVM_CHANNEL_RADAR)) - ? "Ad-Hoc" : ""); + iwl_nvm_print_channel_flags(dev, IWL_DL_LAR, + nvm_chan[ch_idx], ch_flags); } regd->n_reg_rules = valid_rules; @@ -950,91 +938,3 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, return regd; } IWL_EXPORT_SYMBOL(iwl_parse_nvm_mcc_info); - -#ifdef CONFIG_ACPI -#define WRDD_METHOD "WRDD" -#define WRDD_WIFI (0x07) -#define WRDD_WIGIG (0x10) - -static u32 iwl_wrdd_get_mcc(struct device *dev, union acpi_object *wrdd) -{ - union acpi_object *mcc_pkg, *domain_type, *mcc_value; - u32 i; - - if (wrdd->type != ACPI_TYPE_PACKAGE || - wrdd->package.count < 2 || - wrdd->package.elements[0].type != ACPI_TYPE_INTEGER || - wrdd->package.elements[0].integer.value != 0) { - IWL_DEBUG_EEPROM(dev, "Unsupported wrdd structure\n"); - return 0; - } - - for (i = 1 ; i < wrdd->package.count ; ++i) { - mcc_pkg = &wrdd->package.elements[i]; - - if (mcc_pkg->type != ACPI_TYPE_PACKAGE || - mcc_pkg->package.count < 2 || - mcc_pkg->package.elements[0].type != ACPI_TYPE_INTEGER || - mcc_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) { - mcc_pkg = NULL; - continue; - } - - domain_type = &mcc_pkg->package.elements[0]; - if (domain_type->integer.value == WRDD_WIFI) - break; - - mcc_pkg = NULL; - } - - if (mcc_pkg) { - mcc_value = &mcc_pkg->package.elements[1]; - return mcc_value->integer.value; - } - - return 0; -} - -int iwl_get_bios_mcc(struct device *dev, char *mcc) -{ - acpi_handle root_handle; - acpi_handle handle; - struct acpi_buffer wrdd = {ACPI_ALLOCATE_BUFFER, NULL}; - acpi_status status; - u32 mcc_val; - - root_handle = ACPI_HANDLE(dev); - if (!root_handle) { - IWL_DEBUG_EEPROM(dev, - "Could not retrieve root port ACPI handle\n"); - return -ENOENT; - } - - /* Get the method's handle */ - status = acpi_get_handle(root_handle, (acpi_string)WRDD_METHOD, - &handle); - if (ACPI_FAILURE(status)) { - IWL_DEBUG_EEPROM(dev, "WRD method not found\n"); - return -ENOENT; - } - - /* Call WRDD with no arguments */ - status = acpi_evaluate_object(handle, NULL, NULL, &wrdd); - if (ACPI_FAILURE(status)) { - IWL_DEBUG_EEPROM(dev, "WRDC invocation failed (0x%x)\n", - status); - return -ENOENT; - } - - mcc_val = iwl_wrdd_get_mcc(dev, wrdd.pointer); - kfree(wrdd.pointer); - if (!mcc_val) - return -ENOENT; - - mcc[0] = (mcc_val >> 8) & 0xff; - mcc[1] = mcc_val & 0xff; - mcc[2] = '\0'; - return 0; -} -IWL_EXPORT_SYMBOL(iwl_get_bios_mcc); -#endif diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h index 2d1a24dd8410..306736c7a042 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h @@ -109,21 +109,4 @@ struct ieee80211_regdomain * iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, int num_of_ch, __le32 *channels, u16 fw_mcc); -#ifdef CONFIG_ACPI -/** - * iwl_get_bios_mcc - read MCC from BIOS, if available - * - * @dev: the struct device - * @mcc: output buffer (3 bytes) that will get the MCC - * - * This function tries to read the current MCC from ACPI if available. - */ -int iwl_get_bios_mcc(struct device *dev, char *mcc); -#else -static inline int iwl_get_bios_mcc(struct device *dev, char *mcc) -{ - return -ENOENT; -} -#endif - #endif /* __iwl_nvm_parse_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c index 784bdd0ed233..7e9c924e1220 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c @@ -6,6 +6,7 @@ * GPL LICENSE SUMMARY * * Copyright(c) 2015 Intel Mobile Communications GmbH + * Copyright(c) 2016 - 2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -31,6 +32,7 @@ * BSD LICENSE * * Copyright(c) 2015 Intel Mobile Communications GmbH + * Copyright(c) 2016 - 2017 Intel Deutschland GmbH * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -205,3 +207,17 @@ int iwl_cmd_groups_verify_sorted(const struct iwl_trans_config *trans) return 0; } IWL_EXPORT_SYMBOL(iwl_cmd_groups_verify_sorted); + +void iwl_trans_ref(struct iwl_trans *trans) +{ + if (trans->ops->ref) + trans->ops->ref(trans); +} +IWL_EXPORT_SYMBOL(iwl_trans_ref); + +void iwl_trans_unref(struct iwl_trans *trans) +{ + if (trans->ops->unref) + trans->ops->unref(trans); +} +IWL_EXPORT_SYMBOL(iwl_trans_unref); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h index e90abbfba718..bba4f54cbbbb 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h @@ -749,8 +749,6 @@ struct iwl_trans { struct lockdep_map sync_cmd_lockdep_map; #endif - u64 dflt_pwr_limit; - const struct iwl_fw_dbg_dest_tlv *dbg_dest_tlv; const struct iwl_fw_dbg_conf_tlv *dbg_conf_tlv[FW_DBG_CONF_MAX]; struct iwl_fw_dbg_trigger_tlv * const *dbg_trigger_tlv; @@ -875,18 +873,6 @@ static inline int iwl_trans_d3_resume(struct iwl_trans *trans, return trans->ops->d3_resume(trans, status, test, reset); } -static inline void iwl_trans_ref(struct iwl_trans *trans) -{ - if (trans->ops->ref) - trans->ops->ref(trans); -} - -static inline void iwl_trans_unref(struct iwl_trans *trans) -{ - if (trans->ops->unref) - trans->ops->unref(trans); -} - static inline int iwl_trans_suspend(struct iwl_trans *trans) { if (!trans->ops->suspend) @@ -1191,6 +1177,8 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size, const struct iwl_cfg *cfg, const struct iwl_trans_ops *ops); void iwl_trans_free(struct iwl_trans *trans); +void iwl_trans_ref(struct iwl_trans *trans); +void iwl_trans_unref(struct iwl_trans *trans); /***************************************************** * driver (transport) register/unregister functions diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index b205a7bfb828..b1f73dcabd31 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -664,6 +664,7 @@ static int iwl_mvm_d3_reprogram(struct iwl_mvm *mvm, struct ieee80211_vif *vif, int ret, i; struct iwl_binding_cmd binding_cmd = {}; struct iwl_time_quota_cmd quota_cmd = {}; + struct iwl_time_quota_data *quota; u32 status; int size; @@ -745,17 +746,20 @@ static int iwl_mvm_d3_reprogram(struct iwl_mvm *mvm, struct ieee80211_vif *vif, return ret; /* and some quota */ - quota_cmd.quotas[0].id_and_color = + quota = iwl_mvm_quota_cmd_get_quota(mvm, "a_cmd, 0); + quota->id_and_color = cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->phy_ctxt->id, mvmvif->phy_ctxt->color)); - quota_cmd.quotas[0].quota = cpu_to_le32(IWL_MVM_MAX_QUOTA); - quota_cmd.quotas[0].max_duration = cpu_to_le32(IWL_MVM_MAX_QUOTA); + quota->quota = cpu_to_le32(IWL_MVM_MAX_QUOTA); + quota->max_duration = cpu_to_le32(IWL_MVM_MAX_QUOTA); - for (i = 1; i < MAX_BINDINGS; i++) - quota_cmd.quotas[i].id_and_color = cpu_to_le32(FW_CTXT_INVALID); + for (i = 1; i < MAX_BINDINGS; i++) { + quota = iwl_mvm_quota_cmd_get_quota(mvm, "a_cmd, i); + quota->id_and_color = cpu_to_le32(FW_CTXT_INVALID); + } ret = iwl_mvm_send_cmd_pdu(mvm, TIME_QUOTA_CMD, 0, - sizeof(quota_cmd), "a_cmd); + iwl_mvm_quota_cmd_size(mvm), "a_cmd); if (ret) IWL_ERR(mvm, "Failed to send quota: %d\n", ret); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c index 71a01df96f8b..4228fac77f41 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c @@ -1455,80 +1455,6 @@ static const char * const chanwidths[] = { [NL80211_CHAN_WIDTH_160] = "vht160", }; -static bool iwl_mvm_lqm_notif_wait(struct iwl_notif_wait_data *notif_wait, - struct iwl_rx_packet *pkt, void *data) -{ - struct ieee80211_vif *vif = data; - struct iwl_mvm *mvm = - container_of(notif_wait, struct iwl_mvm, notif_wait); - struct iwl_link_qual_msrmnt_notif *report = (void *)pkt->data; - u32 num_of_stations = le32_to_cpu(report->number_of_stations); - int i; - - IWL_INFO(mvm, "LQM report:\n"); - IWL_INFO(mvm, "\tstatus: %d\n", report->status); - IWL_INFO(mvm, "\tmacID: %d\n", le32_to_cpu(report->mac_id)); - IWL_INFO(mvm, "\ttx_frame_dropped: %d\n", - le32_to_cpu(report->tx_frame_dropped)); - IWL_INFO(mvm, "\ttime_in_measurement_window: %d us\n", - le32_to_cpu(report->time_in_measurement_window)); - IWL_INFO(mvm, "\ttotal_air_time_other_stations: %d\n", - le32_to_cpu(report->total_air_time_other_stations)); - IWL_INFO(mvm, "\tchannel_freq: %d\n", - vif->bss_conf.chandef.center_freq1); - IWL_INFO(mvm, "\tchannel_width: %s\n", - chanwidths[vif->bss_conf.chandef.width]); - IWL_INFO(mvm, "\tnumber_of_stations: %d\n", num_of_stations); - for (i = 0; i < num_of_stations; i++) - IWL_INFO(mvm, "\t\tsta[%d]: %d\n", i, - report->frequent_stations_air_time[i]); - - return true; -} - -static ssize_t iwl_dbgfs_lqm_send_cmd_write(struct ieee80211_vif *vif, - char *buf, size_t count, - loff_t *ppos) -{ - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_mvm *mvm = mvmvif->mvm; - struct iwl_notification_wait wait_lqm_notif; - static u16 lqm_notif[] = { - WIDE_ID(MAC_CONF_GROUP, - LINK_QUALITY_MEASUREMENT_COMPLETE_NOTIF) - }; - int err; - u32 duration; - u32 timeout; - - if (sscanf(buf, "%d,%d", &duration, &timeout) != 2) - return -EINVAL; - - iwl_init_notification_wait(&mvm->notif_wait, &wait_lqm_notif, - lqm_notif, ARRAY_SIZE(lqm_notif), - iwl_mvm_lqm_notif_wait, vif); - mutex_lock(&mvm->mutex); - err = iwl_mvm_send_lqm_cmd(vif, LQM_CMD_OPERATION_START_MEASUREMENT, - duration, timeout); - mutex_unlock(&mvm->mutex); - - if (err) { - IWL_ERR(mvm, "Failed to send lqm cmdf(err=%d)\n", err); - iwl_remove_notification(&mvm->notif_wait, &wait_lqm_notif); - return err; - } - - /* wait for 2 * timeout (safety guard) and convert to jiffies*/ - timeout = msecs_to_jiffies((timeout * 2) / 1000); - - err = iwl_wait_notification(&mvm->notif_wait, &wait_lqm_notif, - timeout); - if (err) - IWL_ERR(mvm, "Getting lqm notif timed out\n"); - - return count; -} - #define MVM_DEBUGFS_WRITE_FILE_OPS(name, bufsz) \ _MVM_DEBUGFS_WRITE_FILE_OPS(name, bufsz, struct ieee80211_vif) #define MVM_DEBUGFS_READ_WRITE_FILE_OPS(name, bufsz) \ @@ -1553,7 +1479,6 @@ MVM_DEBUGFS_READ_WRITE_FILE_OPS(tof_range_abort, 32); MVM_DEBUGFS_READ_FILE_OPS(tof_range_response); MVM_DEBUGFS_READ_WRITE_FILE_OPS(tof_responder_params, 32); MVM_DEBUGFS_READ_WRITE_FILE_OPS(quota_min, 32); -MVM_DEBUGFS_WRITE_FILE_OPS(lqm_send_cmd, 64); MVM_DEBUGFS_READ_FILE_OPS(os_device_timediff); @@ -1594,7 +1519,6 @@ void iwl_mvm_vif_dbgfs_register(struct iwl_mvm *mvm, struct ieee80211_vif *vif) S_IRUSR | S_IWUSR); MVM_DEBUGFS_ADD_FILE_VIF(quota_min, mvmvif->dbgfs_dir, S_IRUSR | S_IWUSR); - MVM_DEBUGFS_ADD_FILE_VIF(lqm_send_cmd, mvmvif->dbgfs_dir, S_IWUSR); MVM_DEBUGFS_ADD_FILE_VIF(os_device_timediff, mvmvif->dbgfs_dir, S_IRUSR); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c index e97904c2c4d4..2ff594f11259 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c @@ -660,6 +660,36 @@ out: return ret ?: count; } +static ssize_t iwl_dbgfs_fw_ver_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct iwl_mvm *mvm = file->private_data; + char *buff, *pos, *endpos; + static const size_t bufsz = 1024; + int ret; + + buff = kmalloc(bufsz, GFP_KERNEL); + if (!buff) + return -ENOMEM; + + pos = buff; + endpos = pos + bufsz; + + pos += scnprintf(pos, endpos - pos, "FW prefix: %s\n", + mvm->trans->cfg->fw_name_pre); + pos += scnprintf(pos, endpos - pos, "FW: %s\n", + mvm->fwrt.fw->human_readable); + pos += scnprintf(pos, endpos - pos, "Device: %s\n", + mvm->fwrt.trans->cfg->name); + pos += scnprintf(pos, endpos - pos, "Bus: %s\n", + mvm->fwrt.dev->bus->name); + + ret = simple_read_from_buffer(user_buf, count, ppos, buff, pos - buff); + kfree(buff); + + return ret; +} + #define PRINT_STATS_LE32(_struct, _memb) \ pos += scnprintf(buf + pos, bufsz - pos, \ fmt_table, #_memb, \ @@ -1662,6 +1692,7 @@ MVM_DEBUGFS_READ_FILE_OPS(bt_cmd); MVM_DEBUGFS_READ_WRITE_FILE_OPS(disable_power_off, 64); MVM_DEBUGFS_READ_FILE_OPS(fw_rx_stats); MVM_DEBUGFS_READ_FILE_OPS(drv_rx_stats); +MVM_DEBUGFS_READ_FILE_OPS(fw_ver); MVM_DEBUGFS_WRITE_FILE_OPS(fw_restart, 10); MVM_DEBUGFS_WRITE_FILE_OPS(fw_nmi, 10); MVM_DEBUGFS_WRITE_FILE_OPS(bt_tx_prio, 10); @@ -1843,6 +1874,7 @@ int iwl_mvm_dbgfs_register(struct iwl_mvm *mvm, struct dentry *dbgfs_dir) MVM_DEBUGFS_ADD_FILE(bt_cmd, dbgfs_dir, S_IRUSR); MVM_DEBUGFS_ADD_FILE(disable_power_off, mvm->debugfs_dir, S_IRUSR | S_IWUSR); + MVM_DEBUGFS_ADD_FILE(fw_ver, mvm->debugfs_dir, S_IRUSR); MVM_DEBUGFS_ADD_FILE(fw_rx_stats, mvm->debugfs_dir, S_IRUSR); MVM_DEBUGFS_ADD_FILE(drv_rx_stats, mvm->debugfs_dir, S_IRUSR); MVM_DEBUGFS_ADD_FILE(fw_restart, mvm->debugfs_dir, S_IWUSR); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 83485493a79a..f476882291ae 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -66,7 +66,6 @@ *****************************************************************************/ #include <net/mac80211.h> #include <linux/netdevice.h> -#include <linux/acpi.h> #include "iwl-trans.h" #include "iwl-op-mode.h" @@ -75,7 +74,7 @@ #include "iwl-csr.h" /* for iwl_mvm_rx_card_state_notif */ #include "iwl-io.h" /* for iwl_mvm_rx_card_state_notif */ #include "iwl-prph.h" -#include "iwl-eeprom-parse.h" +#include "fw/acpi.h" #include "mvm.h" #include "fw/dbg.h" @@ -579,17 +578,6 @@ static int iwl_mvm_config_ltr(struct iwl_mvm *mvm) } #ifdef CONFIG_ACPI -#define ACPI_WRDS_METHOD "WRDS" -#define ACPI_EWRD_METHOD "EWRD" -#define ACPI_WGDS_METHOD "WGDS" -#define ACPI_WIFI_DOMAIN (0x07) -#define ACPI_WRDS_WIFI_DATA_SIZE (IWL_MVM_SAR_TABLE_SIZE + 2) -#define ACPI_EWRD_WIFI_DATA_SIZE ((IWL_MVM_SAR_PROFILE_NUM - 1) * \ - IWL_MVM_SAR_TABLE_SIZE + 3) -#define ACPI_WGDS_WIFI_DATA_SIZE 18 -#define ACPI_WGDS_NUM_BANDS 2 -#define ACPI_WGDS_TABLE_SIZE 3 - static int iwl_mvm_sar_set_profile(struct iwl_mvm *mvm, union acpi_object *table, struct iwl_mvm_sar_profile *profile, @@ -599,7 +587,7 @@ static int iwl_mvm_sar_set_profile(struct iwl_mvm *mvm, profile->enabled = enabled; - for (i = 0; i < IWL_MVM_SAR_TABLE_SIZE; i++) { + for (i = 0; i < ACPI_SAR_TABLE_SIZE; i++) { if ((table[i].type != ACPI_TYPE_INTEGER) || (table[i].integer.value > U8_MAX)) return -EINVAL; @@ -610,88 +598,18 @@ static int iwl_mvm_sar_set_profile(struct iwl_mvm *mvm, return 0; } -static union acpi_object *iwl_mvm_sar_find_wifi_pkg(struct iwl_mvm *mvm, - union acpi_object *data, - int data_size) -{ - union acpi_object *wifi_pkg = NULL; - int i; - - /* - * We need at least two packages, one for the revision and one - * for the data itself. Also check that the revision is valid - * (i.e. it is an integer set to 0). - */ - if (data->type != ACPI_TYPE_PACKAGE || - data->package.count < 2 || - data->package.elements[0].type != ACPI_TYPE_INTEGER || - data->package.elements[0].integer.value != 0) { - IWL_DEBUG_RADIO(mvm, "Unsupported packages structure\n"); - return ERR_PTR(-EINVAL); - } - - /* loop through all the packages to find the one for WiFi */ - for (i = 1; i < data->package.count; i++) { - union acpi_object *domain; - - wifi_pkg = &data->package.elements[i]; - - /* Skip anything that is not a package with the right - * amount of elements (i.e. domain_type, - * enabled/disabled plus the actual data size. - */ - if (wifi_pkg->type != ACPI_TYPE_PACKAGE || - wifi_pkg->package.count != data_size) - continue; - - domain = &wifi_pkg->package.elements[0]; - if (domain->type == ACPI_TYPE_INTEGER && - domain->integer.value == ACPI_WIFI_DOMAIN) - break; - - wifi_pkg = NULL; - } - - if (!wifi_pkg) - return ERR_PTR(-ENOENT); - - return wifi_pkg; -} - static int iwl_mvm_sar_get_wrds_table(struct iwl_mvm *mvm) { - union acpi_object *wifi_pkg, *table; - acpi_handle root_handle; - acpi_handle handle; - struct acpi_buffer wrds = {ACPI_ALLOCATE_BUFFER, NULL}; - acpi_status status; + union acpi_object *wifi_pkg, *table, *data; bool enabled; int ret; - root_handle = ACPI_HANDLE(mvm->dev); - if (!root_handle) { - IWL_DEBUG_RADIO(mvm, - "Could not retrieve root port ACPI handle\n"); - return -ENOENT; - } - - /* Get the method's handle */ - status = acpi_get_handle(root_handle, (acpi_string)ACPI_WRDS_METHOD, - &handle); - if (ACPI_FAILURE(status)) { - IWL_DEBUG_RADIO(mvm, "WRDS method not found\n"); - return -ENOENT; - } - - /* Call WRDS with no arguments */ - status = acpi_evaluate_object(handle, NULL, NULL, &wrds); - if (ACPI_FAILURE(status)) { - IWL_DEBUG_RADIO(mvm, "WRDS invocation failed (0x%x)\n", status); - return -ENOENT; - } + data = iwl_acpi_get_object(mvm->dev, ACPI_WRDS_METHOD); + if (IS_ERR(data)) + return PTR_ERR(data); - wifi_pkg = iwl_mvm_sar_find_wifi_pkg(mvm, wrds.pointer, - ACPI_WRDS_WIFI_DATA_SIZE); + wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data, + ACPI_WRDS_WIFI_DATA_SIZE); if (IS_ERR(wifi_pkg)) { ret = PTR_ERR(wifi_pkg); goto out_free; @@ -712,46 +630,23 @@ static int iwl_mvm_sar_get_wrds_table(struct iwl_mvm *mvm) */ ret = iwl_mvm_sar_set_profile(mvm, table, &mvm->sar_profiles[0], enabled); - out_free: - kfree(wrds.pointer); + kfree(data); return ret; } static int iwl_mvm_sar_get_ewrd_table(struct iwl_mvm *mvm) { - union acpi_object *wifi_pkg; - acpi_handle root_handle; - acpi_handle handle; - struct acpi_buffer ewrd = {ACPI_ALLOCATE_BUFFER, NULL}; - acpi_status status; + union acpi_object *wifi_pkg, *data; bool enabled; int i, n_profiles, ret; - root_handle = ACPI_HANDLE(mvm->dev); - if (!root_handle) { - IWL_DEBUG_RADIO(mvm, - "Could not retrieve root port ACPI handle\n"); - return -ENOENT; - } - - /* Get the method's handle */ - status = acpi_get_handle(root_handle, (acpi_string)ACPI_EWRD_METHOD, - &handle); - if (ACPI_FAILURE(status)) { - IWL_DEBUG_RADIO(mvm, "EWRD method not found\n"); - return -ENOENT; - } + data = iwl_acpi_get_object(mvm->dev, ACPI_EWRD_METHOD); + if (IS_ERR(data)) + return PTR_ERR(data); - /* Call EWRD with no arguments */ - status = acpi_evaluate_object(handle, NULL, NULL, &ewrd); - if (ACPI_FAILURE(status)) { - IWL_DEBUG_RADIO(mvm, "EWRD invocation failed (0x%x)\n", status); - return -ENOENT; - } - - wifi_pkg = iwl_mvm_sar_find_wifi_pkg(mvm, ewrd.pointer, - ACPI_EWRD_WIFI_DATA_SIZE); + wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data, + ACPI_EWRD_WIFI_DATA_SIZE); if (IS_ERR(wifi_pkg)) { ret = PTR_ERR(wifi_pkg); goto out_free; @@ -788,55 +683,33 @@ static int iwl_mvm_sar_get_ewrd_table(struct iwl_mvm *mvm) break; /* go to the next table */ - pos += IWL_MVM_SAR_TABLE_SIZE; + pos += ACPI_SAR_TABLE_SIZE; } out_free: - kfree(ewrd.pointer); + kfree(data); return ret; } static int iwl_mvm_sar_get_wgds_table(struct iwl_mvm *mvm) { - union acpi_object *wifi_pkg; - acpi_handle root_handle; - acpi_handle handle; - struct acpi_buffer wgds = {ACPI_ALLOCATE_BUFFER, NULL}; - acpi_status status; + union acpi_object *wifi_pkg, *data; int i, j, ret; int idx = 1; - root_handle = ACPI_HANDLE(mvm->dev); - if (!root_handle) { - IWL_DEBUG_RADIO(mvm, - "Could not retrieve root port ACPI handle\n"); - return -ENOENT; - } + data = iwl_acpi_get_object(mvm->dev, ACPI_WGDS_METHOD); + if (IS_ERR(data)) + return PTR_ERR(data); - /* Get the method's handle */ - status = acpi_get_handle(root_handle, (acpi_string)ACPI_WGDS_METHOD, - &handle); - if (ACPI_FAILURE(status)) { - IWL_DEBUG_RADIO(mvm, "WGDS method not found\n"); - return -ENOENT; - } - - /* Call WGDS with no arguments */ - status = acpi_evaluate_object(handle, NULL, NULL, &wgds); - if (ACPI_FAILURE(status)) { - IWL_DEBUG_RADIO(mvm, "WGDS invocation failed (0x%x)\n", status); - return -ENOENT; - } - - wifi_pkg = iwl_mvm_sar_find_wifi_pkg(mvm, wgds.pointer, - ACPI_WGDS_WIFI_DATA_SIZE); + wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data, + ACPI_WGDS_WIFI_DATA_SIZE); if (IS_ERR(wifi_pkg)) { ret = PTR_ERR(wifi_pkg); goto out_free; } - for (i = 0; i < IWL_NUM_GEO_PROFILES; i++) { - for (j = 0; j < IWL_MVM_GEO_TABLE_SIZE; j++) { + for (i = 0; i < ACPI_NUM_GEO_PROFILES; i++) { + for (j = 0; j < ACPI_GEO_TABLE_SIZE; j++) { union acpi_object *entry; entry = &wifi_pkg->package.elements[idx++]; @@ -851,7 +724,7 @@ static int iwl_mvm_sar_get_wgds_table(struct iwl_mvm *mvm) } ret = 0; out_free: - kfree(wgds.pointer); + kfree(data); return ret; } @@ -861,25 +734,25 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b) .v3.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_CHAINS), }; int i, j, idx; - int profs[IWL_NUM_CHAIN_LIMITS] = { prof_a, prof_b }; + int profs[ACPI_SAR_NUM_CHAIN_LIMITS] = { prof_a, prof_b }; int len = sizeof(cmd); - BUILD_BUG_ON(IWL_NUM_CHAIN_LIMITS < 2); - BUILD_BUG_ON(IWL_NUM_CHAIN_LIMITS * IWL_NUM_SUB_BANDS != - IWL_MVM_SAR_TABLE_SIZE); + BUILD_BUG_ON(ACPI_SAR_NUM_CHAIN_LIMITS < 2); + BUILD_BUG_ON(ACPI_SAR_NUM_CHAIN_LIMITS * ACPI_SAR_NUM_SUB_BANDS != + ACPI_SAR_TABLE_SIZE); if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_TX_POWER_ACK)) len = sizeof(cmd.v3); - for (i = 0; i < IWL_NUM_CHAIN_LIMITS; i++) { + for (i = 0; i < ACPI_SAR_NUM_CHAIN_LIMITS; i++) { struct iwl_mvm_sar_profile *prof; /* don't allow SAR to be disabled (profile 0 means disable) */ if (profs[i] == 0) return -EPERM; - /* we are off by one, so allow up to IWL_MVM_SAR_PROFILE_NUM */ - if (profs[i] > IWL_MVM_SAR_PROFILE_NUM) + /* we are off by one, so allow up to ACPI_SAR_PROFILE_NUM */ + if (profs[i] > ACPI_SAR_PROFILE_NUM) return -EINVAL; /* profiles go from 1 to 4, so decrement to access the array */ @@ -894,8 +767,8 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b) } IWL_DEBUG_RADIO(mvm, " Chain[%d]:\n", i); - for (j = 0; j < IWL_NUM_SUB_BANDS; j++) { - idx = (i * IWL_NUM_SUB_BANDS) + j; + for (j = 0; j < ACPI_SAR_NUM_SUB_BANDS; j++) { + idx = (i * ACPI_SAR_NUM_SUB_BANDS) + j; cmd.v3.per_chain_restriction[i][j] = cpu_to_le16(prof->table[idx]); IWL_DEBUG_RADIO(mvm, " Band[%d] = %d * .125dBm\n", @@ -931,7 +804,7 @@ int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm) resp = (void *)cmd.resp_pkt->data; ret = le32_to_cpu(resp->profile_idx); - if (WARN_ON(ret > IWL_NUM_GEO_PROFILES)) { + if (WARN_ON(ret > ACPI_NUM_GEO_PROFILES)) { ret = -EIO; IWL_WARN(mvm, "Invalid geographic profile idx (%d)\n", ret); } @@ -959,10 +832,12 @@ static int iwl_mvm_sar_geo_init(struct iwl_mvm *mvm) IWL_DEBUG_RADIO(mvm, "Sending GEO_TX_POWER_LIMIT\n"); - BUILD_BUG_ON(IWL_NUM_GEO_PROFILES * ACPI_WGDS_NUM_BANDS * + BUILD_BUG_ON(ACPI_NUM_GEO_PROFILES * ACPI_WGDS_NUM_BANDS * ACPI_WGDS_TABLE_SIZE != ACPI_WGDS_WIFI_DATA_SIZE); - for (i = 0; i < IWL_NUM_GEO_PROFILES; i++) { + BUILD_BUG_ON(ACPI_NUM_GEO_PROFILES > IWL_NUM_GEO_PROFILES); + + for (i = 0; i < ACPI_NUM_GEO_PROFILES; i++) { struct iwl_per_chain_offset *chain = (struct iwl_per_chain_offset *)&cmd.table[i]; @@ -970,7 +845,7 @@ static int iwl_mvm_sar_geo_init(struct iwl_mvm *mvm) u8 *value; value = &mvm->geo_profiles[i].values[j * - IWL_GEO_PER_CHAIN_SIZE]; + ACPI_GEO_PER_CHAIN_SIZE]; chain[j].max_tx_power = cpu_to_le16(value[0]); chain[j].chain_a = value[1]; chain[j].chain_b = value[2]; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 3bcaa82f59b2..0b3d275fe177 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1077,6 +1077,7 @@ static void iwl_mvm_restart_cleanup(struct iwl_mvm *mvm) mvm->vif_count = 0; mvm->rx_ba_sessions = 0; mvm->fwrt.dump.conf = FW_DBG_INVALID; + mvm->monitor_on = false; /* keep statistics ticking */ iwl_mvm_accu_radio_stats(mvm); @@ -1437,6 +1438,9 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw, mvm->p2p_device_vif = vif; } + if (vif->type == NL80211_IFTYPE_MONITOR) + mvm->monitor_on = true; + iwl_mvm_vif_dbgfs_register(mvm, vif); goto out_unlock; @@ -1526,6 +1530,9 @@ static void iwl_mvm_mac_remove_interface(struct ieee80211_hw *hw, iwl_mvm_power_update_mac(mvm); iwl_mvm_mac_ctxt_remove(mvm, vif); + if (vif->type == NL80211_IFTYPE_MONITOR) + mvm->monitor_on = false; + out_release: mutex_unlock(&mvm->mutex); } @@ -1892,11 +1899,6 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm, if (changes & BSS_CHANGED_ASSOC && bss_conf->assoc) iwl_mvm_mac_ctxt_recalc_tsf_id(mvm, vif); - if (changes & BSS_CHANGED_ASSOC && !bss_conf->assoc && - mvmvif->lqm_active) - iwl_mvm_send_lqm_cmd(vif, LQM_CMD_OPERATION_STOP_MEASUREMENT, - 0, 0); - /* * If we're not associated yet, take the (new) BSSID before associating * so the firmware knows. If we're already associated, then use the old @@ -3425,10 +3427,24 @@ static void iwl_mvm_change_chanctx(struct ieee80211_hw *hw, return; mutex_lock(&mvm->mutex); + + /* we are only changing the min_width, may be a noop */ + if (changed == IEEE80211_CHANCTX_CHANGE_MIN_WIDTH) { + if (phy_ctxt->width == ctx->min_def.width) + goto out_unlock; + + /* we are just toggling between 20_NOHT and 20 */ + if (phy_ctxt->width <= NL80211_CHAN_WIDTH_20 && + ctx->min_def.width <= NL80211_CHAN_WIDTH_20) + goto out_unlock; + } + iwl_mvm_bt_coex_vif_change(mvm); iwl_mvm_phy_ctxt_changed(mvm, phy_ctxt, &ctx->min_def, ctx->rx_chains_static, ctx->rx_chains_dynamic); + +out_unlock: mutex_unlock(&mvm->mutex); } @@ -3893,11 +3909,6 @@ static int iwl_mvm_pre_channel_switch(struct ieee80211_hw *hw, break; case NL80211_IFTYPE_STATION: - if (mvmvif->lqm_active) - iwl_mvm_send_lqm_cmd(vif, - LQM_CMD_OPERATION_STOP_MEASUREMENT, - 0, 0); - /* Schedule the time event to a bit before beacon 1, * to make sure we're in the new channel when the * GO/AP arrives. In case count <= 1 immediately schedule the @@ -4252,31 +4263,6 @@ static void iwl_mvm_event_bar_rx_callback(struct iwl_mvm *mvm, event->u.ba.ssn); } -static void -iwl_mvm_event_frame_timeout_callback(struct iwl_mvm *mvm, - struct ieee80211_vif *vif, - const struct ieee80211_event *event) -{ - struct iwl_fw_dbg_trigger_tlv *trig; - struct iwl_fw_dbg_trigger_ba *ba_trig; - - if (!iwl_fw_dbg_trigger_enabled(mvm->fw, FW_DBG_TRIGGER_BA)) - return; - - trig = iwl_fw_dbg_get_trigger(mvm->fw, FW_DBG_TRIGGER_BA); - ba_trig = (void *)trig->data; - if (!iwl_fw_dbg_trigger_check_stop(&mvm->fwrt, - ieee80211_vif_to_wdev(vif), trig)) - return; - - if (!(le16_to_cpu(ba_trig->frame_timeout) & BIT(event->u.ba.tid))) - return; - - iwl_fw_dbg_collect_trig(&mvm->fwrt, trig, - "Frame from %pM timed out, tid %d", - event->u.ba.sta->addr, event->u.ba.tid); -} - static void iwl_mvm_mac_event_callback(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const struct ieee80211_event *event) @@ -4291,7 +4277,8 @@ static void iwl_mvm_mac_event_callback(struct ieee80211_hw *hw, iwl_mvm_event_bar_rx_callback(mvm, vif, event); break; case BA_FRAME_TIMEOUT: - iwl_mvm_event_frame_timeout_callback(mvm, vif, event); + iwl_mvm_event_frame_timeout_callback(mvm, vif, event->u.ba.sta, + event->u.ba.tid); break; default: break; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 83303bac0e4b..bf25c3ce7c95 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -89,6 +89,7 @@ #include "tof.h" #include "fw/runtime.h" #include "fw/dbg.h" +#include "fw/acpi.h" #define IWL_MVM_MAX_ADDRESSES 5 /* RSSI offset for WkP */ @@ -147,6 +148,8 @@ struct iwl_mvm_phy_ctxt { u16 color; u32 ref; + enum nl80211_chan_width width; + /* * TODO: This should probably be removed. Currently here only for rate * scaling algorithm @@ -436,12 +439,6 @@ struct iwl_mvm_vif { /* TCP Checksum Offload */ netdev_features_t features; - - /* - * link quality measurement - used to check whether this interface - * is in the middle of a link quality measurement - */ - bool lqm_active; }; static inline struct iwl_mvm_vif * @@ -592,6 +589,7 @@ enum iwl_mvm_tdls_cs_state { * @queue: queue of this reorder buffer * @last_amsdu: track last ASMDU SN for duplication detection * @last_sub_index: track ASMDU sub frame index for duplication detection + * @tid: the tid * @entries: list of skbs stored * @reorder_time: time the packet was stored in the reorder buffer * @reorder_timer: timer for frames are in the reorder buffer. For AMSDU @@ -609,6 +607,7 @@ struct iwl_mvm_reorder_buffer { int queue; u16 last_amsdu; u8 last_sub_index; + u8 tid; struct sk_buff_head entries[IEEE80211_MAX_AMPDU_BUF]; unsigned long reorder_time[IEEE80211_MAX_AMPDU_BUF]; struct timer_list reorder_timer; @@ -685,20 +684,14 @@ enum iwl_mvm_queue_status { #define IWL_MVM_NUM_CIPHERS 10 -#ifdef CONFIG_ACPI -#define IWL_MVM_SAR_TABLE_SIZE 10 -#define IWL_MVM_SAR_PROFILE_NUM 4 -#define IWL_MVM_GEO_TABLE_SIZE 6 - struct iwl_mvm_sar_profile { bool enabled; - u8 table[IWL_MVM_SAR_TABLE_SIZE]; + u8 table[ACPI_SAR_TABLE_SIZE]; }; struct iwl_mvm_geo_profile { - u8 values[IWL_MVM_GEO_TABLE_SIZE]; + u8 values[ACPI_GEO_TABLE_SIZE]; }; -#endif struct iwl_mvm { /* for logger access */ @@ -1015,9 +1008,12 @@ struct iwl_mvm { bool drop_bcn_ap_mode; struct delayed_work cs_tx_unblock_dwork; + + /* does a monitor vif exist (only one can exist hence bool) */ + bool monitor_on; #ifdef CONFIG_ACPI - struct iwl_mvm_sar_profile sar_profiles[IWL_MVM_SAR_PROFILE_NUM]; - struct iwl_mvm_geo_profile geo_profiles[IWL_NUM_GEO_PROFILES]; + struct iwl_mvm_sar_profile sar_profiles[ACPI_SAR_PROFILE_NUM]; + struct iwl_mvm_geo_profile geo_profiles[ACPI_NUM_GEO_PROFILES]; #endif }; @@ -1159,7 +1155,7 @@ static inline bool iwl_mvm_is_lar_supported(struct iwl_mvm *mvm) * Enable LAR only if it is supported by the FW (TLV) && * enabled in the NVM */ - if (mvm->cfg->ext_nvm) + if (mvm->cfg->nvm_type == IWL_NVM_EXT) return nvm_lar && tlv_lar; else return tlv_lar; @@ -1248,6 +1244,12 @@ static inline bool iwl_mvm_has_new_ats_coex_api(struct iwl_mvm *mvm) IWL_UCODE_TLV_API_COEX_ATS_EXTERNAL); } +static inline bool iwl_mvm_has_quota_low_latency(struct iwl_mvm *mvm) +{ + return fw_has_api(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_API_QUOTA_LOW_LATENCY); +} + static inline struct agg_tx_status * iwl_mvm_get_agg_status(struct iwl_mvm *mvm, void *tx_resp) { @@ -1486,6 +1488,27 @@ int iwl_mvm_binding_add_vif(struct iwl_mvm *mvm, struct ieee80211_vif *vif); int iwl_mvm_binding_remove_vif(struct iwl_mvm *mvm, struct ieee80211_vif *vif); /* Quota management */ +static inline size_t iwl_mvm_quota_cmd_size(struct iwl_mvm *mvm) +{ + return iwl_mvm_has_quota_low_latency(mvm) ? + sizeof(struct iwl_time_quota_cmd) : + sizeof(struct iwl_time_quota_cmd_v1); +} + +static inline struct iwl_time_quota_data +*iwl_mvm_quota_cmd_get_quota(struct iwl_mvm *mvm, + struct iwl_time_quota_cmd *cmd, + int i) +{ + struct iwl_time_quota_data_v1 *quotas; + + if (iwl_mvm_has_quota_low_latency(mvm)) + return &cmd->quotas[i]; + + quotas = (struct iwl_time_quota_data_v1 *)cmd->quotas; + return (struct iwl_time_quota_data *)"as[i]; +} + int iwl_mvm_update_quotas(struct iwl_mvm *mvm, bool force_upload, struct ieee80211_vif *disabled_vif); @@ -1818,12 +1841,10 @@ unsigned int iwl_mvm_get_wd_timeout(struct iwl_mvm *mvm, bool tdls, bool cmd_q); void iwl_mvm_connection_loss(struct iwl_mvm *mvm, struct ieee80211_vif *vif, const char *errmsg); - -/* Link Quality Measurement */ -int iwl_mvm_send_lqm_cmd(struct ieee80211_vif *vif, - enum iwl_lqm_cmd_operatrions operation, - u32 duration, u32 timeout); -bool iwl_mvm_lqm_active(struct iwl_mvm *mvm); +void iwl_mvm_event_frame_timeout_callback(struct iwl_mvm *mvm, + struct ieee80211_vif *vif, + const struct ieee80211_sta *sta, + u16 tid); int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b); int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c index 422aa6be9932..5bfe5306524c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c @@ -73,6 +73,7 @@ #include "iwl-eeprom-read.h" #include "iwl-nvm-parse.h" #include "iwl-prph.h" +#include "fw/acpi.h" /* Default NVM size to read */ #define IWL_NVM_DEFAULT_CHUNK_SIZE (2*1024) @@ -295,18 +296,24 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm) const __be16 *hw; const __le16 *sw, *calib, *regulatory, *mac_override, *phy_sku; bool lar_enabled; + int regulatory_type; /* Checking for required sections */ - if (!mvm->trans->cfg->ext_nvm) { + if (mvm->trans->cfg->nvm_type != IWL_NVM_EXT) { if (!mvm->nvm_sections[NVM_SECTION_TYPE_SW].data || !mvm->nvm_sections[mvm->cfg->nvm_hw_section_num].data) { IWL_ERR(mvm, "Can't parse empty OTP/NVM sections\n"); return NULL; } } else { + if (mvm->trans->cfg->nvm_type == IWL_NVM_SDP) + regulatory_type = NVM_SECTION_TYPE_REGULATORY_SDP; + else + regulatory_type = NVM_SECTION_TYPE_REGULATORY; + /* SW and REGULATORY sections are mandatory */ if (!mvm->nvm_sections[NVM_SECTION_TYPE_SW].data || - !mvm->nvm_sections[NVM_SECTION_TYPE_REGULATORY].data) { + !mvm->nvm_sections[regulatory_type].data) { IWL_ERR(mvm, "Can't parse empty family 8000 OTP/NVM sections\n"); return NULL; @@ -330,11 +337,14 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm) hw = (const __be16 *)sections[mvm->cfg->nvm_hw_section_num].data; sw = (const __le16 *)sections[NVM_SECTION_TYPE_SW].data; calib = (const __le16 *)sections[NVM_SECTION_TYPE_CALIBRATION].data; - regulatory = (const __le16 *)sections[NVM_SECTION_TYPE_REGULATORY].data; mac_override = (const __le16 *)sections[NVM_SECTION_TYPE_MAC_OVERRIDE].data; phy_sku = (const __le16 *)sections[NVM_SECTION_TYPE_PHY_SKU].data; + regulatory = mvm->trans->cfg->nvm_type == IWL_NVM_SDP ? + (const __le16 *)sections[NVM_SECTION_TYPE_REGULATORY_SDP].data : + (const __le16 *)sections[NVM_SECTION_TYPE_REGULATORY].data; + lar_enabled = !iwlwifi_mod_params.lar_disable && fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_LAR_SUPPORT); @@ -394,7 +404,7 @@ int iwl_mvm_read_external_nvm(struct iwl_mvm *mvm) IWL_DEBUG_EEPROM(mvm->trans->dev, "Read from external NVM\n"); /* Maximal size depends on NVM version */ - if (!mvm->trans->cfg->ext_nvm) + if (mvm->trans->cfg->nvm_type != IWL_NVM_EXT) max_section_size = IWL_MAX_NVM_SECTION_SIZE; else max_section_size = IWL_MAX_EXT_NVM_SECTION_SIZE; @@ -465,7 +475,7 @@ int iwl_mvm_read_external_nvm(struct iwl_mvm *mvm) break; } - if (!mvm->trans->cfg->ext_nvm) { + if (mvm->trans->cfg->nvm_type != IWL_NVM_EXT) { section_size = 2 * NVM_WORD1_LEN(le16_to_cpu(file_sec->word1)); section_id = NVM_WORD2_ID(le16_to_cpu(file_sec->word2)); @@ -740,7 +750,7 @@ int iwl_mvm_init_mcc(struct iwl_mvm *mvm) struct ieee80211_regdomain *regd; char mcc[3]; - if (mvm->cfg->ext_nvm) { + if (mvm->cfg->nvm_type == IWL_NVM_EXT) { tlv_lar = fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_LAR_SUPPORT); nvm_lar = mvm->nvm_data->lar_enabled; @@ -775,7 +785,7 @@ int iwl_mvm_init_mcc(struct iwl_mvm *mvm) return -EIO; if (iwl_mvm_is_wifi_mcc_supported(mvm) && - !iwl_get_bios_mcc(mvm->dev, mcc)) { + !iwl_acpi_get_mcc(mvm->dev, mcc)) { kfree(regd); regd = iwl_mvm_get_regdomain(mvm->hw->wiphy, mcc, MCC_SOURCE_BIOS, NULL); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 231878969332..e82b4462722b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -86,6 +86,7 @@ #include "time-event.h" #include "fw-api.h" #include "fw/api/scan.h" +#include "fw/acpi.h" #define DRV_DESCRIPTION "The new Intel(R) wireless AGN driver for Linux" MODULE_DESCRIPTION(DRV_DESCRIPTION); @@ -423,8 +424,6 @@ static const struct iwl_hcmd_names iwl_mvm_system_names[] = { * Access is done through binary search */ static const struct iwl_hcmd_names iwl_mvm_mac_conf_names[] = { - HCMD_NAME(LINK_QUALITY_MEASUREMENT_CMD), - HCMD_NAME(LINK_QUALITY_MEASUREMENT_COMPLETE_NOTIF), HCMD_NAME(CHANNEL_SWITCH_NOA_NOTIF), }; @@ -490,18 +489,21 @@ static const struct iwl_hcmd_arr iwl_mvm_groups[] = { static void iwl_mvm_async_handlers_wk(struct work_struct *wk); static void iwl_mvm_d0i3_exit_work(struct work_struct *wk); -static u32 calc_min_backoff(struct iwl_trans *trans, const struct iwl_cfg *cfg) +static u32 iwl_mvm_min_backoff(struct iwl_mvm *mvm) { - const struct iwl_pwr_tx_backoff *pwr_tx_backoff = cfg->pwr_tx_backoffs; + const struct iwl_pwr_tx_backoff *backoff = mvm->cfg->pwr_tx_backoffs; + u64 dflt_pwr_limit; - if (!pwr_tx_backoff) + if (!backoff) return 0; - while (pwr_tx_backoff->pwr) { - if (trans->dflt_pwr_limit >= pwr_tx_backoff->pwr) - return pwr_tx_backoff->backoff; + dflt_pwr_limit = iwl_acpi_get_pwr_limit(mvm->dev); - pwr_tx_backoff++; + while (backoff->pwr) { + if (dflt_pwr_limit >= backoff->pwr) + return backoff->backoff; + + backoff++; } return 0; @@ -771,7 +773,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, goto out_free; mvm->hw_registered = true; - min_backoff = calc_min_backoff(trans, cfg); + min_backoff = iwl_mvm_min_backoff(mvm); iwl_mvm_thermal_initialize(mvm, min_backoff); err = iwl_mvm_dbgfs_register(mvm, dbgfs_dir); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c index 7ee8e9077baf..305cd56bf746 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c @@ -272,6 +272,7 @@ int iwl_mvm_phy_ctxt_changed(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt, } ctxt->channel = chandef->chan; + ctxt->width = chandef->width; return iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef, chains_static, chains_dynamic, action, 0); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/quota.c b/drivers/net/wireless/intel/iwlwifi/mvm/quota.c index 2141db5bff82..b4a0264329b7 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/quota.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/quota.c @@ -7,7 +7,7 @@ * * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH - * Copyright(c) 2016 Intel Deutschland GmbH + * Copyright(c) 2016 - 2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -34,7 +34,7 @@ * * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH - * Copyright(c) 2016 Intel Deutschland GmbH + * Copyright(c) 2016 - 2017 Intel Deutschland GmbH * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -164,9 +164,12 @@ static void iwl_mvm_adjust_quota_for_noa(struct iwl_mvm *mvm, beacon_int = mvm->noa_vif->bss_conf.beacon_int; for (i = 0; i < MAX_BINDINGS; i++) { - u32 id_n_c = le32_to_cpu(cmd->quotas[i].id_and_color); + struct iwl_time_quota_data *data = + iwl_mvm_quota_cmd_get_quota(mvm, cmd, + i); + u32 id_n_c = le32_to_cpu(data->id_and_color); u32 id = (id_n_c & FW_CTXT_ID_MSK) >> FW_CTXT_ID_POS; - u32 quota = le32_to_cpu(cmd->quotas[i].quota); + u32 quota = le32_to_cpu(data->quota); if (id != phy_id) continue; @@ -175,9 +178,9 @@ static void iwl_mvm_adjust_quota_for_noa(struct iwl_mvm *mvm, quota /= beacon_int; IWL_DEBUG_QUOTA(mvm, "quota: adjust for NoA from %d to %d\n", - le32_to_cpu(cmd->quotas[i].quota), quota); + le32_to_cpu(data->quota), quota); - cmd->quotas[i].quota = cpu_to_le32(quota); + data->quota = cpu_to_le32(quota); } #endif } @@ -194,6 +197,7 @@ int iwl_mvm_update_quotas(struct iwl_mvm *mvm, .disabled_vif = disabled_vif, }; struct iwl_time_quota_cmd *last = &mvm->last_quota_cmd; + struct iwl_time_quota_data *qdata, *last_data; bool send = false; lockdep_assert_held(&mvm->mutex); @@ -216,7 +220,8 @@ int iwl_mvm_update_quotas(struct iwl_mvm *mvm, */ num_active_macs = 0; for (i = 0; i < MAX_BINDINGS; i++) { - cmd.quotas[i].id_and_color = cpu_to_le32(FW_CTXT_INVALID); + qdata = iwl_mvm_quota_cmd_get_quota(mvm, &cmd, i); + qdata->id_and_color = cpu_to_le32(FW_CTXT_INVALID); num_active_macs += data.n_interfaces[i]; } @@ -265,14 +270,16 @@ int iwl_mvm_update_quotas(struct iwl_mvm *mvm, if (data.colors[i] < 0) continue; - cmd.quotas[idx].id_and_color = + qdata = iwl_mvm_quota_cmd_get_quota(mvm, &cmd, idx); + + qdata->id_and_color = cpu_to_le32(FW_CMD_ID_AND_COLOR(i, data.colors[i])); if (data.n_interfaces[i] <= 0) - cmd.quotas[idx].quota = cpu_to_le32(0); + qdata->quota = cpu_to_le32(0); #ifdef CONFIG_IWLWIFI_DEBUGFS else if (data.dbgfs_min[i]) - cmd.quotas[idx].quota = + qdata->quota = cpu_to_le32(data.dbgfs_min[i] * QUOTA_100 / 100); #endif else if (data.n_low_latency_bindings == 1 && n_non_lowlat && @@ -283,24 +290,25 @@ int iwl_mvm_update_quotas(struct iwl_mvm *mvm, * the minimal required quota for the low latency * binding. */ - cmd.quotas[idx].quota = cpu_to_le32(QUOTA_LOWLAT_MIN); + qdata->quota = cpu_to_le32(QUOTA_LOWLAT_MIN); else - cmd.quotas[idx].quota = + qdata->quota = cpu_to_le32(quota * data.n_interfaces[i]); - WARN_ONCE(le32_to_cpu(cmd.quotas[idx].quota) > QUOTA_100, + WARN_ONCE(le32_to_cpu(qdata->quota) > QUOTA_100, "Binding=%d, quota=%u > max=%u\n", - idx, le32_to_cpu(cmd.quotas[idx].quota), QUOTA_100); + idx, le32_to_cpu(qdata->quota), QUOTA_100); - cmd.quotas[idx].max_duration = cpu_to_le32(0); + qdata->max_duration = cpu_to_le32(0); idx++; } /* Give the remainder of the session to the first data binding */ for (i = 0; i < MAX_BINDINGS; i++) { - if (le32_to_cpu(cmd.quotas[i].quota) != 0) { - le32_add_cpu(&cmd.quotas[i].quota, quota_rem); + qdata = iwl_mvm_quota_cmd_get_quota(mvm, &cmd, i); + if (le32_to_cpu(qdata->quota) != 0) { + le32_add_cpu(&qdata->quota, quota_rem); IWL_DEBUG_QUOTA(mvm, "quota: giving remainder of %d to binding %d\n", quota_rem, i); @@ -312,17 +320,19 @@ int iwl_mvm_update_quotas(struct iwl_mvm *mvm, /* check that we have non-zero quota for all valid bindings */ for (i = 0; i < MAX_BINDINGS; i++) { - if (cmd.quotas[i].id_and_color != last->quotas[i].id_and_color) + qdata = iwl_mvm_quota_cmd_get_quota(mvm, &cmd, i); + last_data = iwl_mvm_quota_cmd_get_quota(mvm, last, i); + if (qdata->id_and_color != last_data->id_and_color) send = true; - if (cmd.quotas[i].max_duration != last->quotas[i].max_duration) + if (qdata->max_duration != last_data->max_duration) send = true; - if (abs((int)le32_to_cpu(cmd.quotas[i].quota) - - (int)le32_to_cpu(last->quotas[i].quota)) + if (abs((int)le32_to_cpu(qdata->quota) - + (int)le32_to_cpu(last_data->quota)) > IWL_MVM_QUOTA_THRESHOLD) send = true; - if (cmd.quotas[i].id_and_color == cpu_to_le32(FW_CTXT_INVALID)) + if (qdata->id_and_color == cpu_to_le32(FW_CTXT_INVALID)) continue; - WARN_ONCE(cmd.quotas[i].quota == 0, + WARN_ONCE(qdata->quota == 0, "zero quota on binding %d\n", i); } @@ -334,7 +344,8 @@ int iwl_mvm_update_quotas(struct iwl_mvm *mvm, return 0; } - err = iwl_mvm_send_cmd_pdu(mvm, TIME_QUOTA_CMD, 0, sizeof(cmd), &cmd); + err = iwl_mvm_send_cmd_pdu(mvm, TIME_QUOTA_CMD, 0, + iwl_mvm_quota_cmd_size(mvm), &cmd); if (err) IWL_ERR(mvm, "Failed to send quota: %d\n", err); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c index 184c749766f2..d1a40688d5e1 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c @@ -244,7 +244,9 @@ static u32 iwl_mvm_set_mac80211_rx_flag(struct iwl_mvm *mvm, return 0; default: - IWL_ERR(mvm, "Unhandled alg: 0x%x\n", rx_pkt_status); + /* Expected in monitor (not having the keys) */ + if (!mvm->monitor_on) + IWL_ERR(mvm, "Unhandled alg: 0x%x\n", rx_pkt_status); } return 0; @@ -661,11 +663,10 @@ void iwl_mvm_handle_rx_statistics(struct iwl_mvm *mvm, expected_size = sizeof(struct iwl_notif_statistics_cdb); } - if (iwl_rx_packet_payload_len(pkt) != expected_size) { - IWL_ERR(mvm, "received invalid statistics size (%d)!\n", - iwl_rx_packet_payload_len(pkt)); + if (WARN_ONCE(iwl_rx_packet_payload_len(pkt) != expected_size, + "received invalid statistics size (%d)!\n", + iwl_rx_packet_payload_len(pkt))) return; - } if (!iwl_mvm_has_new_rx_stats_api(mvm)) { struct iwl_notif_statistics_v11 *stats = (void *)&pkt->data; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 77f77bc5d083..5e679859f948 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -277,7 +277,9 @@ static int iwl_mvm_rx_crypto(struct iwl_mvm *mvm, struct ieee80211_hdr *hdr, stats->flag |= RX_FLAG_DECRYPTED; return 0; default: - IWL_ERR(mvm, "Unhandled alg: 0x%x\n", status); + /* Expected in monitor (not having the keys) */ + if (!mvm->monitor_on) + IWL_ERR(mvm, "Unhandled alg: 0x%x\n", status); } return 0; @@ -492,13 +494,18 @@ void iwl_mvm_reorder_timer_expired(unsigned long data) if (expired) { struct ieee80211_sta *sta; + struct iwl_mvm_sta *mvmsta; rcu_read_lock(); sta = rcu_dereference(buf->mvm->fw_id_to_mac_id[buf->sta_id]); + mvmsta = iwl_mvm_sta_from_mac80211(sta); + /* SN is set to the last expired frame + 1 */ IWL_DEBUG_HT(buf->mvm, "Releasing expired frames for sta %u, sn %d\n", buf->sta_id, sn); + iwl_mvm_event_frame_timeout_callback(buf->mvm, mvmsta->vif, + sta, buf->tid); iwl_mvm_release_frames(buf->mvm, sta, NULL, buf, sn); rcu_read_unlock(); } else { @@ -619,7 +626,8 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, return false; /* no sta yet */ - if (WARN_ON(IS_ERR_OR_NULL(sta))) + if (WARN_ONCE(IS_ERR_OR_NULL(sta), + "Got valid BAID without a valid station assigned\n")) return false; mvm_sta = iwl_mvm_sta_from_mac80211(sta); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index c4a343534c5e..282424f40c43 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -2158,6 +2158,7 @@ static void iwl_mvm_init_reorder_buffer(struct iwl_mvm *mvm, reorder_buf->mvm = mvm; reorder_buf->queue = i; reorder_buf->sta_id = sta_id; + reorder_buf->tid = data->tid; reorder_buf->valid = false; for (j = 0; j < reorder_buf->buf_size; j++) __skb_queue_head_init(&reorder_buf->entries[j]); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c index 4d907f60bce9..1232f63278eb 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c @@ -631,7 +631,7 @@ static int iwl_mvm_tzone_get_temp(struct thermal_zone_device *device, if (!iwl_mvm_firmware_running(mvm) || mvm->fwrt.cur_fw_img != IWL_UCODE_REGULAR) { - ret = -EIO; + ret = -ENODATA; goto out; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c index 2ea74abad73d..2da1b088ac01 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c @@ -1368,6 +1368,31 @@ void iwl_mvm_inactivity_check(struct iwl_mvm *mvm) rcu_read_unlock(); } +void iwl_mvm_event_frame_timeout_callback(struct iwl_mvm *mvm, + struct ieee80211_vif *vif, + const struct ieee80211_sta *sta, + u16 tid) +{ + struct iwl_fw_dbg_trigger_tlv *trig; + struct iwl_fw_dbg_trigger_ba *ba_trig; + + if (!iwl_fw_dbg_trigger_enabled(mvm->fw, FW_DBG_TRIGGER_BA)) + return; + + trig = iwl_fw_dbg_get_trigger(mvm->fw, FW_DBG_TRIGGER_BA); + ba_trig = (void *)trig->data; + if (!iwl_fw_dbg_trigger_check_stop(&mvm->fwrt, + ieee80211_vif_to_wdev(vif), trig)) + return; + + if (!(le16_to_cpu(ba_trig->frame_timeout) & BIT(tid))) + return; + + iwl_fw_dbg_collect_trig(&mvm->fwrt, trig, + "Frame from %pM timed out, tid %d", + sta->addr, tid); +} + void iwl_mvm_get_sync_time(struct iwl_mvm *mvm, u32 *gp2, u64 *boottime) { bool ps_disabled; @@ -1389,74 +1414,3 @@ void iwl_mvm_get_sync_time(struct iwl_mvm *mvm, u32 *gp2, u64 *boottime) iwl_mvm_power_update_device(mvm); } } - -int iwl_mvm_send_lqm_cmd(struct ieee80211_vif *vif, - enum iwl_lqm_cmd_operatrions operation, - u32 duration, u32 timeout) -{ - struct iwl_mvm_vif *mvm_vif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_link_qual_msrmnt_cmd cmd = { - .cmd_operation = cpu_to_le32(operation), - .mac_id = cpu_to_le32(mvm_vif->id), - .measurement_time = cpu_to_le32(duration), - .timeout = cpu_to_le32(timeout), - }; - u32 cmdid = - iwl_cmd_id(LINK_QUALITY_MEASUREMENT_CMD, MAC_CONF_GROUP, 0); - int ret; - - if (!fw_has_capa(&mvm_vif->mvm->fw->ucode_capa, - IWL_UCODE_TLV_CAPA_LQM_SUPPORT)) - return -EOPNOTSUPP; - - if (vif->type != NL80211_IFTYPE_STATION || vif->p2p) - return -EINVAL; - - switch (operation) { - case LQM_CMD_OPERATION_START_MEASUREMENT: - if (iwl_mvm_lqm_active(mvm_vif->mvm)) - return -EBUSY; - if (!vif->bss_conf.assoc) - return -EINVAL; - mvm_vif->lqm_active = true; - break; - case LQM_CMD_OPERATION_STOP_MEASUREMENT: - if (!iwl_mvm_lqm_active(mvm_vif->mvm)) - return -EINVAL; - break; - default: - return -EINVAL; - } - - ret = iwl_mvm_send_cmd_pdu(mvm_vif->mvm, cmdid, 0, sizeof(cmd), - &cmd); - - /* command failed - roll back lqm_active state */ - if (ret) { - mvm_vif->lqm_active = - operation == LQM_CMD_OPERATION_STOP_MEASUREMENT; - } - - return ret; -} - -static void iwl_mvm_lqm_active_iterator(void *_data, u8 *mac, - struct ieee80211_vif *vif) -{ - struct iwl_mvm_vif *mvm_vif = iwl_mvm_vif_from_mac80211(vif); - bool *lqm_active = _data; - - *lqm_active = *lqm_active || mvm_vif->lqm_active; -} - -bool iwl_mvm_lqm_active(struct iwl_mvm *mvm) -{ - bool ret = false; - - lockdep_assert_held(&mvm->mutex); - ieee80211_iterate_active_interfaces_atomic( - mvm->hw, IEEE80211_IFACE_ITER_NORMAL, - iwl_mvm_lqm_active_iterator, &ret); - - return ret; -} diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c index 3fc4343581ee..5ef216f3a60b 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c @@ -244,7 +244,7 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans, ctxt_info->hcmd_cfg.cmd_queue_addr = cpu_to_le64(trans_pcie->txq[trans_pcie->cmd_queue]->dma_addr); ctxt_info->hcmd_cfg.cmd_queue_size = - TFD_QUEUE_CB_SIZE(TFD_CMD_SLOTS); + TFD_QUEUE_CB_SIZE(trans_pcie->tx_cmd_queue_size); /* allocate ucode sections in dram and set addresses */ ret = iwl_pcie_ctxt_info_init_fw_sec(trans, fw, ctxt_info); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 858765fed8f8..ce7254ec0514 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -73,6 +73,8 @@ #include <linux/pci-aspm.h> #include <linux/acpi.h> +#include "fw/acpi.h" + #include "iwl-trans.h" #include "iwl-drv.h" #include "internal.h" @@ -576,7 +578,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2720, 0x0000, iwla000_2ax_cfg_hr)}, {IWL_PCI_DEVICE(0x34F0, 0x0070, iwla000_2ax_cfg_hr)}, {IWL_PCI_DEVICE(0x2720, 0x0078, iwla000_2ax_cfg_hr)}, - {IWL_PCI_DEVICE(0x2720, 0x0070, iwla000_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x2720, 0x0070, iwla000_2ac_cfg_hr_cdb)}, + {IWL_PCI_DEVICE(0x2720, 0x0030, iwla000_2ac_cfg_hr_cdb)}, {IWL_PCI_DEVICE(0x2720, 0x1080, iwla000_2ax_cfg_hr)}, #endif /* CONFIG_IWLMVM */ @@ -584,99 +587,6 @@ static const struct pci_device_id iwl_hw_card_ids[] = { }; MODULE_DEVICE_TABLE(pci, iwl_hw_card_ids); -#ifdef CONFIG_ACPI -#define ACPI_SPLC_METHOD "SPLC" -#define ACPI_SPLC_DOMAIN_WIFI (0x07) - -static u64 splc_get_pwr_limit(struct iwl_trans *trans, union acpi_object *splc) -{ - union acpi_object *data_pkg, *dflt_pwr_limit; - int i; - - /* We need at least two elements, one for the revision and one - * for the data itself. Also check that the revision is - * supported (currently only revision 0). - */ - if (splc->type != ACPI_TYPE_PACKAGE || - splc->package.count < 2 || - splc->package.elements[0].type != ACPI_TYPE_INTEGER || - splc->package.elements[0].integer.value != 0) { - IWL_DEBUG_INFO(trans, - "Unsupported structure returned by the SPLC method. Ignoring.\n"); - return 0; - } - - /* loop through all the packages to find the one for WiFi */ - for (i = 1; i < splc->package.count; i++) { - union acpi_object *domain; - - data_pkg = &splc->package.elements[i]; - - /* Skip anything that is not a package with the right - * amount of elements (i.e. at least 2 integers). - */ - if (data_pkg->type != ACPI_TYPE_PACKAGE || - data_pkg->package.count < 2 || - data_pkg->package.elements[0].type != ACPI_TYPE_INTEGER || - data_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) - continue; - - domain = &data_pkg->package.elements[0]; - if (domain->integer.value == ACPI_SPLC_DOMAIN_WIFI) - break; - - data_pkg = NULL; - } - - if (!data_pkg) { - IWL_DEBUG_INFO(trans, - "No element for the WiFi domain returned by the SPLC method.\n"); - return 0; - } - - dflt_pwr_limit = &data_pkg->package.elements[1]; - return dflt_pwr_limit->integer.value; -} - -static void set_dflt_pwr_limit(struct iwl_trans *trans, struct pci_dev *pdev) -{ - acpi_handle pxsx_handle; - acpi_handle handle; - struct acpi_buffer splc = {ACPI_ALLOCATE_BUFFER, NULL}; - acpi_status status; - - pxsx_handle = ACPI_HANDLE(&pdev->dev); - if (!pxsx_handle) { - IWL_DEBUG_INFO(trans, - "Could not retrieve root port ACPI handle\n"); - return; - } - - /* Get the method's handle */ - status = acpi_get_handle(pxsx_handle, (acpi_string)ACPI_SPLC_METHOD, - &handle); - if (ACPI_FAILURE(status)) { - IWL_DEBUG_INFO(trans, "SPLC method not found\n"); - return; - } - - /* Call SPLC with no arguments */ - status = acpi_evaluate_object(handle, NULL, NULL, &splc); - if (ACPI_FAILURE(status)) { - IWL_ERR(trans, "SPLC invocation failed (0x%x)\n", status); - return; - } - - trans->dflt_pwr_limit = splc_get_pwr_limit(trans, splc.pointer); - IWL_DEBUG_INFO(trans, "Default power limit set to %lld\n", - trans->dflt_pwr_limit); - kfree(splc.pointer); -} - -#else /* CONFIG_ACPI */ -static void set_dflt_pwr_limit(struct iwl_trans *trans, struct pci_dev *pdev) {} -#endif - /* PCI registers */ #define PCI_CFG_RETRY_TIMEOUT 0x041 @@ -740,8 +650,6 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto out_free_trans; } - set_dflt_pwr_limit(iwl_trans, pdev); - /* register transport layer debugfs here */ ret = iwl_trans_pcie_dbgfs_register(iwl_trans); if (ret) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h index 4fb7647995c3..d749abeca3ae 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h @@ -383,6 +383,7 @@ struct iwl_self_init_dram { * @hw_init_mask: initial unmasked hw causes * @fh_mask: current unmasked fh causes * @hw_mask: current unmasked hw causes + * @tx_cmd_queue_size: the size of the tx command queue */ struct iwl_trans_pcie { struct iwl_rxq *rxq; @@ -442,6 +443,7 @@ struct iwl_trans_pcie { bool bc_table_dword; bool scd_set_active; bool sw_csum_tx; + bool pcie_dbg_dumped_once; u32 rx_page_order; /*protect hw register */ @@ -463,6 +465,7 @@ struct iwl_trans_pcie { u32 fh_mask; u32 hw_mask; cpumask_t affinity_mask[IWL_MAX_RX_HW_QUEUES]; + u16 tx_cmd_queue_size; }; static inline struct iwl_trans_pcie * @@ -534,6 +537,7 @@ void iwl_pcie_hcmd_complete(struct iwl_trans *trans, void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn, struct sk_buff_head *skbs); void iwl_trans_pcie_tx_reset(struct iwl_trans *trans); +void iwl_pcie_set_tx_cmd_queue_size(struct iwl_trans *trans); static inline u16 iwl_pcie_tfd_tb_get_len(struct iwl_trans *trans, void *_tfd, u8 idx) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 2e3e013ec95a..0008ea323be3 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -88,6 +88,93 @@ #define IWL_FW_MEM_EXTENDED_START 0x40000 #define IWL_FW_MEM_EXTENDED_END 0x57FFF +static void iwl_trans_pcie_err_dump(struct iwl_trans *trans) +{ +#define PCI_DUMP_SIZE 64 +#define PREFIX_LEN 32 + struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); + struct pci_dev *pdev = trans_pcie->pci_dev; + u32 i, pos, alloc_size, *ptr, *buf; + char *prefix; + + if (trans_pcie->pcie_dbg_dumped_once) + return; + + /* Should be a multiple of 4 */ + BUILD_BUG_ON(PCI_DUMP_SIZE > 4096 || PCI_DUMP_SIZE & 0x3); + /* Alloc a max size buffer */ + if (PCI_ERR_ROOT_ERR_SRC + 4 > PCI_DUMP_SIZE) + alloc_size = PCI_ERR_ROOT_ERR_SRC + 4 + PREFIX_LEN; + else + alloc_size = PCI_DUMP_SIZE + PREFIX_LEN; + buf = kmalloc(alloc_size, GFP_ATOMIC); + if (!buf) + return; + prefix = (char *)buf + alloc_size - PREFIX_LEN; + + IWL_ERR(trans, "iwlwifi transaction failed, dumping registers\n"); + + /* Print wifi device registers */ + sprintf(prefix, "iwlwifi %s: ", pci_name(pdev)); + IWL_ERR(trans, "iwlwifi device config registers:\n"); + for (i = 0, ptr = buf; i < PCI_DUMP_SIZE; i += 4, ptr++) + if (pci_read_config_dword(pdev, i, ptr)) + goto err_read; + print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET, 32, 4, buf, i, 0); + + IWL_ERR(trans, "iwlwifi device memory mapped registers:\n"); + for (i = 0, ptr = buf; i < PCI_DUMP_SIZE; i += 4, ptr++) + *ptr = iwl_read32(trans, i); + print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET, 32, 4, buf, i, 0); + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); + if (pos) { + IWL_ERR(trans, "iwlwifi device AER capability structure:\n"); + for (i = 0, ptr = buf; i < PCI_ERR_ROOT_COMMAND; i += 4, ptr++) + if (pci_read_config_dword(pdev, pos + i, ptr)) + goto err_read; + print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET, + 32, 4, buf, i, 0); + } + + /* Print parent device registers next */ + if (!pdev->bus->self) + goto out; + + pdev = pdev->bus->self; + sprintf(prefix, "iwlwifi %s: ", pci_name(pdev)); + + IWL_ERR(trans, "iwlwifi parent port (%s) config registers:\n", + pci_name(pdev)); + for (i = 0, ptr = buf; i < PCI_DUMP_SIZE; i += 4, ptr++) + if (pci_read_config_dword(pdev, i, ptr)) + goto err_read; + print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET, 32, 4, buf, i, 0); + + /* Print root port AER registers */ + pos = 0; + pdev = pcie_find_root_port(pdev); + if (pdev) + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); + if (pos) { + IWL_ERR(trans, "iwlwifi root port (%s) AER cap structure:\n", + pci_name(pdev)); + sprintf(prefix, "iwlwifi %s: ", pci_name(pdev)); + for (i = 0, ptr = buf; i <= PCI_ERR_ROOT_ERR_SRC; i += 4, ptr++) + if (pci_read_config_dword(pdev, pos + i, ptr)) + goto err_read; + print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET, 32, + 4, buf, i, 0); + } + +err_read: + print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET, 32, 4, buf, i, 0); + IWL_ERR(trans, "Read failed at 0x%X\n", i); +out: + trans_pcie->pcie_dbg_dumped_once = 1; + kfree(buf); +} + static void iwl_pcie_free_fw_monitor(struct iwl_trans *trans) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -649,6 +736,7 @@ static int iwl_pcie_load_firmware_chunk(struct iwl_trans *trans, trans_pcie->ucode_write_complete, 5 * HZ); if (!ret) { IWL_ERR(trans, "Failed to load firmware chunk!\n"); + iwl_trans_pcie_err_dump(trans); return -ETIMEDOUT; } @@ -1868,6 +1956,7 @@ static bool iwl_trans_pcie_grab_nic_access(struct iwl_trans *trans, (CSR_GP_CNTRL_REG_FLAG_MAC_CLOCK_READY | CSR_GP_CNTRL_REG_FLAG_GOING_TO_SLEEP), 15000); if (unlikely(ret < 0)) { + iwl_trans_pcie_err_dump(trans); iwl_write32(trans, CSR_RESET, CSR_RESET_REG_FLAG_FORCE_NMI); WARN_ONCE(1, "Timeout waiting for hardware access (CSR_GP_CNTRL 0x%08x)\n", diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c index d74613fcb756..79e4c73a9709 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c @@ -1160,6 +1160,8 @@ int iwl_pcie_gen2_tx_init(struct iwl_trans *trans) struct iwl_txq *cmd_queue; int txq_id = trans_pcie->cmd_queue, ret; + iwl_pcie_set_tx_cmd_queue_size(trans); + /* alloc and init the command queue */ if (!trans_pcie->txq[txq_id]) { cmd_queue = kzalloc(sizeof(*cmd_queue), GFP_KERNEL); @@ -1168,7 +1170,8 @@ int iwl_pcie_gen2_tx_init(struct iwl_trans *trans) return -ENOMEM; } trans_pcie->txq[txq_id] = cmd_queue; - ret = iwl_pcie_txq_alloc(trans, cmd_queue, TFD_CMD_SLOTS, true); + ret = iwl_pcie_txq_alloc(trans, cmd_queue, + trans_pcie->tx_cmd_queue_size, true); if (ret) { IWL_ERR(trans, "Tx %d queue init failed\n", txq_id); goto error; @@ -1177,7 +1180,8 @@ int iwl_pcie_gen2_tx_init(struct iwl_trans *trans) cmd_queue = trans_pcie->txq[txq_id]; } - ret = iwl_pcie_txq_init(trans, cmd_queue, TFD_CMD_SLOTS, true); + ret = iwl_pcie_txq_init(trans, cmd_queue, + trans_pcie->tx_cmd_queue_size, true); if (ret) { IWL_ERR(trans, "Tx %d queue alloc failed\n", txq_id); goto error; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index c645d10d3707..e93c471ef9bf 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -951,7 +951,8 @@ static int iwl_pcie_tx_alloc(struct iwl_trans *trans) txq_id++) { bool cmd_queue = (txq_id == trans_pcie->cmd_queue); - slots_num = cmd_queue ? TFD_CMD_SLOTS : TFD_TX_CMD_SLOTS; + slots_num = cmd_queue ? trans_pcie->tx_cmd_queue_size : + TFD_TX_CMD_SLOTS; trans_pcie->txq[txq_id] = &trans_pcie->txq_memory[txq_id]; ret = iwl_pcie_txq_alloc(trans, trans_pcie->txq[txq_id], slots_num, cmd_queue); @@ -970,6 +971,21 @@ error: return ret; } +void iwl_pcie_set_tx_cmd_queue_size(struct iwl_trans *trans) +{ + struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); + int queue_size = TFD_CMD_SLOTS; + + if (trans->cfg->tx_cmd_queue_size) + queue_size = trans->cfg->tx_cmd_queue_size; + + if (WARN_ON(!(is_power_of_2(queue_size) && + TFD_QUEUE_CB_SIZE(queue_size) > 0))) + trans_pcie->tx_cmd_queue_size = TFD_CMD_SLOTS; + else + trans_pcie->tx_cmd_queue_size = queue_size; +} + int iwl_pcie_tx_init(struct iwl_trans *trans) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -977,6 +993,8 @@ int iwl_pcie_tx_init(struct iwl_trans *trans) int txq_id, slots_num; bool alloc = false; + iwl_pcie_set_tx_cmd_queue_size(trans); + if (!trans_pcie->txq_memory) { ret = iwl_pcie_tx_alloc(trans); if (ret) @@ -1000,7 +1018,8 @@ int iwl_pcie_tx_init(struct iwl_trans *trans) txq_id++) { bool cmd_queue = (txq_id == trans_pcie->cmd_queue); - slots_num = cmd_queue ? TFD_CMD_SLOTS : TFD_TX_CMD_SLOTS; + slots_num = cmd_queue ? trans_pcie->tx_cmd_queue_size : + TFD_TX_CMD_SLOTS; ret = iwl_pcie_txq_init(trans, trans_pcie->txq[txq_id], slots_num, cmd_queue); if (ret) { diff --git a/drivers/net/wireless/intersil/p54/main.c b/drivers/net/wireless/intersil/p54/main.c index d5a3bf91a03e..ab6d39e12069 100644 --- a/drivers/net/wireless/intersil/p54/main.c +++ b/drivers/net/wireless/intersil/p54/main.c @@ -852,12 +852,11 @@ void p54_unregister_common(struct ieee80211_hw *dev) { struct p54_common *priv = dev->priv; -#ifdef CONFIG_P54_LEDS - p54_unregister_leds(priv); -#endif /* CONFIG_P54_LEDS */ - if (priv->registered) { priv->registered = false; +#ifdef CONFIG_P54_LEDS + p54_unregister_leds(priv); +#endif /* CONFIG_P54_LEDS */ ieee80211_unregister_hw(dev); } diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 6467ffac9811..ec2f4c31425a 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -396,7 +396,7 @@ static int mac80211_hwsim_vendor_cmd_test(struct wiphy *wiphy, if (!tb[QCA_WLAN_VENDOR_ATTR_TEST]) return -EINVAL; val = nla_get_u32(tb[QCA_WLAN_VENDOR_ATTR_TEST]); - wiphy_debug(wiphy, "%s: test=%u\n", __func__, val); + wiphy_dbg(wiphy, "%s: test=%u\n", __func__, val); /* Send a vendor event as a test. Note that this would not normally be * done within a command handler, but rather, based on some other @@ -643,9 +643,9 @@ static void hwsim_send_ps_poll(void *dat, u8 *mac, struct ieee80211_vif *vif) if (!vp->assoc) return; - wiphy_debug(data->hw->wiphy, - "%s: send PS-Poll to %pM for aid %d\n", - __func__, vp->bssid, vp->aid); + wiphy_dbg(data->hw->wiphy, + "%s: send PS-Poll to %pM for aid %d\n", + __func__, vp->bssid, vp->aid); skb = dev_alloc_skb(sizeof(*pspoll)); if (!skb) @@ -674,9 +674,9 @@ static void hwsim_send_nullfunc(struct mac80211_hwsim_data *data, u8 *mac, if (!vp->assoc) return; - wiphy_debug(data->hw->wiphy, - "%s: send data::nullfunc to %pM ps=%d\n", - __func__, vp->bssid, ps); + wiphy_dbg(data->hw->wiphy, + "%s: send data::nullfunc to %pM ps=%d\n", + __func__, vp->bssid, ps); skb = dev_alloc_skb(sizeof(*hdr)); if (!skb) @@ -1034,7 +1034,7 @@ static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, msg_head = genlmsg_put(skb, 0, 0, &hwsim_genl_family, 0, HWSIM_CMD_FRAME); if (msg_head == NULL) { - printk(KERN_DEBUG "mac80211_hwsim: problem with msg_head\n"); + pr_debug("mac80211_hwsim: problem with msg_head\n"); goto nla_put_failure; } @@ -1093,7 +1093,7 @@ static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, nla_put_failure: nlmsg_free(skb); err_free_txskb: - printk(KERN_DEBUG "mac80211_hwsim: error occurred in %s\n", __func__); + pr_debug("mac80211_hwsim: error occurred in %s\n", __func__); ieee80211_free_txskb(hw, my_skb); data->tx_failed++; } @@ -1347,7 +1347,7 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw, } if (data->idle && !data->tmp_chan) { - wiphy_debug(hw->wiphy, "Trying to TX when idle - reject\n"); + wiphy_dbg(hw->wiphy, "Trying to TX when idle - reject\n"); ieee80211_free_txskb(hw, skb); return; } @@ -1408,7 +1408,7 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw, static int mac80211_hwsim_start(struct ieee80211_hw *hw) { struct mac80211_hwsim_data *data = hw->priv; - wiphy_debug(hw->wiphy, "%s\n", __func__); + wiphy_dbg(hw->wiphy, "%s\n", __func__); data->started = true; return 0; } @@ -1419,16 +1419,16 @@ static void mac80211_hwsim_stop(struct ieee80211_hw *hw) struct mac80211_hwsim_data *data = hw->priv; data->started = false; tasklet_hrtimer_cancel(&data->beacon_timer); - wiphy_debug(hw->wiphy, "%s\n", __func__); + wiphy_dbg(hw->wiphy, "%s\n", __func__); } static int mac80211_hwsim_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { - wiphy_debug(hw->wiphy, "%s (type=%d mac_addr=%pM)\n", - __func__, ieee80211_vif_type_p2p(vif), - vif->addr); + wiphy_dbg(hw->wiphy, "%s (type=%d mac_addr=%pM)\n", + __func__, ieee80211_vif_type_p2p(vif), + vif->addr); hwsim_set_magic(vif); vif->cab_queue = 0; @@ -1447,9 +1447,9 @@ static int mac80211_hwsim_change_interface(struct ieee80211_hw *hw, bool newp2p) { newtype = ieee80211_iftype_p2p(newtype, newp2p); - wiphy_debug(hw->wiphy, - "%s (old type=%d, new type=%d, mac_addr=%pM)\n", - __func__, ieee80211_vif_type_p2p(vif), + wiphy_dbg(hw->wiphy, + "%s (old type=%d, new type=%d, mac_addr=%pM)\n", + __func__, ieee80211_vif_type_p2p(vif), newtype, vif->addr); hwsim_check_magic(vif); @@ -1465,9 +1465,9 @@ static int mac80211_hwsim_change_interface(struct ieee80211_hw *hw, static void mac80211_hwsim_remove_interface( struct ieee80211_hw *hw, struct ieee80211_vif *vif) { - wiphy_debug(hw->wiphy, "%s (type=%d mac_addr=%pM)\n", - __func__, ieee80211_vif_type_p2p(vif), - vif->addr); + wiphy_dbg(hw->wiphy, "%s (type=%d mac_addr=%pM)\n", + __func__, ieee80211_vif_type_p2p(vif), + vif->addr); hwsim_check_magic(vif); hwsim_clear_magic(vif); } @@ -1589,23 +1589,23 @@ static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed) int idx; if (conf->chandef.chan) - wiphy_debug(hw->wiphy, - "%s (freq=%d(%d - %d)/%s idle=%d ps=%d smps=%s)\n", - __func__, - conf->chandef.chan->center_freq, - conf->chandef.center_freq1, - conf->chandef.center_freq2, - hwsim_chanwidths[conf->chandef.width], - !!(conf->flags & IEEE80211_CONF_IDLE), - !!(conf->flags & IEEE80211_CONF_PS), - smps_modes[conf->smps_mode]); + wiphy_dbg(hw->wiphy, + "%s (freq=%d(%d - %d)/%s idle=%d ps=%d smps=%s)\n", + __func__, + conf->chandef.chan->center_freq, + conf->chandef.center_freq1, + conf->chandef.center_freq2, + hwsim_chanwidths[conf->chandef.width], + !!(conf->flags & IEEE80211_CONF_IDLE), + !!(conf->flags & IEEE80211_CONF_PS), + smps_modes[conf->smps_mode]); else - wiphy_debug(hw->wiphy, - "%s (freq=0 idle=%d ps=%d smps=%s)\n", - __func__, - !!(conf->flags & IEEE80211_CONF_IDLE), - !!(conf->flags & IEEE80211_CONF_PS), - smps_modes[conf->smps_mode]); + wiphy_dbg(hw->wiphy, + "%s (freq=0 idle=%d ps=%d smps=%s)\n", + __func__, + !!(conf->flags & IEEE80211_CONF_IDLE), + !!(conf->flags & IEEE80211_CONF_PS), + smps_modes[conf->smps_mode]); data->idle = !!(conf->flags & IEEE80211_CONF_IDLE); @@ -1659,7 +1659,7 @@ static void mac80211_hwsim_configure_filter(struct ieee80211_hw *hw, { struct mac80211_hwsim_data *data = hw->priv; - wiphy_debug(hw->wiphy, "%s\n", __func__); + wiphy_dbg(hw->wiphy, "%s\n", __func__); data->rx_filter = 0; if (*total_flags & FIF_ALLMULTI) @@ -1688,25 +1688,25 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw, hwsim_check_magic(vif); - wiphy_debug(hw->wiphy, "%s(changed=0x%x vif->addr=%pM)\n", - __func__, changed, vif->addr); + wiphy_dbg(hw->wiphy, "%s(changed=0x%x vif->addr=%pM)\n", + __func__, changed, vif->addr); if (changed & BSS_CHANGED_BSSID) { - wiphy_debug(hw->wiphy, "%s: BSSID changed: %pM\n", - __func__, info->bssid); + wiphy_dbg(hw->wiphy, "%s: BSSID changed: %pM\n", + __func__, info->bssid); memcpy(vp->bssid, info->bssid, ETH_ALEN); } if (changed & BSS_CHANGED_ASSOC) { - wiphy_debug(hw->wiphy, " ASSOC: assoc=%d aid=%d\n", - info->assoc, info->aid); + wiphy_dbg(hw->wiphy, " ASSOC: assoc=%d aid=%d\n", + info->assoc, info->aid); vp->assoc = info->assoc; vp->aid = info->aid; } if (changed & BSS_CHANGED_BEACON_ENABLED) { - wiphy_debug(hw->wiphy, " BCN EN: %d (BI=%u)\n", - info->enable_beacon, info->beacon_int); + wiphy_dbg(hw->wiphy, " BCN EN: %d (BI=%u)\n", + info->enable_beacon, info->beacon_int); vp->bcn_en = info->enable_beacon; if (data->started && !hrtimer_is_queued(&data->beacon_timer.timer) && @@ -1725,8 +1725,8 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw, ieee80211_iterate_active_interfaces_atomic( data->hw, IEEE80211_IFACE_ITER_NORMAL, mac80211_hwsim_bcn_en_iter, &count); - wiphy_debug(hw->wiphy, " beaconing vifs remaining: %u", - count); + wiphy_dbg(hw->wiphy, " beaconing vifs remaining: %u", + count); if (count == 0) { tasklet_hrtimer_cancel(&data->beacon_timer); data->beacon_int = 0; @@ -1735,31 +1735,31 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw, } if (changed & BSS_CHANGED_ERP_CTS_PROT) { - wiphy_debug(hw->wiphy, " ERP_CTS_PROT: %d\n", - info->use_cts_prot); + wiphy_dbg(hw->wiphy, " ERP_CTS_PROT: %d\n", + info->use_cts_prot); } if (changed & BSS_CHANGED_ERP_PREAMBLE) { - wiphy_debug(hw->wiphy, " ERP_PREAMBLE: %d\n", - info->use_short_preamble); + wiphy_dbg(hw->wiphy, " ERP_PREAMBLE: %d\n", + info->use_short_preamble); } if (changed & BSS_CHANGED_ERP_SLOT) { - wiphy_debug(hw->wiphy, " ERP_SLOT: %d\n", info->use_short_slot); + wiphy_dbg(hw->wiphy, " ERP_SLOT: %d\n", info->use_short_slot); } if (changed & BSS_CHANGED_HT) { - wiphy_debug(hw->wiphy, " HT: op_mode=0x%x\n", - info->ht_operation_mode); + wiphy_dbg(hw->wiphy, " HT: op_mode=0x%x\n", + info->ht_operation_mode); } if (changed & BSS_CHANGED_BASIC_RATES) { - wiphy_debug(hw->wiphy, " BASIC_RATES: 0x%llx\n", - (unsigned long long) info->basic_rates); + wiphy_dbg(hw->wiphy, " BASIC_RATES: 0x%llx\n", + (unsigned long long) info->basic_rates); } if (changed & BSS_CHANGED_TXPOWER) - wiphy_debug(hw->wiphy, " TX Power: %d dBm\n", info->txpower); + wiphy_dbg(hw->wiphy, " TX Power: %d dBm\n", info->txpower); } static int mac80211_hwsim_sta_add(struct ieee80211_hw *hw, @@ -1813,11 +1813,11 @@ static int mac80211_hwsim_conf_tx( struct ieee80211_vif *vif, u16 queue, const struct ieee80211_tx_queue_params *params) { - wiphy_debug(hw->wiphy, - "%s (queue=%d txop=%d cw_min=%d cw_max=%d aifs=%d)\n", - __func__, queue, - params->txop, params->cw_min, - params->cw_max, params->aifs); + wiphy_dbg(hw->wiphy, + "%s (queue=%d txop=%d cw_min=%d cw_max=%d aifs=%d)\n", + __func__, queue, + params->txop, params->cw_min, + params->cw_max, params->aifs); return 0; } @@ -1981,7 +1981,7 @@ static void hw_scan_work(struct work_struct *work) .aborted = false, }; - wiphy_debug(hwsim->hw->wiphy, "hw scan complete\n"); + wiphy_dbg(hwsim->hw->wiphy, "hw scan complete\n"); ieee80211_scan_completed(hwsim->hw, &info); hwsim->hw_scan_request = NULL; hwsim->hw_scan_vif = NULL; @@ -1990,8 +1990,8 @@ static void hw_scan_work(struct work_struct *work) return; } - wiphy_debug(hwsim->hw->wiphy, "hw scan %d MHz\n", - req->channels[hwsim->scan_chan_idx]->center_freq); + wiphy_dbg(hwsim->hw->wiphy, "hw scan %d MHz\n", + req->channels[hwsim->scan_chan_idx]->center_freq); hwsim->tmp_chan = req->channels[hwsim->scan_chan_idx]; if (hwsim->tmp_chan->flags & (IEEE80211_CHAN_NO_IR | @@ -2060,7 +2060,7 @@ static int mac80211_hwsim_hw_scan(struct ieee80211_hw *hw, memset(hwsim->survey_data, 0, sizeof(hwsim->survey_data)); mutex_unlock(&hwsim->mutex); - wiphy_debug(hw->wiphy, "hwsim hw_scan request\n"); + wiphy_dbg(hw->wiphy, "hwsim hw_scan request\n"); ieee80211_queue_delayed_work(hwsim->hw, &hwsim->hw_scan, 0); @@ -2075,7 +2075,7 @@ static void mac80211_hwsim_cancel_hw_scan(struct ieee80211_hw *hw, .aborted = true, }; - wiphy_debug(hw->wiphy, "hwsim cancel_hw_scan\n"); + wiphy_dbg(hw->wiphy, "hwsim cancel_hw_scan\n"); cancel_delayed_work_sync(&hwsim->hw_scan); @@ -2096,11 +2096,11 @@ static void mac80211_hwsim_sw_scan(struct ieee80211_hw *hw, mutex_lock(&hwsim->mutex); if (hwsim->scanning) { - printk(KERN_DEBUG "two hwsim sw_scans detected!\n"); + pr_debug("two hwsim sw_scans detected!\n"); goto out; } - printk(KERN_DEBUG "hwsim sw_scan request, prepping stuff\n"); + pr_debug("hwsim sw_scan request, prepping stuff\n"); memcpy(hwsim->scan_addr, mac_addr, ETH_ALEN); hwsim->scanning = true; @@ -2117,7 +2117,7 @@ static void mac80211_hwsim_sw_scan_complete(struct ieee80211_hw *hw, mutex_lock(&hwsim->mutex); - printk(KERN_DEBUG "hwsim sw_scan_complete\n"); + pr_debug("hwsim sw_scan_complete\n"); hwsim->scanning = false; eth_zero_addr(hwsim->scan_addr); @@ -2131,7 +2131,7 @@ static void hw_roc_start(struct work_struct *work) mutex_lock(&hwsim->mutex); - wiphy_debug(hwsim->hw->wiphy, "hwsim ROC begins\n"); + wiphy_dbg(hwsim->hw->wiphy, "hwsim ROC begins\n"); hwsim->tmp_chan = hwsim->roc_chan; ieee80211_ready_on_channel(hwsim->hw); @@ -2151,7 +2151,7 @@ static void hw_roc_done(struct work_struct *work) hwsim->tmp_chan = NULL; mutex_unlock(&hwsim->mutex); - wiphy_debug(hwsim->hw->wiphy, "hwsim ROC expired\n"); + wiphy_dbg(hwsim->hw->wiphy, "hwsim ROC expired\n"); } static int mac80211_hwsim_roc(struct ieee80211_hw *hw, @@ -2172,8 +2172,8 @@ static int mac80211_hwsim_roc(struct ieee80211_hw *hw, hwsim->roc_duration = duration; mutex_unlock(&hwsim->mutex); - wiphy_debug(hw->wiphy, "hwsim ROC (%d MHz, %d ms)\n", - chan->center_freq, duration); + wiphy_dbg(hw->wiphy, "hwsim ROC (%d MHz, %d ms)\n", + chan->center_freq, duration); ieee80211_queue_delayed_work(hw, &hwsim->roc_start, HZ/50); return 0; @@ -2190,7 +2190,7 @@ static int mac80211_hwsim_croc(struct ieee80211_hw *hw) hwsim->tmp_chan = NULL; mutex_unlock(&hwsim->mutex); - wiphy_debug(hw->wiphy, "hwsim ROC canceled\n"); + wiphy_dbg(hw->wiphy, "hwsim ROC canceled\n"); return 0; } @@ -2199,20 +2199,20 @@ static int mac80211_hwsim_add_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx) { hwsim_set_chanctx_magic(ctx); - wiphy_debug(hw->wiphy, - "add channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", - ctx->def.chan->center_freq, ctx->def.width, - ctx->def.center_freq1, ctx->def.center_freq2); + wiphy_dbg(hw->wiphy, + "add channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", + ctx->def.chan->center_freq, ctx->def.width, + ctx->def.center_freq1, ctx->def.center_freq2); return 0; } static void mac80211_hwsim_remove_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx) { - wiphy_debug(hw->wiphy, - "remove channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", - ctx->def.chan->center_freq, ctx->def.width, - ctx->def.center_freq1, ctx->def.center_freq2); + wiphy_dbg(hw->wiphy, + "remove channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", + ctx->def.chan->center_freq, ctx->def.width, + ctx->def.center_freq1, ctx->def.center_freq2); hwsim_check_chanctx_magic(ctx); hwsim_clear_chanctx_magic(ctx); } @@ -2222,10 +2222,10 @@ static void mac80211_hwsim_change_chanctx(struct ieee80211_hw *hw, u32 changed) { hwsim_check_chanctx_magic(ctx); - wiphy_debug(hw->wiphy, - "change channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", - ctx->def.chan->center_freq, ctx->def.width, - ctx->def.center_freq1, ctx->def.center_freq2); + wiphy_dbg(hw->wiphy, + "change channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", + ctx->def.chan->center_freq, ctx->def.width, + ctx->def.center_freq1, ctx->def.center_freq2); } static int mac80211_hwsim_assign_vif_chanctx(struct ieee80211_hw *hw, @@ -2479,7 +2479,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, ops = &mac80211_hwsim_mchan_ops; hw = ieee80211_alloc_hw_nm(sizeof(*data), ops, param->hwname); if (!hw) { - printk(KERN_DEBUG "mac80211_hwsim: ieee80211_alloc_hw failed\n"); + pr_debug("mac80211_hwsim: ieee80211_alloc_hw failed\n"); err = -ENOMEM; goto failed; } @@ -2507,7 +2507,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, data->dev->driver = &mac80211_hwsim_driver.driver; err = device_bind_driver(data->dev); if (err != 0) { - printk(KERN_DEBUG "mac80211_hwsim: device_bind_driver failed (%d)\n", + pr_debug("mac80211_hwsim: device_bind_driver failed (%d)\n", err); goto failed_bind; } @@ -2698,12 +2698,12 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, err = ieee80211_register_hw(hw); if (err < 0) { - printk(KERN_DEBUG "mac80211_hwsim: ieee80211_register_hw failed (%d)\n", + pr_debug("mac80211_hwsim: ieee80211_register_hw failed (%d)\n", err); goto failed_hw; } - wiphy_debug(hw->wiphy, "hwaddr %pM registered\n", hw->wiphy->perm_addr); + wiphy_dbg(hw->wiphy, "hwaddr %pM registered\n", hw->wiphy->perm_addr); if (param->reg_alpha2) { data->alpha2[0] = param->reg_alpha2[0]; @@ -3067,7 +3067,7 @@ static int hwsim_cloned_frame_received_nl(struct sk_buff *skb_2, return 0; err: - printk(KERN_DEBUG "mac80211_hwsim: error occurred in %s\n", __func__); + pr_debug("mac80211_hwsim: error occurred in %s\n", __func__); out: dev_kfree_skb(skb); return -EINVAL; @@ -3098,7 +3098,7 @@ static int hwsim_register_received_nl(struct sk_buff *skb_2, hwsim_register_wmediumd(net, info->snd_portid); - printk(KERN_DEBUG "mac80211_hwsim: received a REGISTER, " + pr_debug("mac80211_hwsim: received a REGISTER, " "switching to wmediumd mode with pid %d\n", info->snd_portid); return 0; @@ -3387,7 +3387,7 @@ static int __init hwsim_init_netlink(void) return 0; failure: - printk(KERN_DEBUG "mac80211_hwsim: error occurred in %s\n", __func__); + pr_debug("mac80211_hwsim: error occurred in %s\n", __func__); return -EINVAL; } @@ -3578,7 +3578,7 @@ module_init(init_mac80211_hwsim); static void __exit exit_mac80211_hwsim(void) { - printk(KERN_DEBUG "mac80211_hwsim: unregister radios\n"); + pr_debug("mac80211_hwsim: unregister radios\n"); hwsim_exit_netlink(); diff --git a/drivers/net/wireless/marvell/mwifiex/11n.c b/drivers/net/wireless/marvell/mwifiex/11n.c index 725206914911..8772e3949327 100644 --- a/drivers/net/wireless/marvell/mwifiex/11n.c +++ b/drivers/net/wireless/marvell/mwifiex/11n.c @@ -658,12 +658,6 @@ void mwifiex_11n_delba(struct mwifiex_private *priv, int tid) unsigned long flags; spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); - if (list_empty(&priv->rx_reorder_tbl_ptr)) { - dev_dbg(priv->adapter->dev, - "mwifiex_11n_delba: rx_reorder_tbl_ptr empty\n"); - goto exit; - } - list_for_each_entry(rx_reor_tbl_ptr, &priv->rx_reorder_tbl_ptr, list) { if (rx_reor_tbl_ptr->tid == tid) { dev_dbg(priv->adapter->dev, @@ -854,9 +848,6 @@ mwifiex_send_delba_txbastream_tbl(struct mwifiex_private *priv, u8 tid) struct mwifiex_adapter *adapter = priv->adapter; struct mwifiex_tx_ba_stream_tbl *tx_ba_stream_tbl_ptr; - if (list_empty(&priv->tx_ba_stream_tbl_ptr)) - return; - list_for_each_entry(tx_ba_stream_tbl_ptr, &priv->tx_ba_stream_tbl_ptr, list) { if (tx_ba_stream_tbl_ptr->ba_status == BA_SETUP_COMPLETE) { diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c index 274dd5a1574a..d87df2dfcfa4 100644 --- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c +++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c @@ -835,12 +835,6 @@ void mwifiex_update_rxreor_flags(struct mwifiex_adapter *adapter, u8 flags) continue; spin_lock_irqsave(&priv->rx_reorder_tbl_lock, lock_flags); - if (list_empty(&priv->rx_reorder_tbl_ptr)) { - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, - lock_flags); - continue; - } - list_for_each_entry(tbl, &priv->rx_reorder_tbl_ptr, list) tbl->flags = flags; spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, lock_flags); diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c index 32c5074da84c..6e0d9a9c5cfb 100644 --- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c +++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c @@ -142,7 +142,7 @@ mwifiex_cfg80211_del_key(struct wiphy *wiphy, struct net_device *netdev, u8 key_index, bool pairwise, const u8 *mac_addr) { struct mwifiex_private *priv = mwifiex_netdev_get_priv(netdev); - const u8 bc_mac[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; + static const u8 bc_mac[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; const u8 *peer_mac = pairwise ? mac_addr : bc_mac; if (mwifiex_set_encode(priv, NULL, NULL, 0, key_index, peer_mac, 1)) { @@ -454,7 +454,7 @@ mwifiex_cfg80211_add_key(struct wiphy *wiphy, struct net_device *netdev, { struct mwifiex_private *priv = mwifiex_netdev_get_priv(netdev); struct mwifiex_wep_key *wep_key; - const u8 bc_mac[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; + static const u8 bc_mac[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; const u8 *peer_mac = pairwise ? mac_addr : bc_mac; if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP && @@ -2503,6 +2503,7 @@ mwifiex_cfg80211_scan(struct wiphy *wiphy, struct ieee80211_channel *chan; struct ieee_types_header *ie; struct mwifiex_user_scan_cfg *user_scan_cfg; + u8 mac_addr[ETH_ALEN]; mwifiex_dbg(priv->adapter, CMD, "info: received scan request on %s\n", dev->name); @@ -2529,15 +2530,10 @@ mwifiex_cfg80211_scan(struct wiphy *wiphy, priv->scan_request = request; if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { - ether_addr_copy(priv->random_mac, request->mac_addr); - for (i = 0; i < ETH_ALEN; i++) { - priv->random_mac[i] &= request->mac_addr_mask[i]; - priv->random_mac[i] |= get_random_int() & - ~(request->mac_addr_mask[i]); - } - ether_addr_copy(user_scan_cfg->random_mac, priv->random_mac); - } else { - eth_zero_addr(priv->random_mac); + get_random_mask_addr(mac_addr, request->mac_addr, + request->mac_addr_mask); + ether_addr_copy(request->mac_addr, mac_addr); + ether_addr_copy(user_scan_cfg->random_mac, mac_addr); } user_scan_cfg->num_ssids = request->n_ssids; @@ -2959,18 +2955,21 @@ struct wireless_dev *mwifiex_add_virtual_intf(struct wiphy *wiphy, } mwifiex_init_priv_params(priv, dev); - mwifiex_set_mac_address(priv, dev); priv->netdev = dev; - ret = mwifiex_send_cmd(priv, HostCmd_CMD_SET_BSS_MODE, - HostCmd_ACT_GEN_SET, 0, NULL, true); - if (ret) - goto err_set_bss_mode; + if (!adapter->mfg_mode) { + mwifiex_set_mac_address(priv, dev); - ret = mwifiex_sta_init_cmd(priv, false, false); - if (ret) - goto err_sta_init; + ret = mwifiex_send_cmd(priv, HostCmd_CMD_SET_BSS_MODE, + HostCmd_ACT_GEN_SET, 0, NULL, true); + if (ret) + goto err_set_bss_mode; + + ret = mwifiex_sta_init_cmd(priv, false, false); + if (ret) + goto err_sta_init; + } mwifiex_setup_ht_caps(&wiphy->bands[NL80211_BAND_2GHZ]->ht_cap, priv); if (adapter->is_hw_11ac_capable) @@ -3250,8 +3249,8 @@ static int mwifiex_set_wowlan_mef_entry(struct mwifiex_private *priv, int i, filt_num = 0, ret = 0; bool first_pat = true; u8 byte_seq[MWIFIEX_MEF_MAX_BYTESEQ + 1]; - const u8 ipv4_mc_mac[] = {0x33, 0x33}; - const u8 ipv6_mc_mac[] = {0x01, 0x00, 0x5e}; + static const u8 ipv4_mc_mac[] = {0x33, 0x33}; + static const u8 ipv6_mc_mac[] = {0x01, 0x00, 0x5e}; mef_entry->mode = MEF_MODE_HOST_SLEEP; mef_entry->action = MEF_ACTION_ALLOW_AND_WAKEUP_HOST; @@ -3544,9 +3543,9 @@ static int mwifiex_set_rekey_data(struct wiphy *wiphy, struct net_device *dev, static int mwifiex_get_coalesce_pkt_type(u8 *byte_seq) { - const u8 ipv4_mc_mac[] = {0x33, 0x33}; - const u8 ipv6_mc_mac[] = {0x01, 0x00, 0x5e}; - const u8 bc_mac[] = {0xff, 0xff, 0xff, 0xff}; + static const u8 ipv4_mc_mac[] = {0x33, 0x33}; + static const u8 ipv6_mc_mac[] = {0x01, 0x00, 0x5e}; + static const u8 bc_mac[] = {0xff, 0xff, 0xff, 0xff}; if ((byte_seq[0] & 0x01) && (byte_seq[MWIFIEX_COALESCE_MAX_BYTESEQ] == 1)) @@ -3795,9 +3794,8 @@ mwifiex_cfg80211_tdls_chan_switch(struct wiphy *wiphy, struct net_device *dev, spin_lock_irqsave(&priv->sta_list_spinlock, flags); sta_ptr = mwifiex_get_sta_entry(priv, addr); - spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); - if (!sta_ptr) { + spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); wiphy_err(wiphy, "%s: Invalid TDLS peer %pM\n", __func__, addr); return -ENOENT; @@ -3805,15 +3803,18 @@ mwifiex_cfg80211_tdls_chan_switch(struct wiphy *wiphy, struct net_device *dev, if (!(sta_ptr->tdls_cap.extcap.ext_capab[3] & WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH)) { + spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); wiphy_err(wiphy, "%pM do not support tdls cs\n", addr); return -ENOENT; } if (sta_ptr->tdls_status == TDLS_CHAN_SWITCHING || sta_ptr->tdls_status == TDLS_IN_OFF_CHAN) { + spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); wiphy_err(wiphy, "channel switch is running, abort request\n"); return -EALREADY; } + spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); chan = chandef->chan->hw_value; second_chan_offset = mwifiex_get_sec_chan_offset(chan); @@ -3834,18 +3835,20 @@ mwifiex_cfg80211_tdls_cancel_chan_switch(struct wiphy *wiphy, spin_lock_irqsave(&priv->sta_list_spinlock, flags); sta_ptr = mwifiex_get_sta_entry(priv, addr); - spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); - if (!sta_ptr) { + spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); wiphy_err(wiphy, "%s: Invalid TDLS peer %pM\n", __func__, addr); } else if (!(sta_ptr->tdls_status == TDLS_CHAN_SWITCHING || sta_ptr->tdls_status == TDLS_IN_BASE_CHAN || sta_ptr->tdls_status == TDLS_IN_OFF_CHAN)) { + spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); wiphy_err(wiphy, "tdls chan switch not initialize by %pM\n", addr); - } else + } else { + spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); mwifiex_stop_tdls_cs(priv, addr); + } } static int @@ -4202,7 +4205,10 @@ int mwifiex_init_channel_scan_gap(struct mwifiex_adapter *adapter) if (adapter->config_bands & BAND_A) n_channels_a = mwifiex_band_5ghz.n_channels; - adapter->num_in_chan_stats = n_channels_bg + n_channels_a; + /* allocate twice the number total channels, since the driver issues an + * additional active scan request for hidden SSIDs on passive channels. + */ + adapter->num_in_chan_stats = 2 * (n_channels_bg + n_channels_a); adapter->chan_stats = vmalloc(sizeof(*adapter->chan_stats) * adapter->num_in_chan_stats); @@ -4306,10 +4312,12 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter) wiphy->features |= NL80211_FEATURE_HT_IBSS | NL80211_FEATURE_INACTIVITY_TIMER | NL80211_FEATURE_LOW_PRIORITY_SCAN | - NL80211_FEATURE_NEED_OBSS_SCAN | - NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR | - NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR | - NL80211_FEATURE_ND_RANDOM_MAC_ADDR; + NL80211_FEATURE_NEED_OBSS_SCAN; + + if (ISSUPP_RANDOM_MAC(adapter->fw_cap_info)) + wiphy->features |= NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR | + NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR | + NL80211_FEATURE_ND_RANDOM_MAC_ADDR; if (ISSUPP_TDLS_ENABLED(adapter->fw_cap_info)) wiphy->features |= NL80211_FEATURE_TDLS_CHANNEL_SWITCH; diff --git a/drivers/net/wireless/marvell/mwifiex/cmdevt.c b/drivers/net/wireless/marvell/mwifiex/cmdevt.c index 0edc5d621304..a9a1a736e6e8 100644 --- a/drivers/net/wireless/marvell/mwifiex/cmdevt.c +++ b/drivers/net/wireless/marvell/mwifiex/cmdevt.c @@ -17,6 +17,7 @@ * this warranty disclaimer. */ +#include <asm/unaligned.h> #include "decl.h" #include "ioctl.h" #include "util.h" @@ -183,7 +184,6 @@ static int mwifiex_dnld_cmd_to_fw(struct mwifiex_private *priv, uint16_t cmd_code; uint16_t cmd_size; unsigned long flags; - __le32 tmp; if (!adapter || !cmd_node) return -1; @@ -249,9 +249,9 @@ static int mwifiex_dnld_cmd_to_fw(struct mwifiex_private *priv, mwifiex_dbg_dump(adapter, CMD_D, "cmd buffer:", host_cmd, cmd_size); if (adapter->iface_type == MWIFIEX_USB) { - tmp = cpu_to_le32(MWIFIEX_USB_TYPE_CMD); skb_push(cmd_node->cmd_skb, MWIFIEX_TYPE_LEN); - memcpy(cmd_node->cmd_skb->data, &tmp, MWIFIEX_TYPE_LEN); + put_unaligned_le32(MWIFIEX_USB_TYPE_CMD, + cmd_node->cmd_skb->data); adapter->cmd_sent = true; ret = adapter->if_ops.host_to_card(adapter, MWIFIEX_USB_EP_CMD_EVENT, @@ -317,7 +317,6 @@ static int mwifiex_dnld_sleep_confirm_cmd(struct mwifiex_adapter *adapter) (struct mwifiex_opt_sleep_confirm *) adapter->sleep_cfm->data; struct sk_buff *sleep_cfm_tmp; - __le32 tmp; priv = mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_ANY); @@ -342,8 +341,7 @@ static int mwifiex_dnld_sleep_confirm_cmd(struct mwifiex_adapter *adapter) + MWIFIEX_TYPE_LEN); skb_put(sleep_cfm_tmp, sizeof(struct mwifiex_opt_sleep_confirm) + MWIFIEX_TYPE_LEN); - tmp = cpu_to_le32(MWIFIEX_USB_TYPE_CMD); - memcpy(sleep_cfm_tmp->data, &tmp, MWIFIEX_TYPE_LEN); + put_unaligned_le32(MWIFIEX_USB_TYPE_CMD, sleep_cfm_tmp->data); memcpy(sleep_cfm_tmp->data + MWIFIEX_TYPE_LEN, adapter->sleep_cfm->data, sizeof(struct mwifiex_opt_sleep_confirm)); diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h index 9e75522d248a..6b765f3f37fd 100644 --- a/drivers/net/wireless/marvell/mwifiex/fw.h +++ b/drivers/net/wireless/marvell/mwifiex/fw.h @@ -238,6 +238,7 @@ enum MWIFIEX_802_11_PRIVACY_FILTER { #define ISSUPP_DRCS_ENABLED(FwCapInfo) (FwCapInfo & BIT(15)) #define ISSUPP_SDIO_SPA_ENABLED(FwCapInfo) (FwCapInfo & BIT(16)) #define ISSUPP_ADHOC_ENABLED(FwCapInfo) (FwCapInfo & BIT(25)) +#define ISSUPP_RANDOM_MAC(FwCapInfo) (FwCapInfo & BIT(27)) #define MWIFIEX_DEF_HT_CAP (IEEE80211_HT_CAP_DSSSCCK40 | \ (1 << IEEE80211_HT_CAP_RX_STBC_SHIFT) | \ diff --git a/drivers/net/wireless/marvell/mwifiex/init.c b/drivers/net/wireless/marvell/mwifiex/init.c index e11919db7818..1176706ab094 100644 --- a/drivers/net/wireless/marvell/mwifiex/init.c +++ b/drivers/net/wireless/marvell/mwifiex/init.c @@ -579,10 +579,6 @@ static void mwifiex_delete_bss_prio_tbl(struct mwifiex_private *priv) { spin_lock_irqsave(lock, flags); - if (list_empty(head)) { - spin_unlock_irqrestore(lock, flags); - continue; - } list_for_each_entry_safe(bssprio_node, tmp_node, head, list) { if (bssprio_node->priv == priv) { diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h index a76bd797e454..a34de8582e91 100644 --- a/drivers/net/wireless/marvell/mwifiex/main.h +++ b/drivers/net/wireless/marvell/mwifiex/main.h @@ -680,7 +680,6 @@ struct mwifiex_private { struct mwifiex_user_scan_chan hidden_chan[MWIFIEX_USER_SCAN_CHAN_MAX]; u8 assoc_resp_ht_param; bool ht_param_present; - u8 random_mac[ETH_ALEN]; }; diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c index c9d41ed77fc7..d7ce7f75ae38 100644 --- a/drivers/net/wireless/marvell/mwifiex/scan.c +++ b/drivers/net/wireless/marvell/mwifiex/scan.c @@ -1936,8 +1936,6 @@ mwifiex_active_scan_req_for_passive_chan(struct mwifiex_private *priv) if (!user_scan_cfg) return -ENOMEM; - memset(user_scan_cfg, 0, sizeof(*user_scan_cfg)); - for (id = 0; id < MWIFIEX_USER_SCAN_CHAN_MAX; id++) { if (!priv->hidden_chan[id].chan_number) break; @@ -1948,7 +1946,8 @@ mwifiex_active_scan_req_for_passive_chan(struct mwifiex_private *priv) adapter->active_scan_triggered = true; if (priv->scan_request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) - ether_addr_copy(user_scan_cfg->random_mac, priv->random_mac); + ether_addr_copy(user_scan_cfg->random_mac, + priv->scan_request->mac_addr); user_scan_cfg->num_ssids = priv->scan_request->n_ssids; user_scan_cfg->ssid_list = priv->scan_request->ssids; diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c index 0fba5b10ef2d..1bd4e13b8449 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c @@ -70,11 +70,7 @@ mwifiex_process_cmdresp_error(struct mwifiex_private *priv, break; case HostCmd_CMD_802_11_SCAN: case HostCmd_CMD_802_11_SCAN_EXT: - mwifiex_cancel_pending_scan_cmd(adapter); - - spin_lock_irqsave(&adapter->mwifiex_cmd_lock, flags); - adapter->scan_processing = false; - spin_unlock_irqrestore(&adapter->mwifiex_cmd_lock, flags); + mwifiex_cancel_scan(adapter); break; case HostCmd_CMD_MAC_CONTROL: diff --git a/drivers/net/wireless/marvell/mwifiex/sta_event.c b/drivers/net/wireless/marvell/mwifiex/sta_event.c index 839df8a9634e..d8db412b76c6 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_event.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_event.c @@ -359,13 +359,12 @@ static void mwifiex_process_uap_tx_pause(struct mwifiex_private *priv, } else { spin_lock_irqsave(&priv->sta_list_spinlock, flags); sta_ptr = mwifiex_get_sta_entry(priv, tp->peermac); - spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); - if (sta_ptr && sta_ptr->tx_pause != tp->tx_pause) { sta_ptr->tx_pause = tp->tx_pause; mwifiex_update_ralist_tx_pause(priv, tp->peermac, tp->tx_pause); } + spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); } } @@ -396,14 +395,13 @@ static void mwifiex_process_sta_tx_pause(struct mwifiex_private *priv, if (mwifiex_is_tdls_link_setup(status)) { spin_lock_irqsave(&priv->sta_list_spinlock, flags); sta_ptr = mwifiex_get_sta_entry(priv, tp->peermac); - spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); - if (sta_ptr && sta_ptr->tx_pause != tp->tx_pause) { sta_ptr->tx_pause = tp->tx_pause; mwifiex_update_ralist_tx_pause(priv, tp->peermac, tp->tx_pause); } + spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); } } } diff --git a/drivers/net/wireless/marvell/mwifiex/tdls.c b/drivers/net/wireless/marvell/mwifiex/tdls.c index e76af2866a19..9fe0bae957b7 100644 --- a/drivers/net/wireless/marvell/mwifiex/tdls.c +++ b/drivers/net/wireless/marvell/mwifiex/tdls.c @@ -1413,13 +1413,6 @@ void mwifiex_check_auto_tdls(unsigned long context) priv->check_tdls_tx = false; - if (list_empty(&priv->auto_tdls_list)) { - mod_timer(&priv->auto_tdls_timer, - jiffies + - msecs_to_jiffies(MWIFIEX_TIMER_10S)); - return; - } - spin_lock_irqsave(&priv->auto_tdls_lock, flags); list_for_each_entry(tdls_peer, &priv->auto_tdls_list, list) { if ((jiffies - tdls_peer->rssi_jiffies) > diff --git a/drivers/net/wireless/marvell/mwifiex/wmm.c b/drivers/net/wireless/marvell/mwifiex/wmm.c index 0edd26881321..936a0a841af8 100644 --- a/drivers/net/wireless/marvell/mwifiex/wmm.c +++ b/drivers/net/wireless/marvell/mwifiex/wmm.c @@ -359,7 +359,8 @@ static enum mwifiex_wmm_ac_e mwifiex_wmm_convert_tos_to_ac(struct mwifiex_adapter *adapter, u32 tos) { /* Map of TOS UP values to WMM AC */ - const enum mwifiex_wmm_ac_e tos_to_ac[] = { WMM_AC_BE, + static const enum mwifiex_wmm_ac_e tos_to_ac[] = { + WMM_AC_BE, WMM_AC_BK, WMM_AC_BK, WMM_AC_BE, diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c index a450bc6bc774..ebc3792a95bd 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c +++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c @@ -133,6 +133,7 @@ int qtnf_del_virtual_intf(struct wiphy *wiphy, struct wireless_dev *wdev) vif->netdev = NULL; vif->wdev.iftype = NL80211_IFTYPE_UNSPECIFIED; eth_zero_addr(vif->mac_addr); + eth_zero_addr(vif->bssid); return 0; } @@ -201,6 +202,8 @@ err_mac: qtnf_cmd_send_del_intf(vif); err_cmd: vif->wdev.iftype = NL80211_IFTYPE_UNSPECIFIED; + eth_zero_addr(vif->mac_addr); + eth_zero_addr(vif->bssid); return ERR_PTR(-EFAULT); } @@ -256,11 +259,6 @@ static int qtnf_change_beacon(struct wiphy *wiphy, struct net_device *dev, { struct qtnf_vif *vif = qtnf_netdev_get_priv(dev); - if (!(vif->bss_status & QTNF_STATE_AP_START)) { - pr_err("VIF%u.%u: not started\n", vif->mac->macid, vif->vifid); - return -EFAULT; - } - return qtnf_mgmt_set_appie(vif, info); } @@ -268,46 +266,15 @@ static int qtnf_start_ap(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ap_settings *settings) { struct qtnf_vif *vif = qtnf_netdev_get_priv(dev); - struct qtnf_wmac *mac = wiphy_priv(wiphy); - struct qtnf_bss_config *bss_cfg; int ret; - if (!cfg80211_chandef_identical(&mac->chandef, &settings->chandef)) { - memcpy(&mac->chandef, &settings->chandef, sizeof(mac->chandef)); - if (vif->vifid != 0) - pr_warn("%s: unexpected chan %u (%u MHz)\n", dev->name, - settings->chandef.chan->hw_value, - settings->chandef.chan->center_freq); - } - - bss_cfg = &vif->bss_cfg; - memset(bss_cfg, 0, sizeof(*bss_cfg)); - - bss_cfg->bcn_period = settings->beacon_interval; - bss_cfg->dtim = settings->dtim_period; - bss_cfg->auth_type = settings->auth_type; - bss_cfg->privacy = settings->privacy; - - bss_cfg->ssid_len = settings->ssid_len; - memcpy(&bss_cfg->ssid, settings->ssid, bss_cfg->ssid_len); - - memcpy(&bss_cfg->crypto, &settings->crypto, - sizeof(struct cfg80211_crypto_settings)); - - ret = qtnf_cmd_send_config_ap(vif); + ret = qtnf_cmd_send_config_ap(vif, settings); if (ret) { pr_err("VIF%u.%u: failed to push config to FW\n", vif->mac->macid, vif->vifid); goto out; } - if (!(vif->bss_status & QTNF_STATE_AP_CONFIG)) { - pr_err("VIF%u.%u: AP config failed in FW\n", vif->mac->macid, - vif->vifid); - ret = -EFAULT; - goto out; - } - ret = qtnf_mgmt_set_appie(vif, &settings->beacon); if (ret) { pr_err("VIF%u.%u: failed to add IEs to beacon\n", @@ -316,17 +283,9 @@ static int qtnf_start_ap(struct wiphy *wiphy, struct net_device *dev, } ret = qtnf_cmd_send_start_ap(vif); - if (ret) { + if (ret) pr_err("VIF%u.%u: failed to start AP\n", vif->mac->macid, vif->vifid); - goto out; - } - - if (!(vif->bss_status & QTNF_STATE_AP_START)) { - pr_err("VIF%u.%u: FW failed to start AP operation\n", - vif->mac->macid, vif->vifid); - ret = -EFAULT; - } out: return ret; @@ -343,8 +302,6 @@ static int qtnf_stop_ap(struct wiphy *wiphy, struct net_device *dev) if (ret) { pr_err("VIF%u.%u: failed to stop AP operation in FW\n", vif->mac->macid, vif->vifid); - vif->bss_status &= ~QTNF_STATE_AP_START; - vif->bss_status &= ~QTNF_STATE_AP_CONFIG; netif_carrier_off(vif->netdev); } @@ -615,9 +572,6 @@ qtnf_connect(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_connect_params *sme) { struct qtnf_vif *vif = qtnf_netdev_get_priv(dev); - struct qtnf_wmac *mac = wiphy_priv(wiphy); - struct cfg80211_chan_def chandef; - struct qtnf_bss_config *bss_cfg; int ret; if (vif->wdev.iftype != NL80211_IFTYPE_STATION) @@ -626,49 +580,10 @@ qtnf_connect(struct wiphy *wiphy, struct net_device *dev, if (vif->sta_state != QTNF_STA_DISCONNECTED) return -EBUSY; - bss_cfg = &vif->bss_cfg; - memset(bss_cfg, 0, sizeof(*bss_cfg)); - - if (sme->channel) { - /* FIXME: need to set proper nl80211_channel_type value */ - cfg80211_chandef_create(&chandef, sme->channel, - NL80211_CHAN_HT20); - /* fall-back to minimal safe chandef description */ - if (!cfg80211_chandef_valid(&chandef)) - cfg80211_chandef_create(&chandef, sme->channel, - NL80211_CHAN_HT20); - - memcpy(&mac->chandef, &chandef, sizeof(mac->chandef)); - } - - bss_cfg->ssid_len = sme->ssid_len; - memcpy(&bss_cfg->ssid, sme->ssid, bss_cfg->ssid_len); - bss_cfg->auth_type = sme->auth_type; - bss_cfg->privacy = sme->privacy; - bss_cfg->mfp = sme->mfp; - - if ((sme->bg_scan_period > 0) && - (sme->bg_scan_period <= QTNF_MAX_BG_SCAN_PERIOD)) - bss_cfg->bg_scan_period = sme->bg_scan_period; - else if (sme->bg_scan_period == -1) - bss_cfg->bg_scan_period = QTNF_DEFAULT_BG_SCAN_PERIOD; - else - bss_cfg->bg_scan_period = 0; /* disabled */ - - bss_cfg->connect_flags = 0; - - if (sme->flags & ASSOC_REQ_DISABLE_HT) - bss_cfg->connect_flags |= QLINK_STA_CONNECT_DISABLE_HT; - if (sme->flags & ASSOC_REQ_DISABLE_VHT) - bss_cfg->connect_flags |= QLINK_STA_CONNECT_DISABLE_VHT; - if (sme->flags & ASSOC_REQ_USE_RRM) - bss_cfg->connect_flags |= QLINK_STA_CONNECT_USE_RRM; - - memcpy(&bss_cfg->crypto, &sme->crypto, sizeof(bss_cfg->crypto)); if (sme->bssid) - ether_addr_copy(bss_cfg->bssid, sme->bssid); + ether_addr_copy(vif->bssid, sme->bssid); else - eth_zero_addr(bss_cfg->bssid); + eth_zero_addr(vif->bssid); ret = qtnf_cmd_send_connect(vif, sme); if (ret) { @@ -717,15 +632,15 @@ qtnf_dump_survey(struct wiphy *wiphy, struct net_device *dev, int idx, struct survey_info *survey) { struct qtnf_wmac *mac = wiphy_priv(wiphy); + struct wireless_dev *wdev = dev->ieee80211_ptr; struct ieee80211_supported_band *sband; - struct cfg80211_chan_def *chandef; + const struct cfg80211_chan_def *chandef = &wdev->chandef; struct ieee80211_channel *chan; struct qtnf_chan_stats stats; struct qtnf_vif *vif; int ret; vif = qtnf_netdev_get_priv(dev); - chandef = &mac->chandef; sband = wiphy->bands[NL80211_BAND_2GHZ]; if (sband && idx >= sband->n_channels) { @@ -792,46 +707,35 @@ static int qtnf_get_channel(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_chan_def *chandef) { - struct qtnf_wmac *mac = wiphy_priv(wiphy); struct net_device *ndev = wdev->netdev; struct qtnf_vif *vif; + int ret; if (!ndev) return -ENODEV; vif = qtnf_netdev_get_priv(wdev->netdev); - switch (vif->wdev.iftype) { - case NL80211_IFTYPE_STATION: - if (vif->sta_state == QTNF_STA_DISCONNECTED) { - pr_warn("%s: STA disconnected\n", ndev->name); - return -ENODATA; - } - break; - case NL80211_IFTYPE_AP: - if (!(vif->bss_status & QTNF_STATE_AP_START)) { - pr_warn("%s: AP not started\n", ndev->name); - return -ENODATA; - } - break; - default: - pr_err("unsupported vif type (%d)\n", vif->wdev.iftype); - return -ENODATA; + ret = qtnf_cmd_get_channel(vif, chandef); + if (ret) { + pr_err("%s: failed to get channel: %d\n", ndev->name, ret); + goto out; } - if (!cfg80211_chandef_valid(&mac->chandef)) { - pr_err("invalid channel settings on %s\n", ndev->name); - return -ENODATA; + if (!cfg80211_chandef_valid(chandef)) { + pr_err("%s: bad chan freq1=%u freq2=%u bw=%u\n", ndev->name, + chandef->center_freq1, chandef->center_freq2, + chandef->width); + ret = -ENODATA; } - memcpy(chandef, &mac->chandef, sizeof(*chandef)); - return 0; +out: + return ret; } static int qtnf_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_csa_settings *params) { - struct qtnf_wmac *mac = wiphy_priv(wiphy); struct qtnf_vif *vif = qtnf_netdev_get_priv(dev); int ret; @@ -839,41 +743,12 @@ static int qtnf_channel_switch(struct wiphy *wiphy, struct net_device *dev, params->chandef.chan->hw_value, params->count, params->radar_required, params->block_tx); - switch (vif->wdev.iftype) { - case NL80211_IFTYPE_AP: - if (!(vif->bss_status & QTNF_STATE_AP_START)) { - pr_warn("AP not started on %s\n", dev->name); - return -ENOTCONN; - } - break; - default: - pr_err("unsupported vif type (%d) on %s\n", - vif->wdev.iftype, dev->name); - return -EOPNOTSUPP; - } - - if (vif->vifid != 0) { - if (!(mac->status & QTNF_MAC_CSA_ACTIVE)) - return -EOPNOTSUPP; - - if (!cfg80211_chandef_identical(¶ms->chandef, - &mac->csa_chandef)) - return -EINVAL; - - return 0; - } - if (!cfg80211_chandef_valid(¶ms->chandef)) { pr_err("%s: invalid channel\n", dev->name); return -EINVAL; } - if (cfg80211_chandef_identical(¶ms->chandef, &mac->chandef)) { - pr_err("%s: switch request to the same channel\n", dev->name); - return -EALREADY; - } - - ret = qtnf_cmd_send_chan_switch(mac, params); + ret = qtnf_cmd_send_chan_switch(vif, params); if (ret) pr_warn("%s: failed to switch to channel (%u)\n", dev->name, params->chandef.chan->hw_value); @@ -1119,7 +994,7 @@ void qtnf_virtual_intf_cleanup(struct net_device *ndev) break; case QTNF_STA_CONNECTING: cfg80211_connect_result(vif->netdev, - vif->bss_cfg.bssid, NULL, 0, + vif->bssid, NULL, 0, NULL, 0, WLAN_STATUS_UNSPECIFIED_FAILURE, GFP_KERNEL); @@ -1147,7 +1022,7 @@ void qtnf_cfg80211_vif_reset(struct qtnf_vif *vif) switch (vif->sta_state) { case QTNF_STA_CONNECTING: cfg80211_connect_result(vif->netdev, - vif->bss_cfg.bssid, NULL, 0, + vif->bssid, NULL, 0, NULL, 0, WLAN_STATUS_UNSPECIFIED_FAILURE, GFP_KERNEL); diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c index 4206886b110c..babdc600c193 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/commands.c +++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c @@ -173,7 +173,6 @@ int qtnf_cmd_send_start_ap(struct qtnf_vif *vif) goto out; } - vif->bss_status |= QTNF_STATE_AP_START; netif_carrier_on(vif->netdev); out: @@ -181,62 +180,68 @@ out: return ret; } -int qtnf_cmd_send_config_ap(struct qtnf_vif *vif) +int qtnf_cmd_send_config_ap(struct qtnf_vif *vif, + const struct cfg80211_ap_settings *s) { struct sk_buff *cmd_skb; - struct qtnf_bss_config *bss_cfg = &vif->bss_cfg; - struct cfg80211_chan_def *chandef = &vif->mac->chandef; - struct qlink_tlv_channel *qchan; - struct qlink_auth_encr aen; + struct qlink_cmd_config_ap *cmd; + struct qlink_auth_encr *aen; u16 res_code = QLINK_CMD_RESULT_OK; int ret; int i; cmd_skb = qtnf_cmd_alloc_new_cmdskb(vif->mac->macid, vif->vifid, QLINK_CMD_CONFIG_AP, - sizeof(struct qlink_cmd)); + sizeof(*cmd)); if (unlikely(!cmd_skb)) return -ENOMEM; - qtnf_bus_lock(vif->mac->bus); - - qtnf_cmd_skb_put_tlv_arr(cmd_skb, WLAN_EID_SSID, bss_cfg->ssid, - bss_cfg->ssid_len); - qtnf_cmd_skb_put_tlv_u16(cmd_skb, QTN_TLV_ID_BCN_PERIOD, - bss_cfg->bcn_period); - qtnf_cmd_skb_put_tlv_u8(cmd_skb, QTN_TLV_ID_DTIM, bss_cfg->dtim); - - qchan = skb_put_zero(cmd_skb, sizeof(*qchan)); - qchan->hdr.type = cpu_to_le16(QTN_TLV_ID_CHANNEL); - qchan->hdr.len = cpu_to_le16(sizeof(*qchan) - - sizeof(struct qlink_tlv_hdr)); - qchan->hw_value = cpu_to_le16( - ieee80211_frequency_to_channel(chandef->chan->center_freq)); - - memset(&aen, 0, sizeof(aen)); - aen.auth_type = bss_cfg->auth_type; - aen.privacy = !!bss_cfg->privacy; - aen.mfp = bss_cfg->mfp; - aen.wpa_versions = cpu_to_le32(bss_cfg->crypto.wpa_versions); - aen.cipher_group = cpu_to_le32(bss_cfg->crypto.cipher_group); - aen.n_ciphers_pairwise = cpu_to_le32( - bss_cfg->crypto.n_ciphers_pairwise); + cmd = (struct qlink_cmd_config_ap *)cmd_skb->data; + cmd->dtim_period = s->dtim_period; + cmd->beacon_interval = cpu_to_le16(s->beacon_interval); + cmd->hidden_ssid = qlink_hidden_ssid_nl2q(s->hidden_ssid); + cmd->inactivity_timeout = cpu_to_le16(s->inactivity_timeout); + cmd->smps_mode = s->smps_mode; + cmd->p2p_ctwindow = s->p2p_ctwindow; + cmd->p2p_opp_ps = s->p2p_opp_ps; + cmd->pbss = s->pbss; + cmd->ht_required = s->ht_required; + cmd->vht_required = s->vht_required; + + aen = &cmd->aen; + aen->auth_type = s->auth_type; + aen->privacy = !!s->privacy; + aen->mfp = 0; + aen->wpa_versions = cpu_to_le32(s->crypto.wpa_versions); + aen->cipher_group = cpu_to_le32(s->crypto.cipher_group); + aen->n_ciphers_pairwise = cpu_to_le32(s->crypto.n_ciphers_pairwise); for (i = 0; i < QLINK_MAX_NR_CIPHER_SUITES; i++) - aen.ciphers_pairwise[i] = cpu_to_le32( - bss_cfg->crypto.ciphers_pairwise[i]); - aen.n_akm_suites = cpu_to_le32( - bss_cfg->crypto.n_akm_suites); + aen->ciphers_pairwise[i] = + cpu_to_le32(s->crypto.ciphers_pairwise[i]); + aen->n_akm_suites = cpu_to_le32(s->crypto.n_akm_suites); for (i = 0; i < QLINK_MAX_NR_AKM_SUITES; i++) - aen.akm_suites[i] = cpu_to_le32( - bss_cfg->crypto.akm_suites[i]); - aen.control_port = bss_cfg->crypto.control_port; - aen.control_port_no_encrypt = - bss_cfg->crypto.control_port_no_encrypt; - aen.control_port_ethertype = cpu_to_le16(be16_to_cpu( - bss_cfg->crypto.control_port_ethertype)); + aen->akm_suites[i] = cpu_to_le32(s->crypto.akm_suites[i]); + aen->control_port = s->crypto.control_port; + aen->control_port_no_encrypt = s->crypto.control_port_no_encrypt; + aen->control_port_ethertype = + cpu_to_le16(be16_to_cpu(s->crypto.control_port_ethertype)); + + if (s->ssid && s->ssid_len > 0 && s->ssid_len <= IEEE80211_MAX_SSID_LEN) + qtnf_cmd_skb_put_tlv_arr(cmd_skb, WLAN_EID_SSID, s->ssid, + s->ssid_len); - qtnf_cmd_skb_put_tlv_arr(cmd_skb, QTN_TLV_ID_CRYPTO, (u8 *)&aen, - sizeof(aen)); + if (cfg80211_chandef_valid(&s->chandef)) { + struct qlink_tlv_chandef *chtlv = + (struct qlink_tlv_chandef *)skb_put(cmd_skb, + sizeof(*chtlv)); + + chtlv->hdr.type = cpu_to_le16(QTN_TLV_ID_CHANDEF); + chtlv->hdr.len = cpu_to_le16(sizeof(*chtlv) - + sizeof(chtlv->hdr)); + qlink_chandef_cfg2q(&s->chandef, &chtlv->chan); + } + + qtnf_bus_lock(vif->mac->bus); ret = qtnf_cmd_send(vif->mac->bus, cmd_skb, &res_code); @@ -250,8 +255,6 @@ int qtnf_cmd_send_config_ap(struct qtnf_vif *vif) goto out; } - vif->bss_status |= QTNF_STATE_AP_CONFIG; - out: qtnf_bus_unlock(vif->mac->bus); return ret; @@ -283,9 +286,6 @@ int qtnf_cmd_send_stop_ap(struct qtnf_vif *vif) goto out; } - vif->bss_status &= ~QTNF_STATE_AP_START; - vif->bss_status &= ~QTNF_STATE_AP_CONFIG; - netif_carrier_off(vif->netdev); out: @@ -2037,11 +2037,11 @@ int qtnf_cmd_send_connect(struct qtnf_vif *vif, { struct sk_buff *cmd_skb; struct qlink_cmd_connect *cmd; - struct qtnf_bss_config *bss_cfg = &vif->bss_cfg; - struct qlink_auth_encr aen; + struct qlink_auth_encr *aen; u16 res_code = QLINK_CMD_RESULT_OK; int ret; int i; + u32 connect_flags = 0; cmd_skb = qtnf_cmd_alloc_new_cmdskb(vif->mac->macid, vif->vifid, QLINK_CMD_CONNECT, @@ -2049,52 +2049,65 @@ int qtnf_cmd_send_connect(struct qtnf_vif *vif, if (unlikely(!cmd_skb)) return -ENOMEM; - qtnf_bus_lock(vif->mac->bus); - cmd = (struct qlink_cmd_connect *)cmd_skb->data; - ether_addr_copy(cmd->bssid, bss_cfg->bssid); + ether_addr_copy(cmd->bssid, vif->bssid); + + if (sme->channel) + cmd->channel = cpu_to_le16(sme->channel->hw_value); + else + cmd->channel = 0; + + if ((sme->bg_scan_period > 0) && + (sme->bg_scan_period <= QTNF_MAX_BG_SCAN_PERIOD)) + cmd->bg_scan_period = cpu_to_le16(sme->bg_scan_period); + else if (sme->bg_scan_period == -1) + cmd->bg_scan_period = cpu_to_le16(QTNF_DEFAULT_BG_SCAN_PERIOD); + else + cmd->bg_scan_period = 0; /* disabled */ - if (vif->mac->chandef.chan) - cmd->channel = cpu_to_le16(vif->mac->chandef.chan->hw_value); + if (sme->flags & ASSOC_REQ_DISABLE_HT) + connect_flags |= QLINK_STA_CONNECT_DISABLE_HT; + if (sme->flags & ASSOC_REQ_DISABLE_VHT) + connect_flags |= QLINK_STA_CONNECT_DISABLE_VHT; + if (sme->flags & ASSOC_REQ_USE_RRM) + connect_flags |= QLINK_STA_CONNECT_USE_RRM; - cmd->bg_scan_period = cpu_to_le16(bss_cfg->bg_scan_period); + cmd->flags = cpu_to_le32(connect_flags); - memset(&aen, 0, sizeof(aen)); - aen.auth_type = bss_cfg->auth_type; - aen.privacy = !!bss_cfg->privacy; - aen.mfp = bss_cfg->mfp; - aen.wpa_versions = cpu_to_le32(bss_cfg->crypto.wpa_versions); - aen.cipher_group = cpu_to_le32(bss_cfg->crypto.cipher_group); - aen.n_ciphers_pairwise = cpu_to_le32( - bss_cfg->crypto.n_ciphers_pairwise); + aen = &cmd->aen; + aen->auth_type = sme->auth_type; + aen->privacy = !!sme->privacy; + aen->mfp = sme->mfp; + aen->wpa_versions = cpu_to_le32(sme->crypto.wpa_versions); + aen->cipher_group = cpu_to_le32(sme->crypto.cipher_group); + aen->n_ciphers_pairwise = cpu_to_le32(sme->crypto.n_ciphers_pairwise); for (i = 0; i < QLINK_MAX_NR_CIPHER_SUITES; i++) - aen.ciphers_pairwise[i] = cpu_to_le32( - bss_cfg->crypto.ciphers_pairwise[i]); + aen->ciphers_pairwise[i] = + cpu_to_le32(sme->crypto.ciphers_pairwise[i]); - aen.n_akm_suites = cpu_to_le32(bss_cfg->crypto.n_akm_suites); + aen->n_akm_suites = cpu_to_le32(sme->crypto.n_akm_suites); for (i = 0; i < QLINK_MAX_NR_AKM_SUITES; i++) - aen.akm_suites[i] = cpu_to_le32( - bss_cfg->crypto.akm_suites[i]); + aen->akm_suites[i] = cpu_to_le32(sme->crypto.akm_suites[i]); - aen.control_port = bss_cfg->crypto.control_port; - aen.control_port_no_encrypt = - bss_cfg->crypto.control_port_no_encrypt; - aen.control_port_ethertype = cpu_to_le16(be16_to_cpu( - bss_cfg->crypto.control_port_ethertype)); + aen->control_port = sme->crypto.control_port; + aen->control_port_no_encrypt = + sme->crypto.control_port_no_encrypt; + aen->control_port_ethertype = + cpu_to_le16(be16_to_cpu(sme->crypto.control_port_ethertype)); - qtnf_cmd_skb_put_tlv_arr(cmd_skb, WLAN_EID_SSID, bss_cfg->ssid, - bss_cfg->ssid_len); - qtnf_cmd_skb_put_tlv_arr(cmd_skb, QTN_TLV_ID_CRYPTO, (u8 *)&aen, - sizeof(aen)); + qtnf_cmd_skb_put_tlv_arr(cmd_skb, WLAN_EID_SSID, sme->ssid, + sme->ssid_len); if (sme->ie_len != 0) qtnf_cmd_skb_put_tlv_arr(cmd_skb, QTN_TLV_ID_IE_SET, sme->ie, sme->ie_len); + qtnf_bus_lock(vif->mac->bus); + ret = qtnf_cmd_send(vif->mac->bus, cmd_skb, &res_code); if (unlikely(ret)) @@ -2304,15 +2317,16 @@ out: return ret; } -int qtnf_cmd_send_chan_switch(struct qtnf_wmac *mac, +int qtnf_cmd_send_chan_switch(struct qtnf_vif *vif, struct cfg80211_csa_settings *params) { + struct qtnf_wmac *mac = vif->mac; struct qlink_cmd_chan_switch *cmd; struct sk_buff *cmd_skb; u16 res_code = QLINK_CMD_RESULT_OK; int ret; - cmd_skb = qtnf_cmd_alloc_new_cmdskb(mac->macid, 0x0, + cmd_skb = qtnf_cmd_alloc_new_cmdskb(mac->macid, vif->vifid, QLINK_CMD_CHAN_SWITCH, sizeof(*cmd)); @@ -2334,9 +2348,6 @@ int qtnf_cmd_send_chan_switch(struct qtnf_wmac *mac, switch (res_code) { case QLINK_CMD_RESULT_OK: - memcpy(&mac->csa_chandef, ¶ms->chandef, - sizeof(mac->csa_chandef)); - mac->status |= QTNF_MAC_CSA_ACTIVE; ret = 0; break; case QLINK_CMD_RESULT_ENOTFOUND: @@ -2358,3 +2369,41 @@ out: qtnf_bus_unlock(mac->bus); return ret; } + +int qtnf_cmd_get_channel(struct qtnf_vif *vif, struct cfg80211_chan_def *chdef) +{ + struct qtnf_bus *bus = vif->mac->bus; + const struct qlink_resp_channel_get *resp; + struct sk_buff *cmd_skb; + struct sk_buff *resp_skb = NULL; + u16 res_code = QLINK_CMD_RESULT_OK; + int ret; + + cmd_skb = qtnf_cmd_alloc_new_cmdskb(vif->mac->macid, vif->vifid, + QLINK_CMD_CHAN_GET, + sizeof(struct qlink_cmd)); + if (unlikely(!cmd_skb)) + return -ENOMEM; + + qtnf_bus_lock(bus); + + ret = qtnf_cmd_send_with_reply(bus, cmd_skb, &resp_skb, &res_code, + sizeof(*resp), NULL); + + qtnf_bus_unlock(bus); + + if (unlikely(ret)) + goto out; + + if (unlikely(res_code != QLINK_CMD_RESULT_OK)) { + ret = -ENODATA; + goto out; + } + + resp = (const struct qlink_resp_channel_get *)resp_skb->data; + qlink_chandef_q2cfg(priv_to_wiphy(vif->mac), &resp->chan, chdef); + +out: + consume_skb(resp_skb); + return ret; +} diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.h b/drivers/net/wireless/quantenna/qtnfmac/commands.h index 783b20364296..e87c4a484dd4 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/commands.h +++ b/drivers/net/wireless/quantenna/qtnfmac/commands.h @@ -33,7 +33,8 @@ int qtnf_cmd_send_del_intf(struct qtnf_vif *vif); int qtnf_cmd_get_mac_chan_info(struct qtnf_wmac *mac, struct ieee80211_supported_band *band); int qtnf_cmd_send_regulatory_config(struct qtnf_wmac *mac, const char *alpha2); -int qtnf_cmd_send_config_ap(struct qtnf_vif *vif); +int qtnf_cmd_send_config_ap(struct qtnf_vif *vif, + const struct cfg80211_ap_settings *s); int qtnf_cmd_send_start_ap(struct qtnf_vif *vif); int qtnf_cmd_send_stop_ap(struct qtnf_vif *vif); int qtnf_cmd_send_register_mgmt(struct qtnf_vif *vif, u16 frame_type, bool reg); @@ -73,7 +74,8 @@ int qtnf_cmd_send_updown_intf(struct qtnf_vif *vif, int qtnf_cmd_reg_notify(struct qtnf_bus *bus, struct regulatory_request *req); int qtnf_cmd_get_chan_stats(struct qtnf_wmac *mac, u16 channel, struct qtnf_chan_stats *stats); -int qtnf_cmd_send_chan_switch(struct qtnf_wmac *mac, +int qtnf_cmd_send_chan_switch(struct qtnf_vif *vif, struct cfg80211_csa_settings *params); +int qtnf_cmd_get_channel(struct qtnf_vif *vif, struct cfg80211_chan_def *chdef); #endif /* QLINK_COMMANDS_H_ */ diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.h b/drivers/net/wireless/quantenna/qtnfmac/core.h index 066fcd1095a0..44a2cbb19310 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/core.h +++ b/drivers/net/wireless/quantenna/qtnfmac/core.h @@ -52,27 +52,11 @@ #define QTNF_DEF_WDOG_TIMEOUT 5 #define QTNF_TX_TIMEOUT_TRSHLD 100 -#define QTNF_STATE_AP_CONFIG BIT(2) -#define QTNF_STATE_AP_START BIT(1) - extern const struct net_device_ops qtnf_netdev_ops; + struct qtnf_bus; struct qtnf_vif; -struct qtnf_bss_config { - u8 ssid[IEEE80211_MAX_SSID_LEN]; - u8 bssid[ETH_ALEN]; - size_t ssid_len; - u8 dtim; - u16 bcn_period; - u16 auth_type; - bool privacy; - enum nl80211_mfp mfp; - struct cfg80211_crypto_settings crypto; - u16 bg_scan_period; - u32 connect_flags; -}; - struct qtnf_sta_node { struct list_head list; u8 mac_addr[ETH_ALEN]; @@ -89,12 +73,10 @@ enum qtnf_sta_state { QTNF_STA_CONNECTED }; -enum qtnf_mac_status { - QTNF_MAC_CSA_ACTIVE = BIT(0) -}; - struct qtnf_vif { struct wireless_dev wdev; + u8 bssid[ETH_ALEN]; + u8 mac_addr[ETH_ALEN]; u8 vifid; u8 bss_priority; u8 bss_status; @@ -102,9 +84,8 @@ struct qtnf_vif { u16 mgmt_frames_bitmask; struct net_device *netdev; struct qtnf_wmac *mac; - u8 mac_addr[ETH_ALEN]; + struct work_struct reset_work; - struct qtnf_bss_config bss_cfg; struct qtnf_sta_list sta_list; unsigned long cons_tx_timeout_cnt; }; @@ -141,13 +122,10 @@ struct qtnf_wmac { u8 macid; u8 wiphy_registered; u8 macaddr[ETH_ALEN]; - u32 status; struct qtnf_bus *bus; struct qtnf_mac_info macinfo; struct qtnf_vif iflist[QTNF_MAX_INTF]; struct cfg80211_scan_request *scan_req; - struct cfg80211_chan_def chandef; - struct cfg80211_chan_def csa_chandef; struct mutex mac_lock; /* lock during wmac speicific ops */ struct timer_list scan_timeout; }; diff --git a/drivers/net/wireless/quantenna/qtnfmac/event.c b/drivers/net/wireless/quantenna/qtnfmac/event.c index 43d2e7fd6e02..4b29f9fb9c3c 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/event.c +++ b/drivers/net/wireless/quantenna/qtnfmac/event.c @@ -25,6 +25,7 @@ #include "trans.h" #include "util.h" #include "event.h" +#include "qlink_util.h" static int qtnf_event_handle_sta_assoc(struct qtnf_wmac *mac, struct qtnf_vif *vif, @@ -52,12 +53,6 @@ qtnf_event_handle_sta_assoc(struct qtnf_wmac *mac, struct qtnf_vif *vif, return -EPROTO; } - if (!(vif->bss_status & QTNF_STATE_AP_START)) { - pr_err("VIF%u.%u: STA_ASSOC event when AP is not started\n", - mac->macid, vif->vifid); - return -EPROTO; - } - sta_addr = sta_assoc->sta_addr; frame_control = le16_to_cpu(sta_assoc->frame_control); @@ -126,12 +121,6 @@ qtnf_event_handle_sta_deauth(struct qtnf_wmac *mac, struct qtnf_vif *vif, return -EPROTO; } - if (!(vif->bss_status & QTNF_STATE_AP_START)) { - pr_err("VIF%u.%u: STA_DEAUTH event when AP is not started\n", - mac->macid, vif->vifid); - return -EPROTO; - } - sta_addr = sta_deauth->sta_addr; reason = le16_to_cpu(sta_deauth->reason); @@ -357,40 +346,29 @@ qtnf_event_handle_freq_change(struct qtnf_wmac *mac, { struct wiphy *wiphy = priv_to_wiphy(mac); struct cfg80211_chan_def chandef; - struct ieee80211_channel *chan; struct qtnf_vif *vif; - int freq; int i; if (len < sizeof(*data)) { - pr_err("payload is too short\n"); + pr_err("MAC%u: payload is too short\n", mac->macid); return -EINVAL; } - freq = le32_to_cpu(data->freq); - chan = ieee80211_get_channel(wiphy, freq); - if (!chan) { - pr_err("channel at %d MHz not found\n", freq); - return -EINVAL; - } + if (!wiphy->registered) + return 0; - pr_debug("MAC%d switch to new channel %u MHz\n", mac->macid, freq); + qlink_chandef_q2cfg(wiphy, &data->chan, &chandef); - if (mac->status & QTNF_MAC_CSA_ACTIVE) { - mac->status &= ~QTNF_MAC_CSA_ACTIVE; - if (chan->hw_value != mac->csa_chandef.chan->hw_value) - pr_warn("unexpected switch to %u during CSA to %u\n", - chan->hw_value, - mac->csa_chandef.chan->hw_value); + if (!cfg80211_chandef_valid(&chandef)) { + pr_err("MAC%u: bad channel f1=%u f2=%u bw=%u\n", mac->macid, + chandef.center_freq1, chandef.center_freq2, + chandef.width); + return -EINVAL; } - /* FIXME: need to figure out proper nl80211_channel_type value */ - cfg80211_chandef_create(&chandef, chan, NL80211_CHAN_HT20); - /* fall-back to minimal safe chandef description */ - if (!cfg80211_chandef_valid(&chandef)) - cfg80211_chandef_create(&chandef, chan, NL80211_CHAN_HT20); - - memcpy(&mac->chandef, &chandef, sizeof(mac->chandef)); + pr_debug("MAC%d: new channel ieee=%u freq1=%u freq2=%u bw=%u\n", + mac->macid, chandef.chan->hw_value, chandef.center_freq1, + chandef.center_freq2, chandef.width); for (i = 0; i < QTNF_MAX_INTF; i++) { vif = &mac->iflist[i]; diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink.h b/drivers/net/wireless/quantenna/qtnfmac/qlink.h index a8242f678496..7b313d38c30b 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/qlink.h +++ b/drivers/net/wireless/quantenna/qtnfmac/qlink.h @@ -108,16 +108,48 @@ enum qlink_sta_flags { }; enum qlink_channel_width { - QLINK_CHAN_WIDTH_5 = BIT(0), - QLINK_CHAN_WIDTH_10 = BIT(1), - QLINK_CHAN_WIDTH_20_NOHT = BIT(2), - QLINK_CHAN_WIDTH_20 = BIT(3), - QLINK_CHAN_WIDTH_40 = BIT(4), - QLINK_CHAN_WIDTH_80 = BIT(5), - QLINK_CHAN_WIDTH_80P80 = BIT(6), - QLINK_CHAN_WIDTH_160 = BIT(7), + QLINK_CHAN_WIDTH_5 = 0, + QLINK_CHAN_WIDTH_10, + QLINK_CHAN_WIDTH_20_NOHT, + QLINK_CHAN_WIDTH_20, + QLINK_CHAN_WIDTH_40, + QLINK_CHAN_WIDTH_80, + QLINK_CHAN_WIDTH_80P80, + QLINK_CHAN_WIDTH_160, }; +/** + * struct qlink_chandef - qlink channel definition + * + * @center_freq1: center frequency of first segment + * @center_freq2: center frequency of second segment (80+80 only) + * @width: channel width, one of @enum qlink_channel_width + */ +struct qlink_chandef { + __le16 center_freq1; + __le16 center_freq2; + u8 width; + u8 rsvd[3]; +} __packed; + +#define QLINK_MAX_NR_CIPHER_SUITES 5 +#define QLINK_MAX_NR_AKM_SUITES 2 + +struct qlink_auth_encr { + __le32 wpa_versions; + __le32 cipher_group; + __le32 n_ciphers_pairwise; + __le32 ciphers_pairwise[QLINK_MAX_NR_CIPHER_SUITES]; + __le32 n_akm_suites; + __le32 akm_suites[QLINK_MAX_NR_AKM_SUITES]; + __le16 control_port_ethertype; + u8 auth_type; + u8 privacy; + u8 mfp; + u8 control_port; + u8 control_port_no_encrypt; +} __packed; + /* QLINK Command messages related definitions */ @@ -155,6 +187,7 @@ enum qlink_cmd_type { QLINK_CMD_REG_NOTIFY = 0x0019, QLINK_CMD_CHANS_INFO_GET = 0x001A, QLINK_CMD_CHAN_SWITCH = 0x001B, + QLINK_CMD_CHAN_GET = 0x001C, QLINK_CMD_CONFIG_AP = 0x0020, QLINK_CMD_START_AP = 0x0021, QLINK_CMD_STOP_AP = 0x0022, @@ -384,8 +417,9 @@ enum qlink_sta_connect_flags { * struct qlink_cmd_connect - data for QLINK_CMD_CONNECT command * * @flags: for future use. - * @freq: center frequence of a channel which should be used to connect. + * @channel: channel which should be used to connect. * @bg_scan_period: period of background scan. + * @aen: authentication information. * @bssid: BSSID of the BSS to connect to. * @payload: variable portion of connection request. */ @@ -394,6 +428,7 @@ struct qlink_cmd_connect { __le32 flags; __le16 channel; __le16 bg_scan_period; + struct qlink_auth_encr aen; u8 bssid[ETH_ALEN]; u8 payload[0]; } __packed; @@ -506,6 +541,46 @@ struct qlink_cmd_chan_switch { u8 beacon_count; } __packed; +/** + * enum qlink_hidden_ssid - values for %NL80211_ATTR_HIDDEN_SSID + * + * Refer to &enum nl80211_hidden_ssid + */ +enum qlink_hidden_ssid { + QLINK_HIDDEN_SSID_NOT_IN_USE, + QLINK_HIDDEN_SSID_ZERO_LEN, + QLINK_HIDDEN_SSID_ZERO_CONTENTS +}; + +/** + * struct qlink_cmd_config_ap - data for QLINK_CMD_CONFIG_AP command + * + * @beacon_interval: beacon interval + * @inactivity_timeout: station's inactivity period in seconds + * @dtim_period: DTIM period + * @hidden_ssid: whether to hide the SSID, one of &enum qlink_hidden_ssid + * @smps_mode: SMPS mode + * @ht_required: stations must support HT + * @vht_required: stations must support VHT + * @aen: encryption info + * @info: variable configurations + */ +struct qlink_cmd_config_ap { + struct qlink_cmd chdr; + __le16 beacon_interval; + __le16 inactivity_timeout; + u8 dtim_period; + u8 hidden_ssid; + u8 smps_mode; + u8 p2p_ctwindow; + u8 p2p_opp_ps; + u8 pbss; + u8 ht_required; + u8 vht_required; + struct qlink_auth_encr aen; + u8 info[0]; +} __packed; + /* QLINK Command Responses messages related definitions */ @@ -680,6 +755,16 @@ struct qlink_resp_get_chan_stats { u8 info[0]; } __packed; +/** + * struct qlink_resp_channel_get - response for QLINK_CMD_CHAN_GET command + * + * @chan: definition of current operating channel. + */ +struct qlink_resp_channel_get { + struct qlink_resp rhdr; + struct qlink_chandef chan; +} __packed; + /* QLINK Events messages related definitions */ @@ -764,11 +849,11 @@ struct qlink_event_bss_leave { /** * struct qlink_event_freq_change - data for QLINK_EVENT_FREQ_CHANGE event * - * @freq: new operating frequency in MHz + * @chan: new operating channel definition */ struct qlink_event_freq_change { struct qlink_event ehdr; - __le32 freq; + struct qlink_chandef chan; } __packed; enum qlink_rxmgmt_flags { @@ -856,10 +941,9 @@ enum qlink_tlv_id { QTN_TLV_ID_RTS_THRESH = 0x0202, QTN_TLV_ID_SRETRY_LIMIT = 0x0203, QTN_TLV_ID_LRETRY_LIMIT = 0x0204, - QTN_TLV_ID_BCN_PERIOD = 0x0205, - QTN_TLV_ID_DTIM = 0x0206, QTN_TLV_ID_REG_RULE = 0x0207, QTN_TLV_ID_CHANNEL = 0x020F, + QTN_TLV_ID_CHANDEF = 0x0210, QTN_TLV_ID_COVERAGE_CLASS = 0x0213, QTN_TLV_ID_IFACE_LIMIT = 0x0214, QTN_TLV_ID_NUM_IFACE_COMB = 0x0215, @@ -868,7 +952,6 @@ enum qlink_tlv_id { QTN_TLV_ID_STA_GENERIC_INFO = 0x0301, QTN_TLV_ID_KEY = 0x0302, QTN_TLV_ID_SEQ = 0x0303, - QTN_TLV_ID_CRYPTO = 0x0304, QTN_TLV_ID_IE_SET = 0x0305, }; @@ -1047,22 +1130,16 @@ struct qlink_tlv_channel { u8 rsvd[2]; } __packed; -#define QLINK_MAX_NR_CIPHER_SUITES 5 -#define QLINK_MAX_NR_AKM_SUITES 2 - -struct qlink_auth_encr { - __le32 wpa_versions; - __le32 cipher_group; - __le32 n_ciphers_pairwise; - __le32 ciphers_pairwise[QLINK_MAX_NR_CIPHER_SUITES]; - __le32 n_akm_suites; - __le32 akm_suites[QLINK_MAX_NR_AKM_SUITES]; - __le16 control_port_ethertype; - u8 auth_type; - u8 privacy; - u8 mfp; - u8 control_port; - u8 control_port_no_encrypt; +/** + * struct qlink_tlv_chandef - data for QTN_TLV_ID_CHANDEF TLV + * + * Channel definition. + * + * @chan: channel definition data. + */ +struct qlink_tlv_chandef { + struct qlink_tlv_hdr hdr; + struct qlink_chandef chan; } __packed; struct qlink_chan_stats { diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink_util.c b/drivers/net/wireless/quantenna/qtnfmac/qlink_util.c index cf024c995fd6..61d999affb09 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/qlink_util.c +++ b/drivers/net/wireless/quantenna/qtnfmac/qlink_util.c @@ -49,29 +49,126 @@ u8 qlink_chan_width_mask_to_nl(u16 qlink_mask) { u8 result = 0; - if (qlink_mask & QLINK_CHAN_WIDTH_5) + if (qlink_mask & BIT(QLINK_CHAN_WIDTH_5)) result |= BIT(NL80211_CHAN_WIDTH_5); - if (qlink_mask & QLINK_CHAN_WIDTH_10) + if (qlink_mask & BIT(QLINK_CHAN_WIDTH_10)) result |= BIT(NL80211_CHAN_WIDTH_10); - if (qlink_mask & QLINK_CHAN_WIDTH_20_NOHT) + if (qlink_mask & BIT(QLINK_CHAN_WIDTH_20_NOHT)) result |= BIT(NL80211_CHAN_WIDTH_20_NOHT); - if (qlink_mask & QLINK_CHAN_WIDTH_20) + if (qlink_mask & BIT(QLINK_CHAN_WIDTH_20)) result |= BIT(NL80211_CHAN_WIDTH_20); - if (qlink_mask & QLINK_CHAN_WIDTH_40) + if (qlink_mask & BIT(QLINK_CHAN_WIDTH_40)) result |= BIT(NL80211_CHAN_WIDTH_40); - if (qlink_mask & QLINK_CHAN_WIDTH_80) + if (qlink_mask & BIT(QLINK_CHAN_WIDTH_80)) result |= BIT(NL80211_CHAN_WIDTH_80); - if (qlink_mask & QLINK_CHAN_WIDTH_80P80) + if (qlink_mask & BIT(QLINK_CHAN_WIDTH_80P80)) result |= BIT(NL80211_CHAN_WIDTH_80P80); - if (qlink_mask & QLINK_CHAN_WIDTH_160) + if (qlink_mask & BIT(QLINK_CHAN_WIDTH_160)) result |= BIT(NL80211_CHAN_WIDTH_160); return result; } + +static enum nl80211_chan_width qlink_chanwidth_to_nl(u8 qlw) +{ + switch (qlw) { + case QLINK_CHAN_WIDTH_20_NOHT: + return NL80211_CHAN_WIDTH_20_NOHT; + case QLINK_CHAN_WIDTH_20: + return NL80211_CHAN_WIDTH_20; + case QLINK_CHAN_WIDTH_40: + return NL80211_CHAN_WIDTH_40; + case QLINK_CHAN_WIDTH_80: + return NL80211_CHAN_WIDTH_80; + case QLINK_CHAN_WIDTH_80P80: + return NL80211_CHAN_WIDTH_80P80; + case QLINK_CHAN_WIDTH_160: + return NL80211_CHAN_WIDTH_160; + case QLINK_CHAN_WIDTH_5: + return NL80211_CHAN_WIDTH_5; + case QLINK_CHAN_WIDTH_10: + return NL80211_CHAN_WIDTH_10; + default: + return -1; + } +} + +void qlink_chandef_q2cfg(struct wiphy *wiphy, + const struct qlink_chandef *qch, + struct cfg80211_chan_def *chdef) +{ + chdef->center_freq1 = le16_to_cpu(qch->center_freq1); + chdef->center_freq2 = le16_to_cpu(qch->center_freq2); + chdef->width = qlink_chanwidth_to_nl(qch->width); + + switch (chdef->width) { + case NL80211_CHAN_WIDTH_20_NOHT: + case NL80211_CHAN_WIDTH_20: + case NL80211_CHAN_WIDTH_5: + case NL80211_CHAN_WIDTH_10: + chdef->chan = ieee80211_get_channel(wiphy, chdef->center_freq1); + break; + case NL80211_CHAN_WIDTH_40: + case NL80211_CHAN_WIDTH_80: + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_160: + chdef->chan = ieee80211_get_channel(wiphy, + chdef->center_freq1 - 10); + break; + default: + chdef->chan = NULL; + break; + } +} + +static u8 qlink_chanwidth_nl_to_qlink(enum nl80211_chan_width nlwidth) +{ + switch (nlwidth) { + case NL80211_CHAN_WIDTH_20_NOHT: + return QLINK_CHAN_WIDTH_20_NOHT; + case NL80211_CHAN_WIDTH_20: + return QLINK_CHAN_WIDTH_20; + case NL80211_CHAN_WIDTH_40: + return QLINK_CHAN_WIDTH_40; + case NL80211_CHAN_WIDTH_80: + return QLINK_CHAN_WIDTH_80; + case NL80211_CHAN_WIDTH_80P80: + return QLINK_CHAN_WIDTH_80P80; + case NL80211_CHAN_WIDTH_160: + return QLINK_CHAN_WIDTH_160; + case NL80211_CHAN_WIDTH_5: + return QLINK_CHAN_WIDTH_5; + case NL80211_CHAN_WIDTH_10: + return QLINK_CHAN_WIDTH_10; + default: + return -1; + } +} + +void qlink_chandef_cfg2q(const struct cfg80211_chan_def *chdef, + struct qlink_chandef *qch) +{ + qch->center_freq1 = cpu_to_le16(chdef->center_freq1); + qch->center_freq2 = cpu_to_le16(chdef->center_freq2); + qch->width = qlink_chanwidth_nl_to_qlink(chdef->width); +} + +enum qlink_hidden_ssid qlink_hidden_ssid_nl2q(enum nl80211_hidden_ssid nl_val) +{ + switch (nl_val) { + case NL80211_HIDDEN_SSID_ZERO_LEN: + return QLINK_HIDDEN_SSID_ZERO_LEN; + case NL80211_HIDDEN_SSID_ZERO_CONTENTS: + return QLINK_HIDDEN_SSID_ZERO_CONTENTS; + case NL80211_HIDDEN_SSID_NOT_IN_USE: + default: + return QLINK_HIDDEN_SSID_NOT_IN_USE; + } +} diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink_util.h b/drivers/net/wireless/quantenna/qtnfmac/qlink_util.h index de06c1e20b5b..260383d6d109 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/qlink_util.h +++ b/drivers/net/wireless/quantenna/qtnfmac/qlink_util.h @@ -19,6 +19,7 @@ #include <linux/types.h> #include <linux/skbuff.h> +#include <net/cfg80211.h> #include "qlink.h" @@ -62,5 +63,11 @@ static inline void qtnf_cmd_skb_put_tlv_u16(struct sk_buff *skb, u16 qlink_iface_type_to_nl_mask(u16 qlink_type); u8 qlink_chan_width_mask_to_nl(u16 qlink_mask); +void qlink_chandef_q2cfg(struct wiphy *wiphy, + const struct qlink_chandef *qch, + struct cfg80211_chan_def *chdef); +void qlink_chandef_cfg2q(const struct cfg80211_chan_def *chdef, + struct qlink_chandef *qch); +enum qlink_hidden_ssid qlink_hidden_ssid_nl2q(enum nl80211_hidden_ssid nl_val); #endif /* _QTN_FMAC_QLINK_UTIL_H_ */ diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index 170cd504e8ff..d8afcdfca1ed 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -92,7 +92,7 @@ static const struct iw_handler_def ray_handler_def; /***** Prototypes for raylink functions **************************************/ static void authenticate(ray_dev_t *local); static int build_auth_frame(ray_dev_t *local, UCHAR *dest, int auth_type); -static void authenticate_timeout(u_long); +static void authenticate_timeout(struct timer_list *t); static int get_free_ccs(ray_dev_t *local); static int get_free_tx_ccs(ray_dev_t *local); static void init_startup_params(ray_dev_t *local); @@ -102,7 +102,7 @@ static int ray_init(struct net_device *dev); static int interrupt_ecf(ray_dev_t *local, int ccs); static void ray_reset(struct net_device *dev); static void ray_update_parm(struct net_device *dev, UCHAR objid, UCHAR *value, int len); -static void verify_dl_startup(u_long); +static void verify_dl_startup(struct timer_list *t); /* Prototypes for interrpt time functions **********************************/ static irqreturn_t ray_interrupt(int reg, void *dev_id); @@ -120,9 +120,8 @@ static void associate(ray_dev_t *local); /* Card command functions */ static int dl_startup_params(struct net_device *dev); -static void join_net(u_long local); -static void start_net(u_long local); -/* void start_net(ray_dev_t *local); */ +static void join_net(struct timer_list *t); +static void start_net(struct timer_list *t); /*===========================================================================*/ /* Parameters that can be set with 'insmod' */ @@ -323,7 +322,7 @@ static int ray_probe(struct pcmcia_device *p_dev) dev_dbg(&p_dev->dev, "ray_cs ray_attach calling ether_setup.)\n"); netif_stop_queue(dev); - init_timer(&local->timer); + timer_setup(&local->timer, NULL, 0); this_device = p_dev; return ray_config(p_dev); @@ -570,8 +569,7 @@ static int dl_startup_params(struct net_device *dev) local->card_status = CARD_DL_PARAM; /* Start kernel timer to wait for dl startup to complete. */ local->timer.expires = jiffies + HZ / 2; - local->timer.data = (long)local; - local->timer.function = verify_dl_startup; + local->timer.function = (TIMER_FUNC_TYPE)verify_dl_startup; add_timer(&local->timer); dev_dbg(&link->dev, "ray_cs dl_startup_params started timer for verify_dl_startup\n"); @@ -641,9 +639,9 @@ static void init_startup_params(ray_dev_t *local) } /* init_startup_params */ /*===========================================================================*/ -static void verify_dl_startup(u_long data) +static void verify_dl_startup(struct timer_list *t) { - ray_dev_t *local = (ray_dev_t *) data; + ray_dev_t *local = from_timer(local, t, timer); struct ccs __iomem *pccs = ccs_base(local) + local->dl_param_ccs; UCHAR status; struct pcmcia_device *link = local->finder; @@ -676,16 +674,16 @@ static void verify_dl_startup(u_long data) return; } if (local->sparm.b4.a_network_type == ADHOC) - start_net((u_long) local); + start_net(&local->timer); else - join_net((u_long) local); + join_net(&local->timer); } /* end verify_dl_startup */ /*===========================================================================*/ /* Command card to start a network */ -static void start_net(u_long data) +static void start_net(struct timer_list *t) { - ray_dev_t *local = (ray_dev_t *) data; + ray_dev_t *local = from_timer(local, t, timer); struct ccs __iomem *pccs; int ccsindex; struct pcmcia_device *link = local->finder; @@ -710,9 +708,9 @@ static void start_net(u_long data) /*===========================================================================*/ /* Command card to join a network */ -static void join_net(u_long data) +static void join_net(struct timer_list *t) { - ray_dev_t *local = (ray_dev_t *) data; + ray_dev_t *local = from_timer(local, t, timer); struct ccs __iomem *pccs; int ccsindex; @@ -1639,13 +1637,13 @@ static int get_free_ccs(ray_dev_t *local) } /* get_free_ccs */ /*===========================================================================*/ -static void authenticate_timeout(u_long data) +static void authenticate_timeout(struct timer_list *t) { - ray_dev_t *local = (ray_dev_t *) data; + ray_dev_t *local = from_timer(local, t, timer); del_timer(&local->timer); printk(KERN_INFO "ray_cs Authentication with access point failed" " - timeout\n"); - join_net((u_long) local); + join_net(&local->timer); } /*===========================================================================*/ @@ -1945,17 +1943,16 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id) del_timer(&local->timer); local->timer.expires = jiffies + HZ * 5; - local->timer.data = (long)local; if (status == CCS_START_NETWORK) { dev_dbg(&link->dev, "ray_cs interrupt network \"%s\" start failed\n", memtmp); - local->timer.function = start_net; + local->timer.function = (TIMER_FUNC_TYPE)start_net; } else { dev_dbg(&link->dev, "ray_cs interrupt network \"%s\" join failed\n", memtmp); - local->timer.function = join_net; + local->timer.function = (TIMER_FUNC_TYPE)join_net; } add_timer(&local->timer); } @@ -1967,7 +1964,7 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id) } else { dev_dbg(&link->dev, "ray_cs association failed,\n"); local->card_status = CARD_ASSOC_FAILED; - join_net((u_long) local); + join_net(&local->timer); } break; case CCS_TX_REQUEST: @@ -2420,12 +2417,11 @@ static void authenticate(ray_dev_t *local) del_timer(&local->timer); if (build_auth_frame(local, local->bss_id, OPEN_AUTH_REQUEST)) { - local->timer.function = join_net; + local->timer.function = (TIMER_FUNC_TYPE)join_net; } else { - local->timer.function = authenticate_timeout; + local->timer.function = (TIMER_FUNC_TYPE)authenticate_timeout; } local->timer.expires = jiffies + HZ * 2; - local->timer.data = (long)local; add_timer(&local->timer); local->authentication_state = AWAITING_RESPONSE; } /* end authenticate */ @@ -2468,7 +2464,7 @@ static void rx_authenticate(ray_dev_t *local, struct rcs __iomem *prcs, } else { pr_debug("Authentication refused\n"); local->card_status = CARD_AUTH_REFUSED; - join_net((u_long) local); + join_net(&local->timer); local->authentication_state = UNAUTHENTICATED; } @@ -2506,8 +2502,7 @@ static void associate(ray_dev_t *local) del_timer(&local->timer); local->timer.expires = jiffies + HZ * 2; - local->timer.data = (long)local; - local->timer.function = join_net; + local->timer.function = (TIMER_FUNC_TYPE)join_net; add_timer(&local->timer); local->card_status = CARD_ASSOC_FAILED; return; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c index 80fee699f58a..38b2ba1ac6f8 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c @@ -614,7 +614,10 @@ static int rtl8192eu_parse_efuse(struct rtl8xxxu_priv *priv) dev_info(&priv->udev->dev, "Vendor: %.7s\n", efuse->vendor_name); dev_info(&priv->udev->dev, "Product: %.11s\n", efuse->device_name); - dev_info(&priv->udev->dev, "Serial: %.11s\n", efuse->serial); + if (memchr_inv(efuse->serial, 0xff, 11)) + dev_info(&priv->udev->dev, "Serial: %.11s\n", efuse->serial); + else + dev_info(&priv->udev->dev, "Serial not available.\n"); if (rtl8xxxu_debug & RTL8XXXU_DEBUG_EFUSE) { unsigned char *raw = priv->efuse_wifi.raw; diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c index ea18aa7afecb..0b34886321f1 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.c +++ b/drivers/net/wireless/realtek/rtlwifi/base.c @@ -249,8 +249,6 @@ static void _rtl_init_hw_vht_capab(struct ieee80211_hw *hw, vht_cap->vht_supported = true; vht_cap->cap = - IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 | - IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 | IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 | IEEE80211_VHT_CAP_SHORT_GI_80 | IEEE80211_VHT_CAP_TXSTBC | @@ -283,8 +281,6 @@ static void _rtl_init_hw_vht_capab(struct ieee80211_hw *hw, vht_cap->vht_supported = true; vht_cap->cap = - IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 | - IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 | IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 | IEEE80211_VHT_CAP_SHORT_GI_80 | IEEE80211_VHT_CAP_TXSTBC | @@ -835,7 +831,7 @@ static u8 _rtl_get_vht_highest_n_rate(struct ieee80211_hw *hw, else if ((tx_mcs_map & 0x000c) >> 2 == IEEE80211_VHT_MCS_SUPPORT_0_8) hw_rate = - rtlpriv->cfg->maps[RTL_RC_VHT_RATE_2SS_MCS9]; + rtlpriv->cfg->maps[RTL_RC_VHT_RATE_2SS_MCS8]; else hw_rate = rtlpriv->cfg->maps[RTL_RC_VHT_RATE_2SS_MCS9]; @@ -847,7 +843,7 @@ static u8 _rtl_get_vht_highest_n_rate(struct ieee80211_hw *hw, else if ((tx_mcs_map & 0x0003) == IEEE80211_VHT_MCS_SUPPORT_0_8) hw_rate = - rtlpriv->cfg->maps[RTL_RC_VHT_RATE_1SS_MCS9]; + rtlpriv->cfg->maps[RTL_RC_VHT_RATE_1SS_MCS8]; else hw_rate = rtlpriv->cfg->maps[RTL_RC_VHT_RATE_1SS_MCS9]; @@ -1103,6 +1099,42 @@ int rtlwifi_rate_mapping(struct ieee80211_hw *hw, bool isht, bool isvht, } EXPORT_SYMBOL(rtlwifi_rate_mapping); +static u8 _rtl_get_tx_hw_rate(struct ieee80211_hw *hw, + struct ieee80211_tx_info *info) +{ + struct rtl_priv *rtlpriv = rtl_priv(hw); + struct ieee80211_tx_rate *r = &info->status.rates[0]; + struct ieee80211_rate *txrate; + u8 hw_value = 0x0; + + if (r->flags & IEEE80211_TX_RC_MCS) { + /* HT MCS0-15 */ + hw_value = rtlpriv->cfg->maps[RTL_RC_HT_RATEMCS15] - 15 + + r->idx; + } else if (r->flags & IEEE80211_TX_RC_VHT_MCS) { + /* VHT MCS0-9, NSS */ + if (ieee80211_rate_get_vht_nss(r) == 2) + hw_value = rtlpriv->cfg->maps[RTL_RC_VHT_RATE_2SS_MCS9]; + else + hw_value = rtlpriv->cfg->maps[RTL_RC_VHT_RATE_1SS_MCS9]; + + hw_value = hw_value - 9 + ieee80211_rate_get_vht_mcs(r); + } else { + /* legacy */ + txrate = ieee80211_get_tx_rate(hw, info); + + if (txrate) + hw_value = txrate->hw_value; + } + + /* check 5G band */ + if (rtlpriv->rtlhal.current_bandtype == BAND_ON_5G && + hw_value < rtlpriv->cfg->maps[RTL_RC_OFDM_RATE6M]) + hw_value = rtlpriv->cfg->maps[RTL_RC_OFDM_RATE6M]; + + return hw_value; +} + void rtl_get_tcb_desc(struct ieee80211_hw *hw, struct ieee80211_tx_info *info, struct ieee80211_sta *sta, @@ -1111,12 +1143,10 @@ void rtl_get_tcb_desc(struct ieee80211_hw *hw, struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_mac *rtlmac = rtl_mac(rtl_priv(hw)); struct ieee80211_hdr *hdr = rtl_get_hdr(skb); - struct ieee80211_rate *txrate; + __le16 fc = rtl_get_fc(skb); - txrate = ieee80211_get_tx_rate(hw, info); - if (txrate) - tcb_desc->hw_rate = txrate->hw_value; + tcb_desc->hw_rate = _rtl_get_tx_hw_rate(hw, info); if (rtl_is_tx_report_skb(hw, skb)) tcb_desc->use_spe_rpt = 1; @@ -1527,6 +1557,42 @@ void rtl_wait_tx_report_acked(struct ieee80211_hw *hw, u32 wait_ms) "Wait 1ms (%d/%d) to disable key.\n", i, wait_ms); } } + +u32 rtl_get_hal_edca_param(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + enum wireless_mode wirelessmode, + struct ieee80211_tx_queue_params *param) +{ + u32 reg = 0; + u8 sifstime = 10; + u8 slottime = 20; + + /* AIFS = AIFSN * slot time + SIFS */ + switch (wirelessmode) { + case WIRELESS_MODE_A: + case WIRELESS_MODE_N_24G: + case WIRELESS_MODE_N_5G: + case WIRELESS_MODE_AC_5G: + case WIRELESS_MODE_AC_24G: + sifstime = 16; + slottime = 9; + break; + case WIRELESS_MODE_G: + slottime = (vif->bss_conf.use_short_slot ? 9 : 20); + break; + default: + break; + } + + reg |= (param->txop & 0x7FF) << 16; + reg |= (fls(param->cw_max) & 0xF) << 12; + reg |= (fls(param->cw_min) & 0xF) << 8; + reg |= (param->aifs & 0x0F) * slottime + sifstime; + + return reg; +} +EXPORT_SYMBOL_GPL(rtl_get_hal_edca_param); + /********************************************************* * * functions called by core.c @@ -1932,6 +1998,22 @@ label_lps_done: rtlpriv->link_info.tx_busy_traffic = tx_busy_traffic; rtlpriv->link_info.higher_busyrxtraffic = higher_busyrxtraffic; + rtlpriv->stats.txbytesunicast_inperiod = + rtlpriv->stats.txbytesunicast - + rtlpriv->stats.txbytesunicast_last; + rtlpriv->stats.rxbytesunicast_inperiod = + rtlpriv->stats.rxbytesunicast - + rtlpriv->stats.rxbytesunicast_last; + rtlpriv->stats.txbytesunicast_last = rtlpriv->stats.txbytesunicast; + rtlpriv->stats.rxbytesunicast_last = rtlpriv->stats.rxbytesunicast; + + rtlpriv->stats.txbytesunicast_inperiod_tp = + (u32)(rtlpriv->stats.txbytesunicast_inperiod * 8 / 2 / + 1024 / 1024); + rtlpriv->stats.rxbytesunicast_inperiod_tp = + (u32)(rtlpriv->stats.rxbytesunicast_inperiod * 8 / 2 / + 1024 / 1024); + /* <3> DM */ if (!rtlpriv->cfg->mod_params->disable_watchdog) rtlpriv->cfg->ops->dm_watchdog(hw); @@ -2204,7 +2286,7 @@ int rtl_send_smps_action(struct ieee80211_hw *hw, struct rtl_sta_info *sta_entry = (struct rtl_sta_info *) sta->drv_priv; sta_entry->mimo_ps = smps; - /* rtlpriv->cfg->ops->update_rate_tbl(hw, sta, 0); */ + /* rtlpriv->cfg->ops->update_rate_tbl(hw, sta, 0, true); */ info->control.rates[0].idx = 0; info->band = hw->conf.chandef.chan->band; diff --git a/drivers/net/wireless/realtek/rtlwifi/base.h b/drivers/net/wireless/realtek/rtlwifi/base.h index b56d1b7f5567..cfea9fc39a9f 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.h +++ b/drivers/net/wireless/realtek/rtlwifi/base.h @@ -137,6 +137,10 @@ void rtl_tx_report_handler(struct ieee80211_hw *hw, u8 *tmp_buf, u8 c2h_cmd_len); bool rtl_check_tx_report_acked(struct ieee80211_hw *hw); void rtl_wait_tx_report_acked(struct ieee80211_hw *hw, u32 wait_ms); +u32 rtl_get_hal_edca_param(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + enum wireless_mode wirelessmode, + struct ieee80211_tx_queue_params *param); void rtl_beacon_statistic(struct ieee80211_hw *hw, struct sk_buff *skb); void rtl_collect_scan_list(struct ieee80211_hw *hw, struct sk_buff *skb); diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b1ant.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b1ant.c index c04425236ce4..5f726f6d3567 100644 --- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b1ant.c +++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b1ant.c @@ -2260,14 +2260,11 @@ static void halbtc8723b1ant_run_coexist_mechanism(struct btc_coexist *btcoexist) if (iot_peer != BTC_IOT_PEER_CISCO && iot_peer != BTC_IOT_PEER_BROADCOM) { - if (bt_link_info->sco_exist) - halbtc8723b1ant_limited_rx(btcoexist, - NORMAL_EXEC, false, - false, 0x5); - else - halbtc8723b1ant_limited_rx(btcoexist, - NORMAL_EXEC, false, - false, 0x5); + bool sco_exist = bt_link_info->sco_exist; + + halbtc8723b1ant_limited_rx(btcoexist, + NORMAL_EXEC, sco_exist, + false, 0x5); } else { if (bt_link_info->sco_exist) { halbtc8723b1ant_limited_rx(btcoexist, diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c index c53cbf3d52bd..015a8ec36703 100644 --- a/drivers/net/wireless/realtek/rtlwifi/core.c +++ b/drivers/net/wireless/realtek/rtlwifi/core.c @@ -453,7 +453,8 @@ static void _rtl_add_wowlan_patterns(struct ieee80211_hw *hw, for (i = 0; i < wow->n_patterns; i++) { memset(&rtl_pattern, 0, sizeof(struct rtl_wow_pattern)); memset(mask, 0, MAX_WOL_BIT_MASK_SIZE); - if (patterns[i].pattern_len > MAX_WOL_PATTERN_SIZE) { + if (patterns[i].pattern_len < 0 || + patterns[i].pattern_len > MAX_WOL_PATTERN_SIZE) { RT_TRACE(rtlpriv, COMP_POWER, DBG_WARNING, "Pattern[%d] is too long\n", i); continue; @@ -945,7 +946,7 @@ static int rtl_op_sta_add(struct ieee80211_hw *hw, memcpy(sta_entry->mac_addr, sta->addr, ETH_ALEN); RT_TRACE(rtlpriv, COMP_MAC80211, DBG_DMESG, "Add sta addr is %pM\n", sta->addr); - rtlpriv->cfg->ops->update_rate_tbl(hw, sta, 0); + rtlpriv->cfg->ops->update_rate_tbl(hw, sta, 0, true); } return 0; @@ -1151,7 +1152,8 @@ static void rtl_op_bss_info_changed(struct ieee80211_hw *hw, } if (vif->type == NL80211_IFTYPE_STATION) - rtlpriv->cfg->ops->update_rate_tbl(hw, sta, 0); + rtlpriv->cfg->ops->update_rate_tbl(hw, sta, 0, + true); rcu_read_unlock(); /* to avoid AP Disassociation caused by inactivity */ diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c index 08dc8919ef60..b9a6d23364be 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.c +++ b/drivers/net/wireless/realtek/rtlwifi/pci.c @@ -586,7 +586,7 @@ static void _rtl_pci_tx_isr(struct ieee80211_hw *hw, int prio) skb = __skb_dequeue(&ring->queue); pci_unmap_single(rtlpci->pdev, rtlpriv->cfg->ops-> - get_desc((u8 *)entry, true, + get_desc(hw, (u8 *)entry, true, HW_DESC_TXBUFF_ADDR), skb->len, PCI_DMA_TODEVICE); @@ -691,9 +691,10 @@ remap: return 0; rtlpci->rx_ring[rxring_idx].rx_buf[desc_idx] = skb; if (rtlpriv->use_new_trx_flow) { + /* skb->cb may be 64 bit address */ rtlpriv->cfg->ops->set_desc(hw, (u8 *)entry, false, HW_DESC_RX_PREPARE, - (u8 *)&bufferaddress); + (u8 *)(dma_addr_t *)skb->cb); } else { rtlpriv->cfg->ops->set_desc(hw, (u8 *)entry, false, HW_DESC_RXBUFF_ADDR, @@ -798,7 +799,7 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw) pdesc = &rtlpci->rx_ring[rxring_idx].desc[ rtlpci->rx_ring[rxring_idx].idx]; - own = (u8)rtlpriv->cfg->ops->get_desc((u8 *)pdesc, + own = (u8)rtlpriv->cfg->ops->get_desc(hw, (u8 *)pdesc, false, HW_DESC_OWN); if (own) /* wait data to be filled by hardware */ @@ -825,7 +826,7 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw) (u8 *)buffer_desc, hw_queue); - len = rtlpriv->cfg->ops->get_desc((u8 *)pdesc, false, + len = rtlpriv->cfg->ops->get_desc(hw, (u8 *)pdesc, false, HW_DESC_RXPKT_LEN); if (skb->end - skb->tail > len) { @@ -1122,7 +1123,7 @@ static void _rtl_pci_prepare_bcn_tasklet(struct ieee80211_hw *hw) if (pskb) { pci_unmap_single(rtlpci->pdev, rtlpriv->cfg->ops->get_desc( - (u8 *)entry, true, HW_DESC_TXBUFF_ADDR), + hw, (u8 *)entry, true, HW_DESC_TXBUFF_ADDR), pskb->len, PCI_DMA_TODEVICE); kfree_skb(pskb); } @@ -1378,7 +1379,8 @@ static void _rtl_pci_free_tx_ring(struct ieee80211_hw *hw, pci_unmap_single(rtlpci->pdev, rtlpriv->cfg-> - ops->get_desc((u8 *)entry, true, + ops->get_desc(hw, (u8 *)entry, + true, HW_DESC_TXBUFF_ADDR), skb->len, PCI_DMA_TODEVICE); kfree_skb(skb); @@ -1507,7 +1509,7 @@ int rtl_pci_reset_trx_ring(struct ieee80211_hw *hw) for (i = 0; i < rtlpci->rxringcount; i++) { entry = &rtlpci->rx_ring[rxring_idx].desc[i]; bufferaddress = - rtlpriv->cfg->ops->get_desc((u8 *)entry, + rtlpriv->cfg->ops->get_desc(hw, (u8 *)entry, false , HW_DESC_RXBUFF_ADDR); memset((u8 *)entry , 0 , sizeof(*rtlpci->rx_ring @@ -1560,7 +1562,7 @@ int rtl_pci_reset_trx_ring(struct ieee80211_hw *hw) pci_unmap_single(rtlpci->pdev, rtlpriv->cfg->ops-> - get_desc((u8 *) + get_desc(hw, (u8 *) entry, true, HW_DESC_TXBUFF_ADDR), @@ -1673,7 +1675,7 @@ static int rtl_pci_tx(struct ieee80211_hw *hw, if (rtlpriv->use_new_trx_flow) { ptx_bd_desc = &ring->buffer_desc[idx]; } else { - own = (u8) rtlpriv->cfg->ops->get_desc((u8 *)pdesc, + own = (u8)rtlpriv->cfg->ops->get_desc(hw, (u8 *)pdesc, true, HW_DESC_OWN); if ((own == 1) && (hw_queue != BEACON_QUEUE)) { @@ -2163,6 +2165,21 @@ static int rtl_pci_intr_mode_decide(struct ieee80211_hw *hw) return ret; } +static void platform_enable_dma64(struct pci_dev *pdev, bool dma64) +{ + u8 value; + + pci_read_config_byte(pdev, 0x719, &value); + + /* 0x719 Bit5 is DMA64 bit fetch. */ + if (dma64) + value |= BIT(5); + else + value &= ~BIT(5); + + pci_write_config_byte(pdev, 0x719, value); +} + int rtl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { @@ -2181,13 +2198,25 @@ int rtl_pci_probe(struct pci_dev *pdev, return err; } - if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) { + if (((struct rtl_hal_cfg *)id->driver_data)->mod_params->dma64 && + !pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) { + if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) { + WARN_ONCE(true, + "Unable to obtain 64bit DMA for consistent allocations\n"); + err = -ENOMEM; + goto fail1; + } + + platform_enable_dma64(pdev, true); + } else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) { if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32))) { WARN_ONCE(true, "rtlwifi: Unable to obtain 32bit DMA for consistent allocations\n"); err = -ENOMEM; goto fail1; } + + platform_enable_dma64(pdev, false); } pci_set_master(pdev); diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.h b/drivers/net/wireless/realtek/rtlwifi/pci.h index d9039ea10ba4..1af92b34979d 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.h +++ b/drivers/net/wireless/realtek/rtlwifi/pci.h @@ -143,13 +143,7 @@ struct rtl_pci_capabilities_header { * RX wifi info == RX descriptor in old flow */ struct rtl_tx_buffer_desc { -#if (RTL8192EE_SEG_NUM == 2) - u32 dword[2*(DMA_IS_64BIT + 1)*8]; /*seg = 8*/ -#elif (RTL8192EE_SEG_NUM == 1) - u32 dword[2*(DMA_IS_64BIT + 1)*4]; /*seg = 4*/ -#elif (RTL8192EE_SEG_NUM == 0) - u32 dword[2*(DMA_IS_64BIT + 1)*2]; /*seg = 2*/ -#endif + u32 dword[4 * (1 << (BUFDESC_SEG_NUM + 1))]; } __packed; struct rtl_tx_desc { @@ -157,7 +151,7 @@ struct rtl_tx_desc { } __packed; struct rtl_rx_buffer_desc { /*rx buffer desc*/ - u32 dword[2]; + u32 dword[4]; } __packed; struct rtl_rx_desc { /*old: rx desc new: rx wifi info*/ diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/dm.c index f936a491371b..207411d1b015 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/dm.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/dm.c @@ -1221,7 +1221,8 @@ static void rtl88e_dm_refresh_rate_adaptive_mask(struct ieee80211_hw *hw) sta = rtl_find_sta(hw, mac->bssid); if (sta) rtlpriv->cfg->ops->update_rate_tbl(hw, sta, - p_ra->ratr_state); + p_ra->ratr_state, + true); rcu_read_unlock(); p_ra->pre_ratr_state = p_ra->ratr_state; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c index 0ba26d27d11c..d31117d52381 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c @@ -99,6 +99,7 @@ static void _rtl88ee_return_beacon_queue_skb(struct ieee80211_hw *hw) pci_unmap_single(rtlpci->pdev, rtlpriv->cfg->ops->get_desc( + hw, (u8 *)entry, true, HW_DESC_TXBUFF_ADDR), skb->len, PCI_DMA_TODEVICE); kfree_skb(skb); @@ -2076,7 +2077,7 @@ static void rtl88ee_update_hal_rate_table(struct ieee80211_hw *hw, } static void rtl88ee_update_hal_rate_mask(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level) + struct ieee80211_sta *sta, u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_phy *rtlphy = &(rtlpriv->phy); @@ -2207,12 +2208,12 @@ static void rtl88ee_update_hal_rate_mask(struct ieee80211_hw *hw, } void rtl88ee_update_hal_rate_tbl(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level) + struct ieee80211_sta *sta, u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); if (rtlpriv->dm.useramask) - rtl88ee_update_hal_rate_mask(hw, sta, rssi_level); + rtl88ee_update_hal_rate_mask(hw, sta, rssi_level, update_bw); else rtl88ee_update_hal_rate_table(hw, sta); } @@ -2235,7 +2236,7 @@ bool rtl88ee_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw)); - enum rf_pwrstate e_rfpowerstate_toset, cur_rfstate; + enum rf_pwrstate e_rfpowerstate_toset; u32 u4tmp; bool b_actuallyset = false; @@ -2254,8 +2255,6 @@ bool rtl88ee_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid) spin_unlock(&rtlpriv->locks.rf_ps_lock); } - cur_rfstate = ppsc->rfpwr_state; - u4tmp = rtl_read_dword(rtlpriv, REG_GPIO_OUTPUT); e_rfpowerstate_toset = (u4tmp & BIT(31)) ? ERFON : ERFOFF; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.h index d38dbca3c19e..719b78a3b7db 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.h @@ -43,7 +43,8 @@ void rtl88ee_update_interrupt_mask(struct ieee80211_hw *hw, u32 add_msr, u32 rm_msr); void rtl88ee_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val); void rtl88ee_update_hal_rate_tbl(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level); + struct ieee80211_sta *sta, u8 rssi_level, + bool update_bw); void rtl88ee_update_channel_access_setting(struct ieee80211_hw *hw); bool rtl88ee_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid); void rtl88ee_enable_hw_security_config(struct ieee80211_hw *hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c index 57e5d5c1d24b..35de3aeafcc9 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c @@ -41,6 +41,7 @@ static void rtl88e_init_aspm_vars(struct ieee80211_hw *hw) { + struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); /*close ASPM for AMD defaultly */ @@ -77,7 +78,7 @@ static void rtl88e_init_aspm_vars(struct ieee80211_hw *hw) * 1 - Support ASPM, * 2 - According to chipset. */ - rtlpci->const_support_pciaspm = 1; + rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support; } int rtl88e_init_sw_vars(struct ieee80211_hw *hw) @@ -276,6 +277,7 @@ static struct rtl_mod_params rtl88ee_mod_params = { .swctrl_lps = false, .fwctrl_lps = false, .msi_support = true, + .aspm_support = 1, .debug_level = 0, .debug_mask = 0, }; @@ -399,6 +401,7 @@ module_param_named(ips, rtl88ee_mod_params.inactiveps, bool, 0444); module_param_named(swlps, rtl88ee_mod_params.swctrl_lps, bool, 0444); module_param_named(fwlps, rtl88ee_mod_params.fwctrl_lps, bool, 0444); module_param_named(msi, rtl88ee_mod_params.msi_support, bool, 0444); +module_param_named(aspm, rtl88ee_mod_params.aspm_support, int, 0444); module_param_named(disable_watchdog, rtl88ee_mod_params.disable_watchdog, bool, 0444); MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n"); @@ -406,6 +409,7 @@ MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n"); MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n"); MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n"); MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 1)\n"); +MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n"); MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)"); MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)"); MODULE_PARM_DESC(disable_watchdog, "Set to 1 to disable the watchdog (default 0)\n"); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c index dd3e12b74447..9670732b2bc6 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c @@ -786,7 +786,8 @@ void rtl88ee_set_desc(struct ieee80211_hw *hw, u8 *pdesc, } } -u32 rtl88ee_get_desc(u8 *pdesc, bool istx, u8 desc_name) +u64 rtl88ee_get_desc(struct ieee80211_hw *hw, + u8 *pdesc, bool istx, u8 desc_name) { u32 ret = 0; @@ -828,7 +829,7 @@ bool rtl88ee_is_tx_desc_closed(struct ieee80211_hw *hw, u8 hw_queue, u16 index) struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue]; u8 *entry = (u8 *)(&ring->desc[ring->idx]); - u8 own = (u8)rtl88ee_get_desc(entry, true, HW_DESC_OWN); + u8 own = (u8)rtl88ee_get_desc(hw, entry, true, HW_DESC_OWN); /*beacon packet will only use the first *descriptor defautly,and the own may not diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.h index 9a1c2087adee..f902d6769aa8 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.h @@ -782,7 +782,8 @@ bool rtl88ee_rx_query_desc(struct ieee80211_hw *hw, u8 *pdesc, struct sk_buff *skb); void rtl88ee_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, u8 desc_name, u8 *val); -u32 rtl88ee_get_desc(u8 *pdesc, bool istx, u8 desc_name); +u64 rtl88ee_get_desc(struct ieee80211_hw *hw, + u8 *pdesc, bool istx, u8 desc_name); bool rtl88ee_is_tx_desc_closed(struct ieee80211_hw *hw, u8 hw_queue, u16 index); void rtl88ee_tx_polling(struct ieee80211_hw *hw, u8 hw_queue); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c index 9956026bae0a..9310fad69cd9 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c @@ -1865,7 +1865,7 @@ static void rtl92ce_update_hal_rate_table(struct ieee80211_hw *hw, } static void rtl92ce_update_hal_rate_mask(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level) + struct ieee80211_sta *sta, u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_phy *rtlphy = &(rtlpriv->phy); @@ -1995,12 +1995,12 @@ static void rtl92ce_update_hal_rate_mask(struct ieee80211_hw *hw, } void rtl92ce_update_hal_rate_tbl(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level) + struct ieee80211_sta *sta, u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); if (rtlpriv->dm.useramask) - rtl92ce_update_hal_rate_mask(hw, sta, rssi_level); + rtl92ce_update_hal_rate_mask(hw, sta, rssi_level, update_bw); else rtl92ce_update_hal_rate_table(hw, sta); } diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.h index 877f138a0cb9..7683c5dfe851 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.h @@ -56,9 +56,8 @@ void rtl92ce_update_interrupt_mask(struct ieee80211_hw *hw, u32 add_msr, u32 rm_msr); void rtl92ce_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val); void rtl92ce_update_hal_rate_tbl(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level); -void rtl92ce_update_hal_rate_tbl(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level); + struct ieee80211_sta *sta, u8 rssi_level, + bool update_bw); void rtl92ce_update_channel_access_setting(struct ieee80211_hw *hw); bool rtl92ce_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid); void rtl92ce_enable_hw_security_config(struct ieee80211_hw *hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c index 38f85bfdf0c7..71a6761d3648 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c @@ -44,6 +44,7 @@ static void rtl92c_init_aspm_vars(struct ieee80211_hw *hw) { + struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); /*close ASPM for AMD defaultly */ @@ -83,7 +84,7 @@ static void rtl92c_init_aspm_vars(struct ieee80211_hw *hw) * 1 - Support ASPM, * 2 - According to chipset. */ - rtlpci->const_support_pciaspm = 1; + rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support; } int rtl92c_init_sw_vars(struct ieee80211_hw *hw) @@ -252,6 +253,7 @@ static struct rtl_mod_params rtl92ce_mod_params = { .inactiveps = true, .swctrl_lps = false, .fwctrl_lps = true, + .aspm_support = 1, .debug_level = 0, .debug_mask = 0, }; @@ -375,10 +377,12 @@ module_param_named(debug_mask, rtl92ce_mod_params.debug_mask, ullong, 0644); module_param_named(ips, rtl92ce_mod_params.inactiveps, bool, 0444); module_param_named(swlps, rtl92ce_mod_params.swctrl_lps, bool, 0444); module_param_named(fwlps, rtl92ce_mod_params.fwctrl_lps, bool, 0444); +module_param_named(aspm, rtl92ce_mod_params.aspm_support, int, 0444); MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n"); MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n"); MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n"); MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n"); +MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n"); MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)"); MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)"); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.c index 94a4b39437cd..d36e0060cc7a 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.c @@ -697,7 +697,8 @@ void rtl92ce_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, } } -u32 rtl92ce_get_desc(u8 *p_desc, bool istx, u8 desc_name) +u64 rtl92ce_get_desc(struct ieee80211_hw *hw, u8 *p_desc, + bool istx, u8 desc_name) { u32 ret = 0; @@ -740,7 +741,7 @@ bool rtl92ce_is_tx_desc_closed(struct ieee80211_hw *hw, struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue]; u8 *entry = (u8 *)(&ring->desc[ring->idx]); - u8 own = (u8)rtl92ce_get_desc(entry, true, HW_DESC_OWN); + u8 own = (u8)rtl92ce_get_desc(hw, entry, true, HW_DESC_OWN); /*beacon packet will only use the first *descriptor defautly,and the own may not diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.h index 66291fc341e7..91f0bd6b752f 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/trx.h @@ -718,7 +718,8 @@ bool rtl92ce_rx_query_desc(struct ieee80211_hw *hw, u8 *pdesc, struct sk_buff *skb); void rtl92ce_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, u8 desc_name, u8 *val); -u32 rtl92ce_get_desc(u8 *pdesc, bool istx, u8 desc_name); +u64 rtl92ce_get_desc(struct ieee80211_hw *hw, u8 *p_desc, + bool istx, u8 desc_name); bool rtl92ce_is_tx_desc_closed(struct ieee80211_hw *hw, u8 hw_queue, u16 index); void rtl92ce_tx_polling(struct ieee80211_hw *hw, u8 hw_queue); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c index 530e80f0ef0b..1e60f70481f5 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c @@ -2006,7 +2006,7 @@ static void rtl92cu_update_hal_rate_table(struct ieee80211_hw *hw, static void rtl92cu_update_hal_rate_mask(struct ieee80211_hw *hw, struct ieee80211_sta *sta, - u8 rssi_level) + u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_phy *rtlphy = &(rtlpriv->phy); @@ -2153,12 +2153,12 @@ static void rtl92cu_update_hal_rate_mask(struct ieee80211_hw *hw, void rtl92cu_update_hal_rate_tbl(struct ieee80211_hw *hw, struct ieee80211_sta *sta, - u8 rssi_level) + u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); if (rtlpriv->dm.useramask) - rtl92cu_update_hal_rate_mask(hw, sta, rssi_level); + rtl92cu_update_hal_rate_mask(hw, sta, rssi_level, update_bw); else rtl92cu_update_hal_rate_table(hw, sta); } diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.h index 932f056f7ef8..ebd168400d45 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.h @@ -104,6 +104,6 @@ void rtl92c_fill_h2c_cmd(struct ieee80211_hw *hw, bool rtl92cu_phy_mac_config(struct ieee80211_hw *hw); void rtl92cu_update_hal_rate_tbl(struct ieee80211_hw *hw, struct ieee80211_sta *sta, - u8 rssi_level); + u8 rssi_level, bool update_bw); #endif diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c index f4129cf96e7c..85cedd083d2b 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/fw.c @@ -490,7 +490,7 @@ static bool _rtl92d_cmd_send_packet(struct ieee80211_hw *hw, spin_lock_irqsave(&rtlpriv->locks.irq_th_lock, flags); pdesc = &ring->desc[idx]; /* discard output from call below */ - rtlpriv->cfg->ops->get_desc((u8 *) pdesc, true, HW_DESC_OWN); + rtlpriv->cfg->ops->get_desc(hw, (u8 *)pdesc, true, HW_DESC_OWN); rtlpriv->cfg->ops->fill_tx_cmddesc(hw, (u8 *) pdesc, 1, 1, skb); __skb_queue_tail(&ring->queue, skb); spin_unlock_irqrestore(&rtlpriv->locks.irq_th_lock, flags); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c index cf28d25c551f..5a67f85fa165 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c @@ -1897,7 +1897,7 @@ static void rtl92de_update_hal_rate_table(struct ieee80211_hw *hw, } static void rtl92de_update_hal_rate_mask(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level) + struct ieee80211_sta *sta, u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_phy *rtlphy = &(rtlpriv->phy); @@ -2033,12 +2033,12 @@ static void rtl92de_update_hal_rate_mask(struct ieee80211_hw *hw, } void rtl92de_update_hal_rate_tbl(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level) + struct ieee80211_sta *sta, u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); if (rtlpriv->dm.useramask) - rtl92de_update_hal_rate_mask(hw, sta, rssi_level); + rtl92de_update_hal_rate_mask(hw, sta, rssi_level, update_bw); else rtl92de_update_hal_rate_table(hw, sta); } diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.h index 24b03b9999be..85c565b86ae3 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.h @@ -43,7 +43,8 @@ void rtl92de_update_interrupt_mask(struct ieee80211_hw *hw, u32 add_msr, u32 rm_msr); void rtl92de_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val); void rtl92de_update_hal_rate_tbl(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level); + struct ieee80211_sta *sta, u8 rssi_level, + bool update_bw); void rtl92de_update_channel_access_setting(struct ieee80211_hw *hw); bool rtl92de_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid); void rtl92de_enable_hw_security_config(struct ieee80211_hw *hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c index a6549f5f6c59..d5ba2bace79b 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c @@ -40,6 +40,7 @@ static void rtl92d_init_aspm_vars(struct ieee80211_hw *hw) { + struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); /*close ASPM for AMD defaultly */ @@ -79,7 +80,7 @@ static void rtl92d_init_aspm_vars(struct ieee80211_hw *hw) * 1 - Support ASPM, * 2 - According to chipset. */ - rtlpci->const_support_pciaspm = 1; + rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support; } static int rtl92d_init_sw_vars(struct ieee80211_hw *hw) @@ -254,6 +255,7 @@ static struct rtl_mod_params rtl92de_mod_params = { .inactiveps = true, .swctrl_lps = true, .fwctrl_lps = false, + .aspm_support = 1, .debug_level = 0, .debug_mask = 0, }; @@ -369,11 +371,13 @@ module_param_named(debug_level, rtl92de_mod_params.debug_level, int, 0644); module_param_named(ips, rtl92de_mod_params.inactiveps, bool, 0444); module_param_named(swlps, rtl92de_mod_params.swctrl_lps, bool, 0444); module_param_named(fwlps, rtl92de_mod_params.fwctrl_lps, bool, 0444); +module_param_named(aspm, rtl92de_mod_params.aspm_support, int, 0444); module_param_named(debug_mask, rtl92de_mod_params.debug_mask, ullong, 0644); MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n"); MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n"); MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 1)\n"); MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 0)\n"); +MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n"); MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)"); MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)"); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c index 86019f654428..d7b023cf7400 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c @@ -821,7 +821,8 @@ void rtl92de_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, } } -u32 rtl92de_get_desc(u8 *p_desc, bool istx, u8 desc_name) +u64 rtl92de_get_desc(struct ieee80211_hw *hw, + u8 *p_desc, bool istx, u8 desc_name) { u32 ret = 0; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h index 9bb6cc648590..f7f776539438 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h @@ -735,7 +735,8 @@ bool rtl92de_rx_query_desc(struct ieee80211_hw *hw, u8 *pdesc, struct sk_buff *skb); void rtl92de_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, u8 desc_name, u8 *val); -u32 rtl92de_get_desc(u8 *pdesc, bool istx, u8 desc_name); +u64 rtl92de_get_desc(struct ieee80211_hw *hw, + u8 *p_desc, bool istx, u8 desc_name); void rtl92de_tx_polling(struct ieee80211_hw *hw, u8 hw_queue); void rtl92de_tx_fill_cmddesc(struct ieee80211_hw *hw, u8 *pdesc, bool b_firstseg, bool b_lastseg, diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c index e6b5786c7d4a..faed6e2dedf6 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c @@ -1039,7 +1039,8 @@ static void rtl92ee_dm_refresh_rate_adaptive_mask(struct ieee80211_hw *hw) sta = rtl_find_sta(hw, mac->bssid); if (sta) rtlpriv->cfg->ops->update_rate_tbl(hw, sta, - p_ra->ratr_state); + p_ra->ratr_state, + true); rcu_read_unlock(); p_ra->pre_ratr_state = p_ra->ratr_state; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.c index 7eae27f8e173..f9563ae301ad 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/fw.c @@ -682,7 +682,7 @@ void rtl92ee_set_fw_rsvdpagepkt(struct ieee80211_hw *hw, bool b_dl_finished) struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_mac *mac = rtl_mac(rtl_priv(hw)); struct sk_buff *skb = NULL; - + bool rtstatus; u32 totalpacketlen; u8 u1rsvdpageloc[5] = { 0 }; bool b_dlok = false; @@ -768,7 +768,9 @@ void rtl92ee_set_fw_rsvdpagepkt(struct ieee80211_hw *hw, bool b_dl_finished) skb = dev_alloc_skb(totalpacketlen); skb_put_data(skb, &reserved_page_packet, totalpacketlen); - b_dlok = true; + rtstatus = rtl_cmd_send_packet(hw, skb); + if (rtstatus) + b_dlok = true; if (b_dlok) { RT_TRACE(rtlpriv, COMP_POWER, DBG_LOUD , diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c index ef9394be7016..6fc3090c4b72 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c @@ -840,6 +840,31 @@ static bool _rtl92ee_init_mac(struct ieee80211_hw *hw) /* Set TCR register */ rtl_write_dword(rtlpriv, REG_TCR, rtlpci->transmit_config); + /* Set TX/RX descriptor physical address -- HI part */ + if (!rtlpriv->cfg->mod_params->dma64) + goto dma64_end; + + rtl_write_dword(rtlpriv, REG_BCNQ_DESA + 4, + ((u64)rtlpci->tx_ring[BEACON_QUEUE].buffer_desc_dma) >> + 32); + rtl_write_dword(rtlpriv, REG_MGQ_DESA + 4, + (u64)rtlpci->tx_ring[MGNT_QUEUE].buffer_desc_dma >> 32); + rtl_write_dword(rtlpriv, REG_VOQ_DESA + 4, + (u64)rtlpci->tx_ring[VO_QUEUE].buffer_desc_dma >> 32); + rtl_write_dword(rtlpriv, REG_VIQ_DESA + 4, + (u64)rtlpci->tx_ring[VI_QUEUE].buffer_desc_dma >> 32); + rtl_write_dword(rtlpriv, REG_BEQ_DESA + 4, + (u64)rtlpci->tx_ring[BE_QUEUE].buffer_desc_dma >> 32); + rtl_write_dword(rtlpriv, REG_BKQ_DESA + 4, + (u64)rtlpci->tx_ring[BK_QUEUE].buffer_desc_dma >> 32); + rtl_write_dword(rtlpriv, REG_HQ0_DESA + 4, + (u64)rtlpci->tx_ring[HIGH_QUEUE].buffer_desc_dma >> 32); + + rtl_write_dword(rtlpriv, REG_RX_DESA + 4, + (u64)rtlpci->rx_ring[RX_MPDU_QUEUE].dma >> 32); + +dma64_end: + /* Set TX/RX descriptor physical address(from OS API). */ rtl_write_dword(rtlpriv, REG_BCNQ_DESA, ((u64)rtlpci->tx_ring[BEACON_QUEUE].buffer_desc_dma) & @@ -913,15 +938,9 @@ static bool _rtl92ee_init_mac(struct ieee80211_hw *hw) rtl_write_word(rtlpriv, REG_HI7Q_TXBD_NUM, TX_DESC_NUM_92E | ((RTL8192EE_SEG_NUM << 12) & 0x3000)); /*Rx*/ -#if (DMA_IS_64BIT == 1) rtl_write_word(rtlpriv, REG_RX_RXBD_NUM, RX_DESC_NUM_92E | ((RTL8192EE_SEG_NUM << 13) & 0x6000) | 0x8000); -#else - rtl_write_word(rtlpriv, REG_RX_RXBD_NUM, - RX_DESC_NUM_92E | - ((RTL8192EE_SEG_NUM << 13) & 0x6000) | 0x0000); -#endif rtl_write_dword(rtlpriv, REG_TSFTIMER_HCI, 0XFFFFFFFF); @@ -2251,7 +2270,7 @@ static u8 _rtl92ee_mrate_idx_to_arfr_id(struct ieee80211_hw *hw, u8 rate_index) static void rtl92ee_update_hal_rate_mask(struct ieee80211_hw *hw, struct ieee80211_sta *sta, - u8 rssi_level) + u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_phy *rtlphy = &rtlpriv->phy; @@ -2370,7 +2389,7 @@ static void rtl92ee_update_hal_rate_mask(struct ieee80211_hw *hw, (ratr_index << 28); rate_mask[0] = macid; rate_mask[1] = ratr_index | (b_shortgi ? 0x80 : 0x00); - rate_mask[2] = curtxbw_40mhz; + rate_mask[2] = curtxbw_40mhz | ((!update_bw) << 3); rate_mask[3] = (u8)(ratr_bitmap & 0x000000ff); rate_mask[4] = (u8)((ratr_bitmap & 0x0000ff00) >> 8); rate_mask[5] = (u8)((ratr_bitmap & 0x00ff0000) >> 16); @@ -2385,12 +2404,13 @@ static void rtl92ee_update_hal_rate_mask(struct ieee80211_hw *hw, } void rtl92ee_update_hal_rate_tbl(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level) + struct ieee80211_sta *sta, u8 rssi_level, + bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); if (rtlpriv->dm.useramask) - rtl92ee_update_hal_rate_mask(hw, sta, rssi_level); + rtl92ee_update_hal_rate_mask(hw, sta, rssi_level, update_bw); } void rtl92ee_update_channel_access_setting(struct ieee80211_hw *hw) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.h index 05413f189685..cd6aeb44b996 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.h @@ -43,7 +43,8 @@ void rtl92ee_update_interrupt_mask(struct ieee80211_hw *hw, u32 add_msr, u32 rm_msr); void rtl92ee_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val); void rtl92ee_update_hal_rate_tbl(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level); + struct ieee80211_sta *sta, u8 rssi_level, + bool update_bw); void rtl92ee_update_channel_access_setting(struct ieee80211_hw *hw); bool rtl92ee_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid); void rtl92ee_enable_hw_security_config(struct ieee80211_hw *hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c index a3490080d066..ef92a789871d 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c @@ -44,6 +44,7 @@ static void rtl92ee_init_aspm_vars(struct ieee80211_hw *hw) { + struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); /*close ASPM for AMD defaultly */ @@ -83,7 +84,7 @@ static void rtl92ee_init_aspm_vars(struct ieee80211_hw *hw) * 1 - Support ASPM, * 2 - According to chipset. */ - rtlpci->const_support_pciaspm = 1; + rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support; } int rtl92ee_init_sw_vars(struct ieee80211_hw *hw) @@ -259,6 +260,8 @@ static struct rtl_mod_params rtl92ee_mod_params = { .swctrl_lps = false, .fwctrl_lps = true, .msi_support = true, + .dma64 = false, + .aspm_support = 1, .debug_level = 0, .debug_mask = 0, }; @@ -376,6 +379,8 @@ module_param_named(ips, rtl92ee_mod_params.inactiveps, bool, 0444); module_param_named(swlps, rtl92ee_mod_params.swctrl_lps, bool, 0444); module_param_named(fwlps, rtl92ee_mod_params.fwctrl_lps, bool, 0444); module_param_named(msi, rtl92ee_mod_params.msi_support, bool, 0444); +module_param_named(dma64, rtl92ee_mod_params.dma64, bool, 0444); +module_param_named(aspm, rtl92ee_mod_params.aspm_support, int, 0444); module_param_named(disable_watchdog, rtl92ee_mod_params.disable_watchdog, bool, 0444); MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n"); @@ -383,6 +388,8 @@ MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n"); MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n"); MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n"); MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 1)\n"); +MODULE_PARM_DESC(dma64, "Set to 1 to use DMA 64 (default 0)\n"); +MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n"); MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)"); MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)"); MODULE_PARM_DESC(disable_watchdog, "Set to 1 to disable the watchdog (default 0)\n"); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.c index c58393eab6a1..12255682e890 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.c @@ -581,13 +581,9 @@ void rtl92ee_pre_fill_tx_bd_desc(struct ieee80211_hw *hw, u8 i = 0; u16 real_desc_size = 0x28; u16 append_early_mode_size = 0; -#if (RTL8192EE_SEG_NUM == 0) - u8 segmentnum = 2; -#elif (RTL8192EE_SEG_NUM == 1) - u8 segmentnum = 4; -#elif (RTL8192EE_SEG_NUM == 2) - u8 segmentnum = 8; -#endif + u8 segmentnum = 1 << (RTL8192EE_SEG_NUM + 1); + dma_addr_t desc_dma_addr; + bool dma64 = rtlpriv->cfg->mod_params->dma64; tx_page_size = 2; current_bd_desc = rtlpci->tx_ring[queue_index].cur_tx_wp; @@ -609,6 +605,10 @@ void rtl92ee_pre_fill_tx_bd_desc(struct ieee80211_hw *hw, psblen += 1; } + /* tx desc addr */ + desc_dma_addr = rtlpci->tx_ring[queue_index].dma + + (current_bd_desc * TX_DESC_SIZE); + /* Reset */ SET_TX_BUFF_DESC_LEN_0(tx_bd_desc, 0); SET_TX_BUFF_DESC_PSB(tx_bd_desc, 0); @@ -618,17 +618,9 @@ void rtl92ee_pre_fill_tx_bd_desc(struct ieee80211_hw *hw, SET_TXBUFFER_DESC_LEN_WITH_OFFSET(tx_bd_desc, i, 0); SET_TXBUFFER_DESC_AMSDU_WITH_OFFSET(tx_bd_desc, i, 0); SET_TXBUFFER_DESC_ADD_LOW_WITH_OFFSET(tx_bd_desc, i, 0); -#if (DMA_IS_64BIT == 1) - SET_TXBUFFER_DESC_ADD_HIGT_WITH_OFFSET(tx_bd_desc, i, 0); -#endif + SET_TXBUFFER_DESC_ADD_HIGH_WITH_OFFSET(tx_bd_desc, i, 0, dma64); } - SET_TX_BUFF_DESC_LEN_1(tx_bd_desc, 0); - SET_TX_BUFF_DESC_AMSDU_1(tx_bd_desc, 0); - SET_TX_BUFF_DESC_LEN_2(tx_bd_desc, 0); - SET_TX_BUFF_DESC_AMSDU_2(tx_bd_desc, 0); - SET_TX_BUFF_DESC_LEN_3(tx_bd_desc, 0); - SET_TX_BUFF_DESC_AMSDU_3(tx_bd_desc, 0); /* Clear all status */ CLEAR_PCI_TX_DESC_CONTENT(desc, TX_DESC_SIZE); @@ -643,14 +635,16 @@ void rtl92ee_pre_fill_tx_bd_desc(struct ieee80211_hw *hw, SET_TX_BUFF_DESC_LEN_0(tx_bd_desc, desc_size); } SET_TX_BUFF_DESC_PSB(tx_bd_desc, psblen); - SET_TX_BUFF_DESC_ADDR_LOW_0(tx_bd_desc, - rtlpci->tx_ring[queue_index].dma + - (current_bd_desc * TX_DESC_SIZE)); + SET_TX_BUFF_DESC_ADDR_LOW_0(tx_bd_desc, desc_dma_addr); + SET_TX_BUFF_DESC_ADDR_HIGH_0(tx_bd_desc, ((u64)desc_dma_addr >> 32), + dma64); SET_TXBUFFER_DESC_LEN_WITH_OFFSET(tx_bd_desc, 1, pkt_len); /* don't using extendsion mode. */ SET_TXBUFFER_DESC_AMSDU_WITH_OFFSET(tx_bd_desc, 1, 0); SET_TXBUFFER_DESC_ADD_LOW_WITH_OFFSET(tx_bd_desc, 1, addr); + SET_TXBUFFER_DESC_ADD_HIGH_WITH_OFFSET(tx_bd_desc, 1, + ((u64)addr >> 32), dma64); SET_TX_DESC_PKT_SIZE(desc, (u16)(pkt_len)); SET_TX_DESC_TX_BUFFER_SIZE(desc, (u16)(pkt_len)); @@ -918,6 +912,7 @@ void rtl92ee_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, static bool over_run; u32 tmp = 0; u8 q_idx = *val; + bool dma64 = rtlpriv->cfg->mod_params->dma64; if (istx) { switch (desc_name) { @@ -982,7 +977,12 @@ void rtl92ee_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, MAX_RECEIVE_BUFFER_SIZE + RX_DESC_SIZE); - SET_RX_BUFFER_PHYSICAL_LOW(pdesc, *(u32 *)val); + SET_RX_BUFFER_PHYSICAL_LOW(pdesc, (*(dma_addr_t *)val) & + DMA_BIT_MASK(32)); + SET_RX_BUFFER_PHYSICAL_HIGH(pdesc, + ((u64)(*(dma_addr_t *)val) + >> 32), + dma64); break; case HW_DESC_RXERO: SET_RX_DESC_EOR(pdesc, 1); @@ -996,9 +996,12 @@ void rtl92ee_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, } } -u32 rtl92ee_get_desc(u8 *pdesc, bool istx, u8 desc_name) +u64 rtl92ee_get_desc(struct ieee80211_hw *hw, + u8 *pdesc, bool istx, u8 desc_name) { - u32 ret = 0; + struct rtl_priv *rtlpriv = rtl_priv(hw); + u64 ret = 0; + bool dma64 = rtlpriv->cfg->mod_params->dma64; if (istx) { switch (desc_name) { @@ -1007,6 +1010,8 @@ u32 rtl92ee_get_desc(u8 *pdesc, bool istx, u8 desc_name) break; case HW_DESC_TXBUFF_ADDR: ret = GET_TXBUFFER_DESC_ADDR_LOW(pdesc, 1); + ret |= (u64)GET_TXBUFFER_DESC_ADDR_HIGH(pdesc, 1, + dma64) << 32; break; default: WARN_ONCE(true, diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.h index b0105c529010..48c16fff20c6 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/trx.h @@ -26,24 +26,6 @@ #ifndef __RTL92E_TRX_H__ #define __RTL92E_TRX_H__ -#if (DMA_IS_64BIT == 1) -#if (RTL8192EE_SEG_NUM == 2) -#define TX_BD_DESC_SIZE 128 -#elif (RTL8192EE_SEG_NUM == 1) -#define TX_BD_DESC_SIZE 64 -#elif (RTL8192EE_SEG_NUM == 0) -#define TX_BD_DESC_SIZE 32 -#endif -#else -#if (RTL8192EE_SEG_NUM == 2) -#define TX_BD_DESC_SIZE 64 -#elif (RTL8192EE_SEG_NUM == 1) -#define TX_BD_DESC_SIZE 32 -#elif (RTL8192EE_SEG_NUM == 0) -#define TX_BD_DESC_SIZE 16 -#endif -#endif - #define TX_DESC_SIZE 64 #define RX_DRV_INFO_SIZE_UNIT 8 @@ -331,111 +313,34 @@ SET_BITS_TO_LE_4BYTE(__pdesc+(__set*16)+8, 0, 32, __val) /* for Txfilldescroptor92ee, fill the desc content. */ -#if (DMA_IS_64BIT == 1) -#define SET_TXBUFFER_DESC_LEN_WITH_OFFSET(__pdesc, __offset, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+(__offset*16), 0, 16, __val) -#define SET_TXBUFFER_DESC_AMSDU_WITH_OFFSET(__pdesc, __offset, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+(__offset*16), 31, 1, __val) -#define SET_TXBUFFER_DESC_ADD_LOW_WITH_OFFSET(__pdesc, __offset, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+(__offset*16)+4, 0, 32, __val) -#define SET_TXBUFFER_DESC_ADD_HIGT_WITH_OFFSET(__pdesc, __offset, __val)\ - SET_BITS_TO_LE_4BYTE(__pdesc+(__offset*16)+8, 0, 32, __val) -#define GET_TXBUFFER_DESC_ADDR_LOW(__pdesc, __offset) \ - LE_BITS_TO_4BYTE(__pdesc+(__offset*16)+4, 0, 32) -#else -#define SET_TXBUFFER_DESC_LEN_WITH_OFFSET(__pdesc, __offset, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+(__offset*8), 0, 16, __val) -#define SET_TXBUFFER_DESC_AMSDU_WITH_OFFSET(__pdesc, __offset, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+(__offset*8), 31, 1, __val) -#define SET_TXBUFFER_DESC_ADD_LOW_WITH_OFFSET(__pdesc, __offset, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+(__offset*8)+4, 0, 32, __val) -#define SET_TXBUFFER_DESC_ADD_HIGT_WITH_OFFSET(__pdesc, __offset, __val) -#define GET_TXBUFFER_DESC_ADDR_LOW(__pdesc, __offset) \ - LE_BITS_TO_4BYTE(__pdesc+(__offset*8)+4, 0, 32) -#endif +#define SET_TXBUFFER_DESC_LEN_WITH_OFFSET(__pdesc, __offset, __val) \ + SET_BITS_TO_LE_4BYTE((__pdesc) + ((__offset) * 16), 0, 16, __val) +#define SET_TXBUFFER_DESC_AMSDU_WITH_OFFSET(__pdesc, __offset, __val) \ + SET_BITS_TO_LE_4BYTE((__pdesc) + ((__offset) * 16), 31, 1, __val) +#define SET_TXBUFFER_DESC_ADD_LOW_WITH_OFFSET(__pdesc, __offset, __val) \ + SET_BITS_TO_LE_4BYTE((__pdesc) + ((__offset) * 16) + 4, 0, 32, __val) +#define SET_TXBUFFER_DESC_ADD_HIGH_WITH_OFFSET(pbd, off, val, dma64) \ + (dma64 ? SET_BITS_TO_LE_4BYTE((pbd) + ((off) * 16) + 8, 0, 32, val) : 0) +#define GET_TXBUFFER_DESC_ADDR_LOW(__pdesc, __offset) \ + LE_BITS_TO_4BYTE((__pdesc) + ((__offset) * 16) + 4, 0, 32) +#define GET_TXBUFFER_DESC_ADDR_HIGH(pbd, off, dma64) \ + (dma64 ? LE_BITS_TO_4BYTE((pbd) + ((off) * 16) + 8, 0, 32) : 0) /* Dword 0 */ -#define SET_TX_BUFF_DESC_LEN_0(__pdesc, __val) \ +#define SET_TX_BUFF_DESC_LEN_0(__pdesc, __val) \ SET_BITS_TO_LE_4BYTE(__pdesc, 0, 14, __val) -#define SET_TX_BUFF_DESC_PSB(__pdesc, __val) \ +#define SET_TX_BUFF_DESC_PSB(__pdesc, __val) \ SET_BITS_TO_LE_4BYTE(__pdesc, 16, 15, __val) -#define SET_TX_BUFF_DESC_OWN(__pdesc, __val) \ +#define SET_TX_BUFF_DESC_OWN(__pdesc, __val) \ SET_BITS_TO_LE_4BYTE(__pdesc, 31, 1, __val) /* Dword 1 */ -#define SET_TX_BUFF_DESC_ADDR_LOW_0(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+4, 0, 32, __val) -#if (DMA_IS_64BIT == 1) +#define SET_TX_BUFF_DESC_ADDR_LOW_0(__pdesc, __val) \ + SET_BITS_TO_LE_4BYTE((__pdesc) + 4, 0, 32, __val) /* Dword 2 */ -#define SET_TX_BUFF_DESC_ADDR_HIGH_0(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+8, 0, 32, __val) +#define SET_TX_BUFF_DESC_ADDR_HIGH_0(bdesc, val, dma64) \ + SET_TXBUFFER_DESC_ADD_HIGH_WITH_OFFSET(bdesc, 0, val, dma64) /* Dword 3 / RESERVED 0 */ -/* Dword 4 */ -#define SET_TX_BUFF_DESC_LEN_1(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+16, 0, 16, __val) -#define SET_TX_BUFF_DESC_AMSDU_1(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+16, 31, 1, __val) -/* Dword 5 */ -#define SET_TX_BUFF_DESC_ADDR_LOW_1(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+20, 0, 32, __val) -/* Dword 6 */ -#define SET_TX_BUFF_DESC_ADDR_HIGH_1(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+24, 0, 32, __val) -/* Dword 7 / RESERVED 0 */ -/* Dword 8 */ -#define SET_TX_BUFF_DESC_LEN_2(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+32, 0, 16, __val) -#define SET_TX_BUFF_DESC_AMSDU_2(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+32, 31, 1, __val) -/* Dword 9 */ -#define SET_TX_BUFF_DESC_ADDR_LOW_2(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+36, 0, 32, __val) -/* Dword 10 */ -#define SET_TX_BUFF_DESC_ADDR_HIGH_2(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+40, 0, 32, __val) -/* Dword 11 / RESERVED 0 */ -/* Dword 12 */ -#define SET_TX_BUFF_DESC_LEN_3(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+48, 0, 16, __val) -#define SET_TX_BUFF_DESC_AMSDU_3(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+48, 31, 1, __val) -/* Dword 13 */ -#define SET_TX_BUFF_DESC_ADDR_LOW_3(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+52, 0, 32, __val) -/* Dword 14 */ -#define SET_TX_BUFF_DESC_ADDR_HIGH_3(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+56, 0, 32, __val) -/* Dword 15 / RESERVED 0 */ -#else -#define SET_TX_BUFF_DESC_ADDR_HIGH_0(__pdesc, __val) -/* Dword 2 */ -#define SET_TX_BUFF_DESC_LEN_1(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+8, 0, 16, __val) -#define SET_TX_BUFF_DESC_AMSDU_1(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+8, 31, 1, __val) -/* Dword 3 */ -#define SET_TX_BUFF_DESC_ADDR_LOW_1(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+12, 0, 32, __val) -#define SET_TX_BUFF_DESC_ADDR_HIGH_1(__pdesc, __val) -/* Dword 4 */ -#define SET_TX_BUFF_DESC_LEN_2(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+16, 0, 16, __val) -#define SET_TX_BUFF_DESC_AMSDU_2(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+16, 31, 1, __val) -/* Dword 5 */ -#define SET_TX_BUFF_DESC_ADDR_LOW_2(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+20, 0, 32, __val) -#define SET_TX_BUFF_DESC_ADDR_HIGH_2(__pdesc, __val) -/* Dword 6 */ -#define SET_TX_BUFF_DESC_LEN_3(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+24, 0, 16, __val) -#define SET_TX_BUFF_DESC_AMSDU_3(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+24, 31, 1, __val) -/* Dword 7 */ -#define SET_TX_BUFF_DESC_ADDR_LOW_3(__pdesc, __val) \ - SET_BITS_TO_LE_4BYTE(__pdesc+28, 0, 32, __val) -#define SET_TX_BUFF_DESC_ADDR_HIGH_3(__pdesc, __val) -#endif /* RX buffer */ @@ -463,8 +368,8 @@ SET_BITS_TO_LE_4BYTE(__status+4, 0, 32, __val) /* DWORD 2 */ -#define SET_RX_BUFFER_PHYSICAL_HIGH(__status, __val) \ - SET_BITS_TO_LE_4BYTE(__status+8, 0, 32, __val) +#define SET_RX_BUFFER_PHYSICAL_HIGH(__rx_status_desc, __val, dma64) \ + (dma64 ? SET_BITS_TO_LE_4BYTE((__rx_status_desc) + 8, 0, 32, __val) : 0) #define GET_RX_DESC_PKT_LEN(__pdesc) \ LE_BITS_TO_4BYTE(__pdesc, 0, 14) @@ -850,7 +755,8 @@ bool rtl92ee_rx_query_desc(struct ieee80211_hw *hw, void rtl92ee_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, u8 desc_name, u8 *val); -u32 rtl92ee_get_desc(u8 *pdesc, bool istx, u8 desc_name); +u64 rtl92ee_get_desc(struct ieee80211_hw *hw, + u8 *pdesc, bool istx, u8 desc_name); bool rtl92ee_is_tx_desc_closed(struct ieee80211_hw *hw, u8 hw_queue, u16 index); void rtl92ee_tx_polling(struct ieee80211_hw *hw, u8 hw_queue); void rtl92ee_tx_fill_cmddesc(struct ieee80211_hw *hw, u8 *pdesc, diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/dm.c index 2c073a77b194..44f510a94b09 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/dm.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/dm.c @@ -295,7 +295,8 @@ static void _rtl92s_dm_refresh_rateadaptive_mask(struct ieee80211_hw *hw) sta = rtl_find_sta(hw, mac->bssid); if (sta) rtlpriv->cfg->ops->update_rate_tbl(hw, sta, - ra->ratr_state); + ra->ratr_state, + true); rcu_read_unlock(); ra->pre_ratr_state = ra->ratr_state; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.c index ba1bd782238b..66be79ca4247 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.c @@ -2129,7 +2129,7 @@ static void rtl92se_update_hal_rate_table(struct ieee80211_hw *hw, static void rtl92se_update_hal_rate_mask(struct ieee80211_hw *hw, struct ieee80211_sta *sta, - u8 rssi_level) + u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_phy *rtlphy = &(rtlpriv->phy); @@ -2288,12 +2288,12 @@ static void rtl92se_update_hal_rate_mask(struct ieee80211_hw *hw, } void rtl92se_update_hal_rate_tbl(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level) + struct ieee80211_sta *sta, u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); if (rtlpriv->dm.useramask) - rtl92se_update_hal_rate_mask(hw, sta, rssi_level); + rtl92se_update_hal_rate_mask(hw, sta, rssi_level, update_bw); else rtl92se_update_hal_rate_table(hw, sta); } diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.h index 86bce1be83ce..3c93d30fcae7 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/hw.h @@ -59,7 +59,7 @@ void rtl92se_update_interrupt_mask(struct ieee80211_hw *hw, void rtl92se_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val); void rtl92se_update_hal_rate_tbl(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level); + struct ieee80211_sta *sta, u8 rssi_level, bool update_bw); void rtl92se_update_channel_access_setting(struct ieee80211_hw *hw); bool rtl92se_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c index d7945b9db493..d55554b7fa9a 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c @@ -41,6 +41,7 @@ static void rtl92s_init_aspm_vars(struct ieee80211_hw *hw) { + struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); /*close ASPM for AMD defaultly */ @@ -77,7 +78,7 @@ static void rtl92s_init_aspm_vars(struct ieee80211_hw *hw) * 1 - Support ASPM, * 2 - According to chipset. */ - rtlpci->const_support_pciaspm = 2; + rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support; } static void rtl92se_fw_cb(const struct firmware *firmware, void *context) @@ -240,7 +241,7 @@ static bool rtl92se_is_tx_desc_closed(struct ieee80211_hw *hw, u8 hw_queue, struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue]; u8 *entry = (u8 *)(&ring->desc[ring->idx]); - u8 own = (u8)rtl92se_get_desc(entry, true, HW_DESC_OWN); + u8 own = (u8)rtl92se_get_desc(hw, entry, true, HW_DESC_OWN); if (own) return false; @@ -297,6 +298,7 @@ static struct rtl_mod_params rtl92se_mod_params = { .inactiveps = true, .swctrl_lps = true, .fwctrl_lps = false, + .aspm_support = 2, .debug_level = 0, .debug_mask = 0, }; @@ -422,10 +424,12 @@ module_param_named(debug_mask, rtl92se_mod_params.debug_mask, ullong, 0644); module_param_named(ips, rtl92se_mod_params.inactiveps, bool, 0444); module_param_named(swlps, rtl92se_mod_params.swctrl_lps, bool, 0444); module_param_named(fwlps, rtl92se_mod_params.fwctrl_lps, bool, 0444); +module_param_named(aspm, rtl92se_mod_params.aspm_support, int, 0444); MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n"); MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n"); MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 1)\n"); MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 0)\n"); +MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n"); MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)"); MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)"); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c index a01dbd31d1b4..e1904c39f147 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c @@ -610,7 +610,8 @@ void rtl92se_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, } } -u32 rtl92se_get_desc(u8 *desc, bool istx, u8 desc_name) +u64 rtl92se_get_desc(struct ieee80211_hw *hw, + u8 *desc, bool istx, u8 desc_name) { u32 ret = 0; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.h index 728589138072..81a5445c04a3 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.h @@ -38,7 +38,8 @@ bool rtl92se_rx_query_desc(struct ieee80211_hw *hw, struct rtl_stats *stats, struct sk_buff *skb); void rtl92se_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, u8 desc_name, u8 *val); -u32 rtl92se_get_desc(u8 *pdesc, bool istx, u8 desc_name); +u64 rtl92se_get_desc(struct ieee80211_hw *hw, + u8 *desc, bool istx, u8 desc_name); void rtl92se_tx_polling(struct ieee80211_hw *hw, u8 hw_queue); #endif diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c index 5ac7b815648a..8cfd4993c90a 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c @@ -1943,7 +1943,7 @@ static void rtl8723e_update_hal_rate_table(struct ieee80211_hw *hw, static void rtl8723e_update_hal_rate_mask(struct ieee80211_hw *hw, struct ieee80211_sta *sta, - u8 rssi_level) + u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_phy *rtlphy = &(rtlpriv->phy); @@ -2074,12 +2074,13 @@ static void rtl8723e_update_hal_rate_mask(struct ieee80211_hw *hw, } void rtl8723e_update_hal_rate_tbl(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level) + struct ieee80211_sta *sta, u8 rssi_level, + bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); if (rtlpriv->dm.useramask) - rtl8723e_update_hal_rate_mask(hw, sta, rssi_level); + rtl8723e_update_hal_rate_mask(hw, sta, rssi_level, update_bw); else rtl8723e_update_hal_rate_table(hw, sta); } @@ -2103,7 +2104,7 @@ bool rtl8723e_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid) struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw)); struct rtl_phy *rtlphy = &(rtlpriv->phy); - enum rf_pwrstate e_rfpowerstate_toset, cur_rfstate; + enum rf_pwrstate e_rfpowerstate_toset; u8 u1tmp; bool b_actuallyset = false; @@ -2122,8 +2123,6 @@ bool rtl8723e_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid) spin_unlock(&rtlpriv->locks.rf_ps_lock); } - cur_rfstate = ppsc->rfpwr_state; - rtl_write_byte(rtlpriv, REG_GPIO_IO_SEL_2, rtl_read_byte(rtlpriv, REG_GPIO_IO_SEL_2)&~(BIT(1))); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.h index 32c1ace97c3f..1e7063105c96 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.h @@ -49,7 +49,8 @@ void rtl8723e_update_interrupt_mask(struct ieee80211_hw *hw, u32 add_msr, u32 rm_msr); void rtl8723e_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val); void rtl8723e_update_hal_rate_tbl(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level); + struct ieee80211_sta *sta, u8 rssi_level, + bool update_bw); void rtl8723e_update_channel_access_setting(struct ieee80211_hw *hw); bool rtl8723e_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid); void rtl8723e_enable_hw_security_config(struct ieee80211_hw *hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c index 97b8bd294aa8..a545ea317323 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c @@ -46,6 +46,7 @@ static void rtl8723e_init_aspm_vars(struct ieee80211_hw *hw) { + struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); /*close ASPM for AMD defaultly */ @@ -85,7 +86,7 @@ static void rtl8723e_init_aspm_vars(struct ieee80211_hw *hw) * 1 - Support ASPM, * 2 - According to chipset. */ - rtlpci->const_support_pciaspm = 1; + rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support; } int rtl8723e_init_sw_vars(struct ieee80211_hw *hw) @@ -268,6 +269,7 @@ static struct rtl_mod_params rtl8723e_mod_params = { .inactiveps = true, .swctrl_lps = false, .fwctrl_lps = true, + .aspm_support = 1, .debug_level = 0, .debug_mask = 0, .msi_support = false, @@ -389,6 +391,7 @@ module_param_named(ips, rtl8723e_mod_params.inactiveps, bool, 0444); module_param_named(swlps, rtl8723e_mod_params.swctrl_lps, bool, 0444); module_param_named(fwlps, rtl8723e_mod_params.fwctrl_lps, bool, 0444); module_param_named(msi, rtl8723e_mod_params.msi_support, bool, 0444); +module_param_named(aspm, rtl8723e_mod_params.aspm_support, int, 0444); module_param_named(disable_watchdog, rtl8723e_mod_params.disable_watchdog, bool, 0444); MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n"); @@ -396,6 +399,7 @@ MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n"); MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n"); MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n"); MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 0)\n"); +MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n"); MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)"); MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)"); MODULE_PARM_DESC(disable_watchdog, "Set to 1 to disable the watchdog (default 0)\n"); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c index f713c7249fed..23485602a9a1 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c @@ -643,7 +643,8 @@ void rtl8723e_set_desc(struct ieee80211_hw *hw, u8 *pdesc, } } -u32 rtl8723e_get_desc(u8 *pdesc, bool istx, u8 desc_name) +u64 rtl8723e_get_desc(struct ieee80211_hw *hw, + u8 *pdesc, bool istx, u8 desc_name) { u32 ret = 0; @@ -686,7 +687,7 @@ bool rtl8723e_is_tx_desc_closed(struct ieee80211_hw *hw, struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue]; u8 *entry = (u8 *)(&ring->desc[ring->idx]); - u8 own = (u8)rtl8723e_get_desc(entry, true, HW_DESC_OWN); + u8 own = (u8)rtl8723e_get_desc(hw, entry, true, HW_DESC_OWN); /** *beacon packet will only use the first diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.h index 43d4c791d563..985ce0b77ea5 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.h @@ -708,7 +708,8 @@ bool rtl8723e_rx_query_desc(struct ieee80211_hw *hw, u8 *pdesc, struct sk_buff *skb); void rtl8723e_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, u8 desc_name, u8 *val); -u32 rtl8723e_get_desc(u8 *pdesc, bool istx, u8 desc_name); +u64 rtl8723e_get_desc(struct ieee80211_hw *hw, + u8 *pdesc, bool istx, u8 desc_name); bool rtl8723e_is_tx_desc_closed(struct ieee80211_hw *hw, u8 hw_queue, u16 index); void rtl8723e_tx_polling(struct ieee80211_hw *hw, u8 hw_queue); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/dm.c index 15c117e95a99..47e87a21ae27 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/dm.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/dm.c @@ -984,7 +984,8 @@ static void rtl8723be_dm_refresh_rate_adaptive_mask(struct ieee80211_hw *hw) sta = rtl_find_sta(hw, mac->bssid); if (sta) rtlpriv->cfg->ops->update_rate_tbl(hw, sta, - p_ra->ratr_state); + p_ra->ratr_state, + true); rcu_read_unlock(); p_ra->pre_ratr_state = p_ra->ratr_state; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c index 4d47b97adfed..239518bd31f1 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c @@ -60,6 +60,7 @@ static void _rtl8723be_return_beacon_queue_skb(struct ieee80211_hw *hw) pci_unmap_single(rtlpci->pdev, rtlpriv->cfg->ops->get_desc( + hw, (u8 *)entry, true, HW_DESC_TXBUFF_ADDR), skb->len, PCI_DMA_TODEVICE); kfree_skb(skb); @@ -2324,7 +2325,7 @@ static u8 _rtl8723be_mrate_idx_to_arfr_id(struct ieee80211_hw *hw, static void rtl8723be_update_hal_rate_mask(struct ieee80211_hw *hw, struct ieee80211_sta *sta, - u8 rssi_level) + u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_phy *rtlphy = &(rtlpriv->phy); @@ -2440,7 +2441,7 @@ static void rtl8723be_update_hal_rate_mask(struct ieee80211_hw *hw, rate_mask[0] = macid; rate_mask[1] = _rtl8723be_mrate_idx_to_arfr_id(hw, ratr_index) | (shortgi ? 0x80 : 0x00); - rate_mask[2] = curtxbw_40mhz; + rate_mask[2] = curtxbw_40mhz | ((!update_bw) << 3); rate_mask[3] = (u8)(ratr_bitmap & 0x000000ff); rate_mask[4] = (u8)((ratr_bitmap & 0x0000ff00) >> 8); @@ -2460,11 +2461,11 @@ static void rtl8723be_update_hal_rate_mask(struct ieee80211_hw *hw, void rtl8723be_update_hal_rate_tbl(struct ieee80211_hw *hw, struct ieee80211_sta *sta, - u8 rssi_level) + u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); if (rtlpriv->dm.useramask) - rtl8723be_update_hal_rate_mask(hw, sta, rssi_level); + rtl8723be_update_hal_rate_mask(hw, sta, rssi_level, update_bw); } void rtl8723be_update_channel_access_setting(struct ieee80211_hw *hw) @@ -2486,7 +2487,7 @@ bool rtl8723be_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid) struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw)); struct rtl_phy *rtlphy = &(rtlpriv->phy); - enum rf_pwrstate e_rfpowerstate_toset, cur_rfstate; + enum rf_pwrstate e_rfpowerstate_toset; u8 u1tmp; bool b_actuallyset = false; @@ -2505,8 +2506,6 @@ bool rtl8723be_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid) spin_unlock(&rtlpriv->locks.rf_ps_lock); } - cur_rfstate = ppsc->rfpwr_state; - rtl_write_byte(rtlpriv, REG_GPIO_IO_SEL_2, rtl_read_byte(rtlpriv, REG_GPIO_IO_SEL_2) & ~(BIT(1))); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.h index eae863d08de8..54d7afa7297e 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.h @@ -46,7 +46,7 @@ void rtl8723be_update_interrupt_mask(struct ieee80211_hw *hw, void rtl8723be_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val); void rtl8723be_update_hal_rate_tbl(struct ieee80211_hw *hw, struct ieee80211_sta *sta, - u8 rssi_level); + u8 rssi_level, bool update_bw); void rtl8723be_update_channel_access_setting(struct ieee80211_hw *hw); bool rtl8723be_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid); void rtl8723be_enable_hw_security_config(struct ieee80211_hw *hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c index 2b16a1467e78..6a42988aad65 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c @@ -46,6 +46,7 @@ static void rtl8723be_init_aspm_vars(struct ieee80211_hw *hw) { + struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); /*close ASPM for AMD defaultly */ @@ -82,7 +83,7 @@ static void rtl8723be_init_aspm_vars(struct ieee80211_hw *hw) * 1 - Support ASPM, * 2 - According to chipset. */ - rtlpci->const_support_pciaspm = 1; + rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support; } int rtl8723be_init_sw_vars(struct ieee80211_hw *hw) @@ -271,6 +272,7 @@ static struct rtl_mod_params rtl8723be_mod_params = { .swctrl_lps = false, .fwctrl_lps = true, .msi_support = false, + .aspm_support = 1, .disable_watchdog = false, .debug_level = 0, .debug_mask = 0, @@ -396,6 +398,7 @@ module_param_named(ips, rtl8723be_mod_params.inactiveps, bool, 0444); module_param_named(swlps, rtl8723be_mod_params.swctrl_lps, bool, 0444); module_param_named(fwlps, rtl8723be_mod_params.fwctrl_lps, bool, 0444); module_param_named(msi, rtl8723be_mod_params.msi_support, bool, 0444); +module_param_named(aspm, rtl8723be_mod_params.aspm_support, int, 0444); module_param_named(disable_watchdog, rtl8723be_mod_params.disable_watchdog, bool, 0444); module_param_named(ant_sel, rtl8723be_mod_params.ant_sel, int, 0444); @@ -404,6 +407,7 @@ MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n"); MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n"); MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n"); MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 0)\n"); +MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n"); MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)"); MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)"); MODULE_PARM_DESC(disable_watchdog, diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.c index 0e8944119652..fd9b38aa08a1 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.c @@ -695,7 +695,8 @@ void rtl8723be_set_desc(struct ieee80211_hw *hw, u8 *pdesc, } } -u32 rtl8723be_get_desc(u8 *pdesc, bool istx, u8 desc_name) +u64 rtl8723be_get_desc(struct ieee80211_hw *hw, + u8 *pdesc, bool istx, u8 desc_name) { u32 ret = 0; @@ -738,7 +739,7 @@ bool rtl8723be_is_tx_desc_closed(struct ieee80211_hw *hw, struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue]; u8 *entry = (u8 *)(&ring->desc[ring->idx]); - u8 own = (u8)rtl8723be_get_desc(entry, true, HW_DESC_OWN); + u8 own = (u8)rtl8723be_get_desc(hw, entry, true, HW_DESC_OWN); /*beacon packet will only use the first *descriptor defautly,and the own may not diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.h index 0274659f48ed..988bf0586674 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/trx.h @@ -624,7 +624,8 @@ bool rtl8723be_rx_query_desc(struct ieee80211_hw *hw, u8 *pdesc, struct sk_buff *skb); void rtl8723be_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, u8 desc_name, u8 *val); -u32 rtl8723be_get_desc(u8 *pdesc, bool istx, u8 desc_name); +u64 rtl8723be_get_desc(struct ieee80211_hw *hw, + u8 *pdesc, bool istx, u8 desc_name); bool rtl8723be_is_tx_desc_closed(struct ieee80211_hw *hw, u8 hw_queue, u16 index); void rtl8723be_tx_polling(struct ieee80211_hw *hw, u8 hw_queue); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.c index ac573d69f6d6..efa7e1262461 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723com/fw_common.c @@ -253,7 +253,8 @@ bool rtl8723_cmd_send_packet(struct ieee80211_hw *hw, spin_lock_irqsave(&rtlpriv->locks.irq_th_lock, flags); pdesc = &ring->desc[0]; - own = (u8) rtlpriv->cfg->ops->get_desc((u8 *)pdesc, true, HW_DESC_OWN); + own = (u8)rtlpriv->cfg->ops->get_desc(hw, (u8 *)pdesc, true, + HW_DESC_OWN); rtlpriv->cfg->ops->fill_tx_cmddesc(hw, (u8 *)pdesc, 1, 1, skb); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c index 32900c51f024..b11365a5ee1f 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c @@ -2592,7 +2592,7 @@ static void rtl8821ae_dm_refresh_rate_adaptive_mask(struct ieee80211_hw *hw) sta = rtl_find_sta(hw, mac->bssid); if (sta) rtlpriv->cfg->ops->update_rate_tbl(hw, - sta, p_ra->ratr_state); + sta, p_ra->ratr_state, true); rcu_read_unlock(); p_ra->pre_ratr_state = p_ra->ratr_state; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c index 4f73012978e9..6408bc8456f3 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c @@ -57,6 +57,7 @@ static void _rtl8821ae_return_beacon_queue_skb(struct ieee80211_hw *hw) pci_unmap_single(rtlpci->pdev, rtlpriv->cfg->ops->get_desc( + hw, (u8 *)entry, true, HW_DESC_TXBUFF_ADDR), skb->len, PCI_DMA_TODEVICE); kfree_skb(skb); @@ -1122,7 +1123,7 @@ static u8 _rtl8821ae_dbi_read(struct rtl_priv *rtlpriv, u16 addr) } if (0 == tmp) { read_addr = REG_DBI_RDATA + addr % 4; - ret = rtl_read_byte(rtlpriv, read_addr); + ret = rtl_read_word(rtlpriv, read_addr); } return ret; } @@ -3598,7 +3599,7 @@ static bool _rtl8821ae_get_ra_shortgi(struct ieee80211_hw *hw, struct ieee80211_ } static void rtl8821ae_update_hal_rate_mask(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level) + struct ieee80211_sta *sta, u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_phy *rtlphy = &rtlpriv->phy; @@ -3777,7 +3778,7 @@ static void rtl8821ae_update_hal_rate_mask(struct ieee80211_hw *hw, rate_mask[0] = macid; rate_mask[1] = ratr_index | (b_shortgi ? 0x80 : 0x00); - rate_mask[2] = rtlphy->current_chan_bw + rate_mask[2] = rtlphy->current_chan_bw | ((!update_bw) << 3) | _rtl8821ae_get_vht_eni(wirelessmode, ratr_bitmap) | _rtl8821ae_get_ra_ldpc(hw, macid, sta_entry, wirelessmode); @@ -3798,11 +3799,11 @@ static void rtl8821ae_update_hal_rate_mask(struct ieee80211_hw *hw, } void rtl8821ae_update_hal_rate_tbl(struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level) + struct ieee80211_sta *sta, u8 rssi_level, bool update_bw) { struct rtl_priv *rtlpriv = rtl_priv(hw); if (rtlpriv->dm.useramask) - rtl8821ae_update_hal_rate_mask(hw, sta, rssi_level); + rtl8821ae_update_hal_rate_mask(hw, sta, rssi_level, update_bw); else /*RT_TRACE(rtlpriv, COMP_RATR,DBG_LOUD, "rtl8821ae_update_hal_rate_tbl() Error! 8821ae FW RA Only\n");*/ @@ -3845,7 +3846,7 @@ bool rtl8821ae_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid) struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw)); struct rtl_phy *rtlphy = &rtlpriv->phy; - enum rf_pwrstate e_rfpowerstate_toset, cur_rfstate; + enum rf_pwrstate e_rfpowerstate_toset; u8 u1tmp = 0; bool b_actuallyset = false; @@ -3864,8 +3865,6 @@ bool rtl8821ae_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid) spin_unlock(&rtlpriv->locks.rf_ps_lock); } - cur_rfstate = ppsc->rfpwr_state; - rtl_write_byte(rtlpriv, REG_GPIO_IO_SEL_2, rtl_read_byte(rtlpriv, REG_GPIO_IO_SEL_2) & ~(BIT(1))); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.h index a3553e3abaa1..50fa9c718189 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.h @@ -46,7 +46,7 @@ void rtl8821ae_update_interrupt_mask(struct ieee80211_hw *hw, void rtl8821ae_set_hw_reg(struct ieee80211_hw *hw, u8 variable, u8 *val); void rtl8821ae_update_hal_rate_tbl(struct ieee80211_hw *hw, struct ieee80211_sta *sta, - u8 rssi_level); + u8 rssi_level, bool update_bw); void rtl8821ae_update_channel_access_setting(struct ieee80211_hw *hw); bool rtl8821ae_gpio_radio_on_off_checking(struct ieee80211_hw *hw, u8 *valid); void rtl8821ae_enable_hw_security_config(struct ieee80211_hw *hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c index 0894ef48ab87..ab5d462b1a3a 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c @@ -43,6 +43,7 @@ static void rtl8821ae_init_aspm_vars(struct ieee80211_hw *hw) { + struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); /*close ASPM for AMD defaultly */ @@ -82,7 +83,7 @@ static void rtl8821ae_init_aspm_vars(struct ieee80211_hw *hw) * 1 - Support ASPM, * 2 - According to chipset. */ - rtlpci->const_support_pciaspm = 1; + rtlpci->const_support_pciaspm = rtlpriv->cfg->mod_params->aspm_support; } /*InitializeVariables8812E*/ @@ -313,6 +314,7 @@ static struct rtl_mod_params rtl8821ae_mod_params = { .swctrl_lps = false, .fwctrl_lps = true, .msi_support = true, + .aspm_support = 1, .int_clear = true, .debug_level = 0, .debug_mask = 0, @@ -444,6 +446,7 @@ module_param_named(ips, rtl8821ae_mod_params.inactiveps, bool, 0444); module_param_named(swlps, rtl8821ae_mod_params.swctrl_lps, bool, 0444); module_param_named(fwlps, rtl8821ae_mod_params.fwctrl_lps, bool, 0444); module_param_named(msi, rtl8821ae_mod_params.msi_support, bool, 0444); +module_param_named(aspm, rtl8821ae_mod_params.aspm_support, int, 0444); module_param_named(disable_watchdog, rtl8821ae_mod_params.disable_watchdog, bool, 0444); module_param_named(int_clear, rtl8821ae_mod_params.int_clear, bool, 0444); @@ -452,6 +455,7 @@ MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n"); MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n"); MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n"); MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 1)\n"); +MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n"); MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)"); MODULE_PARM_DESC(debug_mask, "Set debug mask (default 0)"); MODULE_PARM_DESC(disable_watchdog, "Set to 1 to disable the watchdog (default 0)\n"); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c index 749818929e8f..1e1bacf562f3 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.c @@ -935,7 +935,8 @@ void rtl8821ae_set_desc(struct ieee80211_hw *hw, u8 *pdesc, } } -u32 rtl8821ae_get_desc(u8 *pdesc, bool istx, u8 desc_name) +u64 rtl8821ae_get_desc(struct ieee80211_hw *hw, + u8 *pdesc, bool istx, u8 desc_name) { u32 ret = 0; @@ -980,7 +981,7 @@ bool rtl8821ae_is_tx_desc_closed(struct ieee80211_hw *hw, struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl8192_tx_ring *ring = &rtlpci->tx_ring[hw_queue]; u8 *entry = (u8 *)(&ring->desc[ring->idx]); - u8 own = (u8)rtl8821ae_get_desc(entry, true, HW_DESC_OWN); + u8 own = (u8)rtl8821ae_get_desc(hw, entry, true, HW_DESC_OWN); /** *beacon packet will only use the first diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h index 9843a616dcec..221dd2b29d3b 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h @@ -620,7 +620,8 @@ bool rtl8821ae_rx_query_desc(struct ieee80211_hw *hw, u8 *pdesc, struct sk_buff *skb); void rtl8821ae_set_desc(struct ieee80211_hw *hw, u8 *pdesc, bool istx, u8 desc_name, u8 *val); -u32 rtl8821ae_get_desc(u8 *pdesc, bool istx, u8 desc_name); +u64 rtl8821ae_get_desc(struct ieee80211_hw *hw, + u8 *pdesc, bool istx, u8 desc_name); bool rtl8821ae_is_tx_desc_closed(struct ieee80211_hw *hw, u8 hw_queue, u16 index); void rtl8821ae_tx_polling(struct ieee80211_hw *hw, u8 hw_queue); diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h index 1ab1024330fb..7dfc73b554f1 100644 --- a/drivers/net/wireless/realtek/rtlwifi/wifi.h +++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h @@ -169,16 +169,14 @@ enum rtl8192c_h2c_cmd { #define MAX_BASE_NUM_IN_PHY_REG_PG_24G 6 #define MAX_BASE_NUM_IN_PHY_REG_PG_5G 5 -#define RTL8192EE_SEG_NUM 1 /* 0:2 seg, 1: 4 seg, 2: 8 seg */ +#define BUFDESC_SEG_NUM 1 /* 0:2 seg, 1: 4 seg, 2: 8 seg */ #define DEL_SW_IDX_SZ 30 -#define BAND_NUM 3 /* For now, it's just for 8192ee * but not OK yet, keep it 0 */ -#define DMA_IS_64BIT 0 -#define RTL8192EE_SEG_NUM 1 /* 0:2 seg, 1: 4 seg, 2: 8 seg */ +#define RTL8192EE_SEG_NUM BUFDESC_SEG_NUM enum rf_tx_num { RF_1TX = 0, @@ -561,6 +559,11 @@ enum rf_type { RF_1T2R = 1, RF_2T2R = 2, RF_2T2R_GREEN = 3, + RF_2T3R = 4, + RF_2T4R = 5, + RF_3T3R = 6, + RF_3T4R = 7, + RF_4T4R = 8, }; enum ht_channel_width { @@ -1014,10 +1017,17 @@ struct init_gain { }; struct wireless_stats { - unsigned long txbytesunicast; - unsigned long txbytesmulticast; - unsigned long txbytesbroadcast; - unsigned long rxbytesunicast; + u64 txbytesunicast; + u64 txbytesmulticast; + u64 txbytesbroadcast; + u64 rxbytesunicast; + + u64 txbytesunicast_inperiod; + u64 rxbytesunicast_inperiod; + u32 txbytesunicast_inperiod_tp; + u32 rxbytesunicast_inperiod_tp; + u64 txbytesunicast_last; + u64 rxbytesunicast_last; long rx_snr_db[4]; /*Correct smoothed ss in Dbm, only used @@ -1323,6 +1333,7 @@ struct rtl_sta_info { struct rtl_tid_data tids[MAX_TID_COUNT]; /* just used for ap adhoc or mesh*/ struct rssi_sta rssi_stat; + u8 rssi_level; u16 wireless_mode; u8 ratr_index; u8 mimo_ps; @@ -1736,21 +1747,6 @@ struct rtl_dm { s8 swing_diff_2g; s8 swing_diff_5g; - u8 delta_swing_table_idx_24gccka_p[DEL_SW_IDX_SZ]; - u8 delta_swing_table_idx_24gccka_n[DEL_SW_IDX_SZ]; - u8 delta_swing_table_idx_24gcckb_p[DEL_SW_IDX_SZ]; - u8 delta_swing_table_idx_24gcckb_n[DEL_SW_IDX_SZ]; - u8 delta_swing_table_idx_24ga_p[DEL_SW_IDX_SZ]; - u8 delta_swing_table_idx_24ga_n[DEL_SW_IDX_SZ]; - u8 delta_swing_table_idx_24gb_p[DEL_SW_IDX_SZ]; - u8 delta_swing_table_idx_24gb_n[DEL_SW_IDX_SZ]; - u8 delta_swing_table_idx_5ga_p[BAND_NUM][DEL_SW_IDX_SZ]; - u8 delta_swing_table_idx_5ga_n[BAND_NUM][DEL_SW_IDX_SZ]; - u8 delta_swing_table_idx_5gb_p[BAND_NUM][DEL_SW_IDX_SZ]; - u8 delta_swing_table_idx_5gb_n[BAND_NUM][DEL_SW_IDX_SZ]; - u8 delta_swing_table_idx_24ga_p_8188e[DEL_SW_IDX_SZ]; - u8 delta_swing_table_idx_24ga_n_8188e[DEL_SW_IDX_SZ]; - /* DMSP */ bool supp_phymode_switch; @@ -2127,7 +2123,8 @@ struct rtl_hal_ops { void (*get_hw_reg) (struct ieee80211_hw *hw, u8 variable, u8 *val); void (*set_hw_reg) (struct ieee80211_hw *hw, u8 variable, u8 *val); void (*update_rate_tbl) (struct ieee80211_hw *hw, - struct ieee80211_sta *sta, u8 rssi_level); + struct ieee80211_sta *sta, u8 rssi_leve, + bool update_bw); void (*pre_fill_tx_bd_desc)(struct ieee80211_hw *hw, u8 *tx_bd_desc, u8 *desc, u8 queue_index, struct sk_buff *skb, dma_addr_t addr); @@ -2162,7 +2159,8 @@ struct rtl_hal_ops { enum led_ctl_mode ledaction); void (*set_desc)(struct ieee80211_hw *hw, u8 *pdesc, bool istx, u8 desc_name, u8 *val); - u32 (*get_desc) (u8 *pdesc, bool istx, u8 desc_name); + u64 (*get_desc)(struct ieee80211_hw *hw, u8 *pdesc, bool istx, + u8 desc_name); bool (*is_tx_desc_closed) (struct ieee80211_hw *hw, u8 hw_queue, u16 index); void (*tx_polling) (struct ieee80211_hw *hw, u8 hw_queue); @@ -2261,6 +2259,12 @@ struct rtl_mod_params { */ bool msi_support; + /* default: 0 = dma 32 */ + bool dma64; + + /* default: 1 = enable aspm */ + int aspm_support; + /* default 0: 1 means disable */ bool disable_watchdog; @@ -2857,19 +2861,19 @@ value to host byte ordering.*/ cpu_to_le32( \ LE_BITS_CLEARED_TO_4BYTE(__pstart, __bitoffset, __bitlen) | \ ((((u32)__val) & BIT_LEN_MASK_32(__bitlen)) << (__bitoffset)) \ - ); + ) #define SET_BITS_TO_LE_2BYTE(__pstart, __bitoffset, __bitlen, __val) \ *((__le16 *)(__pstart)) = \ cpu_to_le16( \ LE_BITS_CLEARED_TO_2BYTE(__pstart, __bitoffset, __bitlen) | \ ((((u16)__val) & BIT_LEN_MASK_16(__bitlen)) << (__bitoffset)) \ - ); + ) #define SET_BITS_TO_LE_1BYTE(__pstart, __bitoffset, __bitlen, __val) \ *((u8 *)(__pstart)) = EF1BYTE \ ( \ LE_BITS_CLEARED_TO_1BYTE(__pstart, __bitoffset, __bitlen) | \ ((((u8)__val) & BIT_LEN_MASK_8(__bitlen)) << (__bitoffset)) \ - ); + ) #define N_BYTE_ALIGMENT(__value, __aligment) ((__aligment == 1) ? \ (__value) : (((__value + __aligment - 1) / __aligment) * __aligment)) diff --git a/drivers/net/wireless/rsi/rsi_91x_core.c b/drivers/net/wireless/rsi/rsi_91x_core.c index 2b0516d2f63d..bc18a191aef9 100644 --- a/drivers/net/wireless/rsi/rsi_91x_core.c +++ b/drivers/net/wireless/rsi/rsi_91x_core.c @@ -95,6 +95,8 @@ static u32 rsi_get_num_pkts_dequeue(struct rsi_common *common, u8 q_num) s16 txop = common->tx_qinfo[q_num].txop * 32; __le16 r_txop; struct ieee80211_rate rate; + struct ieee80211_hdr *wh; + struct ieee80211_vif *vif; rate.bitrate = RSI_RATE_MCS0 * 5 * 10; /* Convert to Kbps */ if (q_num == VI_Q) @@ -106,8 +108,10 @@ static u32 rsi_get_num_pkts_dequeue(struct rsi_common *common, u8 q_num) return 0; do { + wh = (struct ieee80211_hdr *)skb->data; + vif = rsi_get_vif(adapter, wh->addr2); r_txop = ieee80211_generic_frame_duration(adapter->hw, - adapter->vifs[0], + vif, common->band, skb->len, &rate); txop -= le16_to_cpu(r_txop); @@ -334,6 +338,21 @@ struct rsi_sta *rsi_find_sta(struct rsi_common *common, u8 *mac_addr) return NULL; } +struct ieee80211_vif *rsi_get_vif(struct rsi_hw *adapter, u8 *mac) +{ + struct ieee80211_vif *vif; + int i; + + for (i = 0; i < RSI_MAX_VIFS; i++) { + vif = adapter->vifs[i]; + if (!vif) + continue; + if (!memcmp(vif->addr, mac, ETH_ALEN)) + return vif; + } + return NULL; +} + /** * rsi_core_xmit() - This function transmits the packets received from mac80211 * @common: Pointer to the driver private structure. @@ -346,8 +365,8 @@ void rsi_core_xmit(struct rsi_common *common, struct sk_buff *skb) struct rsi_hw *adapter = common->priv; struct ieee80211_tx_info *info; struct skb_info *tx_params; - struct ieee80211_hdr *wh; - struct ieee80211_vif *vif = adapter->vifs[0]; + struct ieee80211_hdr *wh = NULL; + struct ieee80211_vif *vif; u8 q_num, tid = 0; struct rsi_sta *rsta = NULL; @@ -366,6 +385,11 @@ void rsi_core_xmit(struct rsi_common *common, struct sk_buff *skb) wh = (struct ieee80211_hdr *)&skb->data[0]; tx_params->sta_id = 0; + vif = rsi_get_vif(adapter, wh->addr2); + if (!vif) + goto xmit_fail; + tx_params->vif = vif; + tx_params->vap_id = ((struct vif_priv *)vif->drv_priv)->vap_id; if ((ieee80211_is_mgmt(wh->frame_control)) || (ieee80211_is_ctl(wh->frame_control)) || (ieee80211_is_qos_nullfunc(wh->frame_control))) { @@ -383,7 +407,8 @@ void rsi_core_xmit(struct rsi_common *common, struct sk_buff *skb) q_num = skb->priority; tx_params->tid = tid; - if ((vif->type == NL80211_IFTYPE_AP) && + if (((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO)) && (!is_broadcast_ether_addr(wh->addr1)) && (!is_multicast_ether_addr(wh->addr1))) { rsta = rsi_find_sta(common, wh->addr1); diff --git a/drivers/net/wireless/rsi/rsi_91x_debugfs.c b/drivers/net/wireless/rsi/rsi_91x_debugfs.c index e98eb55c26cc..8c6ca8e689e4 100644 --- a/drivers/net/wireless/rsi/rsi_91x_debugfs.c +++ b/drivers/net/wireless/rsi/rsi_91x_debugfs.c @@ -83,19 +83,12 @@ static int rsi_version_read(struct seq_file *seq, void *data) { struct rsi_common *common = seq->private; - common->driver_ver.major = 0; - common->driver_ver.minor = 1; - common->driver_ver.release_num = 0; - common->driver_ver.patch_num = 0; - seq_printf(seq, "Driver : %x.%d.%d.%d\nLMAC : %d.%d.%d.%d\n", - common->driver_ver.major, - common->driver_ver.minor, - common->driver_ver.release_num, - common->driver_ver.patch_num, - common->fw_ver.major, - common->fw_ver.minor, - common->fw_ver.release_num, - common->fw_ver.patch_num); + seq_printf(seq, "LMAC : %d.%d.%d.%d\n", + common->lmac_ver.major, + common->lmac_ver.minor, + common->lmac_ver.release_num, + common->lmac_ver.patch_num); + return 0; } diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c index 7ad286d6e9a7..689527d7007a 100644 --- a/drivers/net/wireless/rsi/rsi_91x_hal.c +++ b/drivers/net/wireless/rsi/rsi_91x_hal.c @@ -42,7 +42,7 @@ static int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb) struct ieee80211_hdr *wh = NULL; struct ieee80211_tx_info *info; struct ieee80211_conf *conf = &adapter->hw->conf; - struct ieee80211_vif *vif = adapter->vifs[0]; + struct ieee80211_vif *vif; struct rsi_mgmt_desc *mgmt_desc; struct skb_info *tx_params; struct ieee80211_bss_conf *bss = NULL; @@ -57,6 +57,7 @@ static int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb) info = IEEE80211_SKB_CB(skb); tx_params = (struct skb_info *)info->driver_data; + vif = tx_params->vif; /* Update header size */ header_size = FRAME_DESC_SZ + sizeof(struct xtended_desc); @@ -78,7 +79,7 @@ static int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb) tx_params->internal_hdr_size = header_size; memset(&skb->data[0], 0, header_size); - bss = &info->control.vif->bss_conf; + bss = &vif->bss_conf; wh = (struct ieee80211_hdr *)&skb->data[header_size]; mgmt_desc = (struct rsi_mgmt_desc *)skb->data; @@ -95,10 +96,10 @@ static int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb) mgmt_desc->seq_ctrl = cpu_to_le16(IEEE80211_SEQ_TO_SN(le16_to_cpu(wh->seq_ctrl))); - if (common->band == NL80211_BAND_2GHZ) - mgmt_desc->rate_info = RSI_RATE_1; + if ((common->band == NL80211_BAND_2GHZ) && !common->p2p_enabled) + mgmt_desc->rate_info = cpu_to_le16(RSI_RATE_1); else - mgmt_desc->rate_info = RSI_RATE_6; + mgmt_desc->rate_info = cpu_to_le16(RSI_RATE_6); if (conf_is_ht40(conf)) mgmt_desc->bbp_info = cpu_to_le16(FULL40M_ENABLE); @@ -121,7 +122,8 @@ static int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb) xtend_desc->retry_cnt = PROBE_RESP_RETRY_CNT; } - if ((vif->type == NL80211_IFTYPE_AP) && + if (((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO)) && (ieee80211_is_action(wh->frame_control))) { struct rsi_sta *rsta = rsi_find_sta(common, wh->addr1); @@ -130,6 +132,10 @@ static int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb) else return -EINVAL; } + mgmt_desc->rate_info |= + cpu_to_le16((tx_params->vap_id << RSI_DESC_VAP_ID_OFST) & + RSI_DESC_VAP_ID_MASK); + return 0; } @@ -151,7 +157,8 @@ static int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb) u16 seq_num; info = IEEE80211_SKB_CB(skb); - bss = &info->control.vif->bss_conf; + vif = info->control.vif; + bss = &vif->bss_conf; tx_params = (struct skb_info *)info->driver_data; header_size = FRAME_DESC_SZ + sizeof(struct xtended_desc); @@ -175,7 +182,6 @@ static int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb) xtend_desc = (struct xtended_desc *)&skb->data[FRAME_DESC_SZ]; wh = (struct ieee80211_hdr *)&skb->data[header_size]; seq_num = IEEE80211_SEQ_TO_SN(le16_to_cpu(wh->seq_ctrl)); - vif = adapter->vifs[0]; data_desc->xtend_desc_size = header_size - FRAME_DESC_SZ; @@ -184,7 +190,8 @@ static int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb) data_desc->mac_flags |= cpu_to_le16(RSI_QOS_ENABLE); } - if ((vif->type == NL80211_IFTYPE_STATION) && + if (((vif->type == NL80211_IFTYPE_STATION) || + (vif->type == NL80211_IFTYPE_P2P_CLIENT)) && (adapter->ps_state == PS_ENABLED)) wh->frame_control |= cpu_to_le16(RSI_SET_PS_ENABLE); @@ -240,17 +247,23 @@ static int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb) data_desc->frame_info |= cpu_to_le16(RSI_BROADCAST_PKT); data_desc->sta_id = vap_id; - if (vif->type == NL80211_IFTYPE_AP) { + if ((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO)) { if (common->band == NL80211_BAND_5GHZ) data_desc->rate_info = cpu_to_le16(RSI_RATE_6); else data_desc->rate_info = cpu_to_le16(RSI_RATE_1); } } - if ((vif->type == NL80211_IFTYPE_AP) && + if (((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO)) && (ieee80211_has_moredata(wh->frame_control))) data_desc->frame_info |= cpu_to_le16(MORE_DATA_PRESENT); + data_desc->rate_info |= + cpu_to_le16((tx_params->vap_id << RSI_DESC_VAP_ID_OFST) & + RSI_DESC_VAP_ID_MASK); + return 0; } @@ -258,7 +271,7 @@ static int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb) int rsi_send_data_pkt(struct rsi_common *common, struct sk_buff *skb) { struct rsi_hw *adapter = common->priv; - struct ieee80211_vif *vif = adapter->vifs[0]; + struct ieee80211_vif *vif; struct ieee80211_tx_info *info; struct ieee80211_bss_conf *bss; int status = -EINVAL; @@ -271,9 +284,12 @@ int rsi_send_data_pkt(struct rsi_common *common, struct sk_buff *skb) info = IEEE80211_SKB_CB(skb); if (!info->control.vif) goto err; - bss = &info->control.vif->bss_conf; + vif = info->control.vif; + bss = &vif->bss_conf; - if ((vif->type == NL80211_IFTYPE_STATION) && (!bss->assoc)) + if (((vif->type == NL80211_IFTYPE_STATION) || + (vif->type == NL80211_IFTYPE_P2P_CLIENT)) && + (!bss->assoc)) goto err; status = rsi_prepare_data_desc(common, skb); @@ -306,21 +322,11 @@ int rsi_send_mgmt_pkt(struct rsi_common *common, struct ieee80211_tx_info *info; struct skb_info *tx_params; int status = -E2BIG; - u8 extnd_size; info = IEEE80211_SKB_CB(skb); tx_params = (struct skb_info *)info->driver_data; - extnd_size = ((uintptr_t)skb->data & 0x3); if (tx_params->flags & INTERNAL_MGMT_PKT) { - skb->data[1] |= BIT(7); /* Immediate Wakeup bit*/ - if ((extnd_size) > skb_headroom(skb)) { - rsi_dbg(ERR_ZONE, "%s: Unable to send pkt\n", __func__); - dev_kfree_skb(skb); - return -ENOSPC; - } - skb_push(skb, extnd_size); - skb->data[extnd_size + 4] = extnd_size; status = adapter->host_intf_ops->write_pkt(common->priv, (u8 *)skb->data, skb->len); @@ -352,12 +358,23 @@ int rsi_prepare_beacon(struct rsi_common *common, struct sk_buff *skb) struct rsi_data_desc *bcn_frm; struct ieee80211_hw *hw = common->priv->hw; struct ieee80211_conf *conf = &hw->conf; + struct ieee80211_vif *vif; struct sk_buff *mac_bcn; - u8 vap_id = 0; - u16 tim_offset; - + u8 vap_id = 0, i; + u16 tim_offset = 0; + + for (i = 0; i < RSI_MAX_VIFS; i++) { + vif = adapter->vifs[i]; + if (!vif) + continue; + if ((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO)) + break; + } + if (!vif) + return -EINVAL; mac_bcn = ieee80211_beacon_get_tim(adapter->hw, - adapter->vifs[adapter->sc_nvifs - 1], + vif, &tim_offset, NULL); if (!mac_bcn) { rsi_dbg(ERR_ZONE, "Failed to get beacon from mac80211\n"); @@ -751,6 +768,7 @@ static int auto_fw_upgrade(struct rsi_hw *adapter, u8 *flash_content, static int rsi_load_firmware(struct rsi_hw *adapter) { + struct rsi_common *common = adapter->priv; struct rsi_host_intf_ops *hif_ops = adapter->host_intf_ops; const struct firmware *fw_entry = NULL; u32 regout_val = 0, content_size; @@ -826,6 +844,18 @@ static int rsi_load_firmware(struct rsi_hw *adapter) content_size = fw_entry->size; rsi_dbg(INFO_ZONE, "FW Length = %d bytes\n", content_size); + /* Get the firmware version */ + common->lmac_ver.ver.info.fw_ver[0] = + flash_content[LMAC_VER_OFFSET] & 0xFF; + common->lmac_ver.ver.info.fw_ver[1] = + flash_content[LMAC_VER_OFFSET + 1] & 0xFF; + common->lmac_ver.major = flash_content[LMAC_VER_OFFSET + 2] & 0xFF; + common->lmac_ver.release_num = + flash_content[LMAC_VER_OFFSET + 3] & 0xFF; + common->lmac_ver.minor = flash_content[LMAC_VER_OFFSET + 4] & 0xFF; + common->lmac_ver.patch_num = 0; + rsi_print_version(common); + status = bl_write_header(adapter, flash_content, content_size); if (status) { rsi_dbg(ERR_ZONE, diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c index fa12c05d9e23..b1f5dbbde3cb 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c +++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c @@ -139,6 +139,32 @@ static const u32 rsi_max_ap_stas[16] = { 4, /* 14 - AP + BT Dual */ }; +static const struct ieee80211_iface_limit rsi_iface_limits[] = { + { + .max = 1, + .types = BIT(NL80211_IFTYPE_STATION), + }, + { + .max = 1, + .types = BIT(NL80211_IFTYPE_AP) | + BIT(NL80211_IFTYPE_P2P_CLIENT) | + BIT(NL80211_IFTYPE_P2P_GO), + }, + { + .max = 1, + .types = BIT(NL80211_IFTYPE_P2P_DEVICE), + }, +}; + +static const struct ieee80211_iface_combination rsi_iface_combinations[] = { + { + .num_different_channels = 1, + .max_interfaces = 3, + .limits = rsi_iface_limits, + .n_limits = ARRAY_SIZE(rsi_iface_limits), + }, +}; + /** * rsi_is_cipher_wep() - This function determines if the cipher is WEP or not. * @common: Pointer to the driver private structure. @@ -329,6 +355,24 @@ static void rsi_mac80211_stop(struct ieee80211_hw *hw) mutex_unlock(&common->mutex); } +static int rsi_map_intf_mode(enum nl80211_iftype vif_type) +{ + switch (vif_type) { + case NL80211_IFTYPE_STATION: + return RSI_OPMODE_STA; + case NL80211_IFTYPE_AP: + return RSI_OPMODE_AP; + case NL80211_IFTYPE_P2P_DEVICE: + return RSI_OPMODE_P2P_CLIENT; + case NL80211_IFTYPE_P2P_CLIENT: + return RSI_OPMODE_P2P_CLIENT; + case NL80211_IFTYPE_P2P_GO: + return RSI_OPMODE_P2P_GO; + default: + return RSI_OPMODE_UNSUPPORTED; + } +} + /** * rsi_mac80211_add_interface() - This function is called when a netdevice * attached to the hardware is enabled. @@ -342,54 +386,62 @@ static int rsi_mac80211_add_interface(struct ieee80211_hw *hw, { struct rsi_hw *adapter = hw->priv; struct rsi_common *common = adapter->priv; + struct vif_priv *vif_info = (struct vif_priv *)vif->drv_priv; enum opmode intf_mode; - int ret = -EOPNOTSUPP; + enum vap_status vap_status; + int vap_idx = -1, i; vif->driver_flags |= IEEE80211_VIF_SUPPORTS_UAPSD; mutex_lock(&common->mutex); - if (adapter->sc_nvifs > 1) { - mutex_unlock(&common->mutex); - return -EOPNOTSUPP; - } - - switch (vif->type) { - case NL80211_IFTYPE_STATION: - rsi_dbg(INFO_ZONE, "Station Mode"); - intf_mode = STA_OPMODE; - break; - case NL80211_IFTYPE_AP: - rsi_dbg(INFO_ZONE, "AP Mode"); - intf_mode = AP_OPMODE; - break; - default: + intf_mode = rsi_map_intf_mode(vif->type); + if (intf_mode == RSI_OPMODE_UNSUPPORTED) { rsi_dbg(ERR_ZONE, "%s: Interface type %d not supported\n", __func__, vif->type); - goto out; + mutex_unlock(&common->mutex); + return -EOPNOTSUPP; + } + if ((vif->type == NL80211_IFTYPE_P2P_DEVICE) || + (vif->type == NL80211_IFTYPE_P2P_CLIENT) || + (vif->type == NL80211_IFTYPE_P2P_GO)) + common->p2p_enabled = true; + + /* Get free vap index */ + for (i = 0; i < RSI_MAX_VIFS; i++) { + if (!adapter->vifs[i]) { + vap_idx = i; + break; + } + } + if (vap_idx < 0) { + rsi_dbg(ERR_ZONE, "Reject: Max VAPs reached\n"); + mutex_unlock(&common->mutex); + return -EOPNOTSUPP; } + vif_info->vap_id = vap_idx; + adapter->vifs[vap_idx] = vif; + adapter->sc_nvifs++; + vap_status = VAP_ADD; - adapter->vifs[adapter->sc_nvifs++] = vif; - ret = rsi_set_vap_capabilities(common, intf_mode, common->mac_addr, - 0, VAP_ADD); - if (ret) { + if (rsi_set_vap_capabilities(common, intf_mode, vif->addr, + vif_info->vap_id, vap_status)) { rsi_dbg(ERR_ZONE, "Failed to set VAP capabilities\n"); - goto out; + mutex_unlock(&common->mutex); + return -EINVAL; } - if (vif->type == NL80211_IFTYPE_AP) { - int i; - + if ((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO)) { rsi_send_rx_filter_frame(common, DISALLOW_BEACONS); common->min_rate = RSI_RATE_AUTO; for (i = 0; i < common->max_stations; i++) common->stations[i].sta = NULL; } -out: mutex_unlock(&common->mutex); - return ret; + return 0; } /** @@ -406,6 +458,7 @@ static void rsi_mac80211_remove_interface(struct ieee80211_hw *hw, struct rsi_hw *adapter = hw->priv; struct rsi_common *common = adapter->priv; enum opmode opmode; + int i; rsi_dbg(INFO_ZONE, "Remove Interface Called\n"); @@ -416,23 +469,22 @@ static void rsi_mac80211_remove_interface(struct ieee80211_hw *hw, return; } - switch (vif->type) { - case NL80211_IFTYPE_STATION: - opmode = STA_OPMODE; - break; - case NL80211_IFTYPE_AP: - opmode = AP_OPMODE; - break; - default: + opmode = rsi_map_intf_mode(vif->type); + if (opmode == RSI_OPMODE_UNSUPPORTED) { + rsi_dbg(ERR_ZONE, "Opmode error : %d\n", opmode); mutex_unlock(&common->mutex); return; } - rsi_set_vap_capabilities(common, opmode, vif->addr, - 0, VAP_DELETE); - adapter->sc_nvifs--; - - if (!memcmp(adapter->vifs[0], vif, sizeof(struct ieee80211_vif))) - adapter->vifs[0] = NULL; + for (i = 0; i < RSI_MAX_VIFS; i++) { + if (!adapter->vifs[i]) + continue; + if (vif == adapter->vifs[i]) { + rsi_set_vap_capabilities(common, opmode, vif->addr, + i, VAP_DELETE); + adapter->sc_nvifs--; + adapter->vifs[i] = NULL; + } + } mutex_unlock(&common->mutex); } @@ -451,35 +503,44 @@ static int rsi_channel_change(struct ieee80211_hw *hw) int status = -EOPNOTSUPP; struct ieee80211_channel *curchan = hw->conf.chandef.chan; u16 channel = curchan->hw_value; - struct ieee80211_bss_conf *bss = &adapter->vifs[0]->bss_conf; + struct ieee80211_vif *vif; + struct ieee80211_bss_conf *bss; + bool assoc = false; + int i; rsi_dbg(INFO_ZONE, "%s: Set channel: %d MHz type: %d channel_no %d\n", __func__, curchan->center_freq, curchan->flags, channel); - if (bss->assoc) { + for (i = 0; i < RSI_MAX_VIFS; i++) { + vif = adapter->vifs[i]; + if (!vif) + continue; + if (vif->type == NL80211_IFTYPE_STATION) { + bss = &vif->bss_conf; + if (bss->assoc) { + assoc = true; + break; + } + } + } + if (assoc) { if (!common->hw_data_qs_blocked && - (rsi_get_connected_channel(adapter) != channel)) { + (rsi_get_connected_channel(vif) != channel)) { rsi_dbg(INFO_ZONE, "blk data q %d\n", channel); if (!rsi_send_block_unblock_frame(common, true)) common->hw_data_qs_blocked = true; } } - status = rsi_band_check(common); + status = rsi_band_check(common, curchan); if (!status) status = rsi_set_channel(adapter->priv, curchan); - if (bss->assoc) { + if (assoc) { if (common->hw_data_qs_blocked && - (rsi_get_connected_channel(adapter) == channel)) { - rsi_dbg(INFO_ZONE, "unblk data q %d\n", channel); - if (!rsi_send_block_unblock_frame(common, false)) - common->hw_data_qs_blocked = false; - } - } else { - if (common->hw_data_qs_blocked) { + (rsi_get_connected_channel(vif) == channel)) { rsi_dbg(INFO_ZONE, "unblk data q %d\n", channel); if (!rsi_send_block_unblock_frame(common, false)) common->hw_data_qs_blocked = false; @@ -531,7 +592,6 @@ static int rsi_mac80211_config(struct ieee80211_hw *hw, { struct rsi_hw *adapter = hw->priv; struct rsi_common *common = adapter->priv; - struct ieee80211_vif *vif = adapter->vifs[0]; struct ieee80211_conf *conf = &hw->conf; int status = -EOPNOTSUPP; @@ -547,16 +607,30 @@ static int rsi_mac80211_config(struct ieee80211_hw *hw, } /* Power save parameters */ - if ((changed & IEEE80211_CONF_CHANGE_PS) && - (vif->type == NL80211_IFTYPE_STATION)) { + if (changed & IEEE80211_CONF_CHANGE_PS) { + struct ieee80211_vif *vif; unsigned long flags; + int i, set_ps = 1; - spin_lock_irqsave(&adapter->ps_lock, flags); - if (conf->flags & IEEE80211_CONF_PS) - rsi_enable_ps(adapter); - else - rsi_disable_ps(adapter); - spin_unlock_irqrestore(&adapter->ps_lock, flags); + for (i = 0; i < RSI_MAX_VIFS; i++) { + vif = adapter->vifs[i]; + if (!vif) + continue; + /* Don't go to power save if AP vap exists */ + if ((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO)) { + set_ps = 0; + break; + } + } + if (set_ps) { + spin_lock_irqsave(&adapter->ps_lock, flags); + if (conf->flags & IEEE80211_CONF_PS) + rsi_enable_ps(adapter, vif); + else + rsi_disable_ps(adapter, vif); + spin_unlock_irqrestore(&adapter->ps_lock, flags); + } } /* RTS threshold */ @@ -580,16 +654,42 @@ static int rsi_mac80211_config(struct ieee80211_hw *hw, * * Return: Current connected AP's channel number is returned. */ -u16 rsi_get_connected_channel(struct rsi_hw *adapter) +u16 rsi_get_connected_channel(struct ieee80211_vif *vif) { - struct ieee80211_vif *vif = adapter->vifs[0]; - if (vif) { - struct ieee80211_bss_conf *bss = &vif->bss_conf; - struct ieee80211_channel *channel = bss->chandef.chan; - return channel->hw_value; - } + struct ieee80211_bss_conf *bss; + struct ieee80211_channel *channel; - return 0; + if (!vif) + return 0; + + bss = &vif->bss_conf; + channel = bss->chandef.chan; + + if (!channel) + return 0; + + return channel->hw_value; +} + +static void rsi_switch_channel(struct rsi_hw *adapter, + struct ieee80211_vif *vif) +{ + struct rsi_common *common = adapter->priv; + struct ieee80211_channel *channel; + + if (common->iface_down) + return; + if (!vif) + return; + + channel = vif->bss_conf.chandef.chan; + + if (!channel) + return; + + rsi_band_check(common, channel); + rsi_set_channel(common, channel); + rsi_dbg(INFO_ZONE, "Switched to channel - %d\n", channel->hw_value); } /** @@ -626,12 +726,12 @@ static void rsi_mac80211_bss_info_changed(struct ieee80211_hw *hw, rsi_send_rx_filter_frame(common, rx_filter_word); } rsi_inform_bss_status(common, - STA_OPMODE, + RSI_OPMODE_STA, bss_conf->assoc, bss_conf->bssid, bss_conf->qos, bss_conf->aid, - NULL, 0); + NULL, 0, vif); adapter->ps_info.dtim_interval_duration = bss->dtim_period; adapter->ps_info.listen_interval = conf->listen_interval; @@ -639,7 +739,7 @@ static void rsi_mac80211_bss_info_changed(struct ieee80211_hw *hw, if (bss->assoc) { if (common->uapsd_bitmap) { rsi_dbg(INFO_ZONE, "Configuring UAPSD\n"); - rsi_conf_uapsd(adapter); + rsi_conf_uapsd(adapter, vif); } } else { common->uapsd_bitmap = 0; @@ -656,7 +756,8 @@ static void rsi_mac80211_bss_info_changed(struct ieee80211_hw *hw, } if ((changed & BSS_CHANGED_BEACON_ENABLED) && - (vif->type == NL80211_IFTYPE_AP)) { + ((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO))) { if (bss->enable_beacon) { rsi_dbg(INFO_ZONE, "===> BEACON ENABLED <===\n"); common->beacon_enabled = 1; @@ -775,7 +876,8 @@ static int rsi_hal_key_config(struct ieee80211_hw *hw, rsi_dbg(ERR_ZONE, "%s: Cipher 0x%x key_type: %d key_len: %d\n", __func__, key->cipher, key_type, key->keylen); - if (vif->type == NL80211_IFTYPE_AP) { + if ((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO)) { if (sta) { rsta = rsi_find_sta(adapter->priv, sta->addr); if (rsta) @@ -791,7 +893,8 @@ static int rsi_hal_key_config(struct ieee80211_hw *hw, RSI_PAIRWISE_KEY, key->keyidx, key->cipher, - sta_id); + sta_id, + vif); if (status) return status; } @@ -803,7 +906,8 @@ static int rsi_hal_key_config(struct ieee80211_hw *hw, key_type, key->keyidx, key->cipher, - sta_id); + sta_id, + vif); } /** @@ -902,7 +1006,8 @@ static int rsi_mac80211_ampdu_action(struct ieee80211_hw *hw, if (ssn != NULL) seq_no = *ssn; - if (vif->type == NL80211_IFTYPE_AP) { + if ((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO)) { rsta = rsi_find_sta(common, sta->addr); if (!rsta) { rsi_dbg(ERR_ZONE, "No station mapped\n"); @@ -936,9 +1041,11 @@ static int rsi_mac80211_ampdu_action(struct ieee80211_hw *hw, break; case IEEE80211_AMPDU_TX_START: - if (vif->type == NL80211_IFTYPE_STATION) + if ((vif->type == NL80211_IFTYPE_STATION) || + (vif->type == NL80211_IFTYPE_P2P_CLIENT)) common->vif_info[ii].seq_start = seq_no; - else if (vif->type == NL80211_IFTYPE_AP) + else if ((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO)) rsta->seq_start[tid] = seq_no; ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid); status = 0; @@ -958,9 +1065,11 @@ static int rsi_mac80211_ampdu_action(struct ieee80211_hw *hw, break; case IEEE80211_AMPDU_TX_OPERATIONAL: - if (vif->type == NL80211_IFTYPE_STATION) + if ((vif->type == NL80211_IFTYPE_STATION) || + (vif->type == NL80211_IFTYPE_P2P_CLIENT)) seq_start = common->vif_info[ii].seq_start; - else if (vif->type == NL80211_IFTYPE_AP) + else if ((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO)) seq_start = rsta->seq_start[tid]; status = rsi_send_aggregation_params_frame(common, tid, @@ -1039,9 +1148,9 @@ static int rsi_mac80211_set_rate_mask(struct ieee80211_hw *hw, */ static void rsi_perform_cqm(struct rsi_common *common, u8 *bssid, - s8 rssi) + s8 rssi, + struct ieee80211_vif *vif) { - struct rsi_hw *adapter = common->priv; s8 last_event = common->cqm_info.last_cqm_event_rssi; int thold = common->cqm_info.rssi_thold; u32 hyst = common->cqm_info.rssi_hyst; @@ -1057,7 +1166,7 @@ static void rsi_perform_cqm(struct rsi_common *common, common->cqm_info.last_cqm_event_rssi = rssi; rsi_dbg(INFO_ZONE, "CQM: Notifying event: %d\n", event); - ieee80211_cqm_rssi_notify(adapter->vifs[0], event, rssi, GFP_KERNEL); + ieee80211_cqm_rssi_notify(vif, event, rssi, GFP_KERNEL); return; } @@ -1077,7 +1186,9 @@ static void rsi_fill_rx_status(struct ieee80211_hw *hw, struct rsi_common *common, struct ieee80211_rx_status *rxs) { - struct ieee80211_bss_conf *bss = &common->priv->vifs[0]->bss_conf; + struct rsi_hw *adapter = common->priv; + struct ieee80211_vif *vif; + struct ieee80211_bss_conf *bss = NULL; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct skb_info *rx_params = (struct skb_info *)info->driver_data; struct ieee80211_hdr *hdr; @@ -1085,6 +1196,7 @@ static void rsi_fill_rx_status(struct ieee80211_hw *hw, u8 hdrlen = 0; u8 channel = rx_params->channel; s32 freq; + int i; hdr = ((struct ieee80211_hdr *)(skb->data)); hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -1113,10 +1225,21 @@ static void rsi_fill_rx_status(struct ieee80211_hw *hw, rxs->flag |= RX_FLAG_IV_STRIPPED; } + for (i = 0; i < RSI_MAX_VIFS; i++) { + vif = adapter->vifs[i]; + if (!vif) + continue; + if (vif->type == NL80211_IFTYPE_STATION) { + bss = &vif->bss_conf; + break; + } + } + if (!bss) + return; /* CQM only for connected AP beacons, the RSSI is a weighted avg */ if (bss->assoc && !(memcmp(bss->bssid, hdr->addr2, ETH_ALEN))) { if (ieee80211_is_beacon(hdr->frame_control)) - rsi_perform_cqm(common, hdr->addr2, rxs->signal); + rsi_perform_cqm(common, hdr->addr2, rxs->signal, vif); } return; @@ -1210,7 +1333,8 @@ static int rsi_mac80211_sta_add(struct ieee80211_hw *hw, mutex_lock(&common->mutex); - if (vif->type == NL80211_IFTYPE_AP) { + if ((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO)) { u8 cnt; int sta_idx = -1; int free_index = -1; @@ -1259,8 +1383,9 @@ static int rsi_mac80211_sta_add(struct ieee80211_hw *hw, /* Send peer notify to device */ rsi_dbg(INFO_ZONE, "Indicate bss status to device\n"); - rsi_inform_bss_status(common, AP_OPMODE, 1, sta->addr, - sta->wme, sta->aid, sta, sta_idx); + rsi_inform_bss_status(common, RSI_OPMODE_AP, 1, + sta->addr, sta->wme, sta->aid, + sta, sta_idx, vif); if (common->key) { struct ieee80211_key_conf *key = common->key; @@ -1273,14 +1398,16 @@ static int rsi_mac80211_sta_add(struct ieee80211_hw *hw, RSI_PAIRWISE_KEY, key->keyidx, key->cipher, - sta_idx); + sta_idx, + vif); } common->num_stations++; } } - if (vif->type == NL80211_IFTYPE_STATION) { + if ((vif->type == NL80211_IFTYPE_STATION) || + (vif->type == NL80211_IFTYPE_P2P_CLIENT)) { rsi_set_min_rate(hw, sta, common); if (sta->ht_cap.ht_supported) { common->vif_info[0].is_ht = true; @@ -1321,7 +1448,8 @@ static int rsi_mac80211_sta_remove(struct ieee80211_hw *hw, mutex_lock(&common->mutex); - if (vif->type == NL80211_IFTYPE_AP) { + if ((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO)) { u8 sta_idx, cnt; /* Send peer notify to device */ @@ -1332,9 +1460,10 @@ static int rsi_mac80211_sta_remove(struct ieee80211_hw *hw, if (!rsta->sta) continue; if (!memcmp(rsta->sta->addr, sta->addr, ETH_ALEN)) { - rsi_inform_bss_status(common, AP_OPMODE, 0, + rsi_inform_bss_status(common, RSI_OPMODE_AP, 0, sta->addr, sta->wme, - sta->aid, sta, sta_idx); + sta->aid, sta, sta_idx, + vif); rsta->sta = NULL; rsta->sta_id = -1; for (cnt = 0; cnt < IEEE80211_NUM_TIDS; cnt++) @@ -1348,7 +1477,8 @@ static int rsi_mac80211_sta_remove(struct ieee80211_hw *hw, rsi_dbg(ERR_ZONE, "%s: No station found\n", __func__); } - if (vif->type == NL80211_IFTYPE_STATION) { + if ((vif->type == NL80211_IFTYPE_STATION) || + (vif->type == NL80211_IFTYPE_P2P_CLIENT)) { /* Resetting all the fields to default values */ memcpy((u8 *)bss->bssid, (u8 *)sta->addr, ETH_ALEN); bss->qos = sta->wme; @@ -1508,6 +1638,114 @@ static void rsi_mac80211_rfkill_poll(struct ieee80211_hw *hw) mutex_unlock(&common->mutex); } +static void rsi_resume_conn_channel(struct rsi_common *common) +{ + struct rsi_hw *adapter = common->priv; + struct ieee80211_vif *vif; + int cnt; + + for (cnt = 0; cnt < RSI_MAX_VIFS; cnt++) { + vif = adapter->vifs[cnt]; + if (!vif) + continue; + + if ((vif->type == NL80211_IFTYPE_AP) || + (vif->type == NL80211_IFTYPE_P2P_GO)) { + rsi_switch_channel(adapter, vif); + break; + } + if (((vif->type == NL80211_IFTYPE_STATION) || + (vif->type == NL80211_IFTYPE_P2P_CLIENT)) && + vif->bss_conf.assoc) { + rsi_switch_channel(adapter, vif); + break; + } + } +} + +void rsi_roc_timeout(unsigned long data) +{ + struct rsi_common *common = (struct rsi_common *)data; + + rsi_dbg(INFO_ZONE, "Remain on channel expired\n"); + + mutex_lock(&common->mutex); + ieee80211_remain_on_channel_expired(common->priv->hw); + + if (timer_pending(&common->roc_timer)) + del_timer(&common->roc_timer); + + rsi_resume_conn_channel(common); + mutex_unlock(&common->mutex); +} + +static int rsi_mac80211_roc(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct ieee80211_channel *chan, int duration, + enum ieee80211_roc_type type) +{ + struct rsi_hw *adapter = (struct rsi_hw *)hw->priv; + struct rsi_common *common = (struct rsi_common *)adapter->priv; + int status = 0; + + rsi_dbg(INFO_ZONE, "***** Remain on channel *****\n"); + + mutex_lock(&common->mutex); + rsi_dbg(INFO_ZONE, "%s: channel: %d duration: %dms\n", + __func__, chan->hw_value, duration); + + if (timer_pending(&common->roc_timer)) { + rsi_dbg(INFO_ZONE, "Stop on-going ROC\n"); + del_timer(&common->roc_timer); + } + common->roc_timer.expires = msecs_to_jiffies(duration) + jiffies; + add_timer(&common->roc_timer); + + /* Configure band */ + if (rsi_band_check(common, chan)) { + rsi_dbg(ERR_ZONE, "Failed to set band\n"); + status = -EINVAL; + goto out; + } + + /* Configure channel */ + if (rsi_set_channel(common, chan)) { + rsi_dbg(ERR_ZONE, "Failed to set the channel\n"); + status = -EINVAL; + goto out; + } + + common->roc_vif = vif; + ieee80211_ready_on_channel(hw); + rsi_dbg(INFO_ZONE, "%s: Ready on channel :%d\n", + __func__, chan->hw_value); + +out: + mutex_unlock(&common->mutex); + + return status; +} + +static int rsi_mac80211_cancel_roc(struct ieee80211_hw *hw) +{ + struct rsi_hw *adapter = hw->priv; + struct rsi_common *common = adapter->priv; + + rsi_dbg(INFO_ZONE, "Cancel remain on channel\n"); + + mutex_lock(&common->mutex); + if (!timer_pending(&common->roc_timer)) { + mutex_unlock(&common->mutex); + return 0; + } + + del_timer(&common->roc_timer); + + rsi_resume_conn_channel(common); + mutex_unlock(&common->mutex); + + return 0; +} + static const struct ieee80211_ops mac80211_ops = { .tx = rsi_mac80211_tx, .start = rsi_mac80211_start, @@ -1527,6 +1765,8 @@ static const struct ieee80211_ops mac80211_ops = { .set_antenna = rsi_mac80211_set_antenna, .get_antenna = rsi_mac80211_get_antenna, .rfkill_poll = rsi_mac80211_rfkill_poll, + .remain_on_channel = rsi_mac80211_roc, + .cancel_remain_on_channel = rsi_mac80211_cancel_roc, }; /** @@ -1581,7 +1821,11 @@ int rsi_mac80211_attach(struct rsi_common *common) ether_addr_copy(hw->wiphy->addr_mask, addr_mask); wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) | - BIT(NL80211_IFTYPE_AP); + BIT(NL80211_IFTYPE_AP) | + BIT(NL80211_IFTYPE_P2P_DEVICE) | + BIT(NL80211_IFTYPE_P2P_CLIENT) | + BIT(NL80211_IFTYPE_P2P_GO); + wiphy->signal_type = CFG80211_SIGNAL_TYPE_MBM; wiphy->retry_short = RETRY_SHORT; wiphy->retry_long = RETRY_LONG; @@ -1608,6 +1852,14 @@ int rsi_mac80211_attach(struct rsi_common *common) wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST); + /* Wi-Fi direct parameters */ + wiphy->flags |= WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL; + wiphy->flags |= WIPHY_FLAG_OFFCHAN_TX; + wiphy->max_remain_on_channel_duration = 10000; + hw->max_listen_interval = 10; + wiphy->iface_combinations = rsi_iface_combinations; + wiphy->n_iface_combinations = ARRAY_SIZE(rsi_iface_combinations); + status = ieee80211_register_hw(hw); if (status) return status; diff --git a/drivers/net/wireless/rsi/rsi_91x_main.c b/drivers/net/wireless/rsi/rsi_91x_main.c index 3e1e80888d98..71b8cfb8252e 100644 --- a/drivers/net/wireless/rsi/rsi_91x_main.c +++ b/drivers/net/wireless/rsi/rsi_91x_main.c @@ -20,6 +20,7 @@ #include <linux/firmware.h> #include "rsi_mgmt.h" #include "rsi_common.h" +#include "rsi_hal.h" u32 rsi_zone_enabled = /* INFO_ZONE | INIT_ZONE | @@ -56,6 +57,30 @@ void rsi_dbg(u32 zone, const char *fmt, ...) } EXPORT_SYMBOL_GPL(rsi_dbg); +static char *opmode_str(int oper_mode) +{ + switch (oper_mode) { + case RSI_DEV_OPMODE_WIFI_ALONE: + return "Wi-Fi alone"; + } + + return "Unknown"; +} + +void rsi_print_version(struct rsi_common *common) +{ + rsi_dbg(ERR_ZONE, "================================================\n"); + rsi_dbg(ERR_ZONE, "================ RSI Version Info ==============\n"); + rsi_dbg(ERR_ZONE, "================================================\n"); + rsi_dbg(ERR_ZONE, "FW Version\t: %d.%d.%d\n", + common->lmac_ver.major, common->lmac_ver.minor, + common->lmac_ver.release_num); + rsi_dbg(ERR_ZONE, "Operating mode\t: %d [%s]", + common->oper_mode, opmode_str(common->oper_mode)); + rsi_dbg(ERR_ZONE, "Firmware file\t: %s", common->priv->fw_file_name); + rsi_dbg(ERR_ZONE, "================================================\n"); +} + /** * rsi_prepare_skb() - This function prepares the skb. * @common: Pointer to the driver private structure. @@ -74,6 +99,8 @@ static struct sk_buff *rsi_prepare_skb(struct rsi_common *common, struct skb_info *rx_params; struct sk_buff *skb = NULL; u8 payload_offset; + struct ieee80211_vif *vif; + struct ieee80211_hdr *wh; if (WARN(!pkt_len, "%s: Dummy pkt received", __func__)) return NULL; @@ -92,11 +119,13 @@ static struct sk_buff *rsi_prepare_skb(struct rsi_common *common, payload_offset = (extended_desc + FRAME_DESC_SZ); skb_put(skb, pkt_len); memcpy((skb->data), (buffer + payload_offset), skb->len); + wh = (struct ieee80211_hdr *)skb->data; + vif = rsi_get_vif(common->priv, wh->addr1); info = IEEE80211_SKB_CB(skb); rx_params = (struct skb_info *)info->driver_data; rx_params->rssi = rsi_get_rssi(buffer); - rx_params->channel = rsi_get_connected_channel(common->priv); + rx_params->channel = rsi_get_connected_channel(vif); return skb; } @@ -233,6 +262,9 @@ struct rsi_hw *rsi_91x_init(void) rsi_default_ps_params(adapter); spin_lock_init(&adapter->ps_lock); + common->roc_timer.data = (unsigned long)common; + common->roc_timer.function = (void *)&rsi_roc_timeout; + init_timer(&common->roc_timer); common->init_done = true; return adapter; diff --git a/drivers/net/wireless/rsi/rsi_91x_mgmt.c b/drivers/net/wireless/rsi/rsi_91x_mgmt.c index f7b550f900c4..4b94190c9797 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mgmt.c +++ b/drivers/net/wireless/rsi/rsi_91x_mgmt.c @@ -460,12 +460,12 @@ static int rsi_hal_send_sta_notify_frame(struct rsi_common *common, const unsigned char *bssid, u8 qos_enable, u16 aid, - u16 sta_id) + u16 sta_id, + struct ieee80211_vif *vif) { - struct ieee80211_vif *vif = common->priv->vifs[0]; struct sk_buff *skb = NULL; struct rsi_peer_notify *peer_notify; - u16 vap_id = 0; + u16 vap_id = ((struct vif_priv *)vif->drv_priv)->vap_id; int status; u16 frame_len = sizeof(struct rsi_peer_notify); @@ -482,9 +482,9 @@ static int rsi_hal_send_sta_notify_frame(struct rsi_common *common, memset(skb->data, 0, frame_len); peer_notify = (struct rsi_peer_notify *)skb->data; - if (opmode == STA_OPMODE) + if (opmode == RSI_OPMODE_STA) peer_notify->command = cpu_to_le16(PEER_TYPE_AP << 1); - else if (opmode == AP_OPMODE) + else if (opmode == RSI_OPMODE_AP) peer_notify->command = cpu_to_le16(PEER_TYPE_STA << 1); switch (notify_event) { @@ -716,9 +716,9 @@ int rsi_hal_load_key(struct rsi_common *common, u8 key_type, u8 key_id, u32 cipher, - s16 sta_id) + s16 sta_id, + struct ieee80211_vif *vif) { - struct ieee80211_vif *vif = common->priv->vifs[0]; struct sk_buff *skb = NULL; struct rsi_set_key *set_key; u16 key_descriptor = 0; @@ -926,13 +926,13 @@ static int rsi_send_reset_mac(struct rsi_common *common) * * Return: 0 on success, corresponding error code on failure. */ -int rsi_band_check(struct rsi_common *common) +int rsi_band_check(struct rsi_common *common, + struct ieee80211_channel *curchan) { struct rsi_hw *adapter = common->priv; struct ieee80211_hw *hw = adapter->hw; u8 prev_bw = common->channel_width; u8 prev_ep = common->endpoint; - struct ieee80211_channel *curchan = hw->conf.chandef.chan; int status = 0; if (common->band != curchan->band) { @@ -1160,9 +1160,9 @@ static bool rsi_map_rates(u16 rate, int *offset) */ static int rsi_send_auto_rate_request(struct rsi_common *common, struct ieee80211_sta *sta, - u16 sta_id) + u16 sta_id, + struct ieee80211_vif *vif) { - struct ieee80211_vif *vif = common->priv->vifs[0]; struct sk_buff *skb; struct rsi_auto_rate *auto_rate; int ii = 0, jj = 0, kk = 0; @@ -1318,33 +1318,36 @@ void rsi_inform_bss_status(struct rsi_common *common, u8 qos_enable, u16 aid, struct ieee80211_sta *sta, - u16 sta_id) + u16 sta_id, + struct ieee80211_vif *vif) { if (status) { - if (opmode == STA_OPMODE) + if (opmode == RSI_OPMODE_STA) common->hw_data_qs_blocked = true; rsi_hal_send_sta_notify_frame(common, opmode, STA_CONNECTED, addr, qos_enable, - aid, sta_id); + aid, sta_id, + vif); if (common->min_rate == 0xffff) - rsi_send_auto_rate_request(common, sta, sta_id); - if (opmode == STA_OPMODE) { + rsi_send_auto_rate_request(common, sta, sta_id, vif); + if (opmode == RSI_OPMODE_STA) { if (!rsi_send_block_unblock_frame(common, false)) common->hw_data_qs_blocked = false; } } else { - if (opmode == STA_OPMODE) + if (opmode == RSI_OPMODE_STA) common->hw_data_qs_blocked = true; rsi_hal_send_sta_notify_frame(common, opmode, STA_DISCONNECTED, addr, qos_enable, - aid, sta_id); - if (opmode == STA_OPMODE) + aid, sta_id, + vif); + if (opmode == RSI_OPMODE_STA) rsi_send_block_unblock_frame(common, true); } } @@ -1471,10 +1474,11 @@ int rsi_send_rx_filter_frame(struct rsi_common *common, u16 rx_filter_word) return rsi_send_internal_mgmt_frame(common, skb); } -int rsi_send_ps_request(struct rsi_hw *adapter, bool enable) +int rsi_send_ps_request(struct rsi_hw *adapter, bool enable, + struct ieee80211_vif *vif) { struct rsi_common *common = adapter->priv; - struct ieee80211_bss_conf *bss = &adapter->vifs[0]->bss_conf; + struct ieee80211_bss_conf *bss = &vif->bss_conf; struct rsi_request_ps *ps; struct rsi_ps_info *ps_info; struct sk_buff *skb; diff --git a/drivers/net/wireless/rsi/rsi_91x_ps.c b/drivers/net/wireless/rsi/rsi_91x_ps.c index 48c79f035c59..523f5329d2b7 100644 --- a/drivers/net/wireless/rsi/rsi_91x_ps.c +++ b/drivers/net/wireless/rsi/rsi_91x_ps.c @@ -67,7 +67,7 @@ void rsi_default_ps_params(struct rsi_hw *adapter) ps_info->deep_sleep_wakeup_period = RSI_DEF_DS_WAKEUP_PERIOD; } -void rsi_enable_ps(struct rsi_hw *adapter) +void rsi_enable_ps(struct rsi_hw *adapter, struct ieee80211_vif *vif) { if (adapter->ps_state != PS_NONE) { rsi_dbg(ERR_ZONE, @@ -76,7 +76,7 @@ void rsi_enable_ps(struct rsi_hw *adapter) return; } - if (rsi_send_ps_request(adapter, true)) { + if (rsi_send_ps_request(adapter, true, vif)) { rsi_dbg(ERR_ZONE, "%s: Failed to send PS request to device\n", __func__); @@ -86,7 +86,8 @@ void rsi_enable_ps(struct rsi_hw *adapter) rsi_modify_ps_state(adapter, PS_ENABLE_REQ_SENT); } -void rsi_disable_ps(struct rsi_hw *adapter) +/* This function is used to disable power save */ +void rsi_disable_ps(struct rsi_hw *adapter, struct ieee80211_vif *vif) { if (adapter->ps_state != PS_ENABLED) { rsi_dbg(ERR_ZONE, @@ -95,7 +96,7 @@ void rsi_disable_ps(struct rsi_hw *adapter) return; } - if (rsi_send_ps_request(adapter, false)) { + if (rsi_send_ps_request(adapter, false, vif)) { rsi_dbg(ERR_ZONE, "%s: Failed to send PS request to device\n", __func__); @@ -105,16 +106,16 @@ void rsi_disable_ps(struct rsi_hw *adapter) rsi_modify_ps_state(adapter, PS_DISABLE_REQ_SENT); } -void rsi_conf_uapsd(struct rsi_hw *adapter) +void rsi_conf_uapsd(struct rsi_hw *adapter, struct ieee80211_vif *vif) { int ret; if (adapter->ps_state != PS_ENABLED) return; - ret = rsi_send_ps_request(adapter, false); + ret = rsi_send_ps_request(adapter, false, vif); if (!ret) - ret = rsi_send_ps_request(adapter, true); + ret = rsi_send_ps_request(adapter, true, vif); if (ret) rsi_dbg(ERR_ZONE, "%s: Failed to send PS request to device\n", diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio.c b/drivers/net/wireless/rsi/rsi_91x_sdio.c index 8d3a4839b6ef..b3f8006c0e9b 100644 --- a/drivers/net/wireless/rsi/rsi_91x_sdio.c +++ b/drivers/net/wireless/rsi/rsi_91x_sdio.c @@ -1059,16 +1059,136 @@ static void rsi_disconnect(struct sdio_func *pfunction) } #ifdef CONFIG_PM +static int rsi_set_sdio_pm_caps(struct rsi_hw *adapter) +{ + struct rsi_91x_sdiodev *dev = + (struct rsi_91x_sdiodev *)adapter->rsi_dev; + struct sdio_func *func = dev->pfunction; + int ret; + + ret = sdio_set_host_pm_flags(func, MMC_PM_KEEP_POWER); + if (ret) + rsi_dbg(ERR_ZONE, "Set sdio keep pwr flag failed: %d\n", ret); + + return ret; +} + +static int rsi_sdio_disable_interrupts(struct sdio_func *pfunc) +{ + struct rsi_hw *adapter = sdio_get_drvdata(pfunc); + u8 isr_status = 0, data = 0; + int ret; + unsigned long t1; + + rsi_dbg(INFO_ZONE, "Waiting for interrupts to be cleared.."); + t1 = jiffies; + do { + rsi_sdio_read_register(adapter, RSI_FN1_INT_REGISTER, + &isr_status); + rsi_dbg(INFO_ZONE, "."); + } while ((isr_status) && (jiffies_to_msecs(jiffies - t1) < 20)); + rsi_dbg(INFO_ZONE, "Interrupts cleared\n"); + + sdio_claim_host(pfunc); + ret = rsi_cmd52readbyte(pfunc->card, RSI_INT_ENABLE_REGISTER, &data); + if (ret < 0) { + rsi_dbg(ERR_ZONE, + "%s: Failed to read int enable register\n", + __func__); + goto done; + } + + data &= RSI_INT_ENABLE_MASK; + ret = rsi_cmd52writebyte(pfunc->card, RSI_INT_ENABLE_REGISTER, data); + if (ret < 0) { + rsi_dbg(ERR_ZONE, + "%s: Failed to write to int enable register\n", + __func__); + goto done; + } + ret = rsi_cmd52readbyte(pfunc->card, RSI_INT_ENABLE_REGISTER, &data); + if (ret < 0) { + rsi_dbg(ERR_ZONE, + "%s: Failed to read int enable register\n", + __func__); + goto done; + } + rsi_dbg(INFO_ZONE, "int enable reg content = %x\n", data); + +done: + sdio_release_host(pfunc); + return ret; +} + +static int rsi_sdio_enable_interrupts(struct sdio_func *pfunc) +{ + u8 data; + int ret; + + sdio_claim_host(pfunc); + ret = rsi_cmd52readbyte(pfunc->card, RSI_INT_ENABLE_REGISTER, &data); + if (ret < 0) { + rsi_dbg(ERR_ZONE, + "%s: Failed to read int enable register\n", __func__); + goto done; + } + + data |= ~RSI_INT_ENABLE_MASK & 0xff; + + ret = rsi_cmd52writebyte(pfunc->card, RSI_INT_ENABLE_REGISTER, data); + if (ret < 0) { + rsi_dbg(ERR_ZONE, + "%s: Failed to write to int enable register\n", + __func__); + goto done; + } + + ret = rsi_cmd52readbyte(pfunc->card, RSI_INT_ENABLE_REGISTER, &data); + if (ret < 0) { + rsi_dbg(ERR_ZONE, + "%s: Failed to read int enable register\n", __func__); + goto done; + } + rsi_dbg(INFO_ZONE, "int enable reg content = %x\n", data); + +done: + sdio_release_host(pfunc); + return ret; +} + static int rsi_suspend(struct device *dev) { - /* Not yet implemented */ - return -ENOSYS; + int ret; + struct sdio_func *pfunction = dev_to_sdio_func(dev); + struct rsi_hw *adapter = sdio_get_drvdata(pfunction); + struct rsi_common *common; + + if (!adapter) { + rsi_dbg(ERR_ZONE, "Device is not ready\n"); + return -ENODEV; + } + common = adapter->priv; + rsi_sdio_disable_interrupts(pfunction); + + ret = rsi_set_sdio_pm_caps(adapter); + if (ret) + rsi_dbg(INFO_ZONE, + "Setting power management caps failed\n"); + common->fsm_state = FSM_CARD_NOT_READY; + + return 0; } static int rsi_resume(struct device *dev) { - /* Not yet implemented */ - return -ENOSYS; + struct sdio_func *pfunction = dev_to_sdio_func(dev); + struct rsi_hw *adapter = sdio_get_drvdata(pfunction); + struct rsi_common *common = adapter->priv; + + common->fsm_state = FSM_MAC_INIT_DONE; + rsi_sdio_enable_interrupts(pfunction); + + return 0; } static const struct dev_pm_ops rsi_pm_ops = { diff --git a/drivers/net/wireless/rsi/rsi_91x_usb.c b/drivers/net/wireless/rsi/rsi_91x_usb.c index 81df09dd2636..08730227cd18 100644 --- a/drivers/net/wireless/rsi/rsi_91x_usb.c +++ b/drivers/net/wireless/rsi/rsi_91x_usb.c @@ -73,8 +73,7 @@ static int rsi_write_multiple(struct rsi_hw *adapter, u8 *data, u32 count) { - struct rsi_91x_usbdev *dev = - (struct rsi_91x_usbdev *)adapter->rsi_dev; + struct rsi_91x_usbdev *dev; if (!adapter) return -ENODEV; @@ -82,6 +81,7 @@ static int rsi_write_multiple(struct rsi_hw *adapter, if (endpoint == 0) return -EINVAL; + dev = (struct rsi_91x_usbdev *)adapter->rsi_dev; if (dev->write_fail) return -ENETDOWN; diff --git a/drivers/net/wireless/rsi/rsi_common.h b/drivers/net/wireless/rsi/rsi_common.h index e579d694d13c..272e18d750ff 100644 --- a/drivers/net/wireless/rsi/rsi_common.h +++ b/drivers/net/wireless/rsi/rsi_common.h @@ -79,9 +79,11 @@ static inline int rsi_kill_thread(struct rsi_thread *handle) } void rsi_mac80211_detach(struct rsi_hw *hw); -u16 rsi_get_connected_channel(struct rsi_hw *adapter); +u16 rsi_get_connected_channel(struct ieee80211_vif *vif); struct rsi_hw *rsi_91x_init(void); void rsi_91x_deinit(struct rsi_hw *adapter); int rsi_read_pkt(struct rsi_common *common, s32 rcv_pkt_len); struct rsi_sta *rsi_find_sta(struct rsi_common *common, u8 *mac_addr); +struct ieee80211_vif *rsi_get_vif(struct rsi_hw *adapter, u8 *mac); +void rsi_roc_timeout(unsigned long data); #endif diff --git a/drivers/net/wireless/rsi/rsi_hal.h b/drivers/net/wireless/rsi/rsi_hal.h index 7c145053da6d..a09d36b6b765 100644 --- a/drivers/net/wireless/rsi/rsi_hal.h +++ b/drivers/net/wireless/rsi/rsi_hal.h @@ -101,6 +101,9 @@ #define BBP_INFO_40MHZ 0x6 +#define FW_FLASH_OFFSET 0x820 +#define LMAC_VER_OFFSET (FW_FLASH_OFFSET + 0x200) + struct bl_header { __le32 flags; __le32 image_no; @@ -121,8 +124,7 @@ struct rsi_mgmt_desc { u8 xtend_desc_size; u8 header_len; __le16 frame_info; - u8 rate_info; - u8 reserved1; + __le16 rate_info; __le16 bbp_info; __le16 seq_ctrl; u8 reserved2; diff --git a/drivers/net/wireless/rsi/rsi_main.h b/drivers/net/wireless/rsi/rsi_main.h index 2c18dde633ea..a118b7aaeca0 100644 --- a/drivers/net/wireless/rsi/rsi_main.h +++ b/drivers/net/wireless/rsi/rsi_main.h @@ -60,7 +60,7 @@ enum RSI_FSM_STATES { extern u32 rsi_zone_enabled; extern __printf(2, 3) void rsi_dbg(u32 zone, const char *fmt, ...); -#define RSI_MAX_VIFS 1 +#define RSI_MAX_VIFS 3 #define NUM_EDCA_QUEUES 4 #define IEEE80211_ADDR_LEN 6 #define FRAME_DESC_SZ 16 @@ -113,8 +113,13 @@ extern __printf(2, 3) void rsi_dbg(u32 zone, const char *fmt, ...); struct version_info { u16 major; u16 minor; - u16 release_num; - u16 patch_num; + u8 release_num; + u8 patch_num; + union { + struct { + u8 fw_ver[8]; + } info; + } ver; } __packed; struct skb_info { @@ -124,6 +129,8 @@ struct skb_info { s8 tid; s8 sta_id; u8 internal_hdr_size; + struct ieee80211_vif *vif; + u8 vap_id; }; enum edca_queue { @@ -157,6 +164,7 @@ struct vif_priv { bool is_ht; bool sgi; u16 seq_start; + int vap_id; }; struct rsi_event { @@ -196,8 +204,7 @@ struct rsi_common { struct vif_priv vif_info[RSI_MAX_VIFS]; bool mgmt_q_block; - struct version_info driver_ver; - struct version_info fw_ver; + struct version_info lmac_ver; struct rsi_thread tx_thread; struct sk_buff_head tx_queue[NUM_EDCA_QUEUES + 2]; @@ -270,6 +277,11 @@ struct rsi_common { int num_stations; int max_stations; struct ieee80211_key_conf *key; + + /* Wi-Fi direct mode related */ + bool p2p_enabled; + struct timer_list roc_timer; + struct ieee80211_vif *roc_vif; }; enum host_intf { @@ -326,6 +338,8 @@ struct rsi_hw { int (*determine_event_timeout)(struct rsi_hw *adapter); }; +void rsi_print_version(struct rsi_common *common); + struct rsi_host_intf_ops { int (*read_pkt)(struct rsi_hw *adapter, u8 *pkt, u32 len); int (*write_pkt)(struct rsi_hw *adapter, u8 *pkt, u32 len); diff --git a/drivers/net/wireless/rsi/rsi_mgmt.h b/drivers/net/wireless/rsi/rsi_mgmt.h index c6e1fa669a27..e21723013f8d 100644 --- a/drivers/net/wireless/rsi/rsi_mgmt.h +++ b/drivers/net/wireless/rsi/rsi_mgmt.h @@ -189,6 +189,8 @@ IEEE80211_WMM_IE_STA_QOSINFO_AC_BE | \ IEEE80211_WMM_IE_STA_QOSINFO_AC_BK) +#define RSI_DESC_VAP_ID_MASK 0xC000u +#define RSI_DESC_VAP_ID_OFST 14 #define RSI_DATA_DESC_MAC_BBP_INFO BIT(0) #define RSI_DATA_DESC_NO_ACK_IND BIT(9) #define RSI_DATA_DESC_QOS_EN BIT(12) @@ -200,8 +202,11 @@ #define RSI_DATA_DESC_INSERT_SEQ_NO BIT(2) enum opmode { - AP_OPMODE = 0, - STA_OPMODE, + RSI_OPMODE_UNSUPPORTED = -1, + RSI_OPMODE_AP = 0, + RSI_OPMODE_STA, + RSI_OPMODE_P2P_GO, + RSI_OPMODE_P2P_CLIENT }; enum vap_status { @@ -363,9 +368,9 @@ struct rsi_vap_caps { u8 vif_type; u8 channel_bw; __le16 antenna_info; + __le16 token; u8 radioid_macid; u8 vap_id; - __le16 reserved3; u8 mac_addr[6]; __le16 keep_alive_period; u8 bssid[6]; @@ -613,14 +618,16 @@ int rsi_send_aggregation_params_frame(struct rsi_common *common, u16 tid, u16 ssn, u8 buf_size, u8 event, u8 sta_id); int rsi_hal_load_key(struct rsi_common *common, u8 *data, u16 key_len, - u8 key_type, u8 key_id, u32 cipher, s16 sta_id); + u8 key_type, u8 key_id, u32 cipher, s16 sta_id, + struct ieee80211_vif *vif); int rsi_set_channel(struct rsi_common *common, struct ieee80211_channel *channel); int rsi_send_vap_dynamic_update(struct rsi_common *common); int rsi_send_block_unblock_frame(struct rsi_common *common, bool event); void rsi_inform_bss_status(struct rsi_common *common, enum opmode opmode, u8 status, const u8 *addr, u8 qos_enable, u16 aid, - struct ieee80211_sta *sta, u16 sta_id); + struct ieee80211_sta *sta, u16 sta_id, + struct ieee80211_vif *vif); void rsi_indicate_pkt_to_os(struct rsi_common *common, struct sk_buff *skb); int rsi_mac80211_attach(struct rsi_common *common); void rsi_indicate_tx_status(struct rsi_hw *common, struct sk_buff *skb, @@ -630,8 +637,10 @@ void rsi_core_qos_processor(struct rsi_common *common); void rsi_core_xmit(struct rsi_common *common, struct sk_buff *skb); int rsi_send_mgmt_pkt(struct rsi_common *common, struct sk_buff *skb); int rsi_send_data_pkt(struct rsi_common *common, struct sk_buff *skb); -int rsi_band_check(struct rsi_common *common); +int rsi_band_check(struct rsi_common *common, struct ieee80211_channel *chan); int rsi_send_rx_filter_frame(struct rsi_common *common, u16 rx_filter_word); int rsi_send_radio_params_update(struct rsi_common *common); int rsi_set_antenna(struct rsi_common *common, u8 antenna); +int rsi_send_ps_request(struct rsi_hw *adapter, bool enable, + struct ieee80211_vif *vif); #endif diff --git a/drivers/net/wireless/rsi/rsi_ps.h b/drivers/net/wireless/rsi/rsi_ps.h index d8475873df36..98ff6a4ced57 100644 --- a/drivers/net/wireless/rsi/rsi_ps.h +++ b/drivers/net/wireless/rsi/rsi_ps.h @@ -55,10 +55,9 @@ struct rsi_ps_info { } __packed; char *str_psstate(enum ps_state state); -void rsi_enable_ps(struct rsi_hw *adapter); -void rsi_disable_ps(struct rsi_hw *adapter); +void rsi_enable_ps(struct rsi_hw *adapter, struct ieee80211_vif *vif); +void rsi_disable_ps(struct rsi_hw *adapter, struct ieee80211_vif *vif); int rsi_handle_ps_confirm(struct rsi_hw *adapter, u8 *msg); void rsi_default_ps_params(struct rsi_hw *hw); -int rsi_send_ps_request(struct rsi_hw *adapter, bool enable); -void rsi_conf_uapsd(struct rsi_hw *adapter); +void rsi_conf_uapsd(struct rsi_hw *adapter, struct ieee80211_vif *vif); #endif diff --git a/drivers/net/wireless/rsi/rsi_sdio.h b/drivers/net/wireless/rsi/rsi_sdio.h index 95e4bed57baf..49c549ba6682 100644 --- a/drivers/net/wireless/rsi/rsi_sdio.h +++ b/drivers/net/wireless/rsi/rsi_sdio.h @@ -48,6 +48,8 @@ enum sdio_interrupt_type { #define RSI_DEVICE_BUFFER_STATUS_REGISTER 0xf3 #define RSI_FN1_INT_REGISTER 0xf9 +#define RSI_INT_ENABLE_REGISTER 0x04 +#define RSI_INT_ENABLE_MASK 0xfc #define RSI_SD_REQUEST_MASTER 0x10000 /* FOR SD CARD ONLY */ diff --git a/drivers/net/wireless/st/cw1200/pm.c b/drivers/net/wireless/st/cw1200/pm.c index d2202ae92bdd..ded23df1ac1d 100644 --- a/drivers/net/wireless/st/cw1200/pm.c +++ b/drivers/net/wireless/st/cw1200/pm.c @@ -91,7 +91,7 @@ struct cw1200_suspend_state { u8 prev_ps_mode; }; -static void cw1200_pm_stay_awake_tmo(unsigned long arg) +static void cw1200_pm_stay_awake_tmo(struct timer_list *unused) { /* XXX what's the point of this ? */ } @@ -101,8 +101,7 @@ int cw1200_pm_init(struct cw1200_pm_state *pm, { spin_lock_init(&pm->lock); - setup_timer(&pm->stay_awake, cw1200_pm_stay_awake_tmo, - (unsigned long)pm); + timer_setup(&pm->stay_awake, cw1200_pm_stay_awake_tmo, 0); return 0; } diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 5b1d2e8402d9..a46a1e94505d 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -307,7 +307,7 @@ static inline struct xenbus_device *xenvif_to_xenbus_device(struct xenvif *vif) return to_xenbus_device(vif->dev->dev.parent); } -void xenvif_tx_credit_callback(unsigned long data); +void xenvif_tx_credit_callback(struct timer_list *t); struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index dcfcb153918c..5cbe0ae55a07 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -520,7 +520,7 @@ int xenvif_init_queue(struct xenvif_queue *queue) queue->credit_bytes = queue->remaining_credit = ~0UL; queue->credit_usec = 0UL; - setup_timer(&queue->credit_timeout, xenvif_tx_credit_callback, 0UL); + timer_setup(&queue->credit_timeout, xenvif_tx_credit_callback, 0); queue->credit_window_start = get_jiffies_64(); queue->rx_queue_max = XENVIF_RX_QUEUE_BYTES; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 5042ff8d449a..a27daa23c9dc 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -183,9 +183,9 @@ static void tx_add_credit(struct xenvif_queue *queue) queue->rate_limited = false; } -void xenvif_tx_credit_callback(unsigned long data) +void xenvif_tx_credit_callback(struct timer_list *t) { - struct xenvif_queue *queue = (struct xenvif_queue *)data; + struct xenvif_queue *queue = from_timer(queue, t, credit_timeout); tx_add_credit(queue); xenvif_napi_schedule_or_enable_events(queue); } @@ -700,8 +700,6 @@ static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size) /* Still too big to send right now? Set a callback. */ if (size > queue->remaining_credit) { - queue->credit_timeout.data = - (unsigned long)queue; mod_timer(&queue->credit_timeout, next_credit); queue->credit_window_start = next_credit; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index bb2aad078637..5a14cc7f28ee 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2136,7 +2136,7 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj, struct nvme_ns *ns = nvme_get_ns_from_dev(dev); if (a == &dev_attr_uuid.attr) { - if (uuid_is_null(&ns->uuid) || + if (uuid_is_null(&ns->uuid) && !memchr_inv(ns->nguid, 0, sizeof(ns->nguid))) return 0; } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index cb73bc8cad3b..3f5a04c586ce 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -94,7 +94,7 @@ struct nvme_dev { struct mutex shutdown_lock; bool subsystem; void __iomem *cmb; - dma_addr_t cmb_dma_addr; + pci_bus_addr_t cmb_bus_addr; u64 cmb_size; u32 cmbsz; u32 cmbloc; @@ -1226,7 +1226,7 @@ static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq, if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev->cmbsz)) { unsigned offset = (qid - 1) * roundup(SQ_SIZE(depth), dev->ctrl.page_size); - nvmeq->sq_dma_addr = dev->cmb_dma_addr + offset; + nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset; nvmeq->sq_cmds_io = dev->cmb + offset; } else { nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth), @@ -1527,7 +1527,7 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev) resource_size_t bar_size; struct pci_dev *pdev = to_pci_dev(dev->dev); void __iomem *cmb; - dma_addr_t dma_addr; + int bar; dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ); if (!(NVME_CMB_SZ(dev->cmbsz))) @@ -1540,7 +1540,8 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev) szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz)); size = szu * NVME_CMB_SZ(dev->cmbsz); offset = szu * NVME_CMB_OFST(dev->cmbloc); - bar_size = pci_resource_len(pdev, NVME_CMB_BIR(dev->cmbloc)); + bar = NVME_CMB_BIR(dev->cmbloc); + bar_size = pci_resource_len(pdev, bar); if (offset > bar_size) return NULL; @@ -1553,12 +1554,11 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev) if (size > bar_size - offset) size = bar_size - offset; - dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(dev->cmbloc)) + offset; - cmb = ioremap_wc(dma_addr, size); + cmb = ioremap_wc(pci_resource_start(pdev, bar) + offset, size); if (!cmb) return NULL; - dev->cmb_dma_addr = dma_addr; + dev->cmb_bus_addr = pci_bus_address(pdev, bar) + offset; dev->cmb_size = size; return cmb; } diff --git a/drivers/pcmcia/electra_cf.c b/drivers/pcmcia/electra_cf.c index c6fe2a4a7a6a..9671ded549f0 100644 --- a/drivers/pcmcia/electra_cf.c +++ b/drivers/pcmcia/electra_cf.c @@ -79,9 +79,9 @@ static int electra_cf_ss_init(struct pcmcia_socket *s) } /* the timer is primarily to kick this socket's pccardd */ -static void electra_cf_timer(unsigned long _cf) +static void electra_cf_timer(struct timer_list *t) { - struct electra_cf_socket *cf = (void *) _cf; + struct electra_cf_socket *cf = from_timer(cf, t, timer); int present = electra_cf_present(cf); if (present != cf->present) { @@ -95,7 +95,9 @@ static void electra_cf_timer(unsigned long _cf) static irqreturn_t electra_cf_irq(int irq, void *_cf) { - electra_cf_timer((unsigned long)_cf); + struct electra_cf_socket *cf = _cf; + + electra_cf_timer(&cf->timer); return IRQ_HANDLED; } @@ -206,7 +208,7 @@ static int electra_cf_probe(struct platform_device *ofdev) if (!cf) return -ENOMEM; - setup_timer(&cf->timer, electra_cf_timer, (unsigned long)cf); + timer_setup(&cf->timer, electra_cf_timer, 0); cf->irq = 0; cf->ofdev = ofdev; @@ -305,7 +307,7 @@ static int electra_cf_probe(struct platform_device *ofdev) cf->mem_phys, io.start, cf->irq); cf->active = 1; - electra_cf_timer((unsigned long)cf); + electra_cf_timer(&cf->timer); return 0; fail3: diff --git a/drivers/s390/net/fsm.c b/drivers/s390/net/fsm.c index e5dea67f902e..8c14c6c3ad3d 100644 --- a/drivers/s390/net/fsm.c +++ b/drivers/s390/net/fsm.c @@ -170,9 +170,7 @@ fsm_addtimer(fsm_timer *this, int millisec, int event, void *arg) this->fi->name, this, millisec); #endif - init_timer(&this->tl); - this->tl.function = (void *)fsm_expire_timer; - this->tl.data = (long)this; + setup_timer(&this->tl, (void *)fsm_expire_timer, (long)this); this->expire_event = event; this->event_arg = arg; this->tl.expires = jiffies + (millisec * HZ) / 1000; @@ -191,9 +189,7 @@ fsm_modtimer(fsm_timer *this, int millisec, int event, void *arg) #endif del_timer(&this->tl); - init_timer(&this->tl); - this->tl.function = (void *)fsm_expire_timer; - this->tl.data = (long)this; + setup_timer(&this->tl, (void *)fsm_expire_timer, (long)this); this->expire_event = event; this->event_arg = arg; this->tl.expires = jiffies + (millisec * HZ) / 1000; diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 91fcadbede80..dbdf09a1299a 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -231,20 +231,6 @@ static inline int qeth_is_ipa_enabled(struct qeth_ipa_info *ipa, #define QETH_IDX_FUNC_LEVEL_OSD 0x0101 #define QETH_IDX_FUNC_LEVEL_IQD 0x4108 -#define QETH_MODELLIST_ARRAY \ - {{0x1731, 0x01, 0x1732, QETH_CARD_TYPE_OSD, QETH_MAX_QUEUES, 0}, \ - {0x1731, 0x05, 0x1732, QETH_CARD_TYPE_IQD, QETH_MAX_QUEUES, 0x103}, \ - {0x1731, 0x06, 0x1732, QETH_CARD_TYPE_OSN, QETH_MAX_QUEUES, 0}, \ - {0x1731, 0x02, 0x1732, QETH_CARD_TYPE_OSM, QETH_MAX_QUEUES, 0}, \ - {0x1731, 0x02, 0x1732, QETH_CARD_TYPE_OSX, QETH_MAX_QUEUES, 0}, \ - {0, 0, 0, 0, 0, 0} } -#define QETH_CU_TYPE_IND 0 -#define QETH_CU_MODEL_IND 1 -#define QETH_DEV_TYPE_IND 2 -#define QETH_DEV_MODEL_IND 3 -#define QETH_QUEUE_NO_IND 4 -#define QETH_MULTICAST_IND 5 - #define QETH_REAL_CARD 1 #define QETH_VLAN_CARD 2 #define QETH_BUFSIZE 4096 @@ -998,7 +984,7 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *, __u16, __u16, enum qeth_prot_versions); int qeth_set_features(struct net_device *, netdev_features_t); -int qeth_recover_features(struct net_device *); +void qeth_recover_features(struct net_device *dev); netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t); int qeth_vm_request_mac(struct qeth_card *card); int qeth_push_hdr(struct sk_buff *skb, struct qeth_hdr **hdr, unsigned int len); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 68e118f1202e..457a4b4e8212 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -52,7 +52,6 @@ EXPORT_SYMBOL_GPL(qeth_core_header_cache); static struct kmem_cache *qeth_qdio_outbuf_cache; static struct device *qeth_core_root_dev; -static unsigned int known_devices[][6] = QETH_MODELLIST_ARRAY; static struct lock_class_key qdio_out_skb_queue_key; static struct mutex qeth_mod_mutex; @@ -1386,6 +1385,7 @@ static void qeth_init_qdio_info(struct qeth_card *card) QETH_DBF_TEXT(SETUP, 4, "intqdinf"); atomic_set(&card->qdio.state, QETH_QDIO_UNINITIALIZED); /* inbound */ + card->qdio.no_in_queues = 1; card->qdio.in_buf_size = QETH_IN_BUF_SIZE_DEFAULT; if (card->info.type == QETH_CARD_TYPE_IQD) card->qdio.init_pool.buf_count = QETH_IN_BUF_COUNT_HSDEFAULT; @@ -1519,34 +1519,17 @@ out: return NULL; } -static int qeth_determine_card_type(struct qeth_card *card) +static void qeth_determine_card_type(struct qeth_card *card) { - int i = 0; - QETH_DBF_TEXT(SETUP, 2, "detcdtyp"); card->qdio.do_prio_queueing = QETH_PRIOQ_DEFAULT; card->qdio.default_out_queue = QETH_DEFAULT_QUEUE; - while (known_devices[i][QETH_DEV_MODEL_IND]) { - if ((CARD_RDEV(card)->id.dev_type == - known_devices[i][QETH_DEV_TYPE_IND]) && - (CARD_RDEV(card)->id.dev_model == - known_devices[i][QETH_DEV_MODEL_IND])) { - card->info.type = known_devices[i][QETH_DEV_MODEL_IND]; - card->qdio.no_out_queues = - known_devices[i][QETH_QUEUE_NO_IND]; - card->qdio.no_in_queues = 1; - card->info.is_multicast_different = - known_devices[i][QETH_MULTICAST_IND]; - qeth_update_from_chp_desc(card); - return 0; - } - i++; - } - card->info.type = QETH_CARD_TYPE_UNKNOWN; - dev_err(&card->gdev->dev, "The adapter hardware is of an " - "unknown type\n"); - return -ENOENT; + card->info.type = CARD_RDEV(card)->id.driver_info; + card->qdio.no_out_queues = QETH_MAX_QUEUES; + if (card->info.type == QETH_CARD_TYPE_IQD) + card->info.is_multicast_different = 0x0103; + qeth_update_from_chp_desc(card); } static int qeth_clear_channel(struct qeth_channel *channel) @@ -2090,7 +2073,6 @@ int qeth_send_control_data(struct qeth_card *card, int len, spin_lock_irqsave(&card->lock, flags); list_add_tail(&reply->list, &card->cmd_waiter_list); spin_unlock_irqrestore(&card->lock, flags); - QETH_DBF_HEX(CTRL, 2, iob->data, QETH_DBF_CTRL_LEN); while (atomic_cmpxchg(&card->write.irq_pending, 0, 1)) ; qeth_prepare_control_data(card, len, iob); @@ -2233,23 +2215,15 @@ static int qeth_cm_setup(struct qeth_card *card) static int qeth_get_initial_mtu_for_card(struct qeth_card *card) { switch (card->info.type) { - case QETH_CARD_TYPE_UNKNOWN: - return 1500; case QETH_CARD_TYPE_IQD: return card->info.max_mtu; case QETH_CARD_TYPE_OSD: - switch (card->info.link_type) { - case QETH_LINK_TYPE_HSTR: - case QETH_LINK_TYPE_LANE_TR: - return 2000; - default: - return card->options.layer2 ? 1500 : 1492; - } - case QETH_CARD_TYPE_OSM: case QETH_CARD_TYPE_OSX: - return card->options.layer2 ? 1500 : 1492; + if (!card->options.layer2) + return ETH_DATA_LEN - 8; /* L3: allow for LLC + SNAP */ + /* fall through */ default: - return 1500; + return ETH_DATA_LEN; } } @@ -2279,7 +2253,6 @@ static int qeth_mtu_is_valid(struct qeth_card *card, int mtu) return ((mtu >= 576) && (mtu <= card->info.max_mtu)); case QETH_CARD_TYPE_OSN: - case QETH_CARD_TYPE_UNKNOWN: default: return 1; } @@ -5196,49 +5169,27 @@ out: } EXPORT_SYMBOL_GPL(qeth_core_hardsetup_card); -static int qeth_create_skb_frag(struct qeth_qdio_buffer *qethbuffer, - struct qdio_buffer_element *element, - struct sk_buff **pskb, int offset, int *pfrag, - int data_len) +static void qeth_create_skb_frag(struct qdio_buffer_element *element, + struct sk_buff *skb, int offset, int data_len) { struct page *page = virt_to_page(element->addr); - if (*pskb == NULL) { - if (qethbuffer->rx_skb) { - /* only if qeth_card.options.cq == QETH_CQ_ENABLED */ - *pskb = qethbuffer->rx_skb; - qethbuffer->rx_skb = NULL; - } else { - *pskb = dev_alloc_skb(QETH_RX_PULL_LEN + ETH_HLEN); - if (!(*pskb)) - return -ENOMEM; - } + unsigned int next_frag; - skb_reserve(*pskb, ETH_HLEN); - if (data_len <= QETH_RX_PULL_LEN) { - skb_put_data(*pskb, element->addr + offset, data_len); - } else { - get_page(page); - skb_put_data(*pskb, element->addr + offset, - QETH_RX_PULL_LEN); - skb_fill_page_desc(*pskb, *pfrag, page, - offset + QETH_RX_PULL_LEN, - data_len - QETH_RX_PULL_LEN); - (*pskb)->data_len += data_len - QETH_RX_PULL_LEN; - (*pskb)->len += data_len - QETH_RX_PULL_LEN; - (*pskb)->truesize += data_len - QETH_RX_PULL_LEN; - (*pfrag)++; - } - } else { - get_page(page); - skb_fill_page_desc(*pskb, *pfrag, page, offset, data_len); - (*pskb)->data_len += data_len; - (*pskb)->len += data_len; - (*pskb)->truesize += data_len; - (*pfrag)++; - } + /* first fill the linear space */ + if (!skb->len) { + unsigned int linear = min(data_len, skb_tailroom(skb)); + skb_put_data(skb, element->addr + offset, linear); + data_len -= linear; + if (!data_len) + return; + offset += linear; + /* fall through to add page frag for remaining data */ + } - return 0; + next_frag = skb_shinfo(skb)->nr_frags; + get_page(page); + skb_add_rx_frag(skb, next_frag, page, offset, data_len, data_len); } static inline int qeth_is_last_sbale(struct qdio_buffer_element *sbale) @@ -5254,22 +5205,19 @@ struct sk_buff *qeth_core_get_next_skb(struct qeth_card *card, struct qdio_buffer_element *element = *__element; struct qdio_buffer *buffer = qethbuffer->buffer; int offset = *__offset; - struct sk_buff *skb = NULL; + struct sk_buff *skb; int skb_len = 0; void *data_ptr; int data_len; int headroom = 0; int use_rx_sg = 0; - int frag = 0; /* qeth_hdr must not cross element boundaries */ - if (element->length < offset + sizeof(struct qeth_hdr)) { + while (element->length < offset + sizeof(struct qeth_hdr)) { if (qeth_is_last_sbale(element)) return NULL; element++; offset = 0; - if (element->length < sizeof(struct qeth_hdr)) - return NULL; } *hdr = element->addr + offset; @@ -5296,27 +5244,32 @@ struct sk_buff *qeth_core_get_next_skb(struct qeth_card *card, if (((skb_len >= card->options.rx_sg_cb) && (!(card->info.type == QETH_CARD_TYPE_OSN)) && (!atomic_read(&card->force_alloc_skb))) || - (card->options.cq == QETH_CQ_ENABLED)) { + (card->options.cq == QETH_CQ_ENABLED)) use_rx_sg = 1; + + if (use_rx_sg && qethbuffer->rx_skb) { + /* QETH_CQ_ENABLED only: */ + skb = qethbuffer->rx_skb; + qethbuffer->rx_skb = NULL; } else { - skb = dev_alloc_skb(skb_len + headroom); - if (!skb) - goto no_mem; - if (headroom) - skb_reserve(skb, headroom); + unsigned int linear = (use_rx_sg) ? QETH_RX_PULL_LEN : skb_len; + + skb = dev_alloc_skb(linear + headroom); } + if (!skb) + goto no_mem; + if (headroom) + skb_reserve(skb, headroom); data_ptr = element->addr + offset; while (skb_len) { data_len = min(skb_len, (int)(element->length - offset)); if (data_len) { - if (use_rx_sg) { - if (qeth_create_skb_frag(qethbuffer, element, - &skb, offset, &frag, data_len)) - goto no_mem; - } else { + if (use_rx_sg) + qeth_create_skb_frag(element, skb, offset, + data_len); + else skb_put_data(skb, data_ptr, data_len); - } } skb_len -= data_len; if (skb_len) { @@ -5416,7 +5369,7 @@ int qeth_poll(struct napi_struct *napi, int budget) } } - napi_complete(napi); + napi_complete_done(napi, work_done); if (qdio_start_irq(card->data.ccwdev, 0)) napi_schedule(&card->napi); out: @@ -5724,11 +5677,7 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) gdev->cdev[1]->handler = qeth_irq; gdev->cdev[2]->handler = qeth_irq; - rc = qeth_determine_card_type(card); - if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc); - goto err_card; - } + qeth_determine_card_type(card); rc = qeth_setup_card(card); if (rc) { QETH_DBF_TEXT_(SETUP, 2, "2err%d", rc); @@ -6403,32 +6352,29 @@ static int qeth_set_ipa_tso(struct qeth_card *card, int on) return rc; } -/* try to restore device features on a device after recovery */ -int qeth_recover_features(struct net_device *dev) +#define QETH_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO) + +/** + * qeth_recover_features() - Restore device features after recovery + * @dev: the recovering net_device + * + * Caller must hold rtnl lock. + */ +void qeth_recover_features(struct net_device *dev) { + netdev_features_t features = dev->features; struct qeth_card *card = dev->ml_priv; - netdev_features_t recover = dev->features; - if (recover & NETIF_F_IP_CSUM) { - if (qeth_set_ipa_csum(card, 1, IPA_OUTBOUND_CHECKSUM)) - recover ^= NETIF_F_IP_CSUM; - } - if (recover & NETIF_F_RXCSUM) { - if (qeth_set_ipa_csum(card, 1, IPA_INBOUND_CHECKSUM)) - recover ^= NETIF_F_RXCSUM; - } - if (recover & NETIF_F_TSO) { - if (qeth_set_ipa_tso(card, 1)) - recover ^= NETIF_F_TSO; - } - - if (recover == dev->features) - return 0; + /* force-off any feature that needs an IPA sequence. + * netdev_update_features() will restart them. + */ + dev->features &= ~QETH_HW_FEATURES; + netdev_update_features(dev); + if (features == dev->features) + return; dev_warn(&card->gdev->dev, "Device recovery failed to restore all offload features\n"); - dev->features = recover; - return -EIO; } EXPORT_SYMBOL_GPL(qeth_recover_features); @@ -6485,8 +6431,7 @@ netdev_features_t qeth_fix_features(struct net_device *dev, /* if the card isn't up, remove features that require hw changes */ if (card->state == CARD_STATE_DOWN || card->state == CARD_STATE_RECOVER) - features = features & ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM | - NETIF_F_TSO); + features &= ~QETH_HW_FEATURES; QETH_DBF_HEX(SETUP, 2, &features, sizeof(features)); return features; } diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index 6a7654df6e78..413f0f268b17 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -44,7 +44,6 @@ extern unsigned char IPA_PDU_HEADER[]; #define IPA_CMD_PRIM_VERSION_NO 0x01 enum qeth_card_types { - QETH_CARD_TYPE_UNKNOWN = 0, QETH_CARD_TYPE_OSD = 1, QETH_CARD_TYPE_IQD = 5, QETH_CARD_TYPE_OSN = 6, diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index d1ee9e30c68b..b22ed2a57acd 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -475,10 +475,8 @@ static ssize_t qeth_dev_isolation_store(struct device *dev, return -EINVAL; mutex_lock(&card->conf_mutex); - /* check for unknown, too, in case we do not yet know who we are */ if (card->info.type != QETH_CARD_TYPE_OSD && - card->info.type != QETH_CARD_TYPE_OSX && - card->info.type != QETH_CARD_TYPE_UNKNOWN) { + card->info.type != QETH_CARD_TYPE_OSX) { rc = -EOPNOTSUPP; dev_err(&card->gdev->dev, "Adapter does not " "support QDIO data connection isolation\n"); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 7b61c2ef4c74..d2537c09126d 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -38,24 +38,6 @@ static void qeth_l2_vnicc_init(struct qeth_card *card); static bool qeth_l2_vnicc_recover_timeout(struct qeth_card *card, u32 vnicc, u32 *timeout); -static int qeth_l2_verify_dev(struct net_device *dev) -{ - struct qeth_card *card; - unsigned long flags; - int rc = 0; - - read_lock_irqsave(&qeth_core_card_list.rwlock, flags); - list_for_each_entry(card, &qeth_core_card_list.list, list) { - if (card->dev == dev) { - rc = QETH_REAL_CARD; - break; - } - } - read_unlock_irqrestore(&qeth_core_card_list.rwlock, flags); - - return rc; -} - static struct net_device *qeth_l2_netdev_by_devno(unsigned char *read_dev_no) { struct qeth_card *card; @@ -366,10 +348,6 @@ static int qeth_l2_vlan_rx_add_vid(struct net_device *dev, QETH_CARD_TEXT_(card, 4, "aid:%d", vid); if (!vid) return 0; - if (card->info.type == QETH_CARD_TYPE_OSM) { - QETH_CARD_TEXT(card, 3, "aidOSM"); - return 0; - } if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) { QETH_CARD_TEXT(card, 3, "aidREC"); return 0; @@ -399,10 +377,6 @@ static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev, int rc = 0; QETH_CARD_TEXT_(card, 4, "kid:%d", vid); - if (card->info.type == QETH_CARD_TYPE_OSM) { - QETH_CARD_TEXT(card, 3, "kidOSM"); - return 0; - } if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) { QETH_CARD_TEXT(card, 3, "kidREC"); return 0; @@ -568,11 +542,6 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p) QETH_CARD_TEXT(card, 3, "setmac"); - if (qeth_l2_verify_dev(dev) != QETH_REAL_CARD) { - QETH_CARD_TEXT(card, 3, "setmcINV"); - return -EOPNOTSUPP; - } - if (card->info.type == QETH_CARD_TYPE_OSN || card->info.type == QETH_CARD_TYPE_OSM || card->info.type == QETH_CARD_TYPE_OSX) { @@ -1033,7 +1002,11 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) } else { card->dev->ethtool_ops = &qeth_l2_ethtool_ops; } - card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + if (card->info.type == QETH_CARD_TYPE_OSM) + card->dev->features |= NETIF_F_VLAN_CHALLENGED; + else + card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) { card->dev->hw_features = NETIF_F_SG; card->dev->vlan_features = NETIF_F_SG; @@ -1143,8 +1116,7 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) goto out_remove; } - if (card->info.type != QETH_CARD_TYPE_OSN && - card->info.type != QETH_CARD_TYPE_OSM) + if (card->info.type != QETH_CARD_TYPE_OSN) qeth_l2_process_vlans(card); netif_tx_disable(card->dev); diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index 4608daedb204..470a4e5f3c62 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -146,18 +146,15 @@ static ssize_t qeth_bridgeport_hostnotification_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct qeth_card *card = dev_get_drvdata(dev); - int rc = 0; - int enable; + bool enable; + int rc; if (!card) return -EINVAL; - if (sysfs_streq(buf, "0")) - enable = 0; - else if (sysfs_streq(buf, "1")) - enable = 1; - else - return -EINVAL; + rc = kstrtobool(buf, &enable); + if (rc) + return rc; mutex_lock(&card->conf_mutex); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 270ac9515f6b..aadd384316a3 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1553,7 +1553,7 @@ static void qeth_l3_free_vlan_addresses4(struct qeth_card *card, addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4); if (!addr) - return; + goto out; spin_lock_bh(&card->ip_lock); @@ -1567,6 +1567,7 @@ static void qeth_l3_free_vlan_addresses4(struct qeth_card *card, spin_unlock_bh(&card->ip_lock); kfree(addr); +out: in_dev_put(in_dev); } @@ -1591,7 +1592,7 @@ static void qeth_l3_free_vlan_addresses6(struct qeth_card *card, addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6); if (!addr) - return; + goto out; spin_lock_bh(&card->ip_lock); @@ -1606,6 +1607,7 @@ static void qeth_l3_free_vlan_addresses6(struct qeth_card *card, spin_unlock_bh(&card->ip_lock); kfree(addr); +out: in6_dev_put(in6_dev); #endif /* CONFIG_QETH_IPV6 */ } diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index 785fb42f6650..2799a6b08f73 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -3767,7 +3767,7 @@ static int ibmvscsis_write_pending(struct se_cmd *se_cmd) */ if ((vscsi->flags & (CLIENT_FAILED | RESPONSE_Q_DOWN))) { pr_err("write_pending failed since: %d\n", vscsi->flags); - return 0; + return -EIO; } rc = srp_transfer_data(cmd, &vio_iu(iue)->srp.cmd, ibmvscsis_rdma, diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index bd4605a34f54..c62e8d111fd9 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -2851,9 +2851,6 @@ EXPORT_SYMBOL_GPL(iscsi_session_setup); /** * iscsi_session_teardown - destroy session, host, and cls_session * @cls_session: iscsi session - * - * The driver must have called iscsi_remove_session before - * calling this. */ void iscsi_session_teardown(struct iscsi_cls_session *cls_session) { @@ -2863,6 +2860,8 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session) iscsi_pool_free(&session->cmdpool); + iscsi_remove_session(cls_session); + kfree(session->password); kfree(session->password_in); kfree(session->username); @@ -2877,7 +2876,8 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session) kfree(session->portal_type); kfree(session->discovery_parent_type); - iscsi_destroy_session(cls_session); + iscsi_free_session(cls_session); + iscsi_host_dec_session_cnt(shost); module_put(owner); } diff --git a/drivers/scsi/qedi/Kconfig b/drivers/scsi/qedi/Kconfig index 2ff753ce6e27..d1db92d24889 100644 --- a/drivers/scsi/qedi/Kconfig +++ b/drivers/scsi/qedi/Kconfig @@ -4,6 +4,7 @@ config QEDI depends on QED select SCSI_ISCSI_ATTRS select QED_LL2 + select QED_OOO select QED_ISCSI select ISCSI_BOOT_SYSFS ---help--- diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index e7818afeda2b..15590a063ad9 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -956,6 +956,9 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, if (*bflags & BLIST_NO_DIF) sdev->no_dif = 1; + if (*bflags & BLIST_UNMAP_LIMIT_WS) + sdev->unmap_limit_for_ws = 1; + sdev->eh_timeout = SCSI_DEFAULT_EH_TIMEOUT; if (*bflags & BLIST_TRY_VPD_PAGES) diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 0190aeff5f7f..7404d26895f5 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2211,22 +2211,6 @@ void iscsi_free_session(struct iscsi_cls_session *session) EXPORT_SYMBOL_GPL(iscsi_free_session); /** - * iscsi_destroy_session - destroy iscsi session - * @session: iscsi_session - * - * Can be called by a LLD or iscsi_transport. There must not be - * any running connections. - */ -int iscsi_destroy_session(struct iscsi_cls_session *session) -{ - iscsi_remove_session(session); - ISCSI_DBG_TRANS_SESSION(session, "Completing session destruction\n"); - iscsi_free_session(session); - return 0; -} -EXPORT_SYMBOL_GPL(iscsi_destroy_session); - -/** * iscsi_create_conn - create iscsi class connection * @session: iscsi cls session * @dd_size: private driver data size diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index fb9f8b5f4673..d175c5c5ccf8 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -715,13 +715,21 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) break; case SD_LBP_WS16: - max_blocks = min_not_zero(sdkp->max_ws_blocks, - (u32)SD_MAX_WS16_BLOCKS); + if (sdkp->device->unmap_limit_for_ws) + max_blocks = sdkp->max_unmap_blocks; + else + max_blocks = sdkp->max_ws_blocks; + + max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS16_BLOCKS); break; case SD_LBP_WS10: - max_blocks = min_not_zero(sdkp->max_ws_blocks, - (u32)SD_MAX_WS10_BLOCKS); + if (sdkp->device->unmap_limit_for_ws) + max_blocks = sdkp->max_unmap_blocks; + else + max_blocks = sdkp->max_ws_blocks; + + max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS10_BLOCKS); break; case SD_LBP_ZERO: @@ -3099,8 +3107,6 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_security(sdkp, buffer); } - sdkp->first_scan = 0; - /* * We now have all cache related info, determine how we deal * with flush requests. @@ -3115,7 +3121,7 @@ static int sd_revalidate_disk(struct gendisk *disk) q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max); /* - * Use the device's preferred I/O size for reads and writes + * Determine the device's preferred I/O size for reads and writes * unless the reported value is unreasonably small, large, or * garbage. */ @@ -3129,8 +3135,19 @@ static int sd_revalidate_disk(struct gendisk *disk) rw_max = min_not_zero(logical_to_sectors(sdp, dev_max), (sector_t)BLK_DEF_MAX_SECTORS); - /* Combine with controller limits */ - q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q)); + /* Do not exceed controller limit */ + rw_max = min(rw_max, queue_max_hw_sectors(q)); + + /* + * Only update max_sectors if previously unset or if the current value + * exceeds the capabilities of the hardware. + */ + if (sdkp->first_scan || + q->limits.max_sectors > q->limits.max_dev_sectors || + q->limits.max_sectors > q->limits.max_hw_sectors) + q->limits.max_sectors = rw_max; + + sdkp->first_scan = 0; set_capacity(disk, logical_to_sectors(sdp, sdkp->capacity)); sd_config_write_same(sdkp); diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 0e79eebfcbb7..419a7a90bce0 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -1144,5 +1144,5 @@ static void __exit nhi_unload(void) tb_domain_exit(); } -module_init(nhi_init); +fs_initcall(nhi_init); module_exit(nhi_unload); diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index f2d06f6f7be9..ff8d91189e99 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -56,7 +56,7 @@ static bool tb_xdomain_match(const struct tb_cfg_request *req, case TB_CFG_PKG_XDOMAIN_RESP: { const struct tb_xdp_header *res_hdr = pkg->buffer; const struct tb_xdp_header *req_hdr = req->request; - u8 req_seq, res_seq; + u32 req_seq, res_seq; if (pkg->frame.size < req->response_size / 4) return false; @@ -476,7 +476,7 @@ static void tb_xdp_handle_request(struct work_struct *work) struct tb_ctl *ctl = tb->ctl; const uuid_t *uuid; int ret = 0; - u8 sequence; + u32 sequence; u64 route; route = ((u64)xhdr->route_hi << 32 | xhdr->route_lo) & ~BIT_ULL(63); @@ -1487,6 +1487,9 @@ int tb_register_property_dir(const char *key, struct tb_property_dir *dir) { int ret; + if (WARN_ON(!xdomain_property_dir)) + return -EAGAIN; + if (!key || strlen(key) > 8) return -EINVAL; diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 58585ec8699e..68677d930e20 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -436,8 +436,8 @@ static bool vhost_exceeds_maxpend(struct vhost_net *net) struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *vq = &nvq->vq; - return (nvq->upend_idx + vq->num - VHOST_MAX_PEND) % UIO_MAXIOV - == nvq->done_idx; + return (nvq->upend_idx + UIO_MAXIOV - nvq->done_idx) % UIO_MAXIOV > + min_t(unsigned int, VHOST_MAX_PEND, vq->num >> 2); } /* Expects to be always run from workqueue - which acts as @@ -480,11 +480,6 @@ static void handle_tx(struct vhost_net *net) if (zcopy) vhost_zerocopy_signal_used(net, vq); - /* If more outstanding DMAs, queue the work. - * Handle upend_idx wrap around - */ - if (unlikely(vhost_exceeds_maxpend(net))) - break; head = vhost_net_tx_get_vq_desc(net, vq, vq->iov, ARRAY_SIZE(vq->iov), @@ -519,8 +514,7 @@ static void handle_tx(struct vhost_net *net) len = msg_data_left(&msg); zcopy_used = zcopy && len >= VHOST_GOODCOPY_LEN - && (nvq->upend_idx + 1) % UIO_MAXIOV != - nvq->done_idx + && !vhost_exceeds_maxpend(net) && vhost_net_tx_select_zcopy(net); /* use msg_control to pass vhost zerocopy ubuf info to skb */ diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 82e16556afea..3f03f7888302 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -100,6 +100,7 @@ struct afs_call { bool send_pages; /* T if data from mapping should be sent */ bool need_attention; /* T if RxRPC poked us */ bool async; /* T if asynchronous */ + bool upgrade; /* T to request service upgrade */ u16 service_id; /* RxRPC service ID to call */ __be16 port; /* target UDP port */ u32 operation_ID; /* operation ID for an incoming call */ diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 0bf191f0dbaf..bb1e2caa1720 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -387,7 +387,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, tx_total_len, gfp, (async ? afs_wake_up_async_call : - afs_wake_up_call_waiter)); + afs_wake_up_call_waiter), + call->upgrade); call->key = NULL; if (IS_ERR(rxcall)) { ret = PTR_ERR(rxcall); @@ -406,7 +407,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, call->request_size); msg.msg_control = NULL; msg.msg_controllen = 0; - msg.msg_flags = (call->send_pages ? MSG_MORE : 0); + msg.msg_flags = MSG_WAITALL | (call->send_pages ? MSG_MORE : 0); /* We have to change the state *before* sending the last packet as * rxrpc might give us the reply before it returns from sending the @@ -443,7 +444,7 @@ error_do_abort: abort_code = 0; offset = 0; rxrpc_kernel_recv_data(afs_socket, rxcall, NULL, 0, &offset, - false, &abort_code); + false, &abort_code, &call->service_id); ret = call->type->abort_to_error(abort_code); } error_kill_call: @@ -471,7 +472,8 @@ static void afs_deliver_to_call(struct afs_call *call) size_t offset = 0; ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall, NULL, 0, &offset, false, - &call->abort_code); + &call->abort_code, + &call->service_id); trace_afs_recv_data(call, 0, offset, false, ret); if (ret == -EINPROGRESS || ret == -EAGAIN) @@ -536,15 +538,26 @@ call_complete: */ static int afs_wait_for_call_to_complete(struct afs_call *call) { + signed long rtt2, timeout; int ret; + u64 rtt; + u32 life, last_life; DECLARE_WAITQUEUE(myself, current); _enter(""); + rtt = rxrpc_kernel_get_rtt(afs_socket, call->rxcall); + rtt2 = nsecs_to_jiffies64(rtt) * 2; + if (rtt2 < 2) + rtt2 = 2; + + timeout = rtt2; + last_life = rxrpc_kernel_check_life(afs_socket, call->rxcall); + add_wait_queue(&call->waitq, &myself); for (;;) { - set_current_state(TASK_INTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); /* deliver any messages that are in the queue */ if (call->state < AFS_CALL_COMPLETE && call->need_attention) { @@ -554,10 +567,20 @@ static int afs_wait_for_call_to_complete(struct afs_call *call) continue; } - if (call->state == AFS_CALL_COMPLETE || - signal_pending(current)) + if (call->state == AFS_CALL_COMPLETE) break; - schedule(); + + life = rxrpc_kernel_check_life(afs_socket, call->rxcall); + if (timeout == 0 && + life == last_life && signal_pending(current)) + break; + + if (life != last_life) { + timeout = rtt2; + last_life = life; + } + + timeout = schedule_timeout(timeout); } remove_wait_queue(&call->waitq, &myself); @@ -851,7 +874,8 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count, ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall, buf, count, &call->offset, - want_more, &call->abort_code); + want_more, &call->abort_code, + &call->service_id); trace_afs_recv_data(call, count, call->offset, want_more, ret); if (ret == 0 || ret == -EAGAIN) return ret; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 899ddaeeacec..8fc690384c58 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -722,7 +722,7 @@ struct btrfs_delayed_root; * Indicate that a whole-filesystem exclusive operation is running * (device replace, resize, device add/delete, balance) */ -#define BTRFS_FS_EXCL_OP 14 +#define BTRFS_FS_EXCL_OP 16 struct btrfs_fs_info { u8 fsid[BTRFS_FSID_SIZE]; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 12ab19a4b93e..970190cd347e 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2801,7 +2801,7 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree, } } - bio = btrfs_bio_alloc(bdev, sector << 9); + bio = btrfs_bio_alloc(bdev, (u64)sector << 9); bio_add_page(bio, page, page_size, offset); bio->bi_end_io = end_io_func; bio->bi_private = tree; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 84edfc60d87a..f23c820daaed 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -734,12 +734,13 @@ static int __choose_mds(struct ceph_mds_client *mdsc, inode = req->r_inode; ihold(inode); } else { - /* req->r_dentry is non-null for LSSNAP request. - * fall-thru */ - WARN_ON_ONCE(!req->r_dentry); + /* req->r_dentry is non-null for LSSNAP request */ + rcu_read_lock(); + inode = get_nonsnap_parent(req->r_dentry); + rcu_read_unlock(); + dout("__choose_mds using snapdir's parent %p\n", inode); } - } - if (!inode && req->r_dentry) { + } else if (req->r_dentry) { /* ignore race with rename; old or new d_parent is okay */ struct dentry *parent; struct inode *dir; diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 1ffc8b426c1c..7fc0b850c352 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -374,12 +374,10 @@ static int build_snap_context(struct ceph_snap_realm *realm, realm->ino, realm, snapc, snapc->seq, (unsigned int) snapc->num_snaps); - if (realm->cached_context) { - ceph_put_snap_context(realm->cached_context); - /* queue realm for cap_snap creation */ - list_add_tail(&realm->dirty_item, dirty_realms); - } + ceph_put_snap_context(realm->cached_context); realm->cached_context = snapc; + /* queue realm for cap_snap creation */ + list_add_tail(&realm->dirty_item, dirty_realms); return 0; fail: diff --git a/fs/namespace.c b/fs/namespace.c index 54059b142d6b..3b601f115b6c 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -468,7 +468,9 @@ static inline int may_write_real(struct file *file) /* File refers to upper, writable layer? */ upperdentry = d_real(dentry, NULL, 0, D_REAL_UPPER); - if (upperdentry && file_inode(file) == d_inode(upperdentry)) + if (upperdentry && + (file_inode(file) == d_inode(upperdentry) || + file_inode(file) == d_inode(dentry))) return 0; /* Lower layer: can't write to real file, sorry... */ diff --git a/fs/nfs/client.c b/fs/nfs/client.c index efebe6cf4378..22880ef6d8dd 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -218,7 +218,6 @@ static void nfs_cb_idr_remove_locked(struct nfs_client *clp) static void pnfs_init_server(struct nfs_server *server) { rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC"); - rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC"); } #else @@ -888,6 +887,7 @@ struct nfs_server *nfs_alloc_server(void) ida_init(&server->openowner_id); ida_init(&server->lockowner_id); pnfs_init_server(server); + rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC"); return server; } diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 44c638b7876c..508126eb49f9 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -745,7 +745,8 @@ filelayout_free_lseg(struct pnfs_layout_segment *lseg) struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); dprintk("--> %s\n", __func__); - nfs4_fl_put_deviceid(fl->dsaddr); + if (fl->dsaddr != NULL) + nfs4_fl_put_deviceid(fl->dsaddr); /* This assumes a single RW lseg */ if (lseg->pls_range.iomode == IOMODE_RW) { struct nfs4_filelayout *flo; diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index dd5d27da8c0c..30426c1a1bbd 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -274,7 +274,7 @@ static struct key *nfs_idmap_request_key(const char *name, size_t namelen, ssize_t ret; ret = nfs_idmap_get_desc(name, namelen, type, strlen(type), &desc); - if (ret <= 0) + if (ret < 0) return ERR_PTR(ret); rkey = request_key(&key_type_id_resolver, desc, ""); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6c61e2b99635..f90090e8c959 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -8399,8 +8399,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task, lo = NFS_I(inode)->layout; /* If the open stateid was bad, then recover it. */ if (!lo || test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) || - nfs4_stateid_match_other(&lgp->args.stateid, - &lgp->args.ctx->state->stateid)) { + !nfs4_stateid_match_other(&lgp->args.stateid, &lo->plh_stateid)) { spin_unlock(&inode->i_lock); exception->state = lgp->args.ctx->state; exception->stateid = &lgp->args.stateid; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 37c8af003275..14ed9791ec9c 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1842,8 +1842,8 @@ static void encode_create_session(struct xdr_stream *xdr, * Assumes OPEN is the biggest non-idempotent compound. * 2 is the verifier. */ - max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE + - RPC_MAX_AUTH_SIZE + 2) * XDR_UNIT; + max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE + 2) + * XDR_UNIT + RPC_MAX_AUTH_SIZE; encode_op_hdr(xdr, OP_CREATE_SESSION, decode_create_session_maxsz, hdr); p = reserve_space(xdr, 16 + 2*28 + 20 + clnt->cl_nodelen + 12); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index aad97b30d5e6..c441f9387a1b 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -561,10 +561,8 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c) c->tmpfile = true; err = ovl_copy_up_locked(c); } else { - err = -EIO; - if (lock_rename(c->workdir, c->destdir) != NULL) { - pr_err("overlayfs: failed to lock workdir+upperdir\n"); - } else { + err = ovl_lock_rename_workdir(c->workdir, c->destdir); + if (!err) { err = ovl_copy_up_locked(c); unlock_rename(c->workdir, c->destdir); } diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 3309b1912241..cc961a3bd3bd 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -216,26 +216,6 @@ out_unlock: return err; } -static int ovl_lock_rename_workdir(struct dentry *workdir, - struct dentry *upperdir) -{ - /* Workdir should not be the same as upperdir */ - if (workdir == upperdir) - goto err; - - /* Workdir should not be subdir of upperdir and vice versa */ - if (lock_rename(workdir, upperdir) != NULL) - goto err_unlock; - - return 0; - -err_unlock: - unlock_rename(workdir, upperdir); -err: - pr_err("overlayfs: failed to lock workdir+upperdir\n"); - return -EIO; -} - static struct dentry *ovl_clear_empty(struct dentry *dentry, struct list_head *list) { diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index c3addd1114f1..654bea1a5ac9 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -506,6 +506,7 @@ static struct dentry *ovl_lookup_index(struct dentry *dentry, index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len); if (IS_ERR(index)) { + err = PTR_ERR(index); pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%*s, err=%i);\n" "overlayfs: mount with '-o index=off' to disable inodes index.\n", d_inode(origin)->i_ino, name.len, name.name, diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index d4e8c1a08fb0..c706a6f99928 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -235,6 +235,7 @@ bool ovl_inuse_trylock(struct dentry *dentry); void ovl_inuse_unlock(struct dentry *dentry); int ovl_nlink_start(struct dentry *dentry, bool *locked); void ovl_nlink_end(struct dentry *dentry, bool locked); +int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir); static inline bool ovl_is_impuredir(struct dentry *dentry) { diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 878a750986dd..25d9b5adcd42 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -37,6 +37,9 @@ struct ovl_fs { bool noxattr; /* sb common to all layers */ struct super_block *same_sb; + /* Did we take the inuse lock? */ + bool upperdir_locked; + bool workdir_locked; }; /* private information held for every overlayfs dentry */ diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 62e9b22a2077..0f85ee9c3268 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -988,6 +988,7 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, struct path *lowerstack, unsigned int numlower) { int err; + struct dentry *index = NULL; struct inode *dir = dentry->d_inode; struct path path = { .mnt = mnt, .dentry = dentry }; LIST_HEAD(list); @@ -1007,8 +1008,6 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, inode_lock_nested(dir, I_MUTEX_PARENT); list_for_each_entry(p, &list, l_node) { - struct dentry *index; - if (p->name[0] == '.') { if (p->len == 1) continue; @@ -1018,6 +1017,7 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, index = lookup_one_len(p->name, dentry, p->len); if (IS_ERR(index)) { err = PTR_ERR(index); + index = NULL; break; } err = ovl_verify_index(index, lowerstack, numlower); @@ -1029,7 +1029,9 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, break; } dput(index); + index = NULL; } + dput(index); inode_unlock(dir); out: ovl_cache_free(&list); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index fd5ea4facc62..092d150643c1 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -211,9 +211,10 @@ static void ovl_put_super(struct super_block *sb) dput(ufs->indexdir); dput(ufs->workdir); - ovl_inuse_unlock(ufs->workbasedir); + if (ufs->workdir_locked) + ovl_inuse_unlock(ufs->workbasedir); dput(ufs->workbasedir); - if (ufs->upper_mnt) + if (ufs->upper_mnt && ufs->upperdir_locked) ovl_inuse_unlock(ufs->upper_mnt->mnt_root); mntput(ufs->upper_mnt); for (i = 0; i < ufs->numlower; i++) @@ -881,9 +882,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) goto out_put_upperpath; err = -EBUSY; - if (!ovl_inuse_trylock(upperpath.dentry)) { - pr_err("overlayfs: upperdir is in-use by another mount\n"); + if (ovl_inuse_trylock(upperpath.dentry)) { + ufs->upperdir_locked = true; + } else if (ufs->config.index) { + pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n"); goto out_put_upperpath; + } else { + pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); } err = ovl_mount_dir(ufs->config.workdir, &workpath); @@ -901,9 +906,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) } err = -EBUSY; - if (!ovl_inuse_trylock(workpath.dentry)) { - pr_err("overlayfs: workdir is in-use by another mount\n"); + if (ovl_inuse_trylock(workpath.dentry)) { + ufs->workdir_locked = true; + } else if (ufs->config.index) { + pr_err("overlayfs: workdir is in-use by another mount, mount with '-o index=off' to override exclusive workdir protection.\n"); goto out_put_workpath; + } else { + pr_warn("overlayfs: workdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); } ufs->workbasedir = workpath.dentry; @@ -1156,11 +1165,13 @@ out_put_lowerpath: out_free_lowertmp: kfree(lowertmp); out_unlock_workdentry: - ovl_inuse_unlock(workpath.dentry); + if (ufs->workdir_locked) + ovl_inuse_unlock(workpath.dentry); out_put_workpath: path_put(&workpath); out_unlock_upperdentry: - ovl_inuse_unlock(upperpath.dentry); + if (ufs->upperdir_locked) + ovl_inuse_unlock(upperpath.dentry); out_put_upperpath: path_put(&upperpath); out_free_config: diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 117794582f9f..b9b239fa5cfd 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -430,7 +430,7 @@ void ovl_inuse_unlock(struct dentry *dentry) } } -/* Called must hold OVL_I(inode)->oi_lock */ +/* Caller must hold OVL_I(inode)->lock */ static void ovl_cleanup_index(struct dentry *dentry) { struct inode *dir = ovl_indexdir(dentry->d_sb)->d_inode; @@ -469,6 +469,9 @@ static void ovl_cleanup_index(struct dentry *dentry) err = PTR_ERR(index); if (!IS_ERR(index)) err = ovl_cleanup(dir, index); + else + index = NULL; + inode_unlock(dir); if (err) goto fail; @@ -557,3 +560,22 @@ void ovl_nlink_end(struct dentry *dentry, bool locked) mutex_unlock(&OVL_I(d_inode(dentry))->lock); } } + +int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir) +{ + /* Workdir should not be the same as upperdir */ + if (workdir == upperdir) + goto err; + + /* Workdir should not be subdir of upperdir and vice versa */ + if (lock_rename(workdir, upperdir) != NULL) + goto err_unlock; + + return 0; + +err_unlock: + unlock_rename(workdir, upperdir); +err: + pr_err("overlayfs: failed to lock workdir+upperdir\n"); + return -EIO; +} diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index bc6c6e10a969..e9db7fc95b70 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -2122,11 +2122,31 @@ xfs_swap_extents( ip->i_d.di_flags2 |= tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK; tip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; tip->i_d.di_flags2 |= f & XFS_DIFLAG2_REFLINK; + } + + /* Swap the cow forks. */ + if (xfs_sb_version_hasreflink(&mp->m_sb)) { + xfs_extnum_t extnum; + + ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS); + ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS); + + extnum = ip->i_cnextents; + ip->i_cnextents = tip->i_cnextents; + tip->i_cnextents = extnum; + cowfp = ip->i_cowfp; ip->i_cowfp = tip->i_cowfp; tip->i_cowfp = cowfp; - xfs_inode_set_cowblocks_tag(ip); - xfs_inode_set_cowblocks_tag(tip); + + if (ip->i_cowfp && ip->i_cnextents) + xfs_inode_set_cowblocks_tag(ip); + else + xfs_inode_clear_cowblocks_tag(ip); + if (tip->i_cowfp && tip->i_cnextents) + xfs_inode_set_cowblocks_tag(tip); + else + xfs_inode_clear_cowblocks_tag(tip); } xfs_trans_log_inode(tp, ip, src_log_flags); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 3246815c24d6..37e603bf1591 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -736,7 +736,13 @@ xfs_reflink_end_cow( /* If there is a hole at end_fsb - 1 go to the previous extent */ if (!xfs_iext_lookup_extent(ip, ifp, end_fsb - 1, &idx, &got) || got.br_startoff > end_fsb) { - ASSERT(idx > 0); + /* + * In case of racing, overlapping AIO writes no COW extents + * might be left by the time I/O completes for the loser of + * the race. In that case we are done. + */ + if (idx <= 0) + goto out_cancel; xfs_iext_get_extent(ifp, --idx, &got); } @@ -809,6 +815,7 @@ next_extent: out_defer: xfs_defer_cancel(&dfops); +out_cancel: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); out: diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 60e5d90cb18a..3ce61342fa31 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -333,8 +333,8 @@ struct virtchnl_vsi_queue_config_info { * additional queues must be negotiated. This is a best effort request as it * is possible the PF does not have enough queues left to support the request. * If the PF cannot support the number requested it will respond with the - * maximum number it is able to support; otherwise it will respond with the - * number requested. + * maximum number it is able to support. If the request is successful, PF will + * then reset the VF to institute required changes. */ /* VF resource request */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a67daea731ab..1e334b248ff6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -56,7 +56,10 @@ struct bpf_map { struct work_struct work; atomic_t usercnt; struct bpf_map *inner_map_meta; - u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; +#ifdef CONFIG_SECURITY + void *security; +#endif }; /* function argument constraints */ @@ -157,6 +160,11 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) aux->ctx_field_size = size; } +struct bpf_prog_ops { + int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr); +}; + struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); @@ -172,8 +180,6 @@ struct bpf_verifier_ops { const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); - int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, - union bpf_attr __user *uattr); }; struct bpf_prog_aux { @@ -184,12 +190,15 @@ struct bpf_prog_aux { u32 id; struct latch_tree_node ksym_tnode; struct list_head ksym_lnode; - const struct bpf_verifier_ops *ops; + const struct bpf_prog_ops *ops; struct bpf_map **used_maps; struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ - u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; +#ifdef CONFIG_SECURITY + void *security; +#endif union { struct work_struct work; struct rcu_head rcu; @@ -279,14 +288,21 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); -#define BPF_PROG_TYPE(_id, _ops) \ - extern const struct bpf_verifier_ops _ops; +extern const struct file_operations bpf_map_fops; +extern const struct file_operations bpf_prog_fops; + +#define BPF_PROG_TYPE(_id, _name) \ + extern const struct bpf_prog_ops _name ## _prog_ops; \ + extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ extern const struct bpf_map_ops _ops; #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE +extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops; +extern const struct bpf_verifier_ops xdp_analyzer_ops; + struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); @@ -308,11 +324,11 @@ void bpf_map_area_free(void *base); extern int sysctl_unprivileged_bpf_disabled; -int bpf_map_new_fd(struct bpf_map *map); +int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); -int bpf_obj_get_user(const char __user *pathname); +int bpf_obj_get_user(const char __user *pathname, int flags); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); @@ -331,6 +347,8 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); +int bpf_get_file_flag(int flags); + /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. * Best-effort only. No barriers here, since it _will_ race with concurrent @@ -355,6 +373,13 @@ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); +struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); +void __cpu_map_insert_ctx(struct bpf_map *map, u32 index); +void __cpu_map_flush(struct bpf_map *map); +struct xdp_buff; +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, + struct net_device *dev_rx); + /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) { @@ -362,7 +387,7 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) attr->numa_node : NUMA_NO_NODE; } -#else +#else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { return ERR_PTR(-EOPNOTSUPP); @@ -407,6 +432,11 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } +static inline int bpf_obj_get_user(const char __user *pathname, int flags) +{ + return -EOPNOTSUPP; +} + static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { @@ -420,6 +450,28 @@ static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index) static inline void __dev_map_flush(struct bpf_map *map) { } + +static inline +struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) +{ + return NULL; +} + +static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index) +{ +} + +static inline void __cpu_map_flush(struct bpf_map *map) +{ +} + +struct xdp_buff; +static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, + struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + return 0; +} #endif /* CONFIG_BPF_SYSCALL */ #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 6f1a567667b8..36418ad43245 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -1,22 +1,22 @@ /* internal file - do not include directly */ #ifdef CONFIG_NET -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act) +BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb) #endif #ifdef CONFIG_BPF_EVENTS -BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe) +BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint) +BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) @@ -41,4 +41,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) #ifdef CONFIG_STREAM_PARSER BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) #endif +BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b8d200f60a40..feeaea93d959 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -115,6 +115,21 @@ struct bpf_insn_aux_data { #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ +#define BPF_VERIFIER_TMP_LOG_SIZE 1024 + +struct bpf_verifer_log { + u32 level; + char kbuf[BPF_VERIFIER_TMP_LOG_SIZE]; + char __user *ubuf; + u32 len_used; + u32 len_total; +}; + +static inline bool bpf_verifier_log_full(const struct bpf_verifer_log *log) +{ + return log->len_used >= log->len_total - 1; +} + struct bpf_verifier_env; struct bpf_ext_analyzer_ops { int (*insn_hook)(struct bpf_verifier_env *env, @@ -126,6 +141,7 @@ struct bpf_ext_analyzer_ops { */ struct bpf_verifier_env { struct bpf_prog *prog; /* eBPF program being verified */ + const struct bpf_verifier_ops *ops; struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ @@ -139,6 +155,8 @@ struct bpf_verifier_env { bool allow_ptr_leaks; bool seen_direct_write; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ + + struct bpf_verifer_log log; }; int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index abcda9b458ab..9ac9e3e3d1e5 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -63,6 +63,7 @@ #define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00002000 #define PHY_BRCM_CLEAR_RGMII_MODE 0x00004000 #define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000 +#define PHY_BRCM_EN_MASTER_MODE 0x00010000 /* Broadcom BCM7xxx specific workarounds */ #define PHY_BRCM_7XXX_REV(x) (((x) >> 8) & 0xff) diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h index a4be70398ce1..f69f98541953 100644 --- a/include/linux/dynamic_queue_limits.h +++ b/include/linux/dynamic_queue_limits.h @@ -98,7 +98,7 @@ void dql_completed(struct dql *dql, unsigned int count); void dql_reset(struct dql *dql); /* Initialize dql state */ -int dql_init(struct dql *dql, unsigned hold_time); +void dql_init(struct dql *dql, unsigned int hold_time); #endif /* _KERNEL_ */ diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 4587a4c36923..c77fa3529e15 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -163,6 +163,16 @@ extern int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings); +/** + * ethtool_intersect_link_masks - Given two link masks, AND them together + * @dst: first mask and where result is stored + * @src: second mask to intersect with + * + * Given two link mode masks, AND them together and save the result in dst. + */ +void ethtool_intersect_link_masks(struct ethtool_link_ksettings *dst, + struct ethtool_link_ksettings *src); + void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst, u32 legacy_u32); diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 55a604ad459f..ee6657a0ed69 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2445,6 +2445,7 @@ enum ieee80211_sa_query_action { #define WLAN_OUI_TYPE_MICROSOFT_WPA 1 #define WLAN_OUI_TYPE_MICROSOFT_WMM 2 #define WLAN_OUI_TYPE_MICROSOFT_WPS 4 +#define WLAN_OUI_TYPE_MICROSOFT_TPC 8 /* * WMM/802.11e Tspec Element diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 3cd18ac0697f..02639ebea2f0 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -49,6 +49,7 @@ struct br_ip_list { #define BR_MULTICAST_TO_UNICAST BIT(12) #define BR_VLAN_TUNNEL BIT(13) #define BR_BCAST_FLOOD BIT(14) +#define BR_NEIGH_SUPPRESS BIT(15) #define BR_DEFAULT_AGEING_TIME (300 * HZ) @@ -63,6 +64,7 @@ int br_multicast_list_adjacent(struct net_device *dev, bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto); bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto); bool br_multicast_enabled(const struct net_device *dev); +bool br_multicast_router(const struct net_device *dev); #else static inline int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) @@ -83,6 +85,10 @@ static inline bool br_multicast_enabled(const struct net_device *dev) { return false; } +static inline bool br_multicast_router(const struct net_device *dev) +{ + return false; +} #endif #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) diff --git a/include/linux/if_phonet.h b/include/linux/if_phonet.h index bbcdb0a767d8..a118ee4a8428 100644 --- a/include/linux/if_phonet.h +++ b/include/linux/if_phonet.h @@ -10,5 +10,5 @@ #include <uapi/linux/if_phonet.h> -extern struct header_ops phonet_header_ops; +extern const struct header_ops phonet_header_ops; #endif diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 751d051f0bc7..681dff30940b 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -154,6 +154,7 @@ struct in_ifaddr { struct in_validator_info { __be32 ivi_addr; struct in_device *ivi_dev; + struct netlink_ext_ack *extack; }; int register_inetaddr_notifier(struct notifier_block *nb); diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index c9258124e417..7161d8e7ee79 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1351,6 +1351,40 @@ * @inode we wish to get the security context of. * @ctx is a pointer in which to place the allocated security context. * @ctxlen points to the place to put the length of @ctx. + * + * Security hooks for using the eBPF maps and programs functionalities through + * eBPF syscalls. + * + * @bpf: + * Do a initial check for all bpf syscalls after the attribute is copied + * into the kernel. The actual security module can implement their own + * rules to check the specific cmd they need. + * + * @bpf_map: + * Do a check when the kernel generate and return a file descriptor for + * eBPF maps. + * + * @map: bpf map that we want to access + * @mask: the access flags + * + * @bpf_prog: + * Do a check when the kernel generate and return a file descriptor for + * eBPF programs. + * + * @prog: bpf prog that userspace want to use. + * + * @bpf_map_alloc_security: + * Initialize the security field inside bpf map. + * + * @bpf_map_free_security: + * Clean up the security information stored inside bpf map. + * + * @bpf_prog_alloc_security: + * Initialize the security field inside bpf program. + * + * @bpf_prog_free_security: + * Clean up the security information stored inside bpf prog. + * */ union security_list_options { int (*binder_set_context_mgr)(struct task_struct *mgr); @@ -1682,6 +1716,17 @@ union security_list_options { struct audit_context *actx); void (*audit_rule_free)(void *lsmrule); #endif /* CONFIG_AUDIT */ + +#ifdef CONFIG_BPF_SYSCALL + int (*bpf)(int cmd, union bpf_attr *attr, + unsigned int size); + int (*bpf_map)(struct bpf_map *map, fmode_t fmode); + int (*bpf_prog)(struct bpf_prog *prog); + int (*bpf_map_alloc_security)(struct bpf_map *map); + void (*bpf_map_free_security)(struct bpf_map *map); + int (*bpf_prog_alloc_security)(struct bpf_prog_aux *aux); + void (*bpf_prog_free_security)(struct bpf_prog_aux *aux); +#endif /* CONFIG_BPF_SYSCALL */ }; struct security_hook_heads { @@ -1901,6 +1946,15 @@ struct security_hook_heads { struct list_head audit_rule_match; struct list_head audit_rule_free; #endif /* CONFIG_AUDIT */ +#ifdef CONFIG_BPF_SYSCALL + struct list_head bpf; + struct list_head bpf_map; + struct list_head bpf_prog; + struct list_head bpf_map_alloc_security; + struct list_head bpf_map_free_security; + struct list_head bpf_prog_alloc_security; + struct list_head bpf_prog_free_security; +#endif /* CONFIG_BPF_SYSCALL */ } __randomize_layout; /* diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 401c8972cc3a..08c77b7e59cb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -49,6 +49,8 @@ #include <linux/mlx5/device.h> #include <linux/mlx5/doorbell.h> #include <linux/mlx5/srq.h> +#include <linux/timecounter.h> +#include <linux/ptp_clock_kernel.h> enum { MLX5_BOARD_ID_LEN = 64, @@ -760,6 +762,27 @@ struct mlx5_rsvd_gids { struct ida ida; }; +#define MAX_PIN_NUM 8 +struct mlx5_pps { + u8 pin_caps[MAX_PIN_NUM]; + struct work_struct out_work; + u64 start[MAX_PIN_NUM]; + u8 enabled; +}; + +struct mlx5_clock { + rwlock_t lock; + struct cyclecounter cycles; + struct timecounter tc; + struct hwtstamp_config hwtstamp_config; + u32 nominal_c_mult; + unsigned long overflow_period; + struct delayed_work overflow_work; + struct ptp_clock *ptp; + struct ptp_clock_info ptp_info; + struct mlx5_pps pps_info; +}; + struct mlx5_core_dev { struct pci_dev *pdev; /* sync pci state */ @@ -800,6 +823,7 @@ struct mlx5_core_dev { #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rmap; #endif + struct mlx5_clock clock; }; struct mlx5_db { diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index f3f2d07feb2a..9a43763a68ad 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -316,7 +316,7 @@ struct mmc_host { #define MMC_CAP_UHS_SDR50 (1 << 18) /* Host supports UHS SDR50 mode */ #define MMC_CAP_UHS_SDR104 (1 << 19) /* Host supports UHS SDR104 mode */ #define MMC_CAP_UHS_DDR50 (1 << 20) /* Host supports UHS DDR50 mode */ -#define MMC_CAP_NO_BOUNCE_BUFF (1 << 21) /* Disable bounce buffers on host */ +/* (1 << 21) is free for reuse */ #define MMC_CAP_DRIVER_TYPE_A (1 << 23) /* Host supports Driver Type A */ #define MMC_CAP_DRIVER_TYPE_C (1 << 24) /* Host supports Driver Type C */ #define MMC_CAP_DRIVER_TYPE_D (1 << 25) /* Host supports Driver Type D */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 31bb3010c69b..bf014afcb914 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3260,6 +3260,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); +int netif_receive_skb_core(struct sk_buff *skb); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 2c2a5514b0df..528b24c78308 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -108,9 +108,10 @@ struct ebt_table { #define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \ ~(__alignof__(struct _xt_align)-1)) -extern struct ebt_table *ebt_register_table(struct net *net, - const struct ebt_table *table, - const struct nf_hook_ops *); +extern int ebt_register_table(struct net *net, + const struct ebt_table *table, + const struct nf_hook_ops *ops, + struct ebt_table **res); extern void ebt_unregister_table(struct net *net, struct ebt_table *table, const struct nf_hook_ops *); extern unsigned int ebt_do_table(struct sk_buff *skb, diff --git a/include/linux/nmi.h b/include/linux/nmi.h index a36abe2da13e..27e249ed7c5c 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -12,11 +12,31 @@ #ifdef CONFIG_LOCKUP_DETECTOR void lockup_detector_init(void); +void lockup_detector_soft_poweroff(void); +void lockup_detector_cleanup(void); +bool is_hardlockup(void); + +extern int watchdog_user_enabled; +extern int nmi_watchdog_user_enabled; +extern int soft_watchdog_user_enabled; +extern int watchdog_thresh; +extern unsigned long watchdog_enabled; + +extern struct cpumask watchdog_cpumask; +extern unsigned long *watchdog_cpumask_bits; +#ifdef CONFIG_SMP +extern int sysctl_softlockup_all_cpu_backtrace; +extern int sysctl_hardlockup_all_cpu_backtrace; #else -static inline void lockup_detector_init(void) -{ -} -#endif +#define sysctl_softlockup_all_cpu_backtrace 0 +#define sysctl_hardlockup_all_cpu_backtrace 0 +#endif /* !CONFIG_SMP */ + +#else /* CONFIG_LOCKUP_DETECTOR */ +static inline void lockup_detector_init(void) { } +static inline void lockup_detector_soft_poweroff(void) { } +static inline void lockup_detector_cleanup(void) { } +#endif /* !CONFIG_LOCKUP_DETECTOR */ #ifdef CONFIG_SOFTLOCKUP_DETECTOR extern void touch_softlockup_watchdog_sched(void); @@ -24,29 +44,17 @@ extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; -extern int soft_watchdog_enabled; -extern atomic_t watchdog_park_in_progress; #else -static inline void touch_softlockup_watchdog_sched(void) -{ -} -static inline void touch_softlockup_watchdog(void) -{ -} -static inline void touch_softlockup_watchdog_sync(void) -{ -} -static inline void touch_all_softlockup_watchdogs(void) -{ -} +static inline void touch_softlockup_watchdog_sched(void) { } +static inline void touch_softlockup_watchdog(void) { } +static inline void touch_softlockup_watchdog_sync(void) { } +static inline void touch_all_softlockup_watchdogs(void) { } #endif #ifdef CONFIG_DETECT_HUNG_TASK void reset_hung_task_detector(void); #else -static inline void reset_hung_task_detector(void) -{ -} +static inline void reset_hung_task_detector(void) { } #endif /* @@ -54,12 +62,12 @@ static inline void reset_hung_task_detector(void) * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit - * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector. * - * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled' - * are variables that are only used as an 'interface' between the parameters - * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The - * 'watchdog_thresh' variable is handled differently because its value is not - * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh' - * is equal zero. + * 'watchdog_user_enabled', 'nmi_watchdog_user_enabled' and + * 'soft_watchdog_user_enabled' are variables that are only used as an + * 'interface' between the parameters in /proc/sys/kernel and the internal + * state bits in 'watchdog_enabled'. The 'watchdog_thresh' variable is + * handled differently because its value is not boolean, and the lockup + * detectors are 'suspended' while 'watchdog_thresh' is equal zero. */ #define NMI_WATCHDOG_ENABLED_BIT 0 #define SOFT_WATCHDOG_ENABLED_BIT 1 @@ -73,17 +81,41 @@ extern unsigned int hardlockup_panic; static inline void hardlockup_detector_disable(void) {} #endif +#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) +# define NMI_WATCHDOG_SYSCTL_PERM 0644 +#else +# define NMI_WATCHDOG_SYSCTL_PERM 0444 +#endif + #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) extern void arch_touch_nmi_watchdog(void); +extern void hardlockup_detector_perf_stop(void); +extern void hardlockup_detector_perf_restart(void); +extern void hardlockup_detector_perf_disable(void); +extern void hardlockup_detector_perf_enable(void); +extern void hardlockup_detector_perf_cleanup(void); +extern int hardlockup_detector_perf_init(void); #else -#if !defined(CONFIG_HAVE_NMI_WATCHDOG) +static inline void hardlockup_detector_perf_stop(void) { } +static inline void hardlockup_detector_perf_restart(void) { } +static inline void hardlockup_detector_perf_disable(void) { } +static inline void hardlockup_detector_perf_enable(void) { } +static inline void hardlockup_detector_perf_cleanup(void) { } +# if !defined(CONFIG_HAVE_NMI_WATCHDOG) +static inline int hardlockup_detector_perf_init(void) { return -ENODEV; } static inline void arch_touch_nmi_watchdog(void) {} +# else +static inline int hardlockup_detector_perf_init(void) { return 0; } +# endif #endif -#endif + +void watchdog_nmi_stop(void); +void watchdog_nmi_start(void); +int watchdog_nmi_probe(void); /** * touch_nmi_watchdog - restart NMI watchdog timeout. - * + * * If the architecture supports the NMI watchdog, touch_nmi_watchdog() * may be used to reset the timeout - for code which intentionally * disables interrupts for a long time. This call is stateless. @@ -153,22 +185,6 @@ static inline bool trigger_single_cpu_backtrace(int cpu) u64 hw_nmi_get_sample_period(int watchdog_thresh); #endif -#ifdef CONFIG_LOCKUP_DETECTOR -extern int nmi_watchdog_enabled; -extern int watchdog_user_enabled; -extern int watchdog_thresh; -extern unsigned long watchdog_enabled; -extern struct cpumask watchdog_cpumask; -extern unsigned long *watchdog_cpumask_bits; -extern int __read_mostly watchdog_suspended; -#ifdef CONFIG_SMP -extern int sysctl_softlockup_all_cpu_backtrace; -extern int sysctl_hardlockup_all_cpu_backtrace; -#else -#define sysctl_softlockup_all_cpu_backtrace 0 -#define sysctl_hardlockup_all_cpu_backtrace 0 -#endif - #if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \ defined(CONFIG_HARDLOCKUP_DETECTOR) void watchdog_update_hrtimer_threshold(u64 period); @@ -176,7 +192,6 @@ void watchdog_update_hrtimer_threshold(u64 period); static inline void watchdog_update_hrtimer_threshold(u64 period) { } #endif -extern bool is_hardlockup(void); struct ctl_table; extern int proc_watchdog(struct ctl_table *, int , void __user *, size_t *, loff_t *); @@ -188,18 +203,6 @@ extern int proc_watchdog_thresh(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int proc_watchdog_cpumask(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int lockup_detector_suspend(void); -extern void lockup_detector_resume(void); -#else -static inline int lockup_detector_suspend(void) -{ - return 0; -} - -static inline void lockup_detector_resume(void) -{ -} -#endif #ifdef CONFIG_HAVE_ACPI_APEI_NMI #include <asm/nmi.h> diff --git a/include/linux/once.h b/include/linux/once.h index 9c98aaa87cbc..724724918e8b 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -5,7 +5,7 @@ #include <linux/jump_label.h> bool __do_once_start(bool *done, unsigned long *flags); -void __do_once_done(bool *done, struct static_key *once_key, +void __do_once_done(bool *done, struct static_key_true *once_key, unsigned long *flags); /* Call a function exactly once. The idea of DO_ONCE() is to perform @@ -38,8 +38,8 @@ void __do_once_done(bool *done, struct static_key *once_key, ({ \ bool ___ret = false; \ static bool ___done = false; \ - static struct static_key ___once_key = STATIC_KEY_INIT_TRUE; \ - if (static_key_true(&___once_key)) { \ + static DEFINE_STATIC_KEY_TRUE(___once_key); \ + if (static_branch_unlikely(&___once_key)) { \ unsigned long ___flags; \ ___ret = __do_once_start(&___done, &___flags); \ if (unlikely(___ret)) { \ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8e22f24ded6a..79b18a20cf5d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -806,6 +806,7 @@ struct perf_output_handle { struct bpf_perf_event_data_kern { struct pt_regs *regs; struct perf_sample_data *data; + struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF @@ -884,7 +885,8 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); -int perf_event_read_local(struct perf_event *event, u64 *value); +int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); @@ -1286,7 +1288,8 @@ static inline const struct perf_event_attr *perf_event_attrs(struct perf_event * { return ERR_PTR(-EINVAL); } -static inline int perf_event_read_local(struct perf_event *event, u64 *value) +static inline int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running) { return -EINVAL; } diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index 89fa0bbd54f3..e755954d85fd 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -64,6 +64,7 @@ enum qed_ll2_roce_flavor_type { enum qed_ll2_tx_dest { QED_LL2_TX_DEST_NW, /* Light L2 TX Destination to the Network */ QED_LL2_TX_DEST_LB, /* Light L2 TX Destination to the Loopback */ + QED_LL2_TX_DEST_DROP, /* Light L2 Drop the TX packet */ QED_LL2_TX_DEST_MAX }; @@ -150,11 +151,16 @@ void (*qed_ll2_release_tx_packet_cb)(void *cxt, dma_addr_t first_frag_addr, bool b_last_fragment, bool b_last_packet); +typedef +void (*qed_ll2_slowpath_cb)(void *cxt, u8 connection_handle, + u32 opaque_data_0, u32 opaque_data_1); + struct qed_ll2_cbs { qed_ll2_complete_rx_packet_cb rx_comp_cb; qed_ll2_release_rx_packet_cb rx_release_cb; qed_ll2_complete_tx_packet_cb tx_comp_cb; qed_ll2_release_tx_packet_cb tx_release_cb; + qed_ll2_slowpath_cb slowpath_cb; void *cookie; }; @@ -171,6 +177,7 @@ struct qed_ll2_acquire_data_inputs { enum qed_ll2_tx_dest tx_dest; enum qed_ll2_error_handle ai_err_packet_too_big; enum qed_ll2_error_handle ai_err_no_buf; + bool secondary_queue; u8 gsi_enable; }; diff --git a/include/linux/security.h b/include/linux/security.h index ce6265960d6c..18800b0911e5 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -31,6 +31,7 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/fs.h> +#include <linux/bpf.h> struct linux_binprm; struct cred; @@ -1730,6 +1731,50 @@ static inline void securityfs_remove(struct dentry *dentry) #endif +#ifdef CONFIG_BPF_SYSCALL +#ifdef CONFIG_SECURITY +extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size); +extern int security_bpf_map(struct bpf_map *map, fmode_t fmode); +extern int security_bpf_prog(struct bpf_prog *prog); +extern int security_bpf_map_alloc(struct bpf_map *map); +extern void security_bpf_map_free(struct bpf_map *map); +extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux); +extern void security_bpf_prog_free(struct bpf_prog_aux *aux); +#else +static inline int security_bpf(int cmd, union bpf_attr *attr, + unsigned int size) +{ + return 0; +} + +static inline int security_bpf_map(struct bpf_map *map, fmode_t fmode) +{ + return 0; +} + +static inline int security_bpf_prog(struct bpf_prog *prog) +{ + return 0; +} + +static inline int security_bpf_map_alloc(struct bpf_map *map) +{ + return 0; +} + +static inline void security_bpf_map_free(struct bpf_map *map) +{ } + +static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +{ + return 0; +} + +static inline void security_bpf_prog_free(struct bpf_prog_aux *aux) +{ } +#endif /* CONFIG_SECURITY */ +#endif /* CONFIG_BPF_SYSCALL */ + #ifdef CONFIG_SECURITY static inline char *alloc_secdata(void) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 01a985937867..03634ec2f918 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3158,6 +3158,12 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) return __skb_grow(skb, len); } +#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) +#define skb_rb_first(root) rb_to_skb(rb_first(root)) +#define skb_rb_last(root) rb_to_skb(rb_last(root)) +#define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode)) +#define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode)) + #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ @@ -3172,6 +3178,18 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) for (; skb != (struct sk_buff *)(queue); \ skb = skb->next) +#define skb_rbtree_walk(skb, root) \ + for (skb = skb_rb_first(root); skb != NULL; \ + skb = skb_rb_next(skb)) + +#define skb_rbtree_walk_from(skb) \ + for (; skb != NULL; \ + skb = skb_rb_next(skb)) + +#define skb_rbtree_walk_from_safe(skb, tmp) \ + for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \ + skb = tmp) + #define skb_queue_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index 12910cf19869..c149aa7bedf3 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -55,7 +55,7 @@ smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) } void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread); -int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *); +void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, + const struct cpumask *); #endif diff --git a/include/net/act_api.h b/include/net/act_api.h index b944e0eb93be..f5e8c9048fb0 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -93,8 +93,7 @@ struct tc_action_ops { int (*walk)(struct net *, struct sk_buff *, struct netlink_callback *, int, const struct tc_action_ops *); void (*stats_update)(struct tc_action *, u64, u32, u64); - int (*get_dev)(const struct tc_action *a, struct net *net, - struct net_device **mirred_dev); + struct net_device *(*get_dev)(const struct tc_action *a); }; struct tc_action_net { @@ -175,4 +174,38 @@ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, #endif } +typedef int tc_setup_cb_t(enum tc_setup_type type, + void *type_data, void *cb_priv); + +#ifdef CONFIG_NET_CLS_ACT +int tc_setup_cb_egdev_register(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv); +void tc_setup_cb_egdev_unregister(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv); +int tc_setup_cb_egdev_call(const struct net_device *dev, + enum tc_setup_type type, void *type_data, + bool err_stop); +#else +static inline +int tc_setup_cb_egdev_register(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ + return 0; +} + +static inline +void tc_setup_cb_egdev_unregister(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ +} + +static inline +int tc_setup_cb_egdev_call(const struct net_device *dev, + enum tc_setup_type type, void *type_data, + bool err_stop) +{ + return 0; +} +#endif + #endif diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 87981cd63180..b8b16437c6d5 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -55,6 +55,7 @@ struct prefix_info { struct in6_validator_info { struct in6_addr i6vi_addr; struct inet6_dev *i6vi_dev; + struct netlink_ext_ack *extack; }; #define IN6_ADDR_HSIZE_SHIFT 4 diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 3ac79150291f..2b3a6eec4570 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -49,17 +49,19 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *, unsigned long, s64, gfp_t, - rxrpc_notify_rx_t); + rxrpc_notify_rx_t, + bool); int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *, struct msghdr *, size_t, rxrpc_notify_end_tx_t); int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *, - void *, size_t, size_t *, bool, u32 *); + void *, size_t, size_t *, bool, u32 *, u16 *); bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *, u32, int, const char *); void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *); void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *, struct sockaddr_rxrpc *); +u64 rxrpc_kernel_get_rtt(struct socket *, struct rxrpc_call *); int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, rxrpc_user_attach_call_t, unsigned long, gfp_t); void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64); @@ -67,5 +69,6 @@ int rxrpc_kernel_retry_call(struct socket *, struct rxrpc_call *, struct sockaddr_rxrpc *, struct key *); int rxrpc_kernel_check_call(struct socket *, struct rxrpc_call *, enum rxrpc_call_completion *, u32 *); +u32 rxrpc_kernel_check_life(struct socket *, struct rxrpc_call *); #endif /* _NET_RXRPC_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f12fa5245a45..8b8118a7fadb 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4347,19 +4347,6 @@ static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, } /** - * ieee80211_data_from_8023 - convert an 802.3 frame to 802.11 - * @skb: the 802.3 frame - * @addr: the device MAC address - * @iftype: the virtual interface type - * @bssid: the network bssid (used only for iftype STATION and ADHOC) - * @qos: build 802.11 QoS data frame - * Return: 0 on success, or a negative error code. - */ -int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr, - enum nl80211_iftype iftype, const u8 *bssid, - bool qos); - -/** * ieee80211_amsdu_to_8023s - decode an IEEE 802.11n A-MSDU frame * * Decode an IEEE 802.11 A-MSDU and convert it to a list of 802.3 frames. @@ -5441,9 +5428,6 @@ cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid, * @req_ie_len: association request IEs length * @resp_ie: association response IEs (may be %NULL) * @resp_ie_len: assoc response IEs length - * @authorized: true if the 802.1X authentication was done by the driver or is - * not needed (e.g., when Fast Transition protocol was used), false - * otherwise. Ignored for networks that don't use 802.1X authentication. */ struct cfg80211_roam_info { struct ieee80211_channel *channel; @@ -5453,7 +5437,6 @@ struct cfg80211_roam_info { size_t req_ie_len; const u8 *resp_ie; size_t resp_ie_len; - bool authorized; }; /** @@ -5478,6 +5461,23 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, gfp_t gfp); /** + * cfg80211_port_authorized - notify cfg80211 of successful security association + * + * @dev: network device + * @bssid: the BSSID of the AP + * @gfp: allocation flags + * + * This function should be called by a driver that supports 4 way handshake + * offload after a security association was successfully established (i.e., + * the 4 way handshake was completed successfully). The call to this function + * should be preceded with a call to cfg80211_connect_result(), + * cfg80211_connect_done(), cfg80211_connect_bss() or cfg80211_roamed() to + * indicate the 802.11 association. + */ +void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, + gfp_t gfp); + +/** * cfg80211_disconnected - notify cfg80211 that connection was dropped * * @dev: network device @@ -5934,7 +5934,8 @@ int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len, * @ies: the IE buffer * @ielen: the length of the IE buffer * @ids: an array with element IDs that are allowed before - * the split + * the split. A WLAN_EID_EXTENSION value means that the next + * EID in the list is a sub-element of the EXTENSION IE. * @n_ids: the size of the element ID array * @after_ric: array IE types that come after the RIC element * @n_after_ric: size of the @after_ric array @@ -5965,7 +5966,8 @@ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, * @ies: the IE buffer * @ielen: the length of the IE buffer * @ids: an array with element IDs that are allowed before - * the split + * the split. A WLAN_EID_EXTENSION value means that the next + * EID in the list is a sub-element of the EXTENSION IE. * @n_ids: the size of the element ID array * @offset: offset where to start splitting in the buffer * diff --git a/include/net/dn.h b/include/net/dn.h index 913b73d239f5..4394f7d5cfe8 100644 --- a/include/net/dn.h +++ b/include/net/dn.h @@ -122,13 +122,6 @@ struct dn_scp /* Session Control Port */ unsigned long keepalive; void (*keepalive_fxn)(struct sock *sk); - /* - * This stuff is for the fast timer for delayed acks - */ - struct timer_list delack_timer; - int delack_pending; - void (*delack_fxn)(struct sock *sk); - }; static inline struct dn_scp *DN_SK(struct sock *sk) diff --git a/include/net/dn_nsp.h b/include/net/dn_nsp.h index 3a3e33d18456..413a15e5339c 100644 --- a/include/net/dn_nsp.h +++ b/include/net/dn_nsp.h @@ -17,7 +17,6 @@ void dn_nsp_send_data_ack(struct sock *sk); void dn_nsp_send_oth_ack(struct sock *sk); -void dn_nsp_delayed_ack(struct sock *sk); void dn_send_conn_ack(struct sock *sk); void dn_send_conn_conf(struct sock *sk, gfp_t gfp); void dn_nsp_send_disc(struct sock *sk, unsigned char type, diff --git a/include/net/dsa.h b/include/net/dsa.h index 10dceccd9ce8..38961ef91d3d 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -164,6 +164,14 @@ struct dsa_mall_tc_entry { struct dsa_port { + /* A CPU port is physically connected to a master device. + * A user port exposed to userspace has a slave device. + */ + union { + struct net_device *master; + struct net_device *slave; + }; + /* CPU port tagging operations used by master or slave devices */ const struct dsa_device_ops *tag_ops; @@ -176,7 +184,6 @@ struct dsa_port { unsigned int index; const char *name; struct dsa_port *cpu_dp; - struct net_device *netdev; struct device_node *dn; unsigned int ageing_time; u8 stp_state; @@ -262,6 +269,11 @@ static inline bool dsa_is_normal_port(struct dsa_switch *ds, int p) return !dsa_is_cpu_port(ds, p) && !dsa_is_dsa_port(ds, p); } +static inline const struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) +{ + return &ds->ports[p]; +} + static inline u8 dsa_upstream_port(struct dsa_switch *ds) { struct dsa_switch_tree *dst = ds->dst; @@ -291,7 +303,6 @@ struct dsa_switch_ops { enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds); int (*setup)(struct dsa_switch *ds); - int (*set_addr)(struct dsa_switch *ds, u8 *addr); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* @@ -471,4 +482,54 @@ static inline int dsa_switch_resume(struct dsa_switch *ds) } #endif /* CONFIG_PM_SLEEP */ +enum dsa_notifier_type { + DSA_PORT_REGISTER, + DSA_PORT_UNREGISTER, +}; + +struct dsa_notifier_info { + struct net_device *dev; +}; + +struct dsa_notifier_register_info { + struct dsa_notifier_info info; /* must be first */ + struct net_device *master; + unsigned int port_number; + unsigned int switch_number; +}; + +static inline struct net_device * +dsa_notifier_info_to_dev(const struct dsa_notifier_info *info) +{ + return info->dev; +} + +#if IS_ENABLED(CONFIG_NET_DSA) +int register_dsa_notifier(struct notifier_block *nb); +int unregister_dsa_notifier(struct notifier_block *nb); +int call_dsa_notifiers(unsigned long val, struct net_device *dev, + struct dsa_notifier_info *info); +#else +static inline int register_dsa_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int unregister_dsa_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int call_dsa_notifiers(unsigned long val, struct net_device *dev, + struct dsa_notifier_info *info) +{ + return NOTIFY_DONE; +} +#endif + +/* Broadcom tag specific helpers to insert and extract queue/port number */ +#define BRCM_TAG_SET_PORT_QUEUE(p, q) ((p) << 8 | q) +#define BRCM_TAG_GET_PORT(v) ((v) >> 8) +#define BRCM_TAG_GET_QUEUE(v) ((v) & 0xff) + #endif diff --git a/include/net/dst.h b/include/net/dst.h index 06a6765da074..5047e8053d6c 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -101,7 +101,7 @@ struct dst_entry { union { struct dst_entry *next; struct rtable __rcu *rt_next; - struct rt6_info *rt6_next; + struct rt6_info __rcu *rt6_next; struct dn_route __rcu *dn_next; }; }; @@ -255,17 +255,18 @@ static inline void dst_hold(struct dst_entry *dst) WARN_ON(atomic_inc_not_zero(&dst->__refcnt) == 0); } -static inline void dst_use(struct dst_entry *dst, unsigned long time) +static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) { - dst_hold(dst); - dst->__use++; - dst->lastuse = time; + if (time != dst->lastuse) { + dst->__use++; + dst->lastuse = time; + } } -static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) +static inline void dst_hold_and_use(struct dst_entry *dst, unsigned long time) { - dst->__use++; - dst->lastuse = time; + dst_hold(dst); + dst_use_noref(dst, time); } static inline struct dst_entry *dst_clone(struct dst_entry *dst) diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 9fba2ebf6dda..87a0bb8d449f 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -87,6 +87,7 @@ static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, void metadata_dst_free(struct metadata_dst *); struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, gfp_t flags); +void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst); struct metadata_dst __percpu * metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags); diff --git a/include/net/fq.h b/include/net/fq.h index 6d8521a30c5c..ac944a686840 100644 --- a/include/net/fq.h +++ b/include/net/fq.h @@ -90,6 +90,13 @@ typedef void fq_skb_free_t(struct fq *, struct fq_flow *, struct sk_buff *); +/* Return %true to filter (drop) the frame. */ +typedef bool fq_skb_filter_t(struct fq *, + struct fq_tin *, + struct fq_flow *, + struct sk_buff *, + void *); + typedef struct fq_flow *fq_flow_get_default_t(struct fq *, struct fq_tin *, int idx, diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h index 4e6131cd3f43..8b237e4afee6 100644 --- a/include/net/fq_impl.h +++ b/include/net/fq_impl.h @@ -12,24 +12,22 @@ /* functions that are embedded into includer */ -static struct sk_buff *fq_flow_dequeue(struct fq *fq, - struct fq_flow *flow) +static void fq_adjust_removal(struct fq *fq, + struct fq_flow *flow, + struct sk_buff *skb) { struct fq_tin *tin = flow->tin; - struct fq_flow *i; - struct sk_buff *skb; - - lockdep_assert_held(&fq->lock); - - skb = __skb_dequeue(&flow->queue); - if (!skb) - return NULL; tin->backlog_bytes -= skb->len; tin->backlog_packets--; flow->backlog -= skb->len; fq->backlog--; fq->memory_usage -= skb->truesize; +} + +static void fq_rejigger_backlog(struct fq *fq, struct fq_flow *flow) +{ + struct fq_flow *i; if (flow->backlog == 0) { list_del_init(&flow->backlogchain); @@ -43,6 +41,21 @@ static struct sk_buff *fq_flow_dequeue(struct fq *fq, list_move_tail(&flow->backlogchain, &i->backlogchain); } +} + +static struct sk_buff *fq_flow_dequeue(struct fq *fq, + struct fq_flow *flow) +{ + struct sk_buff *skb; + + lockdep_assert_held(&fq->lock); + + skb = __skb_dequeue(&flow->queue); + if (!skb) + return NULL; + + fq_adjust_removal(fq, flow, skb); + fq_rejigger_backlog(fq, flow); return skb; } @@ -188,6 +201,45 @@ static void fq_tin_enqueue(struct fq *fq, } } +static void fq_flow_filter(struct fq *fq, + struct fq_flow *flow, + fq_skb_filter_t filter_func, + void *filter_data, + fq_skb_free_t free_func) +{ + struct fq_tin *tin = flow->tin; + struct sk_buff *skb, *tmp; + + lockdep_assert_held(&fq->lock); + + skb_queue_walk_safe(&flow->queue, skb, tmp) { + if (!filter_func(fq, tin, flow, skb, filter_data)) + continue; + + __skb_unlink(skb, &flow->queue); + fq_adjust_removal(fq, flow, skb); + free_func(fq, tin, flow, skb); + } + + fq_rejigger_backlog(fq, flow); +} + +static void fq_tin_filter(struct fq *fq, + struct fq_tin *tin, + fq_skb_filter_t filter_func, + void *filter_data, + fq_skb_free_t free_func) +{ + struct fq_flow *flow; + + lockdep_assert_held(&fq->lock); + + list_for_each_entry(flow, &tin->new_flows, flowchain) + fq_flow_filter(fq, flow, filter_func, filter_data, free_func); + list_for_each_entry(flow, &tin->old_flows, flowchain) + fq_flow_filter(fq, flow, filter_func, filter_data, free_func); +} + static void fq_flow_reset(struct fq *fq, struct fq_flow *flow, fq_skb_free_t free_func) diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 13e4c89a8231..0358745ea059 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -169,9 +169,9 @@ enum inet_csk_ack_state_t { }; void inet_csk_init_xmit_timers(struct sock *sk, - void (*retransmit_handler)(unsigned long), - void (*delack_handler)(unsigned long), - void (*keepalive_handler)(unsigned long)); + void (*retransmit_handler)(struct timer_list *), + void (*delack_handler)(struct timer_list *), + void (*keepalive_handler)(struct timer_list *)); void inet_csk_clear_xmit_timers(struct sock *sk); static inline void inet_csk_schedule_ack(struct sock *sk) diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index fc59e0775e00..c695807ca707 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -95,7 +95,7 @@ struct inet_frags { void (*constructor)(struct inet_frag_queue *q, const void *arg); void (*destructor)(struct inet_frag_queue *); - void (*frag_expire)(unsigned long data); + void (*frag_expire)(struct timer_list *t); struct kmem_cache *frags_cachep; const char *frags_cache_name; }; diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index d060d711a624..10c913816032 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -29,6 +29,14 @@ #define FIB6_TABLE_HASHSZ 1 #endif +#define RT6_DEBUG 2 + +#if RT6_DEBUG >= 3 +#define RT6_TRACE(x...) pr_debug(x) +#else +#define RT6_TRACE(x...) do { ; } while (0) +#endif + struct rt6_info; struct fib6_config { @@ -60,25 +68,30 @@ struct fib6_config { }; struct fib6_node { - struct fib6_node *parent; - struct fib6_node *left; - struct fib6_node *right; + struct fib6_node __rcu *parent; + struct fib6_node __rcu *left; + struct fib6_node __rcu *right; #ifdef CONFIG_IPV6_SUBTREES - struct fib6_node *subtree; + struct fib6_node __rcu *subtree; #endif - struct rt6_info *leaf; + struct rt6_info __rcu *leaf; __u16 fn_bit; /* bit key */ __u16 fn_flags; int fn_sernum; - struct rt6_info *rr_ptr; + struct rt6_info __rcu *rr_ptr; struct rcu_head rcu; }; +struct fib6_gc_args { + int timeout; + int more; +}; + #ifndef CONFIG_IPV6_SUBTREES #define FIB6_SUBTREE(fn) NULL #else -#define FIB6_SUBTREE(fn) ((fn)->subtree) +#define FIB6_SUBTREE(fn) (rcu_dereference_protected((fn)->subtree, 1)) #endif struct mx6_config { @@ -98,6 +111,22 @@ struct rt6key { struct fib6_table; +struct rt6_exception_bucket { + struct hlist_head chain; + int depth; +}; + +struct rt6_exception { + struct hlist_node hlist; + struct rt6_info *rt6i; + unsigned long stamp; + struct rcu_head rcu; +}; + +#define FIB6_EXCEPTION_BUCKET_SIZE_SHIFT 10 +#define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT) +#define FIB6_MAX_DEPTH 5 + struct rt6_info { struct dst_entry dst; @@ -134,14 +163,25 @@ struct rt6_info { struct inet6_dev *rt6i_idev; struct rt6_info * __percpu *rt6i_pcpu; + struct rt6_exception_bucket __rcu *rt6i_exception_bucket; u32 rt6i_metric; u32 rt6i_pmtu; /* more non-fragment space at head required */ unsigned short rt6i_nfheader_len; u8 rt6i_protocol; + u8 exception_bucket_flushed:1, + unused:7; }; +#define for_each_fib6_node_rt_rcu(fn) \ + for (rt = rcu_dereference((fn)->leaf); rt; \ + rt = rcu_dereference(rt->dst.rt6_next)) + +#define for_each_fib6_walker_rt(w) \ + for (rt = (w)->leaf; rt; \ + rt = rcu_dereference_protected(rt->dst.rt6_next, 1)) + static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) { return ((struct rt6_info *)dst)->rt6i_idev; @@ -188,6 +228,8 @@ static inline bool rt6_get_cookie_safe(const struct rt6_info *rt, if (fn) { *cookie = fn->fn_sernum; + /* pairs with smp_wmb() in fib6_update_sernum_upto_root() */ + smp_rmb(); status = true; } @@ -248,7 +290,6 @@ struct fib6_walker { struct fib6_node *root, *node; struct rt6_info *leaf; enum fib6_walk_state state; - bool prune; unsigned int skip; unsigned int count; int (*func)(struct fib6_walker *); @@ -256,12 +297,15 @@ struct fib6_walker { }; struct rt6_statistics { - __u32 fib_nodes; - __u32 fib_route_nodes; - __u32 fib_rt_alloc; /* permanent routes */ - __u32 fib_rt_entries; /* rt entries in table */ - __u32 fib_rt_cache; /* cache routes */ - __u32 fib_discarded_routes; + __u32 fib_nodes; /* all fib6 nodes */ + __u32 fib_route_nodes; /* intermediate nodes */ + __u32 fib_rt_entries; /* rt entries in fib table */ + __u32 fib_rt_cache; /* cached rt entries in exception table */ + __u32 fib_discarded_routes; /* total number of routes delete */ + + /* The following stats are not protected by any lock */ + atomic_t fib_rt_alloc; /* total number of routes alloced */ + atomic_t fib_rt_uncache; /* rt entries in uncached list */ }; #define RTN_TL_ROOT 0x0001 @@ -277,7 +321,7 @@ struct rt6_statistics { struct fib6_table { struct hlist_node tb6_hlist; u32 tb6_id; - rwlock_t tb6_lock; + spinlock_t tb6_lock; struct fib6_node tb6_root; struct inet_peer_base tb6_peers; unsigned int flags; @@ -325,7 +369,8 @@ struct fib6_node *fib6_lookup(struct fib6_node *root, struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, - const struct in6_addr *saddr, int src_len); + const struct in6_addr *saddr, int src_len, + bool exact_match); void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), void *arg); @@ -358,6 +403,8 @@ void __net_exit fib6_notifier_exit(struct net *net); unsigned int fib6_tables_seq_read(struct net *net); int fib6_tables_dump(struct net *net, struct notifier_block *nb); +void fib6_update_sernum(struct rt6_info *rt); + #ifdef CONFIG_IPV6_MULTIPLE_TABLES int fib6_rules_init(void); void fib6_rules_cleanup(void); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index ee96f402cb75..a0087fb9864b 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -95,6 +95,11 @@ int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack); int ip6_ins_rt(struct rt6_info *); int ip6_del_rt(struct rt6_info *); +void rt6_flush_exceptions(struct rt6_info *rt); +int rt6_remove_exception_rt(struct rt6_info *rt); +void rt6_age_exceptions(struct rt6_info *rt, struct fib6_gc_args *gc_args, + unsigned long now); + static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt, const struct in6_addr *daddr, unsigned int prefs, diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 885690fa39c8..cc9073e45be9 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5441,8 +5441,14 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, */ void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn); +/** + * ieee80211_manage_rx_ba_offl - helper to queue an RX BA work + * @vif: &struct ieee80211_vif pointer from the add_interface callback + * @addr: station mac address + * @tid: the rx tid + */ void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, const u8 *addr, - unsigned int bit); + unsigned int tid); /** * ieee80211_start_rx_ba_session_offl - start a Rx BA session diff --git a/include/net/phonet/phonet.h b/include/net/phonet/phonet.h index 039cc29cb4a8..51e1a2a45d02 100644 --- a/include/net/phonet/phonet.h +++ b/include/net/phonet/phonet.h @@ -108,8 +108,10 @@ struct phonet_protocol { int sock_type; }; -int phonet_proto_register(unsigned int protocol, struct phonet_protocol *pp); -void phonet_proto_unregister(unsigned int protocol, struct phonet_protocol *pp); +int phonet_proto_register(unsigned int protocol, + const struct phonet_protocol *pp); +void phonet_proto_unregister(unsigned int protocol, + const struct phonet_protocol *pp); int phonet_sysctl_init(void); void phonet_sysctl_exit(void); diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index e80edd8879ef..49a143e0fe65 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -22,15 +22,26 @@ struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, bool create); void tcf_chain_put(struct tcf_chain *chain); int tcf_block_get(struct tcf_block **p_block, - struct tcf_proto __rcu **p_filter_chain); + struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q); void tcf_block_put(struct tcf_block *block); + +static inline struct Qdisc *tcf_block_q(struct tcf_block *block) +{ + return block->q; +} + +static inline struct net_device *tcf_block_dev(struct tcf_block *block) +{ + return tcf_block_q(block)->dev_queue->dev; +} + int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode); #else static inline int tcf_block_get(struct tcf_block **p_block, - struct tcf_proto __rcu **p_filter_chain) + struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q) { return 0; } @@ -39,6 +50,16 @@ static inline void tcf_block_put(struct tcf_block *block) { } +static inline struct Qdisc *tcf_block_q(struct tcf_block *block) +{ + return NULL; +} + +static inline struct net_device *tcf_block_dev(struct tcf_block *block) +{ + return NULL; +} + static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode) { @@ -53,36 +74,43 @@ __cls_set_class(unsigned long *clp, unsigned long cl) } static inline unsigned long -cls_set_class(struct tcf_proto *tp, unsigned long *clp, - unsigned long cl) +cls_set_class(struct Qdisc *q, unsigned long *clp, unsigned long cl) { unsigned long old_cl; - - tcf_tree_lock(tp); + + sch_tree_lock(q); old_cl = __cls_set_class(clp, cl); - tcf_tree_unlock(tp); - + sch_tree_unlock(q); return old_cl; } static inline void tcf_bind_filter(struct tcf_proto *tp, struct tcf_result *r, unsigned long base) { + struct Qdisc *q = tp->chain->block->q; unsigned long cl; - cl = tp->q->ops->cl_ops->bind_tcf(tp->q, base, r->classid); - cl = cls_set_class(tp, &r->class, cl); + /* Check q as it is not set for shared blocks. In that case, + * setting class is not supported. + */ + if (!q) + return; + cl = q->ops->cl_ops->bind_tcf(q, base, r->classid); + cl = cls_set_class(q, &r->class, cl); if (cl) - tp->q->ops->cl_ops->unbind_tcf(tp->q, cl); + q->ops->cl_ops->unbind_tcf(q, cl); } static inline void tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r) { + struct Qdisc *q = tp->chain->block->q; unsigned long cl; + if (!q) + return; if ((cl = __cls_set_class(&r->class, 0)) != 0) - tp->q->ops->cl_ops->unbind_tcf(tp->q, cl); + q->ops->cl_ops->unbind_tcf(q, cl); } struct tcf_exts { @@ -204,8 +232,6 @@ void tcf_exts_destroy(struct tcf_exts *exts); void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src); int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts); -int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, - struct net_device **hw_dev); /** * struct tcf_pkt_info - packet information @@ -405,6 +431,9 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) } #endif /* CONFIG_NET_CLS_IND */ +int tc_setup_cb_call(struct tcf_exts *exts, enum tc_setup_type type, + void *type_data, bool err_stop); + struct tc_cls_common_offload { u32 chain_index; __be16 protocol; @@ -514,7 +543,6 @@ struct tc_cls_flower_offload { struct fl_flow_key *mask; struct fl_flow_key *key; struct tcf_exts *exts; - bool egress_dev; }; enum tc_matchall_command { @@ -546,6 +574,15 @@ struct tc_cls_bpf_offload { u32 gen_flags; }; +struct tc_mqprio_qopt_offload { + /* struct tc_mqprio_qopt must always be the first element */ + struct tc_mqprio_qopt qopt; + u16 mode; + u16 shaper; + u32 flags; + u64 min_rate[TC_QOPT_MAX_QUEUE]; + u64 max_rate[TC_QOPT_MAX_QUEUE]; +}; /* This structure holds cookie structure that is passed from user * to the kernel for actions and classifiers diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 259bc191ba59..2d234af15f3e 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -4,7 +4,9 @@ #include <linux/jiffies.h> #include <linux/ktime.h> #include <linux/if_vlan.h> +#include <linux/netdevice.h> #include <net/sch_generic.h> +#include <net/net_namespace.h> #include <uapi/linux/pkt_sched.h> #define DEFAULT_TX_QUEUE_LEN 1000 @@ -146,4 +148,9 @@ static inline bool is_classid_clsact_egress(u32 classid) TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_EGRESS); } +static inline struct net *qdisc_net(struct Qdisc *q) +{ + return dev_net(q->dev_queue->dev); +} + #endif diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 23e22054aa60..347015515a7d 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -150,6 +150,8 @@ struct fastopen_queue { spinlock_t lock; int qlen; /* # of pending (TCP_SYN_RECV) reqs */ int max_qlen; /* != 0 iff TFO is currently enabled */ + + struct tcp_fastopen_context __rcu *ctx; /* cipher context for cookie */ }; /** struct request_sock_queue - queue of request_socks diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 684d8ed27eaa..0aea9e23e97a 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -270,6 +270,8 @@ struct tcf_chain { struct tcf_block { struct list_head chain_list; + struct net *net; + struct Qdisc *q; }; static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) @@ -357,9 +359,6 @@ static inline void sch_tree_unlock(const struct Qdisc *q) spin_unlock_bh(qdisc_root_sleeping_lock(q)); } -#define tcf_tree_lock(tp) sch_tree_lock((tp)->q) -#define tcf_tree_unlock(tp) sch_tree_unlock((tp)->q) - extern struct Qdisc noop_qdisc; extern struct Qdisc_ops noop_qdisc_ops; extern struct Qdisc_ops pfifo_fast_ops; diff --git a/include/net/sock.h b/include/net/sock.h index a6b9a8d1a6df..4827094f1db4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -60,7 +60,7 @@ #include <linux/sched.h> #include <linux/wait.h> #include <linux/cgroup-defs.h> - +#include <linux/rbtree.h> #include <linux/filter.h> #include <linux/rculist_nulls.h> #include <linux/poll.h> @@ -397,7 +397,10 @@ struct sock { int sk_wmem_queued; refcount_t sk_wmem_alloc; unsigned long sk_tsq_flags; - struct sk_buff *sk_send_head; + union { + struct sk_buff *sk_send_head; + struct rb_root tcp_rtx_queue; + }; struct sk_buff_head sk_write_queue; __s32 sk_peek_off; int sk_write_pending; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index d767b7991887..d756fbe46625 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -51,6 +51,7 @@ enum switchdev_attr_id { SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME, SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED, + SWITCHDEV_ATTR_ID_BRIDGE_MROUTER, }; struct switchdev_attr { diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h index 30ba459ddd34..c7fb99c3f76c 100644 --- a/include/net/tc_act/tc_ife.h +++ b/include/net/tc_act/tc_ife.h @@ -6,12 +6,18 @@ #include <linux/rtnetlink.h> #include <linux/module.h> -struct tcf_ife_info { - struct tc_action common; +struct tcf_ife_params { u8 eth_dst[ETH_ALEN]; u8 eth_src[ETH_ALEN]; u16 eth_type; u16 flags; + + struct rcu_head rcu; +}; + +struct tcf_ife_info { + struct tc_action common; + struct tcf_ife_params __rcu *params; /* list of metaids allowed */ struct list_head metalist; }; @@ -40,7 +46,7 @@ struct tcf_meta_ops { struct module *owner; }; -#define MODULE_ALIAS_IFE_META(metan) MODULE_ALIAS("ifemeta" __stringify_1(metan)) +#define MODULE_ALIAS_IFE_META(metan) MODULE_ALIAS("ife-meta-" metan) int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi); int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi); diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index 604bc31e23ab..21a656569840 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -10,6 +10,7 @@ struct tcf_mirred { int tcfm_ifindex; bool tcfm_mac_header_xmit; struct net_device __rcu *tcfm_dev; + struct net *net; struct list_head tcfm_list; }; #define to_mirred(a) ((struct tcf_mirred *)a) diff --git a/include/net/tcp.h b/include/net/tcp.h index 3b16f353b539..1efe8365cb28 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -551,7 +551,13 @@ void tcp_xmit_retransmit_queue(struct sock *); void tcp_simple_retransmit(struct sock *); void tcp_enter_recovery(struct sock *sk, bool ece_ack); int tcp_trim_head(struct sock *, struct sk_buff *, u32); -int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int, gfp_t); +enum tcp_queue { + TCP_FRAG_IN_WRITE_QUEUE, + TCP_FRAG_IN_RTX_QUEUE, +}; +int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, + struct sk_buff *skb, u32 len, + unsigned int mss_now, gfp_t gfp); void tcp_send_probe0(struct sock *); void tcp_send_partial(struct sock *); @@ -1549,9 +1555,10 @@ struct tcp_fastopen_request { int copied; /* queued in tcp_connect() */ }; void tcp_free_fastopen_req(struct tcp_sock *tp); - +void tcp_fastopen_destroy_cipher(struct sock *sk); void tcp_fastopen_ctx_destroy(struct net *net); -int tcp_fastopen_reset_cipher(struct net *net, void *key, unsigned int len); +int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, + void *key, unsigned int len); void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, @@ -1606,19 +1613,11 @@ static inline void tcp_skb_tsorted_anchor_cleanup(struct sk_buff *skb) skb->_skb_refdst = _save; \ } -/* write queue abstraction */ -static inline void tcp_write_queue_purge(struct sock *sk) -{ - struct sk_buff *skb; +void tcp_write_queue_purge(struct sock *sk); - tcp_chrono_stop(sk, TCP_CHRONO_BUSY); - while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { - tcp_skb_tsorted_anchor_cleanup(skb); - sk_wmem_free_skb(sk, skb); - } - INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); - sk_mem_reclaim(sk); - tcp_clear_all_retrans_hints(tcp_sk(sk)); +static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk) +{ + return skb_rb_first(&sk->tcp_rtx_queue); } static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk) @@ -1631,30 +1630,12 @@ static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk) return skb_peek_tail(&sk->sk_write_queue); } -static inline struct sk_buff *tcp_write_queue_next(const struct sock *sk, - const struct sk_buff *skb) -{ - return skb_queue_next(&sk->sk_write_queue, skb); -} - -static inline struct sk_buff *tcp_write_queue_prev(const struct sock *sk, - const struct sk_buff *skb) -{ - return skb_queue_prev(&sk->sk_write_queue, skb); -} - -#define tcp_for_write_queue(skb, sk) \ - skb_queue_walk(&(sk)->sk_write_queue, skb) - -#define tcp_for_write_queue_from(skb, sk) \ - skb_queue_walk_from(&(sk)->sk_write_queue, skb) - #define tcp_for_write_queue_from_safe(skb, tmp, sk) \ skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp) static inline struct sk_buff *tcp_send_head(const struct sock *sk) { - return sk->sk_send_head; + return skb_peek(&sk->sk_write_queue); } static inline bool tcp_skb_is_last(const struct sock *sk, @@ -1663,29 +1644,30 @@ static inline bool tcp_skb_is_last(const struct sock *sk, return skb_queue_is_last(&sk->sk_write_queue, skb); } -static inline void tcp_advance_send_head(struct sock *sk, const struct sk_buff *skb) +static inline bool tcp_write_queue_empty(const struct sock *sk) { - if (tcp_skb_is_last(sk, skb)) - sk->sk_send_head = NULL; - else - sk->sk_send_head = tcp_write_queue_next(sk, skb); + return skb_queue_empty(&sk->sk_write_queue); +} + +static inline bool tcp_rtx_queue_empty(const struct sock *sk) +{ + return RB_EMPTY_ROOT(&sk->tcp_rtx_queue); +} + +static inline bool tcp_rtx_and_write_queues_empty(const struct sock *sk) +{ + return tcp_rtx_queue_empty(sk) && tcp_write_queue_empty(sk); } static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unlinked) { - if (sk->sk_send_head == skb_unlinked) { - sk->sk_send_head = NULL; + if (tcp_write_queue_empty(sk)) tcp_chrono_stop(sk, TCP_CHRONO_BUSY); - } + if (tcp_sk(sk)->highest_sack == skb_unlinked) tcp_sk(sk)->highest_sack = NULL; } -static inline void tcp_init_send_head(struct sock *sk) -{ - sk->sk_send_head = NULL; -} - static inline void __tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb) { __skb_queue_tail(&sk->sk_write_queue, skb); @@ -1696,8 +1678,7 @@ static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb __tcp_add_write_queue_tail(sk, skb); /* Queue it, remembering where we must start sending. */ - if (sk->sk_send_head == NULL) { - sk->sk_send_head = skb; + if (sk->sk_write_queue.next == skb) { tcp_chrono_start(sk, TCP_CHRONO_BUSY); if (tcp_sk(sk)->highest_sack == NULL) @@ -1705,40 +1686,33 @@ static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb } } -static inline void __tcp_add_write_queue_head(struct sock *sk, struct sk_buff *skb) -{ - __skb_queue_head(&sk->sk_write_queue, skb); -} - -/* Insert buff after skb on the write queue of sk. */ -static inline void tcp_insert_write_queue_after(struct sk_buff *skb, - struct sk_buff *buff, - struct sock *sk) -{ - __skb_queue_after(&sk->sk_write_queue, skb, buff); -} - /* Insert new before skb on the write queue of sk. */ static inline void tcp_insert_write_queue_before(struct sk_buff *new, struct sk_buff *skb, struct sock *sk) { __skb_queue_before(&sk->sk_write_queue, skb, new); - - if (sk->sk_send_head == skb) - sk->sk_send_head = new; } static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk) { - list_del(&skb->tcp_tsorted_anchor); tcp_skb_tsorted_anchor_cleanup(skb); __skb_unlink(skb, &sk->sk_write_queue); } -static inline bool tcp_write_queue_empty(struct sock *sk) +void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb); + +static inline void tcp_rtx_queue_unlink(struct sk_buff *skb, struct sock *sk) { - return skb_queue_empty(&sk->sk_write_queue); + tcp_skb_tsorted_anchor_cleanup(skb); + rb_erase(&skb->rbnode, &sk->tcp_rtx_queue); +} + +static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct sock *sk) +{ + list_del(&skb->tcp_tsorted_anchor); + tcp_rtx_queue_unlink(skb, sk); + sk_wmem_free_skb(sk, skb); } static inline void tcp_push_pending_frames(struct sock *sk) @@ -1767,8 +1741,9 @@ static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp) static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb) { - tcp_sk(sk)->highest_sack = tcp_skb_is_last(sk, skb) ? NULL : - tcp_write_queue_next(sk, skb); + struct sk_buff *next = skb_rb_next(skb); + + tcp_sk(sk)->highest_sack = next ?: tcp_send_head(sk); } static inline struct sk_buff *tcp_highest_sack(struct sock *sk) @@ -1778,7 +1753,9 @@ static inline struct sk_buff *tcp_highest_sack(struct sock *sk) static inline void tcp_highest_sack_reset(struct sock *sk) { - tcp_sk(sk)->highest_sack = tcp_write_queue_head(sk); + struct sk_buff *skb = tcp_rtx_queue_head(sk); + + tcp_sk(sk)->highest_sack = skb ?: tcp_send_head(sk); } /* Called when old skb is about to be deleted (to be combined with new skb) */ @@ -1948,7 +1925,7 @@ extern void tcp_rack_reo_timeout(struct sock *sk); /* At how many usecs into the future should the RTO fire? */ static inline s64 tcp_rto_delta_us(const struct sock *sk) { - const struct sk_buff *skb = tcp_write_queue_head(sk); + const struct sk_buff *skb = tcp_rtx_queue_head(sk); u32 rto = inet_csk(sk)->icsk_rto; u64 rto_time_stamp_us = skb->skb_mstamp + jiffies_to_usecs(rto); diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 82e93ee94708..67c5a9f223f7 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -192,6 +192,7 @@ struct scsi_device { unsigned no_dif:1; /* T10 PI (DIF) should be disabled */ unsigned broken_fua:1; /* Don't set FUA bit */ unsigned lun_in_cdb:1; /* Store LUN bits in CDB[1] */ + unsigned unmap_limit_for_ws:1; /* Use the UNMAP limit for WRITE SAME */ atomic_t disk_events_disable_depth; /* disable depth for disk events */ diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h index 9592570e092a..36b03013d629 100644 --- a/include/scsi/scsi_devinfo.h +++ b/include/scsi/scsi_devinfo.h @@ -29,5 +29,6 @@ #define BLIST_TRY_VPD_PAGES 0x10000000 /* Attempt to read VPD pages */ #define BLIST_NO_RSOC 0x20000000 /* don't try to issue RSOC */ #define BLIST_MAX_1024 0x40000000 /* maximum 1024 sector cdb length */ +#define BLIST_UNMAP_LIMIT_WS 0x80000000 /* Use UNMAP limit for WRITE SAME */ #endif diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index 6183d20a01fb..b266d2a3bcb1 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -434,7 +434,6 @@ extern struct iscsi_cls_session *iscsi_create_session(struct Scsi_Host *shost, unsigned int target_id); extern void iscsi_remove_session(struct iscsi_cls_session *session); extern void iscsi_free_session(struct iscsi_cls_session *session); -extern int iscsi_destroy_session(struct iscsi_cls_session *session); extern struct iscsi_cls_conn *iscsi_create_conn(struct iscsi_cls_session *sess, int dd_size, uint32_t cid); extern int iscsi_destroy_conn(struct iscsi_cls_conn *conn); diff --git a/include/trace/events/bpf.h b/include/trace/events/bpf.h index 52c8425d144b..1fb58faa4a44 100644 --- a/include/trace/events/bpf.h +++ b/include/trace/events/bpf.h @@ -4,6 +4,9 @@ #if !defined(_TRACE_BPF_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_BPF_H +/* These are only used within the BPF_SYSCALL code */ +#ifdef CONFIG_BPF_SYSCALL + #include <linux/filter.h> #include <linux/bpf.h> #include <linux/fs.h> @@ -345,7 +348,7 @@ TRACE_EVENT(bpf_map_next_key, __print_hex(__get_dynamic_array(nxt), __entry->key_len), __entry->key_trunc ? " ..." : "") ); - +#endif /* CONFIG_BPF_SYSCALL */ #endif /* _TRACE_BPF_H */ #include <trace/define_trace.h> diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h new file mode 100644 index 000000000000..c3220d914475 --- /dev/null +++ b/include/trace/events/tcp.h @@ -0,0 +1,70 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM tcp + +#if !defined(_TRACE_TCP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_TCP_H + +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/tracepoint.h> +#include <net/ipv6.h> + +TRACE_EVENT(tcp_retransmit_skb, + + TP_PROTO(struct sock *sk, struct sk_buff *skb), + + TP_ARGS(sk, skb), + + TP_STRUCT__entry( + __field(void *, skbaddr) + __field(void *, skaddr) + __field(__u16, sport) + __field(__u16, dport) + __array(__u8, saddr, 4) + __array(__u8, daddr, 4) + __array(__u8, saddr_v6, 16) + __array(__u8, daddr_v6, 16) + ), + + TP_fast_assign( + struct inet_sock *inet = inet_sk(sk); + struct in6_addr *pin6; + __be32 *p32; + + __entry->skbaddr = skb; + __entry->skaddr = sk; + + __entry->sport = ntohs(inet->inet_sport); + __entry->dport = ntohs(inet->inet_dport); + + p32 = (__be32 *) __entry->saddr; + *p32 = inet->inet_saddr; + + p32 = (__be32 *) __entry->daddr; + *p32 = inet->inet_daddr; + +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) { + pin6 = (struct in6_addr *)__entry->saddr_v6; + *pin6 = sk->sk_v6_rcv_saddr; + pin6 = (struct in6_addr *)__entry->daddr_v6; + *pin6 = sk->sk_v6_daddr; + } else +#endif + { + pin6 = (struct in6_addr *)__entry->saddr_v6; + ipv6_addr_set_v4mapped(inet->inet_saddr, pin6); + pin6 = (struct in6_addr *)__entry->daddr_v6; + ipv6_addr_set_v4mapped(inet->inet_daddr, pin6); + } + ), + + TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c", + __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, + __entry->saddr_v6, __entry->daddr_v6) +); + +#endif /* _TRACE_TCP_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index 4e16c43fba10..0c8dec61987e 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -136,14 +136,90 @@ DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err, __entry->map_id, __entry->map_index) ); +#define devmap_ifindex(fwd, map) \ + (!fwd ? 0 : \ + (!map ? 0 : \ + ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \ + ((struct net_device *)fwd)->ifindex : 0))) + #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \ - trace_xdp_redirect_map(dev, xdp, fwd ? fwd->ifindex : 0, \ + trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map), \ 0, map, idx) #define _trace_xdp_redirect_map_err(dev, xdp, fwd, map, idx, err) \ - trace_xdp_redirect_map_err(dev, xdp, fwd ? fwd->ifindex : 0, \ + trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map), \ err, map, idx) +TRACE_EVENT(xdp_cpumap_kthread, + + TP_PROTO(int map_id, unsigned int processed, unsigned int drops, + int sched), + + TP_ARGS(map_id, processed, drops, sched), + + TP_STRUCT__entry( + __field(int, map_id) + __field(u32, act) + __field(int, cpu) + __field(unsigned int, drops) + __field(unsigned int, processed) + __field(int, sched) + ), + + TP_fast_assign( + __entry->map_id = map_id; + __entry->act = XDP_REDIRECT; + __entry->cpu = smp_processor_id(); + __entry->drops = drops; + __entry->processed = processed; + __entry->sched = sched; + ), + + TP_printk("kthread" + " cpu=%d map_id=%d action=%s" + " processed=%u drops=%u" + " sched=%d", + __entry->cpu, __entry->map_id, + __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), + __entry->processed, __entry->drops, + __entry->sched) +); + +TRACE_EVENT(xdp_cpumap_enqueue, + + TP_PROTO(int map_id, unsigned int processed, unsigned int drops, + int to_cpu), + + TP_ARGS(map_id, processed, drops, to_cpu), + + TP_STRUCT__entry( + __field(int, map_id) + __field(u32, act) + __field(int, cpu) + __field(unsigned int, drops) + __field(unsigned int, processed) + __field(int, to_cpu) + ), + + TP_fast_assign( + __entry->map_id = map_id; + __entry->act = XDP_REDIRECT; + __entry->cpu = smp_processor_id(); + __entry->drops = drops; + __entry->processed = processed; + __entry->to_cpu = to_cpu; + ), + + TP_printk("enqueue" + " cpu=%d map_id=%d action=%s" + " processed=%u drops=%u" + " to_cpu=%d", + __entry->cpu, __entry->map_id, + __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), + __entry->processed, __entry->drops, + __entry->to_cpu) +); + #endif /* _TRACE_XDP_H */ #include <trace/define_trace.h> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6082faf5fd2a..d83f95ea6a1b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -112,6 +112,7 @@ enum bpf_map_type { BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_DEVMAP, BPF_MAP_TYPE_SOCKMAP, + BPF_MAP_TYPE_CPUMAP, }; enum bpf_prog_type { @@ -217,6 +218,10 @@ enum bpf_attach_type { #define BPF_OBJ_NAME_LEN 16U +/* Flags for accessing BPF object */ +#define BPF_F_RDONLY (1U << 3) +#define BPF_F_WRONLY (1U << 4) + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -230,7 +235,7 @@ union bpf_attr { __u32 numa_node; /* numa node (effective only if * BPF_F_NUMA_NODE is set). */ - __u8 map_name[BPF_OBJ_NAME_LEN]; + char map_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -253,12 +258,13 @@ union bpf_attr { __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ __u32 prog_flags; - __u8 prog_name[BPF_OBJ_NAME_LEN]; + char prog_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ __aligned_u64 pathname; __u32 bpf_fd; + __u32 file_flags; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ @@ -286,6 +292,7 @@ union bpf_attr { __u32 map_id; }; __u32 next_id; + __u32 open_flags; }; struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ @@ -641,6 +648,21 @@ union bpf_attr { * @xdp_md: pointer to xdp_md * @delta: An positive/negative integer to be added to xdp_md.data_meta * Return: 0 on success or negative on error + * + * int bpf_perf_event_read_value(map, flags, buf, buf_size) + * read perf event counter value and perf event enabled/running time + * @map: pointer to perf_event_array map + * @flags: index of event in the map or bitmask flags + * @buf: buf to fill + * @buf_size: size of the buf + * Return: 0 on success or negative error code + * + * int bpf_perf_prog_read_value(ctx, buf, buf_size) + * read perf prog attached perf event counter and enabled/running time + * @ctx: pointer to ctx + * @buf: buf to fill + * @buf_size: size of the buf + * Return : 0 on success or negative error code */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -697,7 +719,9 @@ union bpf_attr { FN(redirect_map), \ FN(sk_redirect_map), \ FN(sock_map_update), \ - FN(xdp_adjust_meta), + FN(xdp_adjust_meta), \ + FN(perf_event_read_value), \ + FN(perf_prog_read_value), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -741,7 +765,9 @@ enum bpf_func_id { #define BPF_F_ZERO_CSUM_TX (1ULL << 1) #define BPF_F_DONT_FRAGMENT (1ULL << 2) -/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */ +/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and + * BPF_FUNC_perf_event_read_value flags. + */ #define BPF_F_INDEX_MASK 0xffffffffULL #define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK /* BPF_FUNC_perf_event_output for sk_buff input context. */ @@ -869,7 +895,7 @@ struct bpf_prog_info { __u32 created_by_uid; __u32 nr_map_ids; __aligned_u64 map_ids; - __u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); struct bpf_map_info { @@ -879,7 +905,7 @@ struct bpf_map_info { __u32 value_size; __u32 max_entries; __u32 map_flags; - __u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); /* User bpf_sock_ops struct to access socket values and specify request ops @@ -934,4 +960,10 @@ enum { #define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ #define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */ +struct bpf_perf_event_value { + __u64 counter; + __u64 enabled; + __u64 running; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index cd580fc0e58f..b037e0ab1975 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -327,6 +327,7 @@ enum { IFLA_BRPORT_VLAN_TUNNEL, IFLA_BRPORT_BCAST_FLOOD, IFLA_BRPORT_GROUP_FWD_MASK, + IFLA_BRPORT_NEIGH_SUPPRESS, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 2e520883c054..a2f48c01365e 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -84,6 +84,7 @@ enum tunnel_encap_types { TUNNEL_ENCAP_NONE, TUNNEL_ENCAP_FOU, TUNNEL_ENCAP_GUE, + TUNNEL_ENCAP_MPLS, }; #define TUNNEL_ENCAP_FLAG_CSUM (1<<0) diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h index b97725af2ac0..da161b56c79e 100644 --- a/include/uapi/linux/netfilter/xt_bpf.h +++ b/include/uapi/linux/netfilter/xt_bpf.h @@ -23,6 +23,7 @@ enum xt_bpf_modes { XT_BPF_MODE_FD_PINNED, XT_BPF_MODE_FD_ELF, }; +#define XT_BPF_MODE_PATH_PINNED XT_BPF_MODE_FD_PINNED struct xt_bpf_info_v1 { __u16 mode; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 51626b4175c0..f882fe1f9709 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -569,13 +569,14 @@ * authentication/association or not receiving a response from the AP. * Non-zero %NL80211_ATTR_STATUS_CODE value is indicated in that case as * well to remain backwards compatible. - * @NL80211_CMD_ROAM: notifcation indicating the card/driver roamed by itself. - * When the driver roamed in a network that requires 802.1X authentication, - * %NL80211_ATTR_PORT_AUTHORIZED should be set if the 802.1X authentication - * was done by the driver or if roaming was done using Fast Transition - * protocol (in which case 802.1X authentication is not needed). If - * %NL80211_ATTR_PORT_AUTHORIZED is not set, user space is responsible for - * the 802.1X authentication. + * When establishing a security association, drivers that support 4 way + * handshake offload should send %NL80211_CMD_PORT_AUTHORIZED event when + * the 4 way handshake is completed successfully. + * @NL80211_CMD_ROAM: Notification indicating the card/driver roamed by itself. + * When a security association was established with the new AP (e.g. if + * the FT protocol was used for roaming or the driver completed the 4 way + * handshake), this event should be followed by an + * %NL80211_CMD_PORT_AUTHORIZED event. * @NL80211_CMD_DISCONNECT: drop a given connection; also used to notify * userspace that a connection was dropped by the AP or due to other * reasons, for this the %NL80211_ATTR_DISCONNECTED_BY_AP and @@ -982,6 +983,14 @@ * @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously * configured PMK for the authenticator address identified by * &NL80211_ATTR_MAC. + * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates that the 4 way + * handshake was completed successfully by the driver. The BSSID is + * specified with &NL80211_ATTR_MAC. Drivers that support 4 way handshake + * offload should send this event after indicating 802.11 association with + * &NL80211_CMD_CONNECT or &NL80211_CMD_ROAM. If the 4 way handshake failed + * &NL80211_CMD_DISCONNECT should be indicated instead. + * + * @NL80211_CMD_RELOAD_REGDB: Request that the regdb firmware file is reloaded. * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use @@ -1185,6 +1194,10 @@ enum nl80211_commands { NL80211_CMD_SET_PMK, NL80211_CMD_DEL_PMK, + NL80211_CMD_PORT_AUTHORIZED, + + NL80211_CMD_RELOAD_REGDB, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -1407,8 +1420,12 @@ enum nl80211_commands { * * @NL80211_ATTR_USE_MFP: Whether management frame protection (IEEE 802.11w) is * used for the association (&enum nl80211_mfp, represented as a u32); - * this attribute can be used - * with %NL80211_CMD_ASSOCIATE and %NL80211_CMD_CONNECT requests + * this attribute can be used with %NL80211_CMD_ASSOCIATE and + * %NL80211_CMD_CONNECT requests. %NL80211_MFP_OPTIONAL is not allowed for + * %NL80211_CMD_ASSOCIATE since user space SME is expected and hence, it + * must have decided whether to use management frame protection or not. + * Setting %NL80211_MFP_OPTIONAL with a %NL80211_CMD_CONNECT request will + * let the driver (or the firmware) decide whether to use MFP or not. * * @NL80211_ATTR_STA_FLAGS2: Attribute containing a * &struct nl80211_sta_flag_update. @@ -2134,10 +2151,7 @@ enum nl80211_commands { * in %NL80211_CMD_CONNECT to indicate that for 802.1X authentication it * wants to use the supported offload of the 4-way handshake. * @NL80211_ATTR_PMKR0_NAME: PMK-R0 Name for offloaded FT. - * @NL80211_ATTR_PORT_AUTHORIZED: flag attribute used in %NL80211_CMD_ROAMED - * notification indicating that that 802.1X authentication was done by - * the driver or is not needed (because roaming used the Fast Transition - * protocol). + * @NL80211_ATTR_PORT_AUTHORIZED: (reserved) * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined @@ -3947,10 +3961,12 @@ enum nl80211_key_type { * enum nl80211_mfp - Management frame protection state * @NL80211_MFP_NO: Management frame protection not used * @NL80211_MFP_REQUIRED: Management frame protection required + * @NL80211_MFP_OPTIONAL: Management frame protection is optional */ enum nl80211_mfp { NL80211_MFP_NO, NL80211_MFP_REQUIRED, + NL80211_MFP_OPTIONAL, }; enum nl80211_wpa_versions { @@ -4914,6 +4930,17 @@ enum nl80211_feature_flags { * handshake with 802.1X in station mode (will pass EAP frames to the host * and accept the set_pmk/del_pmk commands), doing it in the host might not * be supported. + * @NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME: Driver is capable of overriding + * the max channel attribute in the FILS request params IE with the + * actual dwell time. + * @NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP: Driver accepts broadcast probe + * response + * @NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE: Driver supports sending + * the first probe request in each channel at rate of at least 5.5Mbps. + * @NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: Driver supports + * probe request tx deferral and suppression + * @NL80211_EXT_FEATURE_MFP_OPTIONAL: Driver supports the %NL80211_MFP_OPTIONAL + * value in %NL80211_ATTR_USE_MFP. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4936,6 +4963,11 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_FILS_SK_OFFLOAD, NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK, NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X, + NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME, + NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION, + NL80211_EXT_FEATURE_MFP_OPTIONAL, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -5012,12 +5044,28 @@ enum nl80211_timeout_reason { * locally administered 1, multicast 0) is assumed. * This flag must not be requested when the feature isn't supported, check * the nl80211 feature flags for the device. + * @NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME: fill the dwell time in the FILS + * request parameters IE in the probe request + * @NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP: accept broadcast probe responses + * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE: send probe request frames at + * rate of at least 5.5M. In case non OCE AP is dicovered in the channel, + * only the first probe req in the channel will be sent in high rate. + * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: allow probe request + * tx deferral (dot11FILSProbeDelay shall be set to 15ms) + * and suppression (if it has received a broadcast Probe Response frame, + * Beacon frame or FILS Discovery frame from an AP that the STA considers + * a suitable candidate for (re-)association - suitable in terms of + * SSID and/or RSSI */ enum nl80211_scan_flags { - NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0, - NL80211_SCAN_FLAG_FLUSH = 1<<1, - NL80211_SCAN_FLAG_AP = 1<<2, - NL80211_SCAN_FLAG_RANDOM_ADDR = 1<<3, + NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0, + NL80211_SCAN_FLAG_FLUSH = 1<<1, + NL80211_SCAN_FLAG_AP = 1<<2, + NL80211_SCAN_FLAG_RANDOM_ADDR = 1<<3, + NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME = 1<<4, + NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP = 1<<5, + NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE = 1<<6, + NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION = 1<<7, }; /** diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 156ee4cab82e..0cd6f8833147 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -359,6 +359,7 @@ enum ovs_tunnel_key_attr { OVS_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */ OVS_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */ OVS_TUNNEL_KEY_ATTR_PAD, + OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, /* be32 ERSPAN index. */ __OVS_TUNNEL_KEY_ATTR_MAX }; @@ -806,6 +807,7 @@ struct ovs_action_push_eth { * packet. * @OVS_ACTION_ATTR_POP_ETH: Pop the outermost Ethernet header off the * packet. + * @OVS_ACTION_ATTR_CT_CLEAR: Clear conntrack state from the packet. * * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all * fields within a header are modifiable, e.g. the IPv4 protocol and fragment @@ -835,6 +837,7 @@ enum ovs_action_attr { OVS_ACTION_ATTR_TRUNC, /* u32 struct ovs_action_trunc. */ OVS_ACTION_ATTR_PUSH_ETH, /* struct ovs_action_push_eth. */ OVS_ACTION_ATTR_POP_ETH, /* No argument. */ + OVS_ACTION_ATTR_CT_CLEAR, /* No argument. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 099bf5528fed..e7cc3d3c7421 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -74,6 +74,7 @@ struct tc_estimator { #define TC_H_INGRESS (0xFFFFFFF1U) #define TC_H_CLSACT TC_H_INGRESS +#define TC_H_MIN_PRIORITY 0xFFE0U #define TC_H_MIN_INGRESS 0xFFF2U #define TC_H_MIN_EGRESS 0xFFF3U @@ -625,6 +626,22 @@ enum { #define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1) +enum { + TC_MQPRIO_MODE_DCB, + TC_MQPRIO_MODE_CHANNEL, + __TC_MQPRIO_MODE_MAX +}; + +#define __TC_MQPRIO_MODE_MAX (__TC_MQPRIO_MODE_MAX - 1) + +enum { + TC_MQPRIO_SHAPER_DCB, + TC_MQPRIO_SHAPER_BW_RATE, /* Add new shapers below */ + __TC_MQPRIO_SHAPER_MAX +}; + +#define __TC_MQPRIO_SHAPER_MAX (__TC_MQPRIO_SHAPER_MAX - 1) + struct tc_mqprio_qopt { __u8 num_tc; __u8 prio_tc_map[TC_QOPT_BITMASK + 1]; @@ -633,6 +650,22 @@ struct tc_mqprio_qopt { __u16 offset[TC_QOPT_MAX_QUEUE]; }; +#define TC_MQPRIO_F_MODE 0x1 +#define TC_MQPRIO_F_SHAPER 0x2 +#define TC_MQPRIO_F_MIN_RATE 0x4 +#define TC_MQPRIO_F_MAX_RATE 0x8 + +enum { + TCA_MQPRIO_UNSPEC, + TCA_MQPRIO_MODE, + TCA_MQPRIO_SHAPER, + TCA_MQPRIO_MIN_RATE64, + TCA_MQPRIO_MAX_RATE64, + __TCA_MQPRIO_MAX, +}; + +#define TCA_MQPRIO_MAX (__TCA_MQPRIO_MAX - 1) + /* SFB */ enum { diff --git a/include/uapi/linux/qrtr.h b/include/uapi/linux/qrtr.h index 9d76c566f66e..179af64846e0 100644 --- a/include/uapi/linux/qrtr.h +++ b/include/uapi/linux/qrtr.h @@ -4,10 +4,45 @@ #include <linux/socket.h> #include <linux/types.h> +#define QRTR_NODE_BCAST 0xffffffffu +#define QRTR_PORT_CTRL 0xfffffffeu + struct sockaddr_qrtr { __kernel_sa_family_t sq_family; __u32 sq_node; __u32 sq_port; }; +enum qrtr_pkt_type { + QRTR_TYPE_DATA = 1, + QRTR_TYPE_HELLO = 2, + QRTR_TYPE_BYE = 3, + QRTR_TYPE_NEW_SERVER = 4, + QRTR_TYPE_DEL_SERVER = 5, + QRTR_TYPE_DEL_CLIENT = 6, + QRTR_TYPE_RESUME_TX = 7, + QRTR_TYPE_EXIT = 8, + QRTR_TYPE_PING = 9, + QRTR_TYPE_NEW_LOOKUP = 10, + QRTR_TYPE_DEL_LOOKUP = 11, +}; + +struct qrtr_ctrl_pkt { + __le32 cmd; + + union { + struct { + __le32 service; + __le32 instance; + __le32 node; + __le32 port; + } server; + + struct { + __le32 node; + __le32 port; + } client; + }; +} __packed; + #endif /* _LINUX_QRTR_H */ diff --git a/include/uapi/linux/tc_act/tc_mirred.h b/include/uapi/linux/tc_act/tc_mirred.h index 3d7a2b352a62..69038c29e8a9 100644 --- a/include/uapi/linux/tc_act/tc_mirred.h +++ b/include/uapi/linux/tc_act/tc_mirred.h @@ -9,13 +9,13 @@ #define TCA_EGRESS_MIRROR 2 /* mirror packet to EGRESS */ #define TCA_INGRESS_REDIR 3 /* packet redirect to INGRESS*/ #define TCA_INGRESS_MIRROR 4 /* mirror packet to INGRESS */ - + struct tc_mirred { tc_gen; int eaction; /* one of IN/EGRESS_MIRROR/REDIR */ __u32 ifindex; /* ifindex of egress port */ }; - + enum { TCA_MIRRED_UNSPEC, TCA_MIRRED_TM, @@ -24,5 +24,5 @@ enum { __TCA_MIRRED_MAX }; #define TCA_MIRRED_MAX (__TCA_MIRRED_MAX - 1) - + #endif diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 15c25eccab2b..69c7493e42f8 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -119,6 +119,7 @@ enum { #define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */ #define TCP_ULP 31 /* Attach a ULP to a TCP connection */ #define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */ +#define TCP_FASTOPEN_KEY 33 /* Set the key for Fast Open (cookie) */ struct tcp_repair_opt { __u32 opt_code; diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h index 5351b08c897a..ef41c11a7f38 100644 --- a/include/uapi/linux/tipc.h +++ b/include/uapi/linux/tipc.h @@ -231,6 +231,21 @@ struct sockaddr_tipc { #define TIPC_SOCK_RECVQ_DEPTH 132 /* Default: none (read only) */ #define TIPC_MCAST_BROADCAST 133 /* Default: TIPC selects. No arg */ #define TIPC_MCAST_REPLICAST 134 /* Default: TIPC selects. No arg */ +#define TIPC_GROUP_JOIN 135 /* Takes struct tipc_group_req* */ +#define TIPC_GROUP_LEAVE 136 /* No argument */ + +/* + * Flag values + */ +#define TIPC_GROUP_LOOPBACK 0x1 /* Receive copy of sent msg when match */ +#define TIPC_GROUP_MEMBER_EVTS 0x2 /* Receive membership events in socket */ + +struct tipc_group_req { + __u32 type; /* group id */ + __u32 instance; /* member id */ + __u32 scope; /* zone/cluster/node */ + __u32 flags; +}; /* * Maximum sizes of TIPC bearer-related names (including terminating NULL) diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 897daa005b23..e597daae6120 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -2,8 +2,10 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o +obj-$(CONFIG_BPF_SYSCALL) += disasm.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o +obj-$(CONFIG_BPF_SYSCALL) += cpumap.o ifeq ($(CONFIG_STREAM_PARSER),y) obj-$(CONFIG_BPF_SYSCALL) += sockmap.o endif diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 98c0f00c3f5e..988c04c91e10 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -19,6 +19,9 @@ #include "map_in_map.h" +#define ARRAY_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + static void bpf_array_free_percpu(struct bpf_array *array) { int i; @@ -56,7 +59,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size == 0 || attr->map_flags & ~BPF_F_NUMA_NODE || + attr->value_size == 0 || + attr->map_flags & ~ARRAY_CREATE_FLAG_MASK || (percpu && numa_node != NUMA_NO_NODE)) return ERR_PTR(-EINVAL); @@ -492,7 +496,7 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, ee = ERR_PTR(-EOPNOTSUPP); event = perf_file->private_data; - if (perf_event_read_local(event, &value) == -EOPNOTSUPP) + if (perf_event_read_local(event, &value, NULL, NULL) == -EOPNOTSUPP) goto err_out; ee = bpf_event_entry_gen(perf_file, map_file); diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index e88abc0865d5..3db5a17fcfe8 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -192,7 +192,6 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, struct cgroup_subsys_state *css; struct bpf_prog_list *pl; bool pl_was_allocated; - u32 old_flags; int err; if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) @@ -239,7 +238,6 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, pl->prog = prog; } - old_flags = cgrp->bpf.flags[type]; cgrp->bpf.flags[type] = flags; /* allocate and recompute effective prog arrays */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index c6be15ae83ee..8e7c8bf2b687 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -309,12 +309,25 @@ bpf_get_prog_addr_region(const struct bpf_prog *prog, static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) { + const char *end = sym + KSYM_NAME_LEN; + BUILD_BUG_ON(sizeof("bpf_prog_") + - sizeof(prog->tag) * 2 + 1 > KSYM_NAME_LEN); + sizeof(prog->tag) * 2 + + /* name has been null terminated. + * We should need +1 for the '_' preceding + * the name. However, the null character + * is double counted between the name and the + * sizeof("bpf_prog_") above, so we omit + * the +1 here. + */ + sizeof(prog->aux->name) > KSYM_NAME_LEN); sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_"); sym = bin2hex(sym, prog->tag, sizeof(prog->tag)); - *sym = 0; + if (prog->aux->name[0]) + snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name); + else + *sym = 0; } static __always_inline unsigned long @@ -1567,5 +1580,8 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception); +/* These are only used within the BPF_SYSCALL code */ +#ifdef CONFIG_BPF_SYSCALL EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_get_type); EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_put_rcu); +#endif diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c new file mode 100644 index 000000000000..b4358d84ddf1 --- /dev/null +++ b/kernel/bpf/cpumap.c @@ -0,0 +1,702 @@ +/* bpf/cpumap.c + * + * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. + * Released under terms in GPL version 2. See COPYING. + */ + +/* The 'cpumap' is primarily used as a backend map for XDP BPF helper + * call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'. + * + * Unlike devmap which redirects XDP frames out another NIC device, + * this map type redirects raw XDP frames to another CPU. The remote + * CPU will do SKB-allocation and call the normal network stack. + * + * This is a scalability and isolation mechanism, that allow + * separating the early driver network XDP layer, from the rest of the + * netstack, and assigning dedicated CPUs for this stage. This + * basically allows for 10G wirespeed pre-filtering via bpf. + */ +#include <linux/bpf.h> +#include <linux/filter.h> +#include <linux/ptr_ring.h> + +#include <linux/sched.h> +#include <linux/workqueue.h> +#include <linux/kthread.h> +#include <linux/capability.h> +#include <trace/events/xdp.h> + +#include <linux/netdevice.h> /* netif_receive_skb_core */ +#include <linux/etherdevice.h> /* eth_type_trans */ + +/* General idea: XDP packets getting XDP redirected to another CPU, + * will maximum be stored/queued for one driver ->poll() call. It is + * guaranteed that setting flush bit and flush operation happen on + * same CPU. Thus, cpu_map_flush operation can deduct via this_cpu_ptr() + * which queue in bpf_cpu_map_entry contains packets. + */ + +#define CPU_MAP_BULK_SIZE 8 /* 8 == one cacheline on 64-bit archs */ +struct xdp_bulk_queue { + void *q[CPU_MAP_BULK_SIZE]; + unsigned int count; +}; + +/* Struct for every remote "destination" CPU in map */ +struct bpf_cpu_map_entry { + u32 cpu; /* kthread CPU and map index */ + int map_id; /* Back reference to map */ + u32 qsize; /* Queue size placeholder for map lookup */ + + /* XDP can run multiple RX-ring queues, need __percpu enqueue store */ + struct xdp_bulk_queue __percpu *bulkq; + + /* Queue with potential multi-producers, and single-consumer kthread */ + struct ptr_ring *queue; + struct task_struct *kthread; + struct work_struct kthread_stop_wq; + + atomic_t refcnt; /* Control when this struct can be free'ed */ + struct rcu_head rcu; +}; + +struct bpf_cpu_map { + struct bpf_map map; + /* Below members specific for map type */ + struct bpf_cpu_map_entry **cpu_map; + unsigned long __percpu *flush_needed; +}; + +static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, + struct xdp_bulk_queue *bq); + +static u64 cpu_map_bitmap_size(const union bpf_attr *attr) +{ + return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long); +} + +static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) +{ + struct bpf_cpu_map *cmap; + int err = -ENOMEM; + u64 cost; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + return ERR_PTR(-EINVAL); + + cmap = kzalloc(sizeof(*cmap), GFP_USER); + if (!cmap) + return ERR_PTR(-ENOMEM); + + /* mandatory map attributes */ + cmap->map.map_type = attr->map_type; + cmap->map.key_size = attr->key_size; + cmap->map.value_size = attr->value_size; + cmap->map.max_entries = attr->max_entries; + cmap->map.map_flags = attr->map_flags; + cmap->map.numa_node = bpf_map_attr_numa_node(attr); + + /* Pre-limit array size based on NR_CPUS, not final CPU check */ + if (cmap->map.max_entries > NR_CPUS) { + err = -E2BIG; + goto free_cmap; + } + + /* make sure page count doesn't overflow */ + cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *); + cost += cpu_map_bitmap_size(attr) * num_possible_cpus(); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_cmap; + cmap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + /* Notice returns -EPERM on if map size is larger than memlock limit */ + ret = bpf_map_precharge_memlock(cmap->map.pages); + if (ret) { + err = ret; + goto free_cmap; + } + + /* A per cpu bitfield with a bit per possible CPU in map */ + cmap->flush_needed = __alloc_percpu(cpu_map_bitmap_size(attr), + __alignof__(unsigned long)); + if (!cmap->flush_needed) + goto free_cmap; + + /* Alloc array for possible remote "destination" CPUs */ + cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries * + sizeof(struct bpf_cpu_map_entry *), + cmap->map.numa_node); + if (!cmap->cpu_map) + goto free_percpu; + + return &cmap->map; +free_percpu: + free_percpu(cmap->flush_needed); +free_cmap: + kfree(cmap); + return ERR_PTR(err); +} + +void __cpu_map_queue_destructor(void *ptr) +{ + /* The tear-down procedure should have made sure that queue is + * empty. See __cpu_map_entry_replace() and work-queue + * invoked cpu_map_kthread_stop(). Catch any broken behaviour + * gracefully and warn once. + */ + if (WARN_ON_ONCE(ptr)) + page_frag_free(ptr); +} + +static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) +{ + if (atomic_dec_and_test(&rcpu->refcnt)) { + /* The queue should be empty at this point */ + ptr_ring_cleanup(rcpu->queue, __cpu_map_queue_destructor); + kfree(rcpu->queue); + kfree(rcpu); + } +} + +static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) +{ + atomic_inc(&rcpu->refcnt); +} + +/* called from workqueue, to workaround syscall using preempt_disable */ +static void cpu_map_kthread_stop(struct work_struct *work) +{ + struct bpf_cpu_map_entry *rcpu; + + rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq); + + /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier, + * as it waits until all in-flight call_rcu() callbacks complete. + */ + rcu_barrier(); + + /* kthread_stop will wake_up_process and wait for it to complete */ + kthread_stop(rcpu->kthread); +} + +/* For now, xdp_pkt is a cpumap internal data structure, with info + * carried between enqueue to dequeue. It is mapped into the top + * headroom of the packet, to avoid allocating separate mem. + */ +struct xdp_pkt { + void *data; + u16 len; + u16 headroom; + u16 metasize; + struct net_device *dev_rx; +}; + +/* Convert xdp_buff to xdp_pkt */ +static struct xdp_pkt *convert_to_xdp_pkt(struct xdp_buff *xdp) +{ + struct xdp_pkt *xdp_pkt; + int metasize; + int headroom; + + /* Assure headroom is available for storing info */ + headroom = xdp->data - xdp->data_hard_start; + metasize = xdp->data - xdp->data_meta; + metasize = metasize > 0 ? metasize : 0; + if ((headroom - metasize) < sizeof(*xdp_pkt)) + return NULL; + + /* Store info in top of packet */ + xdp_pkt = xdp->data_hard_start; + + xdp_pkt->data = xdp->data; + xdp_pkt->len = xdp->data_end - xdp->data; + xdp_pkt->headroom = headroom - sizeof(*xdp_pkt); + xdp_pkt->metasize = metasize; + + return xdp_pkt; +} + +struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, + struct xdp_pkt *xdp_pkt) +{ + unsigned int frame_size; + void *pkt_data_start; + struct sk_buff *skb; + + /* build_skb need to place skb_shared_info after SKB end, and + * also want to know the memory "truesize". Thus, need to + * know the memory frame size backing xdp_buff. + * + * XDP was designed to have PAGE_SIZE frames, but this + * assumption is not longer true with ixgbe and i40e. It + * would be preferred to set frame_size to 2048 or 4096 + * depending on the driver. + * frame_size = 2048; + * frame_len = frame_size - sizeof(*xdp_pkt); + * + * Instead, with info avail, skb_shared_info in placed after + * packet len. This, unfortunately fakes the truesize. + * Another disadvantage of this approach, the skb_shared_info + * is not at a fixed memory location, with mixed length + * packets, which is bad for cache-line hotness. + */ + frame_size = SKB_DATA_ALIGN(xdp_pkt->len) + xdp_pkt->headroom + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + pkt_data_start = xdp_pkt->data - xdp_pkt->headroom; + skb = build_skb(pkt_data_start, frame_size); + if (!skb) + return NULL; + + skb_reserve(skb, xdp_pkt->headroom); + __skb_put(skb, xdp_pkt->len); + if (xdp_pkt->metasize) + skb_metadata_set(skb, xdp_pkt->metasize); + + /* Essential SKB info: protocol and skb->dev */ + skb->protocol = eth_type_trans(skb, xdp_pkt->dev_rx); + + /* Optional SKB info, currently missing: + * - HW checksum info (skb->ip_summed) + * - HW RX hash (skb_set_hash) + * - RX ring dev queue index (skb_record_rx_queue) + */ + + return skb; +} + +static int cpu_map_kthread_run(void *data) +{ + struct bpf_cpu_map_entry *rcpu = data; + + set_current_state(TASK_INTERRUPTIBLE); + + /* When kthread gives stop order, then rcpu have been disconnected + * from map, thus no new packets can enter. Remaining in-flight + * per CPU stored packets are flushed to this queue. Wait honoring + * kthread_stop signal until queue is empty. + */ + while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { + unsigned int processed = 0, drops = 0, sched = 0; + struct xdp_pkt *xdp_pkt; + + /* Release CPU reschedule checks */ + if (__ptr_ring_empty(rcpu->queue)) { + __set_current_state(TASK_INTERRUPTIBLE); + schedule(); + sched = 1; + } else { + sched = cond_resched(); + } + __set_current_state(TASK_RUNNING); + + /* Process packets in rcpu->queue */ + local_bh_disable(); + /* + * The bpf_cpu_map_entry is single consumer, with this + * kthread CPU pinned. Lockless access to ptr_ring + * consume side valid as no-resize allowed of queue. + */ + while ((xdp_pkt = __ptr_ring_consume(rcpu->queue))) { + struct sk_buff *skb; + int ret; + + skb = cpu_map_build_skb(rcpu, xdp_pkt); + if (!skb) { + page_frag_free(xdp_pkt); + continue; + } + + /* Inject into network stack */ + ret = netif_receive_skb_core(skb); + if (ret == NET_RX_DROP) + drops++; + + /* Limit BH-disable period */ + if (++processed == 8) + break; + } + /* Feedback loop via tracepoint */ + trace_xdp_cpumap_kthread(rcpu->map_id, processed, drops, sched); + + local_bh_enable(); /* resched point, may call do_softirq() */ + } + __set_current_state(TASK_RUNNING); + + put_cpu_map_entry(rcpu); + return 0; +} + +struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id) +{ + gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN; + struct bpf_cpu_map_entry *rcpu; + int numa, err; + + /* Have map->numa_node, but choose node of redirect target CPU */ + numa = cpu_to_node(cpu); + + rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa); + if (!rcpu) + return NULL; + + /* Alloc percpu bulkq */ + rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq), + sizeof(void *), gfp); + if (!rcpu->bulkq) + goto free_rcu; + + /* Alloc queue */ + rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa); + if (!rcpu->queue) + goto free_bulkq; + + err = ptr_ring_init(rcpu->queue, qsize, gfp); + if (err) + goto free_queue; + + rcpu->cpu = cpu; + rcpu->map_id = map_id; + rcpu->qsize = qsize; + + /* Setup kthread */ + rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa, + "cpumap/%d/map:%d", cpu, map_id); + if (IS_ERR(rcpu->kthread)) + goto free_ptr_ring; + + get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */ + get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */ + + /* Make sure kthread runs on a single CPU */ + kthread_bind(rcpu->kthread, cpu); + wake_up_process(rcpu->kthread); + + return rcpu; + +free_ptr_ring: + ptr_ring_cleanup(rcpu->queue, NULL); +free_queue: + kfree(rcpu->queue); +free_bulkq: + free_percpu(rcpu->bulkq); +free_rcu: + kfree(rcpu); + return NULL; +} + +void __cpu_map_entry_free(struct rcu_head *rcu) +{ + struct bpf_cpu_map_entry *rcpu; + int cpu; + + /* This cpu_map_entry have been disconnected from map and one + * RCU graze-period have elapsed. Thus, XDP cannot queue any + * new packets and cannot change/set flush_needed that can + * find this entry. + */ + rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu); + + /* Flush remaining packets in percpu bulkq */ + for_each_online_cpu(cpu) { + struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu); + + /* No concurrent bq_enqueue can run at this point */ + bq_flush_to_queue(rcpu, bq); + } + free_percpu(rcpu->bulkq); + /* Cannot kthread_stop() here, last put free rcpu resources */ + put_cpu_map_entry(rcpu); +} + +/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to + * ensure any driver rcu critical sections have completed, but this + * does not guarantee a flush has happened yet. Because driver side + * rcu_read_lock/unlock only protects the running XDP program. The + * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a + * pending flush op doesn't fail. + * + * The bpf_cpu_map_entry is still used by the kthread, and there can + * still be pending packets (in queue and percpu bulkq). A refcnt + * makes sure to last user (kthread_stop vs. call_rcu) free memory + * resources. + * + * The rcu callback __cpu_map_entry_free flush remaining packets in + * percpu bulkq to queue. Due to caller map_delete_elem() disable + * preemption, cannot call kthread_stop() to make sure queue is empty. + * Instead a work_queue is started for stopping kthread, + * cpu_map_kthread_stop, which waits for an RCU graze period before + * stopping kthread, emptying the queue. + */ +void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, + u32 key_cpu, struct bpf_cpu_map_entry *rcpu) +{ + struct bpf_cpu_map_entry *old_rcpu; + + old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu); + if (old_rcpu) { + call_rcu(&old_rcpu->rcu, __cpu_map_entry_free); + INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop); + schedule_work(&old_rcpu->kthread_stop_wq); + } +} + +int cpu_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + u32 key_cpu = *(u32 *)key; + + if (key_cpu >= map->max_entries) + return -EINVAL; + + /* notice caller map_delete_elem() use preempt_disable() */ + __cpu_map_entry_replace(cmap, key_cpu, NULL); + return 0; +} + +int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + struct bpf_cpu_map_entry *rcpu; + + /* Array index key correspond to CPU number */ + u32 key_cpu = *(u32 *)key; + /* Value is the queue size */ + u32 qsize = *(u32 *)value; + + if (unlikely(map_flags > BPF_EXIST)) + return -EINVAL; + if (unlikely(key_cpu >= cmap->map.max_entries)) + return -E2BIG; + if (unlikely(map_flags == BPF_NOEXIST)) + return -EEXIST; + if (unlikely(qsize > 16384)) /* sanity limit on qsize */ + return -EOVERFLOW; + + /* Make sure CPU is a valid possible cpu */ + if (!cpu_possible(key_cpu)) + return -ENODEV; + + if (qsize == 0) { + rcpu = NULL; /* Same as deleting */ + } else { + /* Updating qsize cause re-allocation of bpf_cpu_map_entry */ + rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id); + if (!rcpu) + return -ENOMEM; + } + rcu_read_lock(); + __cpu_map_entry_replace(cmap, key_cpu, rcpu); + rcu_read_unlock(); + return 0; +} + +void cpu_map_free(struct bpf_map *map) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + int cpu; + u32 i; + + /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the bpf programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding critical sections in + * these programs to complete. The rcu critical section only guarantees + * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map. + * It does __not__ ensure pending flush operations (if any) are + * complete. + */ + synchronize_rcu(); + + /* To ensure all pending flush operations have completed wait for flush + * bitmap to indicate all flush_needed bits to be zero on _all_ cpus. + * Because the above synchronize_rcu() ensures the map is disconnected + * from the program we can assume no new bits will be set. + */ + for_each_online_cpu(cpu) { + unsigned long *bitmap = per_cpu_ptr(cmap->flush_needed, cpu); + + while (!bitmap_empty(bitmap, cmap->map.max_entries)) + cond_resched(); + } + + /* For cpu_map the remote CPUs can still be using the entries + * (struct bpf_cpu_map_entry). + */ + for (i = 0; i < cmap->map.max_entries; i++) { + struct bpf_cpu_map_entry *rcpu; + + rcpu = READ_ONCE(cmap->cpu_map[i]); + if (!rcpu) + continue; + + /* bq flush and cleanup happens after RCU graze-period */ + __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */ + } + free_percpu(cmap->flush_needed); + bpf_map_area_free(cmap->cpu_map); + kfree(cmap); +} + +struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + struct bpf_cpu_map_entry *rcpu; + + if (key >= map->max_entries) + return NULL; + + rcpu = READ_ONCE(cmap->cpu_map[key]); + return rcpu; +} + +static void *cpu_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_cpu_map_entry *rcpu = + __cpu_map_lookup_elem(map, *(u32 *)key); + + return rcpu ? &rcpu->qsize : NULL; +} + +static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + u32 index = key ? *(u32 *)key : U32_MAX; + u32 *next = next_key; + + if (index >= cmap->map.max_entries) { + *next = 0; + return 0; + } + + if (index == cmap->map.max_entries - 1) + return -ENOENT; + *next = index + 1; + return 0; +} + +const struct bpf_map_ops cpu_map_ops = { + .map_alloc = cpu_map_alloc, + .map_free = cpu_map_free, + .map_delete_elem = cpu_map_delete_elem, + .map_update_elem = cpu_map_update_elem, + .map_lookup_elem = cpu_map_lookup_elem, + .map_get_next_key = cpu_map_get_next_key, +}; + +static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, + struct xdp_bulk_queue *bq) +{ + unsigned int processed = 0, drops = 0; + const int to_cpu = rcpu->cpu; + struct ptr_ring *q; + int i; + + if (unlikely(!bq->count)) + return 0; + + q = rcpu->queue; + spin_lock(&q->producer_lock); + + for (i = 0; i < bq->count; i++) { + void *xdp_pkt = bq->q[i]; + int err; + + err = __ptr_ring_produce(q, xdp_pkt); + if (err) { + drops++; + page_frag_free(xdp_pkt); /* Free xdp_pkt */ + } + processed++; + } + bq->count = 0; + spin_unlock(&q->producer_lock); + + /* Feedback loop via tracepoints */ + trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu); + return 0; +} + +/* Runs under RCU-read-side, plus in softirq under NAPI protection. + * Thus, safe percpu variable access. + */ +static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt) +{ + struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); + + if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) + bq_flush_to_queue(rcpu, bq); + + /* Notice, xdp_buff/page MUST be queued here, long enough for + * driver to code invoking us to finished, due to driver + * (e.g. ixgbe) recycle tricks based on page-refcnt. + * + * Thus, incoming xdp_pkt is always queued here (else we race + * with another CPU on page-refcnt and remaining driver code). + * Queue time is very short, as driver will invoke flush + * operation, when completing napi->poll call. + */ + bq->q[bq->count++] = xdp_pkt; + return 0; +} + +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + struct xdp_pkt *xdp_pkt; + + xdp_pkt = convert_to_xdp_pkt(xdp); + if (!xdp_pkt) + return -EOVERFLOW; + + /* Info needed when constructing SKB on remote CPU */ + xdp_pkt->dev_rx = dev_rx; + + bq_enqueue(rcpu, xdp_pkt); + return 0; +} + +void __cpu_map_insert_ctx(struct bpf_map *map, u32 bit) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed); + + __set_bit(bit, bitmap); +} + +void __cpu_map_flush(struct bpf_map *map) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed); + u32 bit; + + /* The napi->poll softirq makes sure __cpu_map_insert_ctx() + * and __cpu_map_flush() happen on same CPU. Thus, the percpu + * bitmap indicate which percpu bulkq have packets. + */ + for_each_set_bit(bit, bitmap, map->max_entries) { + struct bpf_cpu_map_entry *rcpu = READ_ONCE(cmap->cpu_map[bit]); + struct xdp_bulk_queue *bq; + + /* This is possible if entry is removed by user space + * between xdp redirect and flush op. + */ + if (unlikely(!rcpu)) + continue; + + __clear_bit(bit, bitmap); + + /* Flush all frames in bulkq to real queue */ + bq = this_cpu_ptr(rcpu->bulkq); + bq_flush_to_queue(rcpu, bq); + + /* If already running, costs spin_lock_irqsave + smb_mb */ + wake_up_process(rcpu->kthread); + } +} diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index e093d9a2c4dd..e5d3de7cff2e 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -50,6 +50,9 @@ #include <linux/bpf.h> #include <linux/filter.h> +#define DEV_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + struct bpf_dtab_netdev { struct net_device *dev; struct bpf_dtab *dtab; @@ -80,7 +83,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); dtab = kzalloc(sizeof(*dtab), GFP_USER); diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c new file mode 100644 index 000000000000..e682850c9715 --- /dev/null +++ b/kernel/bpf/disasm.c @@ -0,0 +1,214 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#include <linux/bpf.h> + +#include "disasm.h" + +#define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x) +static const char * const func_id_str[] = { + __BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN) +}; +#undef __BPF_FUNC_STR_FN + +const char *func_id_name(int id) +{ + BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID); + + if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id]) + return func_id_str[id]; + else + return "unknown"; +} + +const char *const bpf_class_string[8] = { + [BPF_LD] = "ld", + [BPF_LDX] = "ldx", + [BPF_ST] = "st", + [BPF_STX] = "stx", + [BPF_ALU] = "alu", + [BPF_JMP] = "jmp", + [BPF_RET] = "BUG", + [BPF_ALU64] = "alu64", +}; + +const char *const bpf_alu_string[16] = { + [BPF_ADD >> 4] = "+=", + [BPF_SUB >> 4] = "-=", + [BPF_MUL >> 4] = "*=", + [BPF_DIV >> 4] = "/=", + [BPF_OR >> 4] = "|=", + [BPF_AND >> 4] = "&=", + [BPF_LSH >> 4] = "<<=", + [BPF_RSH >> 4] = ">>=", + [BPF_NEG >> 4] = "neg", + [BPF_MOD >> 4] = "%=", + [BPF_XOR >> 4] = "^=", + [BPF_MOV >> 4] = "=", + [BPF_ARSH >> 4] = "s>>=", + [BPF_END >> 4] = "endian", +}; + +static const char *const bpf_ldst_string[] = { + [BPF_W >> 3] = "u32", + [BPF_H >> 3] = "u16", + [BPF_B >> 3] = "u8", + [BPF_DW >> 3] = "u64", +}; + +static const char *const bpf_jmp_string[16] = { + [BPF_JA >> 4] = "jmp", + [BPF_JEQ >> 4] = "==", + [BPF_JGT >> 4] = ">", + [BPF_JLT >> 4] = "<", + [BPF_JGE >> 4] = ">=", + [BPF_JLE >> 4] = "<=", + [BPF_JSET >> 4] = "&", + [BPF_JNE >> 4] = "!=", + [BPF_JSGT >> 4] = "s>", + [BPF_JSLT >> 4] = "s<", + [BPF_JSGE >> 4] = "s>=", + [BPF_JSLE >> 4] = "s<=", + [BPF_CALL >> 4] = "call", + [BPF_EXIT >> 4] = "exit", +}; + +static void print_bpf_end_insn(bpf_insn_print_cb verbose, + struct bpf_verifier_env *env, + const struct bpf_insn *insn) +{ + verbose(env, "(%02x) r%d = %s%d r%d\n", insn->code, insn->dst_reg, + BPF_SRC(insn->code) == BPF_TO_BE ? "be" : "le", + insn->imm, insn->dst_reg); +} + +void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env, + const struct bpf_insn *insn, bool allow_ptr_leaks) +{ + u8 class = BPF_CLASS(insn->code); + + if (class == BPF_ALU || class == BPF_ALU64) { + if (BPF_OP(insn->code) == BPF_END) { + if (class == BPF_ALU64) + verbose(env, "BUG_alu64_%02x\n", insn->code); + else + print_bpf_end_insn(verbose, env, insn); + } else if (BPF_OP(insn->code) == BPF_NEG) { + verbose(env, "(%02x) r%d = %s-r%d\n", + insn->code, insn->dst_reg, + class == BPF_ALU ? "(u32) " : "", + insn->dst_reg); + } else if (BPF_SRC(insn->code) == BPF_X) { + verbose(env, "(%02x) %sr%d %s %sr%d\n", + insn->code, class == BPF_ALU ? "(u32) " : "", + insn->dst_reg, + bpf_alu_string[BPF_OP(insn->code) >> 4], + class == BPF_ALU ? "(u32) " : "", + insn->src_reg); + } else { + verbose(env, "(%02x) %sr%d %s %s%d\n", + insn->code, class == BPF_ALU ? "(u32) " : "", + insn->dst_reg, + bpf_alu_string[BPF_OP(insn->code) >> 4], + class == BPF_ALU ? "(u32) " : "", + insn->imm); + } + } else if (class == BPF_STX) { + if (BPF_MODE(insn->code) == BPF_MEM) + verbose(env, "(%02x) *(%s *)(r%d %+d) = r%d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->src_reg); + else if (BPF_MODE(insn->code) == BPF_XADD) + verbose(env, "(%02x) lock *(%s *)(r%d %+d) += r%d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, insn->off, + insn->src_reg); + else + verbose(env, "BUG_%02x\n", insn->code); + } else if (class == BPF_ST) { + if (BPF_MODE(insn->code) != BPF_MEM) { + verbose(env, "BUG_st_%02x\n", insn->code); + return; + } + verbose(env, "(%02x) *(%s *)(r%d %+d) = %d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->imm); + } else if (class == BPF_LDX) { + if (BPF_MODE(insn->code) != BPF_MEM) { + verbose(env, "BUG_ldx_%02x\n", insn->code); + return; + } + verbose(env, "(%02x) r%d = *(%s *)(r%d %+d)\n", + insn->code, insn->dst_reg, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->off); + } else if (class == BPF_LD) { + if (BPF_MODE(insn->code) == BPF_ABS) { + verbose(env, "(%02x) r0 = *(%s *)skb[%d]\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->imm); + } else if (BPF_MODE(insn->code) == BPF_IND) { + verbose(env, "(%02x) r0 = *(%s *)skb[r%d + %d]\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->imm); + } else if (BPF_MODE(insn->code) == BPF_IMM && + BPF_SIZE(insn->code) == BPF_DW) { + /* At this point, we already made sure that the second + * part of the ldimm64 insn is accessible. + */ + u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; + bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD; + + if (map_ptr && !allow_ptr_leaks) + imm = 0; + + verbose(env, "(%02x) r%d = 0x%llx\n", insn->code, + insn->dst_reg, (unsigned long long)imm); + } else { + verbose(env, "BUG_ld_%02x\n", insn->code); + return; + } + } else if (class == BPF_JMP) { + u8 opcode = BPF_OP(insn->code); + + if (opcode == BPF_CALL) { + verbose(env, "(%02x) call %s#%d\n", insn->code, + func_id_name(insn->imm), insn->imm); + } else if (insn->code == (BPF_JMP | BPF_JA)) { + verbose(env, "(%02x) goto pc%+d\n", + insn->code, insn->off); + } else if (insn->code == (BPF_JMP | BPF_EXIT)) { + verbose(env, "(%02x) exit\n", insn->code); + } else if (BPF_SRC(insn->code) == BPF_X) { + verbose(env, "(%02x) if r%d %s r%d goto pc%+d\n", + insn->code, insn->dst_reg, + bpf_jmp_string[BPF_OP(insn->code) >> 4], + insn->src_reg, insn->off); + } else { + verbose(env, "(%02x) if r%d %s 0x%x goto pc%+d\n", + insn->code, insn->dst_reg, + bpf_jmp_string[BPF_OP(insn->code) >> 4], + insn->imm, insn->off); + } + } else { + verbose(env, "(%02x) %s\n", + insn->code, bpf_class_string[class]); + } +} diff --git a/kernel/bpf/disasm.h b/kernel/bpf/disasm.h new file mode 100644 index 000000000000..8de977e420b6 --- /dev/null +++ b/kernel/bpf/disasm.h @@ -0,0 +1,32 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef __BPF_DISASM_H__ +#define __BPF_DISASM_H__ + +#include <linux/bpf.h> +#include <linux/kernel.h> +#include <linux/stringify.h> + +extern const char *const bpf_alu_string[16]; +extern const char *const bpf_class_string[8]; + +const char *func_id_name(int id); + +struct bpf_verifier_env; +typedef void (*bpf_insn_print_cb)(struct bpf_verifier_env *env, + const char *, ...); +void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env, + const struct bpf_insn *insn, bool allow_ptr_leaks); + +#endif diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 431126f31ea3..919955236e63 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -18,8 +18,9 @@ #include "bpf_lru_list.h" #include "map_in_map.h" -#define HTAB_CREATE_FLAG_MASK \ - (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE) +#define HTAB_CREATE_FLAG_MASK \ + (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ + BPF_F_RDONLY | BPF_F_WRONLY) struct bucket { struct hlist_nulls_head head; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index e833ed914358..01aaef1a77c5 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -295,7 +295,7 @@ out: } static void *bpf_obj_do_get(const struct filename *pathname, - enum bpf_type *type) + enum bpf_type *type, int flags) { struct inode *inode; struct path path; @@ -307,7 +307,7 @@ static void *bpf_obj_do_get(const struct filename *pathname, return ERR_PTR(ret); inode = d_backing_inode(path.dentry); - ret = inode_permission(inode, MAY_WRITE); + ret = inode_permission(inode, ACC_MODE(flags)); if (ret) goto out; @@ -326,18 +326,23 @@ out: return ERR_PTR(ret); } -int bpf_obj_get_user(const char __user *pathname) +int bpf_obj_get_user(const char __user *pathname, int flags) { enum bpf_type type = BPF_TYPE_UNSPEC; struct filename *pname; int ret = -ENOENT; + int f_flags; void *raw; + f_flags = bpf_get_file_flag(flags); + if (f_flags < 0) + return f_flags; + pname = getname(pathname); if (IS_ERR(pname)) return PTR_ERR(pname); - raw = bpf_obj_do_get(pname, &type); + raw = bpf_obj_do_get(pname, &type, f_flags); if (IS_ERR(raw)) { ret = PTR_ERR(raw); goto out; @@ -346,7 +351,7 @@ int bpf_obj_get_user(const char __user *pathname) if (type == BPF_TYPE_PROG) ret = bpf_prog_new_fd(raw); else if (type == BPF_TYPE_MAP) - ret = bpf_map_new_fd(raw); + ret = bpf_map_new_fd(raw, f_flags); else goto out; @@ -363,6 +368,7 @@ out: putname(pname); return ret; } +EXPORT_SYMBOL_GPL(bpf_obj_get_user); static void bpf_evict_inode(struct inode *inode) { diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 34d8a690ea05..885e45479680 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -495,7 +495,8 @@ out: #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) -#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE) +#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \ + BPF_F_RDONLY | BPF_F_WRONLY) static struct bpf_map *trie_alloc(union bpf_attr *attr) { diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index a298d6666698..86ec846f2d5e 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -40,6 +40,9 @@ #include <linux/list.h> #include <net/strparser.h> +#define SOCK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + struct bpf_stab { struct bpf_map map; struct sock **sock_map; @@ -489,7 +492,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); if (attr->value_size > KMALLOC_MAX_SIZE) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 135be433e9a0..a15bc636cc98 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -11,6 +11,9 @@ #include <linux/perf_event.h> #include "percpu_freelist.h" +#define STACK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + struct stack_map_bucket { struct pcpu_freelist_node fnode; u32 hash; @@ -60,7 +63,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - if (attr->map_flags & ~BPF_F_NUMA_NODE) + if (attr->map_flags & ~STACK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); /* check sanity of attributes */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0048cb24ba7b..323be2473c4b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -34,6 +34,8 @@ #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) #define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map)) +#define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) + DEFINE_PER_CPU(int, bpf_prog_active); static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); @@ -210,6 +212,7 @@ static void bpf_map_free_deferred(struct work_struct *work) struct bpf_map *map = container_of(work, struct bpf_map, work); bpf_map_uncharge_memlock(map); + security_bpf_map_free(map); /* implementation dependent freeing */ map->ops->map_free(map); } @@ -294,17 +297,54 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) } #endif -static const struct file_operations bpf_map_fops = { +static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz, + loff_t *ppos) +{ + /* We need this handler such that alloc_file() enables + * f_mode with FMODE_CAN_READ. + */ + return -EINVAL; +} + +static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, + size_t siz, loff_t *ppos) +{ + /* We need this handler such that alloc_file() enables + * f_mode with FMODE_CAN_WRITE. + */ + return -EINVAL; +} + +const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, #endif .release = bpf_map_release, + .read = bpf_dummy_read, + .write = bpf_dummy_write, }; -int bpf_map_new_fd(struct bpf_map *map) +int bpf_map_new_fd(struct bpf_map *map, int flags) { + int ret; + + ret = security_bpf_map(map, OPEN_FMODE(flags)); + if (ret < 0) + return ret; + return anon_inode_getfd("bpf-map", &bpf_map_fops, map, - O_RDWR | O_CLOEXEC); + flags | O_CLOEXEC); +} + +int bpf_get_file_flag(int flags) +{ + if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY)) + return -EINVAL; + if (flags & BPF_F_RDONLY) + return O_RDONLY; + if (flags & BPF_F_WRONLY) + return O_WRONLY; + return O_RDWR; } /* helper macro to check that unused fields 'union bpf_attr' are zero */ @@ -322,6 +362,8 @@ static int bpf_obj_name_cpy(char *dst, const char *src) { const char *end = src + BPF_OBJ_NAME_LEN; + memset(dst, 0, BPF_OBJ_NAME_LEN); + /* Copy all isalnum() and '_' char */ while (src < end && *src) { if (!isalnum(*src) && *src != '_') @@ -333,9 +375,6 @@ static int bpf_obj_name_cpy(char *dst, const char *src) if (src == end) return -EINVAL; - /* '\0' terminates dst */ - *dst = 0; - return 0; } @@ -345,12 +384,17 @@ static int map_create(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); struct bpf_map *map; + int f_flags; int err; err = CHECK_ATTR(BPF_MAP_CREATE); if (err) return -EINVAL; + f_flags = bpf_get_file_flag(attr->map_flags); + if (f_flags < 0) + return f_flags; + if (numa_node != NUMA_NO_NODE && ((unsigned int)numa_node >= nr_node_ids || !node_online(numa_node))) @@ -368,15 +412,19 @@ static int map_create(union bpf_attr *attr) atomic_set(&map->refcnt, 1); atomic_set(&map->usercnt, 1); - err = bpf_map_charge_memlock(map); + err = security_bpf_map_alloc(map); if (err) goto free_map_nouncharge; + err = bpf_map_charge_memlock(map); + if (err) + goto free_map_sec; + err = bpf_map_alloc_id(map); if (err) goto free_map; - err = bpf_map_new_fd(map); + err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. * bpf_map_put() is needed because the above @@ -393,6 +441,8 @@ static int map_create(union bpf_attr *attr) free_map: bpf_map_uncharge_memlock(map); +free_map_sec: + security_bpf_map_free(map); free_map_nouncharge: map->ops->map_free(map); return err; @@ -491,6 +541,11 @@ static int map_lookup_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_READ)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -571,6 +626,11 @@ static int map_update_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -593,6 +653,12 @@ static int map_update_elem(union bpf_attr *attr) if (copy_from_user(value, uvalue, value_size) != 0) goto free_value; + /* Need to create a kthread, thus must support schedule */ + if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + err = map->ops->map_update_elem(map, key, value, attr->flags); + goto out; + } + /* must increment bpf_prog_active to avoid kprobe+bpf triggering from * inside bpf map update or delete otherwise deadlocks are possible */ @@ -623,7 +689,7 @@ static int map_update_elem(union bpf_attr *attr) } __this_cpu_dec(bpf_prog_active); preempt_enable(); - +out: if (!err) trace_bpf_map_update_elem(map, ufd, key, value); free_value: @@ -654,6 +720,11 @@ static int map_delete_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -697,6 +768,11 @@ static int map_get_next_key(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_READ)) { + err = -EPERM; + goto err_put; + } + if (ukey) { key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { @@ -734,9 +810,9 @@ err_put: return err; } -static const struct bpf_verifier_ops * const bpf_prog_types[] = { -#define BPF_PROG_TYPE(_id, _ops) \ - [_id] = &_ops, +static const struct bpf_prog_ops * const bpf_prog_types[] = { +#define BPF_PROG_TYPE(_id, _name) \ + [_id] = & _name ## _prog_ops, #define BPF_MAP_TYPE(_id, _ops) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE @@ -851,6 +927,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) free_used_maps(aux); bpf_prog_uncharge_memlock(aux->prog); + security_bpf_prog_free(aux); bpf_prog_free(aux->prog); } @@ -898,15 +975,23 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) } #endif -static const struct file_operations bpf_prog_fops = { +const struct file_operations bpf_prog_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_prog_show_fdinfo, #endif .release = bpf_prog_release, + .read = bpf_dummy_read, + .write = bpf_dummy_write, }; int bpf_prog_new_fd(struct bpf_prog *prog) { + int ret; + + ret = security_bpf_prog(prog); + if (ret < 0) + return ret; + return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); } @@ -1046,10 +1131,14 @@ static int bpf_prog_load(union bpf_attr *attr) if (!prog) return -ENOMEM; - err = bpf_prog_charge_memlock(prog); + err = security_bpf_prog_alloc(prog->aux); if (err) goto free_prog_nouncharge; + err = bpf_prog_charge_memlock(prog); + if (err) + goto free_prog_sec; + prog->len = attr->insn_cnt; err = -EFAULT; @@ -1107,16 +1196,18 @@ free_used_maps: free_used_maps(prog->aux); free_prog: bpf_prog_uncharge_memlock(prog); +free_prog_sec: + security_bpf_prog_free(prog->aux); free_prog_nouncharge: bpf_prog_free(prog); return err; } -#define BPF_OBJ_LAST_FIELD bpf_fd +#define BPF_OBJ_LAST_FIELD file_flags static int bpf_obj_pin(const union bpf_attr *attr) { - if (CHECK_ATTR(BPF_OBJ)) + if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0) return -EINVAL; return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname)); @@ -1124,10 +1215,12 @@ static int bpf_obj_pin(const union bpf_attr *attr) static int bpf_obj_get(const union bpf_attr *attr) { - if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0) + if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 || + attr->file_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; - return bpf_obj_get_user(u64_to_user_ptr(attr->pathname)); + return bpf_obj_get_user(u64_to_user_ptr(attr->pathname), + attr->file_flags); } #ifdef CONFIG_CGROUP_BPF @@ -1387,20 +1480,26 @@ static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) return fd; } -#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD map_id +#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD open_flags static int bpf_map_get_fd_by_id(const union bpf_attr *attr) { struct bpf_map *map; u32 id = attr->map_id; + int f_flags; int fd; - if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID)) + if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID) || + attr->open_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; + f_flags = bpf_get_file_flag(attr->open_flags); + if (f_flags < 0) + return f_flags; + spin_lock_bh(&map_idr_lock); map = idr_find(&map_idr, id); if (map) @@ -1412,7 +1511,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); - fd = bpf_map_new_fd(map); + fd = bpf_map_new_fd(map, f_flags); if (fd < 0) bpf_map_put(map); @@ -1567,6 +1666,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz if (copy_from_user(&attr, uattr, size) != 0) return -EFAULT; + err = security_bpf(cmd, &attr, size); + if (err < 0) + return err; + switch (cmd) { case BPF_MAP_CREATE: err = map_create(&attr); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 52b022310f6a..545b8c45a578 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -21,6 +21,17 @@ #include <linux/vmalloc.h> #include <linux/stringify.h> +#include "disasm.h" + +static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { +#define BPF_PROG_TYPE(_id, _name) \ + [_id] = & _name ## _verifier_ops, +#define BPF_MAP_TYPE(_id, _ops) +#include <linux/bpf_types.h> +#undef BPF_PROG_TYPE +#undef BPF_MAP_TYPE +}; + /* bpf_check() is a static code analyzer that walks eBPF program * instruction by instruction and updates register/stack state. * All paths of conditional branches are analyzed until 'bpf_exit' insn. @@ -153,28 +164,36 @@ struct bpf_call_arg_meta { int access_size; }; -/* verbose verifier prints what it's seeing - * bpf_check() is called under lock, so no race to access these global vars - */ -static u32 log_level, log_size, log_len; -static char *log_buf; - static DEFINE_MUTEX(bpf_verifier_lock); /* log_level controls verbosity level of eBPF verifier. * verbose() is used to dump the verification trace to the log, so the user * can figure out what's wrong with the program */ -static __printf(1, 2) void verbose(const char *fmt, ...) +static __printf(2, 3) void verbose(struct bpf_verifier_env *env, + const char *fmt, ...) { + struct bpf_verifer_log *log = &env->log; + unsigned int n; va_list args; - if (log_level == 0 || log_len >= log_size - 1) + if (!log->level || !log->ubuf || bpf_verifier_log_full(log)) return; va_start(args, fmt); - log_len += vscnprintf(log_buf + log_len, log_size - log_len, fmt, args); + n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args); va_end(args); + + WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1, + "verifier log line truncated - local buffer too short\n"); + + n = min(log->len_total - log->len_used - 1, n); + log->kbuf[n] = '\0'; + + if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1)) + log->len_used += n; + else + log->ubuf = NULL; } static bool type_is_pkt_pointer(enum bpf_reg_type type) @@ -197,23 +216,8 @@ static const char * const reg_type_str[] = { [PTR_TO_PACKET_END] = "pkt_end", }; -#define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x) -static const char * const func_id_str[] = { - __BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN) -}; -#undef __BPF_FUNC_STR_FN - -static const char *func_id_name(int id) -{ - BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID); - - if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id]) - return func_id_str[id]; - else - return "unknown"; -} - -static void print_verifier_state(struct bpf_verifier_state *state) +static void print_verifier_state(struct bpf_verifier_env *env, + struct bpf_verifier_state *state) { struct bpf_reg_state *reg; enum bpf_reg_type t; @@ -224,21 +228,21 @@ static void print_verifier_state(struct bpf_verifier_state *state) t = reg->type; if (t == NOT_INIT) continue; - verbose(" R%d=%s", i, reg_type_str[t]); + verbose(env, " R%d=%s", i, reg_type_str[t]); if ((t == SCALAR_VALUE || t == PTR_TO_STACK) && tnum_is_const(reg->var_off)) { /* reg->off should be 0 for SCALAR_VALUE */ - verbose("%lld", reg->var_off.value + reg->off); + verbose(env, "%lld", reg->var_off.value + reg->off); } else { - verbose("(id=%d", reg->id); + verbose(env, "(id=%d", reg->id); if (t != SCALAR_VALUE) - verbose(",off=%d", reg->off); + verbose(env, ",off=%d", reg->off); if (type_is_pkt_pointer(t)) - verbose(",r=%d", reg->range); + verbose(env, ",r=%d", reg->range); else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE || t == PTR_TO_MAP_VALUE_OR_NULL) - verbose(",ks=%d,vs=%d", + verbose(env, ",ks=%d,vs=%d", reg->map_ptr->key_size, reg->map_ptr->value_size); if (tnum_is_const(reg->var_off)) { @@ -246,218 +250,38 @@ static void print_verifier_state(struct bpf_verifier_state *state) * could be a pointer whose offset is too big * for reg->off */ - verbose(",imm=%llx", reg->var_off.value); + verbose(env, ",imm=%llx", reg->var_off.value); } else { if (reg->smin_value != reg->umin_value && reg->smin_value != S64_MIN) - verbose(",smin_value=%lld", + verbose(env, ",smin_value=%lld", (long long)reg->smin_value); if (reg->smax_value != reg->umax_value && reg->smax_value != S64_MAX) - verbose(",smax_value=%lld", + verbose(env, ",smax_value=%lld", (long long)reg->smax_value); if (reg->umin_value != 0) - verbose(",umin_value=%llu", + verbose(env, ",umin_value=%llu", (unsigned long long)reg->umin_value); if (reg->umax_value != U64_MAX) - verbose(",umax_value=%llu", + verbose(env, ",umax_value=%llu", (unsigned long long)reg->umax_value); if (!tnum_is_unknown(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(",var_off=%s", tn_buf); + verbose(env, ",var_off=%s", tn_buf); } } - verbose(")"); + verbose(env, ")"); } } for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] == STACK_SPILL) - verbose(" fp%d=%s", -MAX_BPF_STACK + i, + verbose(env, " fp%d=%s", -MAX_BPF_STACK + i, reg_type_str[state->spilled_regs[i / BPF_REG_SIZE].type]); } - verbose("\n"); -} - -static const char *const bpf_class_string[] = { - [BPF_LD] = "ld", - [BPF_LDX] = "ldx", - [BPF_ST] = "st", - [BPF_STX] = "stx", - [BPF_ALU] = "alu", - [BPF_JMP] = "jmp", - [BPF_RET] = "BUG", - [BPF_ALU64] = "alu64", -}; - -static const char *const bpf_alu_string[16] = { - [BPF_ADD >> 4] = "+=", - [BPF_SUB >> 4] = "-=", - [BPF_MUL >> 4] = "*=", - [BPF_DIV >> 4] = "/=", - [BPF_OR >> 4] = "|=", - [BPF_AND >> 4] = "&=", - [BPF_LSH >> 4] = "<<=", - [BPF_RSH >> 4] = ">>=", - [BPF_NEG >> 4] = "neg", - [BPF_MOD >> 4] = "%=", - [BPF_XOR >> 4] = "^=", - [BPF_MOV >> 4] = "=", - [BPF_ARSH >> 4] = "s>>=", - [BPF_END >> 4] = "endian", -}; - -static const char *const bpf_ldst_string[] = { - [BPF_W >> 3] = "u32", - [BPF_H >> 3] = "u16", - [BPF_B >> 3] = "u8", - [BPF_DW >> 3] = "u64", -}; - -static const char *const bpf_jmp_string[16] = { - [BPF_JA >> 4] = "jmp", - [BPF_JEQ >> 4] = "==", - [BPF_JGT >> 4] = ">", - [BPF_JLT >> 4] = "<", - [BPF_JGE >> 4] = ">=", - [BPF_JLE >> 4] = "<=", - [BPF_JSET >> 4] = "&", - [BPF_JNE >> 4] = "!=", - [BPF_JSGT >> 4] = "s>", - [BPF_JSLT >> 4] = "s<", - [BPF_JSGE >> 4] = "s>=", - [BPF_JSLE >> 4] = "s<=", - [BPF_CALL >> 4] = "call", - [BPF_EXIT >> 4] = "exit", -}; - -static void print_bpf_end_insn(const struct bpf_verifier_env *env, - const struct bpf_insn *insn) -{ - verbose("(%02x) r%d = %s%d r%d\n", insn->code, insn->dst_reg, - BPF_SRC(insn->code) == BPF_TO_BE ? "be" : "le", - insn->imm, insn->dst_reg); -} - -static void print_bpf_insn(const struct bpf_verifier_env *env, - const struct bpf_insn *insn) -{ - u8 class = BPF_CLASS(insn->code); - - if (class == BPF_ALU || class == BPF_ALU64) { - if (BPF_OP(insn->code) == BPF_END) { - if (class == BPF_ALU64) - verbose("BUG_alu64_%02x\n", insn->code); - else - print_bpf_end_insn(env, insn); - } else if (BPF_OP(insn->code) == BPF_NEG) { - verbose("(%02x) r%d = %s-r%d\n", - insn->code, insn->dst_reg, - class == BPF_ALU ? "(u32) " : "", - insn->dst_reg); - } else if (BPF_SRC(insn->code) == BPF_X) { - verbose("(%02x) %sr%d %s %sr%d\n", - insn->code, class == BPF_ALU ? "(u32) " : "", - insn->dst_reg, - bpf_alu_string[BPF_OP(insn->code) >> 4], - class == BPF_ALU ? "(u32) " : "", - insn->src_reg); - } else { - verbose("(%02x) %sr%d %s %s%d\n", - insn->code, class == BPF_ALU ? "(u32) " : "", - insn->dst_reg, - bpf_alu_string[BPF_OP(insn->code) >> 4], - class == BPF_ALU ? "(u32) " : "", - insn->imm); - } - } else if (class == BPF_STX) { - if (BPF_MODE(insn->code) == BPF_MEM) - verbose("(%02x) *(%s *)(r%d %+d) = r%d\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->dst_reg, - insn->off, insn->src_reg); - else if (BPF_MODE(insn->code) == BPF_XADD) - verbose("(%02x) lock *(%s *)(r%d %+d) += r%d\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->dst_reg, insn->off, - insn->src_reg); - else - verbose("BUG_%02x\n", insn->code); - } else if (class == BPF_ST) { - if (BPF_MODE(insn->code) != BPF_MEM) { - verbose("BUG_st_%02x\n", insn->code); - return; - } - verbose("(%02x) *(%s *)(r%d %+d) = %d\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->dst_reg, - insn->off, insn->imm); - } else if (class == BPF_LDX) { - if (BPF_MODE(insn->code) != BPF_MEM) { - verbose("BUG_ldx_%02x\n", insn->code); - return; - } - verbose("(%02x) r%d = *(%s *)(r%d %+d)\n", - insn->code, insn->dst_reg, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->src_reg, insn->off); - } else if (class == BPF_LD) { - if (BPF_MODE(insn->code) == BPF_ABS) { - verbose("(%02x) r0 = *(%s *)skb[%d]\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->imm); - } else if (BPF_MODE(insn->code) == BPF_IND) { - verbose("(%02x) r0 = *(%s *)skb[r%d + %d]\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->src_reg, insn->imm); - } else if (BPF_MODE(insn->code) == BPF_IMM && - BPF_SIZE(insn->code) == BPF_DW) { - /* At this point, we already made sure that the second - * part of the ldimm64 insn is accessible. - */ - u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; - bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD; - - if (map_ptr && !env->allow_ptr_leaks) - imm = 0; - - verbose("(%02x) r%d = 0x%llx\n", insn->code, - insn->dst_reg, (unsigned long long)imm); - } else { - verbose("BUG_ld_%02x\n", insn->code); - return; - } - } else if (class == BPF_JMP) { - u8 opcode = BPF_OP(insn->code); - - if (opcode == BPF_CALL) { - verbose("(%02x) call %s#%d\n", insn->code, - func_id_name(insn->imm), insn->imm); - } else if (insn->code == (BPF_JMP | BPF_JA)) { - verbose("(%02x) goto pc%+d\n", - insn->code, insn->off); - } else if (insn->code == (BPF_JMP | BPF_EXIT)) { - verbose("(%02x) exit\n", insn->code); - } else if (BPF_SRC(insn->code) == BPF_X) { - verbose("(%02x) if r%d %s r%d goto pc%+d\n", - insn->code, insn->dst_reg, - bpf_jmp_string[BPF_OP(insn->code) >> 4], - insn->src_reg, insn->off); - } else { - verbose("(%02x) if r%d %s 0x%x goto pc%+d\n", - insn->code, insn->dst_reg, - bpf_jmp_string[BPF_OP(insn->code) >> 4], - insn->imm, insn->off); - } - } else { - verbose("(%02x) %s\n", insn->code, bpf_class_string[class]); - } + verbose(env, "\n"); } static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx) @@ -495,7 +319,7 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, env->head = elem; env->stack_size++; if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) { - verbose("BPF program is too complex\n"); + verbose(env, "BPF program is too complex\n"); goto err; } return &elem->st; @@ -533,10 +357,11 @@ static void __mark_reg_known_zero(struct bpf_reg_state *reg) __mark_reg_known(reg, 0); } -static void mark_reg_known_zero(struct bpf_reg_state *regs, u32 regno) +static void mark_reg_known_zero(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { - verbose("mark_reg_known_zero(regs, %u)\n", regno); + verbose(env, "mark_reg_known_zero(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) __mark_reg_not_init(regs + regno); @@ -646,10 +471,11 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg) __mark_reg_unbounded(reg); } -static void mark_reg_unknown(struct bpf_reg_state *regs, u32 regno) +static void mark_reg_unknown(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { - verbose("mark_reg_unknown(regs, %u)\n", regno); + verbose(env, "mark_reg_unknown(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) __mark_reg_not_init(regs + regno); @@ -664,10 +490,11 @@ static void __mark_reg_not_init(struct bpf_reg_state *reg) reg->type = NOT_INIT; } -static void mark_reg_not_init(struct bpf_reg_state *regs, u32 regno) +static void mark_reg_not_init(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { - verbose("mark_reg_not_init(regs, %u)\n", regno); + verbose(env, "mark_reg_not_init(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) __mark_reg_not_init(regs + regno); @@ -676,22 +503,23 @@ static void mark_reg_not_init(struct bpf_reg_state *regs, u32 regno) __mark_reg_not_init(regs + regno); } -static void init_reg_state(struct bpf_reg_state *regs) +static void init_reg_state(struct bpf_verifier_env *env, + struct bpf_reg_state *regs) { int i; for (i = 0; i < MAX_BPF_REG; i++) { - mark_reg_not_init(regs, i); + mark_reg_not_init(env, regs, i); regs[i].live = REG_LIVE_NONE; } /* frame pointer */ regs[BPF_REG_FP].type = PTR_TO_STACK; - mark_reg_known_zero(regs, BPF_REG_FP); + mark_reg_known_zero(env, regs, BPF_REG_FP); /* 1st arg to a function */ regs[BPF_REG_1].type = PTR_TO_CTX; - mark_reg_known_zero(regs, BPF_REG_1); + mark_reg_known_zero(env, regs, BPF_REG_1); } enum reg_arg_type { @@ -704,6 +532,10 @@ static void mark_reg_read(const struct bpf_verifier_state *state, u32 regno) { struct bpf_verifier_state *parent = state->parent; + if (regno == BPF_REG_FP) + /* We don't need to worry about FP liveness because it's read-only */ + return; + while (parent) { /* if read wasn't screened by an earlier write ... */ if (state->regs[regno].live & REG_LIVE_WRITTEN) @@ -721,26 +553,26 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, struct bpf_reg_state *regs = env->cur_state.regs; if (regno >= MAX_BPF_REG) { - verbose("R%d is invalid\n", regno); + verbose(env, "R%d is invalid\n", regno); return -EINVAL; } if (t == SRC_OP) { /* check whether register used as source operand can be read */ if (regs[regno].type == NOT_INIT) { - verbose("R%d !read_ok\n", regno); + verbose(env, "R%d !read_ok\n", regno); return -EACCES; } mark_reg_read(&env->cur_state, regno); } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { - verbose("frame pointer is read only\n"); + verbose(env, "frame pointer is read only\n"); return -EACCES; } regs[regno].live |= REG_LIVE_WRITTEN; if (t == DST_OP) - mark_reg_unknown(regs, regno); + mark_reg_unknown(env, regs, regno); } return 0; } @@ -765,7 +597,8 @@ static bool is_spillable_regtype(enum bpf_reg_type type) /* check_stack_read/write functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ -static int check_stack_write(struct bpf_verifier_state *state, int off, +static int check_stack_write(struct bpf_verifier_env *env, + struct bpf_verifier_state *state, int off, int size, int value_regno) { int i, spi = (MAX_BPF_STACK + off) / BPF_REG_SIZE; @@ -778,7 +611,7 @@ static int check_stack_write(struct bpf_verifier_state *state, int off, /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { - verbose("invalid size of register spill\n"); + verbose(env, "invalid size of register spill\n"); return -EACCES; } @@ -813,7 +646,8 @@ static void mark_stack_slot_read(const struct bpf_verifier_state *state, int slo } } -static int check_stack_read(struct bpf_verifier_state *state, int off, int size, +static int check_stack_read(struct bpf_verifier_env *env, + struct bpf_verifier_state *state, int off, int size, int value_regno) { u8 *slot_type; @@ -823,12 +657,12 @@ static int check_stack_read(struct bpf_verifier_state *state, int off, int size, if (slot_type[0] == STACK_SPILL) { if (size != BPF_REG_SIZE) { - verbose("invalid size of register spill\n"); + verbose(env, "invalid size of register spill\n"); return -EACCES; } for (i = 1; i < BPF_REG_SIZE; i++) { if (slot_type[i] != STACK_SPILL) { - verbose("corrupted spill memory\n"); + verbose(env, "corrupted spill memory\n"); return -EACCES; } } @@ -844,14 +678,14 @@ static int check_stack_read(struct bpf_verifier_state *state, int off, int size, } else { for (i = 0; i < size; i++) { if (slot_type[i] != STACK_MISC) { - verbose("invalid read from stack off %d+%d size %d\n", + verbose(env, "invalid read from stack off %d+%d size %d\n", off, i, size); return -EACCES; } } if (value_regno >= 0) /* have read misc data from the stack */ - mark_reg_unknown(state->regs, value_regno); + mark_reg_unknown(env, state->regs, value_regno); return 0; } } @@ -863,7 +697,7 @@ static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off, struct bpf_map *map = env->cur_state.regs[regno].map_ptr; if (off < 0 || size <= 0 || off + size > map->value_size) { - verbose("invalid access to map value, value_size=%d off=%d size=%d\n", + verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n", map->value_size, off, size); return -EACCES; } @@ -882,8 +716,8 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, * need to try adding each of min_value and max_value to off * to make sure our theoretical access will be safe. */ - if (log_level) - print_verifier_state(state); + if (env->log.level) + print_verifier_state(env, state); /* The minimum value is only important with signed * comparisons where we can't assume the floor of a * value is 0. If we are using signed variables for our @@ -891,13 +725,14 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, * will have a set floor within our range. */ if (reg->smin_value < 0) { - verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", + verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } err = __check_map_access(env, regno, reg->smin_value + off, size); if (err) { - verbose("R%d min value is outside of the array range\n", regno); + verbose(env, "R%d min value is outside of the array range\n", + regno); return err; } @@ -906,13 +741,14 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, * If reg->umax_value + off could overflow, treat that as unbounded too. */ if (reg->umax_value >= BPF_MAX_VAR_OFF) { - verbose("R%d unbounded memory access, make sure to bounds check any array access into a map\n", + verbose(env, "R%d unbounded memory access, make sure to bounds check any array access into a map\n", regno); return -EACCES; } err = __check_map_access(env, regno, reg->umax_value + off, size); if (err) - verbose("R%d max value is outside of the array range\n", regno); + verbose(env, "R%d max value is outside of the array range\n", + regno); return err; } @@ -951,7 +787,7 @@ static int __check_packet_access(struct bpf_verifier_env *env, u32 regno, struct bpf_reg_state *reg = ®s[regno]; if (off < 0 || size <= 0 || (u64)off + size > reg->range) { - verbose("invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n", + verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n", off, size, regno, reg->id, reg->off, reg->range); return -EACCES; } @@ -974,13 +810,13 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, * detail to prove they're safe. */ if (reg->smin_value < 0) { - verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", + verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } err = __check_packet_access(env, regno, off, size); if (err) { - verbose("R%d offset is outside of the packet\n", regno); + verbose(env, "R%d offset is outside of the packet\n", regno); return err; } return err; @@ -994,12 +830,8 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, .reg_type = *reg_type, }; - /* for analyzer ctx accesses are already validated and converted */ - if (env->analyzer_ops) - return 0; - - if (env->prog->aux->ops->is_valid_access && - env->prog->aux->ops->is_valid_access(off, size, t, &info)) { + if (env->ops->is_valid_access && + env->ops->is_valid_access(off, size, t, &info)) { /* A non zero info.ctx_field_size indicates that this field is a * candidate for later verifier transformation to load the whole * field and then apply a mask when accessed with a narrower @@ -1007,16 +839,19 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, * will only allow for whole field access and rejects any other * type of narrower access. */ - env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; *reg_type = info.reg_type; + if (env->analyzer_ops) + return 0; + + env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; return 0; } - verbose("invalid bpf_context access off=%d size=%d\n", off, size); + verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size); return -EACCES; } @@ -1034,7 +869,8 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno) return __is_pointer_value(env->allow_ptr_leaks, &env->cur_state.regs[regno]); } -static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, +static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int off, int size, bool strict) { struct tnum reg_off; @@ -1059,7 +895,8 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose("misaligned packet access off %d+%s+%d+%d size %d\n", + verbose(env, + "misaligned packet access off %d+%s+%d+%d size %d\n", ip_align, tn_buf, reg->off, off, size); return -EACCES; } @@ -1067,7 +904,8 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, return 0; } -static int check_generic_ptr_alignment(const struct bpf_reg_state *reg, +static int check_generic_ptr_alignment(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, const char *pointer_desc, int off, int size, bool strict) { @@ -1082,7 +920,7 @@ static int check_generic_ptr_alignment(const struct bpf_reg_state *reg, char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose("misaligned %saccess off %s+%d+%d size %d\n", + verbose(env, "misaligned %saccess off %s+%d+%d size %d\n", pointer_desc, tn_buf, reg->off, off, size); return -EACCES; } @@ -1103,7 +941,7 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, /* Special case, because of NET_IP_ALIGN. Given metadata sits * right in front, treat it the very same way. */ - return check_pkt_ptr_alignment(reg, off, size, strict); + return check_pkt_ptr_alignment(env, reg, off, size, strict); case PTR_TO_MAP_VALUE: pointer_desc = "value "; break; @@ -1116,7 +954,8 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, default: break; } - return check_generic_ptr_alignment(reg, pointer_desc, off, size, strict); + return check_generic_ptr_alignment(env, reg, pointer_desc, off, size, + strict); } /* check whether memory at (regno + off) is accessible for t = (read | write) @@ -1148,20 +987,20 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (reg->type == PTR_TO_MAP_VALUE) { if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { - verbose("R%d leaks addr into map\n", value_regno); + verbose(env, "R%d leaks addr into map\n", value_regno); return -EACCES; } err = check_map_access(env, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) - mark_reg_unknown(state->regs, value_regno); + mark_reg_unknown(env, state->regs, value_regno); } else if (reg->type == PTR_TO_CTX) { enum bpf_reg_type reg_type = SCALAR_VALUE; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { - verbose("R%d leaks addr into ctx\n", value_regno); + verbose(env, "R%d leaks addr into ctx\n", value_regno); return -EACCES; } /* ctx accesses must be at a fixed offset, so that we can @@ -1171,7 +1010,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose("variable ctx access var_off=%s off=%d size=%d", + verbose(env, + "variable ctx access var_off=%s off=%d size=%d", tn_buf, off, size); return -EACCES; } @@ -1183,9 +1023,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn * case, we know the offset is zero. */ if (reg_type == SCALAR_VALUE) - mark_reg_unknown(state->regs, value_regno); + mark_reg_unknown(env, state->regs, value_regno); else - mark_reg_known_zero(state->regs, value_regno); + mark_reg_known_zero(env, state->regs, + value_regno); state->regs[value_regno].id = 0; state->regs[value_regno].off = 0; state->regs[value_regno].range = 0; @@ -1201,13 +1042,14 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose("variable stack access var_off=%s off=%d size=%d", + verbose(env, "variable stack access var_off=%s off=%d size=%d", tn_buf, off, size); return -EACCES; } off += reg->var_off.value; if (off >= 0 || off < -MAX_BPF_STACK) { - verbose("invalid stack off=%d size=%d\n", off, size); + verbose(env, "invalid stack off=%d size=%d\n", off, + size); return -EACCES; } @@ -1218,29 +1060,32 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (!env->allow_ptr_leaks && state->stack_slot_type[MAX_BPF_STACK + off] == STACK_SPILL && size != BPF_REG_SIZE) { - verbose("attempt to corrupt spilled pointer on stack\n"); + verbose(env, "attempt to corrupt spilled pointer on stack\n"); return -EACCES; } - err = check_stack_write(state, off, size, value_regno); + err = check_stack_write(env, state, off, size, + value_regno); } else { - err = check_stack_read(state, off, size, value_regno); + err = check_stack_read(env, state, off, size, + value_regno); } } else if (reg_is_pkt_pointer(reg)) { if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { - verbose("cannot write into packet\n"); + verbose(env, "cannot write into packet\n"); return -EACCES; } if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { - verbose("R%d leaks addr into packet\n", value_regno); + verbose(env, "R%d leaks addr into packet\n", + value_regno); return -EACCES; } err = check_packet_access(env, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) - mark_reg_unknown(state->regs, value_regno); + mark_reg_unknown(env, state->regs, value_regno); } else { - verbose("R%d invalid mem access '%s'\n", - regno, reg_type_str[reg->type]); + verbose(env, "R%d invalid mem access '%s'\n", regno, + reg_type_str[reg->type]); return -EACCES; } @@ -1260,7 +1105,7 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) || insn->imm != 0) { - verbose("BPF_XADD uses reserved fields\n"); + verbose(env, "BPF_XADD uses reserved fields\n"); return -EINVAL; } @@ -1275,7 +1120,7 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins return err; if (is_pointer_value(env, insn->src_reg)) { - verbose("R%d leaks addr into mem\n", insn->src_reg); + verbose(env, "R%d leaks addr into mem\n", insn->src_reg); return -EACCES; } @@ -1316,7 +1161,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, register_is_null(regs[regno])) return 0; - verbose("R%d type=%s expected=%s\n", regno, + verbose(env, "R%d type=%s expected=%s\n", regno, reg_type_str[regs[regno].type], reg_type_str[PTR_TO_STACK]); return -EACCES; @@ -1327,13 +1172,13 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), regs[regno].var_off); - verbose("invalid variable stack read R%d var_off=%s\n", + verbose(env, "invalid variable stack read R%d var_off=%s\n", regno, tn_buf); } off = regs[regno].off + regs[regno].var_off.value; if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 || access_size <= 0) { - verbose("invalid stack type R%d off=%d access_size=%d\n", + verbose(env, "invalid stack type R%d off=%d access_size=%d\n", regno, off, access_size); return -EACCES; } @@ -1349,7 +1194,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, for (i = 0; i < access_size; i++) { if (state->stack_slot_type[MAX_BPF_STACK + off + i] != STACK_MISC) { - verbose("invalid indirect read from stack off %d+%d size %d\n", + verbose(env, "invalid indirect read from stack off %d+%d size %d\n", off, i, access_size); return -EACCES; } @@ -1392,7 +1237,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_ANYTHING) { if (is_pointer_value(env, regno)) { - verbose("R%d leaks addr into helper function\n", regno); + verbose(env, "R%d leaks addr into helper function\n", + regno); return -EACCES; } return 0; @@ -1400,7 +1246,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (type_is_pkt_pointer(type) && !may_access_direct_pkt_data(env, meta, BPF_READ)) { - verbose("helper access to the packet is not allowed\n"); + verbose(env, "helper access to the packet is not allowed\n"); return -EACCES; } @@ -1438,7 +1284,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, goto err_type; meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM; } else { - verbose("unsupported arg_type %d\n", arg_type); + verbose(env, "unsupported arg_type %d\n", arg_type); return -EFAULT; } @@ -1456,7 +1302,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, * we have to check map_key here. Otherwise it means * that kernel subsystem misconfigured verifier */ - verbose("invalid map_ptr to access map->key\n"); + verbose(env, "invalid map_ptr to access map->key\n"); return -EACCES; } if (type_is_pkt_pointer(type)) @@ -1472,7 +1318,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, */ if (!meta->map_ptr) { /* kernel subsystem misconfigured verifier */ - verbose("invalid map_ptr to access map->value\n"); + verbose(env, "invalid map_ptr to access map->value\n"); return -EACCES; } if (type_is_pkt_pointer(type)) @@ -1492,7 +1338,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, */ if (regno == 0) { /* kernel subsystem misconfigured verifier */ - verbose("ARG_CONST_SIZE cannot be first argument\n"); + verbose(env, + "ARG_CONST_SIZE cannot be first argument\n"); return -EACCES; } @@ -1509,7 +1356,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, meta = NULL; if (reg->smin_value < 0) { - verbose("R%d min value is negative, either use unsigned or 'var &= const'\n", + verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n", regno); return -EACCES; } @@ -1523,7 +1370,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, } if (reg->umax_value >= BPF_MAX_VAR_SIZ) { - verbose("R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", + verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", regno); return -EACCES; } @@ -1534,12 +1381,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return err; err_type: - verbose("R%d type=%s expected=%s\n", regno, + verbose(env, "R%d type=%s expected=%s\n", regno, reg_type_str[type], reg_type_str[expected_type]); return -EACCES; } -static int check_map_func_compatibility(struct bpf_map *map, int func_id) +static int check_map_func_compatibility(struct bpf_verifier_env *env, + struct bpf_map *map, int func_id) { if (!map) return 0; @@ -1552,7 +1400,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) break; case BPF_MAP_TYPE_PERF_EVENT_ARRAY: if (func_id != BPF_FUNC_perf_event_read && - func_id != BPF_FUNC_perf_event_output) + func_id != BPF_FUNC_perf_event_output && + func_id != BPF_FUNC_perf_event_read_value) goto error; break; case BPF_MAP_TYPE_STACK_TRACE: @@ -1572,6 +1421,11 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) if (func_id != BPF_FUNC_redirect_map) goto error; break; + /* Restrict bpf side of cpumap, open when use-cases appear */ + case BPF_MAP_TYPE_CPUMAP: + if (func_id != BPF_FUNC_redirect_map) + goto error; + break; case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: if (func_id != BPF_FUNC_map_lookup_elem) @@ -1595,6 +1449,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) break; case BPF_FUNC_perf_event_read: case BPF_FUNC_perf_event_output: + case BPF_FUNC_perf_event_read_value: if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) goto error; break; @@ -1608,7 +1463,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) goto error; break; case BPF_FUNC_redirect_map: - if (map->map_type != BPF_MAP_TYPE_DEVMAP) + if (map->map_type != BPF_MAP_TYPE_DEVMAP && + map->map_type != BPF_MAP_TYPE_CPUMAP) goto error; break; case BPF_FUNC_sk_redirect_map: @@ -1625,7 +1481,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) return 0; error: - verbose("cannot pass map_type %d into func %s#%d\n", + verbose(env, "cannot pass map_type %d into func %s#%d\n", map->map_type, func_id_name(func_id), func_id); return -EINVAL; } @@ -1659,7 +1515,7 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) for (i = 0; i < MAX_BPF_REG; i++) if (reg_is_pkt_pointer_any(®s[i])) - mark_reg_unknown(regs, i); + mark_reg_unknown(env, regs, i); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) @@ -1681,21 +1537,23 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) /* find function prototype */ if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) { - verbose("invalid func %s#%d\n", func_id_name(func_id), func_id); + verbose(env, "invalid func %s#%d\n", func_id_name(func_id), + func_id); return -EINVAL; } - if (env->prog->aux->ops->get_func_proto) - fn = env->prog->aux->ops->get_func_proto(func_id); + if (env->ops->get_func_proto) + fn = env->ops->get_func_proto(func_id); if (!fn) { - verbose("unknown func %s#%d\n", func_id_name(func_id), func_id); + verbose(env, "unknown func %s#%d\n", func_id_name(func_id), + func_id); return -EINVAL; } /* eBPF programs must be GPL compatible to use GPL-ed functions */ if (!env->prog->gpl_compatible && fn->gpl_only) { - verbose("cannot call GPL only function from proprietary program\n"); + verbose(env, "cannot call GPL only function from proprietary program\n"); return -EINVAL; } @@ -1709,7 +1567,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) */ err = check_raw_mode(fn); if (err) { - verbose("kernel subsystem misconfigured func %s#%d\n", + verbose(env, "kernel subsystem misconfigured func %s#%d\n", func_id_name(func_id), func_id); return err; } @@ -1742,14 +1600,14 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) /* reset caller saved regs */ for (i = 0; i < CALLER_SAVED_REGS; i++) { - mark_reg_not_init(regs, caller_saved[i]); + mark_reg_not_init(env, regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } /* update return register (already marked as written above) */ if (fn->ret_type == RET_INTEGER) { /* sets type to SCALAR_VALUE */ - mark_reg_unknown(regs, BPF_REG_0); + mark_reg_unknown(env, regs, BPF_REG_0); } else if (fn->ret_type == RET_VOID) { regs[BPF_REG_0].type = NOT_INIT; } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) { @@ -1757,14 +1615,15 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; /* There is no offset yet applied, variable or fixed */ - mark_reg_known_zero(regs, BPF_REG_0); + mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].off = 0; /* remember map_ptr, so that check_map_access() * can check 'value_size' boundary of memory access * to map element returned from bpf_map_lookup_elem() */ if (meta.map_ptr == NULL) { - verbose("kernel subsystem misconfigured verifier\n"); + verbose(env, + "kernel subsystem misconfigured verifier\n"); return -EINVAL; } regs[BPF_REG_0].map_ptr = meta.map_ptr; @@ -1775,12 +1634,12 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) else if (insn_aux->map_ptr != meta.map_ptr) insn_aux->map_ptr = BPF_MAP_PTR_POISON; } else { - verbose("unknown return type %d of func %s#%d\n", + verbose(env, "unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); return -EINVAL; } - err = check_map_func_compatibility(meta.map_ptr, func_id); + err = check_map_func_compatibility(env, meta.map_ptr, func_id); if (err) return err; @@ -1839,39 +1698,42 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg = ®s[dst]; if (WARN_ON_ONCE(known && (smin_val != smax_val))) { - print_verifier_state(&env->cur_state); - verbose("verifier internal error: known but bad sbounds\n"); + print_verifier_state(env, &env->cur_state); + verbose(env, + "verifier internal error: known but bad sbounds\n"); return -EINVAL; } if (WARN_ON_ONCE(known && (umin_val != umax_val))) { - print_verifier_state(&env->cur_state); - verbose("verifier internal error: known but bad ubounds\n"); + print_verifier_state(env, &env->cur_state); + verbose(env, + "verifier internal error: known but bad ubounds\n"); return -EINVAL; } if (BPF_CLASS(insn->code) != BPF_ALU64) { /* 32-bit ALU ops on pointers produce (meaningless) scalars */ if (!env->allow_ptr_leaks) - verbose("R%d 32-bit pointer arithmetic prohibited\n", + verbose(env, + "R%d 32-bit pointer arithmetic prohibited\n", dst); return -EACCES; } if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) { if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", + verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", dst); return -EACCES; } if (ptr_reg->type == CONST_PTR_TO_MAP) { if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", + verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", dst); return -EACCES; } if (ptr_reg->type == PTR_TO_PACKET_END) { if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", + verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", dst); return -EACCES; } @@ -1936,7 +1798,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (dst_reg == off_reg) { /* scalar -= pointer. Creates an unknown scalar */ if (!env->allow_ptr_leaks) - verbose("R%d tried to subtract pointer from scalar\n", + verbose(env, "R%d tried to subtract pointer from scalar\n", dst); return -EACCES; } @@ -1946,7 +1808,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, */ if (ptr_reg->type == PTR_TO_STACK) { if (!env->allow_ptr_leaks) - verbose("R%d subtraction from stack pointer prohibited\n", + verbose(env, "R%d subtraction from stack pointer prohibited\n", dst); return -EACCES; } @@ -2001,13 +1863,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, * ptr &= ~3 which would reduce min_value by 3.) */ if (!env->allow_ptr_leaks) - verbose("R%d bitwise operator %s on pointer prohibited\n", + verbose(env, "R%d bitwise operator %s on pointer prohibited\n", dst, bpf_alu_string[opcode >> 4]); return -EACCES; default: /* other operators (e.g. MUL,LSH) produce non-pointer results */ if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic with %s operator prohibited\n", + verbose(env, "R%d pointer arithmetic with %s operator prohibited\n", dst, bpf_alu_string[opcode >> 4]); return -EACCES; } @@ -2173,7 +2035,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Shifts greater than 63 are undefined. This includes * shifts by a negative number. */ - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); break; } /* We lose all sign bit information (except what we can pick @@ -2201,7 +2063,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Shifts greater than 63 are undefined. This includes * shifts by a negative number. */ - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); break; } /* BPF_RSH is an unsigned shift, so make the appropriate casts */ @@ -2229,7 +2091,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, __update_reg_bounds(dst_reg); break; default: - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); break; } @@ -2261,12 +2123,12 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, * an arbitrary scalar. */ if (!env->allow_ptr_leaks) { - verbose("R%d pointer %s pointer prohibited\n", + verbose(env, "R%d pointer %s pointer prohibited\n", insn->dst_reg, bpf_alu_string[opcode >> 4]); return -EACCES; } - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); return 0; } else { /* scalar += pointer @@ -2318,13 +2180,13 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, /* Got here implies adding two SCALAR_VALUEs */ if (WARN_ON_ONCE(ptr_reg)) { - print_verifier_state(&env->cur_state); - verbose("verifier internal error: unexpected ptr_reg\n"); + print_verifier_state(env, &env->cur_state); + verbose(env, "verifier internal error: unexpected ptr_reg\n"); return -EINVAL; } if (WARN_ON(!src_reg)) { - print_verifier_state(&env->cur_state); - verbose("verifier internal error: no src_reg\n"); + print_verifier_state(env, &env->cur_state); + verbose(env, "verifier internal error: no src_reg\n"); return -EINVAL; } return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg); @@ -2342,14 +2204,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) if (BPF_SRC(insn->code) != 0 || insn->src_reg != BPF_REG_0 || insn->off != 0 || insn->imm != 0) { - verbose("BPF_NEG uses reserved fields\n"); + verbose(env, "BPF_NEG uses reserved fields\n"); return -EINVAL; } } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0 || (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) || BPF_CLASS(insn->code) == BPF_ALU64) { - verbose("BPF_END uses reserved fields\n"); + verbose(env, "BPF_END uses reserved fields\n"); return -EINVAL; } } @@ -2360,7 +2222,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; if (is_pointer_value(env, insn->dst_reg)) { - verbose("R%d pointer arithmetic prohibited\n", + verbose(env, "R%d pointer arithmetic prohibited\n", insn->dst_reg); return -EACCES; } @@ -2374,7 +2236,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0 || insn->off != 0) { - verbose("BPF_MOV uses reserved fields\n"); + verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } @@ -2384,7 +2246,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0) { - verbose("BPF_MOV uses reserved fields\n"); + verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } } @@ -2400,14 +2262,16 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) * copy register state to dest reg */ regs[insn->dst_reg] = regs[insn->src_reg]; + regs[insn->dst_reg].live |= REG_LIVE_WRITTEN; } else { /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { - verbose("R%d partial copy of pointer\n", + verbose(env, + "R%d partial copy of pointer\n", insn->src_reg); return -EACCES; } - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); /* high 32 bits are known zero. */ regs[insn->dst_reg].var_off = tnum_cast( regs[insn->dst_reg].var_off, 4); @@ -2422,14 +2286,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } } else if (opcode > BPF_END) { - verbose("invalid BPF_ALU opcode %x\n", opcode); + verbose(env, "invalid BPF_ALU opcode %x\n", opcode); return -EINVAL; } else { /* all other ALU ops: and, sub, xor, add, ... */ if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0 || insn->off != 0) { - verbose("BPF_ALU uses reserved fields\n"); + verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } /* check src1 operand */ @@ -2438,7 +2302,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0) { - verbose("BPF_ALU uses reserved fields\n"); + verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } } @@ -2450,7 +2314,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) if ((opcode == BPF_MOD || opcode == BPF_DIV) && BPF_SRC(insn->code) == BPF_K && insn->imm == 0) { - verbose("div by zero\n"); + verbose(env, "div by zero\n"); return -EINVAL; } @@ -2459,7 +2323,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; if (insn->imm < 0 || insn->imm >= size) { - verbose("invalid shift %d\n", insn->imm); + verbose(env, "invalid shift %d\n", insn->imm); return -EINVAL; } } @@ -2812,13 +2676,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, int err; if (opcode > BPF_JSLE) { - verbose("invalid BPF_JMP opcode %x\n", opcode); + verbose(env, "invalid BPF_JMP opcode %x\n", opcode); return -EINVAL; } if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0) { - verbose("BPF_JMP uses reserved fields\n"); + verbose(env, "BPF_JMP uses reserved fields\n"); return -EINVAL; } @@ -2828,13 +2692,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return err; if (is_pointer_value(env, insn->src_reg)) { - verbose("R%d pointer comparison prohibited\n", + verbose(env, "R%d pointer comparison prohibited\n", insn->src_reg); return -EACCES; } } else { if (insn->src_reg != BPF_REG_0) { - verbose("BPF_JMP uses reserved fields\n"); + verbose(env, "BPF_JMP uses reserved fields\n"); return -EINVAL; } } @@ -2946,11 +2810,12 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, find_good_pkt_pointers(this_branch, ®s[insn->src_reg], PTR_TO_PACKET_META); } else if (is_pointer_value(env, insn->dst_reg)) { - verbose("R%d pointer comparison prohibited\n", insn->dst_reg); + verbose(env, "R%d pointer comparison prohibited\n", + insn->dst_reg); return -EACCES; } - if (log_level) - print_verifier_state(this_branch); + if (env->log.level) + print_verifier_state(env, this_branch); return 0; } @@ -2969,11 +2834,11 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) int err; if (BPF_SIZE(insn->code) != BPF_DW) { - verbose("invalid BPF_LD_IMM insn\n"); + verbose(env, "invalid BPF_LD_IMM insn\n"); return -EINVAL; } if (insn->off != 0) { - verbose("BPF_LD_IMM64 uses reserved fields\n"); + verbose(env, "BPF_LD_IMM64 uses reserved fields\n"); return -EINVAL; } @@ -3031,14 +2896,14 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) int i, err; if (!may_access_skb(env->prog->type)) { - verbose("BPF_LD_[ABS|IND] instructions not allowed for this program type\n"); + verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n"); return -EINVAL; } if (insn->dst_reg != BPF_REG_0 || insn->off != 0 || BPF_SIZE(insn->code) == BPF_DW || (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) { - verbose("BPF_LD_[ABS|IND] uses reserved fields\n"); + verbose(env, "BPF_LD_[ABS|IND] uses reserved fields\n"); return -EINVAL; } @@ -3048,7 +2913,8 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; if (regs[BPF_REG_6].type != PTR_TO_CTX) { - verbose("at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); + verbose(env, + "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); return -EINVAL; } @@ -3061,7 +2927,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) /* reset caller saved regs to unreadable */ for (i = 0; i < CALLER_SAVED_REGS; i++) { - mark_reg_not_init(regs, caller_saved[i]); + mark_reg_not_init(env, regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } @@ -3069,7 +2935,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) * the value fetched from the packet. * Already marked as written above. */ - mark_reg_unknown(regs, BPF_REG_0); + mark_reg_unknown(env, regs, BPF_REG_0); return 0; } @@ -3089,22 +2955,22 @@ static int check_return_code(struct bpf_verifier_env *env) reg = &env->cur_state.regs[BPF_REG_0]; if (reg->type != SCALAR_VALUE) { - verbose("At program exit the register R0 is not a known value (%s)\n", + verbose(env, "At program exit the register R0 is not a known value (%s)\n", reg_type_str[reg->type]); return -EINVAL; } if (!tnum_in(range, reg->var_off)) { - verbose("At program exit the register R0 "); + verbose(env, "At program exit the register R0 "); if (!tnum_is_unknown(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose("has value %s", tn_buf); + verbose(env, "has value %s", tn_buf); } else { - verbose("has unknown scalar value"); + verbose(env, "has unknown scalar value"); } - verbose(" should have been 0 or 1\n"); + verbose(env, " should have been 0 or 1\n"); return -EINVAL; } return 0; @@ -3170,7 +3036,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) return 0; if (w < 0 || w >= env->prog->len) { - verbose("jump out of range from insn %d to %d\n", t, w); + verbose(env, "jump out of range from insn %d to %d\n", t, w); return -EINVAL; } @@ -3187,13 +3053,13 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) insn_stack[cur_stack++] = w; return 1; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { - verbose("back-edge from insn %d to %d\n", t, w); + verbose(env, "back-edge from insn %d to %d\n", t, w); return -EINVAL; } else if (insn_state[w] == EXPLORED) { /* forward- or cross-edge */ insn_state[t] = DISCOVERED | e; } else { - verbose("insn state internal bug\n"); + verbose(env, "insn state internal bug\n"); return -EFAULT; } return 0; @@ -3287,7 +3153,7 @@ peek_stack: mark_explored: insn_state[t] = EXPLORED; if (cur_stack-- <= 0) { - verbose("pop stack internal bug\n"); + verbose(env, "pop stack internal bug\n"); ret = -EFAULT; goto err_free; } @@ -3296,7 +3162,7 @@ mark_explored: check_state: for (i = 0; i < insn_cnt; i++) { if (insn_state[i] != EXPLORED) { - verbose("unreachable insn %d\n", i); + verbose(env, "unreachable insn %d\n", i); ret = -EINVAL; goto err_free; } @@ -3677,7 +3543,7 @@ static int do_check(struct bpf_verifier_env *env) int insn_processed = 0; bool do_print_state = false; - init_reg_state(regs); + init_reg_state(env, regs); state->parent = NULL; insn_idx = 0; for (;;) { @@ -3686,7 +3552,7 @@ static int do_check(struct bpf_verifier_env *env) int err; if (insn_idx >= insn_cnt) { - verbose("invalid insn idx %d insn_cnt %d\n", + verbose(env, "invalid insn idx %d insn_cnt %d\n", insn_idx, insn_cnt); return -EFAULT; } @@ -3695,7 +3561,8 @@ static int do_check(struct bpf_verifier_env *env) class = BPF_CLASS(insn->code); if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { - verbose("BPF program is too large. Processed %d insn\n", + verbose(env, + "BPF program is too large. Processed %d insn\n", insn_processed); return -E2BIG; } @@ -3705,12 +3572,12 @@ static int do_check(struct bpf_verifier_env *env) return err; if (err == 1) { /* found equivalent state, can prune the search */ - if (log_level) { + if (env->log.level) { if (do_print_state) - verbose("\nfrom %d to %d: safe\n", + verbose(env, "\nfrom %d to %d: safe\n", prev_insn_idx, insn_idx); else - verbose("%d: safe\n", insn_idx); + verbose(env, "%d: safe\n", insn_idx); } goto process_bpf_exit; } @@ -3718,19 +3585,20 @@ static int do_check(struct bpf_verifier_env *env) if (need_resched()) cond_resched(); - if (log_level > 1 || (log_level && do_print_state)) { - if (log_level > 1) - verbose("%d:", insn_idx); + if (env->log.level > 1 || (env->log.level && do_print_state)) { + if (env->log.level > 1) + verbose(env, "%d:", insn_idx); else - verbose("\nfrom %d to %d:", + verbose(env, "\nfrom %d to %d:", prev_insn_idx, insn_idx); - print_verifier_state(&env->cur_state); + print_verifier_state(env, &env->cur_state); do_print_state = false; } - if (log_level) { - verbose("%d: ", insn_idx); - print_bpf_insn(env, insn); + if (env->log.level) { + verbose(env, "%d: ", insn_idx); + print_bpf_insn(verbose, env, insn, + env->allow_ptr_leaks); } err = ext_analyzer_insn_hook(env, insn_idx, prev_insn_idx); @@ -3786,7 +3654,7 @@ static int do_check(struct bpf_verifier_env *env) * src_reg == stack|map in some other branch. * Reject it. */ - verbose("same insn cannot be used with different pointers\n"); + verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } @@ -3826,14 +3694,14 @@ static int do_check(struct bpf_verifier_env *env) } else if (dst_reg_type != *prev_dst_type && (dst_reg_type == PTR_TO_CTX || *prev_dst_type == PTR_TO_CTX)) { - verbose("same insn cannot be used with different pointers\n"); + verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } } else if (class == BPF_ST) { if (BPF_MODE(insn->code) != BPF_MEM || insn->src_reg != BPF_REG_0) { - verbose("BPF_ST uses reserved fields\n"); + verbose(env, "BPF_ST uses reserved fields\n"); return -EINVAL; } /* check src operand */ @@ -3856,7 +3724,7 @@ static int do_check(struct bpf_verifier_env *env) insn->off != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0) { - verbose("BPF_CALL uses reserved fields\n"); + verbose(env, "BPF_CALL uses reserved fields\n"); return -EINVAL; } @@ -3869,7 +3737,7 @@ static int do_check(struct bpf_verifier_env *env) insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0) { - verbose("BPF_JA uses reserved fields\n"); + verbose(env, "BPF_JA uses reserved fields\n"); return -EINVAL; } @@ -3881,7 +3749,7 @@ static int do_check(struct bpf_verifier_env *env) insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0) { - verbose("BPF_EXIT uses reserved fields\n"); + verbose(env, "BPF_EXIT uses reserved fields\n"); return -EINVAL; } @@ -3896,7 +3764,7 @@ static int do_check(struct bpf_verifier_env *env) return err; if (is_pointer_value(env, BPF_REG_0)) { - verbose("R0 leaks addr as return value\n"); + verbose(env, "R0 leaks addr as return value\n"); return -EACCES; } @@ -3931,19 +3799,19 @@ process_bpf_exit: insn_idx++; } else { - verbose("invalid BPF_LD mode\n"); + verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; } } else { - verbose("unknown insn class %d\n", class); + verbose(env, "unknown insn class %d\n", class); return -EINVAL; } insn_idx++; } - verbose("processed %d insns, stack depth %d\n", - insn_processed, env->prog->aux->stack_depth); + verbose(env, "processed %d insns, stack depth %d\n", insn_processed, + env->prog->aux->stack_depth); return 0; } @@ -3955,7 +3823,8 @@ static int check_map_prealloc(struct bpf_map *map) !(map->map_flags & BPF_F_NO_PREALLOC); } -static int check_map_prog_compatibility(struct bpf_map *map, +static int check_map_prog_compatibility(struct bpf_verifier_env *env, + struct bpf_map *map, struct bpf_prog *prog) { @@ -3966,12 +3835,12 @@ static int check_map_prog_compatibility(struct bpf_map *map, */ if (prog->type == BPF_PROG_TYPE_PERF_EVENT) { if (!check_map_prealloc(map)) { - verbose("perf_event programs can only use preallocated hash map\n"); + verbose(env, "perf_event programs can only use preallocated hash map\n"); return -EINVAL; } if (map->inner_map_meta && !check_map_prealloc(map->inner_map_meta)) { - verbose("perf_event programs can only use preallocated inner hash map\n"); + verbose(env, "perf_event programs can only use preallocated inner hash map\n"); return -EINVAL; } } @@ -3994,14 +3863,14 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) for (i = 0; i < insn_cnt; i++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) { - verbose("BPF_LDX uses reserved fields\n"); + verbose(env, "BPF_LDX uses reserved fields\n"); return -EINVAL; } if (BPF_CLASS(insn->code) == BPF_STX && ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_XADD) || insn->imm != 0)) { - verbose("BPF_STX uses reserved fields\n"); + verbose(env, "BPF_STX uses reserved fields\n"); return -EINVAL; } @@ -4012,7 +3881,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) if (i == insn_cnt - 1 || insn[1].code != 0 || insn[1].dst_reg != 0 || insn[1].src_reg != 0 || insn[1].off != 0) { - verbose("invalid bpf_ld_imm64 insn\n"); + verbose(env, "invalid bpf_ld_imm64 insn\n"); return -EINVAL; } @@ -4021,19 +3890,20 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) goto next_insn; if (insn->src_reg != BPF_PSEUDO_MAP_FD) { - verbose("unrecognized bpf_ld_imm64 insn\n"); + verbose(env, + "unrecognized bpf_ld_imm64 insn\n"); return -EINVAL; } f = fdget(insn->imm); map = __bpf_map_get(f); if (IS_ERR(map)) { - verbose("fd %d is not pointing to valid bpf_map\n", + verbose(env, "fd %d is not pointing to valid bpf_map\n", insn->imm); return PTR_ERR(map); } - err = check_map_prog_compatibility(map, env->prog); + err = check_map_prog_compatibility(env, map, env->prog); if (err) { fdput(f); return err; @@ -4142,7 +4012,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { - const struct bpf_verifier_ops *ops = env->prog->aux->ops; + const struct bpf_verifier_ops *ops = env->ops; int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; struct bpf_insn insn_buf[16], *insn; @@ -4155,7 +4025,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, env->prog); if (cnt >= ARRAY_SIZE(insn_buf)) { - verbose("bpf verifier is misconfigured\n"); + verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } else if (cnt) { new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt); @@ -4203,7 +4073,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) u8 size_code; if (type == BPF_WRITE) { - verbose("bpf verifier narrow ctx access misconfigured\n"); + verbose(env, "bpf verifier narrow ctx access misconfigured\n"); return -EINVAL; } @@ -4222,7 +4092,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) &target_size); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) || (ctx_field_size && !target_size)) { - verbose("bpf verifier is misconfigured\n"); + verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } @@ -4304,7 +4174,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { - verbose("bpf verifier is misconfigured\n"); + verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } @@ -4343,12 +4213,13 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn = new_prog->insnsi + i + delta; } patch_call_imm: - fn = prog->aux->ops->get_func_proto(insn->imm); + fn = env->ops->get_func_proto(insn->imm); /* all functions that have prototype and verifier allowed * programs to call them, must be real in-kernel functions */ if (!fn->func) { - verbose("kernel subsystem misconfigured func %s#%d\n", + verbose(env, + "kernel subsystem misconfigured func %s#%d\n", func_id_name(insn->imm), insn->imm); return -EFAULT; } @@ -4382,8 +4253,8 @@ static void free_states(struct bpf_verifier_env *env) int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) { - char __user *log_ubuf = NULL; struct bpf_verifier_env *env; + struct bpf_verifer_log *log; int ret = -EINVAL; /* 'struct bpf_verifier_env' can be global, but since it's not small, @@ -4392,6 +4263,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); if (!env) return -ENOMEM; + log = &env->log; env->insn_aux_data = vzalloc(sizeof(struct bpf_insn_aux_data) * (*prog)->len); @@ -4399,6 +4271,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (!env->insn_aux_data) goto err_free_env; env->prog = *prog; + env->ops = bpf_verifier_ops[env->prog->type]; /* grab the mutex to protect few globals used by verifier */ mutex_lock(&bpf_verifier_lock); @@ -4407,23 +4280,15 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) /* user requested verbose verifier output * and supplied buffer to store the verification trace */ - log_level = attr->log_level; - log_ubuf = (char __user *) (unsigned long) attr->log_buf; - log_size = attr->log_size; - log_len = 0; + log->level = attr->log_level; + log->ubuf = (char __user *) (unsigned long) attr->log_buf; + log->len_total = attr->log_size; ret = -EINVAL; - /* log_* values have to be sane */ - if (log_size < 128 || log_size > UINT_MAX >> 8 || - log_level == 0 || log_ubuf == NULL) + /* log attributes have to be sane */ + if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 || + !log->level || !log->ubuf) goto err_unlock; - - ret = -ENOMEM; - log_buf = vmalloc(log_size); - if (!log_buf) - goto err_unlock; - } else { - log_level = 0; } env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); @@ -4460,17 +4325,11 @@ skip_full_check: if (ret == 0) ret = fixup_bpf_calls(env); - if (log_level && log_len >= log_size - 1) { - BUG_ON(log_len >= log_size); - /* verifier log exceeded user supplied buffer */ + if (log->level && bpf_verifier_log_full(log)) ret = -ENOSPC; - /* fall through to return what was recorded */ - } - - /* copy verifier log back to user space including trailing zero */ - if (log_level && copy_to_user(log_ubuf, log_buf, log_len + 1) != 0) { + if (log->level && !log->ubuf) { ret = -EFAULT; - goto free_log_buf; + goto err_release_maps; } if (ret == 0 && env->used_map_cnt) { @@ -4481,7 +4340,7 @@ skip_full_check: if (!env->prog->aux->used_maps) { ret = -ENOMEM; - goto free_log_buf; + goto err_release_maps; } memcpy(env->prog->aux->used_maps, env->used_maps, @@ -4494,9 +4353,7 @@ skip_full_check: convert_pseudo_ld_imm64(env); } -free_log_buf: - if (log_level) - vfree(log_buf); +err_release_maps: if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release * them now. Otherwise free_bpf_prog_info() will release them. @@ -4511,12 +4368,21 @@ err_free_env: return ret; } +static const struct bpf_verifier_ops * const bpf_analyzer_ops[] = { + [BPF_PROG_TYPE_XDP] = &xdp_analyzer_ops, + [BPF_PROG_TYPE_SCHED_CLS] = &tc_cls_act_analyzer_ops, +}; + int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, void *priv) { struct bpf_verifier_env *env; int ret; + if (prog->type >= ARRAY_SIZE(bpf_analyzer_ops) || + !bpf_analyzer_ops[prog->type]) + return -EOPNOTSUPP; + env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); if (!env) return -ENOMEM; @@ -4527,14 +4393,13 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, if (!env->insn_aux_data) goto err_free_env; env->prog = prog; + env->ops = bpf_analyzer_ops[env->prog->type]; env->analyzer_ops = ops; env->analyzer_priv = priv; /* grab the mutex to protect few globals used by verifier */ mutex_lock(&bpf_verifier_lock); - log_level = 0; - env->strict_alignment = false; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; diff --git a/kernel/cpu.c b/kernel/cpu.c index 8de11a29e495..d851df22f5c5 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -24,6 +24,7 @@ #include <linux/lockdep.h> #include <linux/tick.h> #include <linux/irq.h> +#include <linux/nmi.h> #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> @@ -897,6 +898,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, out: cpus_write_unlock(); + /* + * Do post unplug cleanup. This is still protected against + * concurrent CPU hotplug via cpu_add_remove_lock. + */ + lockup_detector_cleanup(); return ret; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 6bc21e202ae4..902149f05381 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3684,10 +3684,12 @@ static inline u64 perf_event_count(struct perf_event *event) * will not be local and we cannot read them atomically * - must not have a pmu::count method */ -int perf_event_read_local(struct perf_event *event, u64 *value) +int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running) { unsigned long flags; int ret = 0; + u64 now; /* * Disabling interrupts avoids all counter scheduling (context @@ -3718,13 +3720,21 @@ int perf_event_read_local(struct perf_event *event, u64 *value) goto out; } + now = event->shadow_ctx_time + perf_clock(); + if (enabled) + *enabled = now - event->tstamp_enabled; /* * If the event is currently on this CPU, its either a per-task event, * or local to this CPU. Furthermore it means its ACTIVE (otherwise * oncpu == -1). */ - if (event->oncpu == smp_processor_id()) + if (event->oncpu == smp_processor_id()) { event->pmu->read(event); + if (running) + *running = now - event->tstamp_running; + } else if (running) { + *running = event->total_time_running; + } *value = local64_read(&event->count); out: @@ -8072,6 +8082,7 @@ static void bpf_overflow_handler(struct perf_event *event, struct bpf_perf_event_data_kern ctx = { .data = data, .regs = regs, + .event = event, }; int ret = 0; diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 1d71c051a951..5043e7433f4b 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -344,39 +344,30 @@ EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); * by the client, but only by calling this function. * This function can only be called on a registered smp_hotplug_thread. */ -int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *new) +void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, + const struct cpumask *new) { struct cpumask *old = plug_thread->cpumask; - cpumask_var_t tmp; + static struct cpumask tmp; unsigned int cpu; - if (!alloc_cpumask_var(&tmp, GFP_KERNEL)) - return -ENOMEM; - - get_online_cpus(); + lockdep_assert_cpus_held(); mutex_lock(&smpboot_threads_lock); /* Park threads that were exclusively enabled on the old mask. */ - cpumask_andnot(tmp, old, new); - for_each_cpu_and(cpu, tmp, cpu_online_mask) + cpumask_andnot(&tmp, old, new); + for_each_cpu_and(cpu, &tmp, cpu_online_mask) smpboot_park_thread(plug_thread, cpu); /* Unpark threads that are exclusively enabled on the new mask. */ - cpumask_andnot(tmp, new, old); - for_each_cpu_and(cpu, tmp, cpu_online_mask) + cpumask_andnot(&tmp, new, old); + for_each_cpu_and(cpu, &tmp, cpu_online_mask) smpboot_unpark_thread(plug_thread, cpu); cpumask_copy(old, new); mutex_unlock(&smpboot_threads_lock); - put_online_cpus(); - - free_cpumask_var(tmp); - - return 0; } -EXPORT_SYMBOL_GPL(smpboot_update_cpumask_percpu_thread); static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 4da9e622471f..d9c31bc2eaea 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -872,9 +872,9 @@ static struct ctl_table kern_table[] = { #if defined(CONFIG_LOCKUP_DETECTOR) { .procname = "watchdog", - .data = &watchdog_user_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_watchdog, .extra1 = &zero, .extra2 = &one, @@ -890,16 +890,12 @@ static struct ctl_table kern_table[] = { }, { .procname = "nmi_watchdog", - .data = &nmi_watchdog_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &nmi_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = NMI_WATCHDOG_SYSCTL_PERM, .proc_handler = proc_nmi_watchdog, .extra1 = &zero, -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) .extra2 = &one, -#else - .extra2 = &zero, -#endif }, { .procname = "watchdog_cpumask", @@ -911,9 +907,9 @@ static struct ctl_table kern_table[] = { #ifdef CONFIG_SOFTLOCKUP_DETECTOR { .procname = "soft_watchdog", - .data = &soft_watchdog_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &soft_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_soft_watchdog, .extra1 = &zero, .extra2 = &one, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index dc498b605d5d..3126da2f468a 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -255,14 +255,14 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } -BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) +static __always_inline int +get_map_perf_counter(struct bpf_map *map, u64 flags, + u64 *value, u64 *enabled, u64 *running) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; - u64 value = 0; - int err; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; @@ -275,7 +275,15 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) if (!ee) return -ENOENT; - err = perf_event_read_local(ee->event, &value); + return perf_event_read_local(ee->event, value, enabled, running); +} + +BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) +{ + u64 value = 0; + int err; + + err = get_map_perf_counter(map, flags, &value, NULL, NULL); /* * this api is ugly since we miss [-22..-2] range of valid * counter values, but that's uapi @@ -293,6 +301,33 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_perf_event_read_value, struct bpf_map *, map, u64, flags, + struct bpf_perf_event_value *, buf, u32, size) +{ + int err = -EINVAL; + + if (unlikely(size != sizeof(struct bpf_perf_event_value))) + goto clear; + err = get_map_perf_counter(map, flags, &buf->counter, &buf->enabled, + &buf->running); + if (unlikely(err)) + goto clear; + return 0; +clear: + memset(buf, 0, size); + return err; +} + +static const struct bpf_func_proto bpf_perf_event_read_value_proto = { + .func = bpf_perf_event_read_value, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd); static __always_inline u64 @@ -499,6 +534,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return &bpf_perf_event_output_proto; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto; + case BPF_FUNC_perf_event_read_value: + return &bpf_perf_event_read_value_proto; default: return tracing_func_proto(func_id); } @@ -524,11 +561,14 @@ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type return true; } -const struct bpf_verifier_ops kprobe_prog_ops = { +const struct bpf_verifier_ops kprobe_verifier_ops = { .get_func_proto = kprobe_prog_func_proto, .is_valid_access = kprobe_prog_is_valid_access, }; +const struct bpf_prog_ops kprobe_prog_ops = { +}; + BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map, u64, flags, void *, data, u64, size) { @@ -576,6 +616,32 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx, + struct bpf_perf_event_value *, buf, u32, size) +{ + int err = -EINVAL; + + if (unlikely(size != sizeof(struct bpf_perf_event_value))) + goto clear; + err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled, + &buf->running); + if (unlikely(err)) + goto clear; + return 0; +clear: + memset(buf, 0, size); + return err; +} + +static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = { + .func = bpf_perf_prog_read_value_tp, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -583,6 +649,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; + case BPF_FUNC_perf_prog_read_value: + return &bpf_perf_prog_read_value_proto_tp; default: return tracing_func_proto(func_id); } @@ -602,11 +670,14 @@ static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type return true; } -const struct bpf_verifier_ops tracepoint_prog_ops = { +const struct bpf_verifier_ops tracepoint_verifier_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = tp_prog_is_valid_access, }; +const struct bpf_prog_ops tracepoint_prog_ops = { +}; + static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { @@ -662,8 +733,11 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } -const struct bpf_verifier_ops perf_event_prog_ops = { +const struct bpf_verifier_ops perf_event_verifier_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = pe_prog_is_valid_access, .convert_ctx_access = pe_prog_convert_ctx_access, }; + +const struct bpf_prog_ops perf_event_prog_ops = { +}; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index f5d52024f6b7..6bcb854909c0 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -29,20 +29,29 @@ #include <linux/kvm_para.h> #include <linux/kthread.h> -/* Watchdog configuration */ -static DEFINE_MUTEX(watchdog_proc_mutex); - -int __read_mostly nmi_watchdog_enabled; +static DEFINE_MUTEX(watchdog_mutex); #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | - NMI_WATCHDOG_ENABLED; +# define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED) +# define NMI_WATCHDOG_DEFAULT 1 #else -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; +# define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED) +# define NMI_WATCHDOG_DEFAULT 0 #endif +unsigned long __read_mostly watchdog_enabled; +int __read_mostly watchdog_user_enabled = 1; +int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT; +int __read_mostly soft_watchdog_user_enabled = 1; +int __read_mostly watchdog_thresh = 10; +int __read_mostly nmi_watchdog_available; + +struct cpumask watchdog_allowed_mask __read_mostly; + +struct cpumask watchdog_cpumask __read_mostly; +unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); + #ifdef CONFIG_HARDLOCKUP_DETECTOR -/* boot commands */ /* * Should we panic when a soft-lockup or hard-lockup occurs: */ @@ -56,9 +65,9 @@ unsigned int __read_mostly hardlockup_panic = * kernel command line parameters are parsed, because otherwise it is not * possible to override this in hardlockup_panic_setup(). */ -void hardlockup_detector_disable(void) +void __init hardlockup_detector_disable(void) { - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 0; } static int __init hardlockup_panic_setup(char *str) @@ -68,48 +77,24 @@ static int __init hardlockup_panic_setup(char *str) else if (!strncmp(str, "nopanic", 7)) hardlockup_panic = 0; else if (!strncmp(str, "0", 1)) - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 0; else if (!strncmp(str, "1", 1)) - watchdog_enabled |= NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 1; return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); -#endif - -#ifdef CONFIG_SOFTLOCKUP_DETECTOR -int __read_mostly soft_watchdog_enabled; -#endif - -int __read_mostly watchdog_user_enabled; -int __read_mostly watchdog_thresh = 10; - -#ifdef CONFIG_SMP -int __read_mostly sysctl_softlockup_all_cpu_backtrace; +# ifdef CONFIG_SMP int __read_mostly sysctl_hardlockup_all_cpu_backtrace; -#endif -struct cpumask watchdog_cpumask __read_mostly; -unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); -/* - * The 'watchdog_running' variable is set to 1 when the watchdog threads - * are registered/started and is set to 0 when the watchdog threads are - * unregistered/stopped, so it is an indicator whether the threads exist. - */ -static int __read_mostly watchdog_running; -/* - * If a subsystem has a need to deactivate the watchdog temporarily, it - * can use the suspend/resume interface to achieve this. The content of - * the 'watchdog_suspended' variable reflects this state. Existing threads - * are parked/unparked by the lockup_detector_{suspend|resume} functions - * (see comment blocks pertaining to those functions for further details). - * - * 'watchdog_suspended' also prevents threads from being registered/started - * or unregistered/stopped via parameters in /proc/sys/kernel, so the state - * of 'watchdog_running' cannot change while the watchdog is deactivated - * temporarily (see related code in 'proc' handlers). - */ -int __read_mostly watchdog_suspended; +static int __init hardlockup_all_cpu_backtrace_setup(char *str) +{ + sysctl_hardlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0); + return 1; +} +__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); +# endif /* CONFIG_SMP */ +#endif /* CONFIG_HARDLOCKUP_DETECTOR */ /* * These functions can be overridden if an architecture implements its @@ -121,36 +106,68 @@ int __read_mostly watchdog_suspended; */ int __weak watchdog_nmi_enable(unsigned int cpu) { + hardlockup_detector_perf_enable(); return 0; } + void __weak watchdog_nmi_disable(unsigned int cpu) { + hardlockup_detector_perf_disable(); } -/* - * watchdog_nmi_reconfigure can be implemented to be notified after any - * watchdog configuration change. The arch hardlockup watchdog should - * respond to the following variables: - * - nmi_watchdog_enabled +/* Return 0, if a NMI watchdog is available. Error code otherwise */ +int __weak __init watchdog_nmi_probe(void) +{ + return hardlockup_detector_perf_init(); +} + +/** + * watchdog_nmi_stop - Stop the watchdog for reconfiguration + * + * The reconfiguration steps are: + * watchdog_nmi_stop(); + * update_variables(); + * watchdog_nmi_start(); + */ +void __weak watchdog_nmi_stop(void) { } + +/** + * watchdog_nmi_start - Start the watchdog after reconfiguration + * + * Counterpart to watchdog_nmi_stop(). + * + * The following variables have been updated in update_variables() and + * contain the currently valid configuration: + * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask - * - sysctl_hardlockup_all_cpu_backtrace - * - hardlockup_panic - * - watchdog_suspended */ -void __weak watchdog_nmi_reconfigure(void) +void __weak watchdog_nmi_start(void) { } + +/** + * lockup_detector_update_enable - Update the sysctl enable bit + * + * Caller needs to make sure that the NMI/perf watchdogs are off, so this + * can't race with watchdog_nmi_disable(). + */ +static void lockup_detector_update_enable(void) { + watchdog_enabled = 0; + if (!watchdog_user_enabled) + return; + if (nmi_watchdog_available && nmi_watchdog_user_enabled) + watchdog_enabled |= NMI_WATCHDOG_ENABLED; + if (soft_watchdog_user_enabled) + watchdog_enabled |= SOFT_WATCHDOG_ENABLED; } - #ifdef CONFIG_SOFTLOCKUP_DETECTOR -/* Helper for online, unparked cpus. */ -#define for_each_watchdog_cpu(cpu) \ - for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) - -atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); +/* Global variables, exported for sysctl */ +unsigned int __read_mostly softlockup_panic = + CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; +static bool softlockup_threads_initialized __read_mostly; static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); @@ -164,50 +181,40 @@ static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static unsigned long soft_lockup_nmi_warn; -unsigned int __read_mostly softlockup_panic = - CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; - static int __init softlockup_panic_setup(char *str) { softlockup_panic = simple_strtoul(str, NULL, 0); - return 1; } __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { - watchdog_enabled = 0; + watchdog_user_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); static int __init nosoftlockup_setup(char *str) { - watchdog_enabled &= ~SOFT_WATCHDOG_ENABLED; + soft_watchdog_user_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); #ifdef CONFIG_SMP +int __read_mostly sysctl_softlockup_all_cpu_backtrace; + static int __init softlockup_all_cpu_backtrace_setup(char *str) { - sysctl_softlockup_all_cpu_backtrace = - !!simple_strtol(str, NULL, 0); + sysctl_softlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0); return 1; } __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup); -#ifdef CONFIG_HARDLOCKUP_DETECTOR -static int __init hardlockup_all_cpu_backtrace_setup(char *str) -{ - sysctl_hardlockup_all_cpu_backtrace = - !!simple_strtol(str, NULL, 0); - return 1; -} -__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); -#endif #endif +static void __lockup_detector_cleanup(void); + /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally @@ -278,11 +285,15 @@ void touch_all_softlockup_watchdogs(void) int cpu; /* - * this is done lockless - * do we care if a 0 races with a timestamp? - * all it means is the softlock check starts one cycle later + * watchdog_mutex cannpt be taken here, as this might be called + * from (soft)interrupt context, so the access to + * watchdog_allowed_cpumask might race with a concurrent update. + * + * The watchdog time stamp can race against a concurrent real + * update as well, the only side effect might be a cycle delay for + * the softlockup check. */ - for_each_watchdog_cpu(cpu) + for_each_cpu(cpu, &watchdog_allowed_mask) per_cpu(watchdog_touch_ts, cpu) = 0; wq_watchdog_touch(-1); } @@ -322,9 +333,6 @@ static void watchdog_interrupt_count(void) __this_cpu_inc(hrtimer_interrupts); } -static int watchdog_enable_all_cpus(void); -static void watchdog_disable_all_cpus(void); - /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { @@ -333,7 +341,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; - if (atomic_read(&watchdog_park_in_progress) != 0) + if (!watchdog_enabled) return HRTIMER_NORESTART; /* kick the hardlockup detector */ @@ -447,32 +455,38 @@ static void watchdog_set_prio(unsigned int policy, unsigned int prio) static void watchdog_enable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); - /* kick off the timer for the hardlockup detector */ + /* + * Start the timer first to prevent the NMI watchdog triggering + * before the timer has a chance to fire. + */ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = watchdog_timer_fn; - - /* Enable the perf event */ - watchdog_nmi_enable(cpu); - - /* done here because hrtimer_start can only pin to smp_processor_id() */ hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL_PINNED); - /* initialize timestamp */ - watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); + /* Initialize timestamp */ __touch_watchdog(); + /* Enable the perf event */ + if (watchdog_enabled & NMI_WATCHDOG_ENABLED) + watchdog_nmi_enable(cpu); + + watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); } static void watchdog_disable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); watchdog_set_prio(SCHED_NORMAL, 0); - hrtimer_cancel(hrtimer); - /* disable the perf event */ + /* + * Disable the perf event first. That prevents that a large delay + * between disabling the timer and disabling the perf event causes + * the perf NMI to detect a false positive. + */ watchdog_nmi_disable(cpu); + hrtimer_cancel(hrtimer); } static void watchdog_cleanup(unsigned int cpu, bool online) @@ -499,21 +513,6 @@ static void watchdog(unsigned int cpu) __this_cpu_write(soft_lockup_hrtimer_cnt, __this_cpu_read(hrtimer_interrupts)); __touch_watchdog(); - - /* - * watchdog_nmi_enable() clears the NMI_WATCHDOG_ENABLED bit in the - * failure path. Check for failures that can occur asynchronously - - * for example, when CPUs are on-lined - and shut down the hardware - * perf event on each CPU accordingly. - * - * The only non-obvious place this bit can be cleared is through - * watchdog_nmi_enable(), so a pr_info() is placed there. Placing a - * pr_info here would be too noisy as it would result in a message - * every few seconds if the hardlockup was disabled but the softlockup - * enabled. - */ - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - watchdog_nmi_disable(cpu); } static struct smp_hotplug_thread watchdog_threads = { @@ -527,295 +526,174 @@ static struct smp_hotplug_thread watchdog_threads = { .unpark = watchdog_enable, }; -/* - * park all watchdog threads that are specified in 'watchdog_cpumask' - * - * This function returns an error if kthread_park() of a watchdog thread - * fails. In this situation, the watchdog threads of some CPUs can already - * be parked and the watchdog threads of other CPUs can still be runnable. - * Callers are expected to handle this special condition as appropriate in - * their context. - * - * This function may only be called in a context that is protected against - * races with CPU hotplug - for example, via get_online_cpus(). - */ -static int watchdog_park_threads(void) +static void softlockup_update_smpboot_threads(void) { - int cpu, ret = 0; + lockdep_assert_held(&watchdog_mutex); - atomic_set(&watchdog_park_in_progress, 1); + if (!softlockup_threads_initialized) + return; - for_each_watchdog_cpu(cpu) { - ret = kthread_park(per_cpu(softlockup_watchdog, cpu)); - if (ret) - break; - } - - atomic_set(&watchdog_park_in_progress, 0); - - return ret; + smpboot_update_cpumask_percpu_thread(&watchdog_threads, + &watchdog_allowed_mask); } -/* - * unpark all watchdog threads that are specified in 'watchdog_cpumask' - * - * This function may only be called in a context that is protected against - * races with CPU hotplug - for example, via get_online_cpus(). - */ -static void watchdog_unpark_threads(void) +/* Temporarily park all watchdog threads */ +static void softlockup_park_all_threads(void) { - int cpu; - - for_each_watchdog_cpu(cpu) - kthread_unpark(per_cpu(softlockup_watchdog, cpu)); + cpumask_clear(&watchdog_allowed_mask); + softlockup_update_smpboot_threads(); } -static int update_watchdog_all_cpus(void) +/* Unpark enabled threads */ +static void softlockup_unpark_threads(void) { - int ret; - - ret = watchdog_park_threads(); - if (ret) - return ret; - - watchdog_unpark_threads(); - - return 0; + cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); + softlockup_update_smpboot_threads(); } -static int watchdog_enable_all_cpus(void) +static void lockup_detector_reconfigure(void) { - int err = 0; - - if (!watchdog_running) { - err = smpboot_register_percpu_thread_cpumask(&watchdog_threads, - &watchdog_cpumask); - if (err) - pr_err("Failed to create watchdog threads, disabled\n"); - else - watchdog_running = 1; - } else { - /* - * Enable/disable the lockup detectors or - * change the sample period 'on the fly'. - */ - err = update_watchdog_all_cpus(); - - if (err) { - watchdog_disable_all_cpus(); - pr_err("Failed to update lockup detectors, disabled\n"); - } - } - - if (err) - watchdog_enabled = 0; - - return err; + cpus_read_lock(); + watchdog_nmi_stop(); + softlockup_park_all_threads(); + set_sample_period(); + lockup_detector_update_enable(); + if (watchdog_enabled && watchdog_thresh) + softlockup_unpark_threads(); + watchdog_nmi_start(); + cpus_read_unlock(); + /* + * Must be called outside the cpus locked section to prevent + * recursive locking in the perf code. + */ + __lockup_detector_cleanup(); } -static void watchdog_disable_all_cpus(void) +/* + * Create the watchdog thread infrastructure and configure the detector(s). + * + * The threads are not unparked as watchdog_allowed_mask is empty. When + * the threads are sucessfully initialized, take the proper locks and + * unpark the threads in the watchdog_cpumask if the watchdog is enabled. + */ +static __init void lockup_detector_setup(void) { - if (watchdog_running) { - watchdog_running = 0; - smpboot_unregister_percpu_thread(&watchdog_threads); - } -} + int ret; -#ifdef CONFIG_SYSCTL -static int watchdog_update_cpus(void) -{ - return smpboot_update_cpumask_percpu_thread( - &watchdog_threads, &watchdog_cpumask); -} -#endif + /* + * If sysctl is off and watchdog got disabled on the command line, + * nothing to do here. + */ + lockup_detector_update_enable(); -#else /* SOFTLOCKUP */ -static int watchdog_park_threads(void) -{ - return 0; -} + if (!IS_ENABLED(CONFIG_SYSCTL) && + !(watchdog_enabled && watchdog_thresh)) + return; -static void watchdog_unpark_threads(void) -{ -} + ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads, + &watchdog_allowed_mask); + if (ret) { + pr_err("Failed to initialize soft lockup detector threads\n"); + return; + } -static int watchdog_enable_all_cpus(void) -{ - return 0; + mutex_lock(&watchdog_mutex); + softlockup_threads_initialized = true; + lockup_detector_reconfigure(); + mutex_unlock(&watchdog_mutex); } -static void watchdog_disable_all_cpus(void) +#else /* CONFIG_SOFTLOCKUP_DETECTOR */ +static inline int watchdog_park_threads(void) { return 0; } +static inline void watchdog_unpark_threads(void) { } +static inline int watchdog_enable_all_cpus(void) { return 0; } +static inline void watchdog_disable_all_cpus(void) { } +static void lockup_detector_reconfigure(void) { + cpus_read_lock(); + watchdog_nmi_stop(); + lockup_detector_update_enable(); + watchdog_nmi_start(); + cpus_read_unlock(); } - -#ifdef CONFIG_SYSCTL -static int watchdog_update_cpus(void) +static inline void lockup_detector_setup(void) { - return 0; + lockup_detector_reconfigure(); } -#endif +#endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ -static void set_sample_period(void) +static void __lockup_detector_cleanup(void) { + lockdep_assert_held(&watchdog_mutex); + hardlockup_detector_perf_cleanup(); } -#endif /* SOFTLOCKUP */ -/* - * Suspend the hard and soft lockup detector by parking the watchdog threads. +/** + * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes + * + * Caller must not hold the cpu hotplug rwsem. */ -int lockup_detector_suspend(void) +void lockup_detector_cleanup(void) { - int ret = 0; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - /* - * Multiple suspend requests can be active in parallel (counted by - * the 'watchdog_suspended' variable). If the watchdog threads are - * running, the first caller takes care that they will be parked. - * The state of 'watchdog_running' cannot change while a suspend - * request is active (see related code in 'proc' handlers). - */ - if (watchdog_running && !watchdog_suspended) - ret = watchdog_park_threads(); - - if (ret == 0) - watchdog_suspended++; - else { - watchdog_disable_all_cpus(); - pr_err("Failed to suspend lockup detectors, disabled\n"); - watchdog_enabled = 0; - } - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - - return ret; + mutex_lock(&watchdog_mutex); + __lockup_detector_cleanup(); + mutex_unlock(&watchdog_mutex); } -/* - * Resume the hard and soft lockup detector by unparking the watchdog threads. +/** + * lockup_detector_soft_poweroff - Interface to stop lockup detector(s) + * + * Special interface for parisc. It prevents lockup detector warnings from + * the default pm_poweroff() function which busy loops forever. */ -void lockup_detector_resume(void) +void lockup_detector_soft_poweroff(void) { - mutex_lock(&watchdog_proc_mutex); - - watchdog_suspended--; - /* - * The watchdog threads are unparked if they were previously running - * and if there is no more active suspend request. - */ - if (watchdog_running && !watchdog_suspended) - watchdog_unpark_threads(); - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + watchdog_enabled = 0; } #ifdef CONFIG_SYSCTL -/* - * Update the run state of the lockup detectors. - */ -static int proc_watchdog_update(void) +/* Propagate any changes to the watchdog threads */ +static void proc_watchdog_update(void) { - int err = 0; - - /* - * Watchdog threads won't be started if they are already active. - * The 'watchdog_running' variable in watchdog_*_all_cpus() takes - * care of this. If those threads are already active, the sample - * period will be updated and the lockup detectors will be enabled - * or disabled 'on the fly'. - */ - if (watchdog_enabled && watchdog_thresh) - err = watchdog_enable_all_cpus(); - else - watchdog_disable_all_cpus(); - - watchdog_nmi_reconfigure(); - - return err; - + /* Remove impossible cpus to keep sysctl output clean. */ + cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); + lockup_detector_reconfigure(); } /* * common function for watchdog, nmi_watchdog and soft_watchdog parameter * - * caller | table->data points to | 'which' contains the flag(s) - * -------------------|-----------------------|----------------------------- - * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED or'ed - * | | with SOFT_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_nmi_watchdog | nmi_watchdog_enabled | NMI_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_soft_watchdog | soft_watchdog_enabled | SOFT_WATCHDOG_ENABLED + * caller | table->data points to | 'which' + * -------------------|----------------------------|-------------------------- + * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED | + * | | SOFT_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_nmi_watchdog | nmi_watchdog_user_enabled | NMI_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED */ static int proc_watchdog_common(int which, struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old, new; - int *watchdog_param = (int *)table->data; + int err, old, *param = table->data; - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); + mutex_lock(&watchdog_mutex); - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } - - /* - * If the parameter is being read return the state of the corresponding - * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the - * run state of the lockup detectors. - */ if (!write) { - *watchdog_param = (watchdog_enabled & which) != 0; + /* + * On read synchronize the userspace interface. This is a + * racy snapshot. + */ + *param = (watchdog_enabled & which) != 0; err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); } else { + old = READ_ONCE(*param); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err) - goto out; - - /* - * There is a race window between fetching the current value - * from 'watchdog_enabled' and storing the new value. During - * this race window, watchdog_nmi_enable() can sneak in and - * clear the NMI_WATCHDOG_ENABLED bit in 'watchdog_enabled'. - * The 'cmpxchg' detects this race and the loop retries. - */ - do { - old = watchdog_enabled; - /* - * If the parameter value is not zero set the - * corresponding bit(s), else clear it(them). - */ - if (*watchdog_param) - new = old | which; - else - new = old & ~which; - } while (cmpxchg(&watchdog_enabled, old, new) != old); - - /* - * Update the run state of the lockup detectors. There is _no_ - * need to check the value returned by proc_watchdog_update() - * and to restore the previous value of 'watchdog_enabled' as - * both lockup detectors are disabled if proc_watchdog_update() - * returns an error. - */ - if (old == new) - goto out; - - err = proc_watchdog_update(); + if (!err && old != READ_ONCE(*param)) + proc_watchdog_update(); } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } @@ -835,6 +713,8 @@ int proc_watchdog(struct ctl_table *table, int write, int proc_nmi_watchdog(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + if (!nmi_watchdog_available && write) + return -ENOTSUPP; return proc_watchdog_common(NMI_WATCHDOG_ENABLED, table, write, buffer, lenp, ppos); } @@ -855,39 +735,17 @@ int proc_soft_watchdog(struct ctl_table *table, int write, int proc_watchdog_thresh(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old, new; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); + int err, old; - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } + mutex_lock(&watchdog_mutex); - old = ACCESS_ONCE(watchdog_thresh); + old = READ_ONCE(watchdog_thresh); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err || !write) - goto out; - - /* - * Update the sample period. Restore on failure. - */ - new = ACCESS_ONCE(watchdog_thresh); - if (old == new) - goto out; + if (!err && write && old != READ_ONCE(watchdog_thresh)) + proc_watchdog_update(); - set_sample_period(); - err = proc_watchdog_update(); - if (err) { - watchdog_thresh = old; - set_sample_period(); - } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } @@ -902,45 +760,19 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, { int err; - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } + mutex_lock(&watchdog_mutex); err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); - if (!err && write) { - /* Remove impossible cpus to keep sysctl output cleaner. */ - cpumask_and(&watchdog_cpumask, &watchdog_cpumask, - cpu_possible_mask); - - if (watchdog_running) { - /* - * Failure would be due to being unable to allocate - * a temporary cpumask, so we are likely not in a - * position to do much else to make things better. - */ - if (watchdog_update_cpus() != 0) - pr_err("cpumask update failed\n"); - } + if (!err && write) + proc_watchdog_update(); - watchdog_nmi_reconfigure(); - } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } - #endif /* CONFIG_SYSCTL */ void __init lockup_detector_init(void) { - set_sample_period(); - #ifdef CONFIG_NO_HZ_FULL if (tick_nohz_full_enabled()) { pr_info("Disabling watchdog on nohz_full cores by default\n"); @@ -951,6 +783,7 @@ void __init lockup_detector_init(void) cpumask_copy(&watchdog_cpumask, cpu_possible_mask); #endif - if (watchdog_enabled) - watchdog_enable_all_cpus(); + if (!watchdog_nmi_probe()) + nmi_watchdog_available = true; + lockup_detector_setup(); } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 3a09ea1b1d3d..71a62ceacdc8 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -21,8 +21,10 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); +static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; +static unsigned int watchdog_cpus; void arch_touch_nmi_watchdog(void) { @@ -103,15 +105,12 @@ static struct perf_event_attr wd_hw_attr = { /* Callback function for perf event subsystem */ static void watchdog_overflow_callback(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs) + struct perf_sample_data *data, + struct pt_regs *regs) { /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; - if (atomic_read(&watchdog_park_in_progress) != 0) - return; - if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; @@ -160,104 +159,131 @@ static void watchdog_overflow_callback(struct perf_event *event, return; } -/* - * People like the simple clean cpu node info on boot. - * Reduce the watchdog noise by only printing messages - * that are different from what cpu0 displayed. - */ -static unsigned long firstcpu_err; -static atomic_t watchdog_cpus; - -int watchdog_nmi_enable(unsigned int cpu) +static int hardlockup_detector_event_create(void) { + unsigned int cpu = smp_processor_id(); struct perf_event_attr *wd_attr; - struct perf_event *event = per_cpu(watchdog_ev, cpu); - int firstcpu = 0; - - /* nothing to do if the hard lockup detector is disabled */ - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - goto out; - - /* is it already setup and enabled? */ - if (event && event->state > PERF_EVENT_STATE_OFF) - goto out; - - /* it is setup but not enabled */ - if (event != NULL) - goto out_enable; - - if (atomic_inc_return(&watchdog_cpus) == 1) - firstcpu = 1; + struct perf_event *evt; wd_attr = &wd_hw_attr; wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); /* Try to register using hardware perf events */ - event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); + evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL, + watchdog_overflow_callback, NULL); + if (IS_ERR(evt)) { + pr_info("Perf event create on CPU %d failed with %ld\n", cpu, + PTR_ERR(evt)); + return PTR_ERR(evt); + } + this_cpu_write(watchdog_ev, evt); + return 0; +} - /* save the first cpu's error for future comparision */ - if (firstcpu && IS_ERR(event)) - firstcpu_err = PTR_ERR(event); +/** + * hardlockup_detector_perf_enable - Enable the local event + */ +void hardlockup_detector_perf_enable(void) +{ + if (hardlockup_detector_event_create()) + return; - if (!IS_ERR(event)) { - /* only print for the first cpu initialized */ - if (firstcpu || firstcpu_err) - pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n"); - goto out_save; - } + if (!watchdog_cpus++) + pr_info("Enabled. Permanently consumes one hw-PMU counter.\n"); - /* - * Disable the hard lockup detector if _any_ CPU fails to set up - * set up the hardware perf event. The watchdog() function checks - * the NMI_WATCHDOG_ENABLED bit periodically. - * - * The barriers are for syncing up watchdog_enabled across all the - * cpus, as clear_bit() does not use barriers. - */ - smp_mb__before_atomic(); - clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled); - smp_mb__after_atomic(); - - /* skip displaying the same error again */ - if (!firstcpu && (PTR_ERR(event) == firstcpu_err)) - return PTR_ERR(event); - - /* vary the KERN level based on the returned errno */ - if (PTR_ERR(event) == -EOPNOTSUPP) - pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu); - else if (PTR_ERR(event) == -ENOENT) - pr_warn("disabled (cpu%i): hardware events not enabled\n", - cpu); - else - pr_err("disabled (cpu%i): unable to create perf event: %ld\n", - cpu, PTR_ERR(event)); - - pr_info("Shutting down hard lockup detector on all cpus\n"); - - return PTR_ERR(event); - - /* success path */ -out_save: - per_cpu(watchdog_ev, cpu) = event; -out_enable: - perf_event_enable(per_cpu(watchdog_ev, cpu)); -out: - return 0; + perf_event_enable(this_cpu_read(watchdog_ev)); } -void watchdog_nmi_disable(unsigned int cpu) +/** + * hardlockup_detector_perf_disable - Disable the local event + */ +void hardlockup_detector_perf_disable(void) { - struct perf_event *event = per_cpu(watchdog_ev, cpu); + struct perf_event *event = this_cpu_read(watchdog_ev); if (event) { perf_event_disable(event); + cpumask_set_cpu(smp_processor_id(), &dead_events_mask); + watchdog_cpus--; + } +} + +/** + * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them + * + * Called from lockup_detector_cleanup(). Serialized by the caller. + */ +void hardlockup_detector_perf_cleanup(void) +{ + int cpu; + + for_each_cpu(cpu, &dead_events_mask) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + /* + * Required because for_each_cpu() reports unconditionally + * CPU0 as set on UP kernels. Sigh. + */ + if (event) + perf_event_release_kernel(event); per_cpu(watchdog_ev, cpu) = NULL; + } + cpumask_clear(&dead_events_mask); +} + +/** + * hardlockup_detector_perf_stop - Globally stop watchdog events + * + * Special interface for x86 to handle the perf HT bug. + */ +void __init hardlockup_detector_perf_stop(void) +{ + int cpu; + + lockdep_assert_cpus_held(); + + for_each_online_cpu(cpu) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) + perf_event_disable(event); + } +} - /* should be in cleanup, but blocks oprofile */ - perf_event_release_kernel(event); +/** + * hardlockup_detector_perf_restart - Globally restart watchdog events + * + * Special interface for x86 to handle the perf HT bug. + */ +void __init hardlockup_detector_perf_restart(void) +{ + int cpu; + + lockdep_assert_cpus_held(); + + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + return; + + for_each_online_cpu(cpu) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) + perf_event_enable(event); + } +} + +/** + * hardlockup_detector_perf_init - Probe whether NMI event is available at all + */ +int __init hardlockup_detector_perf_init(void) +{ + int ret = hardlockup_detector_event_create(); - /* watchdog_nmi_enable() expects this to be zero initially. */ - if (atomic_dec_and_test(&watchdog_cpus)) - firstcpu_err = 0; + if (ret) { + pr_info("Perf NMI watchdog permanently disabled\n"); + } else { + perf_event_release_kernel(this_cpu_read(watchdog_ev)); + this_cpu_write(watchdog_ev, NULL); } + return ret; } diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c index f346715e2255..dbe61c4c2a97 100644 --- a/lib/dynamic_queue_limits.c +++ b/lib/dynamic_queue_limits.c @@ -127,12 +127,11 @@ void dql_reset(struct dql *dql) } EXPORT_SYMBOL(dql_reset); -int dql_init(struct dql *dql, unsigned hold_time) +void dql_init(struct dql *dql, unsigned int hold_time) { dql->max_limit = DQL_MAX_LIMIT; dql->min_limit = 0; dql->slack_hold_time = hold_time; dql_reset(dql); - return 0; } EXPORT_SYMBOL(dql_init); diff --git a/lib/once.c b/lib/once.c index 05c8604627eb..831c5a6b0bb2 100644 --- a/lib/once.c +++ b/lib/once.c @@ -5,7 +5,7 @@ struct once_work { struct work_struct work; - struct static_key *key; + struct static_key_true *key; }; static void once_deferred(struct work_struct *w) @@ -14,11 +14,11 @@ static void once_deferred(struct work_struct *w) work = container_of(w, struct once_work, work); BUG_ON(!static_key_enabled(work->key)); - static_key_slow_dec(work->key); + static_branch_disable(work->key); kfree(work); } -static void once_disable_jump(struct static_key *key) +static void once_disable_jump(struct static_key_true *key) { struct once_work *w; @@ -51,7 +51,7 @@ bool __do_once_start(bool *done, unsigned long *flags) } EXPORT_SYMBOL(__do_once_start); -void __do_once_done(bool *done, struct static_key *once_key, +void __do_once_done(bool *done, struct static_key_true *once_key, unsigned long *flags) __releases(once_lock) { diff --git a/net/atm/clip.c b/net/atm/clip.c index 65f706e4344c..d4f6029d5109 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -153,7 +153,7 @@ static int neigh_check_cb(struct neighbour *n) return 1; } -static void idle_timer_check(unsigned long dummy) +static void idle_timer_check(struct timer_list *unused) { write_lock(&arp_tbl.lock); __neigh_for_each_release(&arp_tbl, neigh_check_cb); @@ -887,7 +887,7 @@ static int __init atm_clip_init(void) register_netdevice_notifier(&clip_dev_notifier); register_inetaddr_notifier(&clip_inet_notifier); - setup_timer(&idle_timer, idle_timer_check, 0); + timer_setup(&idle_timer, idle_timer_check, 0); #ifdef CONFIG_PROC_FS { diff --git a/net/atm/lec.c b/net/atm/lec.c index a3d93a1bb133..c976196da3ea 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1232,7 +1232,7 @@ static void lane2_associate_ind(struct net_device *dev, const u8 *mac_addr, #define LEC_ARP_REFRESH_INTERVAL (3*HZ) static void lec_arp_check_expire(struct work_struct *work); -static void lec_arp_expire_arp(unsigned long data); +static void lec_arp_expire_arp(struct timer_list *t); /* * Arp table funcs @@ -1559,8 +1559,7 @@ static struct lec_arp_table *make_entry(struct lec_priv *priv, } ether_addr_copy(to_return->mac_addr, mac_addr); INIT_HLIST_NODE(&to_return->next); - setup_timer(&to_return->timer, lec_arp_expire_arp, - (unsigned long)to_return); + timer_setup(&to_return->timer, lec_arp_expire_arp, 0); to_return->last_used = jiffies; to_return->priv = priv; skb_queue_head_init(&to_return->tx_wait); @@ -1569,11 +1568,11 @@ static struct lec_arp_table *make_entry(struct lec_priv *priv, } /* Arp sent timer expired */ -static void lec_arp_expire_arp(unsigned long data) +static void lec_arp_expire_arp(struct timer_list *t) { struct lec_arp_table *entry; - entry = (struct lec_arp_table *)data; + entry = from_timer(entry, t, timer); pr_debug("\n"); if (entry->status == ESI_ARP_PENDING) { @@ -1591,10 +1590,10 @@ static void lec_arp_expire_arp(unsigned long data) } /* Unknown/unused vcc expire, remove associated entry */ -static void lec_arp_expire_vcc(unsigned long data) +static void lec_arp_expire_vcc(struct timer_list *t) { unsigned long flags; - struct lec_arp_table *to_remove = (struct lec_arp_table *)data; + struct lec_arp_table *to_remove = from_timer(to_remove, t, timer); struct lec_priv *priv = to_remove->priv; del_timer(&to_remove->timer); @@ -1799,7 +1798,7 @@ static struct atm_vcc *lec_arp_resolve(struct lec_priv *priv, else send_to_lecd(priv, l_arp_xmt, mac_to_find, NULL, NULL); entry->timer.expires = jiffies + (1 * HZ); - entry->timer.function = lec_arp_expire_arp; + entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_arp; add_timer(&entry->timer); found = priv->mcast_vcc; } @@ -1999,7 +1998,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data, entry->old_recv_push = old_push; entry->status = ESI_UNKNOWN; entry->timer.expires = jiffies + priv->vcc_timeout_period; - entry->timer.function = lec_arp_expire_vcc; + entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_vcc; hlist_add_head(&entry->next, &priv->lec_no_forward); add_timer(&entry->timer); dump_arp_table(priv); @@ -2083,7 +2082,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data, entry->status = ESI_UNKNOWN; hlist_add_head(&entry->next, &priv->lec_arp_empty_ones); entry->timer.expires = jiffies + priv->vcc_timeout_period; - entry->timer.function = lec_arp_expire_vcc; + entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_vcc; add_timer(&entry->timer); pr_debug("After vcc was added\n"); dump_arp_table(priv); diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 5677147209e8..b43d99430eb6 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -799,7 +799,6 @@ static int atm_mpoa_mpoad_attach(struct atm_vcc *vcc, int arg) int err; if (mpcs == NULL) { - init_timer(&mpc_timer); mpc_timer_refresh(); /* This lets us now how our LECs are doing */ diff --git a/net/bridge/Makefile b/net/bridge/Makefile index 40b1ede527ca..4aee55fdcc92 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_BRIDGE) += bridge.o bridge-y := br.o br_device.o br_fdb.o br_forward.o br_if.o br_input.o \ br_ioctl.o br_stp.o br_stp_bpdu.o \ br_stp_if.o br_stp_timer.o br_netlink.o \ - br_netlink_tunnel.o + br_netlink_tunnel.o br_arp_nd_proxy.o bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c new file mode 100644 index 000000000000..2cf7716254be --- /dev/null +++ b/net/bridge/br_arp_nd_proxy.c @@ -0,0 +1,469 @@ +/* + * Handle bridge arp/nd proxy/suppress + * + * Copyright (C) 2017 Cumulus Networks + * Copyright (c) 2017 Roopa Prabhu <roopa@cumulusnetworks.com> + * + * Authors: + * Roopa Prabhu <roopa@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/neighbour.h> +#include <net/arp.h> +#include <linux/if_vlan.h> +#include <linux/inetdevice.h> +#include <net/addrconf.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ip6_checksum.h> +#endif + +#include "br_private.h" + +void br_recalculate_neigh_suppress_enabled(struct net_bridge *br) +{ + struct net_bridge_port *p; + bool neigh_suppress = false; + + list_for_each_entry(p, &br->port_list, list) { + if (p->flags & BR_NEIGH_SUPPRESS) { + neigh_suppress = true; + break; + } + } + + br->neigh_suppress_enabled = neigh_suppress; +} + +#if IS_ENABLED(CONFIG_INET) +static void br_arp_send(struct net_bridge *br, struct net_bridge_port *p, + struct net_device *dev, __be32 dest_ip, __be32 src_ip, + const unsigned char *dest_hw, + const unsigned char *src_hw, + const unsigned char *target_hw, + __be16 vlan_proto, u16 vlan_tci) +{ + struct net_bridge_vlan_group *vg; + struct sk_buff *skb; + u16 pvid; + + netdev_dbg(dev, "arp send dev %s dst %pI4 dst_hw %pM src %pI4 src_hw %pM\n", + dev->name, &dest_ip, dest_hw, &src_ip, src_hw); + + if (!vlan_tci) { + arp_send(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip, + dest_hw, src_hw, target_hw); + return; + } + + skb = arp_create(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip, + dest_hw, src_hw, target_hw); + if (!skb) + return; + + if (p) + vg = nbp_vlan_group_rcu(p); + else + vg = br_vlan_group_rcu(br); + pvid = br_get_pvid(vg); + if (pvid == (vlan_tci & VLAN_VID_MASK)) + vlan_tci = 0; + + if (vlan_tci) + __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); + + if (p) { + arp_xmit(skb); + } else { + skb_reset_mac_header(skb); + __skb_pull(skb, skb_network_offset(skb)); + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->pkt_type = PACKET_HOST; + + netif_rx_ni(skb); + } +} + +static int br_chk_addr_ip(struct net_device *dev, void *data) +{ + __be32 ip = *(__be32 *)data; + struct in_device *in_dev; + __be32 addr = 0; + + in_dev = __in_dev_get_rcu(dev); + if (in_dev) + addr = inet_confirm_addr(dev_net(dev), in_dev, 0, ip, + RT_SCOPE_HOST); + + if (addr == ip) + return 1; + + return 0; +} + +static bool br_is_local_ip(struct net_device *dev, __be32 ip) +{ + if (br_chk_addr_ip(dev, &ip)) + return true; + + /* check if ip is configured on upper dev */ + if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip, &ip)) + return true; + + return false; +} + +void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, + u16 vid, struct net_bridge_port *p) +{ + struct net_device *dev = br->dev; + struct net_device *vlandev = dev; + struct neighbour *n; + struct arphdr *parp; + u8 *arpptr, *sha; + __be32 sip, tip; + + BR_INPUT_SKB_CB(skb)->proxyarp_replied = false; + + if ((dev->flags & IFF_NOARP) || + !pskb_may_pull(skb, arp_hdr_len(dev))) + return; + + parp = arp_hdr(skb); + + if (parp->ar_pro != htons(ETH_P_IP) || + parp->ar_hln != dev->addr_len || + parp->ar_pln != 4) + return; + + arpptr = (u8 *)parp + sizeof(struct arphdr); + sha = arpptr; + arpptr += dev->addr_len; /* sha */ + memcpy(&sip, arpptr, sizeof(sip)); + arpptr += sizeof(sip); + arpptr += dev->addr_len; /* tha */ + memcpy(&tip, arpptr, sizeof(tip)); + + if (ipv4_is_loopback(tip) || + ipv4_is_multicast(tip)) + return; + + if (br->neigh_suppress_enabled) { + if (p && (p->flags & BR_NEIGH_SUPPRESS)) + return; + if (ipv4_is_zeronet(sip) || sip == tip) { + /* prevent flooding to neigh suppress ports */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + } + + if (parp->ar_op != htons(ARPOP_REQUEST)) + return; + + if (vid != 0) { + vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto, + vid); + if (!vlandev) + return; + } + + if (br->neigh_suppress_enabled && br_is_local_ip(vlandev, tip)) { + /* its our local ip, so don't proxy reply + * and don't forward to neigh suppress ports + */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + + n = neigh_lookup(&arp_tbl, &tip, vlandev); + if (n) { + struct net_bridge_fdb_entry *f; + + if (!(n->nud_state & NUD_VALID)) { + neigh_release(n); + return; + } + + f = br_fdb_find_rcu(br, n->ha, vid); + if (f) { + bool replied = false; + + if ((p && (p->flags & BR_PROXYARP)) || + (f->dst && (f->dst->flags & (BR_PROXYARP_WIFI | + BR_NEIGH_SUPPRESS)))) { + if (!vid) + br_arp_send(br, p, skb->dev, sip, tip, + sha, n->ha, sha, 0, 0); + else + br_arp_send(br, p, skb->dev, sip, tip, + sha, n->ha, sha, + skb->vlan_proto, + skb_vlan_tag_get(skb)); + replied = true; + } + + /* If we have replied or as long as we know the + * mac, indicate to arp replied + */ + if (replied || br->neigh_suppress_enabled) + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + } + + neigh_release(n); + } +} +#endif + +#if IS_ENABLED(CONFIG_IPV6) +struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *msg) +{ + struct nd_msg *m; + + m = skb_header_pointer(skb, skb_network_offset(skb) + + sizeof(struct ipv6hdr), sizeof(*msg), msg); + if (!m) + return NULL; + + if (m->icmph.icmp6_code != 0 || + (m->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION && + m->icmph.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT)) + return NULL; + + return m; +} + +static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p, + struct sk_buff *request, struct neighbour *n, + __be16 vlan_proto, u16 vlan_tci, struct nd_msg *ns) +{ + struct net_device *dev = request->dev; + struct net_bridge_vlan_group *vg; + struct sk_buff *reply; + struct nd_msg *na; + struct ipv6hdr *pip6; + int na_olen = 8; /* opt hdr + ETH_ALEN for target */ + int ns_olen; + int i, len; + u8 *daddr; + u16 pvid; + + if (!dev) + return; + + len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) + + sizeof(*na) + na_olen + dev->needed_tailroom; + + reply = alloc_skb(len, GFP_ATOMIC); + if (!reply) + return; + + reply->protocol = htons(ETH_P_IPV6); + reply->dev = dev; + skb_reserve(reply, LL_RESERVED_SPACE(dev)); + skb_push(reply, sizeof(struct ethhdr)); + skb_set_mac_header(reply, 0); + + daddr = eth_hdr(request)->h_source; + + /* Do we need option processing ? */ + ns_olen = request->len - (skb_network_offset(request) + + sizeof(struct ipv6hdr)) - sizeof(*ns); + for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) { + if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) { + daddr = ns->opt + i + sizeof(struct nd_opt_hdr); + break; + } + } + + /* Ethernet header */ + ether_addr_copy(eth_hdr(reply)->h_dest, daddr); + ether_addr_copy(eth_hdr(reply)->h_source, n->ha); + eth_hdr(reply)->h_proto = htons(ETH_P_IPV6); + reply->protocol = htons(ETH_P_IPV6); + + skb_pull(reply, sizeof(struct ethhdr)); + skb_set_network_header(reply, 0); + skb_put(reply, sizeof(struct ipv6hdr)); + + /* IPv6 header */ + pip6 = ipv6_hdr(reply); + memset(pip6, 0, sizeof(struct ipv6hdr)); + pip6->version = 6; + pip6->priority = ipv6_hdr(request)->priority; + pip6->nexthdr = IPPROTO_ICMPV6; + pip6->hop_limit = 255; + pip6->daddr = ipv6_hdr(request)->saddr; + pip6->saddr = *(struct in6_addr *)n->primary_key; + + skb_pull(reply, sizeof(struct ipv6hdr)); + skb_set_transport_header(reply, 0); + + na = (struct nd_msg *)skb_put(reply, sizeof(*na) + na_olen); + + /* Neighbor Advertisement */ + memset(na, 0, sizeof(*na) + na_olen); + na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; + na->icmph.icmp6_router = 0; /* XXX: should be 1 ? */ + na->icmph.icmp6_override = 1; + na->icmph.icmp6_solicited = 1; + na->target = ns->target; + ether_addr_copy(&na->opt[2], n->ha); + na->opt[0] = ND_OPT_TARGET_LL_ADDR; + na->opt[1] = na_olen >> 3; + + na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr, + &pip6->daddr, + sizeof(*na) + na_olen, + IPPROTO_ICMPV6, + csum_partial(na, sizeof(*na) + na_olen, 0)); + + pip6->payload_len = htons(sizeof(*na) + na_olen); + + skb_push(reply, sizeof(struct ipv6hdr)); + skb_push(reply, sizeof(struct ethhdr)); + + reply->ip_summed = CHECKSUM_UNNECESSARY; + + if (p) + vg = nbp_vlan_group_rcu(p); + else + vg = br_vlan_group_rcu(br); + pvid = br_get_pvid(vg); + if (pvid == (vlan_tci & VLAN_VID_MASK)) + vlan_tci = 0; + + if (vlan_tci) + __vlan_hwaccel_put_tag(reply, vlan_proto, vlan_tci); + + netdev_dbg(dev, "nd send dev %s dst %pI6 dst_hw %pM src %pI6 src_hw %pM\n", + dev->name, &pip6->daddr, daddr, &pip6->saddr, n->ha); + + if (p) { + dev_queue_xmit(reply); + } else { + skb_reset_mac_header(reply); + __skb_pull(reply, skb_network_offset(reply)); + reply->ip_summed = CHECKSUM_UNNECESSARY; + reply->pkt_type = PACKET_HOST; + + netif_rx_ni(reply); + } +} + +static int br_chk_addr_ip6(struct net_device *dev, void *data) +{ + struct in6_addr *addr = (struct in6_addr *)data; + + if (ipv6_chk_addr(dev_net(dev), addr, dev, 0)) + return 1; + + return 0; +} + +static bool br_is_local_ip6(struct net_device *dev, struct in6_addr *addr) + +{ + if (br_chk_addr_ip6(dev, addr)) + return true; + + /* check if ip is configured on upper dev */ + if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip6, addr)) + return true; + + return false; +} + +void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br, + u16 vid, struct net_bridge_port *p, struct nd_msg *msg) +{ + struct net_device *dev = br->dev; + struct net_device *vlandev = NULL; + struct in6_addr *saddr, *daddr; + struct ipv6hdr *iphdr; + struct neighbour *n; + + BR_INPUT_SKB_CB(skb)->proxyarp_replied = false; + + if (p && (p->flags & BR_NEIGH_SUPPRESS)) + return; + + if (msg->icmph.icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT && + !msg->icmph.icmp6_solicited) { + /* prevent flooding to neigh suppress ports */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + + if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) + return; + + iphdr = ipv6_hdr(skb); + saddr = &iphdr->saddr; + daddr = &iphdr->daddr; + + if (ipv6_addr_any(saddr) || !ipv6_addr_cmp(saddr, daddr)) { + /* prevent flooding to neigh suppress ports */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + + if (vid != 0) { + /* build neigh table lookup on the vlan device */ + vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto, + vid); + if (!vlandev) + return; + } else { + vlandev = dev; + } + + if (br_is_local_ip6(vlandev, &msg->target)) { + /* its our own ip, so don't proxy reply + * and don't forward to arp suppress ports + */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + + n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, vlandev); + if (n) { + struct net_bridge_fdb_entry *f; + + if (!(n->nud_state & NUD_VALID)) { + neigh_release(n); + return; + } + + f = br_fdb_find_rcu(br, n->ha, vid); + if (f) { + bool replied = false; + + if (f->dst && (f->dst->flags & BR_NEIGH_SUPPRESS)) { + if (vid != 0) + br_nd_send(br, p, skb, n, + skb->vlan_proto, + skb_vlan_tag_get(skb), msg); + else + br_nd_send(br, p, skb, n, 0, 0, msg); + replied = true; + } + + /* If we have replied or as long as we know the + * mac, indicate to NEIGH_SUPPRESS ports that we + * have replied + */ + if (replied || br->neigh_suppress_enabled) + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + } + neigh_release(n); + } +} +#endif diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 7acb77c9bd65..28bb22186fa0 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -39,6 +39,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); const struct nf_br_ops *nf_ops; const unsigned char *dest; + struct ethhdr *eth; u16 vid = 0; rcu_read_lock(); @@ -57,11 +58,30 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) BR_INPUT_SKB_CB(skb)->brdev = dev; skb_reset_mac_header(skb); + eth = eth_hdr(skb); skb_pull(skb, ETH_HLEN); if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid)) goto out; + if (IS_ENABLED(CONFIG_INET) && + (eth->h_proto == htons(ETH_P_ARP) || + eth->h_proto == htons(ETH_P_RARP)) && + br->neigh_suppress_enabled) { + br_do_proxy_suppress_arp(skb, br, vid, NULL); + } else if (IS_ENABLED(CONFIG_IPV6) && + skb->protocol == htons(ETH_P_IPV6) && + br->neigh_suppress_enabled && + pskb_may_pull(skb, sizeof(struct ipv6hdr) + + sizeof(struct nd_msg)) && + ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { + struct nd_msg *msg, _msg; + + msg = br_is_nd_neigh_msg(skb, &_msg); + if (msg) + br_do_suppress_nd(skb, br, vid, NULL, msg); + } + dest = eth_hdr(skb)->h_dest; if (is_broadcast_ether_addr(dest)) { br_flood(br, skb, BR_PKT_BROADCAST, false, true); diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 48fb17417fac..b4eed113d2ec 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -204,7 +204,7 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, /* Do not flood to ports that enable proxy ARP */ if (p->flags & BR_PROXYARP) continue; - if ((p->flags & BR_PROXYARP_WIFI) && + if ((p->flags & (BR_PROXYARP_WIFI | BR_NEIGH_SUPPRESS)) && BR_INPUT_SKB_CB(skb)->proxyarp_replied) continue; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 59a74a414e20..ae38547bbf91 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -310,6 +310,8 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) del_nbp(p); } + br_recalculate_neigh_suppress_enabled(br); + br_fdb_delete_by_port(br, NULL, 0, 1); cancel_delayed_work_sync(&br->gc_work); @@ -660,4 +662,7 @@ void br_port_flags_change(struct net_bridge_port *p, unsigned long mask) if (mask & BR_AUTO_MASK) nbp_update_port_count(br); + + if (mask & BR_NEIGH_SUPPRESS) + br_recalculate_neigh_suppress_enabled(br); } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 7cb613776b31..a096d3e189da 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -71,62 +71,6 @@ static int br_pass_frame_up(struct sk_buff *skb) br_netif_receive_skb); } -static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, - u16 vid, struct net_bridge_port *p) -{ - struct net_device *dev = br->dev; - struct neighbour *n; - struct arphdr *parp; - u8 *arpptr, *sha; - __be32 sip, tip; - - BR_INPUT_SKB_CB(skb)->proxyarp_replied = false; - - if ((dev->flags & IFF_NOARP) || - !pskb_may_pull(skb, arp_hdr_len(dev))) - return; - - parp = arp_hdr(skb); - - if (parp->ar_pro != htons(ETH_P_IP) || - parp->ar_op != htons(ARPOP_REQUEST) || - parp->ar_hln != dev->addr_len || - parp->ar_pln != 4) - return; - - arpptr = (u8 *)parp + sizeof(struct arphdr); - sha = arpptr; - arpptr += dev->addr_len; /* sha */ - memcpy(&sip, arpptr, sizeof(sip)); - arpptr += sizeof(sip); - arpptr += dev->addr_len; /* tha */ - memcpy(&tip, arpptr, sizeof(tip)); - - if (ipv4_is_loopback(tip) || - ipv4_is_multicast(tip)) - return; - - n = neigh_lookup(&arp_tbl, &tip, dev); - if (n) { - struct net_bridge_fdb_entry *f; - - if (!(n->nud_state & NUD_VALID)) { - neigh_release(n); - return; - } - - f = br_fdb_find_rcu(br, n->ha, vid); - if (f && ((p->flags & BR_PROXYARP) || - (f->dst && (f->dst->flags & BR_PROXYARP_WIFI)))) { - arp_send(ARPOP_REPLY, ETH_P_ARP, sip, skb->dev, tip, - sha, n->ha, sha); - BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; - } - - neigh_release(n); - } -} - /* note: already called with rcu_read_lock */ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -171,8 +115,22 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb BR_INPUT_SKB_CB(skb)->brdev = br->dev; - if (IS_ENABLED(CONFIG_INET) && skb->protocol == htons(ETH_P_ARP)) - br_do_proxy_arp(skb, br, vid, p); + if (IS_ENABLED(CONFIG_INET) && + (skb->protocol == htons(ETH_P_ARP) || + skb->protocol == htons(ETH_P_RARP))) { + br_do_proxy_suppress_arp(skb, br, vid, p); + } else if (IS_ENABLED(CONFIG_IPV6) && + skb->protocol == htons(ETH_P_IPV6) && + br->neigh_suppress_enabled && + pskb_may_pull(skb, sizeof(struct ipv6hdr) + + sizeof(struct nd_msg)) && + ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { + struct nd_msg *msg, _msg; + + msg = br_is_nd_neigh_msg(skb, &_msg); + if (msg) + br_do_suppress_nd(skb, br, vid, p, msg); + } switch (pkt_type) { case BR_PKT_MULTICAST: diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 8dc5c8d69bcd..7947e0436e18 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -859,8 +859,32 @@ out: spin_unlock(&br->multicast_lock); } +static void br_mc_router_state_change(struct net_bridge *p, + bool is_mc_router) +{ + struct switchdev_attr attr = { + .orig_dev = p->dev, + .id = SWITCHDEV_ATTR_ID_BRIDGE_MROUTER, + .flags = SWITCHDEV_F_DEFER, + .u.mrouter = is_mc_router, + }; + + switchdev_port_attr_set(p->dev, &attr); +} + static void br_multicast_local_router_expired(unsigned long data) { + struct net_bridge *br = (struct net_bridge *)data; + + spin_lock(&br->multicast_lock); + if (br->multicast_router == MDB_RTR_TYPE_DISABLED || + br->multicast_router == MDB_RTR_TYPE_PERM || + timer_pending(&br->multicast_router_timer)) + goto out; + + br_mc_router_state_change(br, false); +out: + spin_unlock(&br->multicast_lock); } static void br_multicast_querier_expired(struct net_bridge *br, @@ -1364,9 +1388,12 @@ static void br_multicast_mark_router(struct net_bridge *br, unsigned long now = jiffies; if (!port) { - if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) + if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) { + if (!timer_pending(&br->multicast_router_timer)) + br_mc_router_state_change(br, true); mod_timer(&br->multicast_router_timer, now + br->multicast_querier_interval); + } return; } @@ -1952,7 +1979,7 @@ void br_multicast_init(struct net_bridge *br) spin_lock_init(&br->multicast_lock); setup_timer(&br->multicast_router_timer, - br_multicast_local_router_expired, 0); + br_multicast_local_router_expired, (unsigned long)br); setup_timer(&br->ip4_other_query.timer, br_ip4_multicast_querier_expired, (unsigned long)br); setup_timer(&br->ip4_own_query.timer, br_ip4_multicast_query_expired, @@ -2042,9 +2069,14 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val) switch (val) { case MDB_RTR_TYPE_DISABLED: case MDB_RTR_TYPE_PERM: + br_mc_router_state_change(br, val == MDB_RTR_TYPE_PERM); del_timer(&br->multicast_router_timer); - /* fall through */ + br->multicast_router = val; + err = 0; + break; case MDB_RTR_TYPE_TEMP_QUERY: + if (br->multicast_router != MDB_RTR_TYPE_TEMP_QUERY) + br_mc_router_state_change(br, false); br->multicast_router = val; err = 0; break; @@ -2184,6 +2216,18 @@ bool br_multicast_enabled(const struct net_device *dev) } EXPORT_SYMBOL_GPL(br_multicast_enabled); +bool br_multicast_router(const struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + bool is_router; + + spin_lock_bh(&br->multicast_lock); + is_router = br_multicast_is_router(br); + spin_unlock_bh(&br->multicast_lock); + return is_router; +} +EXPORT_SYMBOL_GPL(br_multicast_router); + int br_multicast_set_querier(struct net_bridge *br, unsigned long val) { unsigned long max_delay; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index dea88a255d26..f0e82682e071 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -138,6 +138,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */ + + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ @@ -210,7 +211,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) || nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags & BR_VLAN_TUNNEL)) || - nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask)) + nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) || + nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS, + !!(p->flags & BR_NEIGH_SUPPRESS))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); @@ -785,6 +788,11 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) p->group_fwd_mask = fwd_mask; } + err = br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, + BR_NEIGH_SUPPRESS); + if (err) + return err; + br_port_flags_change(p, old_flags ^ p->flags); return 0; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index ab4df24f7bba..fa0039f44818 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -404,6 +404,7 @@ struct net_bridge { #ifdef CONFIG_NET_SWITCHDEV int offload_fwd_mark; #endif + bool neigh_suppress_enabled; }; struct br_input_skb_cb { @@ -1139,4 +1140,11 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb) } #endif /* CONFIG_NET_SWITCHDEV */ +/* br_arp_nd_proxy.c */ +void br_recalculate_neigh_suppress_enabled(struct net_bridge *br); +void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, + u16 vid, struct net_bridge_port *p); +void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br, + u16 vid, struct net_bridge_port *p, struct nd_msg *msg); +struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *m); #endif diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 9110d5e56085..0a1fa9ccd8b7 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -191,6 +191,7 @@ BRPORT_ATTR_FLAG(proxyarp, BR_PROXYARP); BRPORT_ATTR_FLAG(proxyarp_wifi, BR_PROXYARP_WIFI); BRPORT_ATTR_FLAG(multicast_flood, BR_MCAST_FLOOD); BRPORT_ATTR_FLAG(broadcast_flood, BR_BCAST_FLOOD); +BRPORT_ATTR_FLAG(neigh_suppress, BR_NEIGH_SUPPRESS); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf) @@ -241,6 +242,7 @@ static const struct brport_attribute *brport_attrs[] = { &brport_attr_multicast_flood, &brport_attr_broadcast_flood, &brport_attr_group_fwd_mask, + &brport_attr_neigh_suppress, NULL }; diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 2585b100ebbb..276b60262981 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -65,8 +65,8 @@ static int ebt_broute(struct sk_buff *skb) static int __net_init broute_net_init(struct net *net) { - net->xt.broute_table = ebt_register_table(net, &broute_table, NULL); - return PTR_ERR_OR_ZERO(net->xt.broute_table); + return ebt_register_table(net, &broute_table, NULL, + &net->xt.broute_table); } static void __net_exit broute_net_exit(struct net *net) diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 45a00dbdbcad..c41da5fac84f 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -93,8 +93,8 @@ static const struct nf_hook_ops ebt_ops_filter[] = { static int __net_init frame_filter_net_init(struct net *net) { - net->xt.frame_filter = ebt_register_table(net, &frame_filter, ebt_ops_filter); - return PTR_ERR_OR_ZERO(net->xt.frame_filter); + return ebt_register_table(net, &frame_filter, ebt_ops_filter, + &net->xt.frame_filter); } static void __net_exit frame_filter_net_exit(struct net *net) diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 57cd5bb154e7..08df7406ecb3 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -93,8 +93,8 @@ static const struct nf_hook_ops ebt_ops_nat[] = { static int __net_init frame_nat_net_init(struct net *net) { - net->xt.frame_nat = ebt_register_table(net, &frame_nat, ebt_ops_nat); - return PTR_ERR_OR_ZERO(net->xt.frame_nat); + return ebt_register_table(net, &frame_nat, ebt_ops_nat, + &net->xt.frame_nat); } static void __net_exit frame_nat_net_exit(struct net *net) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 83951f978445..3b3dcf719e07 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1169,9 +1169,8 @@ static void __ebt_unregister_table(struct net *net, struct ebt_table *table) kfree(table); } -struct ebt_table * -ebt_register_table(struct net *net, const struct ebt_table *input_table, - const struct nf_hook_ops *ops) +int ebt_register_table(struct net *net, const struct ebt_table *input_table, + const struct nf_hook_ops *ops, struct ebt_table **res) { struct ebt_table_info *newinfo; struct ebt_table *t, *table; @@ -1183,7 +1182,7 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table, repl->entries == NULL || repl->entries_size == 0 || repl->counters != NULL || input_table->private != NULL) { BUGPRINT("Bad table data for ebt_register_table!!!\n"); - return ERR_PTR(-EINVAL); + return -EINVAL; } /* Don't add one table to multiple lists. */ @@ -1252,16 +1251,18 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table, list_add(&table->list, &net->xt.tables[NFPROTO_BRIDGE]); mutex_unlock(&ebt_mutex); + WRITE_ONCE(*res, table); + if (!ops) - return table; + return 0; ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); if (ret) { __ebt_unregister_table(net, table); - return ERR_PTR(ret); + *res = NULL; } - return table; + return ret; free_unlock: mutex_unlock(&ebt_mutex); free_chainstack: @@ -1276,7 +1277,7 @@ free_newinfo: free_table: kfree(table); out: - return ERR_PTR(ret); + return ret; } void ebt_unregister_table(struct net *net, struct ebt_table *table, diff --git a/net/can/af_can.c b/net/can/af_can.c index 88edac0f3e36..1f75e11ac35a 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -882,8 +882,8 @@ static int can_pernet_init(struct net *net) if (IS_ENABLED(CONFIG_PROC_FS)) { /* the statistics are updated every second (timer triggered) */ if (stats_timer) { - setup_timer(&net->can.can_stattimer, can_stat_update, - (unsigned long)net); + timer_setup(&net->can.can_stattimer, can_stat_update, + 0); mod_timer(&net->can.can_stattimer, round_jiffies(jiffies + HZ)); } diff --git a/net/can/af_can.h b/net/can/af_can.h index d0ef45bb2a72..eca6463c6213 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -113,6 +113,6 @@ struct s_pstats { /* function prototypes for the CAN networklayer procfs (proc.c) */ void can_init_proc(struct net *net); void can_remove_proc(struct net *net); -void can_stat_update(unsigned long data); +void can_stat_update(struct timer_list *t); #endif /* AF_CAN_H */ diff --git a/net/can/proc.c b/net/can/proc.c index 83045f00c63c..d979b3dc49a6 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -115,9 +115,9 @@ static unsigned long calc_rate(unsigned long oldjif, unsigned long newjif, return rate; } -void can_stat_update(unsigned long data) +void can_stat_update(struct timer_list *t) { - struct net *net = (struct net *)data; + struct net *net = from_timer(net, t, can.can_stattimer); struct s_stats *can_stats = net->can.can_stats; unsigned long j = jiffies; /* snapshot */ @@ -221,7 +221,7 @@ static int can_stats_proc_show(struct seq_file *m, void *v) seq_putc(m, '\n'); - if (net->can.can_stattimer.function == can_stat_update) { + if (net->can.can_stattimer.function == (TIMER_FUNC_TYPE)can_stat_update) { seq_printf(m, " %8ld %% total match ratio (RXMR)\n", can_stats->total_rx_match_ratio); @@ -291,7 +291,7 @@ static int can_reset_stats_proc_show(struct seq_file *m, void *v) user_reset = 1; - if (net->can.can_stattimer.function == can_stat_update) { + if (net->can.can_stattimer.function == (TIMER_FUNC_TYPE)can_stat_update) { seq_printf(m, "Scheduled statistic reset #%ld.\n", can_pstats->stats_reset + 1); } else { diff --git a/net/core/dev.c b/net/core/dev.c index fcddccb6be41..cf5894f0e6eb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2040,6 +2040,7 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) return 0; } +EXPORT_SYMBOL(netdev_txq_to_tc); #ifdef CONFIG_XPS static DEFINE_MUTEX(xps_map_mutex); @@ -4491,6 +4492,33 @@ out: return ret; } +/** + * netif_receive_skb_core - special purpose version of netif_receive_skb + * @skb: buffer to process + * + * More direct receive version of netif_receive_skb(). It should + * only be used by callers that have a need to skip RPS and Generic XDP. + * Caller must also take care of handling if (page_is_)pfmemalloc. + * + * This function may only be called from softirq context and interrupts + * should be enabled. + * + * Return values (usually ignored): + * NET_RX_SUCCESS: no congestion + * NET_RX_DROP: packet was dropped + */ +int netif_receive_skb_core(struct sk_buff *skb) +{ + int ret; + + rcu_read_lock(); + ret = __netif_receive_skb_core(skb, false); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(netif_receive_skb_core); + static int __netif_receive_skb(struct sk_buff *skb) { int ret; diff --git a/net/core/dst.c b/net/core/dst.c index a6c47da7d0f8..662a2d4a3d19 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -322,3 +322,19 @@ metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags) return md_dst; } EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu); + +void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst) +{ +#ifdef CONFIG_DST_CACHE + int cpu; + + for_each_possible_cpu(cpu) { + struct metadata_dst *one_md_dst = per_cpu_ptr(md_dst, cpu); + + if (one_md_dst->type == METADATA_IP_TUNNEL) + dst_cache_destroy(&one_md_dst->u.tun_info.dst_cache); + } +#endif + free_percpu(md_dst); +} +EXPORT_SYMBOL_GPL(metadata_dst_free_percpu); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 3228411ada0f..0c406306792a 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -403,6 +403,22 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data) return 0; } +/* Given two link masks, AND them together and save the result in dst. */ +void ethtool_intersect_link_masks(struct ethtool_link_ksettings *dst, + struct ethtool_link_ksettings *src) +{ + unsigned int size = BITS_TO_LONGS(__ETHTOOL_LINK_MODE_MASK_NBITS); + unsigned int idx = 0; + + for (; idx < size; idx++) { + dst->link_modes.supported[idx] &= + src->link_modes.supported[idx]; + dst->link_modes.advertising[idx] &= + src->link_modes.advertising[idx]; + } +} +EXPORT_SYMBOL(ethtool_intersect_link_masks); + void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst, u32 legacy_u32) { diff --git a/net/core/filter.c b/net/core/filter.c index b7e8caa1e790..09e011f20291 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -43,6 +43,7 @@ #include <linux/timer.h> #include <linux/uaccess.h> #include <asm/unaligned.h> +#include <asm/cmpxchg.h> #include <linux/filter.h> #include <linux/ratelimit.h> #include <linux/seccomp.h> @@ -2525,10 +2526,36 @@ static int __bpf_tx_xdp(struct net_device *dev, err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp); if (err) return err; - if (map) + dev->netdev_ops->ndo_xdp_flush(dev); + return 0; +} + +static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, + struct bpf_map *map, + struct xdp_buff *xdp, + u32 index) +{ + int err; + + if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + struct net_device *dev = fwd; + + if (!dev->netdev_ops->ndo_xdp_xmit) + return -EOPNOTSUPP; + + err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp); + if (err) + return err; __dev_map_insert_ctx(map, index); - else - dev->netdev_ops->ndo_xdp_flush(dev); + + } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + struct bpf_cpu_map_entry *rcpu = fwd; + + err = cpu_map_enqueue(rcpu, xdp, dev_rx); + if (err) + return err; + __cpu_map_insert_ctx(map, index); + } return 0; } @@ -2538,11 +2565,33 @@ void xdp_do_flush_map(void) struct bpf_map *map = ri->map_to_flush; ri->map_to_flush = NULL; - if (map) - __dev_map_flush(map); + if (map) { + switch (map->map_type) { + case BPF_MAP_TYPE_DEVMAP: + __dev_map_flush(map); + break; + case BPF_MAP_TYPE_CPUMAP: + __cpu_map_flush(map); + break; + default: + break; + } + } } EXPORT_SYMBOL_GPL(xdp_do_flush_map); +static void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index) +{ + switch (map->map_type) { + case BPF_MAP_TYPE_DEVMAP: + return __dev_map_lookup_elem(map, index); + case BPF_MAP_TYPE_CPUMAP: + return __cpu_map_lookup_elem(map, index); + default: + return NULL; + } +} + static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog, unsigned long aux) { @@ -2555,8 +2604,8 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, struct redirect_info *ri = this_cpu_ptr(&redirect_info); unsigned long map_owner = ri->map_owner; struct bpf_map *map = ri->map; - struct net_device *fwd = NULL; u32 index = ri->ifindex; + void *fwd = NULL; int err; ri->ifindex = 0; @@ -2569,7 +2618,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, goto err; } - fwd = __dev_map_lookup_elem(map, index); + fwd = __xdp_map_lookup_elem(map, index); if (!fwd) { err = -EINVAL; goto err; @@ -2577,7 +2626,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, if (ri->map_to_flush && ri->map_to_flush != map) xdp_do_flush_map(); - err = __bpf_tx_xdp(fwd, map, xdp, index); + err = __bpf_tx_xdp_map(dev, fwd, map, xdp, index); if (unlikely(err)) goto err; @@ -2619,54 +2668,88 @@ err: } EXPORT_SYMBOL_GPL(xdp_do_redirect); -int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *xdp_prog) +static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd) +{ + unsigned int len; + + if (unlikely(!(fwd->flags & IFF_UP))) + return -ENETDOWN; + + len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; + if (skb->len > len) + return -EMSGSIZE; + + return 0; +} + +int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog) { struct redirect_info *ri = this_cpu_ptr(&redirect_info); unsigned long map_owner = ri->map_owner; struct bpf_map *map = ri->map; struct net_device *fwd = NULL; u32 index = ri->ifindex; - unsigned int len; int err = 0; ri->ifindex = 0; ri->map = NULL; ri->map_owner = 0; - if (map) { - if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) { - err = -EFAULT; - map = NULL; - goto err; - } - fwd = __dev_map_lookup_elem(map, index); - } else { - fwd = dev_get_by_index_rcu(dev_net(dev), index); + if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) { + err = -EFAULT; + map = NULL; + goto err; } + fwd = __xdp_map_lookup_elem(map, index); if (unlikely(!fwd)) { err = -EINVAL; goto err; } - if (unlikely(!(fwd->flags & IFF_UP))) { - err = -ENETDOWN; + if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd)))) + goto err; + skb->dev = fwd; + } else { + /* TODO: Handle BPF_MAP_TYPE_CPUMAP */ + err = -EBADRQC; goto err; } - len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; - if (skb->len > len) { - err = -EMSGSIZE; + _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index); + return 0; +err: + _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err); + return err; +} + +int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + u32 index = ri->ifindex; + struct net_device *fwd; + int err = 0; + + if (ri->map) + return xdp_do_generic_redirect_map(dev, skb, xdp_prog); + + ri->ifindex = 0; + fwd = dev_get_by_index_rcu(dev_net(dev), index); + if (unlikely(!fwd)) { + err = -EINVAL; goto err; } + if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd)))) + goto err; + skb->dev = fwd; - map ? _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index) - : _trace_xdp_redirect(dev, xdp_prog, index); + _trace_xdp_redirect(dev, xdp_prog, index); return 0; err: - map ? _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err) - : _trace_xdp_redirect_err(dev, xdp_prog, index, err); + _trace_xdp_redirect_err(dev, xdp_prog, index, err); return err; } EXPORT_SYMBOL_GPL(xdp_do_generic_redirect); @@ -2987,14 +3070,15 @@ static const struct bpf_func_proto * bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) { if (!md_dst) { - /* Race is not possible, since it's called from verifier - * that is holding verifier mutex. - */ - md_dst = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, - METADATA_IP_TUNNEL, - GFP_KERNEL); - if (!md_dst) + struct metadata_dst __percpu *tmp; + + tmp = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, + METADATA_IP_TUNNEL, + GFP_KERNEL); + if (!tmp) return NULL; + if (cmpxchg(&md_dst, NULL, tmp)) + metadata_dst_free_percpu(tmp); } switch (which) { @@ -3648,6 +3732,25 @@ static bool tc_cls_act_is_valid_access(int off, int size, return bpf_skb_is_valid_access(off, size, type, info); } +static bool +tc_cls_act_is_valid_access_analyzer(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + switch (off) { + case offsetof(struct sk_buff, len): + return true; + case offsetof(struct sk_buff, data): + info->reg_type = PTR_TO_PACKET; + return true; + case offsetof(struct sk_buff, cb) + + offsetof(struct bpf_skb_data_end, data_end): + info->reg_type = PTR_TO_PACKET_END; + return true; + } + return false; +} + static bool __is_valid_xdp_access(int off, int size) { if (off < 0 || off >= sizeof(struct xdp_md)) @@ -3682,6 +3785,21 @@ static bool xdp_is_valid_access(int off, int size, return __is_valid_xdp_access(off, size); } +static bool xdp_is_valid_access_analyzer(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + switch (off) { + case offsetof(struct xdp_buff, data): + info->reg_type = PTR_TO_PACKET; + return true; + case offsetof(struct xdp_buff, data_end): + info->reg_type = PTR_TO_PACKET_END; + return true; + } + return false; +} + void bpf_warn_invalid_xdp_action(u32 act) { const u32 act_max = XDP_REDIRECT; @@ -4311,68 +4429,103 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } -const struct bpf_verifier_ops sk_filter_prog_ops = { +const struct bpf_verifier_ops sk_filter_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; -const struct bpf_verifier_ops tc_cls_act_prog_ops = { +const struct bpf_prog_ops sk_filter_prog_ops = { +}; + +const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .get_func_proto = tc_cls_act_func_proto, .is_valid_access = tc_cls_act_is_valid_access, .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, +}; + +const struct bpf_verifier_ops tc_cls_act_analyzer_ops = { + .is_valid_access = tc_cls_act_is_valid_access_analyzer, +}; + +const struct bpf_prog_ops tc_cls_act_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops xdp_prog_ops = { +const struct bpf_verifier_ops xdp_verifier_ops = { .get_func_proto = xdp_func_proto, .is_valid_access = xdp_is_valid_access, .convert_ctx_access = xdp_convert_ctx_access, +}; + +const struct bpf_verifier_ops xdp_analyzer_ops = { + .is_valid_access = xdp_is_valid_access_analyzer, +}; + +const struct bpf_prog_ops xdp_prog_ops = { .test_run = bpf_prog_test_run_xdp, }; -const struct bpf_verifier_ops cg_skb_prog_ops = { +const struct bpf_verifier_ops cg_skb_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, +}; + +const struct bpf_prog_ops cg_skb_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops lwt_inout_prog_ops = { +const struct bpf_verifier_ops lwt_inout_verifier_ops = { .get_func_proto = lwt_inout_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, +}; + +const struct bpf_prog_ops lwt_inout_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops lwt_xmit_prog_ops = { +const struct bpf_verifier_ops lwt_xmit_verifier_ops = { .get_func_proto = lwt_xmit_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, +}; + +const struct bpf_prog_ops lwt_xmit_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops cg_sock_prog_ops = { +const struct bpf_verifier_ops cg_sock_verifier_ops = { .get_func_proto = sock_filter_func_proto, .is_valid_access = sock_filter_is_valid_access, .convert_ctx_access = sock_filter_convert_ctx_access, }; -const struct bpf_verifier_ops sock_ops_prog_ops = { +const struct bpf_prog_ops cg_sock_prog_ops = { +}; + +const struct bpf_verifier_ops sock_ops_verifier_ops = { .get_func_proto = sock_ops_func_proto, .is_valid_access = sock_ops_is_valid_access, .convert_ctx_access = sock_ops_convert_ctx_access, }; -const struct bpf_verifier_ops sk_skb_prog_ops = { +const struct bpf_prog_ops sock_ops_prog_ops = { +}; + +const struct bpf_verifier_ops sk_skb_verifier_ops = { .get_func_proto = sk_skb_func_proto, .is_valid_access = sk_skb_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_prologue = sk_skb_prologue, }; +const struct bpf_prog_ops sk_skb_prog_ops = { +}; + int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 1132820c8e62..f4e4fa2db505 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -31,6 +31,7 @@ #include <trace/events/napi.h> #include <trace/events/sock.h> #include <trace/events/udp.h> +#include <trace/events/tcp.h> #include <trace/events/fib.h> #include <trace/events/qdisc.h> #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e84d108cfee4..20b550d07fe3 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -453,7 +453,7 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family) { const struct rtnl_af_ops *ops; - list_for_each_entry(ops, &rtnl_af_ops, list) { + list_for_each_entry_rcu(ops, &rtnl_af_ops, list) { if (ops->family == family) return ops; } @@ -470,7 +470,7 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family) void rtnl_af_register(struct rtnl_af_ops *ops) { rtnl_lock(); - list_add_tail(&ops->list, &rtnl_af_ops); + list_add_tail_rcu(&ops->list, &rtnl_af_ops); rtnl_unlock(); } EXPORT_SYMBOL_GPL(rtnl_af_register); @@ -482,8 +482,10 @@ EXPORT_SYMBOL_GPL(rtnl_af_register); void rtnl_af_unregister(struct rtnl_af_ops *ops) { rtnl_lock(); - list_del(&ops->list); + list_del_rcu(&ops->list); rtnl_unlock(); + + synchronize_rcu(); } EXPORT_SYMBOL_GPL(rtnl_af_unregister); @@ -496,13 +498,15 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev, /* IFLA_AF_SPEC */ size = nla_total_size(sizeof(struct nlattr)); - list_for_each_entry(af_ops, &rtnl_af_ops, list) { + rcu_read_lock(); + list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) { if (af_ops->get_link_af_size) { /* AF_* + nested data */ size += nla_total_size(sizeof(struct nlattr)) + af_ops->get_link_af_size(dev, ext_filter_mask); } } + rcu_read_unlock(); return size; } @@ -1382,6 +1386,47 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb, return 0; } +static int rtnl_fill_link_af(struct sk_buff *skb, + const struct net_device *dev, + u32 ext_filter_mask) +{ + const struct rtnl_af_ops *af_ops; + struct nlattr *af_spec; + + af_spec = nla_nest_start(skb, IFLA_AF_SPEC); + if (!af_spec) + return -EMSGSIZE; + + list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) { + struct nlattr *af; + int err; + + if (!af_ops->fill_link_af) + continue; + + af = nla_nest_start(skb, af_ops->family); + if (!af) + return -EMSGSIZE; + + err = af_ops->fill_link_af(skb, dev, ext_filter_mask); + /* + * Caller may return ENODATA to indicate that there + * was no data to be dumped. This is not an error, it + * means we should trim the attribute header and + * continue. + */ + if (err == -ENODATA) + nla_nest_cancel(skb, af); + else if (err < 0) + return -EMSGSIZE; + + nla_nest_end(skb, af); + } + + nla_nest_end(skb, af_spec); + return 0; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask, @@ -1389,8 +1434,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, { struct ifinfomsg *ifm; struct nlmsghdr *nlh; - struct nlattr *af_spec; - struct rtnl_af_ops *af_ops; ASSERT_RTNL(); nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); @@ -1477,39 +1520,16 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_s32(skb, IFLA_NEW_NETNSID, *new_nsid) < 0) goto nla_put_failure; - if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC))) - goto nla_put_failure; - - list_for_each_entry(af_ops, &rtnl_af_ops, list) { - if (af_ops->fill_link_af) { - struct nlattr *af; - int err; - - if (!(af = nla_nest_start(skb, af_ops->family))) - goto nla_put_failure; - - err = af_ops->fill_link_af(skb, dev, ext_filter_mask); - - /* - * Caller may return ENODATA to indicate that there - * was no data to be dumped. This is not an error, it - * means we should trim the attribute header and - * continue. - */ - if (err == -ENODATA) - nla_nest_cancel(skb, af); - else if (err < 0) - goto nla_put_failure; - - nla_nest_end(skb, af); - } - } - - nla_nest_end(skb, af_spec); + rcu_read_lock(); + if (rtnl_fill_link_af(skb, dev, ext_filter_mask)) + goto nla_put_failure_rcu; + rcu_read_unlock(); nlmsg_end(skb, nlh); return 0; +nla_put_failure_rcu: + rcu_read_unlock(); nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; @@ -1771,17 +1791,27 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { const struct rtnl_af_ops *af_ops; - if (!(af_ops = rtnl_af_lookup(nla_type(af)))) + rcu_read_lock(); + af_ops = rtnl_af_lookup(nla_type(af)); + if (!af_ops) { + rcu_read_unlock(); return -EAFNOSUPPORT; + } - if (!af_ops->set_link_af) + if (!af_ops->set_link_af) { + rcu_read_unlock(); return -EOPNOTSUPP; + } if (af_ops->validate_link_af) { err = af_ops->validate_link_af(dev, af); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); return err; + } } + + rcu_read_unlock(); } } @@ -2239,13 +2269,18 @@ static int do_setlink(const struct sk_buff *skb, nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { const struct rtnl_af_ops *af_ops; + rcu_read_lock(); + if (!(af_ops = rtnl_af_lookup(nla_type(af)))) BUG(); err = af_ops->set_link_af(dev, af); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); goto errout; + } + rcu_read_unlock(); status |= DO_SETLINK_NOTIFY; } } @@ -3066,21 +3101,21 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm, } EXPORT_SYMBOL(ndo_dflt_fdb_add); -static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid) +static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid, + struct netlink_ext_ack *extack) { u16 vid = 0; if (vlan_attr) { if (nla_len(vlan_attr) != sizeof(u16)) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan\n"); + NL_SET_ERR_MSG(extack, "invalid vlan attribute size"); return -EINVAL; } vid = nla_get_u16(vlan_attr); if (!vid || vid >= VLAN_VID_MASK) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan id %d\n", - vid); + NL_SET_ERR_MSG(extack, "invalid vlan id"); return -EINVAL; } } @@ -3105,24 +3140,24 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex == 0) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ifindex\n"); + NL_SET_ERR_MSG(extack, "invalid ifindex"); return -EINVAL; } dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with unknown ifindex\n"); + NL_SET_ERR_MSG(extack, "unknown ifindex"); return -ENODEV; } if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid address\n"); + NL_SET_ERR_MSG(extack, "invalid address"); return -EINVAL; } addr = nla_data(tb[NDA_LLADDR]); - err = fdb_vid_parse(tb[NDA_VLAN], &vid); + err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack); if (err) return err; @@ -3209,24 +3244,24 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex == 0) { - pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ifindex\n"); + NL_SET_ERR_MSG(extack, "invalid ifindex"); return -EINVAL; } dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { - pr_info("PF_BRIDGE: RTM_DELNEIGH with unknown ifindex\n"); + NL_SET_ERR_MSG(extack, "unknown ifindex"); return -ENODEV; } if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { - pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid address\n"); + NL_SET_ERR_MSG(extack, "invalid address"); return -EINVAL; } addr = nla_data(tb[NDA_LLADDR]); - err = fdb_vid_parse(tb[NDA_VLAN], &vid); + err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack); if (err) return err; @@ -3666,7 +3701,7 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, dev = __dev_get_by_index(net, ifm->ifi_index); if (!dev) { - pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n"); + NL_SET_ERR_MSG(extack, "unknown ifindex"); return -ENODEV; } @@ -3741,7 +3776,7 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, dev = __dev_get_by_index(net, ifm->ifi_index); if (!dev) { - pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n"); + NL_SET_ERR_MSG(extack, "unknown ifindex"); return -ENODEV; } @@ -3992,25 +4027,30 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, if (!attr) goto nla_put_failure; - list_for_each_entry(af_ops, &rtnl_af_ops, list) { + rcu_read_lock(); + list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) { if (af_ops->fill_stats_af) { struct nlattr *af; int err; af = nla_nest_start(skb, af_ops->family); - if (!af) + if (!af) { + rcu_read_unlock(); goto nla_put_failure; - + } err = af_ops->fill_stats_af(skb, dev); - if (err == -ENODATA) + if (err == -ENODATA) { nla_nest_cancel(skb, af); - else if (err < 0) + } else if (err < 0) { + rcu_read_unlock(); goto nla_put_failure; + } nla_nest_end(skb, af); } } + rcu_read_unlock(); nla_nest_end(skb, attr); @@ -4079,7 +4119,8 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev, /* for IFLA_STATS_AF_SPEC */ size += nla_total_size(0); - list_for_each_entry(af_ops, &rtnl_af_ops, list) { + rcu_read_lock(); + list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) { if (af_ops->get_stats_af_size) { size += nla_total_size( af_ops->get_stats_af_size(dev)); @@ -4088,6 +4129,7 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev, size += nla_total_size(0); } } + rcu_read_unlock(); } return size; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 822a90e56aea..40717501cbdd 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1350,8 +1350,7 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) /* Set the tail pointer and length */ skb_put(n, skb->len); - if (skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)) - BUG(); + BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)); copy_skb_header(n, skb); return n; @@ -1449,8 +1448,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, BUG_ON(nhead < 0); - if (skb_shared(skb)) - BUG(); + BUG_ON(skb_shared(skb)); size = SKB_DATA_ALIGN(size); @@ -1595,9 +1593,8 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, head_copy_off = newheadroom - head_copy_len; /* Copy the linear header and data. */ - if (skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off, - skb->len + head_copy_len)) - BUG(); + BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off, + skb->len + head_copy_len)); copy_skb_header(n, skb); @@ -1878,8 +1875,8 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta) return NULL; } - if (skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta)) - BUG(); + BUG_ON(skb_copy_bits(skb, skb_headlen(skb), + skb_tail_pointer(skb), delta)); /* Optimization: no fragments, no reasons to preestimate * size of pulled pages. Superb. diff --git a/net/core/sock.c b/net/core/sock.c index 23953b741a41..35656a9e4e44 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2683,7 +2683,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk_init_common(sk); sk->sk_send_head = NULL; - init_timer(&sk->sk_timer); + timer_setup(&sk->sk_timer, NULL, 0); sk->sk_allocation = GFP_KERNEL; sk->sk_rcvbuf = sysctl_rmem_default; diff --git a/net/dccp/input.c b/net/dccp/input.c index fa6be9750bb4..d28d46bff6ab 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -534,6 +534,7 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk, case DCCP_PKT_DATA: if (sk->sk_state == DCCP_RESPOND) break; + /* fall through */ case DCCP_PKT_DATAACK: case DCCP_PKT_ACK: /* diff --git a/net/dccp/options.c b/net/dccp/options.c index 51cdfc3bd8ca..4e40db017e19 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -227,8 +227,8 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, * Ack vectors are processed by the TX CCID if it is * interested. The RX CCID need not parse Ack Vectors, * since it is only interested in clearing old state. - * Fall through. */ + /* fall through */ case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC: if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk, pkt_type, opt, value, len)) diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 3a2c34027758..1e35526bf436 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -125,10 +125,11 @@ static void dccp_retransmit_timer(struct sock *sk) __sk_dst_reset(sk); } -static void dccp_write_timer(unsigned long data) +static void dccp_write_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; - struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = + from_timer(icsk, t, icsk_retransmit_timer); + struct sock *sk = &icsk->icsk_inet.sk; int event = 0; bh_lock_sock(sk); @@ -161,19 +162,20 @@ out: sock_put(sk); } -static void dccp_keepalive_timer(unsigned long data) +static void dccp_keepalive_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; + struct sock *sk = from_timer(sk, t, sk_timer); pr_err("dccp should not use a keepalive timer !\n"); sock_put(sk); } /* This is the same as tcp_delack_timer, sans prequeue & mem_reclaim stuff */ -static void dccp_delack_timer(unsigned long data) +static void dccp_delack_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; - struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = + from_timer(icsk, t, icsk_delack_timer); + struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 73a0399dc7a2..518cea17b811 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -533,10 +533,6 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf scp->keepalive = 10 * HZ; scp->keepalive_fxn = dn_keepalive; - init_timer(&scp->delack_timer); - scp->delack_pending = 0; - scp->delack_fxn = dn_nsp_delayed_ack; - dn_start_slow_timer(sk); out: return sk; @@ -634,10 +630,12 @@ static void dn_destroy_sock(struct sock *sk) goto disc_reject; case DN_RUN: scp->state = DN_DI; + /* fall through */ case DN_DI: case DN_DR: disc_reject: dn_nsp_send_disc(sk, NSP_DISCINIT, 0, sk->sk_allocation); + /* fall through */ case DN_NC: case DN_NR: case DN_RJ: @@ -651,6 +649,7 @@ disc_reject: break; default: printk(KERN_DEBUG "DECnet: dn_destroy_sock passed socket in invalid state\n"); + /* fall through */ case DN_O: dn_stop_slow_timer(sk); diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 4d339de56862..92dbaa3f1eae 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -1038,14 +1038,14 @@ static void dn_eth_down(struct net_device *dev) static void dn_dev_set_timer(struct net_device *dev); -static void dn_dev_timer_func(unsigned long arg) +static void dn_dev_timer_func(struct timer_list *t) { - struct net_device *dev = (struct net_device *)arg; - struct dn_dev *dn_db; + struct dn_dev *dn_db = from_timer(dn_db, t, timer); + struct net_device *dev; struct dn_ifaddr *ifa; rcu_read_lock(); - dn_db = rcu_dereference(dev->dn_ptr); + dev = dn_db->dev; if (dn_db->t3 <= dn_db->parms.t2) { if (dn_db->parms.timer3) { for (ifa = rcu_dereference(dn_db->ifa_list); @@ -1070,8 +1070,6 @@ static void dn_dev_set_timer(struct net_device *dev) if (dn_db->parms.t2 > dn_db->parms.t3) dn_db->parms.t2 = dn_db->parms.t3; - dn_db->timer.data = (unsigned long)dev; - dn_db->timer.function = dn_dev_timer_func; dn_db->timer.expires = jiffies + (dn_db->parms.t2 * HZ); add_timer(&dn_db->timer); @@ -1100,7 +1098,7 @@ static struct dn_dev *dn_dev_create(struct net_device *dev, int *err) rcu_assign_pointer(dev->dn_ptr, dn_db); dn_db->dev = dev; - init_timer(&dn_db->timer); + timer_setup(&dn_db->timer, dn_dev_timer_func, 0); dn_db->uptime = jiffies; diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index 66f035e476ea..e50a4adfcf7e 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -491,17 +491,6 @@ void dn_send_conn_ack (struct sock *sk) dn_nsp_send(skb); } -void dn_nsp_delayed_ack(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - if (scp->ackxmt_oth != scp->numoth_rcv) - dn_nsp_send_oth_ack(sk); - - if (scp->ackxmt_dat != scp->numdat_rcv) - dn_nsp_send_data_ack(sk); -} - static int dn_nsp_retrans_conn_conf(struct sock *sk) { struct dn_scp *scp = DN_SK(sk); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 0bd3afd01dd2..bff5ab88cdbb 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -338,7 +338,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou dn_rt_hash_table[hash].chain); rcu_assign_pointer(dn_rt_hash_table[hash].chain, rth); - dst_use(&rth->dst, now); + dst_hold_and_use(&rth->dst, now); spin_unlock_bh(&dn_rt_hash_table[hash].lock); dst_release_immediate(&rt->dst); @@ -351,7 +351,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou rcu_assign_pointer(rt->dst.dn_next, dn_rt_hash_table[hash].chain); rcu_assign_pointer(dn_rt_hash_table[hash].chain, rt); - dst_use(&rt->dst, now); + dst_hold_and_use(&rt->dst, now); spin_unlock_bh(&dn_rt_hash_table[hash].lock); *rp = rt; return 0; @@ -1258,7 +1258,7 @@ static int __dn_route_output_key(struct dst_entry **pprt, const struct flowidn * (flp->flowidn_mark == rt->fld.flowidn_mark) && dn_is_output_route(rt) && (rt->fld.flowidn_oif == flp->flowidn_oif)) { - dst_use(&rt->dst, jiffies); + dst_hold_and_use(&rt->dst, jiffies); rcu_read_unlock_bh(); *pprt = &rt->dst; return 0; @@ -1535,7 +1535,7 @@ static int dn_route_input(struct sk_buff *skb) (rt->fld.flowidn_oif == 0) && (rt->fld.flowidn_mark == skb->mark) && (rt->fld.flowidn_iif == cb->iif)) { - dst_use(&rt->dst, jiffies); + dst_hold_and_use(&rt->dst, jiffies); rcu_read_unlock(); skb_dst_set(skb, (struct dst_entry *)rt); return 0; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 51ca2a524a27..a3abf7a7b9a2 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -14,6 +14,7 @@ #include <linux/platform_device.h> #include <linux/slab.h> #include <linux/module.h> +#include <linux/notifier.h> #include <linux/of.h> #include <linux/of_mdio.h> #include <linux/of_platform.h> @@ -200,7 +201,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, #ifdef CONFIG_PM_SLEEP static bool dsa_is_port_initialized(struct dsa_switch *ds, int p) { - return ds->enabled_port_mask & (1 << p) && ds->ports[p].netdev; + return ds->enabled_port_mask & (1 << p) && ds->ports[p].slave; } int dsa_switch_suspend(struct dsa_switch *ds) @@ -212,7 +213,7 @@ int dsa_switch_suspend(struct dsa_switch *ds) if (!dsa_is_port_initialized(ds, i)) continue; - ret = dsa_slave_suspend(ds->ports[i].netdev); + ret = dsa_slave_suspend(ds->ports[i].slave); if (ret) return ret; } @@ -239,7 +240,7 @@ int dsa_switch_resume(struct dsa_switch *ds) if (!dsa_is_port_initialized(ds, i)) continue; - ret = dsa_slave_resume(ds->ports[i].netdev); + ret = dsa_slave_resume(ds->ports[i].slave); if (ret) return ret; } @@ -261,6 +262,28 @@ bool dsa_schedule_work(struct work_struct *work) return queue_work(dsa_owq, work); } +static ATOMIC_NOTIFIER_HEAD(dsa_notif_chain); + +int register_dsa_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&dsa_notif_chain, nb); +} +EXPORT_SYMBOL_GPL(register_dsa_notifier); + +int unregister_dsa_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&dsa_notif_chain, nb); +} +EXPORT_SYMBOL_GPL(unregister_dsa_notifier); + +int call_dsa_notifiers(unsigned long val, struct net_device *dev, + struct dsa_notifier_info *info) +{ + info->dev = dev; + return atomic_notifier_call_chain(&dsa_notif_chain, val, info); +} +EXPORT_SYMBOL_GPL(call_dsa_notifiers); + static int __init dsa_init_module(void) { int rc; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 54ed054777bd..9e8b8aab049d 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -279,7 +279,7 @@ static int dsa_user_port_apply(struct dsa_port *port) if (err) { dev_warn(ds->dev, "Failed to create slave %d: %d\n", port->index, err); - port->netdev = NULL; + port->slave = NULL; return err; } @@ -289,7 +289,7 @@ static int dsa_user_port_apply(struct dsa_port *port) if (err) return err; - devlink_port_type_eth_set(&port->devlink_port, port->netdev); + devlink_port_type_eth_set(&port->devlink_port, port->slave); return 0; } @@ -297,9 +297,9 @@ static int dsa_user_port_apply(struct dsa_port *port) static void dsa_user_port_unapply(struct dsa_port *port) { devlink_port_unregister(&port->devlink_port); - if (port->netdev) { - dsa_slave_destroy(port->netdev); - port->netdev = NULL; + if (port->slave) { + dsa_slave_destroy(port->slave); + port->slave = NULL; port->ds->enabled_port_mask &= ~(1 << port->index); } } @@ -336,12 +336,6 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds) if (err) return err; - if (ds->ops->set_addr) { - err = ds->ops->set_addr(ds, dst->cpu_dp->netdev->dev_addr); - if (err < 0) - return err; - } - if (!ds->slave_mii_bus && ds->ops->phy_read) { ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); if (!ds->slave_mii_bus) @@ -438,9 +432,9 @@ static int dsa_dst_apply(struct dsa_switch_tree *dst) * sent to the tag format's receive function. */ wmb(); - dst->cpu_dp->netdev->dsa_ptr = dst->cpu_dp; + dst->cpu_dp->master->dsa_ptr = dst->cpu_dp; - err = dsa_master_ethtool_setup(dst->cpu_dp->netdev); + err = dsa_master_ethtool_setup(dst->cpu_dp->master); if (err) return err; @@ -457,9 +451,9 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst) if (!dst->applied) return; - dsa_master_ethtool_restore(dst->cpu_dp->netdev); + dsa_master_ethtool_restore(dst->cpu_dp->master); - dst->cpu_dp->netdev->dsa_ptr = NULL; + dst->cpu_dp->master->dsa_ptr = NULL; /* If we used a tagging format that doesn't have an ethertype * field, make sure that all packets from this point get sent @@ -505,7 +499,7 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, if (!dst->cpu_dp) { dst->cpu_dp = port; - dst->cpu_dp->netdev = ethernet_dev; + dst->cpu_dp->master = ethernet_dev; } /* Initialize cpu_port_mask now for drv->setup() diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 2850077cc9cc..1e9914062d0b 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -113,8 +113,8 @@ int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], int dsa_master_ethtool_setup(struct net_device *dev); void dsa_master_ethtool_restore(struct net_device *dev); -static inline struct net_device *dsa_master_get_slave(struct net_device *dev, - int device, int port) +static inline struct net_device *dsa_master_find_slave(struct net_device *dev, + int device, int port) { struct dsa_port *cpu_dp = dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; @@ -130,7 +130,7 @@ static inline struct net_device *dsa_master_get_slave(struct net_device *dev, if (port < 0 || port >= ds->num_ports) return NULL; - return ds->ports[port].netdev; + return ds->ports[port].slave; } /* port.c */ @@ -169,6 +169,21 @@ int dsa_slave_resume(struct net_device *slave_dev); int dsa_slave_register_notifier(void); void dsa_slave_unregister_notifier(void); +static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + + return p->dp; +} + +static inline struct net_device * +dsa_slave_to_master(const struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + + return dp->cpu_dp->master; +} + /* switch.c */ int dsa_switch_register_notifier(struct dsa_switch *ds); void dsa_switch_unregister_notifier(struct dsa_switch *ds); @@ -197,9 +212,4 @@ extern const struct dsa_device_ops qca_netdev_ops; /* tag_trailer.c */ extern const struct dsa_device_ops trailer_netdev_ops; -static inline struct net_device *dsa_master_netdev(struct dsa_slave_priv *p) -{ - return p->dp->cpu_dp->netdev; -} - #endif diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 19ff6e0a21dc..b6c88fd33d4f 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -120,7 +120,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, return -EINVAL; } dst->cpu_dp = &ds->ports[i]; - dst->cpu_dp->netdev = master; + dst->cpu_dp->master = master; ds->cpu_port_mask |= 1 << i; } else if (!strcmp(name, "dsa")) { ds->dsa_port_mask |= 1 << i; @@ -172,12 +172,6 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, if (ret) return ret; - if (ops->set_addr) { - ret = ops->set_addr(ds, master->dev_addr); - if (ret < 0) - return ret; - } - if (!ds->slave_mii_bus && ops->phy_read) { ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); if (!ds->slave_mii_bus) @@ -267,10 +261,10 @@ static void dsa_switch_destroy(struct dsa_switch *ds) if (!(ds->enabled_port_mask & (1 << port))) continue; - if (!ds->ports[port].netdev) + if (!ds->ports[port].slave) continue; - dsa_slave_destroy(ds->ports[port].netdev); + dsa_slave_destroy(ds->ports[port].slave); } /* Disable configuration of the CPU and DSA ports */ @@ -607,7 +601,7 @@ static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, wmb(); dev->dsa_ptr = dst->cpu_dp; - return dsa_master_ethtool_setup(dst->cpu_dp->netdev); + return dsa_master_ethtool_setup(dst->cpu_dp->master); } static int dsa_probe(struct platform_device *pdev) @@ -672,9 +666,9 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) { int i; - dsa_master_ethtool_restore(dst->cpu_dp->netdev); + dsa_master_ethtool_restore(dst->cpu_dp->master); - dst->cpu_dp->netdev->dsa_ptr = NULL; + dst->cpu_dp->master->dsa_ptr = NULL; /* If we used a tagging format that doesn't have an ethertype * field, make sure that all packets from this point get sent @@ -689,7 +683,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) dsa_switch_destroy(ds); } - dev_put(dst->cpu_dp->netdev); + dev_put(dst->cpu_dp->master); } static int dsa_remove(struct platform_device *pdev) @@ -746,8 +740,7 @@ int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], const unsigned char *addr, u16 vid, u16 flags) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); return dsa_port_fdb_add(dp, addr, vid); } @@ -756,8 +749,7 @@ int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); return dsa_port_fdb_del(dp, addr, vid); } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index fb2954ff198c..6906de0f0050 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -64,16 +64,13 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds) /* slave device handling ****************************************************/ static int dsa_slave_get_iflink(const struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - - return dsa_master_netdev(p)->ifindex; + return dsa_slave_to_master(dev)->ifindex; } static int dsa_slave_open(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; - struct net_device *master = dsa_master_netdev(p); + struct net_device *master = dsa_slave_to_master(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); int err; if (!(master->flags & IFF_UP)) @@ -120,9 +117,8 @@ out: static int dsa_slave_close(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); - struct dsa_port *dp = p->dp; + struct net_device *master = dsa_slave_to_master(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); if (dev->phydev) phy_stop(dev->phydev); @@ -144,8 +140,7 @@ static int dsa_slave_close(struct net_device *dev) static void dsa_slave_change_rx_flags(struct net_device *dev, int change) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); + struct net_device *master = dsa_slave_to_master(dev); if (change & IFF_ALLMULTI) dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1); @@ -155,8 +150,7 @@ static void dsa_slave_change_rx_flags(struct net_device *dev, int change) static void dsa_slave_set_rx_mode(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); + struct net_device *master = dsa_slave_to_master(dev); dev_mc_sync(master, dev); dev_uc_sync(master, dev); @@ -164,8 +158,7 @@ static void dsa_slave_set_rx_mode(struct net_device *dev) static int dsa_slave_set_mac_address(struct net_device *dev, void *a) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); + struct net_device *master = dsa_slave_to_master(dev); struct sockaddr *addr = a; int err; @@ -246,14 +239,13 @@ dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_dump_ctx dump = { .dev = dev, .skb = skb, .cb = cb, .idx = *idx, }; - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; int err; err = dsa_port_fdb_dump(dp, dsa_slave_port_fdb_do_dump, &dump); @@ -274,8 +266,7 @@ static int dsa_slave_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct switchdev_trans *trans) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); int ret; switch (attr->id) { @@ -301,8 +292,7 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct switchdev_trans *trans) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); int err; /* For the prepare phase, ensure the full set of changes is feasable in @@ -329,8 +319,7 @@ static int dsa_slave_port_obj_add(struct net_device *dev, static int dsa_slave_port_obj_del(struct net_device *dev, const struct switchdev_obj *obj) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); int err; switch (obj->id) { @@ -351,8 +340,8 @@ static int dsa_slave_port_obj_del(struct net_device *dev, static int dsa_slave_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: @@ -413,7 +402,7 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) /* Queue the SKB for transmission on the parent interface, but * do not modify its EtherType */ - nskb->dev = dsa_master_netdev(p); + nskb->dev = dsa_slave_to_master(dev); dev_queue_xmit(nskb); return NETDEV_TX_OK; @@ -431,11 +420,11 @@ static void dsa_slave_get_drvinfo(struct net_device *dev, static int dsa_slave_get_regs_len(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs_len) - return ds->ops->get_regs_len(ds, p->dp->index); + return ds->ops->get_regs_len(ds, dp->index); return -EOPNOTSUPP; } @@ -443,11 +432,11 @@ static int dsa_slave_get_regs_len(struct net_device *dev) static void dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs) - ds->ops->get_regs(ds, p->dp->index, regs, _p); + ds->ops->get_regs(ds, dp->index, regs, _p); } static u32 dsa_slave_get_link(struct net_device *dev) @@ -462,8 +451,8 @@ static u32 dsa_slave_get_link(struct net_device *dev) static int dsa_slave_get_eeprom_len(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->cd && ds->cd->eeprom_len) return ds->cd->eeprom_len; @@ -477,8 +466,8 @@ static int dsa_slave_get_eeprom_len(struct net_device *dev) static int dsa_slave_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->get_eeprom) return ds->ops->get_eeprom(ds, eeprom, data); @@ -489,8 +478,8 @@ static int dsa_slave_get_eeprom(struct net_device *dev, static int dsa_slave_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->set_eeprom) return ds->ops->set_eeprom(ds, eeprom, data); @@ -501,8 +490,8 @@ static int dsa_slave_set_eeprom(struct net_device *dev, static void dsa_slave_get_strings(struct net_device *dev, uint32_t stringset, uint8_t *data) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (stringset == ETH_SS_STATS) { int len = ETH_GSTRING_LEN; @@ -512,7 +501,7 @@ static void dsa_slave_get_strings(struct net_device *dev, strncpy(data + 2 * len, "rx_packets", len); strncpy(data + 3 * len, "rx_bytes", len); if (ds->ops->get_strings) - ds->ops->get_strings(ds, p->dp->index, data + 4 * len); + ds->ops->get_strings(ds, dp->index, data + 4 * len); } } @@ -520,8 +509,9 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, uint64_t *data) { + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_switch *ds = dp->ds; struct pcpu_sw_netstats *s; unsigned int start; int i; @@ -543,13 +533,13 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, data[3] += rx_bytes; } if (ds->ops->get_ethtool_stats) - ds->ops->get_ethtool_stats(ds, p->dp->index, data + 4); + ds->ops->get_ethtool_stats(ds, dp->index, data + 4); } static int dsa_slave_get_sset_count(struct net_device *dev, int sset) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (sset == ETH_SS_STATS) { int count; @@ -566,29 +556,29 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->get_wol) - ds->ops->get_wol(ds, p->dp->index, w); + ds->ops->get_wol(ds, dp->index, w); } static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; int ret = -EOPNOTSUPP; if (ds->ops->set_wol) - ret = ds->ops->set_wol(ds, p->dp->index, w); + ret = ds->ops->set_wol(ds, dp->index, w); return ret; } static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; int ret; /* Port's PHY and MAC both need to be EEE capable */ @@ -598,7 +588,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) if (!ds->ops->set_mac_eee) return -EOPNOTSUPP; - ret = ds->ops->set_mac_eee(ds, p->dp->index, e); + ret = ds->ops->set_mac_eee(ds, dp->index, e); if (ret) return ret; @@ -613,8 +603,8 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; int ret; /* Port's PHY and MAC both need to be EEE capable */ @@ -624,7 +614,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) if (!ds->ops->get_mac_eee) return -EOPNOTSUPP; - ret = ds->ops->get_mac_eee(ds, p->dp->index, e); + ret = ds->ops->get_mac_eee(ds, dp->index, e); if (ret) return ret; @@ -635,8 +625,8 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) static int dsa_slave_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) { + struct net_device *master = dsa_slave_to_master(dev); struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); struct netpoll *netpoll; int err = 0; @@ -676,9 +666,9 @@ static void dsa_slave_poll_controller(struct net_device *dev) static int dsa_slave_get_phys_port_name(struct net_device *dev, char *name, size_t len) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); - if (snprintf(name, len, "p%d", p->dp->index) >= len) + if (snprintf(name, len, "p%d", dp->index) >= len) return -EINVAL; return 0; @@ -701,14 +691,15 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_mall_tc_entry *mall_tc_entry; __be16 protocol = cls->common.protocol; - struct dsa_switch *ds = p->dp->ds; struct net *net = dev_net(dev); - struct dsa_slave_priv *to_p; + struct dsa_switch *ds = dp->ds; struct net_device *to_dev; const struct tc_action *a; + struct dsa_port *to_dp; int err = -EOPNOTSUPP; LIST_HEAD(actions); int ifindex; @@ -741,13 +732,12 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, mall_tc_entry->type = DSA_PORT_MALL_MIRROR; mirror = &mall_tc_entry->mirror; - to_p = netdev_priv(to_dev); + to_dp = dsa_slave_to_port(to_dev); - mirror->to_local_port = to_p->dp->index; + mirror->to_local_port = to_dp->index; mirror->ingress = ingress; - err = ds->ops->port_mirror_add(ds, p->dp->index, mirror, - ingress); + err = ds->ops->port_mirror_add(ds, dp->index, mirror, ingress); if (err) { kfree(mall_tc_entry); return err; @@ -762,9 +752,9 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, static void dsa_slave_del_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_mall_tc_entry *mall_tc_entry; - struct dsa_switch *ds = p->dp->ds; + struct dsa_switch *ds = dp->ds; if (!ds->ops->port_mirror_del) return; @@ -777,8 +767,7 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev, switch (mall_tc_entry->type) { case DSA_PORT_MALL_MIRROR: - ds->ops->port_mirror_del(ds, p->dp->index, - &mall_tc_entry->mirror); + ds->ops->port_mirror_del(ds, dp->index, &mall_tc_entry->mirror); break; default: WARN_ON(1); @@ -855,25 +844,25 @@ static void dsa_slave_get_stats64(struct net_device *dev, static int dsa_slave_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc, u32 *rule_locs) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (!ds->ops->get_rxnfc) return -EOPNOTSUPP; - return ds->ops->get_rxnfc(ds, p->dp->index, nfc, rule_locs); + return ds->ops->get_rxnfc(ds, dp->index, nfc, rule_locs); } static int dsa_slave_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (!ds->ops->set_rxnfc) return -EOPNOTSUPP; - return ds->ops->set_rxnfc(ds, p->dp->index, nfc); + return ds->ops->set_rxnfc(ds, dp->index, nfc); } static const struct ethtool_ops dsa_slave_ethtool_ops = { @@ -933,8 +922,9 @@ static struct device_type dsa_type = { static void dsa_slave_adjust_link(struct net_device *dev) { + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_switch *ds = dp->ds; unsigned int status_changed = 0; if (p->old_link != dev->phydev->link) { @@ -953,7 +943,7 @@ static void dsa_slave_adjust_link(struct net_device *dev) } if (ds->ops->adjust_link && status_changed) - ds->ops->adjust_link(ds, p->dp->index, dev->phydev); + ds->ops->adjust_link(ds, dp->index, dev->phydev); if (status_changed) phy_print_status(dev->phydev); @@ -962,14 +952,14 @@ static void dsa_slave_adjust_link(struct net_device *dev) static int dsa_slave_fixed_link_update(struct net_device *dev, struct fixed_phy_status *status) { - struct dsa_slave_priv *p; struct dsa_switch *ds; + struct dsa_port *dp; if (dev) { - p = netdev_priv(dev); - ds = p->dp->ds; + dp = dsa_slave_to_port(dev); + ds = dp->ds; if (ds->ops->fixed_link_update) - ds->ops->fixed_link_update(ds, p->dp->index, status); + ds->ops->fixed_link_update(ds, dp->index, status); } return 0; @@ -978,8 +968,9 @@ static int dsa_slave_fixed_link_update(struct net_device *dev, /* slave device setup *******************************************************/ static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) { + struct dsa_port *dp = dsa_slave_to_port(slave_dev); struct dsa_slave_priv *p = netdev_priv(slave_dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_switch *ds = dp->ds; slave_dev->phydev = mdiobus_get_phy(ds->slave_mii_bus, addr); if (!slave_dev->phydev) { @@ -997,14 +988,15 @@ static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) static int dsa_slave_phy_setup(struct net_device *slave_dev) { + struct dsa_port *dp = dsa_slave_to_port(slave_dev); struct dsa_slave_priv *p = netdev_priv(slave_dev); - struct dsa_switch *ds = p->dp->ds; - struct device_node *phy_dn, *port_dn; + struct device_node *port_dn = dp->dn; + struct dsa_switch *ds = dp->ds; + struct device_node *phy_dn; bool phy_is_fixed = false; u32 phy_flags = 0; int mode, ret; - port_dn = p->dp->dn; mode = of_get_phy_mode(port_dn); if (mode < 0) mode = PHY_INTERFACE_MODE_NA; @@ -1025,7 +1017,7 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) } if (ds->ops->get_phy_flags) - phy_flags = ds->ops->get_phy_flags(ds, p->dp->index); + phy_flags = ds->ops->get_phy_flags(ds, dp->index); if (phy_dn) { int phy_id = of_mdio_parse_addr(&slave_dev->dev, phy_dn); @@ -1061,10 +1053,10 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) * MDIO bus instead */ if (!slave_dev->phydev) { - ret = dsa_slave_phy_connect(slave_dev, p->dp->index); + ret = dsa_slave_phy_connect(slave_dev, dp->index); if (ret) { netdev_err(slave_dev, "failed to connect to port %d: %d\n", - p->dp->index, ret); + dp->index, ret); if (phy_is_fixed) of_phy_deregister_fixed_link(port_dn); return ret; @@ -1114,18 +1106,29 @@ int dsa_slave_resume(struct net_device *slave_dev) return 0; } +static void dsa_slave_notify(struct net_device *dev, unsigned long val) +{ + struct net_device *master = dsa_slave_to_master(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_notifier_register_info rinfo = { + .switch_number = dp->ds->index, + .port_number = dp->index, + .master = master, + .info.dev = dev, + }; + + call_dsa_notifiers(val, dev, &rinfo.info); +} + int dsa_slave_create(struct dsa_port *port, const char *name) { + struct dsa_port *cpu_dp = port->cpu_dp; + struct net_device *master = cpu_dp->master; struct dsa_switch *ds = port->ds; - struct net_device *master; struct net_device *slave_dev; struct dsa_slave_priv *p; - struct dsa_port *cpu_dp; int ret; - cpu_dp = ds->dst->cpu_dp; - master = cpu_dp->netdev; - if (!ds->num_tx_queues) ds->num_tx_queues = 1; @@ -1167,7 +1170,7 @@ int dsa_slave_create(struct dsa_port *port, const char *name) p->old_link = -1; p->old_duplex = -1; - port->netdev = slave_dev; + port->slave = slave_dev; netif_carrier_off(slave_dev); @@ -1177,6 +1180,8 @@ int dsa_slave_create(struct dsa_port *port, const char *name) goto out_free; } + dsa_slave_notify(slave_dev, DSA_PORT_REGISTER); + ret = register_netdev(slave_dev); if (ret) { netdev_err(master, "error %d registering interface %s\n", @@ -1188,21 +1193,20 @@ int dsa_slave_create(struct dsa_port *port, const char *name) out_phy: phy_disconnect(slave_dev->phydev); - if (of_phy_is_fixed_link(p->dp->dn)) - of_phy_deregister_fixed_link(p->dp->dn); + if (of_phy_is_fixed_link(port->dn)) + of_phy_deregister_fixed_link(port->dn); out_free: free_percpu(p->stats64); free_netdev(slave_dev); - port->netdev = NULL; + port->slave = NULL; return ret; } void dsa_slave_destroy(struct net_device *slave_dev) { + struct dsa_port *dp = dsa_slave_to_port(slave_dev); struct dsa_slave_priv *p = netdev_priv(slave_dev); - struct device_node *port_dn; - - port_dn = p->dp->dn; + struct device_node *port_dn = dp->dn; netif_carrier_off(slave_dev); if (slave_dev->phydev) { @@ -1211,6 +1215,7 @@ void dsa_slave_destroy(struct net_device *slave_dev) if (of_phy_is_fixed_link(port_dn)) of_phy_deregister_fixed_link(port_dn); } + dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); unregister_netdev(slave_dev); free_percpu(p->stats64); free_netdev(slave_dev); @@ -1224,8 +1229,7 @@ static bool dsa_slave_dev_check(struct net_device *dev) static int dsa_slave_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); int err = NOTIFY_DONE; if (netif_is_bridge_master(info->upper_dev)) { @@ -1268,14 +1272,14 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) container_of(work, struct dsa_switchdev_event_work, work); struct net_device *dev = switchdev_work->dev; struct switchdev_notifier_fdb_info *fdb_info; - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); int err; rtnl_lock(); switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; - err = dsa_port_fdb_add(p->dp, fdb_info->addr, fdb_info->vid); + err = dsa_port_fdb_add(dp, fdb_info->addr, fdb_info->vid); if (err) { netdev_dbg(dev, "fdb add failed err=%d\n", err); break; @@ -1286,7 +1290,7 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) case SWITCHDEV_FDB_DEL_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; - err = dsa_port_fdb_del(p->dp, fdb_info->addr, fdb_info->vid); + err = dsa_port_fdb_del(dp, fdb_info->addr, fdb_info->vid); if (err) { netdev_dbg(dev, "fdb del failed err=%d\n", err); dev_close(dev); diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 8e4bdb9d9ae3..9e082bae3cb0 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -61,7 +61,7 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u16 queue = skb_get_queue_mapping(skb); u8 *brcm_tag; @@ -82,9 +82,14 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev ((queue & BRCM_IG_TC_MASK) << BRCM_IG_TC_SHIFT); brcm_tag[1] = 0; brcm_tag[2] = 0; - if (p->dp->index == 8) + if (dp->index == 8) brcm_tag[2] = BRCM_IG_DSTMAP2_MASK; - brcm_tag[3] = (1 << p->dp->index) & BRCM_IG_DSTMAP1_MASK; + brcm_tag[3] = (1 << dp->index) & BRCM_IG_DSTMAP1_MASK; + + /* Now tell the master network device about the desired output queue + * as well + */ + skb_set_queue_mapping(skb, BRCM_TAG_SET_PORT_QUEUE(dp->index, queue)); return skb; } @@ -114,7 +119,7 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, /* Locate which port this is coming from */ source_port = brcm_tag[3] & BRCM_EG_PID_MASK; - skb->dev = dsa_master_get_slave(dev, 0, source_port); + skb->dev = dsa_master_find_slave(dev, 0, source_port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index c77218f173d1..dbbcdafed8c3 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -18,7 +18,7 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u8 *dsa_header; /* @@ -34,8 +34,8 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) * Construct tagged FROM_CPU DSA tag from 802.1q tag. */ dsa_header = skb->data + 2 * ETH_ALEN; - dsa_header[0] = 0x60 | p->dp->ds->index; - dsa_header[1] = p->dp->index << 3; + dsa_header[0] = 0x60 | dp->ds->index; + dsa_header[1] = dp->index << 3; /* * Move CFI field from byte 2 to byte 1. @@ -55,8 +55,8 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) * Construct untagged FROM_CPU DSA tag. */ dsa_header = skb->data + 2 * ETH_ALEN; - dsa_header[0] = 0x40 | p->dp->ds->index; - dsa_header[1] = p->dp->index << 3; + dsa_header[0] = 0x40 | dp->ds->index; + dsa_header[1] = dp->index << 3; dsa_header[2] = 0x00; dsa_header[3] = 0x00; } @@ -91,7 +91,7 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, source_device = dsa_header[0] & 0x1f; source_port = (dsa_header[1] >> 3) & 0x1f; - skb->dev = dsa_master_get_slave(dev, source_device, source_port); + skb->dev = dsa_master_find_slave(dev, source_device, source_port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index 0b83cbe0c9e8..f38a626b3a05 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -19,7 +19,7 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u8 *edsa_header; /* @@ -43,8 +43,8 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) edsa_header[1] = ETH_P_EDSA & 0xff; edsa_header[2] = 0x00; edsa_header[3] = 0x00; - edsa_header[4] = 0x60 | p->dp->ds->index; - edsa_header[5] = p->dp->index << 3; + edsa_header[4] = 0x60 | dp->ds->index; + edsa_header[5] = dp->index << 3; /* * Move CFI field from byte 6 to byte 5. @@ -68,8 +68,8 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) edsa_header[1] = ETH_P_EDSA & 0xff; edsa_header[2] = 0x00; edsa_header[3] = 0x00; - edsa_header[4] = 0x40 | p->dp->ds->index; - edsa_header[5] = p->dp->index << 3; + edsa_header[4] = 0x40 | dp->ds->index; + edsa_header[5] = dp->index << 3; edsa_header[6] = 0x00; edsa_header[7] = 0x00; } @@ -104,7 +104,7 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, source_device = edsa_header[0] & 0x1f; source_port = (edsa_header[1] >> 3) & 0x1f; - skb->dev = dsa_master_get_slave(dev, source_device, source_port); + skb->dev = dsa_master_find_slave(dev, source_device, source_port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index b241c990cde0..0f62effad88f 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -34,7 +34,7 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); struct sk_buff *nskb; int padlen; u8 *tag; @@ -72,7 +72,7 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); tag[0] = 0; - tag[1] = 1 << p->dp->index; /* destination port */ + tag[1] = 1 << dp->index; /* destination port */ return nskb; } @@ -87,7 +87,7 @@ static struct sk_buff *ksz_rcv(struct sk_buff *skb, struct net_device *dev, source_port = tag[0] & 7; - skb->dev = dsa_master_get_slave(dev, 0, source_port); + skb->dev = dsa_master_find_slave(dev, 0, source_port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index 4f211e56c81f..57519597c6fc 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -42,7 +42,7 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u16 *lan9303_tag; /* insert a special VLAN tag between the MAC addresses @@ -62,7 +62,7 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) lan9303_tag = (u16 *)(skb->data + 2 * ETH_ALEN); lan9303_tag[0] = htons(ETH_P_8021Q); - lan9303_tag[1] = htons(p->dp->index | BIT(4)); + lan9303_tag[1] = htons(dp->index | BIT(4)); return skb; } @@ -94,7 +94,7 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, source_port = ntohs(lan9303_tag[1]) & 0x3; - skb->dev = dsa_master_get_slave(dev, 0, source_port); + skb->dev = dsa_master_find_slave(dev, 0, source_port); if (!skb->dev) { dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid source port\n"); return NULL; diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index 968586c5d40e..8475434af7d5 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -23,7 +23,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u8 *mtk_tag; if (skb_cow_head(skb, MTK_HDR_LEN) < 0) @@ -36,7 +36,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, /* Build the tag after the MAC Source Address */ mtk_tag = skb->data + 2 * ETH_ALEN; mtk_tag[0] = 0; - mtk_tag[1] = (1 << p->dp->index) & MTK_HDR_XMIT_DP_BIT_MASK; + mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK; mtk_tag[2] = 0; mtk_tag[3] = 0; @@ -69,7 +69,7 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, /* Get source port information */ port = (hdr & MTK_HDR_RECV_SOURCE_PORT_MASK); - skb->dev = dsa_master_get_slave(dev, 0, port); + skb->dev = dsa_master_find_slave(dev, 0, port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 8d33d9ebf910..613f4ee97771 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -38,7 +38,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u16 *phdr, hdr; dev->stats.tx_packets++; @@ -54,8 +54,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) /* Set the version field, and set destination port information */ hdr = QCA_HDR_VERSION << QCA_HDR_XMIT_VERSION_S | - QCA_HDR_XMIT_FROM_CPU | - BIT(p->dp->index); + QCA_HDR_XMIT_FROM_CPU | BIT(dp->index); *phdr = htons(hdr); @@ -92,7 +91,7 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, /* Get source port information */ port = (hdr & QCA_HDR_RECV_SOURCE_PORT_MASK); - skb->dev = dsa_master_get_slave(dev, 0, port); + skb->dev = dsa_master_find_slave(dev, 0, port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 61668be267f5..7d20e1f3de28 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -16,7 +16,7 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); struct sk_buff *nskb; int padlen; u8 *trailer; @@ -48,7 +48,7 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) trailer = skb_put(nskb, 4); trailer[0] = 0x80; - trailer[1] = 1 << p->dp->index; + trailer[1] = 1 << dp->index; trailer[2] = 0x10; trailer[3] = 0x00; @@ -71,7 +71,7 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, source_port = trailer[1] & 7; - skb->dev = dsa_master_get_slave(dev, 0, source_port); + skb->dev = dsa_master_find_slave(dev, 0, source_port); if (!skb->dev) return NULL; diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index f85b08baff16..85bf86ad6b18 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -80,12 +80,13 @@ static void lowpan_frag_init(struct inet_frag_queue *q, const void *a) fq->daddr = *arg->dst; } -static void lowpan_frag_expire(unsigned long data) +static void lowpan_frag_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; struct net *net; - fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, ieee802154_lowpan.frags); spin_lock(&fq->q.lock); diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index 6bde9e5a5503..96636e3b7aa9 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -89,7 +89,7 @@ int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info) return genlmsg_reply(msg, info); } -static const struct genl_ops ieee8021154_ops[] = { +static const struct genl_ops ieee802154_ops[] = { /* see nl-phy.c */ IEEE802154_DUMP(IEEE802154_LIST_PHY, ieee802154_list_phy, ieee802154_dump_phy), @@ -137,8 +137,8 @@ struct genl_family nl802154_family __ro_after_init = { .version = 1, .maxattr = IEEE802154_ATTR_MAX, .module = THIS_MODULE, - .ops = ieee8021154_ops, - .n_ops = ARRAY_SIZE(ieee8021154_ops), + .ops = ieee802154_ops, + .n_ops = ARRAY_SIZE(ieee802154_ops), .mcgrps = ieee802154_mcgrps, .n_mcgrps = ARRAY_SIZE(ieee802154_mcgrps), }; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 43a1bbed7a42..ce4aa827be05 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -827,6 +827,7 @@ int inet_shutdown(struct socket *sock, int how) err = -ENOTCONN; /* Hack to wake up other listeners, who can poll for POLLHUP, even on eg. unconnected UDP sockets -- RR */ + /* fall through */ default: sk->sk_shutdown |= how; if (sk->sk_prot->shutdown) @@ -840,7 +841,7 @@ int inet_shutdown(struct socket *sock, int how) case TCP_LISTEN: if (!(how & RCV_SHUTDOWN)) break; - /* Fall through */ + /* fall through */ case TCP_SYN_SENT: err = sk->sk_prot->disconnect(sk, O_NONBLOCK); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 7c45b8896709..a8d7c5a9fb05 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1180,6 +1180,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCSARP: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; + /* fall through */ case SIOCGARP: err = copy_from_user(&r, arg, sizeof(struct arpreq)); if (err) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 7ce22a2c07ce..a4573bccd6da 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -444,7 +444,7 @@ static void check_lifetime(struct work_struct *work); static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime); static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, - u32 portid) + u32 portid, struct netlink_ext_ack *extack) { struct in_device *in_dev = ifa->ifa_dev; struct in_ifaddr *ifa1, **ifap, **last_primary; @@ -489,6 +489,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, */ ivi.ivi_addr = ifa->ifa_address; ivi.ivi_dev = ifa->ifa_dev; + ivi.extack = extack; ret = blocking_notifier_call_chain(&inetaddr_validator_chain, NETDEV_UP, &ivi); ret = notifier_to_errno(ret); @@ -521,7 +522,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, static int inet_insert_ifa(struct in_ifaddr *ifa) { - return __inet_insert_ifa(ifa, NULL, 0); + return __inet_insert_ifa(ifa, NULL, 0, NULL); } static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) @@ -902,7 +903,8 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, return ret; } } - return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid); + return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid, + extack); } else { inet_free_ifa(ifa); @@ -1522,6 +1524,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, if (inetdev_valid_mtu(dev->mtu)) break; /* disable IP when MTU is not enough */ + /* fall through */ case NETDEV_UNREGISTER: inetdev_destroy(in_dev); break; @@ -1757,7 +1760,7 @@ static int inet_validate_link_af(const struct net_device *dev, struct nlattr *a, *tb[IFLA_INET_MAX+1]; int err, rem; - if (dev && !__in_dev_get_rtnl(dev)) + if (dev && !__in_dev_get_rcu(dev)) return -EAFNOSUPPORT; err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy, NULL); @@ -1781,7 +1784,7 @@ static int inet_validate_link_af(const struct net_device *dev, static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla) { - struct in_device *in_dev = __in_dev_get_rtnl(dev); + struct in_device *in_dev = __in_dev_get_rcu(dev); struct nlattr *a, *tb[IFLA_INET_MAX+1]; int rem; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index c636650a6a70..aaa1ba09afaa 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -87,32 +87,30 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, enum fib_event_type event_type, u32 dst, - int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 tb_id) + int dst_len, struct fib_alias *fa) { struct fib_entry_notifier_info info = { .dst = dst, .dst_len = dst_len, - .fi = fi, - .tos = tos, - .type = type, - .tb_id = tb_id, + .fi = fa->fa_info, + .tos = fa->fa_tos, + .type = fa->fa_type, + .tb_id = fa->tb_id, }; return call_fib4_notifier(nb, net, event_type, &info.info); } static int call_fib_entry_notifiers(struct net *net, enum fib_event_type event_type, u32 dst, - int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 tb_id) + int dst_len, struct fib_alias *fa) { struct fib_entry_notifier_info info = { .dst = dst, .dst_len = dst_len, - .fi = fi, - .tos = tos, - .type = type, - .tb_id = tb_id, + .fi = fa->fa_info, + .tos = fa->fa_tos, + .type = fa->fa_type, + .tb_id = fa->tb_id, }; return call_fib4_notifiers(net, event_type, &info.info); } @@ -1216,9 +1214,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->fa_default = -1; call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, - key, plen, fi, - new_fa->fa_tos, cfg->fc_type, - tb->tb_id); + key, plen, new_fa); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, nlflags); @@ -1273,8 +1269,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, tb->tb_num_default++; rt_cache_flush(cfg->fc_nlinfo.nl_net); - call_fib_entry_notifiers(net, event, key, plen, fi, tos, cfg->fc_type, - tb->tb_id); + call_fib_entry_notifiers(net, event, key, plen, new_fa); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id, &cfg->fc_nlinfo, nlflags); succeeded: @@ -1574,8 +1569,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, return -ESRCH; call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, plen, - fa_to_delete->fa_info, tos, - fa_to_delete->fa_type, tb->tb_id); + fa_to_delete); rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id, &cfg->fc_nlinfo, 0); @@ -1892,9 +1886,7 @@ int fib_table_flush(struct net *net, struct fib_table *tb) call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, n->key, - KEYLENGTH - fa->fa_slen, - fi, fa->fa_tos, fa->fa_type, - tb->tb_id); + KEYLENGTH - fa->fa_slen, fa); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); @@ -1932,8 +1924,7 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l, continue; call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key, - KEYLENGTH - fa->fa_slen, fi, fa->fa_tos, - fa->fa_type, fa->tb_id); + KEYLENGTH - fa->fa_slen, fa); } } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 416bb304a281..1859c473b21a 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -86,7 +86,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, greh = (struct gre_base_hdr *)skb_transport_header(skb); pcsum = (__sum16 *)(greh + 1); - if (gso_partial) { + if (gso_partial && skb_is_gso(skb)) { unsigned int partial_adj; /* Adjust checksum to account for the fact that diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 681e33998e03..3c1570d3e22f 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -782,7 +782,7 @@ static bool icmp_tag_validation(int proto) } /* - * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and + * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEEDED, ICMP_QUENCH, and * ICMP_PARAMETERPROB. */ @@ -810,7 +810,8 @@ static bool icmp_unreach(struct sk_buff *skb) if (iph->ihl < 5) /* Mangled header, drop. */ goto out_err; - if (icmph->type == ICMP_DEST_UNREACH) { + switch (icmph->type) { + case ICMP_DEST_UNREACH: switch (icmph->code & 15) { case ICMP_NET_UNREACH: case ICMP_HOST_UNREACH: @@ -846,8 +847,16 @@ static bool icmp_unreach(struct sk_buff *skb) } if (icmph->code > NR_ICMP_UNREACH) goto out; - } else if (icmph->type == ICMP_PARAMETERPROB) + break; + case ICMP_PARAMETERPROB: info = ntohl(icmph->un.gateway) >> 24; + break; + case ICMP_TIME_EXCEEDED: + __ICMP_INC_STATS(net, ICMP_MIB_INTIMEEXCDS); + if (icmph->code == ICMP_EXC_FRAGTIME) + goto out; + break; + } /* * Throw it at our lower layers diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 8a91ebbf0c01..5c965ecc96a0 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -494,17 +494,15 @@ EXPORT_SYMBOL(inet_csk_accept); * to optimize. */ void inet_csk_init_xmit_timers(struct sock *sk, - void (*retransmit_handler)(unsigned long), - void (*delack_handler)(unsigned long), - void (*keepalive_handler)(unsigned long)) + void (*retransmit_handler)(struct timer_list *t), + void (*delack_handler)(struct timer_list *t), + void (*keepalive_handler)(struct timer_list *t)) { struct inet_connection_sock *icsk = inet_csk(sk); - setup_timer(&icsk->icsk_retransmit_timer, retransmit_handler, - (unsigned long)sk); - setup_timer(&icsk->icsk_delack_timer, delack_handler, - (unsigned long)sk); - setup_timer(&sk->sk_timer, keepalive_handler, (unsigned long)sk); + timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0); + timer_setup(&icsk->icsk_delack_timer, delack_handler, 0); + timer_setup(&sk->sk_timer, keepalive_handler, 0); icsk->icsk_pending = icsk->icsk_ack.pending = 0; } EXPORT_SYMBOL(inet_csk_init_xmit_timers); @@ -676,9 +674,9 @@ void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put); -static void reqsk_timer_handler(unsigned long data) +static void reqsk_timer_handler(struct timer_list *t) { - struct request_sock *req = (struct request_sock *)data; + struct request_sock *req = from_timer(req, t, rsk_timer); struct sock *sk_listener = req->rsk_listener; struct net *net = sock_net(sk_listener); struct inet_connection_sock *icsk = inet_csk(sk_listener); @@ -749,8 +747,7 @@ static void reqsk_queue_hash_req(struct request_sock *req, req->num_timeout = 0; req->sk = NULL; - setup_pinned_timer(&req->rsk_timer, reqsk_timer_handler, - (unsigned long)req); + timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); inet_ehash_insert(req_to_sk(req), NULL); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index af74d0433453..7f3ef5c287a1 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -147,7 +147,7 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb) spin_unlock(&hb->chain_lock); hlist_for_each_entry_safe(fq, n, &expired, list_evictor) - f->frag_expire((unsigned long) fq); + f->frag_expire(&fq->timer); return evicted; } @@ -366,7 +366,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, f->constructor(q, arg); add_frag_mem_limit(nf, f->qsize); - setup_timer(&q->timer, f->frag_expire, (unsigned long)q); + timer_setup(&q->timer, f->frag_expire, 0); spin_lock_init(&q->lock); refcount_set(&q->refcnt, 1); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 5b039159e67a..a4bab81f1462 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -142,9 +142,9 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, } EXPORT_SYMBOL_GPL(__inet_twsk_hashdance); -static void tw_timer_handler(unsigned long data) +static void tw_timer_handler(struct timer_list *t) { - struct inet_timewait_sock *tw = (struct inet_timewait_sock *)data; + struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer); if (tw->tw_kill) __NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED); @@ -188,8 +188,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, tw->tw_prot = sk->sk_prot_creator; atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie)); twsk_net_set(tw, sock_net(sk)); - setup_pinned_timer(&tw->tw_timer, tw_timer_handler, - (unsigned long)tw); + timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED); /* * Because we use RCU lookups, we should not set tw_refcnt * to a non null value before everything is setup for this diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 46408c220d9d..9215654a401f 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -190,12 +190,13 @@ static bool frag_expire_skip_icmp(u32 user) /* * Oops, a fragment queue timed out. Kill it and send an ICMP reply. */ -static void ip_expire(unsigned long arg) +static void ip_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct ipq *qp; struct net *net; - qp = container_of((struct inet_frag_queue *) arg, struct ipq, q); + qp = container_of(frag, struct ipq, q); net = container_of(qp->q.net, struct net, ipv4.frags); rcu_read_lock(); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index dc2317776499..c105a315b1a3 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -579,8 +579,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, if (gre_handle_offloads(skb, false)) goto err_free_rt; - if (skb->len > dev->mtu) { - pskb_trim(skb, dev->mtu); + if (skb->len > dev->mtu + dev->hard_header_len) { + pskb_trim(skb, dev->mtu + dev->hard_header_len); truncate = true; } @@ -731,8 +731,8 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; - if (skb->len - dev->hard_header_len > dev->mtu) { - pskb_trim(skb, dev->mtu); + if (skb->len > dev->mtu + dev->hard_header_len) { + pskb_trim(skb, dev->mtu + dev->hard_header_len); truncate = true; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index b3ee01b0551b..40a43ad294cb 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1528,6 +1528,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, case MRT_ADD_MFC: case MRT_DEL_MFC: parent = -1; + /* fall through */ case MRT_ADD_MFC_PROXY: case MRT_DEL_MFC_PROXY: if (optlen != sizeof(mfc)) { diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 811689e523c3..f75fc6b53115 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -330,7 +330,8 @@ static unsigned int ipv4_synproxy_hook(void *priv, if (synproxy == NULL) return NF_ACCEPT; - if (nf_is_loopback_packet(skb)) + if (nf_is_loopback_packet(skb) || + ip_hdr(skb)->protocol != IPPROTO_TCP) return NF_ACCEPT; thoff = ip_hdrlen(skb); diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index a0f37b208268..0443ca4120b0 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -276,7 +276,8 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, else return NF_ACCEPT; } - /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ + /* Only ICMPs can be IP_CT_IS_REPLY: */ + /* fall through */ case IP_CT_NEW: /* Seen it before? This can happen for loopback, retrans, * or local packets. diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 1c7ed77968c9..bc40bd411196 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1250,7 +1250,7 @@ static void set_class_tag(struct rtable *rt, u32 tag) static unsigned int ipv4_default_advmss(const struct dst_entry *dst) { unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr); - unsigned int advmss = max_t(unsigned int, dst->dev->mtu - header_size, + unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size, ip_rt_min_advmss); return min(advmss, IPV4_MAX_PMTU - header_size); @@ -2513,7 +2513,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or struct rtable *ort = (struct rtable *) dst_orig; struct rtable *rt; - rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, 0); + rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_DEAD, 0); if (rt) { struct dst_entry *new = &rt->dst; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index cac8dd309f39..81d218346cf7 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -284,7 +284,8 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, ret = -EINVAL; goto bad_key; } - tcp_fastopen_reset_cipher(net, user_key, TCP_FASTOPEN_KEY_LENGTH); + tcp_fastopen_reset_cipher(net, NULL, user_key, + TCP_FASTOPEN_KEY_LENGTH); } bad_key: diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8cf742fd4f99..8b1fa4dd4538 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -413,6 +413,7 @@ void tcp_init_sock(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); tp->out_of_order_queue = RB_ROOT; + sk->tcp_rtx_queue = RB_ROOT; tcp_init_xmit_timers(sk); INIT_LIST_HEAD(&tp->tsq_node); INIT_LIST_HEAD(&tp->tsorted_sent_queue); @@ -469,8 +470,10 @@ void tcp_init_transfer(struct sock *sk, int bpf_op) tcp_init_buffer_space(sk); } -static void tcp_tx_timestamp(struct sock *sk, u16 tsflags, struct sk_buff *skb) +static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) { + struct sk_buff *skb = tcp_write_queue_tail(sk); + if (tsflags && skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); @@ -699,10 +702,9 @@ static void tcp_push(struct sock *sk, int flags, int mss_now, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - if (!tcp_send_head(sk)) - return; - skb = tcp_write_queue_tail(sk); + if (!skb) + return; if (!(flags & MSG_MORE) || forced_push(tp)) tcp_mark_push(tp, skb); @@ -962,14 +964,14 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, int copy, i; bool can_coalesce; - if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0 || + if (!skb || (copy = size_goal - skb->len) <= 0 || !tcp_skb_can_collapse_to(skb)) { new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, - skb_queue_empty(&sk->sk_write_queue)); + tcp_rtx_and_write_queues_empty(sk)); if (!skb) goto wait_for_memory; @@ -1041,7 +1043,7 @@ wait_for_memory: out: if (copied) { - tcp_tx_timestamp(sk, sk->sk_tsflags, tcp_write_queue_tail(sk)); + tcp_tx_timestamp(sk, sk->sk_tsflags); if (!(flags & MSG_SENDPAGE_NOTLAST)) tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } @@ -1197,7 +1199,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) goto out_err; } - skb = tcp_send_head(sk) ? tcp_write_queue_tail(sk) : NULL; + skb = tcp_write_queue_tail(sk); uarg = sock_zerocopy_realloc(sk, size, skb_zcopy(skb)); if (!uarg) { err = -ENOBUFS; @@ -1273,7 +1275,7 @@ restart: int max = size_goal; skb = tcp_write_queue_tail(sk); - if (tcp_send_head(sk)) { + if (skb) { if (skb->ip_summed == CHECKSUM_NONE) max = mss_now; copy = max - skb->len; @@ -1293,7 +1295,7 @@ new_segment: process_backlog = false; goto restart; } - first_skb = skb_queue_empty(&sk->sk_write_queue); + first_skb = tcp_rtx_and_write_queues_empty(sk); skb = sk_stream_alloc_skb(sk, select_size(sk, sg, first_skb), sk->sk_allocation, @@ -1418,7 +1420,7 @@ wait_for_memory: out: if (copied) { - tcp_tx_timestamp(sk, sockc.tsflags, tcp_write_queue_tail(sk)); + tcp_tx_timestamp(sk, sockc.tsflags); tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } out_nopush: @@ -1519,6 +1521,13 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) /* XXX -- need to support SO_PEEK_OFF */ + skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { + err = skb_copy_datagram_msg(skb, 0, msg, skb->len); + if (err) + return err; + copied += skb->len; + } + skb_queue_walk(&sk->sk_write_queue, skb) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) @@ -2318,6 +2327,37 @@ static inline bool tcp_need_reset(int state) TCPF_FIN_WAIT2 | TCPF_SYN_RECV); } +static void tcp_rtx_queue_purge(struct sock *sk) +{ + struct rb_node *p = rb_first(&sk->tcp_rtx_queue); + + while (p) { + struct sk_buff *skb = rb_to_skb(p); + + p = rb_next(p); + /* Since we are deleting whole queue, no need to + * list_del(&skb->tcp_tsorted_anchor) + */ + tcp_rtx_queue_unlink(skb, sk); + sk_wmem_free_skb(sk, skb); + } +} + +void tcp_write_queue_purge(struct sock *sk) +{ + struct sk_buff *skb; + + tcp_chrono_stop(sk, TCP_CHRONO_BUSY); + while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { + tcp_skb_tsorted_anchor_cleanup(skb); + sk_wmem_free_skb(sk, skb); + } + tcp_rtx_queue_purge(sk); + INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); + sk_mem_reclaim(sk); + tcp_clear_all_retrans_hints(tcp_sk(sk)); +} + int tcp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); @@ -2376,7 +2416,6 @@ int tcp_disconnect(struct sock *sk, int flags) * issue in __tcp_select_window() */ icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; - tcp_init_send_head(sk); memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); dst_release(sk->sk_rx_dst); @@ -2532,6 +2571,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level, release_sock(sk); return err; } + case TCP_FASTOPEN_KEY: { + __u8 key[TCP_FASTOPEN_KEY_LENGTH]; + + if (optlen != sizeof(key)) + return -EINVAL; + + if (copy_from_user(key, optval, optlen)) + return -EFAULT; + + return tcp_fastopen_reset_cipher(net, sk, key, sizeof(key)); + } default: /* fallthru */ break; @@ -3118,6 +3168,28 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return -EFAULT; return 0; + case TCP_FASTOPEN_KEY: { + __u8 key[TCP_FASTOPEN_KEY_LENGTH]; + struct tcp_fastopen_context *ctx; + + if (get_user(len, optlen)) + return -EFAULT; + + rcu_read_lock(); + ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx); + if (ctx) + memcpy(key, ctx->key, sizeof(key)); + else + len = 0; + rcu_read_unlock(); + + len = min_t(unsigned int, len, sizeof(key)); + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, key, len)) + return -EFAULT; + return 0; + } case TCP_THIN_LINEAR_TIMEOUTS: val = tp->thin_lto; break; diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 66ac69f7bd19..06fbe102a425 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -389,7 +389,7 @@ static void tcp_cdg_release(struct sock *sk) kfree(ca->gradients); } -struct tcp_congestion_ops tcp_cdg __read_mostly = { +static struct tcp_congestion_ops tcp_cdg __read_mostly = { .cong_avoid = tcp_cdg_cong_avoid, .cwnd_event = tcp_cdg_cwnd_event, .pkts_acked = tcp_cdg_acked, diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 29fff14d5a53..21075ce19cb6 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -29,7 +29,7 @@ void tcp_fastopen_init_key_once(struct net *net) * for a valid cookie, so this is an acceptable risk. */ get_random_bytes(key, sizeof(key)); - tcp_fastopen_reset_cipher(net, key, sizeof(key)); + tcp_fastopen_reset_cipher(net, NULL, key, sizeof(key)); } static void tcp_fastopen_ctx_free(struct rcu_head *head) @@ -40,6 +40,16 @@ static void tcp_fastopen_ctx_free(struct rcu_head *head) kfree(ctx); } +void tcp_fastopen_destroy_cipher(struct sock *sk) +{ + struct tcp_fastopen_context *ctx; + + ctx = rcu_dereference_protected( + inet_csk(sk)->icsk_accept_queue.fastopenq.ctx, 1); + if (ctx) + call_rcu(&ctx->rcu, tcp_fastopen_ctx_free); +} + void tcp_fastopen_ctx_destroy(struct net *net) { struct tcp_fastopen_context *ctxt; @@ -55,10 +65,12 @@ void tcp_fastopen_ctx_destroy(struct net *net) call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free); } -int tcp_fastopen_reset_cipher(struct net *net, void *key, unsigned int len) +int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, + void *key, unsigned int len) { - int err; struct tcp_fastopen_context *ctx, *octx; + struct fastopen_queue *q; + int err; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -79,27 +91,39 @@ error: kfree(ctx); } memcpy(ctx->key, key, len); - spin_lock(&net->ipv4.tcp_fastopen_ctx_lock); - octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx, - lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock)); - rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx); - spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock); + if (sk) { + q = &inet_csk(sk)->icsk_accept_queue.fastopenq; + spin_lock_bh(&q->lock); + octx = rcu_dereference_protected(q->ctx, + lockdep_is_held(&q->lock)); + rcu_assign_pointer(q->ctx, ctx); + spin_unlock_bh(&q->lock); + } else { + spin_lock(&net->ipv4.tcp_fastopen_ctx_lock); + octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx, + lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock)); + rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx); + spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock); + } if (octx) call_rcu(&octx->rcu, tcp_fastopen_ctx_free); return err; } -static bool __tcp_fastopen_cookie_gen(struct net *net, - const void *path, +static bool __tcp_fastopen_cookie_gen(struct sock *sk, const void *path, struct tcp_fastopen_cookie *foc) { struct tcp_fastopen_context *ctx; bool ok = false; rcu_read_lock(); - ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx); + + ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx); + if (!ctx) + ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx); + if (ctx) { crypto_cipher_encrypt_one(ctx->tfm, foc->val, path); foc->len = TCP_FASTOPEN_COOKIE_SIZE; @@ -115,7 +139,7 @@ static bool __tcp_fastopen_cookie_gen(struct net *net, * * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE. */ -static bool tcp_fastopen_cookie_gen(struct net *net, +static bool tcp_fastopen_cookie_gen(struct sock *sk, struct request_sock *req, struct sk_buff *syn, struct tcp_fastopen_cookie *foc) @@ -124,7 +148,7 @@ static bool tcp_fastopen_cookie_gen(struct net *net, const struct iphdr *iph = ip_hdr(syn); __be32 path[4] = { iph->saddr, iph->daddr, 0, 0 }; - return __tcp_fastopen_cookie_gen(net, path, foc); + return __tcp_fastopen_cookie_gen(sk, path, foc); } #if IS_ENABLED(CONFIG_IPV6) @@ -132,13 +156,13 @@ static bool tcp_fastopen_cookie_gen(struct net *net, const struct ipv6hdr *ip6h = ipv6_hdr(syn); struct tcp_fastopen_cookie tmp; - if (__tcp_fastopen_cookie_gen(net, &ip6h->saddr, &tmp)) { + if (__tcp_fastopen_cookie_gen(sk, &ip6h->saddr, &tmp)) { struct in6_addr *buf = &tmp.addr; int i; for (i = 0; i < 4; i++) buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i]; - return __tcp_fastopen_cookie_gen(net, buf, foc); + return __tcp_fastopen_cookie_gen(sk, buf, foc); } } #endif @@ -313,7 +337,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, goto fastopen; if (foc->len >= 0 && /* Client presents or requests a cookie */ - tcp_fastopen_cookie_gen(sock_net(sk), req, skb, &valid_foc) && + tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc) && foc->len == TCP_FASTOPEN_COOKIE_SIZE && foc->len == valid_foc.len && !memcmp(foc->val, valid_foc.val, foc->len)) { @@ -465,17 +489,15 @@ bool tcp_fastopen_active_should_disable(struct sock *sk) void tcp_fastopen_active_disable_ofo_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct rb_node *p; - struct sk_buff *skb; struct dst_entry *dst; + struct sk_buff *skb; if (!tp->syn_fastopen) return; if (!tp->data_segs_in) { - p = rb_first(&tp->out_of_order_queue); - if (p && !rb_next(p)) { - skb = rb_entry(p, struct sk_buff, rbnode); + skb = skb_rb_first(&tp->out_of_order_queue); + if (skb && !skb_rb_next(skb)) { if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_fastopen_active_disable(sk); return; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index fb0d7ed84b94..b2390bfdc68f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1142,6 +1142,7 @@ struct tcp_sacktag_state { u64 last_sackt; struct rate_sample *rate; int flag; + unsigned int mss_now; }; /* Check if skb is fully within the SACK block. In presence of GSO skbs, @@ -1191,7 +1192,8 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, if (pkt_len >= skb->len && !in_sack) return 0; - err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC); + err = tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, + pkt_len, mss, GFP_ATOMIC); if (err < 0) return err; } @@ -1288,13 +1290,13 @@ static u8 tcp_sacktag_one(struct sock *sk, /* Shift newly-SACKed bytes from this skb to the immediately previous * already-SACKed sk_buff. Mark the newly-SACKed bytes as such. */ -static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, +static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev, + struct sk_buff *skb, struct tcp_sacktag_state *state, unsigned int pcount, int shifted, int mss, bool dup_sack) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *prev = tcp_write_queue_prev(sk, skb); u32 start_seq = TCP_SKB_CB(skb)->seq; /* start of newly-SACKed */ u32 end_seq = start_seq + shifted; /* end of newly-SACKed */ @@ -1363,8 +1365,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp)) TCP_SKB_CB(prev)->tx.delivered_mstamp = 0; - tcp_unlink_write_queue(skb, sk); - sk_wmem_free_skb(sk, skb); + tcp_rtx_queue_unlink_and_free(skb, sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKMERGED); @@ -1414,9 +1415,9 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, goto fallback; /* Can only happen with delayed DSACK + discard craziness */ - if (unlikely(skb == tcp_write_queue_head(sk))) + prev = skb_rb_prev(skb); + if (!prev) goto fallback; - prev = tcp_write_queue_prev(sk, skb); if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) goto fallback; @@ -1495,18 +1496,17 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, if (!skb_shift(prev, skb, len)) goto fallback; - if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack)) + if (!tcp_shifted_skb(sk, prev, skb, state, pcount, len, mss, dup_sack)) goto out; /* Hole filled allows collapsing with the next as well, this is very * useful when hole on every nth skb pattern happens */ - if (prev == tcp_write_queue_tail(sk)) + skb = skb_rb_next(prev); + if (!skb) goto out; - skb = tcp_write_queue_next(sk, prev); if (!skb_can_shift(skb) || - (skb == tcp_send_head(sk)) || ((TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) || (mss != tcp_skb_seglen(skb))) goto out; @@ -1514,7 +1514,8 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, len = skb->len; if (skb_shift(prev, skb, len)) { pcount += tcp_skb_pcount(skb); - tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0); + tcp_shifted_skb(sk, prev, skb, state, tcp_skb_pcount(skb), + len, mss, 0); } out: @@ -1538,13 +1539,10 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *tmp; - tcp_for_write_queue_from(skb, sk) { + skb_rbtree_walk_from(skb) { int in_sack = 0; bool dup_sack = dup_sack_in; - if (skb == tcp_send_head(sk)) - break; - /* queue is in-order => we can short-circuit the walk early */ if (!before(TCP_SKB_CB(skb)->seq, end_seq)) break; @@ -1606,23 +1604,44 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, return skb; } -/* Avoid all extra work that is being done by sacktag while walking in - * a normal way - */ +static struct sk_buff *tcp_sacktag_bsearch(struct sock *sk, + struct tcp_sacktag_state *state, + u32 seq) +{ + struct rb_node *parent, **p = &sk->tcp_rtx_queue.rb_node; + struct sk_buff *skb; + int unack_bytes; + + while (*p) { + parent = *p; + skb = rb_to_skb(parent); + if (before(seq, TCP_SKB_CB(skb)->seq)) { + p = &parent->rb_left; + continue; + } + if (!before(seq, TCP_SKB_CB(skb)->end_seq)) { + p = &parent->rb_right; + continue; + } + + state->fack_count = 0; + unack_bytes = TCP_SKB_CB(skb)->seq - tcp_sk(sk)->snd_una; + if (state->mss_now && unack_bytes > 0) + state->fack_count = unack_bytes / state->mss_now; + + return skb; + } + return NULL; +} + static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk, struct tcp_sacktag_state *state, u32 skip_to_seq) { - tcp_for_write_queue_from(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - - if (after(TCP_SKB_CB(skb)->end_seq, skip_to_seq)) - break; + if (skb && after(TCP_SKB_CB(skb)->seq, skip_to_seq)) + return skb; - state->fack_count += tcp_skb_pcount(skb); - } - return skb; + return tcp_sacktag_bsearch(sk, state, skip_to_seq); } static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb, @@ -1744,8 +1763,9 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, } } - skb = tcp_write_queue_head(sk); + state->mss_now = tcp_current_mss(sk); state->fack_count = 0; + skb = NULL; i = 0; if (!tp->sacked_out) { @@ -1969,7 +1989,7 @@ void tcp_enter_loss(struct sock *sk) if (tcp_is_reno(tp)) tcp_reset_reno_sack(tp); - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED); if (is_reneg) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING); @@ -1978,10 +1998,7 @@ void tcp_enter_loss(struct sock *sk) } tcp_clear_all_retrans_hints(tp); - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - + skb_rbtree_walk_from(skb) { mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || is_reneg); if (mark_lost) @@ -2207,20 +2224,18 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq; WARN_ON(packets > tp->packets_out); - if (tp->lost_skb_hint) { - skb = tp->lost_skb_hint; - cnt = tp->lost_cnt_hint; + skb = tp->lost_skb_hint; + if (skb) { /* Head already handled? */ - if (mark_head && skb != tcp_write_queue_head(sk)) + if (mark_head && after(TCP_SKB_CB(skb)->seq, tp->snd_una)) return; + cnt = tp->lost_cnt_hint; } else { - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); cnt = 0; } - tcp_for_write_queue_from(skb, sk) { - if (skb == tcp_send_head(sk)) - break; + skb_rbtree_walk_from(skb) { /* TODO: do this better */ /* this is not the most efficient way to do this... */ tp->lost_skb_hint = skb; @@ -2244,7 +2259,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) /* If needed, chop off the prefix to mark as lost. */ lost = (packets - oldcnt) * mss; if (lost < skb->len && - tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0) + tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, + lost, mss, GFP_ATOMIC) < 0) break; cnt = packets; } @@ -2328,7 +2344,7 @@ static bool tcp_any_retrans_done(const struct sock *sk) if (tp->retrans_out) return true; - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS)) return true; @@ -2369,9 +2385,7 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) if (unmark_loss) { struct sk_buff *skb; - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; + skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST; } tp->lost_out = 0; @@ -2616,9 +2630,7 @@ void tcp_simple_retransmit(struct sock *sk) unsigned int mss = tcp_current_mss(sk); u32 prior_lost = tp->lost_out; - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; + skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { if (tcp_skb_seglen(skb) > mss && !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) { if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { @@ -2712,7 +2724,7 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack, * is updated in tcp_ack()). Otherwise fall back to * the conventional recovery. */ - if (tcp_send_head(sk) && + if (!tcp_write_queue_empty(sk) && after(tcp_wnd_end(tp), tp->snd_nxt)) { *rexmit = REXMIT_NEW; return; @@ -2804,9 +2816,9 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && (tcp_fackets_out(tp) > tp->reordering)); - if (WARN_ON(!tp->packets_out && tp->sacked_out)) + if (!tp->packets_out && tp->sacked_out) tp->sacked_out = 0; - if (WARN_ON(!tp->sacked_out && tp->fackets_out)) + if (!tp->sacked_out && tp->fackets_out) tp->fackets_out = 0; /* Now state machine starts. @@ -2873,6 +2885,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, (*ack_flag & FLAG_LOST_RETRANS))) return; /* Change state if cwnd is undone or retransmits are lost */ + /* fall through */ default: if (tcp_is_reno(tp)) { if (flag & FLAG_SND_UNA_ADVANCED) @@ -3076,11 +3089,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, struct tcp_sock *tp = tcp_sk(sk); u32 prior_sacked = tp->sacked_out; u32 reord = tp->packets_out; + struct sk_buff *skb, *next; bool fully_acked = true; long sack_rtt_us = -1L; long seq_rtt_us = -1L; long ca_rtt_us = -1L; - struct sk_buff *skb; u32 pkts_acked = 0; u32 last_in_flight = 0; bool rtt_update; @@ -3088,7 +3101,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, first_ackt = 0; - while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { + for (skb = skb_rb_first(&sk->tcp_rtx_queue); skb; skb = next) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); u8 sacked = scb->sacked; u32 acked_pcount; @@ -3106,8 +3119,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, break; fully_acked = false; } else { - /* Speedup tcp_unlink_write_queue() and next loop */ - prefetchw(skb->next); acked_pcount = tcp_skb_pcount(skb); } @@ -3159,12 +3170,12 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (!fully_acked) break; - tcp_unlink_write_queue(skb, sk); - sk_wmem_free_skb(sk, skb); + next = skb_rb_next(skb); if (unlikely(skb == tp->retransmit_skb_hint)) tp->retransmit_skb_hint = NULL; if (unlikely(skb == tp->lost_skb_hint)) tp->lost_skb_hint = NULL; + tcp_rtx_queue_unlink_and_free(skb, sk); } if (!skb) @@ -3256,12 +3267,14 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, static void tcp_ack_probe(struct sock *sk) { - const struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct sk_buff *head = tcp_send_head(sk); + const struct tcp_sock *tp = tcp_sk(sk); /* Was it a usable window open? */ - - if (!after(TCP_SKB_CB(tcp_send_head(sk))->end_seq, tcp_wnd_end(tp))) { + if (!head) + return; + if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) { icsk->icsk_backoff = 0; inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0); /* Socket must be waked up by subsequent tcp_data_snd_check(). @@ -3381,7 +3394,7 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 tp->pred_flags = 0; tcp_fast_path_check(sk); - if (tcp_send_head(sk)) + if (!tcp_write_queue_empty(sk)) tcp_slow_start_after_idle_check(sk); if (nwin > tp->max_window) { @@ -3566,8 +3579,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) sack_state.first_sackt = 0; sack_state.rate = &rs; - /* We very likely will need to access write queue head. */ - prefetchw(sk->sk_write_queue.next); + /* We very likely will need to access rtx queue. */ + prefetch(sk->tcp_rtx_queue.rb_node); /* If the ack is older than previous acks * then we can probably ignore it. @@ -3681,8 +3694,7 @@ no_queue: * being used to time the probes, and is probably far higher than * it needs to be for normal retransmission. */ - if (tcp_send_head(sk)) - tcp_ack_probe(sk); + tcp_ack_probe(sk); if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); @@ -4335,7 +4347,7 @@ static void tcp_ofo_queue(struct sock *sk) p = rb_first(&tp->out_of_order_queue); while (p) { - skb = rb_entry(p, struct sk_buff, rbnode); + skb = rb_to_skb(p); if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) break; @@ -4399,7 +4411,7 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); - struct rb_node **p, *q, *parent; + struct rb_node **p, *parent; struct sk_buff *skb1; u32 seq, end_seq; bool fragstolen; @@ -4458,7 +4470,7 @@ coalesce_done: parent = NULL; while (*p) { parent = *p; - skb1 = rb_entry(parent, struct sk_buff, rbnode); + skb1 = rb_to_skb(parent); if (before(seq, TCP_SKB_CB(skb1)->seq)) { p = &parent->rb_left; continue; @@ -4503,9 +4515,7 @@ insert: merge_right: /* Remove other segments covered by skb. */ - while ((q = rb_next(&skb->rbnode)) != NULL) { - skb1 = rb_entry(q, struct sk_buff, rbnode); - + while ((skb1 = skb_rb_next(skb)) != NULL) { if (!after(end_seq, TCP_SKB_CB(skb1)->seq)) break; if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) { @@ -4520,7 +4530,7 @@ merge_right: tcp_drop(sk, skb1); } /* If there is no skb after us, we are the last_skb ! */ - if (!q) + if (!skb1) tp->ooo_last_skb = skb; add_sack: @@ -4706,7 +4716,7 @@ static struct sk_buff *tcp_skb_next(struct sk_buff *skb, struct sk_buff_head *li if (list) return !skb_queue_is_last(list, skb) ? skb->next : NULL; - return rb_entry_safe(rb_next(&skb->rbnode), struct sk_buff, rbnode); + return skb_rb_next(skb); } static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, @@ -4727,7 +4737,7 @@ static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, } /* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */ -static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) +void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -4735,7 +4745,7 @@ static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) while (*p) { parent = *p; - skb1 = rb_entry(parent, struct sk_buff, rbnode); + skb1 = rb_to_skb(parent); if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq)) p = &parent->rb_left; else @@ -4854,26 +4864,19 @@ static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb, *head; - struct rb_node *p; u32 start, end; - p = rb_first(&tp->out_of_order_queue); - skb = rb_entry_safe(p, struct sk_buff, rbnode); + skb = skb_rb_first(&tp->out_of_order_queue); new_range: if (!skb) { - p = rb_last(&tp->out_of_order_queue); - /* Note: This is possible p is NULL here. We do not - * use rb_entry_safe(), as ooo_last_skb is valid only - * if rbtree is not empty. - */ - tp->ooo_last_skb = rb_entry(p, struct sk_buff, rbnode); + tp->ooo_last_skb = skb_rb_last(&tp->out_of_order_queue); return; } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; for (head = skb;;) { - skb = tcp_skb_next(skb, NULL); + skb = skb_rb_next(skb); /* Range is terminated when we see a gap or when * we are at the queue end. @@ -4916,14 +4919,14 @@ static bool tcp_prune_ofo_queue(struct sock *sk) do { prev = rb_prev(node); rb_erase(node, &tp->out_of_order_queue); - tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode)); + tcp_drop(sk, rb_to_skb(node)); sk_mem_reclaim(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !tcp_under_memory_pressure(sk)) break; node = prev; } while (node); - tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode); + tp->ooo_last_skb = rb_to_skb(prev); /* Reset SACK state. A conforming SACK implementation will * do the same at a timeout based retransmit. When a connection @@ -5538,7 +5541,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, struct tcp_fastopen_cookie *cookie) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL; + struct sk_buff *data = tp->syn_data ? tcp_rtx_queue_head(sk) : NULL; u16 mss = tp->rx_opt.mss_clamp, try_exp = 0; bool syn_drop = false; @@ -5573,9 +5576,8 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp); if (data) { /* Retransmit unacked data in SYN */ - tcp_for_write_queue_from(data, sk) { - if (data == tcp_send_head(sk) || - __tcp_retransmit_skb(sk, data, 1)) + skb_rbtree_walk_from(data) { + if (__tcp_retransmit_skb(sk, data, 1)) break; } tcp_rearm_rto(sk); @@ -6043,6 +6045,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_LAST_ACK: if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) break; + /* fall through */ case TCP_FIN_WAIT1: case TCP_FIN_WAIT2: /* RFC 793 says to queue data in these states, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c7460fd90884..28ca4e177047 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -480,7 +480,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) TCP_TIMEOUT_INIT; icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); BUG_ON(!skb); tcp_mstamp_refresh(tp); @@ -1779,8 +1779,9 @@ do_time_wait: refcounted = false; goto process; } - /* Fall through to ACK */ } + /* to ACK */ + /* fall through */ case TCP_TW_ACK: tcp_v4_timewait_ack(sk, skb); break; @@ -1892,6 +1893,7 @@ void tcp_v4_destroy_sock(struct sock *sk) /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); + tcp_fastopen_destroy_cipher(sk); tcp_saved_syn_free(tp); sk_sockets_allocated_dec(sk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8162e2880178..988733f289c8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -42,6 +42,8 @@ #include <linux/gfp.h> #include <linux/module.h> +#include <trace/events/tcp.h> + /* People can turn this off for buggy TCP's found in printers etc. */ int sysctl_tcp_retrans_collapse __read_mostly = 1; @@ -66,15 +68,17 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); /* Account for new data that has been sent to the network. */ -static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) +static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; - tcp_advance_send_head(sk, skb); tp->snd_nxt = TCP_SKB_CB(skb)->end_seq; + __skb_unlink(skb, &sk->sk_write_queue); + tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); + tp->packets_out += tcp_skb_pcount(skb); if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); @@ -1249,12 +1253,25 @@ static void tcp_skb_fragment_eor(struct sk_buff *skb, struct sk_buff *skb2) TCP_SKB_CB(skb)->eor = 0; } +/* Insert buff after skb on the write or rtx queue of sk. */ +static void tcp_insert_write_queue_after(struct sk_buff *skb, + struct sk_buff *buff, + struct sock *sk, + enum tcp_queue tcp_queue) +{ + if (tcp_queue == TCP_FRAG_IN_WRITE_QUEUE) + __skb_queue_after(&sk->sk_write_queue, skb, buff); + else + tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); +} + /* Function to create two new TCP segments. Shrinks the given segment * to the specified size and appends a new segment with the rest of the * packet to the list. This won't be called frequently, I hope. * Remember, these are still headerless SKBs at this point. */ -int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, +int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, + struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); @@ -1337,7 +1354,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, /* Link BUFF into the send queue. */ __skb_header_release(buff); - tcp_insert_write_queue_after(skb, buff, sk); + tcp_insert_write_queue_after(skb, buff, sk, tcp_queue); list_add(&buff->tcp_tsorted_anchor, &skb->tcp_tsorted_anchor); return 0; @@ -1625,10 +1642,10 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) * is caused by insufficient sender buffer: * 1) just sent some data (see tcp_write_xmit) * 2) not cwnd limited (this else condition) - * 3) no more data to send (null tcp_send_head ) + * 3) no more data to send (tcp_write_queue_empty()) * 4) application is hitting buffer limit (SOCK_NOSPACE) */ - if (!tcp_send_head(sk) && sk->sk_socket && + if (tcp_write_queue_empty(sk) && sk->sk_socket && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags) && (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) tcp_chrono_start(sk, TCP_CHRONO_SNDBUF_LIMITED); @@ -1824,7 +1841,8 @@ static bool tcp_snd_wnd_test(const struct tcp_sock *tp, * know that all the data is in scatter-gather pages, and that the * packet has never been sent out before (and thus is not cloned). */ -static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, +static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue, + struct sk_buff *skb, unsigned int len, unsigned int mss_now, gfp_t gfp) { struct sk_buff *buff; @@ -1833,7 +1851,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, /* All of a TSO frame must be composed of paged data. */ if (skb->len != skb->data_len) - return tcp_fragment(sk, skb, len, mss_now, gfp); + return tcp_fragment(sk, tcp_queue, skb, len, mss_now, gfp); buff = sk_stream_alloc_skb(sk, 0, gfp, true); if (unlikely(!buff)) @@ -1869,7 +1887,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, /* Link BUFF into the send queue. */ __skb_header_release(buff); - tcp_insert_write_queue_after(skb, buff, sk); + tcp_insert_write_queue_after(skb, buff, sk, tcp_queue); return 0; } @@ -1939,8 +1957,10 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, goto send_now; } - head = tcp_write_queue_head(sk); - + /* TODO : use tsorted_sent_queue ? */ + head = tcp_rtx_queue_head(sk); + if (!head) + goto send_now; age = tcp_stamp_us_delta(tp->tcp_mstamp, head->skb_mstamp); /* If next ACK is likely to come too late (half srtt), do not defer */ if (age < (tp->srtt_us >> 4)) @@ -2158,13 +2178,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit <<= factor; if (refcount_read(&sk->sk_wmem_alloc) > limit) { - /* Always send the 1st or 2nd skb in write queue. + /* Always send skb if rtx queue is empty. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. * This helps when TX completions are delayed too much. */ - if (skb == sk->sk_write_queue.next || - skb->prev == sk->sk_write_queue.next) + if (tcp_rtx_queue_empty(sk)) return false; set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); @@ -2215,7 +2234,7 @@ void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type) * it's the "most interesting" or current chrono we are * tracking and starts busy chrono if we have pending data. */ - if (tcp_write_queue_empty(sk)) + if (tcp_rtx_and_write_queues_empty(sk)) tcp_chrono_set(tp, TCP_CHRONO_UNSPEC); else if (type == tp->chrono_type) tcp_chrono_set(tp, TCP_CHRONO_BUSY); @@ -2310,7 +2329,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, nonagle); if (skb->len > limit && - unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) + unlikely(tso_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, + skb, limit, mss_now, gfp))) break; if (test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) @@ -2350,7 +2370,7 @@ repair: tcp_cwnd_validate(sk, is_cwnd_limited); return false; } - return !tp->packets_out && tcp_send_head(sk); + return !tp->packets_out && !tcp_write_queue_empty(sk); } bool tcp_schedule_loss_probe(struct sock *sk) @@ -2374,7 +2394,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) return false; if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) && - tcp_send_head(sk)) + !tcp_write_queue_empty(sk)) return false; /* Probe timeout is 2*rtt. Add minimum RTO to account @@ -2427,18 +2447,14 @@ void tcp_send_loss_probe(struct sock *sk) int mss = tcp_current_mss(sk); skb = tcp_send_head(sk); - if (skb) { - if (tcp_snd_wnd_test(tp, skb, mss)) { - pcount = tp->packets_out; - tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); - if (tp->packets_out > pcount) - goto probe_sent; - goto rearm_timer; - } - skb = tcp_write_queue_prev(sk, skb); - } else { - skb = tcp_write_queue_tail(sk); + if (skb && tcp_snd_wnd_test(tp, skb, mss)) { + pcount = tp->packets_out; + tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); + if (tp->packets_out > pcount) + goto probe_sent; + goto rearm_timer; } + skb = skb_rb_last(&sk->tcp_rtx_queue); /* At most one outstanding TLP retransmission. */ if (tp->tlp_high_seq) @@ -2456,10 +2472,11 @@ void tcp_send_loss_probe(struct sock *sk) goto rearm_timer; if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) { - if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss, + if (unlikely(tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, + (pcount - 1) * mss, mss, GFP_ATOMIC))) goto rearm_timer; - skb = tcp_write_queue_next(sk, skb); + skb = skb_rb_next(skb); } if (WARN_ON(!skb || !tcp_skb_pcount(skb))) @@ -2659,7 +2676,7 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb, static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *next_skb = tcp_write_queue_next(sk, skb); + struct sk_buff *next_skb = skb_rb_next(skb); int skb_size, next_skb_size; skb_size = skb->len; @@ -2676,8 +2693,6 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) } tcp_highest_sack_combine(sk, next_skb, skb); - tcp_unlink_write_queue(next_skb, sk); - if (next_skb->ip_summed == CHECKSUM_PARTIAL) skb->ip_summed = CHECKSUM_PARTIAL; @@ -2705,7 +2720,7 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) tcp_skb_collapse_tstamp(skb, next_skb); - sk_wmem_free_skb(sk, next_skb); + tcp_rtx_queue_unlink_and_free(next_skb, sk); return true; } @@ -2716,8 +2731,6 @@ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) return false; if (skb_cloned(skb)) return false; - if (skb == tcp_send_head(sk)) - return false; /* Some heuristics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) return false; @@ -2740,7 +2753,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) return; - tcp_for_write_queue_from_safe(skb, tmp, sk) { + skb_rbtree_walk_from_safe(skb, tmp) { if (!tcp_can_collapse(sk, skb)) break; @@ -2815,7 +2828,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) len = cur_mss * segs; if (skb->len > len) { - if (tcp_fragment(sk, skb, len, cur_mss, GFP_ATOMIC)) + if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len, + cur_mss, GFP_ATOMIC)) return -ENOMEM; /* We'll try again later. */ } else { if (skb_unclone(skb, GFP_ATOMIC)) @@ -2863,6 +2877,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (likely(!err)) { TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + trace_tcp_retransmit_skb(sk, skb); } else if (err != -EBUSY) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); } @@ -2906,29 +2921,21 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) void tcp_xmit_retransmit_queue(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); + struct sk_buff *skb, *rtx_head, *hole = NULL; struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - struct sk_buff *hole = NULL; u32 max_segs; int mib_idx; if (!tp->packets_out) return; - if (tp->retransmit_skb_hint) { - skb = tp->retransmit_skb_hint; - } else { - skb = tcp_write_queue_head(sk); - } - + rtx_head = tcp_rtx_queue_head(sk); + skb = tp->retransmit_skb_hint ?: rtx_head; max_segs = tcp_tso_segs(sk, tcp_current_mss(sk)); - tcp_for_write_queue_from(skb, sk) { + skb_rbtree_walk_from(skb) { __u8 sacked; int segs; - if (skb == tcp_send_head(sk)) - break; - if (tcp_pacing_check(sk)) break; @@ -2973,7 +2980,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) if (tcp_in_cwnd_reduction(sk)) tp->prr_out += tcp_skb_pcount(skb); - if (skb == tcp_write_queue_head(sk) && + if (skb == rtx_head && icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT) inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, @@ -3015,12 +3022,15 @@ void tcp_send_fin(struct sock *sk) * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ - if (tskb && (tcp_send_head(sk) || tcp_under_memory_pressure(sk))) { + if (!tskb && tcp_under_memory_pressure(sk)) + tskb = skb_rb_last(&sk->tcp_rtx_queue); + + if (tskb) { coalesce: TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; - if (!tcp_send_head(sk)) { + if (tcp_write_queue_empty(sk)) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have @@ -3086,9 +3096,9 @@ int tcp_send_synack(struct sock *sk) { struct sk_buff *skb; - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { - pr_debug("%s: wrong queue state\n", __func__); + pr_err("%s: wrong queue state\n", __func__); return -EFAULT; } if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { @@ -3101,10 +3111,9 @@ int tcp_send_synack(struct sock *sk) if (!nskb) return -ENOMEM; INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor); - tcp_unlink_write_queue(skb, sk); + tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); - __tcp_add_write_queue_head(sk, nskb); - sk_wmem_free_skb(sk, skb); + tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); sk->sk_wmem_queued += nskb->truesize; sk_mem_charge(sk, nskb->truesize); skb = nskb; @@ -3327,7 +3336,6 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) tcb->end_seq += skb->len; __skb_header_release(skb); - __tcp_add_write_queue_tail(sk, skb); sk->sk_wmem_queued += skb->truesize; sk_mem_charge(sk, skb->truesize); tp->write_seq = tcb->end_seq; @@ -3375,6 +3383,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) int copied = copy_from_iter(skb_put(syn_data, space), space, &fo->data->msg_iter); if (unlikely(!copied)) { + tcp_skb_tsorted_anchor_cleanup(syn_data); kfree_skb(syn_data); goto fallback; } @@ -3405,12 +3414,13 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH; if (!err) { tp->syn_data = (fo->copied > 0); + tcp_rbtree_insert(&sk->tcp_rtx_queue, syn_data); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT); goto done; } - /* data was not sent, this is our new send_head */ - sk->sk_send_head = syn_data; + /* data was not sent, put it in write_queue */ + __skb_queue_tail(&sk->sk_write_queue, syn_data); tp->packets_out -= tcp_skb_pcount(syn_data); fallback: @@ -3453,6 +3463,7 @@ int tcp_connect(struct sock *sk) tp->retrans_stamp = tcp_time_stamp(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); + tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); /* Send off SYN; include data in Fast Open. */ err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) : @@ -3647,7 +3658,8 @@ int tcp_write_wakeup(struct sock *sk, int mib) skb->len > mss) { seg_size = min(seg_size, mss); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; - if (tcp_fragment(sk, skb, seg_size, mss, GFP_ATOMIC)) + if (tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, + skb, seg_size, mss, GFP_ATOMIC)) return -1; } else if (!tcp_skb_pcount(skb)) tcp_set_skb_tso_segs(skb, mss); @@ -3677,7 +3689,7 @@ void tcp_send_probe0(struct sock *sk) err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE); - if (tp->packets_out || !tcp_send_head(sk)) { + if (tp->packets_out || tcp_write_queue_empty(sk)) { /* Cancel probe timer, if it is not required. */ icsk->icsk_probes_out = 0; icsk->icsk_backoff = 0; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 655dd8d7f064..804a8d34ce86 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -156,8 +156,13 @@ static bool retransmits_timed_out(struct sock *sk, return false; start_ts = tcp_sk(sk)->retrans_stamp; - if (unlikely(!start_ts)) - start_ts = tcp_skb_timestamp(tcp_write_queue_head(sk)); + if (unlikely(!start_ts)) { + struct sk_buff *head = tcp_rtx_queue_head(sk); + + if (!head) + return false; + start_ts = tcp_skb_timestamp(head); + } if (likely(timeout == 0)) { linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); @@ -283,15 +288,17 @@ out: * * Returns: Nothing (void) */ -static void tcp_delack_timer(unsigned long data) +static void tcp_delack_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; + struct inet_connection_sock *icsk = + from_timer(icsk, t, icsk_delack_timer); + struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { tcp_delack_timer_handler(sk); } else { - inet_csk(sk)->icsk_ack.blocked = 1; + icsk->icsk_ack.blocked = 1; __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); /* deleguate our work to tcp_release_cb() */ if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags)) @@ -304,11 +311,12 @@ static void tcp_delack_timer(unsigned long data) static void tcp_probe_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct sk_buff *skb = tcp_send_head(sk); struct tcp_sock *tp = tcp_sk(sk); int max_probes; u32 start_ts; - if (tp->packets_out || !tcp_send_head(sk)) { + if (tp->packets_out || !skb) { icsk->icsk_probes_out = 0; return; } @@ -321,9 +329,9 @@ static void tcp_probe_timer(struct sock *sk) * corresponding system limit. We also implement similar policy when * we use RTO to probe window in tcp_retransmit_timer(). */ - start_ts = tcp_skb_timestamp(tcp_send_head(sk)); + start_ts = tcp_skb_timestamp(skb); if (!start_ts) - tcp_send_head(sk)->skb_mstamp = tp->tcp_mstamp; + skb->skb_mstamp = tp->tcp_mstamp; else if (icsk->icsk_user_timeout && (s32)(tcp_time_stamp(tp) - start_ts) > jiffies_to_msecs(icsk->icsk_user_timeout)) @@ -408,7 +416,7 @@ void tcp_retransmit_timer(struct sock *sk) if (!tp->packets_out) goto out; - WARN_ON(tcp_write_queue_empty(sk)); + WARN_ON(tcp_rtx_queue_empty(sk)); tp->tlp_high_seq = 0; @@ -441,7 +449,7 @@ void tcp_retransmit_timer(struct sock *sk) goto out; } tcp_enter_loss(sk); - tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1); + tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1); __sk_dst_reset(sk); goto out_reset_timer; } @@ -473,7 +481,7 @@ void tcp_retransmit_timer(struct sock *sk) tcp_enter_loss(sk); - if (tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1) > 0) { + if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) { /* Retransmission failed because of local congestion, * do not backoff. */ @@ -570,9 +578,11 @@ out: sk_mem_reclaim(sk); } -static void tcp_write_timer(unsigned long data) +static void tcp_write_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; + struct inet_connection_sock *icsk = + from_timer(icsk, t, icsk_retransmit_timer); + struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { @@ -607,9 +617,9 @@ void tcp_set_keepalive(struct sock *sk, int val) EXPORT_SYMBOL_GPL(tcp_set_keepalive); -static void tcp_keepalive_timer (unsigned long data) +static void tcp_keepalive_timer (struct timer_list *t) { - struct sock *sk = (struct sock *) data; + struct sock *sk = from_timer(sk, t, sk_timer); struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 elapsed; @@ -647,7 +657,7 @@ static void tcp_keepalive_timer (unsigned long data) elapsed = keepalive_time_when(tp); /* It is alive without keepalive 8) */ - if (tp->packets_out || tcp_send_head(sk)) + if (tp->packets_out || !tcp_write_queue_empty(sk)) goto resched; elapsed = keepalive_time_elapsed(tp); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index eb0359bdaa11..7c9a6e4a7253 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2239,20 +2239,16 @@ int udp_v4_early_demux(struct sk_buff *skb) iph = ip_hdr(skb); uh = udp_hdr(skb); - if (skb->pkt_type == PACKET_BROADCAST || - skb->pkt_type == PACKET_MULTICAST) { + if (skb->pkt_type == PACKET_MULTICAST) { in_dev = __in_dev_get_rcu(skb->dev); if (!in_dev) return 0; - /* we are supposed to accept bcast packets */ - if (skb->pkt_type == PACKET_MULTICAST) { - ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, - iph->protocol); - if (!ours) - return 0; - } + ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, + iph->protocol); + if (!ours) + return 0; sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 97658bfc1b58..e360d55be555 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -120,7 +120,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, * will be using a length value equal to only one MSS sized * segment instead of the entire frame. */ - if (gso_partial) { + if (gso_partial && skb_is_gso(skb)) { uh->len = htons(skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)uh); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 837418ff2d4b..93f9c0a61911 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -152,7 +152,7 @@ static void ipv6_regen_rndid(struct inet6_dev *idev); static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr); static int ipv6_generate_eui64(u8 *eui, struct net_device *dev); -static int ipv6_count_addresses(struct inet6_dev *idev); +static int ipv6_count_addresses(const struct inet6_dev *idev); static int ipv6_generate_stable_address(struct in6_addr *addr, u8 dad_count, const struct inet6_dev *idev); @@ -616,23 +616,23 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX+1]; + struct inet6_dev *in6_dev = NULL; + struct net_device *dev = NULL; struct netconfmsg *ncm; struct sk_buff *skb; struct ipv6_devconf *devconf; - struct inet6_dev *in6_dev; - struct net_device *dev; int ifindex; int err; err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, devconf_ipv6_policy, extack); if (err < 0) - goto errout; + return err; - err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) - goto errout; + return -EINVAL; + err = -EINVAL; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); switch (ifindex) { case NETCONFA_IFINDEX_ALL: @@ -642,10 +642,10 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, devconf = net->ipv6.devconf_dflt; break; default: - dev = __dev_get_by_index(net, ifindex); + dev = dev_get_by_index(net, ifindex); if (!dev) - goto errout; - in6_dev = __in6_dev_get(dev); + return -EINVAL; + in6_dev = in6_dev_get(dev); if (!in6_dev) goto errout; devconf = &in6_dev->cnf; @@ -653,7 +653,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, } err = -ENOBUFS; - skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_ATOMIC); + skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); if (!skb) goto errout; @@ -669,6 +669,10 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: + if (in6_dev) + in6_dev_put(in6_dev); + if (dev) + dev_put(dev); return err; } @@ -945,7 +949,7 @@ ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) break; } - list_add_tail(&ifp->if_list, p); + list_add_tail_rcu(&ifp->if_list, p); } static u32 inet6_addr_hash(const struct in6_addr *addr) @@ -953,18 +957,42 @@ static u32 inet6_addr_hash(const struct in6_addr *addr) return hash_32(ipv6_addr_hash(addr), IN6_ADDR_HSIZE_SHIFT); } +static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa) +{ + unsigned int hash; + int err = 0; + + spin_lock(&addrconf_hash_lock); + + /* Ignore adding duplicate addresses on an interface */ + if (ipv6_chk_same_addr(dev_net(dev), &ifa->addr, dev)) { + ADBG("ipv6_add_addr: already assigned\n"); + err = -EEXIST; + goto out; + } + + /* Add to big hash table */ + hash = inet6_addr_hash(&ifa->addr); + hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]); + +out: + spin_unlock(&addrconf_hash_lock); + + return err; +} + /* On success it returns ifp with increased reference count */ static struct inet6_ifaddr * ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, const struct in6_addr *peer_addr, int pfxlen, - int scope, u32 flags, u32 valid_lft, u32 prefered_lft) + int scope, u32 flags, u32 valid_lft, u32 prefered_lft, + bool can_block, struct netlink_ext_ack *extack) { + gfp_t gfp_flags = can_block ? GFP_KERNEL : GFP_ATOMIC; struct net *net = dev_net(idev->dev); struct inet6_ifaddr *ifa = NULL; - struct rt6_info *rt; - struct in6_validator_info i6vi; - unsigned int hash; + struct rt6_info *rt = NULL; int err = 0; int addr_type = ipv6_addr_type(addr); @@ -974,42 +1002,33 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, addr_type & IPV6_ADDR_LOOPBACK)) return ERR_PTR(-EADDRNOTAVAIL); - rcu_read_lock_bh(); - - in6_dev_hold(idev); - if (idev->dead) { err = -ENODEV; /*XXX*/ - goto out2; + goto out; } if (idev->cnf.disable_ipv6) { err = -EACCES; - goto out2; - } - - i6vi.i6vi_addr = *addr; - i6vi.i6vi_dev = idev; - rcu_read_unlock_bh(); - - err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi); - - rcu_read_lock_bh(); - err = notifier_to_errno(err); - if (err) - goto out2; - - spin_lock(&addrconf_hash_lock); - - /* Ignore adding duplicate addresses on an interface */ - if (ipv6_chk_same_addr(dev_net(idev->dev), addr, idev->dev)) { - ADBG("ipv6_add_addr: already assigned\n"); - err = -EEXIST; goto out; } - ifa = kzalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC); + /* validator notifier needs to be blocking; + * do not call in atomic context + */ + if (can_block) { + struct in6_validator_info i6vi = { + .i6vi_addr = *addr, + .i6vi_dev = idev, + .extack = extack, + }; + + err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi); + err = notifier_to_errno(err); + if (err < 0) + goto out; + } + ifa = kzalloc(sizeof(*ifa), gfp_flags); if (!ifa) { ADBG("ipv6_add_addr: malloc failed\n"); err = -ENOBUFS; @@ -1019,6 +1038,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, rt = addrconf_dst_alloc(idev, addr, false); if (IS_ERR(rt)) { err = PTR_ERR(rt); + rt = NULL; goto out; } @@ -1049,16 +1069,21 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifa->rt = rt; ifa->idev = idev; + in6_dev_hold(idev); + /* For caller */ refcount_set(&ifa->refcnt, 1); - /* Add to big hash table */ - hash = inet6_addr_hash(addr); + rcu_read_lock_bh(); - hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]); - spin_unlock(&addrconf_hash_lock); + err = ipv6_add_addr_hash(idev->dev, ifa); + if (err < 0) { + rcu_read_unlock_bh(); + goto out; + } write_lock(&idev->lock); + /* Add to inet6_dev unicast addr list. */ ipv6_link_dev_addr(idev, ifa); @@ -1069,21 +1094,23 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, in6_ifa_hold(ifa); write_unlock(&idev->lock); -out2: + rcu_read_unlock_bh(); - if (likely(err == 0)) - inet6addr_notifier_call_chain(NETDEV_UP, ifa); - else { - kfree(ifa); - in6_dev_put(idev); + inet6addr_notifier_call_chain(NETDEV_UP, ifa); +out: + if (unlikely(err < 0)) { + if (rt) + ip6_rt_put(rt); + if (ifa) { + if (ifa->idev) + in6_dev_put(ifa->idev); + kfree(ifa); + } ifa = ERR_PTR(err); } return ifa; -out: - spin_unlock(&addrconf_hash_lock); - goto out2; } enum cleanup_prefix_rt_t { @@ -1204,7 +1231,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if (ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE)) action = check_cleanup_prefix_route(ifp, &expires); - list_del_init(&ifp->if_list); + list_del_rcu(&ifp->if_list); __in6_ifa_put(ifp); write_unlock_bh(&ifp->idev->lock); @@ -1330,7 +1357,7 @@ retry: ift = ipv6_add_addr(idev, &addr, NULL, tmp_plen, ipv6_addr_scope(&addr), addr_flags, - tmp_valid_lft, tmp_prefered_lft); + tmp_valid_lft, tmp_prefered_lft, true, NULL); if (IS_ERR(ift)) { in6_ifa_put(ifp); in6_dev_put(idev); @@ -1558,8 +1585,7 @@ static int __ipv6_dev_get_saddr(struct net *net, { struct ipv6_saddr_score *score = &scores[1 - hiscore_idx], *hiscore = &scores[hiscore_idx]; - read_lock_bh(&idev->lock); - list_for_each_entry(score->ifa, &idev->addr_list, if_list) { + list_for_each_entry_rcu(score->ifa, &idev->addr_list, if_list) { int i; /* @@ -1609,11 +1635,6 @@ static int __ipv6_dev_get_saddr(struct net *net, } break; } else if (minihiscore < miniscore) { - if (hiscore->ifa) - in6_ifa_put(hiscore->ifa); - - in6_ifa_hold(score->ifa); - swap(hiscore, score); hiscore_idx = 1 - hiscore_idx; @@ -1625,7 +1646,6 @@ static int __ipv6_dev_get_saddr(struct net *net, } } out: - read_unlock_bh(&idev->lock); return hiscore_idx; } @@ -1662,6 +1682,7 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, int dst_type; bool use_oif_addr = false; int hiscore_idx = 0; + int ret = 0; dst_type = __ipv6_addr_type(daddr); dst.addr = daddr; @@ -1737,15 +1758,14 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, } out: - rcu_read_unlock(); - hiscore = &scores[hiscore_idx]; if (!hiscore->ifa) - return -EADDRNOTAVAIL; + ret = -EADDRNOTAVAIL; + else + *saddr = hiscore->ifa->addr; - *saddr = hiscore->ifa->addr; - in6_ifa_put(hiscore->ifa); - return 0; + rcu_read_unlock(); + return ret; } EXPORT_SYMBOL(ipv6_dev_get_saddr); @@ -1785,15 +1805,15 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, return err; } -static int ipv6_count_addresses(struct inet6_dev *idev) +static int ipv6_count_addresses(const struct inet6_dev *idev) { + const struct inet6_ifaddr *ifp; int cnt = 0; - struct inet6_ifaddr *ifp; - read_lock_bh(&idev->lock); - list_for_each_entry(ifp, &idev->addr_list, if_list) + rcu_read_lock(); + list_for_each_entry_rcu(ifp, &idev->addr_list, if_list) cnt++; - read_unlock_bh(&idev->lock); + rcu_read_unlock(); return cnt; } @@ -1859,20 +1879,18 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, bool ipv6_chk_custom_prefix(const struct in6_addr *addr, const unsigned int prefix_len, struct net_device *dev) { - struct inet6_dev *idev; - struct inet6_ifaddr *ifa; + const struct inet6_ifaddr *ifa; + const struct inet6_dev *idev; bool ret = false; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { - read_lock_bh(&idev->lock); - list_for_each_entry(ifa, &idev->addr_list, if_list) { + list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len); if (ret) break; } - read_unlock_bh(&idev->lock); } rcu_read_unlock(); @@ -1882,22 +1900,20 @@ EXPORT_SYMBOL(ipv6_chk_custom_prefix); int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) { - struct inet6_dev *idev; - struct inet6_ifaddr *ifa; + const struct inet6_ifaddr *ifa; + const struct inet6_dev *idev; int onlink; onlink = 0; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { - read_lock_bh(&idev->lock); - list_for_each_entry(ifa, &idev->addr_list, if_list) { + list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { onlink = ipv6_prefix_equal(addr, &ifa->addr, ifa->prefix_len); if (onlink) break; } - read_unlock_bh(&idev->lock); } rcu_read_unlock(); return onlink; @@ -2025,7 +2041,7 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) ifp2 = ipv6_add_addr(idev, &new_addr, NULL, pfxlen, scope, flags, valid_lft, - preferred_lft); + preferred_lft, false, NULL); if (IS_ERR(ifp2)) goto lock_errdad; @@ -2321,24 +2337,24 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, if (!table) return NULL; - read_lock_bh(&table->tb6_lock); - fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0); + rcu_read_lock(); + fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0, true); if (!fn) goto out; - noflags |= RTF_CACHE; - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_node_rt_rcu(fn) { if (rt->dst.dev->ifindex != dev->ifindex) continue; if ((rt->rt6i_flags & flags) != flags) continue; if ((rt->rt6i_flags & noflags) != 0) continue; - dst_hold(&rt->dst); + if (!dst_hold_safe(&rt->dst)) + rt = NULL; break; } out: - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); return rt; } @@ -2483,7 +2499,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, pinfo->prefix_len, addr_type&IPV6_ADDR_SCOPE_MASK, addr_flags, valid_lft, - prefered_lft); + prefered_lft, false, NULL); if (IS_ERR_OR_NULL(ifp)) return -1; @@ -2793,7 +2809,8 @@ static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *pfx, const struct in6_addr *peer_pfx, unsigned int plen, __u32 ifa_flags, - __u32 prefered_lft, __u32 valid_lft) + __u32 prefered_lft, __u32 valid_lft, + struct netlink_ext_ack *extack) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; @@ -2852,7 +2869,7 @@ static int inet6_addr_add(struct net *net, int ifindex, } ifp = ipv6_add_addr(idev, pfx, peer_pfx, plen, scope, ifa_flags, - valid_lft, prefered_lft); + valid_lft, prefered_lft, true, extack); if (!IS_ERR(ifp)) { if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) { @@ -2937,7 +2954,7 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg) rtnl_lock(); err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, NULL, ireq.ifr6_prefixlen, IFA_F_PERMANENT, - INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, NULL); rtnl_unlock(); return err; } @@ -2967,7 +2984,8 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifp = ipv6_add_addr(idev, addr, NULL, plen, scope, IFA_F_PERMANENT, - INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, + true, NULL); if (!IS_ERR(ifp)) { spin_lock_bh(&ifp->lock); ifp->flags &= ~IFA_F_TENTATIVE; @@ -3067,7 +3085,7 @@ void addrconf_add_linklocal(struct inet6_dev *idev, #endif ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, - INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, true, NULL); if (!IS_ERR(ifp)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0); addrconf_dad_start(ifp); @@ -3562,7 +3580,6 @@ static int addrconf_ifdown(struct net_device *dev, int how) struct net *net = dev_net(dev); struct inet6_dev *idev; struct inet6_ifaddr *ifa, *tmp; - struct list_head del_list; int _keep_addr; bool keep_addr; int state, i; @@ -3654,7 +3671,6 @@ restart: */ keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6); - INIT_LIST_HEAD(&del_list); list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { struct rt6_info *rt = NULL; bool keep; @@ -3663,8 +3679,6 @@ restart: keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) && !addr_is_local(&ifa->addr); - if (!keep) - list_move(&ifa->if_list, &del_list); write_unlock_bh(&idev->lock); spin_lock_bh(&ifa->lock); @@ -3698,19 +3712,14 @@ restart: } write_lock_bh(&idev->lock); + if (!keep) { + list_del_rcu(&ifa->if_list); + in6_ifa_put(ifa); + } } write_unlock_bh(&idev->lock); - /* now clean up addresses to be removed */ - while (!list_empty(&del_list)) { - ifa = list_first_entry(&del_list, - struct inet6_ifaddr, if_list); - list_del(&ifa->if_list); - - in6_ifa_put(ifa); - } - /* Step 5: Discard anycast and multicast list */ if (how) { ipv6_ac_destroy_dev(idev); @@ -3820,8 +3829,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) goto out; if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || - dev_net(dev)->ipv6.devconf_all->accept_dad < 1 || - idev->cnf.accept_dad < 1 || + (dev_net(dev)->ipv6.devconf_all->accept_dad < 1 && + idev->cnf.accept_dad < 1) || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { bump_id = ifp->flags & IFA_F_TENTATIVE; @@ -4579,7 +4588,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, */ return inet6_addr_add(net, ifm->ifa_index, pfx, peer_pfx, ifm->ifa_prefixlen, ifa_flags, - preferred_lft, valid_lft); + preferred_lft, valid_lft, extack); } if (nlh->nlmsg_flags & NLM_F_EXCL || @@ -4906,17 +4915,15 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err < 0) - goto errout; + return err; addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); - if (!addr) { - err = -EINVAL; - goto errout; - } + if (!addr) + return -EINVAL; ifm = nlmsg_data(nlh); if (ifm->ifa_index) - dev = __dev_get_by_index(net, ifm->ifa_index); + dev = dev_get_by_index(net, ifm->ifa_index); ifa = ipv6_get_ifaddr(net, addr, dev, 1); if (!ifa) { @@ -4942,6 +4949,8 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, errout_ifa: in6_ifa_put(ifa); errout: + if (dev) + dev_put(dev); return err; } @@ -5898,10 +5907,9 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) spin_lock(&ifa->lock); if (ifa->rt) { struct rt6_info *rt = ifa->rt; - struct fib6_table *table = rt->rt6i_table; int cpu; - read_lock(&table->tb6_lock); + rcu_read_lock(); addrconf_set_nopolicy(ifa->rt, val); if (rt->rt6i_pcpu) { for_each_possible_cpu(cpu) { @@ -5911,7 +5919,7 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) addrconf_set_nopolicy(*rtp, val); } } - read_unlock(&table->tb6_lock); + rcu_read_unlock(); } spin_unlock(&ifa->lock); } @@ -6585,13 +6593,13 @@ int __init addrconf_init(void) __rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, 0); __rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, 0); __rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, - inet6_dump_ifaddr, 0); + inet6_dump_ifaddr, RTNL_FLAG_DOIT_UNLOCKED); __rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL, inet6_dump_ifmcaddr, 0); __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, inet6_dump_ifacaddr, 0); __rtnl_register(PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf, - inet6_netconf_dump_devconf, 0); + inet6_netconf_dump_devconf, RTNL_FLAG_DOIT_UNLOCKED); ipv6_addr_label_rtnl_register(); diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 9e3488d50b15..32b564dfd02a 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -88,7 +88,7 @@ int __ipv6_addr_type(const struct in6_addr *addr) EXPORT_SYMBOL(__ipv6_addr_type); static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); -static ATOMIC_NOTIFIER_HEAD(inet6addr_validator_chain); +static BLOCKING_NOTIFIER_HEAD(inet6addr_validator_chain); int register_inet6addr_notifier(struct notifier_block *nb) { @@ -110,19 +110,20 @@ EXPORT_SYMBOL(inet6addr_notifier_call_chain); int register_inet6addr_validator_notifier(struct notifier_block *nb) { - return atomic_notifier_chain_register(&inet6addr_validator_chain, nb); + return blocking_notifier_chain_register(&inet6addr_validator_chain, nb); } EXPORT_SYMBOL(register_inet6addr_validator_notifier); int unregister_inet6addr_validator_notifier(struct notifier_block *nb) { - return atomic_notifier_chain_unregister(&inet6addr_validator_chain, nb); + return blocking_notifier_chain_unregister(&inet6addr_validator_chain, + nb); } EXPORT_SYMBOL(unregister_inet6addr_validator_notifier); int inet6addr_validator_notifier_call_chain(unsigned long val, void *v) { - return atomic_notifier_call_chain(&inet6addr_validator_chain, val, v); + return blocking_notifier_call_chain(&inet6addr_validator_chain, val, v); } EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index c6311d7108f6..2606d2fa3ac4 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -18,7 +18,6 @@ #include <linux/if_addrlabel.h> #include <linux/netlink.h> #include <linux/rtnetlink.h> -#include <linux/refcount.h> #if 0 #define ADDRLABEL(x...) printk(x) @@ -36,7 +35,6 @@ struct ip6addrlbl_entry { int addrtype; u32 label; struct hlist_node list; - refcount_t refcnt; struct rcu_head rcu; }; @@ -111,28 +109,6 @@ static const __net_initconst struct ip6addrlbl_init_table } }; -/* Object management */ -static inline void ip6addrlbl_free(struct ip6addrlbl_entry *p) -{ - kfree(p); -} - -static void ip6addrlbl_free_rcu(struct rcu_head *h) -{ - ip6addrlbl_free(container_of(h, struct ip6addrlbl_entry, rcu)); -} - -static bool ip6addrlbl_hold(struct ip6addrlbl_entry *p) -{ - return refcount_inc_not_zero(&p->refcnt); -} - -static inline void ip6addrlbl_put(struct ip6addrlbl_entry *p) -{ - if (refcount_dec_and_test(&p->refcnt)) - call_rcu(&p->rcu, ip6addrlbl_free_rcu); -} - /* Find label */ static bool __ip6addrlbl_match(const struct ip6addrlbl_entry *p, const struct in6_addr *addr, @@ -219,7 +195,6 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(const struct in6_addr *prefix, newp->addrtype = addrtype; newp->label = label; INIT_HLIST_NODE(&newp->list); - refcount_set(&newp->refcnt, 1); return newp; } @@ -243,7 +218,7 @@ static int __ip6addrlbl_add(struct net *net, struct ip6addrlbl_entry *newp, goto out; } hlist_replace_rcu(&p->list, &newp->list); - ip6addrlbl_put(p); + kfree_rcu(p, rcu); goto out; } else if ((p->prefixlen == newp->prefixlen && !p->ifindex) || (p->prefixlen < newp->prefixlen)) { @@ -281,7 +256,7 @@ static int ip6addrlbl_add(struct net *net, ret = __ip6addrlbl_add(net, newp, replace); spin_unlock(&net->ipv6.ip6addrlbl_table.lock); if (ret) - ip6addrlbl_free(newp); + kfree(newp); return ret; } @@ -302,7 +277,7 @@ static int __ip6addrlbl_del(struct net *net, p->ifindex == ifindex && ipv6_addr_equal(&p->prefix, prefix)) { hlist_del_rcu(&p->list); - ip6addrlbl_put(p); + kfree_rcu(p, rcu); ret = 0; break; } @@ -360,7 +335,7 @@ static void __net_exit ip6addrlbl_net_exit(struct net *net) spin_lock(&net->ipv6.ip6addrlbl_table.lock); hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { hlist_del_rcu(&p->list); - ip6addrlbl_put(p); + kfree_rcu(p, rcu); } spin_unlock(&net->ipv6.ip6addrlbl_table.lock); } @@ -546,38 +521,28 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, return -EINVAL; addr = nla_data(tb[IFAL_ADDRESS]); - rcu_read_lock(); - p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); - if (p && !ip6addrlbl_hold(p)) - p = NULL; - lseq = net->ipv6.ip6addrlbl_table.seq; - rcu_read_unlock(); - - if (!p) { - err = -ESRCH; - goto out; - } - skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL); - if (!skb) { - ip6addrlbl_put(p); + if (!skb) return -ENOBUFS; - } - err = ip6addrlbl_fill(skb, p, lseq, - NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, - RTM_NEWADDRLABEL, 0); + err = -ESRCH; - ip6addrlbl_put(p); + rcu_read_lock(); + p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); + lseq = net->ipv6.ip6addrlbl_table.seq; + if (p) + err = ip6addrlbl_fill(skb, p, lseq, + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, + RTM_NEWADDRLABEL, 0); + rcu_read_unlock(); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - goto out; + } else { + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); } - - err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); -out: return err; } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 7802b72196f3..37bb33fbc742 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -271,6 +271,7 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) case NEXTHDR_DEST: if (dir == XFRM_POLICY_OUT) ipv6_rearrange_destopt(iph, exthdr.opth); + /* fall through */ case NEXTHDR_HOP: if (!zero_out_mutable_opts(exthdr.opth)) { net_dbg_ratelimited("overrun %sopts\n", diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 95516138e861..7835dea930b4 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -89,6 +89,7 @@ static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff) */ if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) break; + /* fall through */ case 2: /* send ICMP PARM PROB regardless and drop packet */ icmpv6_param_prob(skb, ICMPV6_UNK_OPTION, optoff); return false; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 4e52d52a6752..6ae5dd3f4d0d 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -864,10 +864,8 @@ static int icmpv6_rcv(struct sk_buff *skb) goto discard_it; hdr = icmp6_hdr(skb); - /* - * Drop through to notify - */ - + /* to notify */ + /* fall through */ case ICMPV6_DEST_UNREACH: case ICMPV6_TIME_EXCEED: case ICMPV6_PARAMPROB: diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index e5308d7cbd75..1ada9672d198 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -38,14 +38,6 @@ #include <net/ip6_fib.h> #include <net/ip6_route.h> -#define RT6_DEBUG 2 - -#if RT6_DEBUG >= 3 -#define RT6_TRACE(x...) pr_debug(x) -#else -#define RT6_TRACE(x...) do { ; } while (0) -#endif - static struct kmem_cache *fib6_node_kmem __read_mostly; struct fib6_cleaner { @@ -62,9 +54,12 @@ struct fib6_cleaner { #define FWS_INIT FWS_L #endif -static void fib6_prune_clones(struct net *net, struct fib6_node *fn); -static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn); -static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn); +static struct rt6_info *fib6_find_prefix(struct net *net, + struct fib6_table *table, + struct fib6_node *fn); +static struct fib6_node *fib6_repair_tree(struct net *net, + struct fib6_table *table, + struct fib6_node *fn); static int fib6_walk(struct net *net, struct fib6_walker *w); static int fib6_walk_continue(struct fib6_walker *w); @@ -110,6 +105,20 @@ enum { FIB6_NO_SERNUM_CHANGE = 0, }; +void fib6_update_sernum(struct rt6_info *rt) +{ + struct fib6_table *table = rt->rt6i_table; + struct net *net = dev_net(rt->dst.dev); + struct fib6_node *fn; + + spin_lock_bh(&table->tb6_lock); + fn = rcu_dereference_protected(rt->rt6i_node, + lockdep_is_held(&table->tb6_lock)); + if (fn) + fn->fn_sernum = fib6_new_sernum(net); + spin_unlock_bh(&table->tb6_lock); +} + /* * Auxiliary address test functions for the radix tree. * @@ -140,18 +149,21 @@ static __be32 addr_bit_set(const void *token, int fn_bit) addr[fn_bit >> 5]; } -static struct fib6_node *node_alloc(void) +static struct fib6_node *node_alloc(struct net *net) { struct fib6_node *fn; fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC); + if (fn) + net->ipv6.rt6_stats->fib_nodes++; return fn; } -static void node_free_immediate(struct fib6_node *fn) +static void node_free_immediate(struct net *net, struct fib6_node *fn) { kmem_cache_free(fib6_node_kmem, fn); + net->ipv6.rt6_stats->fib_nodes--; } static void node_free_rcu(struct rcu_head *head) @@ -161,9 +173,10 @@ static void node_free_rcu(struct rcu_head *head) kmem_cache_free(fib6_node_kmem, fn); } -static void node_free(struct fib6_node *fn) +static void node_free(struct net *net, struct fib6_node *fn) { call_rcu(&fn->rcu, node_free_rcu); + net->ipv6.rt6_stats->fib_nodes--; } void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) @@ -185,9 +198,6 @@ void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) *ppcpu_rt = NULL; } } - - free_percpu(non_pcpu_rt->rt6i_pcpu); - non_pcpu_rt->rt6i_pcpu = NULL; } EXPORT_SYMBOL_GPL(rt6_free_pcpu); @@ -205,8 +215,7 @@ static void fib6_link_table(struct net *net, struct fib6_table *tb) * Initialize table lock at a single place to give lockdep a key, * tables aren't visible prior to being linked to the list. */ - rwlock_init(&tb->tb6_lock); - + spin_lock_init(&tb->tb6_lock); h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1); /* @@ -225,7 +234,8 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) table = kzalloc(sizeof(*table), GFP_ATOMIC); if (table) { table->tb6_id = id; - table->tb6_root.leaf = net->ipv6.ip6_null_entry; + rcu_assign_pointer(table->tb6_root.leaf, + net->ipv6.ip6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); } @@ -322,11 +332,8 @@ unsigned int fib6_tables_seq_read(struct net *net) struct hlist_head *head = &net->ipv6.fib_table_hash[h]; struct fib6_table *tb; - hlist_for_each_entry_rcu(tb, head, tb6_hlist) { - read_lock_bh(&tb->tb6_lock); + hlist_for_each_entry_rcu(tb, head, tb6_hlist) fib_seq += tb->fib_seq; - read_unlock_bh(&tb->tb6_lock); - } } rcu_read_unlock(); @@ -372,7 +379,7 @@ static int fib6_node_dump(struct fib6_walker *w) { struct rt6_info *rt; - for (rt = w->leaf; rt; rt = rt->dst.rt6_next) + for_each_fib6_walker_rt(w) fib6_rt_dump(rt, w->args); w->leaf = NULL; return 0; @@ -382,9 +389,9 @@ static void fib6_table_dump(struct net *net, struct fib6_table *tb, struct fib6_walker *w) { w->root = &tb->tb6_root; - read_lock_bh(&tb->tb6_lock); + spin_lock_bh(&tb->tb6_lock); fib6_walk(net, w); - read_unlock_bh(&tb->tb6_lock); + spin_unlock_bh(&tb->tb6_lock); } /* Called with rcu_read_lock() */ @@ -421,7 +428,7 @@ static int fib6_dump_node(struct fib6_walker *w) int res; struct rt6_info *rt; - for (rt = w->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_walker_rt(w) { res = rt6_dump_route(rt, w->args); if (res < 0) { /* Frame is full, suspend walking */ @@ -480,9 +487,9 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, w->count = 0; w->skip = 0; - read_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); res = fib6_walk(net, w); - read_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); if (res > 0) { cb->args[4] = 1; cb->args[5] = w->root->fn_sernum; @@ -497,9 +504,9 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, } else w->skip = 0; - read_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); res = fib6_walk_continue(w); - read_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); if (res <= 0) { fib6_walker_unlink(net, w); cb->args[4] = 0; @@ -580,11 +587,13 @@ out: * node. */ -static struct fib6_node *fib6_add_1(struct fib6_node *root, - struct in6_addr *addr, int plen, - int offset, int allow_create, - int replace_required, int sernum, - struct netlink_ext_ack *extack) +static struct fib6_node *fib6_add_1(struct net *net, + struct fib6_table *table, + struct fib6_node *root, + struct in6_addr *addr, int plen, + int offset, int allow_create, + int replace_required, + struct netlink_ext_ack *extack) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; @@ -599,7 +608,9 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, fn = root; do { - key = (struct rt6key *)((u8 *)fn->leaf + offset); + struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&table->tb6_lock)); + key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match @@ -625,12 +636,10 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, if (plen == fn->fn_bit) { /* clean up an intermediate node */ if (!(fn->fn_flags & RTN_RTINFO)) { - rt6_release(fn->leaf); - fn->leaf = NULL; + RCU_INIT_POINTER(fn->leaf, NULL); + rt6_release(leaf); } - fn->fn_sernum = sernum; - return fn; } @@ -639,10 +648,13 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, */ /* Try to walk down on tree. */ - fn->fn_sernum = sernum; dir = addr_bit_set(addr, fn->fn_bit); pn = fn; - fn = dir ? fn->right : fn->left; + fn = dir ? + rcu_dereference_protected(fn->right, + lockdep_is_held(&table->tb6_lock)) : + rcu_dereference_protected(fn->left, + lockdep_is_held(&table->tb6_lock)); } while (fn); if (!allow_create) { @@ -668,19 +680,17 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, * Create new leaf node without children. */ - ln = node_alloc(); + ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; - - ln->parent = pn; - ln->fn_sernum = sernum; + RCU_INIT_POINTER(ln->parent, pn); if (dir) - pn->right = ln; + rcu_assign_pointer(pn->right, ln); else - pn->left = ln; + rcu_assign_pointer(pn->left, ln); return ln; @@ -694,7 +704,8 @@ insert_above: * and the current */ - pn = fn->parent; + pn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&table->tb6_lock)); /* find 1st bit in difference between the 2 addrs. @@ -710,14 +721,14 @@ insert_above: * (new leaf node)[ln] (old node)[fn] */ if (plen > bit) { - in = node_alloc(); - ln = node_alloc(); + in = node_alloc(net); + ln = node_alloc(net); if (!in || !ln) { if (in) - node_free_immediate(in); + node_free_immediate(net, in); if (ln) - node_free_immediate(ln); + node_free_immediate(net, ln); return ERR_PTR(-ENOMEM); } @@ -731,31 +742,28 @@ insert_above: in->fn_bit = bit; - in->parent = pn; + RCU_INIT_POINTER(in->parent, pn); in->leaf = fn->leaf; - atomic_inc(&in->leaf->rt6i_ref); - - in->fn_sernum = sernum; + atomic_inc(&rcu_dereference_protected(in->leaf, + lockdep_is_held(&table->tb6_lock))->rt6i_ref); /* update parent pointer */ if (dir) - pn->right = in; + rcu_assign_pointer(pn->right, in); else - pn->left = in; + rcu_assign_pointer(pn->left, in); ln->fn_bit = plen; - ln->parent = in; - fn->parent = in; - - ln->fn_sernum = sernum; + RCU_INIT_POINTER(ln->parent, in); + rcu_assign_pointer(fn->parent, in); if (addr_bit_set(addr, bit)) { - in->right = ln; - in->left = fn; + rcu_assign_pointer(in->right, ln); + rcu_assign_pointer(in->left, fn); } else { - in->left = ln; - in->right = fn; + rcu_assign_pointer(in->left, ln); + rcu_assign_pointer(in->right, fn); } } else { /* plen <= bit */ @@ -765,28 +773,26 @@ insert_above: * (old node)[fn] NULL */ - ln = node_alloc(); + ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; - ln->parent = pn; - - ln->fn_sernum = sernum; - - if (dir) - pn->right = ln; - else - pn->left = ln; + RCU_INIT_POINTER(ln->parent, pn); if (addr_bit_set(&key->addr, plen)) - ln->right = fn; + RCU_INIT_POINTER(ln->right, fn); else - ln->left = fn; + RCU_INIT_POINTER(ln->left, fn); - fn->parent = ln; + rcu_assign_pointer(fn->parent, ln); + + if (dir) + rcu_assign_pointer(pn->right, ln); + else + rcu_assign_pointer(pn->left, ln); } return ln; } @@ -832,6 +838,8 @@ static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc) static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, struct net *net) { + struct fib6_table *table = rt->rt6i_table; + if (atomic_read(&rt->rt6i_ref) != 1) { /* This route is used as dummy address holder in some split * nodes. It is not leaked, but it still holds other resources, @@ -840,12 +848,17 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, * to still alive ones. */ while (fn) { - if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { - fn->leaf = fib6_find_prefix(net, fn); - atomic_inc(&fn->leaf->rt6i_ref); + struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *new_leaf; + if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) { + new_leaf = fib6_find_prefix(net, table, fn); + atomic_inc(&new_leaf->rt6i_ref); + rcu_assign_pointer(fn->leaf, new_leaf); rt6_release(rt); } - fn = fn->parent; + fn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&table->tb6_lock)); } } } @@ -857,9 +870,11 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, struct nl_info *info, struct mx6_config *mxc) { + struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); struct rt6_info *iter = NULL; - struct rt6_info **ins; - struct rt6_info **fallback_ins = NULL; + struct rt6_info __rcu **ins; + struct rt6_info __rcu **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); int add = (!info->nlh || @@ -874,7 +889,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, ins = &fn->leaf; - for (iter = fn->leaf; iter; iter = iter->dst.rt6_next) { + for (iter = leaf; iter; + iter = rcu_dereference_protected(iter->dst.rt6_next, + lockdep_is_held(&rt->rt6i_table->tb6_lock))) { /* * Search for duplicates */ @@ -936,7 +953,8 @@ next_iter: if (fallback_ins && !found) { /* No ECMP-able route found, replace first non-ECMP one */ ins = fallback_ins; - iter = *ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); found++; } @@ -950,7 +968,7 @@ next_iter: struct rt6_info *sibling, *temp_sibling; /* Find the first route that have the same metric */ - sibling = fn->leaf; + sibling = leaf; while (sibling) { if (sibling->rt6i_metric == rt->rt6i_metric && rt6_qualify_for_ecmp(sibling)) { @@ -958,7 +976,8 @@ next_iter: &sibling->rt6i_siblings); break; } - sibling = sibling->dst.rt6_next; + sibling = rcu_dereference_protected(sibling->dst.rt6_next, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); } /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings @@ -987,10 +1006,10 @@ add: if (err) return err; - rt->dst.rt6_next = iter; - *ins = rt; - rcu_assign_pointer(rt->rt6i_node, fn); + rcu_assign_pointer(rt->dst.rt6_next, iter); atomic_inc(&rt->rt6i_ref); + rcu_assign_pointer(rt->rt6i_node, fn); + rcu_assign_pointer(*ins, rt); call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_ADD, rt); if (!info->skip_notify) @@ -1016,10 +1035,10 @@ add: if (err) return err; - *ins = rt; + atomic_inc(&rt->rt6i_ref); rcu_assign_pointer(rt->rt6i_node, fn); rt->dst.rt6_next = iter->dst.rt6_next; - atomic_inc(&rt->rt6i_ref); + rcu_assign_pointer(*ins, rt); call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, rt); if (!info->skip_notify) @@ -1031,14 +1050,15 @@ add: nsiblings = iter->rt6i_nsiblings; iter->rt6i_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); - if (fn->rr_ptr == iter) + if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; rt6_release(iter); if (nsiblings) { /* Replacing an ECMP route, remove all siblings */ ins = &rt->dst.rt6_next; - iter = *ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); while (iter) { if (iter->rt6i_metric > rt->rt6i_metric) break; @@ -1046,14 +1066,16 @@ add: *ins = iter->dst.rt6_next; iter->rt6i_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); - if (fn->rr_ptr == iter) + if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; rt6_release(iter); nsiblings--; + info->nl_net->ipv6.rt6_stats->fib_rt_entries--; } else { ins = &iter->dst.rt6_next; } - iter = *ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); } WARN_ON(nsiblings != 0); } @@ -1077,16 +1099,33 @@ void fib6_force_start_gc(struct net *net) jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } +static void fib6_update_sernum_upto_root(struct rt6_info *rt, + int sernum) +{ + struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); + + /* paired with smp_rmb() in rt6_get_cookie_safe() */ + smp_wmb(); + while (fn) { + fn->fn_sernum = sernum; + fn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); + } +} + /* * Add routing information to the routing tree. * <destination addr>/<source addr> * with source addr info in sub-trees + * Need to own table->tb6_lock */ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info, struct mx6_config *mxc, struct netlink_ext_ack *extack) { + struct fib6_table *table = rt->rt6i_table; struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; int allow_create = 1; @@ -1095,6 +1134,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt))) return -EINVAL; + if (WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE)) + return -EINVAL; if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) @@ -1105,9 +1146,10 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (!allow_create && !replace_required) pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); - fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, + fn = fib6_add_1(info->nl_net, table, root, + &rt->rt6i_dst.addr, rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), allow_create, - replace_required, sernum, extack); + replace_required, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); fn = NULL; @@ -1120,7 +1162,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (rt->rt6i_src.plen) { struct fib6_node *sn; - if (!fn->subtree) { + if (!rcu_access_pointer(fn->subtree)) { struct fib6_node *sfn; /* @@ -1134,42 +1176,40 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, */ /* Create subtree root node */ - sfn = node_alloc(); + sfn = node_alloc(info->nl_net); if (!sfn) goto failure; - sfn->leaf = info->nl_net->ipv6.ip6_null_entry; atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref); + rcu_assign_pointer(sfn->leaf, + info->nl_net->ipv6.ip6_null_entry); sfn->fn_flags = RTN_ROOT; - sfn->fn_sernum = sernum; /* Now add the first leaf node to new subtree */ - sn = fib6_add_1(sfn, &rt->rt6i_src.addr, - rt->rt6i_src.plen, + sn = fib6_add_1(info->nl_net, table, sfn, + &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum, - extack); + allow_create, replace_required, extack); if (IS_ERR(sn)) { /* If it is failed, discard just allocated root, and then (in failure) stale node in main tree. */ - node_free_immediate(sfn); + node_free_immediate(info->nl_net, sfn); err = PTR_ERR(sn); goto failure; } /* Now link new subtree to main tree */ - sfn->parent = fn; - fn->subtree = sfn; + rcu_assign_pointer(sfn->parent, fn); + rcu_assign_pointer(fn->subtree, sfn); } else { - sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, - rt->rt6i_src.plen, + sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn), + &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum, - extack); + allow_create, replace_required, extack); if (IS_ERR(sn)) { err = PTR_ERR(sn); @@ -1177,9 +1217,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, } } - if (!fn->leaf) { - fn->leaf = rt; + if (!rcu_access_pointer(fn->leaf)) { atomic_inc(&rt->rt6i_ref); + rcu_assign_pointer(fn->leaf, rt); } fn = sn; } @@ -1187,9 +1227,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, err = fib6_add_rt2node(fn, rt, info, mxc); if (!err) { + fib6_update_sernum_upto_root(rt, sernum); fib6_start_gc(info->nl_net, rt); - if (!(rt->rt6i_flags & RTF_CACHE)) - fib6_prune_clones(info->nl_net, pn); } out: @@ -1199,19 +1238,23 @@ out: * If fib6_add_1 has cleared the old leaf pointer in the * super-tree leaf node we have to find a new one for it. */ - if (pn != fn && pn->leaf == rt) { - pn->leaf = NULL; + struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf, + lockdep_is_held(&table->tb6_lock)); + if (pn != fn && pn_leaf == rt) { + pn_leaf = NULL; + RCU_INIT_POINTER(pn->leaf, NULL); atomic_dec(&rt->rt6i_ref); } - if (pn != fn && !pn->leaf && !(pn->fn_flags & RTN_RTINFO)) { - pn->leaf = fib6_find_prefix(info->nl_net, pn); + if (pn != fn && !pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { + pn_leaf = fib6_find_prefix(info->nl_net, table, pn); #if RT6_DEBUG >= 2 - if (!pn->leaf) { - WARN_ON(pn->leaf == NULL); - pn->leaf = info->nl_net->ipv6.ip6_null_entry; + if (!pn_leaf) { + WARN_ON(!pn_leaf); + pn_leaf = info->nl_net->ipv6.ip6_null_entry; } #endif - atomic_inc(&pn->leaf->rt6i_ref); + atomic_inc(&pn_leaf->rt6i_ref); + rcu_assign_pointer(pn->leaf, pn_leaf); } #endif goto failure; @@ -1226,7 +1269,7 @@ failure: * fn->leaf. */ if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT))) - fib6_repair_tree(info->nl_net, fn); + fib6_repair_tree(info->nl_net, table, fn); /* Always release dst as dst->__refcnt is guaranteed * to be taken before entering this function */ @@ -1264,7 +1307,8 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, dir = addr_bit_set(args->addr, fn->fn_bit); - next = dir ? fn->right : fn->left; + next = dir ? rcu_dereference(fn->right) : + rcu_dereference(fn->left); if (next) { fn = next; @@ -1274,18 +1318,22 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, } while (fn) { - if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) { + struct fib6_node *subtree = FIB6_SUBTREE(fn); + + if (subtree || fn->fn_flags & RTN_RTINFO) { + struct rt6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; - key = (struct rt6key *) ((u8 *) fn->leaf + - args->offset); + if (!leaf) + goto backtrack; + + key = (struct rt6key *) ((u8 *)leaf + args->offset); if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES - if (fn->subtree) { + if (subtree) { struct fib6_node *sfn; - sfn = fib6_lookup_1(fn->subtree, - args + 1); + sfn = fib6_lookup_1(subtree, args + 1); if (!sfn) goto backtrack; fn = sfn; @@ -1295,18 +1343,18 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, return fn; } } -#ifdef CONFIG_IPV6_SUBTREES backtrack: -#endif if (fn->fn_flags & RTN_ROOT) break; - fn = fn->parent; + fn = rcu_dereference(fn->parent); } return NULL; } +/* called with rcu_read_lock() held + */ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr, const struct in6_addr *saddr) { @@ -1337,54 +1385,87 @@ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *dad /* * Get node with specified destination prefix (and source prefix, * if subtrees are used) + * exact_match == true means we try to find fn with exact match of + * the passed in prefix addr + * exact_match == false means we try to find fn with longest prefix + * match of the passed in prefix addr. This is useful for finding fn + * for cached route as it will be stored in the exception table under + * the node with longest prefix length. */ static struct fib6_node *fib6_locate_1(struct fib6_node *root, const struct in6_addr *addr, - int plen, int offset) + int plen, int offset, + bool exact_match) { - struct fib6_node *fn; + struct fib6_node *fn, *prev = NULL; for (fn = root; fn ; ) { - struct rt6key *key = (struct rt6key *)((u8 *)fn->leaf + offset); + struct rt6_info *leaf = rcu_dereference(fn->leaf); + struct rt6key *key; + + /* This node is being deleted */ + if (!leaf) { + if (plen <= fn->fn_bit) + goto out; + else + goto next; + } + + key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match */ if (plen < fn->fn_bit || !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) - return NULL; + goto out; if (plen == fn->fn_bit) return fn; + prev = fn; + +next: /* * We have more bits to go */ if (addr_bit_set(addr, fn->fn_bit)) - fn = fn->right; + fn = rcu_dereference(fn->right); else - fn = fn->left; + fn = rcu_dereference(fn->left); } - return NULL; +out: + if (exact_match) + return NULL; + else + return prev; } struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, - const struct in6_addr *saddr, int src_len) + const struct in6_addr *saddr, int src_len, + bool exact_match) { struct fib6_node *fn; fn = fib6_locate_1(root, daddr, dst_len, - offsetof(struct rt6_info, rt6i_dst)); + offsetof(struct rt6_info, rt6i_dst), + exact_match); #ifdef CONFIG_IPV6_SUBTREES if (src_len) { WARN_ON(saddr == NULL); - if (fn && fn->subtree) - fn = fib6_locate_1(fn->subtree, saddr, src_len, - offsetof(struct rt6_info, rt6i_src)); + if (fn) { + struct fib6_node *subtree = FIB6_SUBTREE(fn); + + if (subtree) { + fn = fib6_locate_1(subtree, saddr, src_len, + offsetof(struct rt6_info, rt6i_src), + exact_match); + } + } } #endif @@ -1400,16 +1481,26 @@ struct fib6_node *fib6_locate(struct fib6_node *root, * */ -static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn) +static struct rt6_info *fib6_find_prefix(struct net *net, + struct fib6_table *table, + struct fib6_node *fn) { + struct fib6_node *child_left, *child_right; + if (fn->fn_flags & RTN_ROOT) return net->ipv6.ip6_null_entry; while (fn) { - if (fn->left) - return fn->left->leaf; - if (fn->right) - return fn->right->leaf; + child_left = rcu_dereference_protected(fn->left, + lockdep_is_held(&table->tb6_lock)); + child_right = rcu_dereference_protected(fn->right, + lockdep_is_held(&table->tb6_lock)); + if (child_left) + return rcu_dereference_protected(child_left->leaf, + lockdep_is_held(&table->tb6_lock)); + if (child_right) + return rcu_dereference_protected(child_right->leaf, + lockdep_is_held(&table->tb6_lock)); fn = FIB6_SUBTREE(fn); } @@ -1419,31 +1510,49 @@ static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn) /* * Called to trim the tree of intermediate nodes when possible. "fn" * is the node we want to try and remove. + * Need to own table->tb6_lock */ static struct fib6_node *fib6_repair_tree(struct net *net, - struct fib6_node *fn) + struct fib6_table *table, + struct fib6_node *fn) { int children; int nstate; - struct fib6_node *child, *pn; + struct fib6_node *child; struct fib6_walker *w; int iter = 0; for (;;) { + struct fib6_node *fn_r = rcu_dereference_protected(fn->right, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *fn_l = rcu_dereference_protected(fn->left, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *pn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *pn_r = rcu_dereference_protected(pn->right, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *pn_l = rcu_dereference_protected(pn->left, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *fn_leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *new_fn_leaf; + RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; WARN_ON(fn->fn_flags & RTN_RTINFO); WARN_ON(fn->fn_flags & RTN_TL_ROOT); - WARN_ON(fn->leaf); + WARN_ON(fn_leaf); children = 0; child = NULL; - if (fn->right) - child = fn->right, children |= 1; - if (fn->left) - child = fn->left, children |= 2; + if (fn_r) + child = fn_r, children |= 1; + if (fn_l) + child = fn_l, children |= 2; if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES @@ -1451,36 +1560,36 @@ static struct fib6_node *fib6_repair_tree(struct net *net, || (children && fn->fn_flags & RTN_ROOT) #endif ) { - fn->leaf = fib6_find_prefix(net, fn); + new_fn_leaf = fib6_find_prefix(net, table, fn); #if RT6_DEBUG >= 2 - if (!fn->leaf) { - WARN_ON(!fn->leaf); - fn->leaf = net->ipv6.ip6_null_entry; + if (!new_fn_leaf) { + WARN_ON(!new_fn_leaf); + new_fn_leaf = net->ipv6.ip6_null_entry; } #endif - atomic_inc(&fn->leaf->rt6i_ref); - return fn->parent; + atomic_inc(&new_fn_leaf->rt6i_ref); + rcu_assign_pointer(fn->leaf, new_fn_leaf); + return pn; } - pn = fn->parent; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { WARN_ON(!(fn->fn_flags & RTN_ROOT)); - FIB6_SUBTREE(pn) = NULL; + RCU_INIT_POINTER(pn->subtree, NULL); nstate = FWS_L; } else { WARN_ON(fn->fn_flags & RTN_ROOT); #endif - if (pn->right == fn) - pn->right = child; - else if (pn->left == fn) - pn->left = child; + if (pn_r == fn) + rcu_assign_pointer(pn->right, child); + else if (pn_l == fn) + rcu_assign_pointer(pn->left, child); #if RT6_DEBUG >= 2 else WARN_ON(1); #endif if (child) - child->parent = pn; + rcu_assign_pointer(child->parent, pn); nstate = FWS_R; #ifdef CONFIG_IPV6_SUBTREES } @@ -1489,19 +1598,12 @@ static struct fib6_node *fib6_repair_tree(struct net *net, read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (!child) { - if (w->root == fn) { - w->root = w->node = NULL; - RT6_TRACE("W %p adjusted by delroot 1\n", w); - } else if (w->node == fn) { + if (w->node == fn) { RT6_TRACE("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate); w->node = pn; w->state = nstate; } } else { - if (w->root == fn) { - w->root = child; - RT6_TRACE("W %p adjusted by delroot 2\n", w); - } if (w->node == fn) { w->node = child; if (children&2) { @@ -1516,33 +1618,39 @@ static struct fib6_node *fib6_repair_tree(struct net *net, } read_unlock(&net->ipv6.fib6_walker_lock); - node_free(fn); + node_free(net, fn); if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) return pn; - rt6_release(pn->leaf); - pn->leaf = NULL; + RCU_INIT_POINTER(pn->leaf, NULL); + rt6_release(pn_leaf); fn = pn; } } -static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, - struct nl_info *info) +static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, + struct rt6_info __rcu **rtp, struct nl_info *info) { struct fib6_walker *w; - struct rt6_info *rt = *rtp; + struct rt6_info *rt = rcu_dereference_protected(*rtp, + lockdep_is_held(&table->tb6_lock)); struct net *net = info->nl_net; RT6_TRACE("fib6_del_route\n"); + WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE); + /* Unlink it */ *rtp = rt->dst.rt6_next; rt->rt6i_node = NULL; net->ipv6.rt6_stats->fib_rt_entries--; net->ipv6.rt6_stats->fib_discarded_routes++; + /* Flush all cached dst in exception table */ + rt6_flush_exceptions(rt); + /* Reset round-robin state, if necessary */ - if (fn->rr_ptr == rt) + if (rcu_access_pointer(fn->rr_ptr) == rt) fn->rr_ptr = NULL; /* Remove this entry from other siblings */ @@ -1561,20 +1669,19 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { RT6_TRACE("walker %p adjusted by delroute\n", w); - w->leaf = rt->dst.rt6_next; + w->leaf = rcu_dereference_protected(rt->dst.rt6_next, + lockdep_is_held(&table->tb6_lock)); if (!w->leaf) w->state = FWS_U; } } read_unlock(&net->ipv6.fib6_walker_lock); - rt->dst.rt6_next = NULL; - /* If it was last route, expunge its radix tree node */ - if (!fn->leaf) { + if (!rcu_access_pointer(fn->leaf)) { fn->fn_flags &= ~RTN_RTINFO; net->ipv6.rt6_stats->fib_route_nodes--; - fn = fib6_repair_tree(net, fn); + fn = fib6_repair_tree(net, table, fn); } fib6_purge_rt(rt, fn, net); @@ -1585,12 +1692,15 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, rt6_release(rt); } +/* Need to own table->tb6_lock */ int fib6_del(struct rt6_info *rt, struct nl_info *info) { struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, lockdep_is_held(&rt->rt6i_table->tb6_lock)); + struct fib6_table *table = rt->rt6i_table; struct net *net = info->nl_net; - struct rt6_info **rtp; + struct rt6_info __rcu **rtp; + struct rt6_info __rcu **rtp_next; #if RT6_DEBUG >= 2 if (rt->dst.obsolete > 0) { @@ -1603,28 +1713,22 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) WARN_ON(!(fn->fn_flags & RTN_RTINFO)); - if (!(rt->rt6i_flags & RTF_CACHE)) { - struct fib6_node *pn = fn; -#ifdef CONFIG_IPV6_SUBTREES - /* clones of this route might be in another subtree */ - if (rt->rt6i_src.plen) { - while (!(pn->fn_flags & RTN_ROOT)) - pn = pn->parent; - pn = pn->parent; - } -#endif - fib6_prune_clones(info->nl_net, pn); - } + /* remove cached dst from exception table */ + if (rt->rt6i_flags & RTF_CACHE) + return rt6_remove_exception_rt(rt); /* * Walk the leaf entries looking for ourself */ - for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->dst.rt6_next) { - if (*rtp == rt) { - fib6_del_route(fn, rtp, info); + for (rtp = &fn->leaf; *rtp; rtp = rtp_next) { + struct rt6_info *cur = rcu_dereference_protected(*rtp, + lockdep_is_held(&table->tb6_lock)); + if (rt == cur) { + fib6_del_route(table, fn, rtp, info); return 0; } + rtp_next = &cur->dst.rt6_next; } return -ENOENT; } @@ -1651,22 +1755,22 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) * 0 -> walk is complete. * >0 -> walk is incomplete (i.e. suspended) * <0 -> walk is terminated by an error. + * + * This function is called with tb6_lock held. */ static int fib6_walk_continue(struct fib6_walker *w) { - struct fib6_node *fn, *pn; + struct fib6_node *fn, *pn, *left, *right; + + /* w->root should always be table->tb6_root */ + WARN_ON_ONCE(!(w->root->fn_flags & RTN_TL_ROOT)); for (;;) { fn = w->node; if (!fn) return 0; - if (w->prune && fn != w->root && - fn->fn_flags & RTN_RTINFO && w->state < FWS_C) { - w->state = FWS_C; - w->leaf = fn->leaf; - } switch (w->state) { #ifdef CONFIG_IPV6_SUBTREES case FWS_S: @@ -1676,21 +1780,26 @@ static int fib6_walk_continue(struct fib6_walker *w) } w->state = FWS_L; #endif + /* fall through */ case FWS_L: - if (fn->left) { - w->node = fn->left; + left = rcu_dereference_protected(fn->left, 1); + if (left) { + w->node = left; w->state = FWS_INIT; continue; } w->state = FWS_R; + /* fall through */ case FWS_R: - if (fn->right) { - w->node = fn->right; + right = rcu_dereference_protected(fn->right, 1); + if (right) { + w->node = right; w->state = FWS_INIT; continue; } w->state = FWS_C; - w->leaf = fn->leaf; + w->leaf = rcu_dereference_protected(fn->leaf, 1); + /* fall through */ case FWS_C: if (w->leaf && fn->fn_flags & RTN_RTINFO) { int err; @@ -1709,10 +1818,13 @@ static int fib6_walk_continue(struct fib6_walker *w) } skip: w->state = FWS_U; + /* fall through */ case FWS_U: if (fn == w->root) return 0; - pn = fn->parent; + pn = rcu_dereference_protected(fn->parent, 1); + left = rcu_dereference_protected(pn->left, 1); + right = rcu_dereference_protected(pn->right, 1); w->node = pn; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { @@ -1721,13 +1833,13 @@ skip: continue; } #endif - if (pn->left == fn) { + if (left == fn) { w->state = FWS_R; continue; } - if (pn->right == fn) { + if (right == fn) { w->state = FWS_C; - w->leaf = w->node->leaf; + w->leaf = rcu_dereference_protected(w->node->leaf, 1); continue; } #if RT6_DEBUG >= 2 @@ -1770,7 +1882,7 @@ static int fib6_clean_node(struct fib6_walker *w) return 0; } - for (rt = w->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_walker_rt(w) { res = c->func(rt, c->arg); if (res < 0) { w->leaf = rt; @@ -1798,20 +1910,16 @@ static int fib6_clean_node(struct fib6_walker *w) * func is called on each route. * It may return -1 -> delete this route. * 0 -> continue walking - * - * prune==1 -> only immediate children of node (certainly, - * ignoring pure split nodes) will be scanned. */ static void fib6_clean_tree(struct net *net, struct fib6_node *root, int (*func)(struct rt6_info *, void *arg), - bool prune, int sernum, void *arg) + int sernum, void *arg) { struct fib6_cleaner c; c.w.root = root; c.w.func = fib6_clean_node; - c.w.prune = prune; c.w.count = 0; c.w.skip = 0; c.func = func; @@ -1834,10 +1942,10 @@ static void __fib6_clean_all(struct net *net, for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, - func, false, sernum, arg); - write_unlock_bh(&table->tb6_lock); + func, sernum, arg); + spin_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); @@ -1849,22 +1957,6 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *), __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg); } -static int fib6_prune_clone(struct rt6_info *rt, void *arg) -{ - if (rt->rt6i_flags & RTF_CACHE) { - RT6_TRACE("pruning clone %p\n", rt); - return -1; - } - - return 0; -} - -static void fib6_prune_clones(struct net *net, struct fib6_node *fn) -{ - fib6_clean_tree(net, fn, fib6_prune_clone, true, - FIB6_NO_SERNUM_CHANGE, NULL); -} - static void fib6_flush_trees(struct net *net) { int new_sernum = fib6_new_sernum(net); @@ -1876,12 +1968,6 @@ static void fib6_flush_trees(struct net *net) * Garbage collection */ -struct fib6_gc_args -{ - int timeout; - int more; -}; - static int fib6_age(struct rt6_info *rt, void *arg) { struct fib6_gc_args *gc_args = arg; @@ -1890,9 +1976,6 @@ static int fib6_age(struct rt6_info *rt, void *arg) /* * check addrconf expiration here. * Routes are expired even if they are in use. - * - * Also age clones. Note, that clones are aged out - * only if they are not in use now. */ if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) { @@ -1901,31 +1984,14 @@ static int fib6_age(struct rt6_info *rt, void *arg) return -1; } gc_args->more++; - } else if (rt->rt6i_flags & RTF_CACHE) { - if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) - rt->dst.obsolete = DST_OBSOLETE_KILL; - if (atomic_read(&rt->dst.__refcnt) == 1 && - rt->dst.obsolete == DST_OBSOLETE_KILL) { - RT6_TRACE("aging clone %p\n", rt); - return -1; - } else if (rt->rt6i_flags & RTF_GATEWAY) { - struct neighbour *neigh; - __u8 neigh_flags = 0; - - neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway); - if (neigh) { - neigh_flags = neigh->flags; - neigh_release(neigh); - } - if (!(neigh_flags & NTF_ROUTER)) { - RT6_TRACE("purging route %p via non-router but gateway\n", - rt); - return -1; - } - } - gc_args->more++; } + /* Also age clones in the exception table. + * Note, that clones are aged out + * only if they are not in use now. + */ + rt6_age_exceptions(rt, gc_args, now); + return 0; } @@ -1993,7 +2059,8 @@ static int __net_init fib6_net_init(struct net *net) goto out_fib_table_hash; net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN; - net->ipv6.fib6_main_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; + rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf, + net->ipv6.ip6_null_entry); net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); @@ -2004,7 +2071,8 @@ static int __net_init fib6_net_init(struct net *net) if (!net->ipv6.fib6_local_tbl) goto out_fib6_main_tbl; net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL; - net->ipv6.fib6_local_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; + rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf, + net->ipv6.ip6_null_entry); net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); @@ -2134,7 +2202,9 @@ static int ipv6_route_yield(struct fib6_walker *w) return 1; do { - iter->w.leaf = iter->w.leaf->dst.rt6_next; + iter->w.leaf = rcu_dereference_protected( + iter->w.leaf->dst.rt6_next, + lockdep_is_held(&iter->tbl->tb6_lock)); iter->skip--; if (!iter->skip && iter->w.leaf) return 1; @@ -2199,7 +2269,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (!v) goto iter_table; - n = ((struct rt6_info *)v)->dst.rt6_next; + n = rcu_dereference_bh(((struct rt6_info *)v)->dst.rt6_next); if (n) { ++*pos; return n; @@ -2207,9 +2277,9 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) iter_table: ipv6_route_check_sernum(iter); - read_lock(&iter->tbl->tb6_lock); + spin_lock_bh(&iter->tbl->tb6_lock); r = fib6_walk_continue(&iter->w); - read_unlock(&iter->tbl->tb6_lock); + spin_unlock_bh(&iter->tbl->tb6_lock); if (r > 0) { if (v) ++*pos; diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index cdb3728faca7..4a87f9428ca5 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -105,7 +105,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, for (skb = segs; skb; skb = skb->next) { ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff); - if (gso_partial) + if (gso_partial && skb_is_gso(skb)) payload_len = skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)(ipv6h + 1); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 825548680b1e..4212879ff35e 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -593,6 +593,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, case NDISC_REDIRECT: rel_type = ICMP_REDIRECT; rel_code = ICMP_REDIR_HOST; + /* fall through */ default: return 0; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index f5500f5444e9..59fad81e5f7a 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1722,6 +1722,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns case MRT6_ADD_MFC: case MRT6_DEL_MFC: parent = -1; + /* fall through */ case MRT6_ADD_MFC_PROXY: case MRT6_DEL_MFC_PROXY: if (optlen < sizeof(mfc)) diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index a5cd43d75393..437af8c95277 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -353,7 +353,7 @@ static unsigned int ipv6_synproxy_hook(void *priv, nexthdr = ipv6_hdr(skb)->nexthdr; thoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); - if (thoff < 0) + if (thoff < 0 || nexthdr != IPPROTO_TCP) return NF_ACCEPT; th = skb_header_pointer(skb, thoff, sizeof(_th), &_th); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index b263bf3a19f7..977d8900cfd1 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -169,12 +169,13 @@ static unsigned int nf_hashfn(const struct inet_frag_queue *q) return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr); } -static void nf_ct_frag6_expire(unsigned long data) +static void nf_ct_frag6_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; struct net *net; - fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, nf_frag.frags); ip6_expire_frag_queue(net, fq, &nf_frags); diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 46d6dba50698..1d2fb9267d6f 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -290,7 +290,8 @@ nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, else return NF_ACCEPT; } - /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ + /* Only ICMPs can be IP_CT_IS_REPLY: */ + /* fall through */ case IP_CT_NEW: /* Seen it before? This can happen for loopback, retrans, * or local packets. diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index e4462b0ff801..761a473a07c5 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1055,6 +1055,7 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return ipv6_setsockopt(sk, level, optname, optval, optlen); } @@ -1077,6 +1078,7 @@ static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return compat_ipv6_setsockopt(sk, level, optname, optval, optlen); @@ -1138,6 +1140,7 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return ipv6_getsockopt(sk, level, optname, optval, optlen); } @@ -1160,6 +1163,7 @@ static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return compat_ipv6_getsockopt(sk, level, optname, optval, optlen); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 846012eae526..afbc000ad4f2 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -170,12 +170,13 @@ out: } EXPORT_SYMBOL(ip6_expire_frag_queue); -static void ip6_frag_expire(unsigned long data) +static void ip6_frag_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; struct net *net; - fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, ipv6.frags); ip6_expire_frag_queue(net, fq, &ip6_frags); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 26cc9f483b6d..074fac966018 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -44,6 +44,7 @@ #include <linux/seq_file.h> #include <linux/nsproxy.h> #include <linux/slab.h> +#include <linux/jhash.h> #include <net/net_namespace.h> #include <net/snmp.h> #include <net/ipv6.h> @@ -104,6 +105,9 @@ static int rt6_fill_node(struct net *net, struct in6_addr *dst, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags); +static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, + struct in6_addr *daddr, + struct in6_addr *saddr); #ifdef CONFIG_IPV6_ROUTE_INFO static struct rt6_info *rt6_add_route_info(struct net *net, @@ -139,9 +143,11 @@ static void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->rt6i_uncached)) { struct uncached_list *ul = rt->rt6i_uncached_list; + struct net *net = dev_net(rt->dst.dev); spin_lock_bh(&ul->lock); list_del(&rt->rt6i_uncached); + atomic_dec(&net->ipv6.rt6_stats->fib_rt_uncache); spin_unlock_bh(&ul->lock); } } @@ -355,8 +361,10 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net, struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, flags); - if (rt) + if (rt) { rt6_info_init(rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); + } return rt; } @@ -369,17 +377,7 @@ struct rt6_info *ip6_dst_alloc(struct net *net, if (rt) { rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC); - if (rt->rt6i_pcpu) { - int cpu; - - for_each_possible_cpu(cpu) { - struct rt6_info **p; - - p = per_cpu_ptr(rt->rt6i_pcpu, cpu); - /* no one shares rt */ - *p = NULL; - } - } else { + if (!rt->rt6i_pcpu) { dst_release_immediate(&rt->dst); return NULL; } @@ -392,6 +390,7 @@ EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *)dst; + struct rt6_exception_bucket *bucket; struct dst_entry *from = dst->from; struct inet6_dev *idev; @@ -404,6 +403,11 @@ static void ip6_dst_destroy(struct dst_entry *dst) rt->rt6i_idev = NULL; in6_dev_put(idev); } + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, 1); + if (bucket) { + rt->rt6i_exception_bucket = NULL; + kfree(bucket); + } dst->from = NULL; dst_release(from); @@ -478,7 +482,7 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match, } /* - * Route lookup. Any table->tb6_lock is implied. + * Route lookup. rcu_read_lock() should be held. */ static inline struct rt6_info *rt6_device_match(struct net *net, @@ -493,7 +497,7 @@ static inline struct rt6_info *rt6_device_match(struct net *net, if (!oif && ipv6_addr_any(saddr)) goto out; - for (sprt = rt; sprt; sprt = sprt->dst.rt6_next) { + for (sprt = rt; sprt; sprt = rcu_dereference(sprt->dst.rt6_next)) { struct net_device *dev = sprt->dst.dev; if (oif) { @@ -702,6 +706,7 @@ out: } static struct rt6_info *find_rr_leaf(struct fib6_node *fn, + struct rt6_info *leaf, struct rt6_info *rr_head, u32 metric, int oif, int strict, bool *do_rr) @@ -711,7 +716,7 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, match = NULL; cont = NULL; - for (rt = rr_head; rt; rt = rt->dst.rt6_next) { + for (rt = rr_head; rt; rt = rcu_dereference(rt->dst.rt6_next)) { if (rt->rt6i_metric != metric) { cont = rt; break; @@ -720,7 +725,8 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, match = find_match(rt, oif, strict, &mpri, match, do_rr); } - for (rt = fn->leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) { + for (rt = leaf; rt && rt != rr_head; + rt = rcu_dereference(rt->dst.rt6_next)) { if (rt->rt6i_metric != metric) { cont = rt; break; @@ -732,37 +738,59 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, if (match || !cont) return match; - for (rt = cont; rt; rt = rt->dst.rt6_next) + for (rt = cont; rt; rt = rcu_dereference(rt->dst.rt6_next)) match = find_match(rt, oif, strict, &mpri, match, do_rr); return match; } -static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) +static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn, + int oif, int strict) { + struct rt6_info *leaf = rcu_dereference(fn->leaf); struct rt6_info *match, *rt0; - struct net *net; bool do_rr = false; + int key_plen; - rt0 = fn->rr_ptr; + if (!leaf) + return net->ipv6.ip6_null_entry; + + rt0 = rcu_dereference(fn->rr_ptr); if (!rt0) - fn->rr_ptr = rt0 = fn->leaf; + rt0 = leaf; - match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict, + /* Double check to make sure fn is not an intermediate node + * and fn->leaf does not points to its child's leaf + * (This might happen if all routes under fn are deleted from + * the tree and fib6_repair_tree() is called on the node.) + */ + key_plen = rt0->rt6i_dst.plen; +#ifdef CONFIG_IPV6_SUBTREES + if (rt0->rt6i_src.plen) + key_plen = rt0->rt6i_src.plen; +#endif + if (fn->fn_bit != key_plen) + return net->ipv6.ip6_null_entry; + + match = find_rr_leaf(fn, leaf, rt0, rt0->rt6i_metric, oif, strict, &do_rr); if (do_rr) { - struct rt6_info *next = rt0->dst.rt6_next; + struct rt6_info *next = rcu_dereference(rt0->dst.rt6_next); /* no entries matched; do round-robin */ if (!next || next->rt6i_metric != rt0->rt6i_metric) - next = fn->leaf; - - if (next != rt0) - fn->rr_ptr = next; + next = leaf; + + if (next != rt0) { + spin_lock_bh(&leaf->rt6i_table->tb6_lock); + /* make sure next is not being deleted from the tree */ + if (next->rt6i_node) + rcu_assign_pointer(fn->rr_ptr, next); + spin_unlock_bh(&leaf->rt6i_table->tb6_lock); + } } - net = dev_net(rt0->dst.dev); return match ? match : net->ipv6.ip6_null_entry; } @@ -850,13 +878,14 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, static struct fib6_node* fib6_backtrack(struct fib6_node *fn, struct in6_addr *saddr) { - struct fib6_node *pn; + struct fib6_node *pn, *sn; while (1) { if (fn->fn_flags & RTN_TL_ROOT) return NULL; - pn = fn->parent; - if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn) - fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr); + pn = rcu_dereference(fn->parent); + sn = FIB6_SUBTREE(pn); + if (sn && sn != fn) + fn = fib6_lookup(sn, NULL, saddr); else fn = pn; if (fn->fn_flags & RTN_RTINFO) @@ -864,27 +893,57 @@ static struct fib6_node* fib6_backtrack(struct fib6_node *fn, } } +static bool ip6_hold_safe(struct net *net, struct rt6_info **prt, + bool null_fallback) +{ + struct rt6_info *rt = *prt; + + if (dst_hold_safe(&rt->dst)) + return true; + if (null_fallback) { + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } else { + rt = NULL; + } + *prt = rt; + return false; +} + static struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, int flags) { + struct rt6_info *rt, *rt_cache; struct fib6_node *fn; - struct rt6_info *rt; - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: - rt = fn->leaf; - rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags); - if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) - rt = rt6_multipath_select(rt, fl6, fl6->flowi6_oif, flags); + rt = rcu_dereference(fn->leaf); + if (!rt) { + rt = net->ipv6.ip6_null_entry; + } else { + rt = rt6_device_match(net, rt, &fl6->saddr, + fl6->flowi6_oif, flags); + if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) + rt = rt6_multipath_select(rt, fl6, + fl6->flowi6_oif, flags); + } if (rt == net->ipv6.ip6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; } - dst_use(&rt->dst, jiffies); - read_unlock_bh(&table->tb6_lock); + /* Search through exception table */ + rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr); + if (rt_cache) + rt = rt_cache; + + if (ip6_hold_safe(net, &rt, true)) + dst_use_noref(&rt->dst, jiffies); + + rcu_read_unlock(); trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); @@ -938,9 +997,9 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, struct fib6_table *table; table = rt->rt6i_table; - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); err = fib6_add(&table->tb6_root, rt, info, mxc, extack); - write_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); return err; } @@ -1038,7 +1097,7 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt) return pcpu_rt; } -/* It should be called with read_lock_bh(&tb6_lock) acquired */ +/* It should be called with rcu_read_lock() acquired */ static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt) { struct rt6_info *pcpu_rt, **p; @@ -1046,16 +1105,14 @@ static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt) p = this_cpu_ptr(rt->rt6i_pcpu); pcpu_rt = *p; - if (pcpu_rt) { - dst_hold(&pcpu_rt->dst); + if (pcpu_rt && ip6_hold_safe(NULL, &pcpu_rt, false)) rt6_dst_from_metrics_check(pcpu_rt); - } + return pcpu_rt; } static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) { - struct fib6_table *table = rt->rt6i_table; struct rt6_info *pcpu_rt, *prev, **p; pcpu_rt = ip6_rt_pcpu_alloc(rt); @@ -1066,36 +1123,526 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) return net->ipv6.ip6_null_entry; } - read_lock_bh(&table->tb6_lock); - if (rt->rt6i_pcpu) { - p = this_cpu_ptr(rt->rt6i_pcpu); - prev = cmpxchg(p, NULL, pcpu_rt); - if (prev) { - /* If someone did it before us, return prev instead */ - dst_release_immediate(&pcpu_rt->dst); - pcpu_rt = prev; - } - } else { - /* rt has been removed from the fib6 tree - * before we have a chance to acquire the read_lock. - * In this case, don't brother to create a pcpu rt - * since rt is going away anyway. The next - * dst_check() will trigger a re-lookup. - */ - dst_release_immediate(&pcpu_rt->dst); - pcpu_rt = rt; - } dst_hold(&pcpu_rt->dst); + p = this_cpu_ptr(rt->rt6i_pcpu); + prev = cmpxchg(p, NULL, pcpu_rt); + BUG_ON(prev); + rt6_dst_from_metrics_check(pcpu_rt); - read_unlock_bh(&table->tb6_lock); return pcpu_rt; } +/* exception hash table implementation + */ +static DEFINE_SPINLOCK(rt6_exception_lock); + +/* Remove rt6_ex from hash table and free the memory + * Caller must hold rt6_exception_lock + */ +static void rt6_remove_exception(struct rt6_exception_bucket *bucket, + struct rt6_exception *rt6_ex) +{ + struct net *net; + + if (!bucket || !rt6_ex) + return; + + net = dev_net(rt6_ex->rt6i->dst.dev); + rt6_ex->rt6i->rt6i_node = NULL; + hlist_del_rcu(&rt6_ex->hlist); + rt6_release(rt6_ex->rt6i); + kfree_rcu(rt6_ex, rcu); + WARN_ON_ONCE(!bucket->depth); + bucket->depth--; + net->ipv6.rt6_stats->fib_rt_cache--; +} + +/* Remove oldest rt6_ex in bucket and free the memory + * Caller must hold rt6_exception_lock + */ +static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket) +{ + struct rt6_exception *rt6_ex, *oldest = NULL; + + if (!bucket) + return; + + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + if (!oldest || time_before(rt6_ex->stamp, oldest->stamp)) + oldest = rt6_ex; + } + rt6_remove_exception(bucket, oldest); +} + +static u32 rt6_exception_hash(const struct in6_addr *dst, + const struct in6_addr *src) +{ + static u32 seed __read_mostly; + u32 val; + + net_get_random_once(&seed, sizeof(seed)); + val = jhash(dst, sizeof(*dst), seed); + +#ifdef CONFIG_IPV6_SUBTREES + if (src) + val = jhash(src, sizeof(*src), val); +#endif + return hash_32(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); +} + +/* Helper function to find the cached rt in the hash table + * and update bucket pointer to point to the bucket for this + * (daddr, saddr) pair + * Caller must hold rt6_exception_lock + */ +static struct rt6_exception * +__rt6_find_exception_spinlock(struct rt6_exception_bucket **bucket, + const struct in6_addr *daddr, + const struct in6_addr *saddr) +{ + struct rt6_exception *rt6_ex; + u32 hval; + + if (!(*bucket) || !daddr) + return NULL; + + hval = rt6_exception_hash(daddr, saddr); + *bucket += hval; + + hlist_for_each_entry(rt6_ex, &(*bucket)->chain, hlist) { + struct rt6_info *rt6 = rt6_ex->rt6i; + bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); + +#ifdef CONFIG_IPV6_SUBTREES + if (matched && saddr) + matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); +#endif + if (matched) + return rt6_ex; + } + return NULL; +} + +/* Helper function to find the cached rt in the hash table + * and update bucket pointer to point to the bucket for this + * (daddr, saddr) pair + * Caller must hold rcu_read_lock() + */ +static struct rt6_exception * +__rt6_find_exception_rcu(struct rt6_exception_bucket **bucket, + const struct in6_addr *daddr, + const struct in6_addr *saddr) +{ + struct rt6_exception *rt6_ex; + u32 hval; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (!(*bucket) || !daddr) + return NULL; + + hval = rt6_exception_hash(daddr, saddr); + *bucket += hval; + + hlist_for_each_entry_rcu(rt6_ex, &(*bucket)->chain, hlist) { + struct rt6_info *rt6 = rt6_ex->rt6i; + bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); + +#ifdef CONFIG_IPV6_SUBTREES + if (matched && saddr) + matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); +#endif + if (matched) + return rt6_ex; + } + return NULL; +} + +static int rt6_insert_exception(struct rt6_info *nrt, + struct rt6_info *ort) +{ + struct net *net = dev_net(ort->dst.dev); + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + int err = 0; + + /* ort can't be a cache or pcpu route */ + if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)) + ort = (struct rt6_info *)ort->dst.from; + WARN_ON_ONCE(ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)); + + spin_lock_bh(&rt6_exception_lock); + + if (ort->exception_bucket_flushed) { + err = -EINVAL; + goto out; + } + + bucket = rcu_dereference_protected(ort->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + if (!bucket) { + bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket), + GFP_ATOMIC); + if (!bucket) { + err = -ENOMEM; + goto out; + } + rcu_assign_pointer(ort->rt6i_exception_bucket, bucket); + } + +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates ort is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (ort->rt6i_src.plen) + src_key = &nrt->rt6i_src.addr; +#endif + + /* Update rt6i_prefsrc as it could be changed + * in rt6_remove_prefsrc() + */ + nrt->rt6i_prefsrc = ort->rt6i_prefsrc; + /* rt6_mtu_change() might lower mtu on ort. + * Only insert this exception route if its mtu + * is less than ort's mtu value. + */ + if (nrt->rt6i_pmtu >= dst_mtu(&ort->dst)) { + err = -EINVAL; + goto out; + } + + rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr, + src_key); + if (rt6_ex) + rt6_remove_exception(bucket, rt6_ex); + + rt6_ex = kzalloc(sizeof(*rt6_ex), GFP_ATOMIC); + if (!rt6_ex) { + err = -ENOMEM; + goto out; + } + rt6_ex->rt6i = nrt; + rt6_ex->stamp = jiffies; + atomic_inc(&nrt->rt6i_ref); + nrt->rt6i_node = ort->rt6i_node; + hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain); + bucket->depth++; + net->ipv6.rt6_stats->fib_rt_cache++; + + if (bucket->depth > FIB6_MAX_DEPTH) + rt6_exception_remove_oldest(bucket); + +out: + spin_unlock_bh(&rt6_exception_lock); + + /* Update fn->fn_sernum to invalidate all cached dst */ + if (!err) { + fib6_update_sernum(ort); + fib6_force_start_gc(net); + } + + return err; +} + +void rt6_flush_exceptions(struct rt6_info *rt) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + struct hlist_node *tmp; + int i; + + spin_lock_bh(&rt6_exception_lock); + /* Prevent rt6_insert_exception() to recreate the bucket list */ + rt->exception_bucket_flushed = 1; + + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + if (!bucket) + goto out; + + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) + rt6_remove_exception(bucket, rt6_ex); + WARN_ON_ONCE(bucket->depth); + bucket++; + } + +out: + spin_unlock_bh(&rt6_exception_lock); +} + +/* Find cached rt in the hash table inside passed in rt + * Caller has to hold rcu_read_lock() + */ +static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, + struct in6_addr *daddr, + struct in6_addr *saddr) +{ + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + struct rt6_info *res = NULL; + + bucket = rcu_dereference(rt->rt6i_exception_bucket); + +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates rt is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (rt->rt6i_src.plen) + src_key = saddr; +#endif + rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); + + if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i)) + res = rt6_ex->rt6i; + + return res; +} + +/* Remove the passed in cached rt from the hash table that contains it */ +int rt6_remove_exception_rt(struct rt6_info *rt) +{ + struct rt6_info *from = (struct rt6_info *)rt->dst.from; + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + int err; + + if (!from || + !(rt->rt6i_flags & RTF_CACHE)) + return -EINVAL; + + if (!rcu_access_pointer(from->rt6i_exception_bucket)) + return -ENOENT; + + spin_lock_bh(&rt6_exception_lock); + bucket = rcu_dereference_protected(from->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates 'from' is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (from->rt6i_src.plen) + src_key = &rt->rt6i_src.addr; +#endif + rt6_ex = __rt6_find_exception_spinlock(&bucket, + &rt->rt6i_dst.addr, + src_key); + if (rt6_ex) { + rt6_remove_exception(bucket, rt6_ex); + err = 0; + } else { + err = -ENOENT; + } + + spin_unlock_bh(&rt6_exception_lock); + return err; +} + +/* Find rt6_ex which contains the passed in rt cache and + * refresh its stamp + */ +static void rt6_update_exception_stamp_rt(struct rt6_info *rt) +{ + struct rt6_info *from = (struct rt6_info *)rt->dst.from; + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + + if (!from || + !(rt->rt6i_flags & RTF_CACHE)) + return; + + rcu_read_lock(); + bucket = rcu_dereference(from->rt6i_exception_bucket); + +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates 'from' is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (from->rt6i_src.plen) + src_key = &rt->rt6i_src.addr; +#endif + rt6_ex = __rt6_find_exception_rcu(&bucket, + &rt->rt6i_dst.addr, + src_key); + if (rt6_ex) + rt6_ex->stamp = jiffies; + + rcu_read_unlock(); +} + +static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + int i; + + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + rt6_ex->rt6i->rt6i_prefsrc.plen = 0; + } + bucket++; + } + } +} + +static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + int i; + + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + struct rt6_info *entry = rt6_ex->rt6i; + /* For RTF_CACHE with rt6i_pmtu == 0 + * (i.e. a redirected route), + * the metrics of its rt->dst.from has already + * been updated. + */ + if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu) + entry->rt6i_pmtu = mtu; + } + bucket++; + } + } +} + +#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) + +static void rt6_exceptions_clean_tohost(struct rt6_info *rt, + struct in6_addr *gateway) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + struct hlist_node *tmp; + int i; + + if (!rcu_access_pointer(rt->rt6i_exception_bucket)) + return; + + spin_lock_bh(&rt6_exception_lock); + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry_safe(rt6_ex, tmp, + &bucket->chain, hlist) { + struct rt6_info *entry = rt6_ex->rt6i; + + if ((entry->rt6i_flags & RTF_CACHE_GATEWAY) == + RTF_CACHE_GATEWAY && + ipv6_addr_equal(gateway, + &entry->rt6i_gateway)) { + rt6_remove_exception(bucket, rt6_ex); + } + } + bucket++; + } + } + + spin_unlock_bh(&rt6_exception_lock); +} + +static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, + struct rt6_exception *rt6_ex, + struct fib6_gc_args *gc_args, + unsigned long now) +{ + struct rt6_info *rt = rt6_ex->rt6i; + + /* we are pruning and obsoleting aged-out and non gateway exceptions + * even if others have still references to them, so that on next + * dst_check() such references can be dropped. + * EXPIRES exceptions - e.g. pmtu-generated ones are pruned when + * expired, independently from their aging, as per RFC 8201 section 4 + */ + if (!(rt->rt6i_flags & RTF_EXPIRES) && + time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { + RT6_TRACE("aging clone %p\n", rt); + rt6_remove_exception(bucket, rt6_ex); + return; + } else if (rt->rt6i_flags & RTF_GATEWAY) { + struct neighbour *neigh; + __u8 neigh_flags = 0; + + neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway); + if (neigh) { + neigh_flags = neigh->flags; + neigh_release(neigh); + } + if (!(neigh_flags & NTF_ROUTER)) { + RT6_TRACE("purging route %p via non-router but gateway\n", + rt); + rt6_remove_exception(bucket, rt6_ex); + return; + } + } else if (__rt6_check_expired(rt)) { + RT6_TRACE("purging expired route %p\n", rt); + rt6_remove_exception(bucket, rt6_ex); + return; + } + gc_args->more++; +} + +void rt6_age_exceptions(struct rt6_info *rt, + struct fib6_gc_args *gc_args, + unsigned long now) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + struct hlist_node *tmp; + int i; + + if (!rcu_access_pointer(rt->rt6i_exception_bucket)) + return; + + spin_lock_bh(&rt6_exception_lock); + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry_safe(rt6_ex, tmp, + &bucket->chain, hlist) { + rt6_age_examine_exception(bucket, rt6_ex, + gc_args, now); + } + bucket++; + } + } + spin_unlock_bh(&rt6_exception_lock); +} + struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, int flags) { struct fib6_node *fn, *saved_fn; - struct rt6_info *rt; + struct rt6_info *rt, *rt_cache; int strict = 0; strict |= flags & RT6_LOOKUP_F_IFACE; @@ -1103,7 +1650,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, if (net->ipv6.devconf_all->forwarding == 0) strict |= RT6_LOOKUP_F_REACHABLE; - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); saved_fn = fn; @@ -1112,7 +1659,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, oif = 0; redo_rt6_select: - rt = rt6_select(fn, oif, strict); + rt = rt6_select(net, fn, oif, strict); if (rt->rt6i_nsiblings) rt = rt6_multipath_select(rt, fl6, oif, strict); if (rt == net->ipv6.ip6_null_entry) { @@ -1127,13 +1674,22 @@ redo_rt6_select: } } + /*Search through exception table */ + rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr); + if (rt_cache) + rt = rt_cache; - if (rt == net->ipv6.ip6_null_entry || (rt->rt6i_flags & RTF_CACHE)) { - dst_use(&rt->dst, jiffies); - read_unlock_bh(&table->tb6_lock); - - rt6_dst_from_metrics_check(rt); - + if (rt == net->ipv6.ip6_null_entry) { + rcu_read_unlock(); + dst_hold(&rt->dst); + trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); + return rt; + } else if (rt->rt6i_flags & RTF_CACHE) { + if (ip6_hold_safe(net, &rt, true)) { + dst_use_noref(&rt->dst, jiffies); + rt6_dst_from_metrics_check(rt); + } + rcu_read_unlock(); trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); return rt; } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && @@ -1146,8 +1702,14 @@ redo_rt6_select: struct rt6_info *uncached_rt; - dst_use(&rt->dst, jiffies); - read_unlock_bh(&table->tb6_lock); + if (ip6_hold_safe(net, &rt, true)) { + dst_use_noref(&rt->dst, jiffies); + } else { + rcu_read_unlock(); + uncached_rt = rt; + goto uncached_rt_out; + } + rcu_read_unlock(); uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL); dst_release(&rt->dst); @@ -1157,11 +1719,13 @@ redo_rt6_select: * No need for another dst_hold() */ rt6_uncached_list_add(uncached_rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache); } else { uncached_rt = net->ipv6.ip6_null_entry; dst_hold(&uncached_rt->dst); } +uncached_rt_out: trace_fib6_table_lookup(net, uncached_rt, table->tb6_id, fl6); return uncached_rt; @@ -1170,26 +1734,28 @@ redo_rt6_select: struct rt6_info *pcpu_rt; - rt->dst.lastuse = jiffies; - rt->dst.__use++; + dst_use_noref(&rt->dst, jiffies); + local_bh_disable(); pcpu_rt = rt6_get_pcpu_route(rt); - if (pcpu_rt) { - read_unlock_bh(&table->tb6_lock); - } else { - /* We have to do the read_unlock first - * because rt6_make_pcpu_route() may trigger - * ip6_dst_gc() which will take the write_lock. - */ - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); - pcpu_rt = rt6_make_pcpu_route(rt); - dst_release(&rt->dst); + if (!pcpu_rt) { + /* atomic_inc_not_zero() is needed when using rcu */ + if (atomic_inc_not_zero(&rt->rt6i_ref)) { + /* No dst_hold() on rt is needed because grabbing + * rt->rt6i_ref makes sure rt can't be released. + */ + pcpu_rt = rt6_make_pcpu_route(rt); + rt6_release(rt); + } else { + /* rt is already removed from tree */ + pcpu_rt = net->ipv6.ip6_null_entry; + dst_hold(&pcpu_rt->dst); + } } - + local_bh_enable(); + rcu_read_unlock(); trace_fib6_table_lookup(net, pcpu_rt, table->tb6_id, fl6); return pcpu_rt; - } } EXPORT_SYMBOL_GPL(ip6_pol_route); @@ -1325,9 +1891,10 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori struct dst_entry *new = NULL; rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, 1, - DST_OBSOLETE_NONE, 0); + DST_OBSOLETE_DEAD, 0); if (rt) { rt6_info_init(rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); new = &rt->dst; new->__use = 1; @@ -1491,23 +2058,17 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (!rt6_cache_allowed_for_pmtu(rt6)) { rt6_do_update_pmtu(rt6, mtu); + /* update rt6_ex->stamp for cache */ + if (rt6->rt6i_flags & RTF_CACHE) + rt6_update_exception_stamp_rt(rt6); } else if (daddr) { struct rt6_info *nrt6; nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr); if (nrt6) { rt6_do_update_pmtu(nrt6, mtu); - - /* ip6_ins_rt(nrt6) will bump the - * rt6->rt6i_node->fn_sernum - * which will fail the next rt6_check() and - * invalidate the sk->sk_dst_cache. - */ - ip6_ins_rt(nrt6); - /* Release the reference taken in - * ip6_rt_cache_alloc() - */ - dst_release(&nrt6->dst); + if (rt6_insert_exception(nrt6, rt6)) + dst_release_immediate(&nrt6->dst); } } } @@ -1571,7 +2132,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, int flags) { struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; - struct rt6_info *rt; + struct rt6_info *rt, *rt_cache; struct fib6_node *fn; /* Get the "current" route for this destination and @@ -1584,10 +2145,10 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, * routes. */ - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_node_rt_rcu(fn) { if (rt6_check_expired(rt)) continue; if (rt->dst.error) @@ -1596,8 +2157,23 @@ restart: continue; if (fl6->flowi6_oif != rt->dst.dev->ifindex) continue; - if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) + /* rt_cache's gateway might be different from its 'parent' + * in the case of an ip redirect. + * So we keep searching in the exception table if the gateway + * is different. + */ + if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) { + rt_cache = rt6_find_cached_rt(rt, + &fl6->daddr, + &fl6->saddr); + if (rt_cache && + ipv6_addr_equal(&rdfl->gateway, + &rt_cache->rt6i_gateway)) { + rt = rt_cache; + break; + } continue; + } break; } @@ -1615,9 +2191,9 @@ restart: } out: - dst_hold(&rt->dst); + ip6_hold_safe(net, &rt, true); - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); return rt; @@ -1766,6 +2342,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, * do proper release of the net_device */ rt6_uncached_list_add(rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache); dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0); @@ -2216,9 +2793,9 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) } table = rt->rt6i_table; - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); err = fib6_del(rt, info); - write_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); out: ip6_rt_put(rt); @@ -2244,7 +2821,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) if (rt == net->ipv6.ip6_null_entry) goto out_put; table = rt->rt6i_table; - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); if (rt->rt6i_nsiblings && cfg->fc_delete_all_nh) { struct rt6_info *sibling, *next_sibling; @@ -2274,7 +2851,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) err = fib6_del(rt, info); out_unlock: - write_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); out_put: ip6_rt_put(rt); @@ -2288,9 +2865,9 @@ out_put: static int ip6_route_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { + struct rt6_info *rt, *rt_cache; struct fib6_table *table; struct fib6_node *fn; - struct rt6_info *rt; int err = -ESRCH; table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table); @@ -2299,17 +2876,22 @@ static int ip6_route_del(struct fib6_config *cfg, return err; } - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_locate(&table->tb6_root, &cfg->fc_dst, cfg->fc_dst_len, - &cfg->fc_src, cfg->fc_src_len); + &cfg->fc_src, cfg->fc_src_len, + !(cfg->fc_flags & RTF_CACHE)); if (fn) { - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { - if ((rt->rt6i_flags & RTF_CACHE) && - !(cfg->fc_flags & RTF_CACHE)) - continue; + for_each_fib6_node_rt_rcu(fn) { + if (cfg->fc_flags & RTF_CACHE) { + rt_cache = rt6_find_cached_rt(rt, &cfg->fc_dst, + &cfg->fc_src); + if (!rt_cache) + continue; + rt = rt_cache; + } if (cfg->fc_ifindex && (!rt->dst.dev || rt->dst.dev->ifindex != cfg->fc_ifindex)) @@ -2321,8 +2903,9 @@ static int ip6_route_del(struct fib6_config *cfg, continue; if (cfg->fc_protocol && cfg->fc_protocol != rt->rt6i_protocol) continue; - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); + if (!dst_hold_safe(&rt->dst)) + break; + rcu_read_unlock(); /* if gateway was specified only delete the one hop */ if (cfg->fc_flags & RTF_GATEWAY) @@ -2331,7 +2914,7 @@ static int ip6_route_del(struct fib6_config *cfg, return __ip6_del_rt_siblings(rt, cfg); } } - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); return err; } @@ -2435,8 +3018,14 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu nrt->rt6i_protocol = RTPROT_REDIRECT; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; - if (ip6_ins_rt(nrt)) - goto out_release; + /* No need to remove rt from the exception table if rt is + * a cached route because rt6_insert_exception() will + * takes care of it + */ + if (rt6_insert_exception(nrt, rt)) { + dst_release_immediate(&nrt->dst); + goto out; + } netevent.old = &rt->dst; netevent.new = &nrt->dst; @@ -2444,17 +3033,6 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu netevent.neigh = neigh; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); - if (rt->rt6i_flags & RTF_CACHE) { - rt = (struct rt6_info *) dst_clone(&rt->dst); - ip6_del_rt(rt); - } - -out_release: - /* Release the reference taken in - * ip6_rt_cache_alloc() - */ - dst_release(&nrt->dst); - out: neigh_release(neigh); } @@ -2511,23 +3089,23 @@ static struct rt6_info *rt6_get_route_info(struct net *net, if (!table) return NULL; - read_lock_bh(&table->tb6_lock); - fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0); + rcu_read_lock(); + fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0, true); if (!fn) goto out; - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_node_rt_rcu(fn) { if (rt->dst.dev->ifindex != ifindex) continue; if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY)) continue; if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr)) continue; - dst_hold(&rt->dst); + ip6_hold_safe(NULL, &rt, false); break; } out: - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); return rt; } @@ -2573,16 +3151,16 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev if (!table) return NULL; - read_lock_bh(&table->tb6_lock); - for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { + rcu_read_lock(); + for_each_fib6_node_rt_rcu(&table->tb6_root) { if (dev == rt->dst.dev && ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&rt->rt6i_gateway, addr)) break; } if (rt) - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); + ip6_hold_safe(NULL, &rt, false); + rcu_read_unlock(); return rt; } @@ -2620,17 +3198,20 @@ static void __rt6_purge_dflt_routers(struct fib6_table *table) struct rt6_info *rt; restart: - read_lock_bh(&table->tb6_lock); - for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { + rcu_read_lock(); + for_each_fib6_node_rt_rcu(&table->tb6_root) { if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) && (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) { - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); - ip6_del_rt(rt); + if (dst_hold_safe(&rt->dst)) { + rcu_read_unlock(); + ip6_del_rt(rt); + } else { + rcu_read_unlock(); + } goto restart; } } - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER; } @@ -2818,8 +3399,12 @@ static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg) if (((void *)rt->dst.dev == dev || !dev) && rt != net->ipv6.ip6_null_entry && ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) { + spin_lock_bh(&rt6_exception_lock); /* remove prefsrc entry */ rt->rt6i_prefsrc.plen = 0; + /* need to update cache as well */ + rt6_exceptions_remove_prefsrc(rt); + spin_unlock_bh(&rt6_exception_lock); } return 0; } @@ -2836,18 +3421,23 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) } #define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY) -#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) /* Remove routers and update dst entries when gateway turn into host. */ static int fib6_clean_tohost(struct rt6_info *rt, void *arg) { struct in6_addr *gateway = (struct in6_addr *)arg; - if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) || - ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) && - ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { + if (((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) && + ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { return -1; } + + /* Further clean up cached routes in exception table. + * This is needed because cached route may have a different + * gateway than its 'parent' in the case of an ip redirect. + */ + rt6_exceptions_clean_tohost(rt, gateway); + return 0; } @@ -2926,19 +3516,14 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) if (rt->dst.dev == arg->dev && dst_metric_raw(&rt->dst, RTAX_MTU) && !dst_metric_locked(&rt->dst, RTAX_MTU)) { - if (rt->rt6i_flags & RTF_CACHE) { - /* For RTF_CACHE with rt6i_pmtu == 0 - * (i.e. a redirected route), - * the metrics of its rt->dst.from has already - * been updated. - */ - if (rt->rt6i_pmtu && rt->rt6i_pmtu > arg->mtu) - rt->rt6i_pmtu = arg->mtu; - } else if (dst_mtu(&rt->dst) >= arg->mtu || - (dst_mtu(&rt->dst) < arg->mtu && - dst_mtu(&rt->dst) == idev->cnf.mtu6)) { + spin_lock_bh(&rt6_exception_lock); + if (dst_mtu(&rt->dst) >= arg->mtu || + (dst_mtu(&rt->dst) < arg->mtu && + dst_mtu(&rt->dst) == idev->cnf.mtu6)) { dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); } + rt6_exceptions_update_pmtu(rt, arg->mtu); + spin_unlock_bh(&rt6_exception_lock); } return 0; } @@ -3839,7 +4424,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n", net->ipv6.rt6_stats->fib_nodes, net->ipv6.rt6_stats->fib_route_nodes, - net->ipv6.rt6_stats->fib_rt_alloc, + atomic_read(&net->ipv6.rt6_stats->fib_rt_alloc), net->ipv6.rt6_stats->fib_rt_entries, net->ipv6.rt6_stats->fib_rt_cache, dst_entries_get_slow(&net->ipv6.ip6_dst_ops), diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 64d94afa427f..ae83615b7f6d 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1577,8 +1577,9 @@ do_time_wait: refcounted = false; goto process; } - /* Fall through to ACK */ } + /* to ACK */ + /* fall through */ case TCP_TW_ACK: tcp_v6_timewait_ack(sk, skb); break; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 11d1314ab6c5..4ed9f8cc3b6a 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -152,6 +152,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) switch (nexthdr) { case NEXTHDR_FRAGMENT: onlyproto = 1; + /* fall through */ case NEXTHDR_ROUTING: case NEXTHDR_HOP: case NEXTHDR_DEST: diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index ac598ec90589..d21a9d128d3e 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1867,6 +1867,7 @@ static int ipx_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) rc = -EPERM; if (!capable(CAP_NET_ADMIN)) break; + /* fall through */ case SIOCGIFADDR: rc = ipxitf_ioctl(cmd, argp); break; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 7135f4645d3a..f5179424eaf1 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -406,7 +406,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla if (nla_put_u16(skb, L2TP_ATTR_UDP_SPORT, ntohs(inet->inet_sport)) || nla_put_u16(skb, L2TP_ATTR_UDP_DPORT, ntohs(inet->inet_dport))) goto nla_put_failure; - /* NOBREAK */ + /* fall through */ case L2TP_ENCAPTYPE_IP: #if IS_ENABLED(CONFIG_IPV6) if (np) { diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index e15314e3b464..db6e0afe3a20 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -127,8 +127,8 @@ static struct lapb_cb *lapb_create_cb(void) skb_queue_head_init(&lapb->write_queue); skb_queue_head_init(&lapb->ack_queue); - init_timer(&lapb->t1timer); - init_timer(&lapb->t2timer); + timer_setup(&lapb->t1timer, NULL, 0); + timer_setup(&lapb->t2timer, NULL, 0); lapb->t1 = LAPB_DEFAULT_T1; lapb->t2 = LAPB_DEFAULT_T2; diff --git a/net/lapb/lapb_timer.c b/net/lapb/lapb_timer.c index 1a5535bc3b8d..8bb469cb3abe 100644 --- a/net/lapb/lapb_timer.c +++ b/net/lapb/lapb_timer.c @@ -35,15 +35,14 @@ #include <linux/interrupt.h> #include <net/lapb.h> -static void lapb_t1timer_expiry(unsigned long); -static void lapb_t2timer_expiry(unsigned long); +static void lapb_t1timer_expiry(struct timer_list *); +static void lapb_t2timer_expiry(struct timer_list *); void lapb_start_t1timer(struct lapb_cb *lapb) { del_timer(&lapb->t1timer); - lapb->t1timer.data = (unsigned long)lapb; - lapb->t1timer.function = &lapb_t1timer_expiry; + lapb->t1timer.function = (TIMER_FUNC_TYPE)lapb_t1timer_expiry; lapb->t1timer.expires = jiffies + lapb->t1; add_timer(&lapb->t1timer); @@ -53,8 +52,7 @@ void lapb_start_t2timer(struct lapb_cb *lapb) { del_timer(&lapb->t2timer); - lapb->t2timer.data = (unsigned long)lapb; - lapb->t2timer.function = &lapb_t2timer_expiry; + lapb->t2timer.function = (TIMER_FUNC_TYPE)lapb_t2timer_expiry; lapb->t2timer.expires = jiffies + lapb->t2; add_timer(&lapb->t2timer); @@ -75,9 +73,9 @@ int lapb_t1timer_running(struct lapb_cb *lapb) return timer_pending(&lapb->t1timer); } -static void lapb_t2timer_expiry(unsigned long param) +static void lapb_t2timer_expiry(struct timer_list *t) { - struct lapb_cb *lapb = (struct lapb_cb *)param; + struct lapb_cb *lapb = from_timer(lapb, t, t2timer); if (lapb->condition & LAPB_ACK_PENDING_CONDITION) { lapb->condition &= ~LAPB_ACK_PENDING_CONDITION; @@ -85,9 +83,9 @@ static void lapb_t2timer_expiry(unsigned long param) } } -static void lapb_t1timer_expiry(unsigned long param) +static void lapb_t1timer_expiry(struct timer_list *t) { - struct lapb_cb *lapb = (struct lapb_cb *)param; + struct lapb_cb *lapb = from_timer(lapb, t, t1timer); switch (lapb->state) { diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index 282912245938..80f25ff2f24b 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -6,6 +6,7 @@ mac80211-y := \ driver-ops.o \ sta_info.o \ wep.o \ + aead_api.o \ wpa.o \ scan.o offchannel.o \ ht.o agg-tx.o agg-rx.o \ @@ -15,8 +16,6 @@ mac80211-y := \ rate.o \ michael.o \ tkip.o \ - aes_ccm.o \ - aes_gcm.o \ aes_cmac.o \ aes_gmac.o \ fils_aead.o \ diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aead_api.c index a4e0d59a40dd..160f9df30402 100644 --- a/net/mac80211/aes_ccm.c +++ b/net/mac80211/aead_api.c @@ -1,6 +1,7 @@ /* * Copyright 2003-2004, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. + * Copyright 2014-2015, Qualcomm Atheros, Inc. * * Rewrite: Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> * @@ -12,30 +13,29 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/err.h> +#include <linux/scatterlist.h> #include <crypto/aead.h> -#include <net/mac80211.h> -#include "key.h" -#include "aes_ccm.h" +#include "aead_api.h" -int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic, - size_t mic_len) +int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len, + u8 *data, size_t data_len, u8 *mic) { + size_t mic_len = crypto_aead_authsize(tfm); struct scatterlist sg[3]; struct aead_request *aead_req; int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); u8 *__aad; - aead_req = kzalloc(reqsize + CCM_AAD_LEN, GFP_ATOMIC); + aead_req = kzalloc(reqsize + aad_len, GFP_ATOMIC); if (!aead_req) return -ENOMEM; __aad = (u8 *)aead_req + reqsize; - memcpy(__aad, aad, CCM_AAD_LEN); + memcpy(__aad, aad, aad_len); sg_init_table(sg, 3); - sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad)); + sg_set_buf(&sg[0], __aad, aad_len); sg_set_buf(&sg[1], data, data_len); sg_set_buf(&sg[2], mic, mic_len); @@ -49,10 +49,10 @@ int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, return 0; } -int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic, - size_t mic_len) +int aead_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len, + u8 *data, size_t data_len, u8 *mic) { + size_t mic_len = crypto_aead_authsize(tfm); struct scatterlist sg[3]; struct aead_request *aead_req; int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); @@ -62,15 +62,15 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, if (data_len == 0) return -EINVAL; - aead_req = kzalloc(reqsize + CCM_AAD_LEN, GFP_ATOMIC); + aead_req = kzalloc(reqsize + aad_len, GFP_ATOMIC); if (!aead_req) return -ENOMEM; __aad = (u8 *)aead_req + reqsize; - memcpy(__aad, aad, CCM_AAD_LEN); + memcpy(__aad, aad, aad_len); sg_init_table(sg, 3); - sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad)); + sg_set_buf(&sg[0], __aad, aad_len); sg_set_buf(&sg[1], data, data_len); sg_set_buf(&sg[2], mic, mic_len); @@ -84,14 +84,14 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, return err; } -struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[], - size_t key_len, - size_t mic_len) +struct crypto_aead * +aead_key_setup_encrypt(const char *alg, const u8 key[], + size_t key_len, size_t mic_len) { struct crypto_aead *tfm; int err; - tfm = crypto_alloc_aead("ccm(aes)", 0, CRYPTO_ALG_ASYNC); + tfm = crypto_alloc_aead(alg, 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) return tfm; @@ -109,7 +109,7 @@ free_aead: return ERR_PTR(err); } -void ieee80211_aes_key_free(struct crypto_aead *tfm) +void aead_key_free(struct crypto_aead *tfm) { crypto_free_aead(tfm); } diff --git a/net/mac80211/aead_api.h b/net/mac80211/aead_api.h new file mode 100644 index 000000000000..5e39ea843bbf --- /dev/null +++ b/net/mac80211/aead_api.h @@ -0,0 +1,27 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _AEAD_API_H +#define _AEAD_API_H + +#include <crypto/aead.h> +#include <linux/crypto.h> + +struct crypto_aead * +aead_key_setup_encrypt(const char *alg, const u8 key[], + size_t key_len, size_t mic_len); + +int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, + size_t aad_len, u8 *data, + size_t data_len, u8 *mic); + +int aead_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, + size_t aad_len, u8 *data, + size_t data_len, u8 *mic); + +void aead_key_free(struct crypto_aead *tfm); + +#endif /* _AEAD_API_H */ diff --git a/net/mac80211/aes_ccm.h b/net/mac80211/aes_ccm.h index fcd3254c5cf0..e9b7ca0bde5b 100644 --- a/net/mac80211/aes_ccm.h +++ b/net/mac80211/aes_ccm.h @@ -10,19 +10,39 @@ #ifndef AES_CCM_H #define AES_CCM_H -#include <linux/crypto.h> +#include "aead_api.h" #define CCM_AAD_LEN 32 -struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[], - size_t key_len, - size_t mic_len); -int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic, - size_t mic_len); -int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic, - size_t mic_len); -void ieee80211_aes_key_free(struct crypto_aead *tfm); +static inline struct crypto_aead * +ieee80211_aes_key_setup_encrypt(const u8 key[], size_t key_len, size_t mic_len) +{ + return aead_key_setup_encrypt("ccm(aes)", key, key_len, mic_len); +} + +static inline int +ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, + u8 *b_0, u8 *aad, u8 *data, + size_t data_len, u8 *mic) +{ + return aead_encrypt(tfm, b_0, aad + 2, + be16_to_cpup((__be16 *)aad), + data, data_len, mic); +} + +static inline int +ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, + u8 *b_0, u8 *aad, u8 *data, + size_t data_len, u8 *mic) +{ + return aead_decrypt(tfm, b_0, aad + 2, + be16_to_cpup((__be16 *)aad), + data, data_len, mic); +} + +static inline void ieee80211_aes_key_free(struct crypto_aead *tfm) +{ + return aead_key_free(tfm); +} #endif /* AES_CCM_H */ diff --git a/net/mac80211/aes_gcm.c b/net/mac80211/aes_gcm.c deleted file mode 100644 index 8a4397cc1b08..000000000000 --- a/net/mac80211/aes_gcm.c +++ /dev/null @@ -1,109 +0,0 @@ -/* - * Copyright 2014-2015, Qualcomm Atheros, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/err.h> -#include <crypto/aead.h> - -#include <net/mac80211.h> -#include "key.h" -#include "aes_gcm.h" - -int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic) -{ - struct scatterlist sg[3]; - struct aead_request *aead_req; - int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); - u8 *__aad; - - aead_req = kzalloc(reqsize + GCM_AAD_LEN, GFP_ATOMIC); - if (!aead_req) - return -ENOMEM; - - __aad = (u8 *)aead_req + reqsize; - memcpy(__aad, aad, GCM_AAD_LEN); - - sg_init_table(sg, 3); - sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad)); - sg_set_buf(&sg[1], data, data_len); - sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN); - - aead_request_set_tfm(aead_req, tfm); - aead_request_set_crypt(aead_req, sg, sg, data_len, j_0); - aead_request_set_ad(aead_req, sg[0].length); - - crypto_aead_encrypt(aead_req); - kzfree(aead_req); - return 0; -} - -int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic) -{ - struct scatterlist sg[3]; - struct aead_request *aead_req; - int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); - u8 *__aad; - int err; - - if (data_len == 0) - return -EINVAL; - - aead_req = kzalloc(reqsize + GCM_AAD_LEN, GFP_ATOMIC); - if (!aead_req) - return -ENOMEM; - - __aad = (u8 *)aead_req + reqsize; - memcpy(__aad, aad, GCM_AAD_LEN); - - sg_init_table(sg, 3); - sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad)); - sg_set_buf(&sg[1], data, data_len); - sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN); - - aead_request_set_tfm(aead_req, tfm); - aead_request_set_crypt(aead_req, sg, sg, - data_len + IEEE80211_GCMP_MIC_LEN, j_0); - aead_request_set_ad(aead_req, sg[0].length); - - err = crypto_aead_decrypt(aead_req); - kzfree(aead_req); - - return err; -} - -struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[], - size_t key_len) -{ - struct crypto_aead *tfm; - int err; - - tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) - return tfm; - - err = crypto_aead_setkey(tfm, key, key_len); - if (err) - goto free_aead; - err = crypto_aead_setauthsize(tfm, IEEE80211_GCMP_MIC_LEN); - if (err) - goto free_aead; - - return tfm; - -free_aead: - crypto_free_aead(tfm); - return ERR_PTR(err); -} - -void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm) -{ - crypto_free_aead(tfm); -} diff --git a/net/mac80211/aes_gcm.h b/net/mac80211/aes_gcm.h index 55aed5352494..d2b096033009 100644 --- a/net/mac80211/aes_gcm.h +++ b/net/mac80211/aes_gcm.h @@ -9,16 +9,38 @@ #ifndef AES_GCM_H #define AES_GCM_H -#include <linux/crypto.h> +#include "aead_api.h" #define GCM_AAD_LEN 32 -int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic); -int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic); -struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[], - size_t key_len); -void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm); +static inline int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, + u8 *j_0, u8 *aad, u8 *data, + size_t data_len, u8 *mic) +{ + return aead_encrypt(tfm, j_0, aad + 2, + be16_to_cpup((__be16 *)aad), + data, data_len, mic); +} + +static inline int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, + u8 *j_0, u8 *aad, u8 *data, + size_t data_len, u8 *mic) +{ + return aead_decrypt(tfm, j_0, aad + 2, + be16_to_cpup((__be16 *)aad), + data, data_len, mic); +} + +static inline struct crypto_aead * +ieee80211_aes_gcm_key_setup_encrypt(const u8 key[], size_t key_len) +{ + return aead_key_setup_encrypt("gcm(aes)", key, + key_len, IEEE80211_GCMP_MIC_LEN); +} + +static inline void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm) +{ + return aead_key_free(tfm); +} #endif /* AES_GCM_H */ diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 2849a1fc41c5..88cc1ae935ea 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -459,7 +459,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, } void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, - const u8 *addr, unsigned int bit) + const u8 *addr, unsigned int tid) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; @@ -470,7 +470,7 @@ void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, if (!sta) goto unlock; - set_bit(bit, sta->ampdu_mlme.tid_rx_manage_offl); + set_bit(tid, sta->ampdu_mlme.tid_rx_manage_offl); ieee80211_queue_work(&local->hw, &sta->ampdu_mlme.work); unlock: rcu_read_unlock(); diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index d6d0b4201e40..41f5e48f8021 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -290,13 +290,15 @@ void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, { int i; + mutex_lock(&sta->ampdu_mlme.mtx); for (i = 0; i < IEEE80211_NUM_TIDS; i++) { - __ieee80211_stop_tx_ba_session(sta, i, reason); - __ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT, - WLAN_REASON_QSTA_LEAVE_QBSS, - reason != AGG_STOP_DESTROY_STA && - reason != AGG_STOP_PEER_REQUEST); + ___ieee80211_stop_tx_ba_session(sta, i, reason); + ___ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT, + WLAN_REASON_QSTA_LEAVE_QBSS, + reason != AGG_STOP_DESTROY_STA && + reason != AGG_STOP_PEER_REQUEST); } + mutex_unlock(&sta->ampdu_mlme.mtx); /* stopping might queue the work again - so cancel only afterwards */ cancel_work_sync(&sta->ampdu_mlme.work); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 9675814f64db..68f874e73561 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2009,6 +2009,8 @@ void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, struct txq_info *txq, int tid); void ieee80211_txq_purge(struct ieee80211_local *local, struct txq_info *txqi); +void ieee80211_txq_remove_vlan(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata); void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, u16 status, const u8 *extra, size_t extra_len, const u8 *bssid, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index f75029abf728..13b16f90e1cf 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -793,9 +793,7 @@ static int ieee80211_open(struct net_device *dev) static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_down) { - struct ieee80211_sub_if_data *txq_sdata = sdata; struct ieee80211_local *local = sdata->local; - struct fq *fq = &local->fq; unsigned long flags; struct sk_buff *skb, *tmp; u32 hw_reconf_flags = 0; @@ -939,9 +937,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: - txq_sdata = container_of(sdata->bss, - struct ieee80211_sub_if_data, u.ap); - mutex_lock(&local->mtx); list_del(&sdata->u.vlan.list); mutex_unlock(&local->mtx); @@ -998,8 +993,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, skb_queue_purge(&sdata->skb_queue); } - sdata->bss = NULL; - spin_lock_irqsave(&local->queue_stop_reason_lock, flags); for (i = 0; i < IEEE80211_MAX_QUEUES; i++) { skb_queue_walk_safe(&local->pending[i], skb, tmp) { @@ -1012,22 +1005,10 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, } spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); - if (txq_sdata->vif.txq) { - struct txq_info *txqi = to_txq_info(txq_sdata->vif.txq); - - /* - * FIXME FIXME - * - * We really shouldn't purge the *entire* txqi since that - * contains frames for the other AP_VLANs (and possibly - * the AP itself) as well, but there's no API in FQ now - * to be able to filter. - */ + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + ieee80211_txq_remove_vlan(local, sdata); - spin_lock_bh(&fq->lock); - ieee80211_txq_purge(local, txqi); - spin_unlock_bh(&fq->lock); - } + sdata->bss = NULL; if (local->open_count == 0) ieee80211_clear_tx_pending(local); @@ -1772,7 +1753,9 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sizeof(void *)); int txq_size = 0; - if (local->ops->wake_tx_queue) + if (local->ops->wake_tx_queue && + type != NL80211_IFTYPE_AP_VLAN && + type != NL80211_IFTYPE_MONITOR) txq_size += sizeof(struct txq_info) + local->hw.txq_data_size; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index a550c707cd8a..7a76c4a6df30 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -675,8 +675,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) enum nl80211_band band; u8 *pos; struct ieee80211_sub_if_data *sdata; - int hdr_len = offsetof(struct ieee80211_mgmt, u.beacon) + - sizeof(mgmt->u.beacon); + int hdr_len = offsetofend(struct ieee80211_mgmt, u.beacon); sdata = container_of(ifmsh, struct ieee80211_sub_if_data, u.mesh); rcu_read_lock(); diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 7e5f271e3c30..465b7853edc0 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -275,6 +275,7 @@ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata, u8 *hw_addr, struct ieee802_11_elems *ie); bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie); u32 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata); +void mesh_plink_timer(struct timer_list *t); void mesh_plink_broken(struct sta_info *sta); u32 mesh_plink_deactivate(struct sta_info *sta); u32 mesh_plink_open(struct sta_info *sta); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index d8bbd0d2225a..146ec6c0f12f 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -111,8 +111,8 @@ static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags, struct sk_buff *skb; struct ieee80211_mgmt *mgmt; u8 *pos, ie_len; - int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.mesh_action) + - sizeof(mgmt->u.action.u.mesh_action); + int hdr_len = offsetofend(struct ieee80211_mgmt, + u.action.u.mesh_action); skb = dev_alloc_skb(local->tx_headroom + hdr_len + @@ -242,8 +242,8 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct ieee80211_mgmt *mgmt; u8 *pos, ie_len; - int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.mesh_action) + - sizeof(mgmt->u.action.u.mesh_action); + int hdr_len = offsetofend(struct ieee80211_mgmt, + u.action.u.mesh_action); if (time_before(jiffies, ifmsh->next_perr)) return -EAGAIN; diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index f69c6c38ca43..e2d00cce3c17 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -220,8 +220,7 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, bool include_plid = false; u16 peering_proto = 0; u8 *pos, ie_len = 4; - int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.self_prot) + - sizeof(mgmt->u.action.u.self_prot); + int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.self_prot); int err = -ENOMEM; skb = dev_alloc_skb(local->tx_headroom + @@ -604,8 +603,9 @@ out: ieee80211_mbss_info_change_notify(sdata, changed); } -static void mesh_plink_timer(unsigned long data) +void mesh_plink_timer(struct timer_list *t) { + struct mesh_sta *mesh = from_timer(mesh, t, plink_timer); struct sta_info *sta; u16 reason = 0; struct ieee80211_sub_if_data *sdata; @@ -617,7 +617,7 @@ static void mesh_plink_timer(unsigned long data) * del_timer_sync() this timer after having made sure * it cannot be readded (by deleting the plink.) */ - sta = (struct sta_info *) data; + sta = mesh->plink_sta; if (sta->sdata->local->quiescing) return; @@ -697,11 +697,8 @@ static void mesh_plink_timer(unsigned long data) static inline void mesh_plink_timer_set(struct sta_info *sta, u32 timeout) { - sta->mesh->plink_timer.expires = jiffies + msecs_to_jiffies(timeout); - sta->mesh->plink_timer.data = (unsigned long) sta; - sta->mesh->plink_timer.function = mesh_plink_timer; sta->mesh->plink_timeout = timeout; - add_timer(&sta->mesh->plink_timer); + mod_timer(&sta->mesh->plink_timer, jiffies + msecs_to_jiffies(timeout)); } static bool llid_in_use(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 3b8e2709d8de..e4ededa1909d 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -145,7 +145,6 @@ static u32 ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, struct ieee80211_channel *channel, - const struct ieee80211_ht_cap *ht_cap, const struct ieee80211_ht_operation *ht_oper, const struct ieee80211_vht_operation *vht_oper, struct cfg80211_chan_def *chandef, bool tracking) @@ -163,20 +162,13 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, chandef->center_freq1 = channel->center_freq; chandef->center_freq2 = 0; - if (!ht_cap || !ht_oper || !sta_ht_cap.ht_supported) { + if (!ht_oper || !sta_ht_cap.ht_supported) { ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; goto out; } chandef->width = NL80211_CHAN_WIDTH_20; - if (!(ht_cap->cap_info & - cpu_to_le16(IEEE80211_HT_CAP_SUP_WIDTH_20_40))) { - ret = IEEE80211_STA_DISABLE_40MHZ; - vht_chandef = *chandef; - goto out; - } - ht_cfreq = ieee80211_channel_to_frequency(ht_oper->primary_chan, channel->band); /* check that channel matches the right operating channel */ @@ -344,7 +336,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, /* calculate new channel (type) based on HT/VHT operation IEs */ flags = ieee80211_determine_chantype(sdata, sband, chan, - ht_cap, ht_oper, vht_oper, + ht_oper, vht_oper, &chandef, true); /* @@ -780,11 +772,12 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) WLAN_EID_SUPPORTED_REGULATORY_CLASSES, WLAN_EID_HT_CAPABILITY, WLAN_EID_BSS_COEX_2040, + /* luckily this is almost always there */ WLAN_EID_EXT_CAPABILITY, WLAN_EID_QOS_TRAFFIC_CAPA, WLAN_EID_TIM_BCAST_REQ, WLAN_EID_INTERWORKING, - /* 60GHz doesn't happen right now */ + /* 60 GHz (Multi-band, DMG, MMS) can't happen */ WLAN_EID_VHT_CAPABILITY, WLAN_EID_OPMODE_NOTIF, }; @@ -811,22 +804,16 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) /* if present, add any custom IEs that go before VHT */ if (assoc_data->ie_len) { static const u8 before_vht[] = { - WLAN_EID_SSID, - WLAN_EID_SUPP_RATES, - WLAN_EID_EXT_SUPP_RATES, - WLAN_EID_PWR_CAPABILITY, - WLAN_EID_SUPPORTED_CHANNELS, - WLAN_EID_RSN, - WLAN_EID_QOS_CAPA, - WLAN_EID_RRM_ENABLED_CAPABILITIES, - WLAN_EID_MOBILITY_DOMAIN, - WLAN_EID_SUPPORTED_REGULATORY_CLASSES, - WLAN_EID_HT_CAPABILITY, + /* + * no need to list the ones split off before HT + * or generated here + */ WLAN_EID_BSS_COEX_2040, WLAN_EID_EXT_CAPABILITY, WLAN_EID_QOS_TRAFFIC_CAPA, WLAN_EID_TIM_BCAST_REQ, WLAN_EID_INTERWORKING, + /* 60 GHz (Multi-band, DMG, MMS) can't happen */ }; /* RIC already taken above, so no need to handle here anymore */ @@ -4317,7 +4304,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ifmgd->flags |= ieee80211_determine_chantype(sdata, sband, cbss->channel, - ht_cap, ht_oper, vht_oper, + ht_oper, vht_oper, &chandef, false); sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss), diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 47d2ed570470..ef2becaade50 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -7,7 +7,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2015 Intel Mobile Communications GmbH - * Copyright 2016 Intel Deutschland GmbH + * Copyright 2016-2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -183,6 +183,20 @@ ieee80211_bss_info_update(struct ieee80211_local *local, return bss; } +static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata, + u32 scan_flags, const u8 *da) +{ + if (!sdata) + return false; + /* accept broadcast for OCE */ + if (scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP && + is_broadcast_ether_addr(da)) + return true; + if (scan_flags & NL80211_SCAN_FLAG_RANDOM_ADDR) + return true; + return ether_addr_equal(da, sdata->vif.addr); +} + void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); @@ -208,19 +222,24 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) if (ieee80211_is_probe_resp(mgmt->frame_control)) { struct cfg80211_scan_request *scan_req; struct cfg80211_sched_scan_request *sched_scan_req; + u32 scan_req_flags = 0, sched_scan_req_flags = 0; scan_req = rcu_dereference(local->scan_req); sched_scan_req = rcu_dereference(local->sched_scan_req); - /* ignore ProbeResp to foreign address unless scanning - * with randomised address + if (scan_req) + scan_req_flags = scan_req->flags; + + if (sched_scan_req) + sched_scan_req_flags = sched_scan_req->flags; + + /* ignore ProbeResp to foreign address or non-bcast (OCE) + * unless scanning with randomised address */ - if (!(sdata1 && - (ether_addr_equal(mgmt->da, sdata1->vif.addr) || - scan_req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR)) && - !(sdata2 && - (ether_addr_equal(mgmt->da, sdata2->vif.addr) || - sched_scan_req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR))) + if (!ieee80211_scan_accept_presp(sdata1, scan_req_flags, + mgmt->da) && + !ieee80211_scan_accept_presp(sdata2, sched_scan_req_flags, + mgmt->da)) return; elements = mgmt->u.probe_resp.variable; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 69615016d5bf..9673e157bf8f 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -329,10 +329,12 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->mesh = kzalloc(sizeof(*sta->mesh), gfp); if (!sta->mesh) goto free; + sta->mesh->plink_sta = sta; spin_lock_init(&sta->mesh->plink_lock); if (ieee80211_vif_is_mesh(&sdata->vif) && !sdata->u.mesh.user_mpm) - init_timer(&sta->mesh->plink_timer); + timer_setup(&sta->mesh->plink_timer, mesh_plink_timer, + 0); sta->mesh->nonpeer_pm = NL80211_MESH_POWER_ACTIVE; } #endif @@ -515,6 +517,31 @@ static int sta_info_insert_drv_state(struct ieee80211_local *local, return err; } +static void +ieee80211_recalc_p2p_go_ps_allowed(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + bool allow_p2p_go_ps = sdata->vif.p2p; + struct sta_info *sta; + + rcu_read_lock(); + list_for_each_entry_rcu(sta, &local->sta_list, list) { + if (sdata != sta->sdata || + !test_sta_flag(sta, WLAN_STA_ASSOC)) + continue; + if (!sta->sta.support_p2p_ps) { + allow_p2p_go_ps = false; + break; + } + } + rcu_read_unlock(); + + if (allow_p2p_go_ps != sdata->vif.bss_conf.allow_p2p_go_ps) { + sdata->vif.bss_conf.allow_p2p_go_ps = allow_p2p_go_ps; + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_P2P_PS); + } +} + /* * should be called with sta_mtx locked * this function replaces the mutex lock @@ -561,6 +588,13 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) goto out_remove; set_sta_flag(sta, WLAN_STA_INSERTED); + + if (sta->sta_state >= IEEE80211_STA_ASSOC) { + ieee80211_recalc_min_chandef(sta->sdata); + if (!sta->sta.support_p2p_ps) + ieee80211_recalc_p2p_go_ps_allowed(sta->sdata); + } + /* accept BA sessions now */ clear_sta_flag(sta, WLAN_STA_BLOCK_BA); @@ -1788,31 +1822,6 @@ void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta, } EXPORT_SYMBOL(ieee80211_sta_set_buffered); -static void -ieee80211_recalc_p2p_go_ps_allowed(struct ieee80211_sub_if_data *sdata) -{ - struct ieee80211_local *local = sdata->local; - bool allow_p2p_go_ps = sdata->vif.p2p; - struct sta_info *sta; - - rcu_read_lock(); - list_for_each_entry_rcu(sta, &local->sta_list, list) { - if (sdata != sta->sdata || - !test_sta_flag(sta, WLAN_STA_ASSOC)) - continue; - if (!sta->sta.support_p2p_ps) { - allow_p2p_go_ps = false; - break; - } - } - rcu_read_unlock(); - - if (allow_p2p_go_ps != sdata->vif.bss_conf.allow_p2p_go_ps) { - sdata->vif.bss_conf.allow_p2p_go_ps = allow_p2p_go_ps; - ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_P2P_PS); - } -} - int sta_info_move_state(struct sta_info *sta, enum ieee80211_sta_state new_state) { diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 3acbdfa9f649..5c54acd10562 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -344,6 +344,7 @@ DECLARE_EWMA(mesh_fail_avg, 20, 8) * @plink_state: peer link state * @plink_timeout: timeout of peer link * @plink_timer: peer link watch timer + * @plink_sta: peer link watch timer's sta_info * @t_offset: timing offset relative to this host * @t_offset_setpoint: reference timing offset of this sta to be used when * calculating clockdrift @@ -356,6 +357,7 @@ DECLARE_EWMA(mesh_fail_avg, 20, 8) */ struct mesh_sta { struct timer_list plink_timer; + struct sta_info *plink_sta; s64 t_offset; s64 t_offset_setpoint; @@ -398,7 +400,7 @@ struct ieee80211_sta_rx_stats { u64 msdu[IEEE80211_NUM_TIDS + 1]; }; -/** +/* * The bandwidth threshold below which the per-station CoDel parameters will be * scaled to be more lenient (to prevent starvation of slow stations). This * value will be scaled by the number of active stations when it is being diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 94826680cf2b..7b8154474b9e 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1396,6 +1396,40 @@ static void ieee80211_txq_enqueue(struct ieee80211_local *local, fq_flow_get_default_func); } +static bool fq_vlan_filter_func(struct fq *fq, struct fq_tin *tin, + struct fq_flow *flow, struct sk_buff *skb, + void *data) +{ + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + + return info->control.vif == data; +} + +void ieee80211_txq_remove_vlan(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + struct fq *fq = &local->fq; + struct txq_info *txqi; + struct fq_tin *tin; + struct ieee80211_sub_if_data *ap; + + if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_AP_VLAN)) + return; + + ap = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); + + if (!ap->vif.txq) + return; + + txqi = to_txq_info(ap->vif.txq); + tin = &txqi->tin; + + spin_lock_bh(&fq->lock); + fq_tin_filter(fq, tin, fq_vlan_filter_func, &sdata->vif, + fq_skb_free_func); + spin_unlock_bh(&fq->lock); +} + void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct txq_info *txqi, int tid) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 6aef6793d052..d57e5f6bd8b6 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1392,10 +1392,10 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, /* insert custom IEs that go before HT */ if (ie && ie_len) { static const u8 before_ht[] = { - WLAN_EID_SSID, - WLAN_EID_SUPP_RATES, - WLAN_EID_REQUEST, - WLAN_EID_EXT_SUPP_RATES, + /* + * no need to list the ones split off already + * (or generated here) + */ WLAN_EID_DS_PARAMS, WLAN_EID_SUPPORTED_REGULATORY_CLASSES, }; @@ -1424,20 +1424,17 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, /* insert custom IEs that go before VHT */ if (ie && ie_len) { static const u8 before_vht[] = { - WLAN_EID_SSID, - WLAN_EID_SUPP_RATES, - WLAN_EID_REQUEST, - WLAN_EID_EXT_SUPP_RATES, - WLAN_EID_DS_PARAMS, - WLAN_EID_SUPPORTED_REGULATORY_CLASSES, - WLAN_EID_HT_CAPABILITY, + /* + * no need to list the ones split off already + * (or generated here) + */ WLAN_EID_BSS_COEX_2040, WLAN_EID_EXT_CAPABILITY, WLAN_EID_SSID_LIST, WLAN_EID_CHANNEL_USAGE, WLAN_EID_INTERWORKING, WLAN_EID_MESH_ID, - /* 60 GHz can't happen here right now */ + /* 60 GHz (Multi-band, DMG, MMS) can't happen */ }; noffset = ieee80211_ie_split(ie, ie_len, before_vht, ARRAY_SIZE(before_vht), @@ -2980,8 +2977,8 @@ int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt; struct ieee80211_local *local = sdata->local; int freq; - int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.chan_switch) + - sizeof(mgmt->u.action.u.chan_switch); + int hdr_len = offsetofend(struct ieee80211_mgmt, + u.action.u.chan_switch); u8 *pos; if (sdata->vif.type != NL80211_IFTYPE_ADHOC && diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 19ec2189d3ac..b9276ac849fa 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -386,6 +386,16 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta) bw = ieee80211_sta_cap_rx_bw(sta); bw = min(bw, sta->cur_max_bandwidth); + + /* Don't consider AP's bandwidth for TDLS peers, section 11.23.1 of + * IEEE80211-2016 specification makes higher bandwidth operation + * possible on the TDLS link if the peers have wider bandwidth + * capability. + */ + if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && + test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW)) + return bw; + bw = min(bw, ieee80211_chan_width_to_rx_bw(bss_width)); return bw; diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 0d722ea98a1b..b58722d9de37 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -464,7 +464,7 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb, pos += IEEE80211_CCMP_HDR_LEN; ccmp_special_blocks(skb, pn, b_0, aad); return ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, b_0, aad, pos, len, - skb_put(skb, mic_len), mic_len); + skb_put(skb, mic_len)); } @@ -543,7 +543,7 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, key->u.ccmp.tfm, b_0, aad, skb->data + hdrlen + IEEE80211_CCMP_HDR_LEN, data_len, - skb->data + skb->len - mic_len, mic_len)) + skb->data + skb->len - mic_len)) return RX_DROP_UNUSABLE; } diff --git a/net/mpls/Kconfig b/net/mpls/Kconfig index 5c467ef97311..801ea9098387 100644 --- a/net/mpls/Kconfig +++ b/net/mpls/Kconfig @@ -24,6 +24,7 @@ config NET_MPLS_GSO config MPLS_ROUTING tristate "MPLS: routing support" + depends on NET_IP_TUNNEL || NET_IP_TUNNEL=n ---help--- Add support for forwarding of mpls packets. diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index c5b9ce41d66f..8ca9915befc8 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -16,6 +16,7 @@ #include <net/arp.h> #include <net/ip_fib.h> #include <net/netevent.h> +#include <net/ip_tunnels.h> #include <net/netns/generic.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> @@ -39,6 +40,36 @@ static int one = 1; static int label_limit = (1 << 20) - 1; static int ttl_max = 255; +#if IS_ENABLED(CONFIG_NET_IP_TUNNEL) +static size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e) +{ + return sizeof(struct mpls_shim_hdr); +} + +static const struct ip_tunnel_encap_ops mpls_iptun_ops = { + .encap_hlen = ipgre_mpls_encap_hlen, +}; + +static int ipgre_tunnel_encap_add_mpls_ops(void) +{ + return ip_tunnel_encap_add_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS); +} + +static void ipgre_tunnel_encap_del_mpls_ops(void) +{ + ip_tunnel_encap_del_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS); +} +#else +static int ipgre_tunnel_encap_add_mpls_ops(void) +{ + return 0; +} + +static void ipgre_tunnel_encap_del_mpls_ops(void) +{ +} +#endif + static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, unsigned int nlm_flags); @@ -2485,6 +2516,10 @@ static int __init mpls_init(void) 0); rtnl_register(PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf, mpls_netconf_dump_devconf, 0); + err = ipgre_tunnel_encap_add_mpls_ops(); + if (err) + pr_err("Can't add mpls over gre tunnel ops\n"); + err = 0; out: return err; @@ -2502,6 +2537,7 @@ static void __exit mpls_exit(void) dev_remove_pack(&mpls_packet_type); unregister_netdevice_notifier(&mpls_dev_notifier); unregister_pernet_subsys(&mpls_net_ops); + ipgre_tunnel_encap_del_mpls_ops(); } module_exit(mpls_exit); diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 8ad2b52a0b32..5ca18f07683b 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -37,11 +37,11 @@ #define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) static void -mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set)) +mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) { struct mtype *map = set->data; - setup_timer(&map->gc, gc, (unsigned long)set); + timer_setup(&map->gc, gc, 0); mod_timer(&map->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); } @@ -272,10 +272,10 @@ out: } static void -mtype_gc(unsigned long ul_set) +mtype_gc(struct timer_list *t) { - struct ip_set *set = (struct ip_set *)ul_set; - struct mtype *map = set->data; + struct mtype *map = from_timer(map, t, gc); + struct ip_set *set = map->set; void *x; u32 id; diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index 4783efff0bde..d8975a0b4282 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -48,6 +48,7 @@ struct bitmap_ip { size_t memsize; /* members size */ u8 netmask; /* subnet netmask */ struct timer_list gc; /* garbage collection */ + struct ip_set *set; /* attached to this ip_set */ unsigned char extensions[0] /* data extensions */ __aligned(__alignof__(u64)); }; @@ -232,6 +233,7 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map, map->netmask = netmask; set->timeout = IPSET_NO_TIMEOUT; + map->set = set; set->data = map; set->family = NFPROTO_IPV4; diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 9a065f672d3a..4c279fbd2d5d 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -52,6 +52,7 @@ struct bitmap_ipmac { u32 elements; /* number of max elements in the set */ size_t memsize; /* members size */ struct timer_list gc; /* garbage collector */ + struct ip_set *set; /* attached to this ip_set */ unsigned char extensions[0] /* MAC + data extensions */ __aligned(__alignof__(u64)); }; @@ -307,6 +308,7 @@ init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map, map->elements = elements; set->timeout = IPSET_NO_TIMEOUT; + map->set = set; set->data = map; set->family = NFPROTO_IPV4; diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 7f0c733358a4..7f9bbd7c98b5 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -40,6 +40,7 @@ struct bitmap_port { u32 elements; /* number of max elements in the set */ size_t memsize; /* members size */ struct timer_list gc; /* garbage collection */ + struct ip_set *set; /* attached to this ip_set */ unsigned char extensions[0] /* data extensions */ __aligned(__alignof__(u64)); }; @@ -214,6 +215,7 @@ init_map_port(struct ip_set *set, struct bitmap_port *map, map->last_port = last_port; set->timeout = IPSET_NO_TIMEOUT; + map->set = set; set->data = map; set->family = NFPROTO_UNSPEC; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index e495b5e484b1..cf84f7b37cd9 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1191,14 +1191,17 @@ static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb, from->family == to->family)) return -IPSET_ERR_TYPE_MISMATCH; - if (from->ref_netlink || to->ref_netlink) + write_lock_bh(&ip_set_ref_lock); + + if (from->ref_netlink || to->ref_netlink) { + write_unlock_bh(&ip_set_ref_lock); return -EBUSY; + } strncpy(from_name, from->name, IPSET_MAXNAMELEN); strncpy(from->name, to->name, IPSET_MAXNAMELEN); strncpy(to->name, from_name, IPSET_MAXNAMELEN); - write_lock_bh(&ip_set_ref_lock); swap(from->ref, to->ref); ip_set(inst, from_id) = to; ip_set(inst, to_id) = from; @@ -2072,25 +2075,28 @@ static struct pernet_operations ip_set_net_ops = { static int __init ip_set_init(void) { - int ret = nfnetlink_subsys_register(&ip_set_netlink_subsys); + int ret = register_pernet_subsys(&ip_set_net_ops); + + if (ret) { + pr_err("ip_set: cannot register pernet_subsys.\n"); + return ret; + } + ret = nfnetlink_subsys_register(&ip_set_netlink_subsys); if (ret != 0) { pr_err("ip_set: cannot register with nfnetlink.\n"); + unregister_pernet_subsys(&ip_set_net_ops); return ret; } + ret = nf_register_sockopt(&so_set); if (ret != 0) { pr_err("SO_SET registry failed: %d\n", ret); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); + unregister_pernet_subsys(&ip_set_net_ops); return ret; } - ret = register_pernet_subsys(&ip_set_net_ops); - if (ret) { - pr_err("ip_set: cannot register pernet_subsys.\n"); - nf_unregister_sockopt(&so_set); - nfnetlink_subsys_unregister(&ip_set_netlink_subsys); - return ret; - } + pr_info("ip_set: protocol %u\n", IPSET_PROTOCOL); return 0; } @@ -2098,9 +2104,10 @@ ip_set_init(void) static void __exit ip_set_fini(void) { - unregister_pernet_subsys(&ip_set_net_ops); nf_unregister_sockopt(&so_set); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); + + unregister_pernet_subsys(&ip_set_net_ops); pr_debug("these are the famous last words\n"); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 51063d9ed0f7..efffc8eabafe 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -280,6 +280,7 @@ htable_bits(u32 hashsize) struct htype { struct htable __rcu *table; /* the hash table */ struct timer_list gc; /* garbage collection when timeout enabled */ + struct ip_set *set; /* attached to this ip_set */ u32 maxelem; /* max elements in the hash */ u32 initval; /* random jhash init value */ #ifdef IP_SET_HASH_WITH_MARKMASK @@ -429,11 +430,11 @@ mtype_destroy(struct ip_set *set) } static void -mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set)) +mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) { struct htype *h = set->data; - setup_timer(&h->gc, gc, (unsigned long)set); + timer_setup(&h->gc, gc, 0); mod_timer(&h->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); pr_debug("gc initialized, run in every %u\n", IPSET_GC_PERIOD(set->timeout)); @@ -526,10 +527,10 @@ mtype_expire(struct ip_set *set, struct htype *h) } static void -mtype_gc(unsigned long ul_set) +mtype_gc(struct timer_list *t) { - struct ip_set *set = (struct ip_set *)ul_set; - struct htype *h = set->data; + struct htype *h = from_timer(h, t, gc); + struct ip_set *set = h->set; pr_debug("called\n"); spin_lock_bh(&set->lock); @@ -1314,6 +1315,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, t->htable_bits = hbits; RCU_INIT_POINTER(h->table, t); + h->set = set; set->data = h; #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) { diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index 20bfbd315f61..613eb212cb48 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -123,13 +123,12 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], return ret; ip &= ip_set_hostmask(h->netmask); + e.ip = htonl(ip); + if (e.ip == 0) + return -IPSET_ERR_HASH_ELEM; - if (adt == IPSET_TEST) { - e.ip = htonl(ip); - if (e.ip == 0) - return -IPSET_ERR_HASH_ELEM; + if (adt == IPSET_TEST) return adtfn(set, &e, &ext, &ext, flags); - } ip_to = ip; if (tb[IPSET_ATTR_IP_TO]) { @@ -148,17 +147,20 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); - if (retried) + if (retried) { ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip += hosts) { e.ip = htonl(ip); - if (e.ip == 0) - return -IPSET_ERR_HASH_ELEM; + } + for (; ip <= ip_to;) { ret = adtfn(set, &e, &ext, &ext, flags); - if (ret && !ip_set_eexist(ret, flags)) return ret; + ip += hosts; + e.ip = htonl(ip); + if (e.ip == 0) + return 0; + ret = 0; } return ret; diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index b64cf14e8352..f3ba8348cf9d 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -149,7 +149,7 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip++) { + for (; ip <= ip_to; ip++) { e.ip = htonl(ip); ret = adtfn(set, &e, &ext, &ext, flags); diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index f438740e6c6a..ddb8039ec1d2 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -178,7 +178,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip++) { + for (; ip <= ip_to; ip++) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; for (; p <= port_to; p++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 6215fb898c50..a7f4d7a85420 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -185,7 +185,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip++) { + for (; ip <= ip_to; ip++) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; for (; p <= port_to; p++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 5ab1b99a53c2..a2f19b9906e9 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -271,7 +271,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip++) { + for (; ip <= ip_to; ip++) { e.ip = htonl(ip); p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; @@ -281,7 +281,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], ip == ntohl(h->next.ip) && p == ntohs(h->next.port) ? ntohl(h->next.ip2) : ip2_from; - while (!after(ip2, ip2_to)) { + while (ip2 <= ip2_to) { e.ip2 = htonl(ip2); ip2_last = ip_set_range_to_cidr(ip2, ip2_to, &cidr); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 5d9e895452e7..1c67a1761e45 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -193,7 +193,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], } if (retried) ip = ntohl(h->next.ip); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &e.cidr); ret = adtfn(set, &e, &ext, &ext, flags); diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 44cf11939c91..d417074f1c1a 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -255,7 +255,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &e.cidr); ret = adtfn(set, &e, &ext, &ext, flags); diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index db614e13b193..7f9ae2e9645b 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -250,13 +250,13 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip[0]); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip[0] = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]); ip2 = (retried && ip == ntohl(h->next.ip[0])) ? ntohl(h->next.ip[1]) : ip2_from; - while (!after(ip2, ip2_to)) { + while (ip2 <= ip2_to) { e.ip[1] = htonl(ip2); last2 = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]); ret = adtfn(set, &e, &ext, &ext, flags); diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 54b64b6cd0cd..e6ef382febe4 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -241,7 +241,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &cidr); e.cidr = cidr - 1; diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index aff846960ac4..8602f2595a1a 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -291,7 +291,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip[0]); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip[0] = htonl(ip); ip_last = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]); p = retried && ip == ntohl(h->next.ip[0]) ? ntohs(h->next.port) @@ -301,7 +301,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], ip2 = (retried && ip == ntohl(h->next.ip[0]) && p == ntohs(h->next.port)) ? ntohl(h->next.ip[1]) : ip2_from; - while (!after(ip2, ip2_to)) { + while (ip2 <= ip2_to) { e.ip[1] = htonl(ip2); ip2_last = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]); diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 178d4eba013b..c9b4e05ad940 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -44,6 +44,7 @@ struct set_adt_elem { struct list_set { u32 size; /* size of set list array */ struct timer_list gc; /* garbage collection */ + struct ip_set *set; /* attached to this ip_set */ struct net *net; /* namespace */ struct list_head members; /* the set members */ }; @@ -571,10 +572,10 @@ static const struct ip_set_type_variant set_variant = { }; static void -list_set_gc(unsigned long ul_set) +list_set_gc(struct timer_list *t) { - struct ip_set *set = (struct ip_set *)ul_set; - struct list_set *map = set->data; + struct list_set *map = from_timer(map, t, gc); + struct ip_set *set = map->set; spin_lock_bh(&set->lock); set_cleanup_entries(set); @@ -585,11 +586,11 @@ list_set_gc(unsigned long ul_set) } static void -list_set_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set)) +list_set_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) { struct list_set *map = set->data; - setup_timer(&map->gc, gc, (unsigned long)set); + timer_setup(&map->gc, gc, 0); mod_timer(&map->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); } @@ -606,6 +607,7 @@ init_list_set(struct net *net, struct ip_set *set, u32 size) map->size = size; map->net = net; + map->set = set; INIT_LIST_HEAD(&map->members); set->data = map; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 90d396814798..4527921b1c3a 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -921,6 +921,7 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, { struct sk_buff *new_skb = NULL; struct iphdr *old_iph = NULL; + __u8 old_dsfield; #ifdef CONFIG_IP_VS_IPV6 struct ipv6hdr *old_ipv6h = NULL; #endif @@ -945,7 +946,7 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, *payload_len = ntohs(old_ipv6h->payload_len) + sizeof(*old_ipv6h); - *dsfield = ipv6_get_dsfield(old_ipv6h); + old_dsfield = ipv6_get_dsfield(old_ipv6h); *ttl = old_ipv6h->hop_limit; if (df) *df = 0; @@ -960,12 +961,15 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, /* fix old IP header checksum */ ip_send_check(old_iph); - *dsfield = ipv4_get_dsfield(old_iph); + old_dsfield = ipv4_get_dsfield(old_iph); *ttl = old_iph->ttl; if (payload_len) *payload_len = ntohs(old_iph->tot_len); } + /* Implement full-functionality option for ECN encapsulation */ + *dsfield = INET_ECN_encapsulate(old_dsfield, old_dsfield); + return skb; error: kfree_skb(skb); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 929927171426..64e1ee091225 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1048,7 +1048,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, if (nla_put_string(skb, NFTA_CHAIN_TYPE, basechain->type->name)) goto nla_put_failure; - if (nft_dump_stats(skb, nft_base_chain(chain)->stats)) + if (basechain->stats && nft_dump_stats(skb, basechain->stats)) goto nla_put_failure; } @@ -1487,8 +1487,8 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, chain2 = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); - if (IS_ERR(chain2)) - return PTR_ERR(chain2); + if (!IS_ERR(chain2)) + return -EEXIST; } if (nla[NFTA_CHAIN_COUNTERS]) { @@ -2741,8 +2741,10 @@ cont: list_for_each_entry(i, &ctx->table->sets, list) { if (!nft_is_active_next(ctx->net, i)) continue; - if (!strcmp(set->name, i->name)) + if (!strcmp(set->name, i->name)) { + kfree(set->name); return -ENFILE; + } } return 0; } diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index c83a3b5e1c6c..d8571f414208 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -892,7 +892,7 @@ void *xt_copy_counters_from_user(const void __user *user, unsigned int len, if (copy_from_user(&compat_tmp, user, sizeof(compat_tmp)) != 0) return ERR_PTR(-EFAULT); - strlcpy(info->name, compat_tmp.name, sizeof(info->name)); + memcpy(info->name, compat_tmp.name, sizeof(info->name) - 1); info->num_counters = compat_tmp.num_counters; user += sizeof(compat_tmp); } else @@ -905,9 +905,9 @@ void *xt_copy_counters_from_user(const void __user *user, unsigned int len, if (copy_from_user(info, user, sizeof(*info)) != 0) return ERR_PTR(-EFAULT); - info->name[sizeof(info->name) - 1] = '\0'; user += sizeof(*info); } + info->name[sizeof(info->name) - 1] = '\0'; size = sizeof(struct xt_counters); size *= info->num_counters; diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 38986a95216c..041da0d9c06f 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -8,6 +8,7 @@ */ #include <linux/module.h> +#include <linux/syscalls.h> #include <linux/skbuff.h> #include <linux/filter.h> #include <linux/bpf.h> @@ -49,6 +50,22 @@ static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret) return 0; } +static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) +{ + mm_segment_t oldfs = get_fs(); + int retval, fd; + + set_fs(KERNEL_DS); + fd = bpf_obj_get_user(path, 0); + set_fs(oldfs); + if (fd < 0) + return fd; + + retval = __bpf_mt_check_fd(fd, ret); + sys_close(fd); + return retval; +} + static int bpf_mt_check(const struct xt_mtchk_param *par) { struct xt_bpf_info *info = par->matchinfo; @@ -66,9 +83,10 @@ static int bpf_mt_check_v1(const struct xt_mtchk_param *par) return __bpf_mt_check_bytecode(info->bpf_program, info->bpf_program_num_elem, &info->filter); - else if (info->mode == XT_BPF_MODE_FD_PINNED || - info->mode == XT_BPF_MODE_FD_ELF) + else if (info->mode == XT_BPF_MODE_FD_ELF) return __bpf_mt_check_fd(info->fd, &info->filter); + else if (info->mode == XT_BPF_MODE_PATH_PINNED) + return __bpf_mt_check_path(info->path, &info->filter); else return -EINVAL; } diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index e75ef39669c5..575d2153e3b8 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -76,7 +76,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, transparent = nf_sk_is_transparent(sk); if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && - transparent) + transparent && sk_fullsock(sk)) pskb->mark = sk->sk_mark; if (sk != skb->sk) @@ -133,7 +133,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) transparent = nf_sk_is_transparent(sk); if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && - transparent) + transparent && sk_fullsock(sk)) pskb->mark = sk->sk_mark; if (sk != skb->sk) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 94c11cf0459d..336d9c6dcad9 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2266,16 +2266,17 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, cb->min_dump_alloc = control->min_dump_alloc; cb->skb = skb; + if (cb->start) { + ret = cb->start(cb); + if (ret) + goto error_unlock; + } + nlk->cb_running = true; mutex_unlock(nlk->cb_mutex); - ret = 0; - if (cb->start) - ret = cb->start(cb); - - if (!ret) - ret = netlink_dump(sk); + ret = netlink_dump(sk); sock_put(sk); @@ -2335,16 +2336,8 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); if (!skb) { - struct sock *sk; - - sk = netlink_lookup(sock_net(in_skb->sk), - in_skb->sk->sk_protocol, - NETLINK_CB(in_skb).portid); - if (sk) { - sk->sk_err = ENOBUFS; - sk->sk_error_report(sk); - sock_put(sk); - } + NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; + NETLINK_CB(in_skb).sk->sk_error_report(NETLINK_CB(in_skb).sk); return; } diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index ebf16f7f9089..2dec3583c97d 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -241,9 +241,9 @@ void nr_destroy_socket(struct sock *); /* * Handler for deferred kills. */ -static void nr_destroy_timer(unsigned long data) +static void nr_destroy_timer(struct timer_list *t) { - struct sock *sk=(struct sock *)data; + struct sock *sk = from_timer(sk, t, sk_timer); bh_lock_sock(sk); sock_hold(sk); nr_destroy_socket(sk); @@ -284,7 +284,7 @@ void nr_destroy_socket(struct sock *sk) if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ - sk->sk_timer.function = nr_destroy_timer; + sk->sk_timer.function = (TIMER_FUNC_TYPE)nr_destroy_timer; sk->sk_timer.expires = jiffies + 2 * HZ; add_timer(&sk->sk_timer); } else diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index 94d05806a9a2..43569aea0f5e 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -29,24 +29,23 @@ #include <linux/interrupt.h> #include <net/netrom.h> -static void nr_heartbeat_expiry(unsigned long); -static void nr_t1timer_expiry(unsigned long); -static void nr_t2timer_expiry(unsigned long); -static void nr_t4timer_expiry(unsigned long); -static void nr_idletimer_expiry(unsigned long); +static void nr_heartbeat_expiry(struct timer_list *); +static void nr_t1timer_expiry(struct timer_list *); +static void nr_t2timer_expiry(struct timer_list *); +static void nr_t4timer_expiry(struct timer_list *); +static void nr_idletimer_expiry(struct timer_list *); void nr_init_timers(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - setup_timer(&nr->t1timer, nr_t1timer_expiry, (unsigned long)sk); - setup_timer(&nr->t2timer, nr_t2timer_expiry, (unsigned long)sk); - setup_timer(&nr->t4timer, nr_t4timer_expiry, (unsigned long)sk); - setup_timer(&nr->idletimer, nr_idletimer_expiry, (unsigned long)sk); + timer_setup(&nr->t1timer, nr_t1timer_expiry, 0); + timer_setup(&nr->t2timer, nr_t2timer_expiry, 0); + timer_setup(&nr->t4timer, nr_t4timer_expiry, 0); + timer_setup(&nr->idletimer, nr_idletimer_expiry, 0); /* initialized by sock_init_data */ - sk->sk_timer.data = (unsigned long)sk; - sk->sk_timer.function = &nr_heartbeat_expiry; + sk->sk_timer.function = (TIMER_FUNC_TYPE)nr_heartbeat_expiry; } void nr_start_t1timer(struct sock *sk) @@ -113,9 +112,9 @@ int nr_t1timer_running(struct sock *sk) return timer_pending(&nr_sk(sk)->t1timer); } -static void nr_heartbeat_expiry(unsigned long param) +static void nr_heartbeat_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct sock *sk = from_timer(sk, t, sk_timer); struct nr_sock *nr = nr_sk(sk); bh_lock_sock(sk); @@ -152,10 +151,10 @@ static void nr_heartbeat_expiry(unsigned long param) bh_unlock_sock(sk); } -static void nr_t2timer_expiry(unsigned long param) +static void nr_t2timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; - struct nr_sock *nr = nr_sk(sk); + struct nr_sock *nr = from_timer(nr, t, t2timer); + struct sock *sk = &nr->sock; bh_lock_sock(sk); if (nr->condition & NR_COND_ACK_PENDING) { @@ -165,19 +164,20 @@ static void nr_t2timer_expiry(unsigned long param) bh_unlock_sock(sk); } -static void nr_t4timer_expiry(unsigned long param) +static void nr_t4timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct nr_sock *nr = from_timer(nr, t, t4timer); + struct sock *sk = &nr->sock; bh_lock_sock(sk); nr_sk(sk)->condition &= ~NR_COND_PEER_RX_BUSY; bh_unlock_sock(sk); } -static void nr_idletimer_expiry(unsigned long param) +static void nr_idletimer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; - struct nr_sock *nr = nr_sk(sk); + struct nr_sock *nr = from_timer(nr, t, idletimer); + struct sock *sk = &nr->sock; bh_lock_sock(sk); @@ -202,10 +202,10 @@ static void nr_idletimer_expiry(unsigned long param) bh_unlock_sock(sk); } -static void nr_t1timer_expiry(unsigned long param) +static void nr_t1timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; - struct nr_sock *nr = nr_sk(sk); + struct nr_sock *nr = from_timer(nr, t, t1timer); + struct sock *sk = &nr->sock; bh_lock_sock(sk); switch (nr->state) { diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index a54a556fcdb5..a551232daf61 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1203,6 +1203,10 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, return err == -EINPROGRESS ? 0 : err; break; + case OVS_ACTION_ATTR_CT_CLEAR: + err = ovs_ct_clear(skb, key); + break; + case OVS_ACTION_ATTR_PUSH_ETH: err = push_eth(skb, key, nla_data(a)); break; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index d558e882ca0c..fe861e2f0deb 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1129,6 +1129,17 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, return err; } +int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) +{ + if (skb_nfct(skb)) { + nf_conntrack_put(skb_nfct(skb)); + nf_ct_set(skb, NULL, IP_CT_UNTRACKED); + ovs_ct_fill_key(skb, key); + } + + return 0; +} + static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, const struct sw_flow_key *key, bool log) { diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index bc7efd1867ab..399dfdd2c4f9 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -30,6 +30,7 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *, struct sk_buff *); int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *, const struct ovs_conntrack_info *); +int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key); void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key); int ovs_ct_put_key(const struct sw_flow_key *swkey, @@ -73,6 +74,12 @@ static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb, return -ENOTSUPP; } +static inline int ovs_ct_clear(struct sk_buff *skb, + struct sw_flow_key *key) +{ + return -ENOTSUPP; +} + static inline void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index e8eb427ce6d1..dc0d79092e74 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -48,6 +48,7 @@ #include <net/ndisc.h> #include <net/mpls.h> #include <net/vxlan.h> +#include <net/erspan.h> #include "flow_netlink.h" @@ -75,6 +76,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) break; case OVS_ACTION_ATTR_CT: + case OVS_ACTION_ATTR_CT_CLEAR: case OVS_ACTION_ATTR_HASH: case OVS_ACTION_ATTR_POP_ETH: case OVS_ACTION_ATTR_POP_MPLS: @@ -319,7 +321,8 @@ size_t ovs_tun_key_attr_size(void) * OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it. */ + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_SRC */ - + nla_total_size(2); /* OVS_TUNNEL_KEY_ATTR_TP_DST */ + + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_DST */ + + nla_total_size(4); /* OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS */ } size_t ovs_key_attr_size(void) @@ -371,6 +374,7 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] .next = ovs_vxlan_ext_key_lens }, [OVS_TUNNEL_KEY_ATTR_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, [OVS_TUNNEL_KEY_ATTR_IPV6_DST] = { .len = sizeof(struct in6_addr) }, + [OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS] = { .len = sizeof(u32) }, }; /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ @@ -593,6 +597,33 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr, return 0; } +static int erspan_tun_opt_from_nlattr(const struct nlattr *attr, + struct sw_flow_match *match, bool is_mask, + bool log) +{ + unsigned long opt_key_offset; + struct erspan_metadata opts; + + BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); + + memset(&opts, 0, sizeof(opts)); + opts.index = nla_get_be32(attr); + + /* Index has only 20-bit */ + if (ntohl(opts.index) & ~INDEX_MASK) { + OVS_NLERR(log, "ERSPAN index number %x too large.", + ntohl(opts.index)); + return -EINVAL; + } + + SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), is_mask); + opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts)); + SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts), + is_mask); + + return 0; +} + static int ip_tun_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool log) @@ -700,6 +731,19 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_PAD: break; + case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: + if (opts_type) { + OVS_NLERR(log, "Multiple metadata blocks provided"); + return -EINVAL; + } + + err = erspan_tun_opt_from_nlattr(a, match, is_mask, log); + if (err) + return err; + + tun_flags |= TUNNEL_ERSPAN_OPT; + opts_type = type; + break; default: OVS_NLERR(log, "Unknown IP tunnel attribute %d", type); @@ -824,6 +868,10 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, else if (output->tun_flags & TUNNEL_VXLAN_OPT && vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len)) return -EMSGSIZE; + else if (output->tun_flags & TUNNEL_ERSPAN_OPT && + nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, + ((struct erspan_metadata *)tun_opts)->index)) + return -EMSGSIZE; } return 0; @@ -2195,6 +2243,8 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: break; + case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: + break; } }; @@ -2479,6 +2529,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_SAMPLE] = (u32)-1, [OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash), [OVS_ACTION_ATTR_CT] = (u32)-1, + [OVS_ACTION_ATTR_CT_CLEAR] = 0, [OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc), [OVS_ACTION_ATTR_PUSH_ETH] = sizeof(struct ovs_action_push_eth), [OVS_ACTION_ATTR_POP_ETH] = 0, @@ -2620,6 +2671,9 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, skip_copy = true; break; + case OVS_ACTION_ATTR_CT_CLEAR: + break; + case OVS_ACTION_ATTR_PUSH_ETH: /* Disallow pushing an Ethernet header if one * is already present */ diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index f925753668a7..3b0ef691f5b1 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -35,11 +35,11 @@ #include <net/phonet/pn_dev.h> /* Transport protocol registration */ -static struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly; +static const struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly; -static struct phonet_protocol *phonet_proto_get(unsigned int protocol) +static const struct phonet_protocol *phonet_proto_get(unsigned int protocol) { - struct phonet_protocol *pp; + const struct phonet_protocol *pp; if (protocol >= PHONET_NPROTO) return NULL; @@ -53,7 +53,7 @@ static struct phonet_protocol *phonet_proto_get(unsigned int protocol) return pp; } -static inline void phonet_proto_put(struct phonet_protocol *pp) +static inline void phonet_proto_put(const struct phonet_protocol *pp) { module_put(pp->prot->owner); } @@ -65,7 +65,7 @@ static int pn_socket_create(struct net *net, struct socket *sock, int protocol, { struct sock *sk; struct pn_sock *pn; - struct phonet_protocol *pnp; + const struct phonet_protocol *pnp; int err; if (!capable(CAP_SYS_ADMIN)) @@ -149,7 +149,7 @@ static int pn_header_parse(const struct sk_buff *skb, unsigned char *haddr) return 1; } -struct header_ops phonet_header_ops = { +const struct header_ops phonet_header_ops = { .create = pn_header_create, .parse = pn_header_parse, }; @@ -470,7 +470,7 @@ static struct packet_type phonet_packet_type __read_mostly = { static DEFINE_MUTEX(proto_tab_lock); int __init_or_module phonet_proto_register(unsigned int protocol, - struct phonet_protocol *pp) + const struct phonet_protocol *pp) { int err = 0; @@ -492,7 +492,8 @@ int __init_or_module phonet_proto_register(unsigned int protocol, } EXPORT_SYMBOL(phonet_proto_register); -void phonet_proto_unregister(unsigned int protocol, struct phonet_protocol *pp) +void phonet_proto_unregister(unsigned int protocol, + const struct phonet_protocol *pp) { mutex_lock(&proto_tab_lock); BUG_ON(proto_tab[protocol] != pp); diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index 5e710435ffa9..b44fb9018fb8 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -195,7 +195,7 @@ static struct proto pn_proto = { .name = "PHONET", }; -static struct phonet_protocol pn_dgram_proto = { +static const struct phonet_protocol pn_dgram_proto = { .ops = &phonet_dgram_ops, .prot = &pn_proto, .sock_type = SOCK_DGRAM, diff --git a/net/phonet/pep.c b/net/phonet/pep.c index e81537991ddf..9fc76b19cd3c 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -1351,7 +1351,7 @@ static struct proto pep_proto = { .name = "PNPIPE", }; -static struct phonet_protocol pep_pn_proto = { +static const struct phonet_protocol pep_pn_proto = { .ops = &phonet_stream_ops, .prot = &pep_proto, .sock_type = SOCK_SEQPACKET, diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index c2f5c13550c0..e458ece96d3d 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -20,26 +20,15 @@ #include "qrtr.h" -#define QRTR_PROTO_VER 1 +#define QRTR_PROTO_VER_1 1 +#define QRTR_PROTO_VER_2 3 /* auto-bind range */ #define QRTR_MIN_EPH_SOCKET 0x4000 #define QRTR_MAX_EPH_SOCKET 0x7fff -enum qrtr_pkt_type { - QRTR_TYPE_DATA = 1, - QRTR_TYPE_HELLO = 2, - QRTR_TYPE_BYE = 3, - QRTR_TYPE_NEW_SERVER = 4, - QRTR_TYPE_DEL_SERVER = 5, - QRTR_TYPE_DEL_CLIENT = 6, - QRTR_TYPE_RESUME_TX = 7, - QRTR_TYPE_EXIT = 8, - QRTR_TYPE_PING = 9, -}; - /** - * struct qrtr_hdr - (I|R)PCrouter packet header + * struct qrtr_hdr_v1 - (I|R)PCrouter packet header version 1 * @version: protocol version * @type: packet type; one of QRTR_TYPE_* * @src_node_id: source node @@ -49,7 +38,7 @@ enum qrtr_pkt_type { * @dst_node_id: destination node * @dst_port_id: destination port */ -struct qrtr_hdr { +struct qrtr_hdr_v1 { __le32 version; __le32 type; __le32 src_node_id; @@ -60,9 +49,44 @@ struct qrtr_hdr { __le32 dst_port_id; } __packed; -#define QRTR_HDR_SIZE sizeof(struct qrtr_hdr) -#define QRTR_NODE_BCAST ((unsigned int)-1) -#define QRTR_PORT_CTRL ((unsigned int)-2) +/** + * struct qrtr_hdr_v2 - (I|R)PCrouter packet header later versions + * @version: protocol version + * @type: packet type; one of QRTR_TYPE_* + * @flags: bitmask of QRTR_FLAGS_* + * @optlen: length of optional header data + * @size: length of packet, excluding this header and optlen + * @src_node_id: source node + * @src_port_id: source port + * @dst_node_id: destination node + * @dst_port_id: destination port + */ +struct qrtr_hdr_v2 { + u8 version; + u8 type; + u8 flags; + u8 optlen; + __le32 size; + __le16 src_node_id; + __le16 src_port_id; + __le16 dst_node_id; + __le16 dst_port_id; +}; + +#define QRTR_FLAGS_CONFIRM_RX BIT(0) + +struct qrtr_cb { + u32 src_node; + u32 src_port; + u32 dst_node; + u32 dst_port; + + u8 type; + u8 confirm_rx; +}; + +#define QRTR_HDR_MAX_SIZE max_t(size_t, sizeof(struct qrtr_hdr_v1), \ + sizeof(struct qrtr_hdr_v2)) struct qrtr_sock { /* WARNING: sk must be the first member */ @@ -111,8 +135,12 @@ struct qrtr_node { struct list_head item; }; -static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb); -static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb); +static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to); +static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to); /* Release node resources and free the node. * @@ -150,10 +178,27 @@ static void qrtr_node_release(struct qrtr_node *node) } /* Pass an outgoing packet socket buffer to the endpoint driver. */ -static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb) +static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to) { + struct qrtr_hdr_v1 *hdr; + size_t len = skb->len; int rc = -ENODEV; + hdr = skb_push(skb, sizeof(*hdr)); + hdr->version = cpu_to_le32(QRTR_PROTO_VER_1); + hdr->type = cpu_to_le32(type); + hdr->src_node_id = cpu_to_le32(from->sq_node); + hdr->src_port_id = cpu_to_le32(from->sq_port); + hdr->dst_node_id = cpu_to_le32(to->sq_node); + hdr->dst_port_id = cpu_to_le32(to->sq_port); + + hdr->size = cpu_to_le32(len); + hdr->confirm_rx = 0; + + skb_put_padto(skb, ALIGN(len, 4)); + mutex_lock(&node->ep_lock); if (node->ep) rc = node->ep->xmit(node->ep, skb); @@ -207,125 +252,103 @@ static void qrtr_node_assign(struct qrtr_node *node, unsigned int nid) int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) { struct qrtr_node *node = ep->node; - const struct qrtr_hdr *phdr = data; + const struct qrtr_hdr_v1 *v1; + const struct qrtr_hdr_v2 *v2; struct sk_buff *skb; - unsigned int psize; + struct qrtr_cb *cb; unsigned int size; - unsigned int type; unsigned int ver; - unsigned int dst; - - if (len < QRTR_HDR_SIZE || len & 3) - return -EINVAL; - - ver = le32_to_cpu(phdr->version); - size = le32_to_cpu(phdr->size); - type = le32_to_cpu(phdr->type); - dst = le32_to_cpu(phdr->dst_port_id); - - psize = (size + 3) & ~3; + size_t hdrlen; - if (ver != QRTR_PROTO_VER) - return -EINVAL; - - if (len != psize + QRTR_HDR_SIZE) - return -EINVAL; - - if (dst != QRTR_PORT_CTRL && type != QRTR_TYPE_DATA) + if (len & 3) return -EINVAL; skb = netdev_alloc_skb(NULL, len); if (!skb) return -ENOMEM; - skb_reset_transport_header(skb); - skb_put_data(skb, data, len); - - skb_queue_tail(&node->rx_queue, skb); - schedule_work(&node->work); - - return 0; -} -EXPORT_SYMBOL_GPL(qrtr_endpoint_post); + cb = (struct qrtr_cb *)skb->cb; -static struct sk_buff *qrtr_alloc_ctrl_packet(u32 type, size_t pkt_len, - u32 src_node, u32 dst_node) -{ - struct qrtr_hdr *hdr; - struct sk_buff *skb; - - skb = alloc_skb(QRTR_HDR_SIZE + pkt_len, GFP_KERNEL); - if (!skb) - return NULL; - skb_reset_transport_header(skb); + /* Version field in v1 is little endian, so this works for both cases */ + ver = *(u8*)data; - hdr = skb_put(skb, QRTR_HDR_SIZE); - hdr->version = cpu_to_le32(QRTR_PROTO_VER); - hdr->type = cpu_to_le32(type); - hdr->src_node_id = cpu_to_le32(src_node); - hdr->src_port_id = cpu_to_le32(QRTR_PORT_CTRL); - hdr->confirm_rx = cpu_to_le32(0); - hdr->size = cpu_to_le32(pkt_len); - hdr->dst_node_id = cpu_to_le32(dst_node); - hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL); + switch (ver) { + case QRTR_PROTO_VER_1: + v1 = data; + hdrlen = sizeof(*v1); - return skb; -} + cb->type = le32_to_cpu(v1->type); + cb->src_node = le32_to_cpu(v1->src_node_id); + cb->src_port = le32_to_cpu(v1->src_port_id); + cb->confirm_rx = !!v1->confirm_rx; + cb->dst_node = le32_to_cpu(v1->dst_node_id); + cb->dst_port = le32_to_cpu(v1->dst_port_id); -/* Allocate and construct a resume-tx packet. */ -static struct sk_buff *qrtr_alloc_resume_tx(u32 src_node, - u32 dst_node, u32 port) -{ - const int pkt_len = 20; - struct sk_buff *skb; - __le32 *buf; + size = le32_to_cpu(v1->size); + break; + case QRTR_PROTO_VER_2: + v2 = data; + hdrlen = sizeof(*v2) + v2->optlen; + + cb->type = v2->type; + cb->confirm_rx = !!(v2->flags & QRTR_FLAGS_CONFIRM_RX); + cb->src_node = le16_to_cpu(v2->src_node_id); + cb->src_port = le16_to_cpu(v2->src_port_id); + cb->dst_node = le16_to_cpu(v2->dst_node_id); + cb->dst_port = le16_to_cpu(v2->dst_port_id); + + if (cb->src_port == (u16)QRTR_PORT_CTRL) + cb->src_port = QRTR_PORT_CTRL; + if (cb->dst_port == (u16)QRTR_PORT_CTRL) + cb->dst_port = QRTR_PORT_CTRL; + + size = le32_to_cpu(v2->size); + break; + default: + pr_err("qrtr: Invalid version %d\n", ver); + goto err; + } - skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_RESUME_TX, pkt_len, - src_node, dst_node); - if (!skb) - return NULL; + if (len != ALIGN(size, 4) + hdrlen) + goto err; - buf = skb_put_zero(skb, pkt_len); - buf[0] = cpu_to_le32(QRTR_TYPE_RESUME_TX); - buf[1] = cpu_to_le32(src_node); - buf[2] = cpu_to_le32(port); + if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA) + goto err; - return skb; -} + skb_put_data(skb, data + hdrlen, size); -/* Allocate and construct a BYE message to signal remote termination */ -static struct sk_buff *qrtr_alloc_local_bye(u32 src_node) -{ - const int pkt_len = 20; - struct sk_buff *skb; - __le32 *buf; + skb_queue_tail(&node->rx_queue, skb); + schedule_work(&node->work); - skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_BYE, pkt_len, - src_node, qrtr_local_nid); - if (!skb) - return NULL; + return 0; - buf = skb_put_zero(skb, pkt_len); - buf[0] = cpu_to_le32(QRTR_TYPE_BYE); +err: + kfree_skb(skb); + return -EINVAL; - return skb; } +EXPORT_SYMBOL_GPL(qrtr_endpoint_post); -static struct sk_buff *qrtr_alloc_del_client(struct sockaddr_qrtr *sq) +/** + * qrtr_alloc_ctrl_packet() - allocate control packet skb + * @pkt: reference to qrtr_ctrl_pkt pointer + * + * Returns newly allocated sk_buff, or NULL on failure + * + * This function allocates a sk_buff large enough to carry a qrtr_ctrl_pkt and + * on success returns a reference to the control packet in @pkt. + */ +static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt) { - const int pkt_len = 20; + const int pkt_len = sizeof(struct qrtr_ctrl_pkt); struct sk_buff *skb; - __le32 *buf; - skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_DEL_CLIENT, pkt_len, - sq->sq_node, QRTR_NODE_BCAST); + skb = alloc_skb(QRTR_HDR_MAX_SIZE + pkt_len, GFP_KERNEL); if (!skb) return NULL; - buf = skb_put_zero(skb, pkt_len); - buf[0] = cpu_to_le32(QRTR_TYPE_DEL_CLIENT); - buf[1] = cpu_to_le32(sq->sq_node); - buf[2] = cpu_to_le32(sq->sq_port); + skb_reserve(skb, QRTR_HDR_MAX_SIZE); + *pkt = skb_put_zero(skb, pkt_len); return skb; } @@ -340,24 +363,26 @@ static void qrtr_port_put(struct qrtr_sock *ipc); static void qrtr_node_rx_work(struct work_struct *work) { struct qrtr_node *node = container_of(work, struct qrtr_node, work); + struct qrtr_ctrl_pkt *pkt; + struct sockaddr_qrtr dst; + struct sockaddr_qrtr src; struct sk_buff *skb; while ((skb = skb_dequeue(&node->rx_queue)) != NULL) { - const struct qrtr_hdr *phdr; - u32 dst_node, dst_port; struct qrtr_sock *ipc; - u32 src_node; + struct qrtr_cb *cb; int confirm; - phdr = (const struct qrtr_hdr *)skb_transport_header(skb); - src_node = le32_to_cpu(phdr->src_node_id); - dst_node = le32_to_cpu(phdr->dst_node_id); - dst_port = le32_to_cpu(phdr->dst_port_id); - confirm = !!phdr->confirm_rx; + cb = (struct qrtr_cb *)skb->cb; + src.sq_node = cb->src_node; + src.sq_port = cb->src_port; + dst.sq_node = cb->dst_node; + dst.sq_port = cb->dst_port; + confirm = !!cb->confirm_rx; - qrtr_node_assign(node, src_node); + qrtr_node_assign(node, cb->src_node); - ipc = qrtr_port_lookup(dst_port); + ipc = qrtr_port_lookup(cb->dst_port); if (!ipc) { kfree_skb(skb); } else { @@ -368,10 +393,16 @@ static void qrtr_node_rx_work(struct work_struct *work) } if (confirm) { - skb = qrtr_alloc_resume_tx(dst_node, node->nid, dst_port); + skb = qrtr_alloc_ctrl_packet(&pkt); if (!skb) break; - if (qrtr_node_enqueue(node, skb)) + + pkt->cmd = cpu_to_le32(QRTR_TYPE_RESUME_TX); + pkt->client.node = cpu_to_le32(dst.sq_node); + pkt->client.port = cpu_to_le32(dst.sq_port); + + if (qrtr_node_enqueue(node, skb, QRTR_TYPE_RESUME_TX, + &dst, &src)) break; } } @@ -421,6 +452,9 @@ EXPORT_SYMBOL_GPL(qrtr_endpoint_register); void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) { struct qrtr_node *node = ep->node; + struct sockaddr_qrtr src = {AF_QIPCRTR, node->nid, QRTR_PORT_CTRL}; + struct sockaddr_qrtr dst = {AF_QIPCRTR, qrtr_local_nid, QRTR_PORT_CTRL}; + struct qrtr_ctrl_pkt *pkt; struct sk_buff *skb; mutex_lock(&node->ep_lock); @@ -428,9 +462,11 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) mutex_unlock(&node->ep_lock); /* Notify the local controller about the event */ - skb = qrtr_alloc_local_bye(node->nid); - if (skb) - qrtr_local_enqueue(NULL, skb); + skb = qrtr_alloc_ctrl_packet(&pkt); + if (skb) { + pkt->cmd = cpu_to_le32(QRTR_TYPE_BYE); + qrtr_local_enqueue(NULL, skb, QRTR_TYPE_BYE, &src, &dst); + } qrtr_node_release(node); ep->node = NULL; @@ -466,13 +502,24 @@ static void qrtr_port_put(struct qrtr_sock *ipc) /* Remove port assignment. */ static void qrtr_port_remove(struct qrtr_sock *ipc) { + struct qrtr_ctrl_pkt *pkt; struct sk_buff *skb; int port = ipc->us.sq_port; + struct sockaddr_qrtr to; - skb = qrtr_alloc_del_client(&ipc->us); + to.sq_family = AF_QIPCRTR; + to.sq_node = QRTR_NODE_BCAST; + to.sq_port = QRTR_PORT_CTRL; + + skb = qrtr_alloc_ctrl_packet(&pkt); if (skb) { + pkt->cmd = cpu_to_le32(QRTR_TYPE_DEL_CLIENT); + pkt->client.node = cpu_to_le32(ipc->us.sq_node); + pkt->client.port = cpu_to_le32(ipc->us.sq_port); + skb_set_owner_w(skb, &ipc->sk); - qrtr_bcast_enqueue(NULL, skb); + qrtr_bcast_enqueue(NULL, skb, QRTR_TYPE_DEL_CLIENT, &ipc->us, + &to); } if (port == QRTR_PORT_CTRL) @@ -541,7 +588,7 @@ static void qrtr_reset_ports(void) sock_hold(&ipc->sk); ipc->sk.sk_err = ENETRESET; - wake_up_interruptible(sk_sleep(&ipc->sk)); + ipc->sk.sk_error_report(&ipc->sk); sock_put(&ipc->sk); } mutex_unlock(&qrtr_port_lock); @@ -620,19 +667,23 @@ static int qrtr_bind(struct socket *sock, struct sockaddr *saddr, int len) } /* Queue packet to local peer socket. */ -static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb) +static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to) { - const struct qrtr_hdr *phdr; struct qrtr_sock *ipc; + struct qrtr_cb *cb; - phdr = (const struct qrtr_hdr *)skb_transport_header(skb); - - ipc = qrtr_port_lookup(le32_to_cpu(phdr->dst_port_id)); + ipc = qrtr_port_lookup(to->sq_port); if (!ipc || &ipc->sk == skb->sk) { /* do not send to self */ kfree_skb(skb); return -ENODEV; } + cb = (struct qrtr_cb *)skb->cb; + cb->src_node = from->sq_node; + cb->src_port = from->sq_port; + if (sock_queue_rcv_skb(&ipc->sk, skb)) { qrtr_port_put(ipc); kfree_skb(skb); @@ -645,7 +696,9 @@ static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb) } /* Queue packet for broadcast. */ -static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb) +static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to) { struct sk_buff *skbn; @@ -655,11 +708,11 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb) if (!skbn) break; skb_set_owner_w(skbn, skb->sk); - qrtr_node_enqueue(node, skbn); + qrtr_node_enqueue(node, skbn, type, from, to); } mutex_unlock(&qrtr_node_lock); - qrtr_local_enqueue(node, skb); + qrtr_local_enqueue(node, skb, type, from, to); return 0; } @@ -667,13 +720,14 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb) static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_qrtr *, addr, msg->msg_name); - int (*enqueue_fn)(struct qrtr_node *, struct sk_buff *); + int (*enqueue_fn)(struct qrtr_node *, struct sk_buff *, int, + struct sockaddr_qrtr *, struct sockaddr_qrtr *); struct qrtr_sock *ipc = qrtr_sk(sock->sk); struct sock *sk = sock->sk; struct qrtr_node *node; - struct qrtr_hdr *hdr; struct sk_buff *skb; size_t plen; + u32 type = QRTR_TYPE_DATA; int rc; if (msg->msg_flags & ~(MSG_DONTWAIT)) @@ -722,37 +776,19 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } plen = (len + 3) & ~3; - skb = sock_alloc_send_skb(sk, plen + QRTR_HDR_SIZE, + skb = sock_alloc_send_skb(sk, plen + QRTR_HDR_MAX_SIZE, msg->msg_flags & MSG_DONTWAIT, &rc); if (!skb) goto out_node; - skb_reset_transport_header(skb); - skb_put(skb, len + QRTR_HDR_SIZE); - - hdr = (struct qrtr_hdr *)skb_transport_header(skb); - hdr->version = cpu_to_le32(QRTR_PROTO_VER); - hdr->src_node_id = cpu_to_le32(ipc->us.sq_node); - hdr->src_port_id = cpu_to_le32(ipc->us.sq_port); - hdr->confirm_rx = cpu_to_le32(0); - hdr->size = cpu_to_le32(len); - hdr->dst_node_id = cpu_to_le32(addr->sq_node); - hdr->dst_port_id = cpu_to_le32(addr->sq_port); + skb_reserve(skb, QRTR_HDR_MAX_SIZE); - rc = skb_copy_datagram_from_iter(skb, QRTR_HDR_SIZE, - &msg->msg_iter, len); + rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc) { kfree_skb(skb); goto out_node; } - if (plen != len) { - rc = skb_pad(skb, plen - len); - if (rc) - goto out_node; - skb_put(skb, plen - len); - } - if (ipc->us.sq_port == QRTR_PORT_CTRL) { if (len < 4) { rc = -EINVAL; @@ -761,12 +797,11 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } /* control messages already require the type as 'command' */ - skb_copy_bits(skb, QRTR_HDR_SIZE, &hdr->type, 4); - } else { - hdr->type = cpu_to_le32(QRTR_TYPE_DATA); + skb_copy_bits(skb, 0, &type, 4); + type = le32_to_cpu(type); } - rc = enqueue_fn(node, skb); + rc = enqueue_fn(node, skb, type, &ipc->us, addr); if (rc >= 0) rc = len; @@ -781,9 +816,9 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { DECLARE_SOCKADDR(struct sockaddr_qrtr *, addr, msg->msg_name); - const struct qrtr_hdr *phdr; struct sock *sk = sock->sk; struct sk_buff *skb; + struct qrtr_cb *cb; int copied, rc; lock_sock(sk); @@ -800,22 +835,22 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, return rc; } - phdr = (const struct qrtr_hdr *)skb_transport_header(skb); - copied = le32_to_cpu(phdr->size); + copied = skb->len; if (copied > size) { copied = size; msg->msg_flags |= MSG_TRUNC; } - rc = skb_copy_datagram_msg(skb, QRTR_HDR_SIZE, msg, copied); + rc = skb_copy_datagram_msg(skb, 0, msg, copied); if (rc < 0) goto out; rc = copied; if (addr) { + cb = (struct qrtr_cb *)skb->cb; addr->sq_family = AF_QIPCRTR; - addr->sq_node = le32_to_cpu(phdr->src_node_id); - addr->sq_port = le32_to_cpu(phdr->src_port_id); + addr->sq_node = cb->src_node; + addr->sq_port = cb->src_port; msg->msg_namelen = sizeof(*addr); } @@ -908,7 +943,7 @@ static int qrtr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case TIOCINQ: skb = skb_peek(&sk->sk_receive_queue); if (skb) - len = skb->len - QRTR_HDR_SIZE; + len = skb->len; rc = put_user(len, (int __user *)argp); break; case SIOCGIFADDR: diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 4a9729257023..6a5c4992cf61 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -318,9 +318,11 @@ void rose_destroy_socket(struct sock *); /* * Handler for deferred kills. */ -static void rose_destroy_timer(unsigned long data) +static void rose_destroy_timer(struct timer_list *t) { - rose_destroy_socket((struct sock *)data); + struct sock *sk = from_timer(sk, t, sk_timer); + + rose_destroy_socket(sk); } /* @@ -353,8 +355,7 @@ void rose_destroy_socket(struct sock *sk) if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ - setup_timer(&sk->sk_timer, rose_destroy_timer, - (unsigned long)sk); + timer_setup(&sk->sk_timer, rose_destroy_timer, 0); sk->sk_timer.expires = jiffies + 10 * HZ; add_timer(&sk->sk_timer); } else @@ -538,8 +539,8 @@ static int rose_create(struct net *net, struct socket *sock, int protocol, sock->ops = &rose_proto_ops; sk->sk_protocol = protocol; - init_timer(&rose->timer); - init_timer(&rose->idletimer); + timer_setup(&rose->timer, NULL, 0); + timer_setup(&rose->idletimer, NULL, 0); rose->t1 = msecs_to_jiffies(sysctl_rose_call_request_timeout); rose->t2 = msecs_to_jiffies(sysctl_rose_reset_request_timeout); @@ -582,8 +583,8 @@ static struct sock *rose_make_new(struct sock *osk) sk->sk_state = TCP_ESTABLISHED; sock_copy_flags(sk, osk); - init_timer(&rose->timer); - init_timer(&rose->idletimer); + timer_setup(&rose->timer, NULL, 0); + timer_setup(&rose->idletimer, NULL, 0); orose = rose_sk(osk); rose->t1 = orose->t1; diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c index c76638cc2cd5..cda4c6678ef1 100644 --- a/net/rose/rose_link.c +++ b/net/rose/rose_link.c @@ -27,8 +27,8 @@ #include <linux/interrupt.h> #include <net/rose.h> -static void rose_ftimer_expiry(unsigned long); -static void rose_t0timer_expiry(unsigned long); +static void rose_ftimer_expiry(struct timer_list *); +static void rose_t0timer_expiry(struct timer_list *); static void rose_transmit_restart_confirmation(struct rose_neigh *neigh); static void rose_transmit_restart_request(struct rose_neigh *neigh); @@ -37,8 +37,7 @@ void rose_start_ftimer(struct rose_neigh *neigh) { del_timer(&neigh->ftimer); - neigh->ftimer.data = (unsigned long)neigh; - neigh->ftimer.function = &rose_ftimer_expiry; + neigh->ftimer.function = (TIMER_FUNC_TYPE)rose_ftimer_expiry; neigh->ftimer.expires = jiffies + msecs_to_jiffies(sysctl_rose_link_fail_timeout); @@ -49,8 +48,7 @@ static void rose_start_t0timer(struct rose_neigh *neigh) { del_timer(&neigh->t0timer); - neigh->t0timer.data = (unsigned long)neigh; - neigh->t0timer.function = &rose_t0timer_expiry; + neigh->t0timer.function = (TIMER_FUNC_TYPE)rose_t0timer_expiry; neigh->t0timer.expires = jiffies + msecs_to_jiffies(sysctl_rose_restart_request_timeout); @@ -77,13 +75,13 @@ static int rose_t0timer_running(struct rose_neigh *neigh) return timer_pending(&neigh->t0timer); } -static void rose_ftimer_expiry(unsigned long param) +static void rose_ftimer_expiry(struct timer_list *t) { } -static void rose_t0timer_expiry(unsigned long param) +static void rose_t0timer_expiry(struct timer_list *t) { - struct rose_neigh *neigh = (struct rose_neigh *)param; + struct rose_neigh *neigh = from_timer(neigh, t, t0timer); rose_transmit_restart_request(neigh); diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 344456206b70..7af4f99c4a93 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -19,12 +19,13 @@ static struct sk_buff_head loopback_queue; static struct timer_list loopback_timer; static void rose_set_loopback_timer(void); +static void rose_loopback_timer(struct timer_list *unused); void rose_loopback_init(void) { skb_queue_head_init(&loopback_queue); - init_timer(&loopback_timer); + timer_setup(&loopback_timer, rose_loopback_timer, 0); } static int rose_loopback_running(void) @@ -50,20 +51,16 @@ int rose_loopback_queue(struct sk_buff *skb, struct rose_neigh *neigh) return 1; } -static void rose_loopback_timer(unsigned long); static void rose_set_loopback_timer(void) { del_timer(&loopback_timer); - loopback_timer.data = 0; - loopback_timer.function = &rose_loopback_timer; loopback_timer.expires = jiffies + 10; - add_timer(&loopback_timer); } -static void rose_loopback_timer(unsigned long param) +static void rose_loopback_timer(struct timer_list *unused) { struct sk_buff *skb; struct net_device *dev; diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index 452bbb38d943..65921cd10323 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -104,8 +104,8 @@ static int __must_check rose_add_node(struct rose_route_struct *rose_route, skb_queue_head_init(&rose_neigh->queue); - init_timer(&rose_neigh->ftimer); - init_timer(&rose_neigh->t0timer); + timer_setup(&rose_neigh->ftimer, NULL, 0); + timer_setup(&rose_neigh->t0timer, NULL, 0); if (rose_route->ndigis != 0) { rose_neigh->digipeat = @@ -390,8 +390,8 @@ void rose_add_loopback_neigh(void) skb_queue_head_init(&sn->queue); - init_timer(&sn->ftimer); - init_timer(&sn->t0timer); + timer_setup(&sn->ftimer, NULL, 0); + timer_setup(&sn->t0timer, NULL, 0); spin_lock_bh(&rose_neigh_list_lock); sn->next = rose_neigh_list; diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c index bc5469d6d9cb..ea613b2a9735 100644 --- a/net/rose/rose_timer.c +++ b/net/rose/rose_timer.c @@ -28,16 +28,15 @@ #include <linux/interrupt.h> #include <net/rose.h> -static void rose_heartbeat_expiry(unsigned long); -static void rose_timer_expiry(unsigned long); -static void rose_idletimer_expiry(unsigned long); +static void rose_heartbeat_expiry(struct timer_list *t); +static void rose_timer_expiry(struct timer_list *); +static void rose_idletimer_expiry(struct timer_list *); void rose_start_heartbeat(struct sock *sk) { del_timer(&sk->sk_timer); - sk->sk_timer.data = (unsigned long)sk; - sk->sk_timer.function = &rose_heartbeat_expiry; + sk->sk_timer.function = (TIMER_FUNC_TYPE)rose_heartbeat_expiry; sk->sk_timer.expires = jiffies + 5 * HZ; add_timer(&sk->sk_timer); @@ -49,8 +48,7 @@ void rose_start_t1timer(struct sock *sk) del_timer(&rose->timer); - rose->timer.data = (unsigned long)sk; - rose->timer.function = &rose_timer_expiry; + rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry; rose->timer.expires = jiffies + rose->t1; add_timer(&rose->timer); @@ -62,8 +60,7 @@ void rose_start_t2timer(struct sock *sk) del_timer(&rose->timer); - rose->timer.data = (unsigned long)sk; - rose->timer.function = &rose_timer_expiry; + rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry; rose->timer.expires = jiffies + rose->t2; add_timer(&rose->timer); @@ -75,8 +72,7 @@ void rose_start_t3timer(struct sock *sk) del_timer(&rose->timer); - rose->timer.data = (unsigned long)sk; - rose->timer.function = &rose_timer_expiry; + rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry; rose->timer.expires = jiffies + rose->t3; add_timer(&rose->timer); @@ -88,8 +84,7 @@ void rose_start_hbtimer(struct sock *sk) del_timer(&rose->timer); - rose->timer.data = (unsigned long)sk; - rose->timer.function = &rose_timer_expiry; + rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry; rose->timer.expires = jiffies + rose->hb; add_timer(&rose->timer); @@ -102,8 +97,7 @@ void rose_start_idletimer(struct sock *sk) del_timer(&rose->idletimer); if (rose->idle > 0) { - rose->idletimer.data = (unsigned long)sk; - rose->idletimer.function = &rose_idletimer_expiry; + rose->idletimer.function = (TIMER_FUNC_TYPE)rose_idletimer_expiry; rose->idletimer.expires = jiffies + rose->idle; add_timer(&rose->idletimer); @@ -125,9 +119,9 @@ void rose_stop_idletimer(struct sock *sk) del_timer(&rose_sk(sk)->idletimer); } -static void rose_heartbeat_expiry(unsigned long param) +static void rose_heartbeat_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct sock *sk = from_timer(sk, t, sk_timer); struct rose_sock *rose = rose_sk(sk); bh_lock_sock(sk); @@ -163,10 +157,10 @@ static void rose_heartbeat_expiry(unsigned long param) bh_unlock_sock(sk); } -static void rose_timer_expiry(unsigned long param) +static void rose_timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; - struct rose_sock *rose = rose_sk(sk); + struct rose_sock *rose = from_timer(rose, t, timer); + struct sock *sk = &rose->sock; bh_lock_sock(sk); switch (rose->state) { @@ -192,9 +186,10 @@ static void rose_timer_expiry(unsigned long param) bh_unlock_sock(sk); } -static void rose_idletimer_expiry(unsigned long param) +static void rose_idletimer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct rose_sock *rose = from_timer(rose, t, idletimer); + struct sock *sk = &rose->sock; bh_lock_sock(sk); rose_clear_queues(sk); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index fb17552fd292..73c980e26581 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -265,6 +265,7 @@ static int rxrpc_listen(struct socket *sock, int backlog) * @tx_total_len: Total length of data to transmit during the call (or -1) * @gfp: The allocation constraints * @notify_rx: Where to send notifications instead of socket queue + * @upgrade: Request service upgrade for call * * Allow a kernel service to begin a call on the nominated socket. This just * sets up all the internal tracking structures and allocates connection and @@ -279,7 +280,8 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, unsigned long user_call_ID, s64 tx_total_len, gfp_t gfp, - rxrpc_notify_rx_t notify_rx) + rxrpc_notify_rx_t notify_rx, + bool upgrade) { struct rxrpc_conn_parameters cp; struct rxrpc_call *call; @@ -304,6 +306,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, cp.key = key; cp.security_level = 0; cp.exclusive = false; + cp.upgrade = upgrade; cp.service_id = srx->srx_service; call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, tx_total_len, gfp); @@ -337,6 +340,25 @@ void rxrpc_kernel_end_call(struct socket *sock, struct rxrpc_call *call) EXPORT_SYMBOL(rxrpc_kernel_end_call); /** + * rxrpc_kernel_check_life - Check to see whether a call is still alive + * @sock: The socket the call is on + * @call: The call to check + * + * Allow a kernel service to find out whether a call is still alive - ie. we're + * getting ACKs from the server. Returns a number representing the life state + * which can be compared to that returned by a previous call. + * + * If this is a client call, ping ACKs will be sent to the server to find out + * whether it's still responsive and whether the call is still alive on the + * server. + */ +u32 rxrpc_kernel_check_life(struct socket *sock, struct rxrpc_call *call) +{ + return call->acks_latest; +} +EXPORT_SYMBOL(rxrpc_kernel_check_life); + +/** * rxrpc_kernel_check_call - Check a call's state * @sock: The socket the call is on * @call: The call to check diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 5787f97f5330..d02a99f37f5f 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -411,3 +411,16 @@ void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call, *_srx = call->peer->srx; } EXPORT_SYMBOL(rxrpc_kernel_get_peer); + +/** + * rxrpc_kernel_get_rtt - Get a call's peer RTT + * @sock: The socket on which the call is in progress. + * @call: The call to query + * + * Get the call's peer RTT. + */ +u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call) +{ + return call->peer->rtt; +} +EXPORT_SYMBOL(rxrpc_kernel_get_rtt); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index bdece21f313d..e4937b3f3685 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -607,6 +607,7 @@ wait_error: * @_offset: The running offset into the buffer. * @want_more: True if more data is expected to be read * @_abort: Where the abort code is stored if -ECONNABORTED is returned + * @_service: Where to store the actual service ID (may be upgraded) * * Allow a kernel service to receive data and pick up information about the * state of a call. Returns 0 if got what was asked for and there's more @@ -624,7 +625,7 @@ wait_error: */ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, void *buf, size_t size, size_t *_offset, - bool want_more, u32 *_abort) + bool want_more, u32 *_abort, u16 *_service) { struct iov_iter iter; struct kvec iov; @@ -680,6 +681,8 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, read_phase_complete: ret = 1; out: + if (_service) + *_service = call->service_id; mutex_unlock(&call->user_mutex); _leave(" = %d [%zu,%d]", ret, *_offset, *_abort); return ret; diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 9ea6f972767e..2d9edc656ca3 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -38,12 +38,86 @@ struct rxrpc_send_params { }; /* + * Wait for space to appear in the Tx queue or a signal to occur. + */ +static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, + struct rxrpc_call *call, + long *timeo) +{ + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + if (call->tx_top - call->tx_hard_ack < + min_t(unsigned int, call->tx_winsize, + call->cong_cwnd + call->cong_extra)) + return 0; + + if (call->state >= RXRPC_CALL_COMPLETE) + return call->error; + + if (signal_pending(current)) + return sock_intr_errno(*timeo); + + trace_rxrpc_transmit(call, rxrpc_transmit_wait); + mutex_unlock(&call->user_mutex); + *timeo = schedule_timeout(*timeo); + if (mutex_lock_interruptible(&call->user_mutex) < 0) + return sock_intr_errno(*timeo); + } +} + +/* + * Wait for space to appear in the Tx queue uninterruptibly, but with + * a timeout of 2*RTT if no progress was made and a signal occurred. + */ +static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, + struct rxrpc_call *call) +{ + rxrpc_seq_t tx_start, tx_win; + signed long rtt2, timeout; + u64 rtt; + + rtt = READ_ONCE(call->peer->rtt); + rtt2 = nsecs_to_jiffies64(rtt) * 2; + if (rtt2 < 1) + rtt2 = 1; + + timeout = rtt2; + tx_start = READ_ONCE(call->tx_hard_ack); + + for (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + + tx_win = READ_ONCE(call->tx_hard_ack); + if (call->tx_top - tx_win < + min_t(unsigned int, call->tx_winsize, + call->cong_cwnd + call->cong_extra)) + return 0; + + if (call->state >= RXRPC_CALL_COMPLETE) + return call->error; + + if (timeout == 0 && + tx_win == tx_start && signal_pending(current)) + return -EINTR; + + if (tx_win != tx_start) { + timeout = rtt2; + tx_start = tx_win; + } + + trace_rxrpc_transmit(call, rxrpc_transmit_wait); + timeout = schedule_timeout(timeout); + } +} + +/* * wait for space to appear in the transmit/ACK window * - caller holds the socket locked */ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, struct rxrpc_call *call, - long *timeo) + long *timeo, + bool waitall) { DECLARE_WAITQUEUE(myself, current); int ret; @@ -53,30 +127,10 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, add_wait_queue(&call->waitq, &myself); - for (;;) { - set_current_state(TASK_INTERRUPTIBLE); - ret = 0; - if (call->tx_top - call->tx_hard_ack < - min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra)) - break; - if (call->state >= RXRPC_CALL_COMPLETE) { - ret = call->error; - break; - } - if (signal_pending(current)) { - ret = sock_intr_errno(*timeo); - break; - } - - trace_rxrpc_transmit(call, rxrpc_transmit_wait); - mutex_unlock(&call->user_mutex); - *timeo = schedule_timeout(*timeo); - if (mutex_lock_interruptible(&call->user_mutex) < 0) { - ret = sock_intr_errno(*timeo); - break; - } - } + if (waitall) + ret = rxrpc_wait_for_tx_window_nonintr(rx, call); + else + ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo); remove_wait_queue(&call->waitq, &myself); set_current_state(TASK_RUNNING); @@ -254,7 +308,8 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, if (msg->msg_flags & MSG_DONTWAIT) goto maybe_error; ret = rxrpc_wait_for_tx_window(rx, call, - &timeo); + &timeo, + msg->msg_flags & MSG_WAITALL); if (ret < 0) goto maybe_error; } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index da6fa82c98a8..c67b820a8307 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -21,6 +21,8 @@ #include <linux/kmod.h> #include <linux/err.h> #include <linux/module.h> +#include <linux/rhashtable.h> +#include <linux/list.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/sch_generic.h> @@ -1249,8 +1251,227 @@ out_module_put: return skb->len; } +struct tcf_action_net { + struct rhashtable egdev_ht; +}; + +static unsigned int tcf_action_net_id; + +struct tcf_action_egdev_cb { + struct list_head list; + tc_setup_cb_t *cb; + void *cb_priv; +}; + +struct tcf_action_egdev { + struct rhash_head ht_node; + const struct net_device *dev; + unsigned int refcnt; + struct list_head cb_list; +}; + +static const struct rhashtable_params tcf_action_egdev_ht_params = { + .key_offset = offsetof(struct tcf_action_egdev, dev), + .head_offset = offsetof(struct tcf_action_egdev, ht_node), + .key_len = sizeof(const struct net_device *), +}; + +static struct tcf_action_egdev * +tcf_action_egdev_lookup(const struct net_device *dev) +{ + struct net *net = dev_net(dev); + struct tcf_action_net *tan = net_generic(net, tcf_action_net_id); + + return rhashtable_lookup_fast(&tan->egdev_ht, &dev, + tcf_action_egdev_ht_params); +} + +static struct tcf_action_egdev * +tcf_action_egdev_get(const struct net_device *dev) +{ + struct tcf_action_egdev *egdev; + struct tcf_action_net *tan; + + egdev = tcf_action_egdev_lookup(dev); + if (egdev) + goto inc_ref; + + egdev = kzalloc(sizeof(*egdev), GFP_KERNEL); + if (!egdev) + return NULL; + INIT_LIST_HEAD(&egdev->cb_list); + egdev->dev = dev; + tan = net_generic(dev_net(dev), tcf_action_net_id); + rhashtable_insert_fast(&tan->egdev_ht, &egdev->ht_node, + tcf_action_egdev_ht_params); + +inc_ref: + egdev->refcnt++; + return egdev; +} + +static void tcf_action_egdev_put(struct tcf_action_egdev *egdev) +{ + struct tcf_action_net *tan; + + if (--egdev->refcnt) + return; + tan = net_generic(dev_net(egdev->dev), tcf_action_net_id); + rhashtable_remove_fast(&tan->egdev_ht, &egdev->ht_node, + tcf_action_egdev_ht_params); + kfree(egdev); +} + +static struct tcf_action_egdev_cb * +tcf_action_egdev_cb_lookup(struct tcf_action_egdev *egdev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev_cb *egdev_cb; + + list_for_each_entry(egdev_cb, &egdev->cb_list, list) + if (egdev_cb->cb == cb && egdev_cb->cb_priv == cb_priv) + return egdev_cb; + return NULL; +} + +static int tcf_action_egdev_cb_call(struct tcf_action_egdev *egdev, + enum tc_setup_type type, + void *type_data, bool err_stop) +{ + struct tcf_action_egdev_cb *egdev_cb; + int ok_count = 0; + int err; + + list_for_each_entry(egdev_cb, &egdev->cb_list, list) { + err = egdev_cb->cb(type, type_data, egdev_cb->cb_priv); + if (err) { + if (err_stop) + return err; + } else { + ok_count++; + } + } + return ok_count; +} + +static int tcf_action_egdev_cb_add(struct tcf_action_egdev *egdev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev_cb *egdev_cb; + + egdev_cb = tcf_action_egdev_cb_lookup(egdev, cb, cb_priv); + if (WARN_ON(egdev_cb)) + return -EEXIST; + egdev_cb = kzalloc(sizeof(*egdev_cb), GFP_KERNEL); + if (!egdev_cb) + return -ENOMEM; + egdev_cb->cb = cb; + egdev_cb->cb_priv = cb_priv; + list_add(&egdev_cb->list, &egdev->cb_list); + return 0; +} + +static void tcf_action_egdev_cb_del(struct tcf_action_egdev *egdev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev_cb *egdev_cb; + + egdev_cb = tcf_action_egdev_cb_lookup(egdev, cb, cb_priv); + if (WARN_ON(!egdev_cb)) + return; + list_del(&egdev_cb->list); + kfree(egdev_cb); +} + +static int __tc_setup_cb_egdev_register(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev *egdev = tcf_action_egdev_get(dev); + int err; + + if (!egdev) + return -ENOMEM; + err = tcf_action_egdev_cb_add(egdev, cb, cb_priv); + if (err) + goto err_cb_add; + return 0; + +err_cb_add: + tcf_action_egdev_put(egdev); + return err; +} +int tc_setup_cb_egdev_register(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ + int err; + + rtnl_lock(); + err = __tc_setup_cb_egdev_register(dev, cb, cb_priv); + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_register); + +static void __tc_setup_cb_egdev_unregister(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev *egdev = tcf_action_egdev_lookup(dev); + + if (WARN_ON(!egdev)) + return; + tcf_action_egdev_cb_del(egdev, cb, cb_priv); + tcf_action_egdev_put(egdev); +} +void tc_setup_cb_egdev_unregister(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ + rtnl_lock(); + __tc_setup_cb_egdev_unregister(dev, cb, cb_priv); + rtnl_unlock(); +} +EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_unregister); + +int tc_setup_cb_egdev_call(const struct net_device *dev, + enum tc_setup_type type, void *type_data, + bool err_stop) +{ + struct tcf_action_egdev *egdev = tcf_action_egdev_lookup(dev); + + if (!egdev) + return 0; + return tcf_action_egdev_cb_call(egdev, type, type_data, err_stop); +} +EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_call); + +static __net_init int tcf_action_net_init(struct net *net) +{ + struct tcf_action_net *tan = net_generic(net, tcf_action_net_id); + + return rhashtable_init(&tan->egdev_ht, &tcf_action_egdev_ht_params); +} + +static void __net_exit tcf_action_net_exit(struct net *net) +{ + struct tcf_action_net *tan = net_generic(net, tcf_action_net_id); + + rhashtable_destroy(&tan->egdev_ht); +} + +static struct pernet_operations tcf_action_net_ops = { + .init = tcf_action_net_init, + .exit = tcf_action_net_exit, + .id = &tcf_action_net_id, + .size = sizeof(struct tcf_action_net), +}; + static int __init tc_action_init(void) { + int err; + + err = register_pernet_subsys(&tcf_action_net_ops); + if (err) + return err; + rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action, diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 8ccd35825b6b..3007cb1310ea 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -248,6 +248,22 @@ static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len) return ret; } +#ifdef CONFIG_MODULES +static const char *ife_meta_id2name(u32 metaid) +{ + switch (metaid) { + case IFE_META_SKBMARK: + return "skbmark"; + case IFE_META_PRIO: + return "skbprio"; + case IFE_META_TCINDEX: + return "tcindex"; + default: + return "unknown"; + } +} +#endif + /* called when adding new meta information * under ife->tcf_lock for existing action */ @@ -263,7 +279,7 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, if (exists) spin_unlock_bh(&ife->tcf_lock); rtnl_unlock(); - request_module("ifemeta%u", metaid); + request_module("ife-meta-%s", ife_meta_id2name(metaid)); rtnl_lock(); if (exists) spin_lock_bh(&ife->tcf_lock); @@ -392,10 +408,14 @@ static void _tcf_ife_cleanup(struct tc_action *a, int bind) static void tcf_ife_cleanup(struct tc_action *a, int bind) { struct tcf_ife_info *ife = to_ife(a); + struct tcf_ife_params *p; spin_lock_bh(&ife->tcf_lock); _tcf_ife_cleanup(a, bind); spin_unlock_bh(&ife->tcf_lock); + + p = rcu_dereference_protected(ife->params, 1); + kfree_rcu(p, rcu); } /* under ife->tcf_lock for existing action */ @@ -432,6 +452,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, ife_net_id); struct nlattr *tb[TCA_IFE_MAX + 1]; struct nlattr *tb2[IFE_META_MAX + 1]; + struct tcf_ife_params *p, *p_old; struct tcf_ife_info *ife; u16 ife_type = ETH_P_IFE; struct tc_ife *parm; @@ -450,24 +471,41 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_IFE_PARMS]); + /* IFE_DECODE is 0 and indicates the opposite of IFE_ENCODE because + * they cannot run as the same time. Check on all other values which + * are not supported right now. + */ + if (parm->flags & ~IFE_ENCODE) + return -EINVAL; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + exists = tcf_idr_check(tn, parm->index, a, bind); - if (exists && bind) + if (exists && bind) { + kfree(p); return 0; + } if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops, - bind, false); - if (ret) + bind, true); + if (ret) { + kfree(p); return ret; + } ret = ACT_P_CREATED; } else { tcf_idr_release(*a, bind); - if (!ovr) + if (!ovr) { + kfree(p); return -EEXIST; + } } ife = to_ife(*a); - ife->flags = parm->flags; + p->flags = parm->flags; if (parm->flags & IFE_ENCODE) { if (tb[TCA_IFE_TYPE]) @@ -478,24 +516,25 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, saddr = nla_data(tb[TCA_IFE_SMAC]); } - if (exists) - spin_lock_bh(&ife->tcf_lock); ife->tcf_action = parm->action; if (parm->flags & IFE_ENCODE) { if (daddr) - ether_addr_copy(ife->eth_dst, daddr); + ether_addr_copy(p->eth_dst, daddr); else - eth_zero_addr(ife->eth_dst); + eth_zero_addr(p->eth_dst); if (saddr) - ether_addr_copy(ife->eth_src, saddr); + ether_addr_copy(p->eth_src, saddr); else - eth_zero_addr(ife->eth_src); + eth_zero_addr(p->eth_src); - ife->eth_type = ife_type; + p->eth_type = ife_type; } + if (exists) + spin_lock_bh(&ife->tcf_lock); + if (ret == ACT_P_CREATED) INIT_LIST_HEAD(&ife->metalist); @@ -511,6 +550,7 @@ metadata_parse_err: if (exists) spin_unlock_bh(&ife->tcf_lock); + kfree(p); return err; } @@ -531,6 +571,7 @@ metadata_parse_err: if (exists) spin_unlock_bh(&ife->tcf_lock); + kfree(p); return err; } } @@ -538,6 +579,11 @@ metadata_parse_err: if (exists) spin_unlock_bh(&ife->tcf_lock); + p_old = rtnl_dereference(ife->params); + rcu_assign_pointer(ife->params, p); + if (p_old) + kfree_rcu(p_old, rcu); + if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); @@ -549,12 +595,13 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, { unsigned char *b = skb_tail_pointer(skb); struct tcf_ife_info *ife = to_ife(a); + struct tcf_ife_params *p = rtnl_dereference(ife->params); struct tc_ife opt = { .index = ife->tcf_index, .refcnt = ife->tcf_refcnt - ref, .bindcnt = ife->tcf_bindcnt - bind, .action = ife->tcf_action, - .flags = ife->flags, + .flags = p->flags, }; struct tcf_t t; @@ -565,17 +612,17 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, if (nla_put_64bit(skb, TCA_IFE_TM, sizeof(t), &t, TCA_IFE_PAD)) goto nla_put_failure; - if (!is_zero_ether_addr(ife->eth_dst)) { - if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, ife->eth_dst)) + if (!is_zero_ether_addr(p->eth_dst)) { + if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, p->eth_dst)) goto nla_put_failure; } - if (!is_zero_ether_addr(ife->eth_src)) { - if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, ife->eth_src)) + if (!is_zero_ether_addr(p->eth_src)) { + if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, p->eth_src)) goto nla_put_failure; } - if (nla_put(skb, TCA_IFE_TYPE, 2, &ife->eth_type)) + if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type)) goto nla_put_failure; if (dump_metalist(skb, ife)) { @@ -617,19 +664,15 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u8 *tlv_data; u16 metalen; - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); + bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); - spin_unlock(&ife->tcf_lock); if (skb_at_tc_ingress(skb)) skb_push(skb, skb->dev->hard_header_len); tlv_data = ife_decode(skb, &metalen); if (unlikely(!tlv_data)) { - spin_lock(&ife->tcf_lock); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -647,14 +690,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, */ pr_info_ratelimited("Unknown metaid %d dlen %d\n", mtype, dlen); - ife->tcf_qstats.overlimits++; + qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats)); } } if (WARN_ON(tlv_data != ifehdr_end)) { - spin_lock(&ife->tcf_lock); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -683,7 +724,7 @@ static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife) } static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) + struct tcf_result *res, struct tcf_ife_params *p) { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; @@ -706,23 +747,20 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, exceed_mtu = true; } - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); + bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); if (!metalen) { /* no metadata to send */ /* abuse overlimits to count when we allow packet * with no metadata */ - ife->tcf_qstats.overlimits++; - spin_unlock(&ife->tcf_lock); + qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats)); return action; } /* could be stupid policy setup or mtu config * so lets be conservative.. */ if ((action == TC_ACT_SHOT) || exceed_mtu) { - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -731,6 +769,8 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, ife_meta = ife_encode(skb, metalen); + spin_lock(&ife->tcf_lock); + /* XXX: we dont have a clever way of telling encode to * not repeat some of the computations that are done by * ops->presence_check... @@ -742,25 +782,24 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, } if (err < 0) { /* too corrupt to keep around if overwritten */ - ife->tcf_qstats.drops++; spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } skboff += err; } + spin_unlock(&ife->tcf_lock); oethh = (struct ethhdr *)skb->data; - if (!is_zero_ether_addr(ife->eth_src)) - ether_addr_copy(oethh->h_source, ife->eth_src); - if (!is_zero_ether_addr(ife->eth_dst)) - ether_addr_copy(oethh->h_dest, ife->eth_dst); - oethh->h_proto = htons(ife->eth_type); + if (!is_zero_ether_addr(p->eth_src)) + ether_addr_copy(oethh->h_source, p->eth_src); + if (!is_zero_ether_addr(p->eth_dst)) + ether_addr_copy(oethh->h_dest, p->eth_dst); + oethh->h_proto = htons(p->eth_type); if (skb_at_tc_ingress(skb)) skb_pull(skb, skb->dev->hard_header_len); - spin_unlock(&ife->tcf_lock); - return action; } @@ -768,21 +807,19 @@ static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_ife_info *ife = to_ife(a); + struct tcf_ife_params *p; + int ret; + + rcu_read_lock(); + p = rcu_dereference(ife->params); + if (p->flags & IFE_ENCODE) { + ret = tcf_ife_encode(skb, a, res, p); + rcu_read_unlock(); + return ret; + } + rcu_read_unlock(); - if (ife->flags & IFE_ENCODE) - return tcf_ife_encode(skb, a, res); - - if (!(ife->flags & IFE_ENCODE)) - return tcf_ife_decode(skb, a, res); - - pr_info_ratelimited("unknown failure(policy neither de/encode\n"); - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); - tcf_lastuse_update(&ife->tcf_tm); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); - - return TC_ACT_SHOT; + return tcf_ife_decode(skb, a, res); } static int tcf_ife_walker(struct net *net, struct sk_buff *skb, diff --git a/net/sched/act_meta_mark.c b/net/sched/act_meta_mark.c index 82892170ce4f..1e3f10e5da99 100644 --- a/net/sched/act_meta_mark.c +++ b/net/sched/act_meta_mark.c @@ -76,4 +76,4 @@ module_exit(ifemark_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2015)"); MODULE_DESCRIPTION("Inter-FE skb mark metadata module"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_SKBMARK); +MODULE_ALIAS_IFE_META("skbmark"); diff --git a/net/sched/act_meta_skbprio.c b/net/sched/act_meta_skbprio.c index 26bf4d86030b..4033f9fc4d4a 100644 --- a/net/sched/act_meta_skbprio.c +++ b/net/sched/act_meta_skbprio.c @@ -73,4 +73,4 @@ module_exit(ifeprio_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2015)"); MODULE_DESCRIPTION("Inter-FE skb prio metadata action"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_PRIO); +MODULE_ALIAS_IFE_META("skbprio"); diff --git a/net/sched/act_meta_skbtcindex.c b/net/sched/act_meta_skbtcindex.c index 3b35774ce890..2ea1f26c9e96 100644 --- a/net/sched/act_meta_skbtcindex.c +++ b/net/sched/act_meta_skbtcindex.c @@ -76,4 +76,4 @@ module_exit(ifetc_index_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2016)"); MODULE_DESCRIPTION("Inter-FE skb tc_index metadata module"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_SKBTCINDEX); +MODULE_ALIAS_IFE_META("tcindex"); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 416627c66f08..8b3e59388480 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -140,6 +140,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, m->tcfm_eaction = parm->eaction; if (dev != NULL) { m->tcfm_ifindex = parm->ifindex; + m->net = net; if (ret != ACT_P_CREATED) dev_put(rcu_dereference_protected(m->tcfm_dev, 1)); dev_hold(dev); @@ -313,15 +314,11 @@ static struct notifier_block mirred_device_notifier = { .notifier_call = mirred_device_event, }; -static int tcf_mirred_device(const struct tc_action *a, struct net *net, - struct net_device **mirred_dev) +static struct net_device *tcf_mirred_get_dev(const struct tc_action *a) { - int ifindex = tcf_mirred_ifindex(a); + struct tcf_mirred *m = to_mirred(a); - *mirred_dev = __dev_get_by_index(net, ifindex); - if (!*mirred_dev) - return -EINVAL; - return 0; + return __dev_get_by_index(m->net, m->tcfm_ifindex); } static struct tc_action_ops act_mirred_ops = { @@ -336,7 +333,7 @@ static struct tc_action_ops act_mirred_ops = { .walk = tcf_mirred_walker, .lookup = tcf_mirred_search, .size = sizeof(struct tcf_mirred), - .get_dev = tcf_mirred_device, + .get_dev = tcf_mirred_get_dev, }; static __net_init int mirred_init_net(struct net *net) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 0b2219adf520..2e8e87fd9d97 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -241,7 +241,7 @@ tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain, } int tcf_block_get(struct tcf_block **p_block, - struct tcf_proto __rcu **p_filter_chain) + struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q) { struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL); struct tcf_chain *chain; @@ -257,6 +257,8 @@ int tcf_block_get(struct tcf_block **p_block, goto err_chain_create; } tcf_chain_filter_chain_ptr_set(chain, p_filter_chain); + block->net = qdisc_net(q); + block->q = q; *p_block = block; return 0; @@ -418,8 +420,8 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, } static int tcf_fill_node(struct net *net, struct sk_buff *skb, - struct tcf_proto *tp, void *fh, u32 portid, - u32 seq, u16 flags, int event) + struct tcf_proto *tp, struct Qdisc *q, u32 parent, + void *fh, u32 portid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -432,8 +434,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; - tcm->tcm_ifindex = qdisc_dev(tp->q)->ifindex; - tcm->tcm_parent = tp->classid; + tcm->tcm_ifindex = qdisc_dev(q)->ifindex; + tcm->tcm_parent = parent; tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); if (nla_put_string(skb, TCA_KIND, tp->ops->kind)) goto nla_put_failure; @@ -456,6 +458,7 @@ nla_put_failure: static int tfilter_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, + struct Qdisc *q, u32 parent, void *fh, int event, bool unicast) { struct sk_buff *skb; @@ -465,7 +468,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, + if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq, n->nlmsg_flags, event) <= 0) { kfree_skb(skb); return -EINVAL; @@ -480,6 +483,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, + struct Qdisc *q, u32 parent, void *fh, bool unicast, bool *last) { struct sk_buff *skb; @@ -490,7 +494,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, + if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER) <= 0) { kfree_skb(skb); return -EINVAL; @@ -510,6 +514,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, } static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, + struct Qdisc *q, u32 parent, struct nlmsghdr *n, struct tcf_chain *chain, int event) { @@ -517,7 +522,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, for (tp = rtnl_dereference(chain->filter_chain); tp; tp = rtnl_dereference(tp->next)) - tfilter_notify(net, oskb, n, tp, 0, event, false); + tfilter_notify(net, oskb, n, tp, q, parent, 0, event, false); } /* Add/change/delete/get a filter node */ @@ -636,7 +641,8 @@ replay: } if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) { - tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER); + tfilter_notify_chain(net, skb, q, parent, n, + chain, RTM_DELTFILTER); tcf_chain_flush(chain); err = 0; goto errout; @@ -683,7 +689,7 @@ replay: if (!fh) { if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) { tcf_chain_tp_remove(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, fh, + tfilter_notify(net, skb, n, tp, q, parent, fh, RTM_DELTFILTER, false); tcf_proto_destroy(tp); err = 0; @@ -708,8 +714,8 @@ replay: } break; case RTM_DELTFILTER: - err = tfilter_del_notify(net, skb, n, tp, fh, false, - &last); + err = tfilter_del_notify(net, skb, n, tp, q, parent, + fh, false, &last); if (err) goto errout; if (last) { @@ -718,7 +724,7 @@ replay: } goto errout; case RTM_GETTFILTER: - err = tfilter_notify(net, skb, n, tp, fh, + err = tfilter_notify(net, skb, n, tp, q, parent, fh, RTM_NEWTFILTER, true); goto errout; default: @@ -732,7 +738,8 @@ replay: if (err == 0) { if (tp_created) tcf_chain_tp_insert(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER, false); + tfilter_notify(net, skb, n, tp, q, parent, fh, + RTM_NEWTFILTER, false); } else { if (tp_created) tcf_proto_destroy(tp); @@ -751,6 +758,8 @@ struct tcf_dump_args { struct tcf_walker w; struct sk_buff *skb; struct netlink_callback *cb; + struct Qdisc *q; + u32 parent; }; static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) @@ -758,13 +767,14 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) struct tcf_dump_args *a = (void *)arg; struct net *net = sock_net(a->skb->sk); - return tcf_fill_node(net, a->skb, tp, n, NETLINK_CB(a->cb->skb).portid, + return tcf_fill_node(net, a->skb, tp, a->q, a->parent, + n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER); } -static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, - struct netlink_callback *cb, +static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, + struct sk_buff *skb, struct netlink_callback *cb, long index_start, long *p_index) { struct net *net = sock_net(skb->sk); @@ -786,7 +796,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (cb->args[1] == 0) { - if (tcf_fill_node(net, skb, tp, 0, + if (tcf_fill_node(net, skb, tp, q, parent, 0, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) @@ -799,6 +809,8 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, arg.w.fn = tcf_node_dump; arg.skb = skb; arg.cb = cb; + arg.q = q; + arg.parent = parent; arg.w.stop = 0; arg.w.skip = cb->args[1] - 1; arg.w.count = 0; @@ -824,6 +836,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) const struct Qdisc_class_ops *cops; long index_start; long index; + u32 parent; int err; if (nlmsg_len(cb->nlh) < sizeof(*tcm)) @@ -837,10 +850,13 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (!dev) return skb->len; - if (!tcm->tcm_parent) + parent = tcm->tcm_parent; + if (!parent) { q = dev->qdisc; - else + parent = q->handle; + } else { q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); + } if (!q) goto out; cops = q->ops->cl_ops; @@ -864,7 +880,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (tca[TCA_CHAIN] && nla_get_u32(tca[TCA_CHAIN]) != chain->index) continue; - if (!tcf_chain_dump(chain, skb, cb, index_start, &index)) + if (!tcf_chain_dump(chain, q, parent, skb, cb, + index_start, &index)) break; } @@ -1004,29 +1021,42 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts) } EXPORT_SYMBOL(tcf_exts_dump_stats); -int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, - struct net_device **hw_dev) +static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts, + enum tc_setup_type type, + void *type_data, bool err_stop) { + int ok_count = 0; #ifdef CONFIG_NET_CLS_ACT const struct tc_action *a; + struct net_device *dev; LIST_HEAD(actions); + int ret; if (!tcf_exts_has_actions(exts)) - return -EINVAL; + return 0; tcf_exts_to_list(exts, &actions); list_for_each_entry(a, &actions, list) { - if (a->ops->get_dev) { - a->ops->get_dev(a, dev_net(dev), hw_dev); - break; - } + if (!a->ops->get_dev) + continue; + dev = a->ops->get_dev(a); + if (!dev || !tc_can_offload(dev)) + continue; + ret = tc_setup_cb_egdev_call(dev, type, type_data, err_stop); + if (ret < 0) + return ret; + ok_count += ret; } - if (*hw_dev) - return 0; #endif - return -EOPNOTSUPP; + return ok_count; +} + +int tc_setup_cb_call(struct tcf_exts *exts, enum tc_setup_type type, + void *type_data, bool err_stop) +{ + return tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop); } -EXPORT_SYMBOL(tcf_exts_get_dev); +EXPORT_SYMBOL(tc_setup_cb_call); static int __init tc_filter_init(void) { diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 2a3a60ec5b86..6b29cef90bec 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -345,9 +345,9 @@ static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; } -static void flow_perturbation(unsigned long arg) +static void flow_perturbation(struct timer_list *t) { - struct flow_filter *f = (struct flow_filter *)arg; + struct flow_filter *f = from_timer(f, t, perturb_timer); get_random_bytes(&f->hashrnd, 4); if (f->perturb_period) @@ -491,8 +491,11 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, perturb_period = nla_get_u32(tb[TCA_FLOW_PERTURB]) * HZ; } - if (TC_H_MAJ(baseclass) == 0) - baseclass = TC_H_MAKE(tp->q->handle, baseclass); + if (TC_H_MAJ(baseclass) == 0) { + struct Qdisc *q = tcf_block_q(tp->chain->block); + + baseclass = TC_H_MAKE(q->handle, baseclass); + } if (TC_H_MIN(baseclass) == 0) baseclass = TC_H_MAKE(baseclass, 1); @@ -502,8 +505,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, get_random_bytes(&fnew->hashrnd, 4); } - setup_deferrable_timer(&fnew->perturb_timer, flow_perturbation, - (unsigned long)fnew); + timer_setup(&fnew->perturb_timer, flow_perturbation, TIMER_DEFERRABLE); netif_keep_dst(qdisc_dev(tp->q)); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index db831ac708f6..5b7bb968d1d4 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -88,7 +88,6 @@ struct cls_fl_filter { u32 handle; u32 flags; struct rcu_head rcu; - struct net_device *hw_dev; }; static unsigned short int fl_mask_range(const struct fl_flow_mask *mask) @@ -201,16 +200,17 @@ static void fl_destroy_filter(struct rcu_head *head) static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f) { struct tc_cls_flower_offload cls_flower = {}; - struct net_device *dev = f->hw_dev; - - if (!tc_can_offload(dev)) - return; + struct net_device *dev = tp->q->dev_queue->dev; tc_cls_common_offload_init(&cls_flower.common, tp); cls_flower.command = TC_CLSFLOWER_DESTROY; cls_flower.cookie = (unsigned long) f; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, &cls_flower); + if (tc_can_offload(dev)) + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, + &cls_flower); + tc_setup_cb_call(&f->exts, TC_SETUP_CLSFLOWER, + &cls_flower, false); } static int fl_hw_replace_filter(struct tcf_proto *tp, @@ -220,20 +220,9 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, { struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_flower_offload cls_flower = {}; + bool skip_sw = tc_skip_sw(f->flags); int err; - if (!tc_can_offload(dev)) { - if (tcf_exts_get_dev(dev, &f->exts, &f->hw_dev) || - (f->hw_dev && !tc_can_offload(f->hw_dev))) { - f->hw_dev = dev; - return tc_skip_sw(f->flags) ? -EINVAL : 0; - } - dev = f->hw_dev; - cls_flower.egress_dev = true; - } else { - f->hw_dev = dev; - } - tc_cls_common_offload_init(&cls_flower.common, tp); cls_flower.command = TC_CLSFLOWER_REPLACE; cls_flower.cookie = (unsigned long) f; @@ -242,31 +231,47 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, cls_flower.key = &f->mkey; cls_flower.exts = &f->exts; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, - &cls_flower); - if (!err) - f->flags |= TCA_CLS_FLAGS_IN_HW; + if (tc_can_offload(dev)) { + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, + &cls_flower); + if (err) { + if (skip_sw) + return err; + } else { + f->flags |= TCA_CLS_FLAGS_IN_HW; + } + } - if (tc_skip_sw(f->flags)) + err = tc_setup_cb_call(&f->exts, TC_SETUP_CLSFLOWER, + &cls_flower, skip_sw); + if (err < 0) { + fl_hw_destroy_filter(tp, f); return err; + } else if (err > 0) { + f->flags |= TCA_CLS_FLAGS_IN_HW; + } + + if (skip_sw && !(f->flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; + return 0; } static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) { struct tc_cls_flower_offload cls_flower = {}; - struct net_device *dev = f->hw_dev; - - if (!tc_can_offload(dev)) - return; + struct net_device *dev = tp->q->dev_queue->dev; tc_cls_common_offload_init(&cls_flower.common, tp); cls_flower.command = TC_CLSFLOWER_STATS; cls_flower.cookie = (unsigned long) f; cls_flower.exts = &f->exts; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, - &cls_flower); + if (tc_can_offload(dev)) + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, + &cls_flower); + tc_setup_cb_call(&f->exts, TC_SETUP_CLSFLOWER, + &cls_flower, false); } static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f) diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 941245ad07fd..aa1e1f3bd20c 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -28,6 +28,7 @@ #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> +#include <net/sch_generic.h> #define HTSIZE 256 @@ -83,9 +84,11 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, } } } else { + struct Qdisc *q = tcf_block_q(tp->chain->block); + /* Old method: classify the packet using its skb mark. */ if (id && (TC_H_MAJ(id) == 0 || - !(TC_H_MAJ(id ^ tp->q->handle)))) { + !(TC_H_MAJ(id ^ q->handle)))) { res->classid = id; res->class = 0; return 0; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 14a7e08b2fa9..d732b5474a4d 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -13,6 +13,7 @@ #include <net/act_api.h> #include <net/netlink.h> #include <net/pkt_cls.h> +#include <net/sch_generic.h> /* * Passing parameters to the root seems to be done more awkwardly than really @@ -90,9 +91,11 @@ static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, f = tcindex_lookup(p, key); if (!f) { + struct Qdisc *q = tcf_block_q(tp->chain->block); + if (!p->fall_through) return -1; - res->classid = TC_H_MAKE(TC_H_MAJ(tp->q->handle), key); + res->classid = TC_H_MAKE(TC_H_MAJ(q->handle), key); res->class = 0; pr_debug("alg 0x%x\n", res->classid); return 0; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 094d224411a9..49d96b45a8ce 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -93,7 +93,7 @@ struct tc_u_hnode { struct tc_u_common { struct tc_u_hnode __rcu *hlist; - struct Qdisc *q; + struct tcf_block *block; int refcnt; struct idr handle_idr; struct hlist_node hnode; @@ -335,11 +335,7 @@ static struct hlist_head *tc_u_common_hash; static unsigned int tc_u_hash(const struct tcf_proto *tp) { - struct net_device *dev = tp->q->dev_queue->dev; - u32 qhandle = tp->q->handle; - int ifindex = dev->ifindex; - - return hash_64((u64)ifindex << 32 | qhandle, U32_HASH_SHIFT); + return hash_ptr(tp->chain->block, U32_HASH_SHIFT); } static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp) @@ -349,7 +345,7 @@ static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp) h = tc_u_hash(tp); hlist_for_each_entry(tc, &tc_u_common_hash[h], hnode) { - if (tc->q == tp->q) + if (tc->block == tp->chain->block) return tc; } return NULL; @@ -378,7 +374,7 @@ static int u32_init(struct tcf_proto *tp) kfree(root_ht); return -ENOBUFS; } - tp_c->q = tp->q; + tp_c->block = tp->chain->block; INIT_HLIST_NODE(&tp_c->hnode); idr_init(&tp_c->handle_idr); diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 03b677bc0700..1331a4c2d8ff 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -178,7 +178,7 @@ static int tcf_em_validate(struct tcf_proto *tp, struct tcf_ematch_hdr *em_hdr = nla_data(nla); int data_len = nla_len(nla) - sizeof(*em_hdr); void *data = (void *) em_hdr + sizeof(*em_hdr); - struct net *net = dev_net(qdisc_dev(tp->q)); + struct net *net = tp->chain->block->net; if (!TCF_EM_REL_VALID(em_hdr->flags)) goto errout; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index aa82116ed10c..a9ac912f1d67 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1661,9 +1661,11 @@ static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg) struct tcf_bind_args *a = (void *)arg; if (tp->ops->bind_class) { - tcf_tree_lock(tp); + struct Qdisc *q = tcf_block_q(tp->chain->block); + + sch_tree_lock(q); tp->ops->bind_class(n, a->classid, a->cl); - tcf_tree_unlock(tp); + sch_tree_unlock(q); } return 0; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index c5fcdf1a58a0..2dbd249c0b2f 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -281,7 +281,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, goto err_out; } - error = tcf_block_get(&flow->block, &flow->filter_list); + error = tcf_block_get(&flow->block, &flow->filter_list, sch); if (error) { kfree(flow); goto err_out; @@ -546,7 +546,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) p->link.q = &noop_qdisc; pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - err = tcf_block_get(&p->link.block, &p->link.filter_list); + err = tcf_block_get(&p->link.block, &p->link.filter_list, sch); if (err) return err; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index dcef97fa8047..c3b92d62190e 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1566,7 +1566,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (cl == NULL) goto failure; - err = tcf_block_get(&cl->block, &cl->filter_list); + err = tcf_block_get(&cl->block, &cl->filter_list, sch); if (err) { kfree(cl); return err; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 2d0e8d4bdc29..753dc7a77b60 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -412,7 +412,7 @@ static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt) struct drr_sched *q = qdisc_priv(sch); int err; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; err = qdisc_class_hash_init(&q->clhash); diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 2836c80c7aa5..fb4fb71c68cf 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -344,7 +344,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) goto errout; - err = tcf_block_get(&p->block, &p->filter_list); + err = tcf_block_get(&p->block, &p->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index de3b57ceca7b..3c40edeff1e8 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -481,7 +481,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) return err; } - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index a0a198768aad..6ced7c89c141 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -288,9 +288,9 @@ unsigned long dev_trans_start(struct net_device *dev) } EXPORT_SYMBOL(dev_trans_start); -static void dev_watchdog(unsigned long arg) +static void dev_watchdog(struct timer_list *t) { - struct net_device *dev = (struct net_device *)arg; + struct net_device *dev = from_timer(dev, t, watchdog_timer); netif_tx_lock(dev); if (!qdisc_tx_is_noop(dev)) { @@ -954,7 +954,7 @@ void dev_init_scheduler(struct net_device *dev) if (dev_ingress_queue(dev)) dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); - setup_timer(&dev->watchdog_timer, dev_watchdog, (unsigned long)dev); + timer_setup(&dev->watchdog_timer, dev_watchdog, 0); } static void shutdown_scheduler_queue(struct net_device *dev, diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 3f88b75488b0..a692184bd333 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1033,7 +1033,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; - err = tcf_block_get(&cl->block, &cl->filter_list); + err = tcf_block_get(&cl->block, &cl->filter_list, sch); if (err) { kfree(cl); return err; @@ -1405,7 +1405,7 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) return err; q->eligible = RB_ROOT; - err = tcf_block_get(&q->root.block, &q->root.filter_list); + err = tcf_block_get(&q->root.block, &q->root.filter_list, sch); if (err) return err; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index c6d7ae81b41f..57be73c0e1d2 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1030,7 +1030,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; @@ -1393,7 +1393,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!cl) goto failure; - err = tcf_block_get(&cl->block, &cl->filter_list); + err = tcf_block_get(&cl->block, &cl->filter_list, sch); if (err) { kfree(cl); goto failure; diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 44de4ee51ce9..9ccc1b89b0d9 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -59,7 +59,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) struct net_device *dev = qdisc_dev(sch); int err; - err = tcf_block_get(&q->block, &dev->ingress_cl_list); + err = tcf_block_get(&q->block, &dev->ingress_cl_list, sch); if (err) return err; @@ -153,11 +153,11 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) struct net_device *dev = qdisc_dev(sch); int err; - err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list); + err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list, sch); if (err) return err; - err = tcf_block_get(&q->egress_block, &dev->egress_cl_list); + err = tcf_block_get(&q->egress_block, &dev->egress_cl_list, sch); if (err) return err; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 6bcdfe6e7b63..51c2b289c69b 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -18,10 +18,16 @@ #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/sch_generic.h> +#include <net/pkt_cls.h> struct mqprio_sched { struct Qdisc **qdiscs; + u16 mode; + u16 shaper; int hw_offload; + u32 flags; + u64 min_rate[TC_QOPT_MAX_QUEUE]; + u64 max_rate[TC_QOPT_MAX_QUEUE]; }; static void mqprio_destroy(struct Qdisc *sch) @@ -39,9 +45,17 @@ static void mqprio_destroy(struct Qdisc *sch) } if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) { - struct tc_mqprio_qopt mqprio = {}; + struct tc_mqprio_qopt_offload mqprio = { { 0 } }; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, &mqprio); + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + case TC_MQPRIO_MODE_CHANNEL: + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, + &mqprio); + break; + default: + return; + } } else { netdev_set_num_tc(dev, 0); } @@ -97,6 +111,26 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) return 0; } +static const struct nla_policy mqprio_policy[TCA_MQPRIO_MAX + 1] = { + [TCA_MQPRIO_MODE] = { .len = sizeof(u16) }, + [TCA_MQPRIO_SHAPER] = { .len = sizeof(u16) }, + [TCA_MQPRIO_MIN_RATE64] = { .type = NLA_NESTED }, + [TCA_MQPRIO_MAX_RATE64] = { .type = NLA_NESTED }, +}; + +static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, + const struct nla_policy *policy, int len) +{ + int nested_len = nla_len(nla) - NLA_ALIGN(len); + + if (nested_len >= nla_attr_size(0)) + return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len), + nested_len, policy, NULL); + + memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); + return 0; +} + static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) { struct net_device *dev = qdisc_dev(sch); @@ -105,6 +139,10 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) struct Qdisc *qdisc; int i, err = -EOPNOTSUPP; struct tc_mqprio_qopt *qopt = NULL; + struct nlattr *tb[TCA_MQPRIO_MAX + 1]; + struct nlattr *attr; + int rem; + int len; BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE); BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK); @@ -115,6 +153,10 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) if (!netif_is_multiqueue(dev)) return -EOPNOTSUPP; + /* make certain can allocate enough classids to handle queues */ + if (dev->num_tx_queues >= TC_H_MIN_PRIORITY) + return -ENOMEM; + if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; @@ -122,6 +164,59 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) if (mqprio_parse_opt(dev, qopt)) return -EINVAL; + len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt)); + if (len > 0) { + err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy, + sizeof(*qopt)); + if (err < 0) + return err; + + if (!qopt->hw) + return -EINVAL; + + if (tb[TCA_MQPRIO_MODE]) { + priv->flags |= TC_MQPRIO_F_MODE; + priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]); + } + + if (tb[TCA_MQPRIO_SHAPER]) { + priv->flags |= TC_MQPRIO_F_SHAPER; + priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]); + } + + if (tb[TCA_MQPRIO_MIN_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->min_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MIN_RATE; + } + + if (tb[TCA_MQPRIO_MAX_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->max_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MAX_RATE; + } + } + /* pre-allocate qdisc, attachment can't fail */ priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), GFP_KERNEL); @@ -146,14 +241,36 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) * supplied and verified mapping */ if (qopt->hw) { - struct tc_mqprio_qopt mqprio = *qopt; + struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt}; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + if (priv->shaper != TC_MQPRIO_SHAPER_DCB) + return -EINVAL; + break; + case TC_MQPRIO_MODE_CHANNEL: + mqprio.flags = priv->flags; + if (priv->flags & TC_MQPRIO_F_MODE) + mqprio.mode = priv->mode; + if (priv->flags & TC_MQPRIO_F_SHAPER) + mqprio.shaper = priv->shaper; + if (priv->flags & TC_MQPRIO_F_MIN_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.min_rate[i] = priv->min_rate[i]; + if (priv->flags & TC_MQPRIO_F_MAX_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.max_rate[i] = priv->max_rate[i]; + break; + default: + return -EINVAL; + } + err = dev->netdev_ops->ndo_setup_tc(dev, + TC_SETUP_MQPRIO, &mqprio); if (err) return err; - priv->hw_offload = mqprio.hw; + priv->hw_offload = mqprio.qopt.hw; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) @@ -193,7 +310,7 @@ static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch, unsigned long cl) { struct net_device *dev = qdisc_dev(sch); - unsigned long ntx = cl - 1 - netdev_get_num_tc(dev); + unsigned long ntx = cl - 1; if (ntx >= dev->num_tx_queues) return NULL; @@ -223,11 +340,51 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, return 0; } +static int dump_rates(struct mqprio_sched *priv, + struct tc_mqprio_qopt *opt, struct sk_buff *skb) +{ + struct nlattr *nest; + int i; + + if (priv->flags & TC_MQPRIO_F_MIN_RATE) { + nest = nla_nest_start(skb, TCA_MQPRIO_MIN_RATE64); + if (!nest) + goto nla_put_failure; + + for (i = 0; i < opt->num_tc; i++) { + if (nla_put(skb, TCA_MQPRIO_MIN_RATE64, + sizeof(priv->min_rate[i]), + &priv->min_rate[i])) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } + + if (priv->flags & TC_MQPRIO_F_MAX_RATE) { + nest = nla_nest_start(skb, TCA_MQPRIO_MAX_RATE64); + if (!nest) + goto nla_put_failure; + + for (i = 0; i < opt->num_tc; i++) { + if (nla_put(skb, TCA_MQPRIO_MAX_RATE64, + sizeof(priv->max_rate[i]), + &priv->max_rate[i])) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) { struct net_device *dev = qdisc_dev(sch); struct mqprio_sched *priv = qdisc_priv(sch); - unsigned char *b = skb_tail_pointer(skb); + struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb); struct tc_mqprio_qopt opt = { 0 }; struct Qdisc *qdisc; unsigned int i; @@ -258,12 +415,25 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.offset[i] = dev->tc_to_txq[i].offset; } - if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) + if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt)) goto nla_put_failure; - return skb->len; + if ((priv->flags & TC_MQPRIO_F_MODE) && + nla_put_u16(skb, TCA_MQPRIO_MODE, priv->mode)) + goto nla_put_failure; + + if ((priv->flags & TC_MQPRIO_F_SHAPER) && + nla_put_u16(skb, TCA_MQPRIO_SHAPER, priv->shaper)) + goto nla_put_failure; + + if ((priv->flags & TC_MQPRIO_F_MIN_RATE || + priv->flags & TC_MQPRIO_F_MAX_RATE) && + (dump_rates(priv, &opt, skb) != 0)) + goto nla_put_failure; + + return nla_nest_end(skb, nla); nla_put_failure: - nlmsg_trim(skb, b); + nlmsg_trim(skb, nla); return -1; } @@ -282,38 +452,35 @@ static unsigned long mqprio_find(struct Qdisc *sch, u32 classid) struct net_device *dev = qdisc_dev(sch); unsigned int ntx = TC_H_MIN(classid); - if (ntx > dev->num_tx_queues + netdev_get_num_tc(dev)) - return 0; - return ntx; + /* There are essentially two regions here that have valid classid + * values. The first region will have a classid value of 1 through + * num_tx_queues. All of these are backed by actual Qdiscs. + */ + if (ntx < TC_H_MIN_PRIORITY) + return (ntx <= dev->num_tx_queues) ? ntx : 0; + + /* The second region represents the hardware traffic classes. These + * are represented by classid values of TC_H_MIN_PRIORITY through + * TC_H_MIN_PRIORITY + netdev_get_num_tc - 1 + */ + return ((ntx - TC_H_MIN_PRIORITY) < netdev_get_num_tc(dev)) ? ntx : 0; } static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { - struct net_device *dev = qdisc_dev(sch); + if (cl < TC_H_MIN_PRIORITY) { + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + struct net_device *dev = qdisc_dev(sch); + int tc = netdev_txq_to_tc(dev, cl - 1); - if (cl <= netdev_get_num_tc(dev)) { + tcm->tcm_parent = (tc < 0) ? 0 : + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(tc + TC_H_MIN_PRIORITY)); + tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + } else { tcm->tcm_parent = TC_H_ROOT; tcm->tcm_info = 0; - } else { - int i; - struct netdev_queue *dev_queue; - - dev_queue = mqprio_queue_get(sch, cl); - tcm->tcm_parent = 0; - for (i = 0; i < netdev_get_num_tc(dev); i++) { - struct netdev_tc_txq tc = dev->tc_to_txq[i]; - int q_idx = cl - netdev_get_num_tc(dev); - - if (q_idx > tc.offset && - q_idx <= tc.offset + tc.count) { - tcm->tcm_parent = - TC_H_MAKE(TC_H_MAJ(sch->handle), - TC_H_MIN(i + 1)); - break; - } - } - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; } tcm->tcm_handle |= TC_H_MIN(cl); return 0; @@ -324,15 +491,14 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, __releases(d->lock) __acquires(d->lock) { - struct net_device *dev = qdisc_dev(sch); - - if (cl <= netdev_get_num_tc(dev)) { + if (cl >= TC_H_MIN_PRIORITY) { int i; __u32 qlen = 0; struct Qdisc *qdisc; struct gnet_stats_queue qstats = {0}; struct gnet_stats_basic_packed bstats = {0}; - struct netdev_tc_txq tc = dev->tc_to_txq[cl - 1]; + struct net_device *dev = qdisc_dev(sch); + struct netdev_tc_txq tc = dev->tc_to_txq[cl & TC_BITMASK]; /* Drop lock here it will be reclaimed before touching * statistics this is required because the d->lock we @@ -385,12 +551,25 @@ static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) /* Walk hierarchy with a virtual class per tc */ arg->count = arg->skip; - for (ntx = arg->skip; - ntx < dev->num_tx_queues + netdev_get_num_tc(dev); - ntx++) { + for (ntx = arg->skip; ntx < netdev_get_num_tc(dev); ntx++) { + if (arg->fn(sch, ntx + TC_H_MIN_PRIORITY, arg) < 0) { + arg->stop = 1; + return; + } + arg->count++; + } + + /* Pad the values and skip over unused traffic classes */ + if (ntx < TC_MAX_QUEUE) { + arg->count = TC_MAX_QUEUE; + ntx = TC_MAX_QUEUE; + } + + /* Reset offset, sort out remaining per-queue qdiscs */ + for (ntx -= TC_MAX_QUEUE; ntx < dev->num_tx_queues; ntx++) { if (arg->fn(sch, ntx + 1, arg) < 0) { arg->stop = 1; - break; + return; } arg->count++; } diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index ff4fc3e0facd..31e0a284eeff 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -245,7 +245,7 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt) if (opt == NULL) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 5a4f10080290..db0228a65e8c 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -148,12 +148,6 @@ struct netem_skb_cb { psched_time_t time_to_send; }; - -static struct sk_buff *netem_rb_to_skb(struct rb_node *rb) -{ - return rb_entry(rb, struct sk_buff, rbnode); -} - static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) { /* we assume we can use skb next/prev/tstamp as storage for rb_node */ @@ -364,7 +358,7 @@ static void tfifo_reset(struct Qdisc *sch) struct rb_node *p = rb_first(&q->t_root); while (p) { - struct sk_buff *skb = netem_rb_to_skb(p); + struct sk_buff *skb = rb_to_skb(p); p = rb_next(p); rb_erase(&skb->rbnode, &q->t_root); @@ -382,7 +376,7 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) struct sk_buff *skb; parent = *p; - skb = netem_rb_to_skb(parent); + skb = rb_to_skb(parent); if (tnext >= netem_skb_cb(skb)->time_to_send) p = &parent->rb_right; else @@ -538,7 +532,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff *t_skb; struct netem_skb_cb *t_last; - t_skb = netem_rb_to_skb(rb_last(&q->t_root)); + t_skb = skb_rb_last(&q->t_root); t_last = netem_skb_cb(t_skb); if (!last || t_last->time_to_send > last->time_to_send) { @@ -617,7 +611,7 @@ deliver: if (p) { psched_time_t time_to_send; - skb = netem_rb_to_skb(p); + skb = rb_to_skb(p); /* if more time remaining? */ time_to_send = netem_skb_cb(skb)->time_to_send; diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 6c2791d6102d..776c694c77c7 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -74,6 +74,7 @@ struct pie_sched_data { struct pie_vars vars; struct pie_stats stats; struct timer_list adapt_timer; + struct Qdisc *sch; }; static void pie_params_init(struct pie_params *params) @@ -422,10 +423,10 @@ static void calculate_probability(struct Qdisc *sch) pie_vars_init(&q->vars); } -static void pie_timer(unsigned long arg) +static void pie_timer(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct pie_sched_data *q = qdisc_priv(sch); + struct pie_sched_data *q = from_timer(q, t, adapt_timer); + struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -446,7 +447,8 @@ static int pie_init(struct Qdisc *sch, struct nlattr *opt) pie_vars_init(&q->vars); sch->limit = q->params.limit; - setup_timer(&q->adapt_timer, pie_timer, (unsigned long)sch); + q->sch = sch; + timer_setup(&q->adapt_timer, pie_timer, 0); if (opt) { int err = pie_change(sch, opt); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 2dd6c68ae91e..95fad348c8d7 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -212,7 +212,7 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 6ddfd4991108..8694c7b6d2b1 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1419,7 +1419,7 @@ static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt) int i, j, err; u32 max_cl_shift, maxbudg_shift, max_classes; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 93b9d70a9b28..fdfdb56aaae2 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -40,6 +40,7 @@ struct red_sched_data { u32 limit; /* HARD maximal queue length */ unsigned char flags; struct timer_list adapt_timer; + struct Qdisc *sch; struct red_parms parms; struct red_vars vars; struct red_stats stats; @@ -221,10 +222,10 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) return 0; } -static inline void red_adaptative_timer(unsigned long arg) +static inline void red_adaptative_timer(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct red_sched_data *q = qdisc_priv(sch); + struct red_sched_data *q = from_timer(q, t, adapt_timer); + struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -238,7 +239,8 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt) struct red_sched_data *q = qdisc_priv(sch); q->qdisc = &noop_qdisc; - setup_timer(&q->adapt_timer, red_adaptative_timer, (unsigned long)sch); + q->sch = sch; + timer_setup(&q->adapt_timer, red_adaptative_timer, 0); return red_change(sch, opt); } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index cc39e170b4aa..487d375f5a06 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -553,7 +553,7 @@ static int sfb_init(struct Qdisc *sch, struct nlattr *opt) struct sfb_sched_data *q = qdisc_priv(sch); int err; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 74ea863b8240..5a9c95149c5c 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -145,6 +145,7 @@ struct sfq_sched_data { int perturb_period; unsigned int quantum; /* Allotment per round: MUST BE >= MTU */ struct timer_list perturb_timer; + struct Qdisc *sch; }; /* @@ -604,10 +605,10 @@ drop: qdisc_tree_reduce_backlog(sch, dropped, drop_len); } -static void sfq_perturbation(unsigned long arg) +static void sfq_perturbation(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct sfq_sched_data *q = qdisc_priv(sch); + struct sfq_sched_data *q = from_timer(q, t, perturb_timer); + struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -722,10 +723,9 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) int i; int err; - setup_deferrable_timer(&q->perturb_timer, sfq_perturbation, - (unsigned long)sch); + timer_setup(&q->perturb_timer, sfq_perturbation, TIMER_DEFERRABLE); - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index 03513a9fa110..0b83ec51e43b 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -124,7 +124,7 @@ static struct sctp_sched_ops sctp_sched_fcfs = { extern struct sctp_sched_ops sctp_sched_prio; extern struct sctp_sched_ops sctp_sched_rr; -struct sctp_sched_ops *sctp_sched_ops[] = { +static struct sctp_sched_ops *sctp_sched_ops[] = { &sctp_sched_fcfs, &sctp_sched_prio, &sctp_sched_rr, diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 20b66e79c5d6..5f6a20084157 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -380,10 +380,14 @@ static int smc_link_determine_gid(struct smc_link_group *lgr) if (ib_query_gid(lnk->smcibdev->ibdev, lnk->ibport, i, &gid, &gattr)) continue; - if (gattr.ndev && - (vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id)) { - lnk->gid = gid; - return 0; + if (gattr.ndev) { + if (is_vlan_dev(gattr.ndev) && + vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id) { + lnk->gid = gid; + dev_put(gattr.ndev); + return 0; + } + dev_put(gattr.ndev); } } return -ENODEV; diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 0b5852299158..468e1d725d97 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -369,26 +369,17 @@ void smc_ib_buf_unmap_sg(struct smc_ib_device *smcibdev, static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport) { - struct net_device *ndev; + struct ib_gid_attr gattr; int rc; rc = ib_query_gid(smcibdev->ibdev, ibport, 0, - &smcibdev->gid[ibport - 1], NULL); - /* the SMC protocol requires specification of the roce MAC address; - * if net_device cannot be determined, it can be derived from gid 0 - */ - ndev = smcibdev->ibdev->get_netdev(smcibdev->ibdev, ibport); - if (ndev) { - memcpy(&smcibdev->mac, ndev->dev_addr, ETH_ALEN); - dev_put(ndev); - } else if (!rc) { - memcpy(&smcibdev->mac[ibport - 1][0], - &smcibdev->gid[ibport - 1].raw[8], 3); - memcpy(&smcibdev->mac[ibport - 1][3], - &smcibdev->gid[ibport - 1].raw[13], 3); - smcibdev->mac[ibport - 1][0] &= ~0x02; - } - return rc; + &smcibdev->gid[ibport - 1], &gattr); + if (rc || !gattr.ndev) + return -ENODEV; + + memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN); + dev_put(gattr.ndev); + return 0; } /* Create an identifier unique for this instance of SMC-R. @@ -419,6 +410,7 @@ int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport) &smcibdev->pattr[ibport - 1]); if (rc) goto out; + /* the SMC protocol requires specification of the RoCE MAC address */ rc = smc_ib_fill_gid_and_mac(smcibdev, ibport); if (rc) goto out; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 0cc83839c13c..5dea47eb31bb 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -44,7 +44,7 @@ static mempool_t *rpc_buffer_mempool __read_mostly; static void rpc_async_schedule(struct work_struct *); static void rpc_release_task(struct rpc_task *task); -static void __rpc_queue_timer_fn(unsigned long ptr); +static void __rpc_queue_timer_fn(struct timer_list *t); /* * RPC tasks sit here while waiting for conditions to improve. @@ -228,7 +228,7 @@ static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const c queue->maxpriority = nr_queues - 1; rpc_reset_waitqueue_priority(queue); queue->qlen = 0; - setup_timer(&queue->timer_list.timer, __rpc_queue_timer_fn, (unsigned long)queue); + timer_setup(&queue->timer_list.timer, __rpc_queue_timer_fn, 0); INIT_LIST_HEAD(&queue->timer_list.list); rpc_assign_waitqueue_name(queue, qname); } @@ -635,9 +635,9 @@ void rpc_wake_up_status(struct rpc_wait_queue *queue, int status) } EXPORT_SYMBOL_GPL(rpc_wake_up_status); -static void __rpc_queue_timer_fn(unsigned long ptr) +static void __rpc_queue_timer_fn(struct timer_list *t) { - struct rpc_wait_queue *queue = (struct rpc_wait_queue *)ptr; + struct rpc_wait_queue *queue = from_timer(queue, t, timer_list.timer); struct rpc_task *task, *n; unsigned long expires, now, timeo; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index aa04666f929d..33f4ae68426d 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -455,7 +455,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, serv->sv_xdrsize = xdrsize; INIT_LIST_HEAD(&serv->sv_tempsocks); INIT_LIST_HEAD(&serv->sv_permsocks); - init_timer(&serv->sv_temptimer); + timer_setup(&serv->sv_temptimer, NULL, 0); spin_lock_init(&serv->sv_lock); __svc_init_bc(serv); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index d16a8b423c20..71de77bd4423 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -28,7 +28,7 @@ module_param(svc_rpc_per_connection_limit, uint, 0644); static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt); static int svc_deferred_recv(struct svc_rqst *rqstp); static struct cache_deferred_req *svc_defer(struct cache_req *req); -static void svc_age_temp_xprts(unsigned long closure); +static void svc_age_temp_xprts(struct timer_list *t); static void svc_delete_xprt(struct svc_xprt *xprt); /* apparently the "standard" is that clients close @@ -785,8 +785,7 @@ static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt serv->sv_tmpcnt++; if (serv->sv_temptimer.function == NULL) { /* setup timer to age temp transports */ - setup_timer(&serv->sv_temptimer, svc_age_temp_xprts, - (unsigned long)serv); + serv->sv_temptimer.function = (TIMER_FUNC_TYPE)svc_age_temp_xprts; mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ); } @@ -960,9 +959,9 @@ out: * Timer function to close old temporary transports, using * a mark-and-sweep algorithm. */ -static void svc_age_temp_xprts(unsigned long closure) +static void svc_age_temp_xprts(struct timer_list *t) { - struct svc_serv *serv = (struct svc_serv *)closure; + struct svc_serv *serv = from_timer(serv, t, sv_temptimer); struct svc_xprt *xprt; struct list_head *le, *next; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index e741ec2b4d8e..4b00302e1867 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -696,9 +696,9 @@ xprt_schedule_autodisconnect(struct rpc_xprt *xprt) } static void -xprt_init_autodisconnect(unsigned long data) +xprt_init_autodisconnect(struct timer_list *t) { - struct rpc_xprt *xprt = (struct rpc_xprt *)data; + struct rpc_xprt *xprt = from_timer(xprt, t, timer); spin_lock(&xprt->transport_lock); if (!list_empty(&xprt->recv)) @@ -1422,10 +1422,9 @@ found: xprt->idle_timeout = 0; INIT_WORK(&xprt->task_cleanup, xprt_autoclose); if (xprt_has_timer(xprt)) - setup_timer(&xprt->timer, xprt_init_autodisconnect, - (unsigned long)xprt); + timer_setup(&xprt->timer, xprt_init_autodisconnect, 0); else - init_timer(&xprt->timer); + timer_setup(&xprt->timer, NULL, 0); if (strlen(args->servername) > RPC_MAXNETNAMELEN) { xprt_destroy(xprt); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 9b5de31aa429..c1841f234a71 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2203,7 +2203,7 @@ static void xs_udp_setup_socket(struct work_struct *work) struct sock_xprt *transport = container_of(work, struct sock_xprt, connect_worker.work); struct rpc_xprt *xprt = &transport->xprt; - struct socket *sock = transport->sock; + struct socket *sock; int status = -EIO; sock = xs_create_sock(xprt, transport, diff --git a/net/tipc/Makefile b/net/tipc/Makefile index 31b9f9c52974..a3af73ec0b78 100644 --- a/net/tipc/Makefile +++ b/net/tipc/Makefile @@ -8,7 +8,7 @@ tipc-y += addr.o bcast.o bearer.o \ core.o link.o discover.o msg.o \ name_distr.o subscr.o monitor.o name_table.o net.o \ netlink.o netlink_compat.o node.o socket.o eth_media.o \ - server.o socket.o + server.o socket.o group.o tipc-$(CONFIG_TIPC_MEDIA_UDP) += udp_media.o tipc-$(CONFIG_TIPC_MEDIA_IB) += ib_media.o diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 7d99029df342..329325bd553e 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -233,7 +233,7 @@ static int tipc_bcast_xmit(struct net *net, struct sk_buff_head *pkts, struct sk_buff_head xmitq; int rc = 0; - __skb_queue_head_init(&xmitq); + skb_queue_head_init(&xmitq); tipc_bcast_lock(net); if (tipc_link_bc_peers(l)) rc = tipc_link_xmit(l, pkts, &xmitq); @@ -258,20 +258,20 @@ static int tipc_bcast_xmit(struct net *net, struct sk_buff_head *pkts, static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, struct tipc_nlist *dests, u16 *cong_link_cnt) { + struct tipc_dest *dst, *tmp; struct sk_buff_head _pkts; - struct u32_item *n, *tmp; - u32 dst, selector; + u32 dnode, selector; selector = msg_link_selector(buf_msg(skb_peek(pkts))); - __skb_queue_head_init(&_pkts); + skb_queue_head_init(&_pkts); - list_for_each_entry_safe(n, tmp, &dests->list, list) { - dst = n->value; - if (!tipc_msg_pskb_copy(dst, pkts, &_pkts)) + list_for_each_entry_safe(dst, tmp, &dests->list, list) { + dnode = dst->node; + if (!tipc_msg_pskb_copy(dnode, pkts, &_pkts)) return -ENOMEM; /* Any other return value than -ELINKCONG is ignored */ - if (tipc_node_xmit(net, &_pkts, dst, selector) == -ELINKCONG) + if (tipc_node_xmit(net, &_pkts, dnode, selector) == -ELINKCONG) (*cong_link_cnt)++; } return 0; @@ -554,7 +554,7 @@ void tipc_nlist_add(struct tipc_nlist *nl, u32 node) { if (node == nl->self) nl->local = true; - else if (u32_push(&nl->list, node)) + else if (tipc_dest_push(&nl->list, node, 0)) nl->remote++; } @@ -562,13 +562,13 @@ void tipc_nlist_del(struct tipc_nlist *nl, u32 node) { if (node == nl->self) nl->local = false; - else if (u32_del(&nl->list, node)) + else if (tipc_dest_del(&nl->list, node, 0)) nl->remote--; } void tipc_nlist_purge(struct tipc_nlist *nl) { - u32_list_purge(&nl->list); + tipc_dest_list_purge(&nl->list); nl->remote = 0; nl->local = 0; } diff --git a/net/tipc/core.h b/net/tipc/core.h index 5cc5398be722..964342689f2c 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -132,6 +132,11 @@ static inline struct list_head *tipc_nodes(struct net *net) return &tipc_net(net)->node_list; } +static inline struct tipc_server *tipc_topsrv(struct net *net) +{ + return tipc_net(net)->topsrv; +} + static inline unsigned int tipc_hashfn(u32 addr) { return addr & (NODE_HTABLE_SIZE - 1); diff --git a/net/tipc/group.c b/net/tipc/group.c new file mode 100644 index 000000000000..7821085a7dd8 --- /dev/null +++ b/net/tipc/group.c @@ -0,0 +1,871 @@ +/* + * net/tipc/group.c: TIPC group messaging code + * + * Copyright (c) 2017, Ericsson AB + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "addr.h" +#include "group.h" +#include "bcast.h" +#include "server.h" +#include "msg.h" +#include "socket.h" +#include "node.h" +#include "name_table.h" +#include "subscr.h" + +#define ADV_UNIT (((MAX_MSG_SIZE + MAX_H_SIZE) / FLOWCTL_BLK_SZ) + 1) +#define ADV_IDLE ADV_UNIT +#define ADV_ACTIVE (ADV_UNIT * 12) + +enum mbr_state { + MBR_QUARANTINED, + MBR_DISCOVERED, + MBR_JOINING, + MBR_PUBLISHED, + MBR_JOINED, + MBR_PENDING, + MBR_ACTIVE, + MBR_RECLAIMING, + MBR_REMITTED, + MBR_LEAVING +}; + +struct tipc_member { + struct rb_node tree_node; + struct list_head list; + struct list_head congested; + struct sk_buff *event_msg; + struct sk_buff_head deferredq; + struct tipc_group *group; + u32 node; + u32 port; + u32 instance; + enum mbr_state state; + u16 advertised; + u16 window; + u16 bc_rcv_nxt; + u16 bc_syncpt; + u16 bc_acked; + bool usr_pending; +}; + +struct tipc_group { + struct rb_root members; + struct list_head congested; + struct list_head pending; + struct list_head active; + struct list_head reclaiming; + struct tipc_nlist dests; + struct net *net; + int subid; + u32 type; + u32 instance; + u32 domain; + u32 scope; + u32 portid; + u16 member_cnt; + u16 active_cnt; + u16 max_active; + u16 bc_snd_nxt; + u16 bc_ackers; + bool loopback; + bool events; +}; + +static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, + int mtyp, struct sk_buff_head *xmitq); + +static void tipc_group_decr_active(struct tipc_group *grp, + struct tipc_member *m) +{ + if (m->state == MBR_ACTIVE || m->state == MBR_RECLAIMING) + grp->active_cnt--; +} + +static int tipc_group_rcvbuf_limit(struct tipc_group *grp) +{ + int max_active, active_pool, idle_pool; + int mcnt = grp->member_cnt + 1; + + /* Limit simultaneous reception from other members */ + max_active = min(mcnt / 8, 64); + max_active = max(max_active, 16); + grp->max_active = max_active; + + /* Reserve blocks for active and idle members */ + active_pool = max_active * ADV_ACTIVE; + idle_pool = (mcnt - max_active) * ADV_IDLE; + + /* Scale to bytes, considering worst-case truesize/msgsize ratio */ + return (active_pool + idle_pool) * FLOWCTL_BLK_SZ * 4; +} + +u16 tipc_group_bc_snd_nxt(struct tipc_group *grp) +{ + return grp->bc_snd_nxt; +} + +static bool tipc_group_is_enabled(struct tipc_member *m) +{ + return m->state != MBR_QUARANTINED && m->state != MBR_LEAVING; +} + +static bool tipc_group_is_receiver(struct tipc_member *m) +{ + return m && m->state >= MBR_JOINED; +} + +u32 tipc_group_exclude(struct tipc_group *grp) +{ + if (!grp->loopback) + return grp->portid; + return 0; +} + +int tipc_group_size(struct tipc_group *grp) +{ + return grp->member_cnt; +} + +struct tipc_group *tipc_group_create(struct net *net, u32 portid, + struct tipc_group_req *mreq) +{ + struct tipc_group *grp; + u32 type = mreq->type; + + grp = kzalloc(sizeof(*grp), GFP_ATOMIC); + if (!grp) + return NULL; + tipc_nlist_init(&grp->dests, tipc_own_addr(net)); + INIT_LIST_HEAD(&grp->congested); + INIT_LIST_HEAD(&grp->active); + INIT_LIST_HEAD(&grp->pending); + INIT_LIST_HEAD(&grp->reclaiming); + grp->members = RB_ROOT; + grp->net = net; + grp->portid = portid; + grp->domain = addr_domain(net, mreq->scope); + grp->type = type; + grp->instance = mreq->instance; + grp->scope = mreq->scope; + grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK; + grp->events = mreq->flags & TIPC_GROUP_MEMBER_EVTS; + if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, &grp->subid)) + return grp; + kfree(grp); + return NULL; +} + +void tipc_group_delete(struct net *net, struct tipc_group *grp) +{ + struct rb_root *tree = &grp->members; + struct tipc_member *m, *tmp; + struct sk_buff_head xmitq; + + __skb_queue_head_init(&xmitq); + + rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) { + tipc_group_proto_xmit(grp, m, GRP_LEAVE_MSG, &xmitq); + list_del(&m->list); + kfree(m); + } + tipc_node_distr_xmit(net, &xmitq); + tipc_nlist_purge(&grp->dests); + tipc_topsrv_kern_unsubscr(net, grp->subid); + kfree(grp); +} + +struct tipc_member *tipc_group_find_member(struct tipc_group *grp, + u32 node, u32 port) +{ + struct rb_node *n = grp->members.rb_node; + u64 nkey, key = (u64)node << 32 | port; + struct tipc_member *m; + + while (n) { + m = container_of(n, struct tipc_member, tree_node); + nkey = (u64)m->node << 32 | m->port; + if (key < nkey) + n = n->rb_left; + else if (key > nkey) + n = n->rb_right; + else + return m; + } + return NULL; +} + +static struct tipc_member *tipc_group_find_dest(struct tipc_group *grp, + u32 node, u32 port) +{ + struct tipc_member *m; + + m = tipc_group_find_member(grp, node, port); + if (m && tipc_group_is_enabled(m)) + return m; + return NULL; +} + +static struct tipc_member *tipc_group_find_node(struct tipc_group *grp, + u32 node) +{ + struct tipc_member *m; + struct rb_node *n; + + for (n = rb_first(&grp->members); n; n = rb_next(n)) { + m = container_of(n, struct tipc_member, tree_node); + if (m->node == node) + return m; + } + return NULL; +} + +static void tipc_group_add_to_tree(struct tipc_group *grp, + struct tipc_member *m) +{ + u64 nkey, key = (u64)m->node << 32 | m->port; + struct rb_node **n, *parent = NULL; + struct tipc_member *tmp; + + n = &grp->members.rb_node; + while (*n) { + tmp = container_of(*n, struct tipc_member, tree_node); + parent = *n; + tmp = container_of(parent, struct tipc_member, tree_node); + nkey = (u64)tmp->node << 32 | tmp->port; + if (key < nkey) + n = &(*n)->rb_left; + else if (key > nkey) + n = &(*n)->rb_right; + else + return; + } + rb_link_node(&m->tree_node, parent, n); + rb_insert_color(&m->tree_node, &grp->members); +} + +static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, + u32 node, u32 port, + int state) +{ + struct tipc_member *m; + + m = kzalloc(sizeof(*m), GFP_ATOMIC); + if (!m) + return NULL; + INIT_LIST_HEAD(&m->list); + INIT_LIST_HEAD(&m->congested); + __skb_queue_head_init(&m->deferredq); + m->group = grp; + m->node = node; + m->port = port; + m->bc_acked = grp->bc_snd_nxt - 1; + grp->member_cnt++; + tipc_group_add_to_tree(grp, m); + tipc_nlist_add(&grp->dests, m->node); + m->state = state; + return m; +} + +void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port) +{ + tipc_group_create_member(grp, node, port, MBR_DISCOVERED); +} + +static void tipc_group_delete_member(struct tipc_group *grp, + struct tipc_member *m) +{ + rb_erase(&m->tree_node, &grp->members); + grp->member_cnt--; + + /* Check if we were waiting for replicast ack from this member */ + if (grp->bc_ackers && less(m->bc_acked, grp->bc_snd_nxt - 1)) + grp->bc_ackers--; + + list_del_init(&m->list); + list_del_init(&m->congested); + tipc_group_decr_active(grp, m); + + /* If last member on a node, remove node from dest list */ + if (!tipc_group_find_node(grp, m->node)) + tipc_nlist_del(&grp->dests, m->node); + + kfree(m); +} + +struct tipc_nlist *tipc_group_dests(struct tipc_group *grp) +{ + return &grp->dests; +} + +void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq, + int *scope) +{ + seq->type = grp->type; + seq->lower = grp->instance; + seq->upper = grp->instance; + *scope = grp->scope; +} + +void tipc_group_update_member(struct tipc_member *m, int len) +{ + struct tipc_group *grp = m->group; + struct tipc_member *_m, *tmp; + + if (!tipc_group_is_enabled(m)) + return; + + m->window -= len; + + if (m->window >= ADV_IDLE) + return; + + if (!list_empty(&m->congested)) + return; + + /* Sort member into congested members' list */ + list_for_each_entry_safe(_m, tmp, &grp->congested, congested) { + if (m->window > _m->window) + continue; + list_add_tail(&m->congested, &_m->congested); + return; + } + list_add_tail(&m->congested, &grp->congested); +} + +void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack) +{ + u16 prev = grp->bc_snd_nxt - 1; + struct tipc_member *m; + struct rb_node *n; + + for (n = rb_first(&grp->members); n; n = rb_next(n)) { + m = container_of(n, struct tipc_member, tree_node); + if (tipc_group_is_enabled(m)) { + tipc_group_update_member(m, len); + m->bc_acked = prev; + } + } + + /* Mark number of acknowledges to expect, if any */ + if (ack) + grp->bc_ackers = grp->member_cnt; + grp->bc_snd_nxt++; +} + +bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport, + int len, struct tipc_member **mbr) +{ + struct sk_buff_head xmitq; + struct tipc_member *m; + int adv, state; + + m = tipc_group_find_dest(grp, dnode, dport); + *mbr = m; + if (!m) + return false; + if (m->usr_pending) + return true; + if (m->window >= len) + return false; + m->usr_pending = true; + + /* If not fully advertised, do it now to prevent mutual blocking */ + adv = m->advertised; + state = m->state; + if (state < MBR_JOINED) + return true; + if (state == MBR_JOINED && adv == ADV_IDLE) + return true; + if (state == MBR_ACTIVE && adv == ADV_ACTIVE) + return true; + if (state == MBR_PENDING && adv == ADV_IDLE) + return true; + skb_queue_head_init(&xmitq); + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, &xmitq); + tipc_node_distr_xmit(grp->net, &xmitq); + return true; +} + +bool tipc_group_bc_cong(struct tipc_group *grp, int len) +{ + struct tipc_member *m = NULL; + + /* If prev bcast was replicast, reject until all receivers have acked */ + if (grp->bc_ackers) + return true; + + if (list_empty(&grp->congested)) + return false; + + m = list_first_entry(&grp->congested, struct tipc_member, congested); + if (m->window >= len) + return false; + + return tipc_group_cong(grp, m->node, m->port, len, &m); +} + +/* tipc_group_sort_msg() - sort msg into queue by bcast sequence number + */ +static void tipc_group_sort_msg(struct sk_buff *skb, struct sk_buff_head *defq) +{ + struct tipc_msg *_hdr, *hdr = buf_msg(skb); + u16 bc_seqno = msg_grp_bc_seqno(hdr); + struct sk_buff *_skb, *tmp; + int mtyp = msg_type(hdr); + + /* Bcast/mcast may be bypassed by ucast or other bcast, - sort it in */ + if (mtyp == TIPC_GRP_BCAST_MSG || mtyp == TIPC_GRP_MCAST_MSG) { + skb_queue_walk_safe(defq, _skb, tmp) { + _hdr = buf_msg(_skb); + if (!less(bc_seqno, msg_grp_bc_seqno(_hdr))) + continue; + __skb_queue_before(defq, _skb, skb); + return; + } + /* Bcast was not bypassed, - add to tail */ + } + /* Unicasts are never bypassed, - always add to tail */ + __skb_queue_tail(defq, skb); +} + +/* tipc_group_filter_msg() - determine if we should accept arriving message + */ +void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, + struct sk_buff_head *xmitq) +{ + struct sk_buff *skb = __skb_dequeue(inputq); + bool ack, deliver, update, leave = false; + struct sk_buff_head *defq; + struct tipc_member *m; + struct tipc_msg *hdr; + u32 node, port; + int mtyp, blks; + + if (!skb) + return; + + hdr = buf_msg(skb); + node = msg_orignode(hdr); + port = msg_origport(hdr); + + if (!msg_in_group(hdr)) + goto drop; + + m = tipc_group_find_member(grp, node, port); + if (!tipc_group_is_receiver(m)) + goto drop; + + if (less(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt)) + goto drop; + + TIPC_SKB_CB(skb)->orig_member = m->instance; + defq = &m->deferredq; + tipc_group_sort_msg(skb, defq); + + while ((skb = skb_peek(defq))) { + hdr = buf_msg(skb); + mtyp = msg_type(hdr); + deliver = true; + ack = false; + update = false; + + if (more(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt)) + break; + + /* Decide what to do with message */ + switch (mtyp) { + case TIPC_GRP_MCAST_MSG: + if (msg_nameinst(hdr) != grp->instance) { + update = true; + deliver = false; + } + /* Fall thru */ + case TIPC_GRP_BCAST_MSG: + m->bc_rcv_nxt++; + ack = msg_grp_bc_ack_req(hdr); + break; + case TIPC_GRP_UCAST_MSG: + break; + case TIPC_GRP_MEMBER_EVT: + if (m->state == MBR_LEAVING) + leave = true; + if (!grp->events) + deliver = false; + break; + default: + break; + } + + /* Execute decisions */ + __skb_dequeue(defq); + if (deliver) + __skb_queue_tail(inputq, skb); + else + kfree_skb(skb); + + if (ack) + tipc_group_proto_xmit(grp, m, GRP_ACK_MSG, xmitq); + + if (leave) { + tipc_group_delete_member(grp, m); + __skb_queue_purge(defq); + break; + } + if (!update) + continue; + + blks = msg_blocks(hdr); + tipc_group_update_rcv_win(grp, blks, node, port, xmitq); + } + return; +drop: + kfree_skb(skb); +} + +void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, + u32 port, struct sk_buff_head *xmitq) +{ + struct list_head *active = &grp->active; + int max_active = grp->max_active; + int reclaim_limit = max_active * 3 / 4; + int active_cnt = grp->active_cnt; + struct tipc_member *m, *rm; + + m = tipc_group_find_member(grp, node, port); + if (!m) + return; + + m->advertised -= blks; + + switch (m->state) { + case MBR_JOINED: + /* Reclaim advertised space from least active member */ + if (!list_empty(active) && active_cnt >= reclaim_limit) { + rm = list_first_entry(active, struct tipc_member, list); + rm->state = MBR_RECLAIMING; + list_move_tail(&rm->list, &grp->reclaiming); + tipc_group_proto_xmit(grp, rm, GRP_RECLAIM_MSG, xmitq); + } + /* If max active, become pending and wait for reclaimed space */ + if (active_cnt >= max_active) { + m->state = MBR_PENDING; + list_add_tail(&m->list, &grp->pending); + break; + } + /* Otherwise become active */ + m->state = MBR_ACTIVE; + list_add_tail(&m->list, &grp->active); + grp->active_cnt++; + /* Fall through */ + case MBR_ACTIVE: + if (!list_is_last(&m->list, &grp->active)) + list_move_tail(&m->list, &grp->active); + if (m->advertised > (ADV_ACTIVE * 3 / 4)) + break; + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); + break; + case MBR_REMITTED: + if (m->advertised > ADV_IDLE) + break; + m->state = MBR_JOINED; + if (m->advertised < ADV_IDLE) { + pr_warn_ratelimited("Rcv unexpected msg after REMIT\n"); + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); + } + break; + case MBR_RECLAIMING: + case MBR_DISCOVERED: + case MBR_JOINING: + case MBR_LEAVING: + default: + break; + } +} + +static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, + int mtyp, struct sk_buff_head *xmitq) +{ + struct tipc_msg *hdr; + struct sk_buff *skb; + int adv = 0; + + skb = tipc_msg_create(GROUP_PROTOCOL, mtyp, INT_H_SIZE, 0, + m->node, tipc_own_addr(grp->net), + m->port, grp->portid, 0); + if (!skb) + return; + + if (m->state == MBR_ACTIVE) + adv = ADV_ACTIVE - m->advertised; + else if (m->state == MBR_JOINED || m->state == MBR_PENDING) + adv = ADV_IDLE - m->advertised; + + hdr = buf_msg(skb); + + if (mtyp == GRP_JOIN_MSG) { + msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt); + msg_set_adv_win(hdr, adv); + m->advertised += adv; + } else if (mtyp == GRP_LEAVE_MSG) { + msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt); + } else if (mtyp == GRP_ADV_MSG) { + msg_set_adv_win(hdr, adv); + m->advertised += adv; + } else if (mtyp == GRP_ACK_MSG) { + msg_set_grp_bc_acked(hdr, m->bc_rcv_nxt); + } else if (mtyp == GRP_REMIT_MSG) { + msg_set_grp_remitted(hdr, m->window); + } + __skb_queue_tail(xmitq, skb); +} + +void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, + struct tipc_msg *hdr, struct sk_buff_head *inputq, + struct sk_buff_head *xmitq) +{ + u32 node = msg_orignode(hdr); + u32 port = msg_origport(hdr); + struct tipc_member *m, *pm; + struct tipc_msg *ehdr; + u16 remitted, in_flight; + + if (!grp) + return; + + m = tipc_group_find_member(grp, node, port); + + switch (msg_type(hdr)) { + case GRP_JOIN_MSG: + if (!m) + m = tipc_group_create_member(grp, node, port, + MBR_QUARANTINED); + if (!m) + return; + m->bc_syncpt = msg_grp_bc_syncpt(hdr); + m->bc_rcv_nxt = m->bc_syncpt; + m->window += msg_adv_win(hdr); + + /* Wait until PUBLISH event is received */ + if (m->state == MBR_DISCOVERED) { + m->state = MBR_JOINING; + } else if (m->state == MBR_PUBLISHED) { + m->state = MBR_JOINED; + *usr_wakeup = true; + m->usr_pending = false; + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); + ehdr = buf_msg(m->event_msg); + msg_set_grp_bc_seqno(ehdr, m->bc_syncpt); + __skb_queue_tail(inputq, m->event_msg); + } + if (m->window < ADV_IDLE) + tipc_group_update_member(m, 0); + else + list_del_init(&m->congested); + return; + case GRP_LEAVE_MSG: + if (!m) + return; + m->bc_syncpt = msg_grp_bc_syncpt(hdr); + + /* Wait until WITHDRAW event is received */ + if (m->state != MBR_LEAVING) { + tipc_group_decr_active(grp, m); + m->state = MBR_LEAVING; + return; + } + /* Otherwise deliver already received WITHDRAW event */ + ehdr = buf_msg(m->event_msg); + msg_set_grp_bc_seqno(ehdr, m->bc_syncpt); + __skb_queue_tail(inputq, m->event_msg); + *usr_wakeup = true; + list_del_init(&m->congested); + return; + case GRP_ADV_MSG: + if (!m) + return; + m->window += msg_adv_win(hdr); + *usr_wakeup = m->usr_pending; + m->usr_pending = false; + list_del_init(&m->congested); + return; + case GRP_ACK_MSG: + if (!m) + return; + m->bc_acked = msg_grp_bc_acked(hdr); + if (--grp->bc_ackers) + break; + *usr_wakeup = true; + m->usr_pending = false; + return; + case GRP_RECLAIM_MSG: + if (!m) + return; + *usr_wakeup = m->usr_pending; + m->usr_pending = false; + tipc_group_proto_xmit(grp, m, GRP_REMIT_MSG, xmitq); + m->window = ADV_IDLE; + return; + case GRP_REMIT_MSG: + if (!m || m->state != MBR_RECLAIMING) + return; + + list_del_init(&m->list); + grp->active_cnt--; + remitted = msg_grp_remitted(hdr); + + /* Messages preceding the REMIT still in receive queue */ + if (m->advertised > remitted) { + m->state = MBR_REMITTED; + in_flight = m->advertised - remitted; + } + /* All messages preceding the REMIT have been read */ + if (m->advertised <= remitted) { + m->state = MBR_JOINED; + in_flight = 0; + } + /* ..and the REMIT overtaken by more messages => re-advertise */ + if (m->advertised < remitted) + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); + + m->advertised = ADV_IDLE + in_flight; + + /* Set oldest pending member to active and advertise */ + if (list_empty(&grp->pending)) + return; + pm = list_first_entry(&grp->pending, struct tipc_member, list); + pm->state = MBR_ACTIVE; + list_move_tail(&pm->list, &grp->active); + grp->active_cnt++; + if (pm->advertised <= (ADV_ACTIVE * 3 / 4)) + tipc_group_proto_xmit(grp, pm, GRP_ADV_MSG, xmitq); + return; + default: + pr_warn("Received unknown GROUP_PROTO message\n"); + } +} + +/* tipc_group_member_evt() - receive and handle a member up/down event + */ +void tipc_group_member_evt(struct tipc_group *grp, + bool *usr_wakeup, + int *sk_rcvbuf, + struct sk_buff *skb, + struct sk_buff_head *inputq, + struct sk_buff_head *xmitq) +{ + struct tipc_msg *hdr = buf_msg(skb); + struct tipc_event *evt = (void *)msg_data(hdr); + u32 instance = evt->found_lower; + u32 node = evt->port.node; + u32 port = evt->port.ref; + int event = evt->event; + struct tipc_member *m; + struct net *net; + bool node_up; + u32 self; + + if (!grp) + goto drop; + + net = grp->net; + self = tipc_own_addr(net); + if (!grp->loopback && node == self && port == grp->portid) + goto drop; + + /* Convert message before delivery to user */ + msg_set_hdr_sz(hdr, GROUP_H_SIZE); + msg_set_user(hdr, TIPC_CRITICAL_IMPORTANCE); + msg_set_type(hdr, TIPC_GRP_MEMBER_EVT); + msg_set_origport(hdr, port); + msg_set_orignode(hdr, node); + msg_set_nametype(hdr, grp->type); + msg_set_grp_evt(hdr, event); + + m = tipc_group_find_member(grp, node, port); + + if (event == TIPC_PUBLISHED) { + if (!m) + m = tipc_group_create_member(grp, node, port, + MBR_DISCOVERED); + if (!m) + goto drop; + + /* Hold back event if JOIN message not yet received */ + if (m->state == MBR_DISCOVERED) { + m->event_msg = skb; + m->state = MBR_PUBLISHED; + } else { + msg_set_grp_bc_seqno(hdr, m->bc_syncpt); + __skb_queue_tail(inputq, skb); + m->state = MBR_JOINED; + *usr_wakeup = true; + m->usr_pending = false; + } + m->instance = instance; + TIPC_SKB_CB(skb)->orig_member = m->instance; + tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq); + if (m->window < ADV_IDLE) + tipc_group_update_member(m, 0); + else + list_del_init(&m->congested); + } else if (event == TIPC_WITHDRAWN) { + if (!m) + goto drop; + + TIPC_SKB_CB(skb)->orig_member = m->instance; + + *usr_wakeup = true; + m->usr_pending = false; + node_up = tipc_node_is_up(net, node); + + /* Hold back event if more messages might be expected */ + if (m->state != MBR_LEAVING && node_up) { + m->event_msg = skb; + tipc_group_decr_active(grp, m); + m->state = MBR_LEAVING; + } else { + if (node_up) + msg_set_grp_bc_seqno(hdr, m->bc_syncpt); + else + msg_set_grp_bc_seqno(hdr, m->bc_rcv_nxt); + __skb_queue_tail(inputq, skb); + } + list_del_init(&m->congested); + } + *sk_rcvbuf = tipc_group_rcvbuf_limit(grp); + return; +drop: + kfree_skb(skb); +} diff --git a/net/tipc/group.h b/net/tipc/group.h new file mode 100644 index 000000000000..d525e1cd7de5 --- /dev/null +++ b/net/tipc/group.h @@ -0,0 +1,73 @@ +/* + * net/tipc/group.h: Include file for TIPC group unicast/multicast functions + * + * Copyright (c) 2017, Ericsson AB + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_GROUP_H +#define _TIPC_GROUP_H + +#include "core.h" + +struct tipc_group; +struct tipc_member; +struct tipc_msg; + +struct tipc_group *tipc_group_create(struct net *net, u32 portid, + struct tipc_group_req *mreq); +void tipc_group_delete(struct net *net, struct tipc_group *grp); +void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port); +struct tipc_nlist *tipc_group_dests(struct tipc_group *grp); +void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq, + int *scope); +u32 tipc_group_exclude(struct tipc_group *grp); +void tipc_group_filter_msg(struct tipc_group *grp, + struct sk_buff_head *inputq, + struct sk_buff_head *xmitq); +void tipc_group_member_evt(struct tipc_group *grp, bool *wakeup, + int *sk_rcvbuf, struct sk_buff *skb, + struct sk_buff_head *inputq, + struct sk_buff_head *xmitq); +void tipc_group_proto_rcv(struct tipc_group *grp, bool *wakeup, + struct tipc_msg *hdr, + struct sk_buff_head *inputq, + struct sk_buff_head *xmitq); +void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack); +bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport, + int len, struct tipc_member **m); +bool tipc_group_bc_cong(struct tipc_group *grp, int len); +void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, + u32 port, struct sk_buff_head *xmitq); +u16 tipc_group_bc_snd_nxt(struct tipc_group *grp); +void tipc_group_update_member(struct tipc_member *m, int len); +int tipc_group_size(struct tipc_group *grp); +#endif diff --git a/net/tipc/link.c b/net/tipc/link.c index ac0144f532aa..870b9b8f877a 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1039,6 +1039,7 @@ int tipc_link_retrans(struct tipc_link *l, struct tipc_link *nacker, static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *inputq) { + struct sk_buff_head *mc_inputq = l->bc_rcvlink->inputq; struct tipc_msg *hdr = buf_msg(skb); switch (msg_user(hdr)) { @@ -1046,13 +1047,16 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, case TIPC_MEDIUM_IMPORTANCE: case TIPC_HIGH_IMPORTANCE: case TIPC_CRITICAL_IMPORTANCE: - if (unlikely(msg_type(hdr) == TIPC_MCAST_MSG)) { - skb_queue_tail(l->bc_rcvlink->inputq, skb); + if (unlikely(msg_in_group(hdr) || msg_mcast(hdr))) { + skb_queue_tail(mc_inputq, skb); return true; } case CONN_MANAGER: skb_queue_tail(inputq, skb); return true; + case GROUP_PROTOCOL: + skb_queue_tail(mc_inputq, skb); + return true; case NAME_DISTRIBUTOR: l->bc_rcvlink->state = LINK_ESTABLISHED; skb_queue_tail(l->namedq, skb); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 121e59a1d0e7..1649d456e22d 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -568,6 +568,14 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) msg_set_destnode(msg, dnode); msg_set_destport(msg, dport); *err = TIPC_OK; + + if (!skb_cloned(skb)) + return true; + + /* Unclone buffer in case it was bundled */ + if (pskb_expand_head(skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC)) + return false; + return true; } @@ -658,3 +666,10 @@ void __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno, } kfree_skb(skb); } + +void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb, + struct sk_buff_head *xmitq) +{ + if (tipc_msg_reverse(tipc_own_addr(net), &skb, err)) + __skb_queue_tail(xmitq, skb); +} diff --git a/net/tipc/msg.h b/net/tipc/msg.h index c843fd2bc48d..cedf811317fb 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -1,7 +1,7 @@ /* * net/tipc/msg.h: Include file for TIPC message header routines * - * Copyright (c) 2000-2007, 2014-2015 Ericsson AB + * Copyright (c) 2000-2007, 2014-2017 Ericsson AB * Copyright (c) 2005-2008, 2010-2011, Wind River Systems * All rights reserved. * @@ -61,10 +61,14 @@ struct plist; /* * Payload message types */ -#define TIPC_CONN_MSG 0 -#define TIPC_MCAST_MSG 1 -#define TIPC_NAMED_MSG 2 -#define TIPC_DIRECT_MSG 3 +#define TIPC_CONN_MSG 0 +#define TIPC_MCAST_MSG 1 +#define TIPC_NAMED_MSG 2 +#define TIPC_DIRECT_MSG 3 +#define TIPC_GRP_MEMBER_EVT 4 +#define TIPC_GRP_BCAST_MSG 5 +#define TIPC_GRP_MCAST_MSG 6 +#define TIPC_GRP_UCAST_MSG 7 /* * Internal message users @@ -73,11 +77,13 @@ struct plist; #define MSG_BUNDLER 6 #define LINK_PROTOCOL 7 #define CONN_MANAGER 8 +#define GROUP_PROTOCOL 9 #define TUNNEL_PROTOCOL 10 #define NAME_DISTRIBUTOR 11 #define MSG_FRAGMENTER 12 #define LINK_CONFIG 13 #define SOCK_WAKEUP 14 /* pseudo user */ +#define TOP_SRV 15 /* pseudo user */ /* * Message header sizes @@ -86,6 +92,7 @@ struct plist; #define BASIC_H_SIZE 32 /* Basic payload message */ #define NAMED_H_SIZE 40 /* Named payload message */ #define MCAST_H_SIZE 44 /* Multicast payload message */ +#define GROUP_H_SIZE 44 /* Group payload message */ #define INT_H_SIZE 40 /* Internal messages */ #define MIN_H_SIZE 24 /* Smallest legal TIPC header size */ #define MAX_H_SIZE 60 /* Largest possible TIPC header size */ @@ -96,6 +103,7 @@ struct plist; struct tipc_skb_cb { u32 bytes_read; + u32 orig_member; struct sk_buff *tail; bool validated; u16 chain_imp; @@ -188,6 +196,11 @@ static inline u32 msg_size(struct tipc_msg *m) return msg_bits(m, 0, 0, 0x1ffff); } +static inline u32 msg_blocks(struct tipc_msg *m) +{ + return (msg_size(m) / 1024) + 1; +} + static inline u32 msg_data_sz(struct tipc_msg *m) { return msg_size(m) - msg_hdr_sz(m); @@ -251,6 +264,18 @@ static inline void msg_set_type(struct tipc_msg *m, u32 n) msg_set_bits(m, 1, 29, 0x7, n); } +static inline int msg_in_group(struct tipc_msg *m) +{ + int mtyp = msg_type(m); + + return mtyp >= TIPC_GRP_MEMBER_EVT && mtyp <= TIPC_GRP_UCAST_MSG; +} + +static inline bool msg_is_grp_evt(struct tipc_msg *m) +{ + return msg_type(m) == TIPC_GRP_MEMBER_EVT; +} + static inline u32 msg_named(struct tipc_msg *m) { return msg_type(m) == TIPC_NAMED_MSG; @@ -258,7 +283,10 @@ static inline u32 msg_named(struct tipc_msg *m) static inline u32 msg_mcast(struct tipc_msg *m) { - return msg_type(m) == TIPC_MCAST_MSG; + int mtyp = msg_type(m); + + return ((mtyp == TIPC_MCAST_MSG) || (mtyp == TIPC_GRP_BCAST_MSG) || + (mtyp == TIPC_GRP_MCAST_MSG)); } static inline u32 msg_connected(struct tipc_msg *m) @@ -514,6 +542,16 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n) #define DSC_RESP_MSG 1 /* + * Group protocol message types + */ +#define GRP_JOIN_MSG 0 +#define GRP_LEAVE_MSG 1 +#define GRP_ADV_MSG 2 +#define GRP_ACK_MSG 3 +#define GRP_RECLAIM_MSG 4 +#define GRP_REMIT_MSG 5 + +/* * Word 1 */ static inline u32 msg_seq_gap(struct tipc_msg *m) @@ -764,12 +802,12 @@ static inline void msg_set_conn_ack(struct tipc_msg *m, u32 n) msg_set_bits(m, 9, 16, 0xffff, n); } -static inline u32 msg_adv_win(struct tipc_msg *m) +static inline u16 msg_adv_win(struct tipc_msg *m) { return msg_bits(m, 9, 0, 0xffff); } -static inline void msg_set_adv_win(struct tipc_msg *m, u32 n) +static inline void msg_set_adv_win(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 0, 0xffff, n); } @@ -794,6 +832,68 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n) msg_set_bits(m, 9, 0, 0xffff, n); } +static inline u16 msg_grp_bc_syncpt(struct tipc_msg *m) +{ + return msg_bits(m, 9, 16, 0xffff); +} + +static inline void msg_set_grp_bc_syncpt(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 9, 16, 0xffff, n); +} + +static inline u16 msg_grp_bc_acked(struct tipc_msg *m) +{ + return msg_bits(m, 9, 16, 0xffff); +} + +static inline void msg_set_grp_bc_acked(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 9, 16, 0xffff, n); +} + +static inline u16 msg_grp_remitted(struct tipc_msg *m) +{ + return msg_bits(m, 9, 16, 0xffff); +} + +static inline void msg_set_grp_remitted(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 9, 16, 0xffff, n); +} + +/* Word 10 + */ +static inline u16 msg_grp_evt(struct tipc_msg *m) +{ + return msg_bits(m, 10, 0, 0x3); +} + +static inline void msg_set_grp_evt(struct tipc_msg *m, int n) +{ + msg_set_bits(m, 10, 0, 0x3, n); +} + +static inline u16 msg_grp_bc_ack_req(struct tipc_msg *m) +{ + return msg_bits(m, 10, 0, 0x1); +} + +static inline void msg_set_grp_bc_ack_req(struct tipc_msg *m, bool n) +{ + msg_set_bits(m, 10, 0, 0x1, n); +} + +static inline u16 msg_grp_bc_seqno(struct tipc_msg *m) +{ + return msg_bits(m, 10, 16, 0xffff); +} + +static inline void msg_set_grp_bc_seqno(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 10, 16, 0xffff, n); +} + static inline bool msg_peer_link_is_up(struct tipc_msg *m) { if (likely(msg_user(m) != LINK_PROTOCOL)) @@ -818,6 +918,8 @@ static inline bool msg_is_reset(struct tipc_msg *hdr) struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp); bool tipc_msg_validate(struct sk_buff *skb); bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err); +void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb, + struct sk_buff_head *xmitq); void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type, u32 hsize, u32 destnode); struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index bd0aac87b41a..2856e19e036e 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -43,6 +43,7 @@ #include "bcast.h" #include "addr.h" #include "node.h" +#include "group.h" #include <net/genetlink.h> #define TIPC_NAMETBL_SIZE 1024 /* must be a power of 2 */ @@ -596,18 +597,47 @@ not_found: return ref; } -/** - * tipc_nametbl_mc_translate - find multicast destinations - * - * Creates list of all local ports that overlap the given multicast address; - * also determines if any off-node ports overlap. - * - * Note: Publications with a scope narrower than 'limit' are ignored. - * (i.e. local node-scope publications mustn't receive messages arriving - * from another node, even if the multcast link brought it here) - * - * Returns non-zero if any off-node ports overlap - */ +bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 domain, + struct list_head *dsts, int *dstcnt, u32 exclude, + bool all) +{ + u32 self = tipc_own_addr(net); + struct publication *publ; + struct name_info *info; + struct name_seq *seq; + struct sub_seq *sseq; + + if (!tipc_in_scope(domain, self)) + return false; + + *dstcnt = 0; + rcu_read_lock(); + seq = nametbl_find_seq(net, type); + if (unlikely(!seq)) + goto exit; + spin_lock_bh(&seq->lock); + sseq = nameseq_find_subseq(seq, instance); + if (likely(sseq)) { + info = sseq->info; + list_for_each_entry(publ, &info->zone_list, zone_list) { + if (!tipc_in_scope(domain, publ->node)) + continue; + if (publ->ref == exclude && publ->node == self) + continue; + tipc_dest_push(dsts, publ->node, publ->ref); + (*dstcnt)++; + if (all) + continue; + list_move_tail(&publ->zone_list, &info->zone_list); + break; + } + } + spin_unlock_bh(&seq->lock); +exit: + rcu_read_unlock(); + return !list_empty(dsts); +} + int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, u32 limit, struct list_head *dports) { @@ -634,7 +664,7 @@ int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, info = sseq->info; list_for_each_entry(publ, &info->node_list, node_list) { if (publ->scope <= limit) - u32_push(dports, publ->ref); + tipc_dest_push(dports, 0, publ->ref); } if (info->cluster_list_size != info->node_list_size) @@ -679,6 +709,37 @@ exit: rcu_read_unlock(); } +/* tipc_nametbl_build_group - build list of communication group members + */ +void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp, + u32 type, u32 domain) +{ + struct sub_seq *sseq, *stop; + struct name_info *info; + struct publication *p; + struct name_seq *seq; + + rcu_read_lock(); + seq = nametbl_find_seq(net, type); + if (!seq) + goto exit; + + spin_lock_bh(&seq->lock); + sseq = seq->sseqs; + stop = seq->sseqs + seq->first_free; + for (; sseq != stop; sseq++) { + info = sseq->info; + list_for_each_entry(p, &info->zone_list, zone_list) { + if (!tipc_in_scope(domain, p->node)) + continue; + tipc_group_add_member(grp, p->node, p->ref); + } + } + spin_unlock_bh(&seq->lock); +exit: + rcu_read_unlock(); +} + /* * tipc_nametbl_publish - add name publication to network name tables */ @@ -1057,78 +1118,79 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -bool u32_find(struct list_head *l, u32 value) +struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port) { - struct u32_item *item; + u64 value = (u64)node << 32 | port; + struct tipc_dest *dst; - list_for_each_entry(item, l, list) { - if (item->value == value) - return true; + list_for_each_entry(dst, l, list) { + if (dst->value != value) + continue; + return dst; } - return false; + return NULL; } -bool u32_push(struct list_head *l, u32 value) +bool tipc_dest_push(struct list_head *l, u32 node, u32 port) { - struct u32_item *item; + u64 value = (u64)node << 32 | port; + struct tipc_dest *dst; - list_for_each_entry(item, l, list) { - if (item->value == value) - return false; - } - item = kmalloc(sizeof(*item), GFP_ATOMIC); - if (unlikely(!item)) + if (tipc_dest_find(l, node, port)) return false; - item->value = value; - list_add(&item->list, l); + dst = kmalloc(sizeof(*dst), GFP_ATOMIC); + if (unlikely(!dst)) + return false; + dst->value = value; + list_add(&dst->list, l); return true; } -u32 u32_pop(struct list_head *l) +bool tipc_dest_pop(struct list_head *l, u32 *node, u32 *port) { - struct u32_item *item; - u32 value = 0; + struct tipc_dest *dst; if (list_empty(l)) - return 0; - item = list_first_entry(l, typeof(*item), list); - value = item->value; - list_del(&item->list); - kfree(item); - return value; + return false; + dst = list_first_entry(l, typeof(*dst), list); + if (port) + *port = dst->port; + if (node) + *node = dst->node; + list_del(&dst->list); + kfree(dst); + return true; } -bool u32_del(struct list_head *l, u32 value) +bool tipc_dest_del(struct list_head *l, u32 node, u32 port) { - struct u32_item *item, *tmp; + struct tipc_dest *dst; - list_for_each_entry_safe(item, tmp, l, list) { - if (item->value != value) - continue; - list_del(&item->list); - kfree(item); - return true; - } - return false; + dst = tipc_dest_find(l, node, port); + if (!dst) + return false; + list_del(&dst->list); + kfree(dst); + return true; } -void u32_list_purge(struct list_head *l) +void tipc_dest_list_purge(struct list_head *l) { - struct u32_item *item, *tmp; + struct tipc_dest *dst, *tmp; - list_for_each_entry_safe(item, tmp, l, list) { - list_del(&item->list); - kfree(item); + list_for_each_entry_safe(dst, tmp, l, list) { + list_del(&dst->list); + kfree(dst); } } -int u32_list_len(struct list_head *l) +int tipc_dest_list_len(struct list_head *l) { - struct u32_item *item; + struct tipc_dest *dst; int i = 0; - list_for_each_entry(item, l, list) { + list_for_each_entry(dst, l, list) { i++; } return i; diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 6ebdeb1d84a5..71926e429446 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -40,6 +40,7 @@ struct tipc_subscription; struct tipc_plist; struct tipc_nlist; +struct tipc_group; /* * TIPC name types reserved for internal TIPC use (both current and planned) @@ -101,9 +102,14 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb); u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *node); int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, u32 limit, struct list_head *dports); +void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp, + u32 type, u32 domain); void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, u32 upper, u32 domain, struct tipc_nlist *nodes); +bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 domain, + struct list_head *dsts, int *dstcnt, u32 exclude, + bool all); struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower, u32 upper, u32 scope, u32 port_ref, u32 key); @@ -120,16 +126,22 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s); int tipc_nametbl_init(struct net *net); void tipc_nametbl_stop(struct net *net); -struct u32_item { +struct tipc_dest { struct list_head list; - u32 value; + union { + struct { + u32 port; + u32 node; + }; + u64 value; + }; }; -bool u32_push(struct list_head *l, u32 value); -u32 u32_pop(struct list_head *l); -bool u32_find(struct list_head *l, u32 value); -bool u32_del(struct list_head *l, u32 value); -void u32_list_purge(struct list_head *l); -int u32_list_len(struct list_head *l); +struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port); +bool tipc_dest_push(struct list_head *l, u32 node, u32 port); +bool tipc_dest_pop(struct list_head *l, u32 *node, u32 *port); +bool tipc_dest_del(struct list_head *l, u32 node, u32 port); +void tipc_dest_list_purge(struct list_head *l); +int tipc_dest_list_len(struct list_head *l); #endif diff --git a/net/tipc/node.c b/net/tipc/node.c index 198dbc7adbe1..89f8ac73bf65 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -157,7 +157,7 @@ static void tipc_node_timeout(unsigned long data); static void tipc_node_fsm_evt(struct tipc_node *n, int evt); static struct tipc_node *tipc_node_find(struct net *net, u32 addr); static void tipc_node_put(struct tipc_node *node); -static bool tipc_node_is_up(struct tipc_node *n); +static bool node_is_up(struct tipc_node *n); struct tipc_sock_conn { u32 port; @@ -657,7 +657,7 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id, *slot1 = i; } - if (!tipc_node_is_up(n)) { + if (!node_is_up(n)) { if (tipc_link_peer_is_down(l)) tipc_node_fsm_evt(n, PEER_LOST_CONTACT_EVT); tipc_node_fsm_evt(n, SELF_LOST_CONTACT_EVT); @@ -717,11 +717,27 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete) tipc_sk_rcv(n->net, &le->inputq); } -static bool tipc_node_is_up(struct tipc_node *n) +static bool node_is_up(struct tipc_node *n) { return n->active_links[0] != INVALID_BEARER_ID; } +bool tipc_node_is_up(struct net *net, u32 addr) +{ + struct tipc_node *n; + bool retval = false; + + if (in_own_node(net, addr)) + return true; + + n = tipc_node_find(net, addr); + if (!n) + return false; + retval = node_is_up(n); + tipc_node_put(n); + return retval; +} + void tipc_node_check_dest(struct net *net, u32 onode, struct tipc_bearer *b, u16 capabilities, u32 signature, @@ -1149,7 +1165,7 @@ static int __tipc_nl_add_node(struct tipc_nl_msg *msg, struct tipc_node *node) if (nla_put_u32(msg->skb, TIPC_NLA_NODE_ADDR, node->addr)) goto attr_msg_full; - if (tipc_node_is_up(node)) + if (node_is_up(node)) if (nla_put_flag(msg->skb, TIPC_NLA_NODE_UP)) goto attr_msg_full; @@ -1238,6 +1254,22 @@ int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode, return 0; } +/* tipc_node_distr_xmit(): send single buffer msgs to individual destinations + * Note: this is only for SYSTEM_IMPORTANCE messages, which cannot be rejected + */ +int tipc_node_distr_xmit(struct net *net, struct sk_buff_head *xmitq) +{ + struct sk_buff *skb; + u32 selector, dnode; + + while ((skb = __skb_dequeue(xmitq))) { + selector = msg_origport(buf_msg(skb)); + dnode = msg_destnode(buf_msg(skb)); + tipc_node_xmit_skb(net, skb, dnode, selector); + } + return 0; +} + void tipc_node_broadcast(struct net *net, struct sk_buff *skb) { struct sk_buff *txskb; @@ -1249,7 +1281,7 @@ void tipc_node_broadcast(struct net *net, struct sk_buff *skb) dst = n->addr; if (in_own_node(net, dst)) continue; - if (!tipc_node_is_up(n)) + if (!node_is_up(n)) continue; txskb = pskb_copy(skb, GFP_ATOMIC); if (!txskb) diff --git a/net/tipc/node.h b/net/tipc/node.h index 898c22916984..acd58d23a70e 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -48,7 +48,8 @@ enum { TIPC_BCAST_SYNCH = (1 << 1), TIPC_BCAST_STATE_NACK = (1 << 2), TIPC_BLOCK_FLOWCTL = (1 << 3), - TIPC_BCAST_RCAST = (1 << 4) + TIPC_BCAST_RCAST = (1 << 4), + TIPC_MCAST_GROUPS = (1 << 5) }; #define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | \ @@ -68,6 +69,7 @@ int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node, char *linkname, size_t len); int tipc_node_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, int selector); +int tipc_node_distr_xmit(struct net *net, struct sk_buff_head *list); int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest, u32 selector); void tipc_node_subscribe(struct net *net, struct list_head *subscr, u32 addr); @@ -76,6 +78,7 @@ void tipc_node_broadcast(struct net *net, struct sk_buff *skb); int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port); void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port); int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel); +bool tipc_node_is_up(struct net *net, u32 addr); u16 tipc_node_get_capabilities(struct net *net, u32 addr); int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_node_dump_link(struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/tipc/server.c b/net/tipc/server.c index 3cd6402e812c..acaef80fb88c 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -36,6 +36,8 @@ #include "server.h" #include "core.h" #include "socket.h" +#include "addr.h" +#include "msg.h" #include <net/sock.h> #include <linux/module.h> @@ -105,13 +107,11 @@ static void tipc_conn_kref_release(struct kref *kref) kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr)); sock_release(sock); con->sock = NULL; - - spin_lock_bh(&s->idr_lock); - idr_remove(&s->conn_idr, con->conid); - s->idr_in_use--; - spin_unlock_bh(&s->idr_lock); } - + spin_lock_bh(&s->idr_lock); + idr_remove(&s->conn_idr, con->conid); + s->idr_in_use--; + spin_unlock_bh(&s->idr_lock); tipc_clean_outqueues(con); kfree(con); } @@ -197,7 +197,8 @@ static void tipc_close_conn(struct tipc_conn *con) struct tipc_server *s = con->server; if (test_and_clear_bit(CF_CONNECTED, &con->flags)) { - tipc_unregister_callbacks(con); + if (con->sock) + tipc_unregister_callbacks(con); if (con->conid) s->tipc_conn_release(con->conid, con->usr_data); @@ -207,8 +208,8 @@ static void tipc_close_conn(struct tipc_conn *con) * are harmless for us here as we have already deleted this * connection from server connection list. */ - kernel_sock_shutdown(con->sock, SHUT_RDWR); - + if (con->sock) + kernel_sock_shutdown(con->sock, SHUT_RDWR); conn_put(con); } } @@ -487,38 +488,104 @@ void tipc_conn_terminate(struct tipc_server *s, int conid) } } +bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, + u32 lower, u32 upper, int *conid) +{ + struct tipc_subscriber *scbr; + struct tipc_subscr sub; + struct tipc_server *s; + struct tipc_conn *con; + + sub.seq.type = type; + sub.seq.lower = lower; + sub.seq.upper = upper; + sub.timeout = TIPC_WAIT_FOREVER; + sub.filter = TIPC_SUB_PORTS; + *(u32 *)&sub.usr_handle = port; + + con = tipc_alloc_conn(tipc_topsrv(net)); + if (IS_ERR(con)) + return false; + + *conid = con->conid; + s = con->server; + scbr = s->tipc_conn_new(*conid); + if (!scbr) { + tipc_close_conn(con); + return false; + } + + con->usr_data = scbr; + con->sock = NULL; + s->tipc_conn_recvmsg(net, *conid, NULL, scbr, &sub, sizeof(sub)); + return true; +} + +void tipc_topsrv_kern_unsubscr(struct net *net, int conid) +{ + struct tipc_conn *con; + + con = tipc_conn_lookup(tipc_topsrv(net), conid); + if (!con) + return; + tipc_close_conn(con); + conn_put(con); +} + +static void tipc_send_kern_top_evt(struct net *net, struct tipc_event *evt) +{ + u32 port = *(u32 *)&evt->s.usr_handle; + u32 self = tipc_own_addr(net); + struct sk_buff_head evtq; + struct sk_buff *skb; + + skb = tipc_msg_create(TOP_SRV, 0, INT_H_SIZE, sizeof(*evt), + self, self, port, port, 0); + if (!skb) + return; + msg_set_dest_droppable(buf_msg(skb), true); + memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt)); + skb_queue_head_init(&evtq); + __skb_queue_tail(&evtq, skb); + tipc_sk_rcv(net, &evtq); +} + static void tipc_send_to_sock(struct tipc_conn *con) { - int count = 0; struct tipc_server *s = con->server; struct outqueue_entry *e; + struct tipc_event *evt; struct msghdr msg; + int count = 0; int ret; spin_lock_bh(&con->outqueue_lock); while (test_bit(CF_CONNECTED, &con->flags)) { - e = list_entry(con->outqueue.next, struct outqueue_entry, - list); + e = list_entry(con->outqueue.next, struct outqueue_entry, list); if ((struct list_head *) e == &con->outqueue) break; - spin_unlock_bh(&con->outqueue_lock); - memset(&msg, 0, sizeof(msg)); - msg.msg_flags = MSG_DONTWAIT; + spin_unlock_bh(&con->outqueue_lock); - if (s->type == SOCK_DGRAM || s->type == SOCK_RDM) { - msg.msg_name = &e->dest; - msg.msg_namelen = sizeof(struct sockaddr_tipc); - } - ret = kernel_sendmsg(con->sock, &msg, &e->iov, 1, - e->iov.iov_len); - if (ret == -EWOULDBLOCK || ret == 0) { - cond_resched(); - goto out; - } else if (ret < 0) { - goto send_err; + if (con->sock) { + memset(&msg, 0, sizeof(msg)); + msg.msg_flags = MSG_DONTWAIT; + if (s->type == SOCK_DGRAM || s->type == SOCK_RDM) { + msg.msg_name = &e->dest; + msg.msg_namelen = sizeof(struct sockaddr_tipc); + } + ret = kernel_sendmsg(con->sock, &msg, &e->iov, 1, + e->iov.iov_len); + if (ret == -EWOULDBLOCK || ret == 0) { + cond_resched(); + goto out; + } else if (ret < 0) { + goto send_err; + } + } else { + evt = e->iov.iov_base; + tipc_send_kern_top_evt(s->net, evt); } - /* Don't starve users filling buffers */ if (++count >= MAX_SEND_MSG_COUNT) { cond_resched(); diff --git a/net/tipc/server.h b/net/tipc/server.h index 34f8055afa3b..2113c9192633 100644 --- a/net/tipc/server.h +++ b/net/tipc/server.h @@ -83,13 +83,16 @@ struct tipc_server { int tipc_conn_sendmsg(struct tipc_server *s, int conid, struct sockaddr_tipc *addr, void *data, size_t len); +bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, + u32 lower, u32 upper, int *conid); +void tipc_topsrv_kern_unsubscr(struct net *net, int conid); + /** * tipc_conn_terminate - terminate connection with server * * Note: Must call it in process context since it might sleep */ void tipc_conn_terminate(struct tipc_server *s, int conid); - int tipc_server_start(struct tipc_server *s); void tipc_server_stop(struct tipc_server *s); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index d50edd6e0019..2bbab4fe2f53 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1,7 +1,7 @@ /* * net/tipc/socket.c: TIPC socket API * - * Copyright (c) 2001-2007, 2012-2016, Ericsson AB + * Copyright (c) 2001-2007, 2012-2017, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems * All rights reserved. * @@ -45,6 +45,7 @@ #include "socket.h" #include "bcast.h" #include "netlink.h" +#include "group.h" #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ #define CONN_PROBING_INTERVAL msecs_to_jiffies(3600000) /* [ms] => 1 h */ @@ -61,6 +62,11 @@ enum { TIPC_CONNECTING = TCP_SYN_SENT, }; +struct sockaddr_pair { + struct sockaddr_tipc sock; + struct sockaddr_tipc member; +}; + /** * struct tipc_sock - TIPC socket structure * @sk: socket - interacts with 'port' and with user via the socket API @@ -78,7 +84,7 @@ enum { * @conn_timeout: the time we can wait for an unresponded setup request * @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue * @cong_link_cnt: number of congested links - * @sent_unacked: # messages sent by socket, and not yet acked by peer + * @snt_unacked: # messages sent by socket, and not yet acked by peer * @rcv_unacked: # messages read by user, but not yet acked back to peer * @peer: 'connected' peer for dgram/rdm * @node: hash table node @@ -109,9 +115,10 @@ struct tipc_sock { struct rhash_head node; struct tipc_mc_method mc_method; struct rcu_head rcu; + struct tipc_group *group; }; -static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb); +static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); static void tipc_data_ready(struct sock *sk); static void tipc_write_space(struct sock *sk); static void tipc_sock_destruct(struct sock *sk); @@ -123,6 +130,7 @@ static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); +static int tipc_sk_leave(struct tipc_sock *tsk); static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid); static int tipc_sk_insert(struct tipc_sock *tsk); static void tipc_sk_remove(struct tipc_sock *tsk); @@ -193,6 +201,11 @@ static bool tsk_conn_cong(struct tipc_sock *tsk) return tsk->snt_unacked > tsk->snd_win; } +static u16 tsk_blocks(int len) +{ + return ((len / FLOWCTL_BLK_SZ) + 1); +} + /* tsk_blocks(): translate a buffer size in bytes to number of * advertisable blocks, taking into account the ratio truesize(len)/len * We can trust that this ratio is always < 4 for len >= FLOWCTL_BLK_SZ @@ -453,7 +466,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, msg_set_origport(msg, tsk->portid); setup_timer(&sk->sk_timer, tipc_sk_timeout, (unsigned long)tsk); sk->sk_shutdown = 0; - sk->sk_backlog_rcv = tipc_backlog_rcv; + sk->sk_backlog_rcv = tipc_sk_backlog_rcv; sk->sk_rcvbuf = sysctl_tipc_rmem[1]; sk->sk_data_ready = tipc_data_ready; sk->sk_write_space = tipc_write_space; @@ -559,13 +572,14 @@ static int tipc_release(struct socket *sock) __tipc_shutdown(sock, TIPC_ERR_NO_PORT); sk->sk_shutdown = SHUTDOWN_MASK; + tipc_sk_leave(tsk); tipc_sk_withdraw(tsk, 0, NULL); sk_stop_timer(sk, &sk->sk_timer); tipc_sk_remove(tsk); /* Reject any messages that accumulated in backlog queue */ release_sock(sk); - u32_list_purge(&tsk->cong_links); + tipc_dest_list_purge(&tsk->cong_links); tsk->cong_link_cnt = 0; call_rcu(&tsk->rcu, tipc_sk_callback); sock->sk = NULL; @@ -601,7 +615,10 @@ static int tipc_bind(struct socket *sock, struct sockaddr *uaddr, res = tipc_sk_withdraw(tsk, 0, NULL); goto exit; } - + if (tsk->group) { + res = -EACCES; + goto exit; + } if (uaddr_len < sizeof(struct sockaddr_tipc)) { res = -EINVAL; goto exit; @@ -697,39 +714,43 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; + struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); struct tipc_sock *tsk = tipc_sk(sk); - u32 mask = 0; + struct tipc_group *grp = tsk->group; + u32 revents = 0; sock_poll_wait(file, sk_sleep(sk), wait); if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP | POLLIN | POLLRDNORM; + revents |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) - mask |= POLLHUP; + revents |= POLLHUP; switch (sk->sk_state) { case TIPC_ESTABLISHED: if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk)) - mask |= POLLOUT; + revents |= POLLOUT; /* fall thru' */ case TIPC_LISTEN: case TIPC_CONNECTING: - if (!skb_queue_empty(&sk->sk_receive_queue)) - mask |= (POLLIN | POLLRDNORM); + if (skb) + revents |= POLLIN | POLLRDNORM; break; case TIPC_OPEN: - if (!tsk->cong_link_cnt) - mask |= POLLOUT; - if (tipc_sk_type_connectionless(sk) && - (!skb_queue_empty(&sk->sk_receive_queue))) - mask |= (POLLIN | POLLRDNORM); + if (!grp || tipc_group_size(grp)) + if (!tsk->cong_link_cnt) + revents |= POLLOUT; + if (!tipc_sk_type_connectionless(sk)) + break; + if (!skb) + break; + revents |= POLLIN | POLLRDNORM; break; case TIPC_DISCONNECTING: - mask = (POLLIN | POLLRDNORM | POLLHUP); + revents = POLLIN | POLLRDNORM | POLLHUP; break; } - - return mask; + return revents; } /** @@ -757,6 +778,9 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, struct tipc_nlist dsts; int rc; + if (tsk->group) + return -EACCES; + /* Block or return if any destination link is congested */ rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt); if (unlikely(rc)) @@ -794,6 +818,296 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, } /** + * tipc_send_group_msg - send a message to a member in the group + * @net: network namespace + * @m: message to send + * @mb: group member + * @dnode: destination node + * @dport: destination port + * @dlen: total length of message data + */ +static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk, + struct msghdr *m, struct tipc_member *mb, + u32 dnode, u32 dport, int dlen) +{ + u16 bc_snd_nxt = tipc_group_bc_snd_nxt(tsk->group); + struct tipc_mc_method *method = &tsk->mc_method; + int blks = tsk_blocks(GROUP_H_SIZE + dlen); + struct tipc_msg *hdr = &tsk->phdr; + struct sk_buff_head pkts; + int mtu, rc; + + /* Complete message header */ + msg_set_type(hdr, TIPC_GRP_UCAST_MSG); + msg_set_hdr_sz(hdr, GROUP_H_SIZE); + msg_set_destport(hdr, dport); + msg_set_destnode(hdr, dnode); + msg_set_grp_bc_seqno(hdr, bc_snd_nxt); + + /* Build message as chain of buffers */ + skb_queue_head_init(&pkts); + mtu = tipc_node_get_mtu(net, dnode, tsk->portid); + rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); + if (unlikely(rc != dlen)) + return rc; + + /* Send message */ + rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid); + if (unlikely(rc == -ELINKCONG)) { + tipc_dest_push(&tsk->cong_links, dnode, 0); + tsk->cong_link_cnt++; + } + + /* Update send window */ + tipc_group_update_member(mb, blks); + + /* A broadcast sent within next EXPIRE period must follow same path */ + method->rcast = true; + method->mandatory = true; + return dlen; +} + +/** + * tipc_send_group_unicast - send message to a member in the group + * @sock: socket structure + * @m: message to send + * @dlen: total length of message data + * @timeout: timeout to wait for wakeup + * + * Called from function tipc_sendmsg(), which has done all sanity checks + * Returns the number of bytes sent on success, or errno + */ +static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m, + int dlen, long timeout) +{ + struct sock *sk = sock->sk; + DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); + int blks = tsk_blocks(GROUP_H_SIZE + dlen); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; + struct net *net = sock_net(sk); + struct tipc_member *mb = NULL; + u32 node, port; + int rc; + + node = dest->addr.id.node; + port = dest->addr.id.ref; + if (!port && !node) + return -EHOSTUNREACH; + + /* Block or return if destination link or member is congested */ + rc = tipc_wait_for_cond(sock, &timeout, + !tipc_dest_find(&tsk->cong_links, node, 0) && + !tipc_group_cong(grp, node, port, blks, &mb)); + if (unlikely(rc)) + return rc; + + if (unlikely(!mb)) + return -EHOSTUNREACH; + + rc = tipc_send_group_msg(net, tsk, m, mb, node, port, dlen); + + return rc ? rc : dlen; +} + +/** + * tipc_send_group_anycast - send message to any member with given identity + * @sock: socket structure + * @m: message to send + * @dlen: total length of message data + * @timeout: timeout to wait for wakeup + * + * Called from function tipc_sendmsg(), which has done all sanity checks + * Returns the number of bytes sent on success, or errno + */ +static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, + int dlen, long timeout) +{ + DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); + struct sock *sk = sock->sk; + struct tipc_sock *tsk = tipc_sk(sk); + struct list_head *cong_links = &tsk->cong_links; + int blks = tsk_blocks(GROUP_H_SIZE + dlen); + struct tipc_group *grp = tsk->group; + struct tipc_member *first = NULL; + struct tipc_member *mbr = NULL; + struct net *net = sock_net(sk); + u32 node, port, exclude; + u32 type, inst, domain; + struct list_head dsts; + int lookups = 0; + int dstcnt, rc; + bool cong; + + INIT_LIST_HEAD(&dsts); + + type = dest->addr.name.name.type; + inst = dest->addr.name.name.instance; + domain = addr_domain(net, dest->scope); + exclude = tipc_group_exclude(grp); + + while (++lookups < 4) { + first = NULL; + + /* Look for a non-congested destination member, if any */ + while (1) { + if (!tipc_nametbl_lookup(net, type, inst, domain, &dsts, + &dstcnt, exclude, false)) + return -EHOSTUNREACH; + tipc_dest_pop(&dsts, &node, &port); + cong = tipc_group_cong(grp, node, port, blks, &mbr); + if (!cong) + break; + if (mbr == first) + break; + if (!first) + first = mbr; + } + + /* Start over if destination was not in member list */ + if (unlikely(!mbr)) + continue; + + if (likely(!cong && !tipc_dest_find(cong_links, node, 0))) + break; + + /* Block or return if destination link or member is congested */ + rc = tipc_wait_for_cond(sock, &timeout, + !tipc_dest_find(cong_links, node, 0) && + !tipc_group_cong(grp, node, port, + blks, &mbr)); + if (unlikely(rc)) + return rc; + + /* Send, unless destination disappeared while waiting */ + if (likely(mbr)) + break; + } + + if (unlikely(lookups >= 4)) + return -EHOSTUNREACH; + + rc = tipc_send_group_msg(net, tsk, m, mbr, node, port, dlen); + + return rc ? rc : dlen; +} + +/** + * tipc_send_group_bcast - send message to all members in communication group + * @sk: socket structure + * @m: message to send + * @dlen: total length of message data + * @timeout: timeout to wait for wakeup + * + * Called from function tipc_sendmsg(), which has done all sanity checks + * Returns the number of bytes sent on success, or errno + */ +static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, + int dlen, long timeout) +{ + DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); + struct sock *sk = sock->sk; + struct net *net = sock_net(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; + struct tipc_nlist *dsts = tipc_group_dests(grp); + struct tipc_mc_method *method = &tsk->mc_method; + bool ack = method->mandatory && method->rcast; + int blks = tsk_blocks(MCAST_H_SIZE + dlen); + struct tipc_msg *hdr = &tsk->phdr; + int mtu = tipc_bcast_get_mtu(net); + struct sk_buff_head pkts; + int rc = -EHOSTUNREACH; + + if (!dsts->local && !dsts->remote) + return -EHOSTUNREACH; + + /* Block or return if any destination link or member is congested */ + rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt && + !tipc_group_bc_cong(grp, blks)); + if (unlikely(rc)) + return rc; + + /* Complete message header */ + if (dest) { + msg_set_type(hdr, TIPC_GRP_MCAST_MSG); + msg_set_nameinst(hdr, dest->addr.name.name.instance); + } else { + msg_set_type(hdr, TIPC_GRP_BCAST_MSG); + msg_set_nameinst(hdr, 0); + } + msg_set_hdr_sz(hdr, GROUP_H_SIZE); + msg_set_destport(hdr, 0); + msg_set_destnode(hdr, 0); + msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp)); + + /* Avoid getting stuck with repeated forced replicasts */ + msg_set_grp_bc_ack_req(hdr, ack); + + /* Build message as chain of buffers */ + skb_queue_head_init(&pkts); + rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); + if (unlikely(rc != dlen)) + return rc; + + /* Send message */ + rc = tipc_mcast_xmit(net, &pkts, method, dsts, &tsk->cong_link_cnt); + if (unlikely(rc)) + return rc; + + /* Update broadcast sequence number and send windows */ + tipc_group_update_bc_members(tsk->group, blks, ack); + + /* Broadcast link is now free to choose method for next broadcast */ + method->mandatory = false; + method->expires = jiffies; + + return dlen; +} + +/** + * tipc_send_group_mcast - send message to all members with given identity + * @sock: socket structure + * @m: message to send + * @dlen: total length of message data + * @timeout: timeout to wait for wakeup + * + * Called from function tipc_sendmsg(), which has done all sanity checks + * Returns the number of bytes sent on success, or errno + */ +static int tipc_send_group_mcast(struct socket *sock, struct msghdr *m, + int dlen, long timeout) +{ + struct sock *sk = sock->sk; + DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); + struct tipc_name_seq *seq = &dest->addr.nameseq; + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; + struct net *net = sock_net(sk); + u32 domain, exclude, dstcnt; + struct list_head dsts; + + INIT_LIST_HEAD(&dsts); + + if (seq->lower != seq->upper) + return -ENOTSUPP; + + domain = addr_domain(net, dest->scope); + exclude = tipc_group_exclude(grp); + if (!tipc_nametbl_lookup(net, seq->type, seq->lower, domain, + &dsts, &dstcnt, exclude, true)) + return -EHOSTUNREACH; + + if (dstcnt == 1) { + tipc_dest_pop(&dsts, &dest->addr.id.node, &dest->addr.id.ref); + return tipc_send_group_unicast(sock, m, dlen, timeout); + } + + tipc_dest_list_purge(&dsts); + return tipc_send_group_bcast(sock, m, dlen, timeout); +} + +/** * tipc_sk_mcast_rcv - Deliver multicast messages to all destination sockets * @arrvq: queue with arriving messages, to be cloned after destination lookup * @inputq: queue with cloned messages, delivered to socket after dest lookup @@ -803,13 +1117,15 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, struct sk_buff_head *inputq) { - struct tipc_msg *msg; - struct list_head dports; - u32 portid; u32 scope = TIPC_CLUSTER_SCOPE; - struct sk_buff_head tmpq; - uint hsz; + u32 self = tipc_own_addr(net); struct sk_buff *skb, *_skb; + u32 lower = 0, upper = ~0; + struct sk_buff_head tmpq; + u32 portid, oport, onode; + struct list_head dports; + struct tipc_msg *msg; + int user, mtyp, hsz; __skb_queue_head_init(&tmpq); INIT_LIST_HEAD(&dports); @@ -817,17 +1133,32 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, skb = tipc_skb_peek(arrvq, &inputq->lock); for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) { msg = buf_msg(skb); + user = msg_user(msg); + mtyp = msg_type(msg); + if (mtyp == TIPC_GRP_UCAST_MSG || user == GROUP_PROTOCOL) { + spin_lock_bh(&inputq->lock); + if (skb_peek(arrvq) == skb) { + __skb_dequeue(arrvq); + __skb_queue_tail(inputq, skb); + } + refcount_dec(&skb->users); + spin_unlock_bh(&inputq->lock); + continue; + } hsz = skb_headroom(skb) + msg_hdr_sz(msg); - - if (in_own_node(net, msg_orignode(msg))) + oport = msg_origport(msg); + onode = msg_orignode(msg); + if (onode == self) scope = TIPC_NODE_SCOPE; /* Create destination port list and message clones: */ - tipc_nametbl_mc_translate(net, - msg_nametype(msg), msg_namelower(msg), - msg_nameupper(msg), scope, &dports); - portid = u32_pop(&dports); - for (; portid; portid = u32_pop(&dports)) { + if (!msg_in_group(msg)) { + lower = msg_namelower(msg); + upper = msg_nameupper(msg); + } + tipc_nametbl_mc_translate(net, msg_nametype(msg), lower, upper, + scope, &dports); + while (tipc_dest_pop(&dports, NULL, &portid)) { _skb = __pskb_copy(skb, hsz, GFP_ATOMIC); if (_skb) { msg_set_destport(buf_msg(_skb), portid); @@ -850,16 +1181,16 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, } /** - * tipc_sk_proto_rcv - receive a connection mng protocol message + * tipc_sk_conn_proto_rcv - receive a connection mng protocol message * @tsk: receiving socket * @skb: pointer to message buffer. */ -static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, - struct sk_buff_head *xmitq) +static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { - struct sock *sk = &tsk->sk; - u32 onode = tsk_own_node(tsk); struct tipc_msg *hdr = buf_msg(skb); + u32 onode = tsk_own_node(tsk); + struct sock *sk = &tsk->sk; int mtyp = msg_type(hdr); bool conn_cong; @@ -931,6 +1262,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) long timeout = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); struct list_head *clinks = &tsk->cong_links; bool syn = !tipc_sk_type_connectionless(sk); + struct tipc_group *grp = tsk->group; struct tipc_msg *hdr = &tsk->phdr; struct tipc_name_seq *seq; struct sk_buff_head pkts; @@ -941,18 +1273,31 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE)) return -EMSGSIZE; + if (likely(dest)) { + if (unlikely(m->msg_namelen < sizeof(*dest))) + return -EINVAL; + if (unlikely(dest->family != AF_TIPC)) + return -EINVAL; + } + + if (grp) { + if (!dest) + return tipc_send_group_bcast(sock, m, dlen, timeout); + if (dest->addrtype == TIPC_ADDR_NAME) + return tipc_send_group_anycast(sock, m, dlen, timeout); + if (dest->addrtype == TIPC_ADDR_ID) + return tipc_send_group_unicast(sock, m, dlen, timeout); + if (dest->addrtype == TIPC_ADDR_MCAST) + return tipc_send_group_mcast(sock, m, dlen, timeout); + return -EINVAL; + } + if (unlikely(!dest)) { dest = &tsk->peer; if (!syn || dest->family != AF_TIPC) return -EDESTADDRREQ; } - if (unlikely(m->msg_namelen < sizeof(*dest))) - return -EINVAL; - - if (unlikely(dest->family != AF_TIPC)) - return -EINVAL; - if (unlikely(syn)) { if (sk->sk_state == TIPC_LISTEN) return -EPIPE; @@ -985,7 +1330,6 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) msg_set_destport(hdr, dport); if (unlikely(!dport && !dnode)) return -EHOSTUNREACH; - } else if (dest->addrtype == TIPC_ADDR_ID) { dnode = dest->addr.id.node; msg_set_type(hdr, TIPC_DIRECT_MSG); @@ -996,7 +1340,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) } /* Block or return if destination link is congested */ - rc = tipc_wait_for_cond(sock, &timeout, !u32_find(clinks, dnode)); + rc = tipc_wait_for_cond(sock, &timeout, + !tipc_dest_find(clinks, dnode, 0)); if (unlikely(rc)) return rc; @@ -1008,7 +1353,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid); if (unlikely(rc == -ELINKCONG)) { - u32_push(clinks, dnode); + tipc_dest_push(clinks, dnode, 0); tsk->cong_link_cnt++; rc = 0; } @@ -1142,26 +1487,38 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port, } /** - * set_orig_addr - capture sender's address for received message + * tipc_sk_set_orig_addr - capture sender's address for received message * @m: descriptor for message info - * @msg: received message header + * @hdr: received message header * * Note: Address is not captured if not requested by receiver. */ -static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg) +static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb) { - DECLARE_SOCKADDR(struct sockaddr_tipc *, addr, m->msg_name); + DECLARE_SOCKADDR(struct sockaddr_pair *, srcaddr, m->msg_name); + struct tipc_msg *hdr = buf_msg(skb); - if (addr) { - addr->family = AF_TIPC; - addr->addrtype = TIPC_ADDR_ID; - memset(&addr->addr, 0, sizeof(addr->addr)); - addr->addr.id.ref = msg_origport(msg); - addr->addr.id.node = msg_orignode(msg); - addr->addr.name.domain = 0; /* could leave uninitialized */ - addr->scope = 0; /* could leave uninitialized */ - m->msg_namelen = sizeof(struct sockaddr_tipc); - } + if (!srcaddr) + return; + + srcaddr->sock.family = AF_TIPC; + srcaddr->sock.addrtype = TIPC_ADDR_ID; + srcaddr->sock.addr.id.ref = msg_origport(hdr); + srcaddr->sock.addr.id.node = msg_orignode(hdr); + srcaddr->sock.addr.name.domain = 0; + srcaddr->sock.scope = 0; + m->msg_namelen = sizeof(struct sockaddr_tipc); + + if (!msg_in_group(hdr)) + return; + + /* Group message users may also want to know sending member's id */ + srcaddr->member.family = AF_TIPC; + srcaddr->member.addrtype = TIPC_ADDR_NAME; + srcaddr->member.addr.name.name.type = msg_nametype(hdr); + srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member; + srcaddr->member.addr.name.domain = 0; + m->msg_namelen = sizeof(*srcaddr); } /** @@ -1318,11 +1675,13 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buflen, int flags) { struct sock *sk = sock->sk; - struct tipc_sock *tsk = tipc_sk(sk); - struct sk_buff *skb; - struct tipc_msg *hdr; bool connected = !tipc_sk_type_connectionless(sk); + struct tipc_sock *tsk = tipc_sk(sk); int rc, err, hlen, dlen, copy; + struct sk_buff_head xmitq; + struct tipc_msg *hdr; + struct sk_buff *skb; + bool grp_evt; long timeout; /* Catch invalid receive requests */ @@ -1336,8 +1695,8 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, } timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + /* Step rcv queue to first msg with data or error; wait if necessary */ do { - /* Look at first msg in receive queue; wait if necessary */ rc = tipc_wait_for_rcvmsg(sock, &timeout); if (unlikely(rc)) goto exit; @@ -1346,13 +1705,14 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, dlen = msg_data_sz(hdr); hlen = msg_hdr_sz(hdr); err = msg_errcode(hdr); + grp_evt = msg_is_grp_evt(hdr); if (likely(dlen || err)) break; tsk_advance_rx_queue(sk); } while (1); /* Collect msg meta data, including error code and rejected data */ - set_orig_addr(m, hdr); + tipc_sk_set_orig_addr(m, skb); rc = tipc_sk_anc_data_recv(m, hdr, tsk); if (unlikely(rc)) goto exit; @@ -1372,15 +1732,33 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, if (unlikely(rc)) goto exit; + /* Mark message as group event if applicable */ + if (unlikely(grp_evt)) { + if (msg_grp_evt(hdr) == TIPC_WITHDRAWN) + m->msg_flags |= MSG_EOR; + m->msg_flags |= MSG_OOB; + copy = 0; + } + /* Caption of data or error code/rejected data was successful */ if (unlikely(flags & MSG_PEEK)) goto exit; + /* Send group flow control advertisement when applicable */ + if (tsk->group && msg_in_group(hdr) && !grp_evt) { + skb_queue_head_init(&xmitq); + tipc_group_update_rcv_win(tsk->group, tsk_blocks(hlen + dlen), + msg_orignode(hdr), msg_origport(hdr), + &xmitq); + tipc_node_distr_xmit(sock_net(sk), &xmitq); + } + tsk_advance_rx_queue(sk); + if (likely(!connected)) goto exit; - /* Send connection flow control ack when applicable */ + /* Send connection flow control advertisement when applicable */ tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen); if (tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE) tipc_sk_send_ack(tsk); @@ -1446,7 +1824,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, /* Collect msg meta data, incl. error code and rejected data */ if (!copied) { - set_orig_addr(m, hdr); + tipc_sk_set_orig_addr(m, skb); rc = tipc_sk_anc_data_recv(m, hdr, tsk); if (rc) break; @@ -1532,14 +1910,51 @@ static void tipc_sock_destruct(struct sock *sk) __skb_queue_purge(&sk->sk_receive_queue); } +static void tipc_sk_proto_rcv(struct sock *sk, + struct sk_buff_head *inputq, + struct sk_buff_head *xmitq) +{ + struct sk_buff *skb = __skb_dequeue(inputq); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_msg *hdr = buf_msg(skb); + struct tipc_group *grp = tsk->group; + bool wakeup = false; + + switch (msg_user(hdr)) { + case CONN_MANAGER: + tipc_sk_conn_proto_rcv(tsk, skb, xmitq); + return; + case SOCK_WAKEUP: + tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0); + tsk->cong_link_cnt--; + wakeup = true; + break; + case GROUP_PROTOCOL: + tipc_group_proto_rcv(grp, &wakeup, hdr, inputq, xmitq); + break; + case TOP_SRV: + tipc_group_member_evt(tsk->group, &wakeup, &sk->sk_rcvbuf, + skb, inputq, xmitq); + skb = NULL; + break; + default: + break; + } + + if (wakeup) + sk->sk_write_space(sk); + + kfree_skb(skb); +} + /** - * filter_connect - Handle all incoming messages for a connection-based socket + * tipc_filter_connect - Handle incoming message for a connection-based socket * @tsk: TIPC socket * @skb: pointer to message buffer. Set to NULL if buffer is consumed * * Returns true if everything ok, false otherwise */ -static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) +static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) { struct sock *sk = &tsk->sk; struct net *net = sock_net(sk); @@ -1643,6 +2058,9 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb) struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *hdr = buf_msg(skb); + if (unlikely(msg_in_group(hdr))) + return sk->sk_rcvbuf; + if (unlikely(!msg_connected(hdr))) return sk->sk_rcvbuf << msg_importance(hdr); @@ -1653,7 +2071,7 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb) } /** - * filter_rcv - validate incoming message + * tipc_sk_filter_rcv - validate incoming message * @sk: socket * @skb: pointer to message. * @@ -1662,99 +2080,71 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb) * * Called with socket lock already taken * - * Returns true if message was added to socket receive queue, otherwise false */ -static bool filter_rcv(struct sock *sk, struct sk_buff *skb, - struct sk_buff_head *xmitq) +static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { + bool sk_conn = !tipc_sk_type_connectionless(sk); struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; struct tipc_msg *hdr = buf_msg(skb); - unsigned int limit = rcvbuf_limit(sk, skb); - int err = TIPC_OK; - int usr = msg_user(hdr); - u32 onode; + struct net *net = sock_net(sk); + struct sk_buff_head inputq; + int limit, err = TIPC_OK; - if (unlikely(msg_user(hdr) == CONN_MANAGER)) { - tipc_sk_proto_rcv(tsk, skb, xmitq); - return false; - } + TIPC_SKB_CB(skb)->bytes_read = 0; + __skb_queue_head_init(&inputq); + __skb_queue_tail(&inputq, skb); - if (unlikely(usr == SOCK_WAKEUP)) { - onode = msg_orignode(hdr); - kfree_skb(skb); - u32_del(&tsk->cong_links, onode); - tsk->cong_link_cnt--; - sk->sk_write_space(sk); - return false; - } + if (unlikely(!msg_isdata(hdr))) + tipc_sk_proto_rcv(sk, &inputq, xmitq); - /* Drop if illegal message type */ - if (unlikely(msg_type(hdr) > TIPC_DIRECT_MSG)) { - kfree_skb(skb); - return false; - } + if (unlikely(grp)) + tipc_group_filter_msg(grp, &inputq, xmitq); - /* Reject if wrong message type for current socket state */ - if (tipc_sk_type_connectionless(sk)) { - if (msg_connected(hdr)) { + /* Validate and add to receive buffer if there is space */ + while ((skb = __skb_dequeue(&inputq))) { + hdr = buf_msg(skb); + limit = rcvbuf_limit(sk, skb); + if ((sk_conn && !tipc_sk_filter_connect(tsk, skb)) || + (!sk_conn && msg_connected(hdr)) || + (!grp && msg_in_group(hdr))) err = TIPC_ERR_NO_PORT; - goto reject; - } - } else if (unlikely(!filter_connect(tsk, skb))) { - err = TIPC_ERR_NO_PORT; - goto reject; - } + else if (sk_rmem_alloc_get(sk) + skb->truesize >= limit) + err = TIPC_ERR_OVERLOAD; - /* Reject message if there isn't room to queue it */ - if (unlikely(sk_rmem_alloc_get(sk) + skb->truesize >= limit)) { - err = TIPC_ERR_OVERLOAD; - goto reject; + if (unlikely(err)) { + tipc_skb_reject(net, err, skb, xmitq); + err = TIPC_OK; + continue; + } + __skb_queue_tail(&sk->sk_receive_queue, skb); + skb_set_owner_r(skb, sk); + sk->sk_data_ready(sk); } - - /* Enqueue message */ - TIPC_SKB_CB(skb)->bytes_read = 0; - __skb_queue_tail(&sk->sk_receive_queue, skb); - skb_set_owner_r(skb, sk); - - sk->sk_data_ready(sk); - return true; - -reject: - if (tipc_msg_reverse(tsk_own_node(tsk), &skb, err)) - __skb_queue_tail(xmitq, skb); - return false; } /** - * tipc_backlog_rcv - handle incoming message from backlog queue + * tipc_sk_backlog_rcv - handle incoming message from backlog queue * @sk: socket * @skb: message * * Caller must hold socket lock - * - * Returns 0 */ -static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) +static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { - unsigned int truesize = skb->truesize; + unsigned int before = sk_rmem_alloc_get(sk); struct sk_buff_head xmitq; - u32 dnode, selector; + unsigned int added; __skb_queue_head_init(&xmitq); - if (likely(filter_rcv(sk, skb, &xmitq))) { - atomic_add(truesize, &tipc_sk(sk)->dupl_rcvcnt); - return 0; - } - - if (skb_queue_empty(&xmitq)) - return 0; + tipc_sk_filter_rcv(sk, skb, &xmitq); + added = sk_rmem_alloc_get(sk) - before; + atomic_add(added, &tipc_sk(sk)->dupl_rcvcnt); - /* Send response/rejected message */ - skb = __skb_dequeue(&xmitq); - dnode = msg_destnode(buf_msg(skb)); - selector = msg_origport(buf_msg(skb)); - tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector); + /* Send pending response/rejected messages, if any */ + tipc_node_distr_xmit(sock_net(sk), &xmitq); return 0; } @@ -1786,7 +2176,7 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, /* Add message directly to receive queue if possible */ if (!sock_owned_by_user(sk)) { - filter_rcv(sk, skb, xmitq); + tipc_sk_filter_rcv(sk, skb, xmitq); continue; } @@ -1833,14 +2223,10 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) spin_unlock_bh(&sk->sk_lock.slock); } /* Send pending response/rejected messages, if any */ - while ((skb = __skb_dequeue(&xmitq))) { - dnode = msg_destnode(buf_msg(skb)); - tipc_node_xmit_skb(net, skb, dnode, dport); - } + tipc_node_distr_xmit(sock_net(sk), &xmitq); sock_put(sk); continue; } - /* No destination socket => dequeue skb if still there */ skb = tipc_skb_dequeue(inputq, dport); if (!skb) @@ -1903,28 +2289,32 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest, int previous; int res = 0; + if (destlen != sizeof(struct sockaddr_tipc)) + return -EINVAL; + lock_sock(sk); - /* DGRAM/RDM connect(), just save the destaddr */ - if (tipc_sk_type_connectionless(sk)) { - if (dst->family == AF_UNSPEC) { - memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc)); - } else if (destlen != sizeof(struct sockaddr_tipc)) { - res = -EINVAL; - } else { - memcpy(&tsk->peer, dest, destlen); - } + if (tsk->group) { + res = -EINVAL; goto exit; } - /* - * Reject connection attempt using multicast address - * - * Note: send_msg() validates the rest of the address fields, - * so there's no need to do it here - */ - if (dst->addrtype == TIPC_ADDR_MCAST) { + if (dst->family == AF_UNSPEC) { + memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc)); + if (!tipc_sk_type_connectionless(sk)) + res = -EINVAL; + goto exit; + } else if (dst->family != AF_TIPC) { res = -EINVAL; + } + if (dst->addrtype != TIPC_ADDR_ID && dst->addrtype != TIPC_ADDR_NAME) + res = -EINVAL; + if (res) + goto exit; + + /* DGRAM/RDM connect(), just save the destaddr */ + if (tipc_sk_type_connectionless(sk)) { + memcpy(&tsk->peer, dest, destlen); goto exit; } @@ -2345,6 +2735,56 @@ void tipc_sk_rht_destroy(struct net *net) rhashtable_destroy(&tn->sk_rht); } +static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq) +{ + struct net *net = sock_net(&tsk->sk); + u32 domain = addr_domain(net, mreq->scope); + struct tipc_group *grp = tsk->group; + struct tipc_msg *hdr = &tsk->phdr; + struct tipc_name_seq seq; + int rc; + + if (mreq->type < TIPC_RESERVED_TYPES) + return -EACCES; + if (grp) + return -EACCES; + grp = tipc_group_create(net, tsk->portid, mreq); + if (!grp) + return -ENOMEM; + tsk->group = grp; + msg_set_lookup_scope(hdr, mreq->scope); + msg_set_nametype(hdr, mreq->type); + msg_set_dest_droppable(hdr, true); + seq.type = mreq->type; + seq.lower = mreq->instance; + seq.upper = seq.lower; + tipc_nametbl_build_group(net, grp, mreq->type, domain); + rc = tipc_sk_publish(tsk, mreq->scope, &seq); + if (rc) + tipc_group_delete(net, grp); + + /* Eliminate any risk that a broadcast overtakes the sent JOIN */ + tsk->mc_method.rcast = true; + tsk->mc_method.mandatory = true; + return rc; +} + +static int tipc_sk_leave(struct tipc_sock *tsk) +{ + struct net *net = sock_net(&tsk->sk); + struct tipc_group *grp = tsk->group; + struct tipc_name_seq seq; + int scope; + + if (!grp) + return -EINVAL; + tipc_group_self(grp, &seq, &scope); + tipc_group_delete(net, grp); + tsk->group = NULL; + tipc_sk_withdraw(tsk, scope, &seq); + return 0; +} + /** * tipc_setsockopt - set socket option * @sock: socket structure @@ -2363,6 +2803,7 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group_req mreq; u32 value = 0; int res = 0; @@ -2378,9 +2819,14 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, case TIPC_CONN_TIMEOUT: if (ol < sizeof(value)) return -EINVAL; - res = get_user(value, (u32 __user *)ov); - if (res) - return res; + if (get_user(value, (u32 __user *)ov)) + return -EFAULT; + break; + case TIPC_GROUP_JOIN: + if (ol < sizeof(mreq)) + return -EINVAL; + if (copy_from_user(&mreq, ov, sizeof(mreq))) + return -EFAULT; break; default: if (ov || ol) @@ -2413,6 +2859,12 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, tsk->mc_method.rcast = true; tsk->mc_method.mandatory = true; break; + case TIPC_GROUP_JOIN: + res = tipc_sk_join(tsk, &mreq); + break; + case TIPC_GROUP_LEAVE: + res = tipc_sk_leave(tsk); + break; default: res = -EINVAL; } @@ -2440,7 +2892,8 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); - int len; + struct tipc_name_seq seq; + int len, scope; u32 value; int res; @@ -2474,6 +2927,12 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, case TIPC_SOCK_RECVQ_DEPTH: value = skb_queue_len(&sk->sk_receive_queue); break; + case TIPC_GROUP_JOIN: + seq.type = 0; + if (tsk->group) + tipc_group_self(tsk->group, &seq, &scope); + value = seq.type; + break; default: res = -EINVAL; } diff --git a/net/wireless/.gitignore b/net/wireless/.gitignore index c33451b896d9..61cbc304a3d3 100644 --- a/net/wireless/.gitignore +++ b/net/wireless/.gitignore @@ -1 +1,2 @@ -regdb.c +shipped-certs.c +extra-certs.c diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 6c606120abfe..da91bb547db3 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -19,6 +19,7 @@ config WEXT_PRIV config CFG80211 tristate "cfg80211 - wireless configuration API" depends on RFKILL || !RFKILL + select FW_LOADER ---help--- cfg80211 is the Linux wireless LAN (802.11) configuration API. Enable this if you have a wireless device. @@ -82,6 +83,36 @@ config CFG80211_CERTIFICATION_ONUS you are a wireless researcher and are working in a controlled and approved environment by your local regulatory agency. +config CFG80211_REQUIRE_SIGNED_REGDB + bool "require regdb signature" if CFG80211_CERTIFICATION_ONUS + default y + select SYSTEM_DATA_VERIFICATION + help + Require that in addition to the "regulatory.db" file a + "regulatory.db.p7s" can be loaded with a valid PKCS#7 + signature for the regulatory.db file made by one of the + keys in the certs/ directory. + +config CFG80211_USE_KERNEL_REGDB_KEYS + bool "allow regdb keys shipped with the kernel" if CFG80211_CERTIFICATION_ONUS + default y + depends on CFG80211_REQUIRE_SIGNED_REGDB + help + Allow the regulatory database to be signed by one of the keys for + which certificates are part of the kernel sources + (in net/wireless/certs/). + + This is currently only Seth Forshee's key, who is the regulatory + database maintainer. + +config CFG80211_EXTRA_REGDB_KEYDIR + string "additional regdb key directory" if CFG80211_CERTIFICATION_ONUS + depends on CFG80211_REQUIRE_SIGNED_REGDB + help + If selected, point to a directory with DER-encoded X.509 + certificates like in the kernel sources (net/wireless/certs/) + that shall be accepted for a signed regulatory database. + config CFG80211_REG_CELLULAR_HINTS bool "cfg80211 regulatory support for cellular base station hints" depends on CFG80211_CERTIFICATION_ONUS @@ -139,35 +170,14 @@ config CFG80211_DEBUGFS If unsure, say N. -config CFG80211_INTERNAL_REGDB - bool "use statically compiled regulatory rules database" if EXPERT - default n - depends on CFG80211 - ---help--- - This option generates an internal data structure representing - the wireless regulatory rules described in net/wireless/db.txt - and includes code to query that database. This is an alternative - to using CRDA for defining regulatory rules for the kernel. - - Using this option requires some parsing of the db.txt at build time, - the parser will be upkept with the latest wireless-regdb updates but - older wireless-regdb formats will be ignored. The parser may later - be replaced to avoid issues with conflicts on versions of - wireless-regdb. - - For details see: - - http://wireless.kernel.org/en/developers/Regulatory - - Most distributions have a CRDA package. So if unsure, say N. - config CFG80211_CRDA_SUPPORT - bool "support CRDA" if CFG80211_INTERNAL_REGDB + bool "support CRDA" if EXPERT default y depends on CFG80211 help You should enable this option unless you know for sure you have no - need for it, for example when using internal regdb (above.) + need for it, for example when using internal regdb (above) or the + database loaded as a firmware file. If unsure, say Y. diff --git a/net/wireless/Makefile b/net/wireless/Makefile index d06e5015751a..e585f3f71f77 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -14,11 +14,27 @@ cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o mesh.o ap.o trace.o ocb.o cfg80211-$(CONFIG_OF) += of.o cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o cfg80211-$(CONFIG_CFG80211_WEXT) += wext-compat.o wext-sme.o -cfg80211-$(CONFIG_CFG80211_INTERNAL_REGDB) += regdb.o CFLAGS_trace.o := -I$(src) -$(obj)/regdb.c: $(src)/db.txt $(src)/genregdb.awk - @$(AWK) -f $(srctree)/$(src)/genregdb.awk < $< > $@ +cfg80211-$(CONFIG_CFG80211_USE_KERNEL_REGDB_KEYS) += shipped-certs.o +ifneq ($(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR),) +cfg80211-y += extra-certs.o +endif -clean-files := regdb.c +$(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.x509) + @$(kecho) " GEN $@" + @echo '#include "reg.h"' > $@ + @echo 'const u8 shipped_regdb_certs[] = {' >> $@ + @for f in $^ ; do hexdump -v -e '1/1 "0x%.2x," "\n"' < $$f >> $@ ; done + @echo '};' >> $@ + @echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);' >> $@ + +$(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \ + $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%)/*.x509) + @$(kecho) " GEN $@" + @echo '#include "reg.h"' > $@ + @echo 'const u8 extra_regdb_certs[] = {' >> $@ + @for f in $^ ; do test -f $$f && hexdump -v -e '1/1 "0x%.2x," "\n"' < $$f >> $@ || true ; done + @echo '};' >> $@ + @echo 'unsigned int extra_regdb_certs_len = sizeof(extra_regdb_certs);' >> $@ diff --git a/net/wireless/certs/sforshee.x509 b/net/wireless/certs/sforshee.x509 Binary files differnew file mode 100644 index 000000000000..c6f8f9d6b988 --- /dev/null +++ b/net/wireless/certs/sforshee.x509 diff --git a/net/wireless/chan.c b/net/wireless/chan.c index b8aa5a7d5c77..eb824270f6e3 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -464,7 +464,7 @@ bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef, struct ieee80211_channel *chan) { int width; - u32 cf_offset, freq; + u32 freq; if (chandef->chan->center_freq == chan->center_freq) return true; @@ -473,8 +473,6 @@ bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef, if (width <= 20) return false; - cf_offset = width / 2 - 10; - for (freq = chandef->center_freq1 - width / 2 + 10; freq <= chandef->center_freq1 + width / 2 - 10; freq += 20) { if (chan->center_freq == freq) diff --git a/net/wireless/core.c b/net/wireless/core.c index 7b33e8c366bc..fdde0d98fde1 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1384,7 +1384,7 @@ out_fail_sysfs: out_fail_pernet: return err; } -subsys_initcall(cfg80211_init); +fs_initcall(cfg80211_init); static void __exit cfg80211_exit(void) { diff --git a/net/wireless/core.h b/net/wireless/core.h index 6e809325af3b..35165f42c2a8 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -216,6 +216,7 @@ enum cfg80211_event_type { EVENT_DISCONNECTED, EVENT_IBSS_JOINED, EVENT_STOPPED, + EVENT_PORT_AUTHORIZED, }; struct cfg80211_event { @@ -235,6 +236,9 @@ struct cfg80211_event { u8 bssid[ETH_ALEN]; struct ieee80211_channel *channel; } ij; + struct { + u8 bssid[ETH_ALEN]; + } pa; }; }; @@ -385,6 +389,7 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev, bool wextev); void __cfg80211_roamed(struct wireless_dev *wdev, struct cfg80211_roam_info *info); +void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid); int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); void cfg80211_autodisconnect_wk(struct work_struct *work); diff --git a/net/wireless/db.txt b/net/wireless/db.txt deleted file mode 100644 index a2fc3a09ccdc..000000000000 --- a/net/wireless/db.txt +++ /dev/null @@ -1,17 +0,0 @@ -# -# This file is a placeholder to prevent accidental build breakage if someone -# enables CONFIG_CFG80211_INTERNAL_REGDB. Almost no one actually needs to -# enable that build option. -# -# You should be using CRDA instead. It is even better if you use the CRDA -# package provided by your distribution, since they will probably keep it -# up-to-date on your behalf. -# -# If you _really_ intend to use CONFIG_CFG80211_INTERNAL_REGDB then you will -# need to replace this file with one containing appropriately formatted -# regulatory rules that cover the regulatory domains you will be using. Your -# best option is to extract the db.txt file from the wireless-regdb git -# repository: -# -# git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-regdb.git -# diff --git a/net/wireless/genregdb.awk b/net/wireless/genregdb.awk deleted file mode 100644 index baf2426b555a..000000000000 --- a/net/wireless/genregdb.awk +++ /dev/null @@ -1,158 +0,0 @@ -#!/usr/bin/awk -f -# -# genregdb.awk -- generate regdb.c from db.txt -# -# Actually, it reads from stdin (presumed to be db.txt) and writes -# to stdout (presumed to be regdb.c), but close enough... -# -# Copyright 2009 John W. Linville <linville@tuxdriver.com> -# -# Permission to use, copy, modify, and/or distribute this software for any -# purpose with or without fee is hereby granted, provided that the above -# copyright notice and this permission notice appear in all copies. -# -# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES -# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF -# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR -# ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES -# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN -# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF -# OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - -BEGIN { - active = 0 - rules = 0; - print "/*" - print " * DO NOT EDIT -- file generated from data in db.txt" - print " */" - print "" - print "#include <linux/nl80211.h>" - print "#include <net/cfg80211.h>" - print "#include \"regdb.h\"" - print "" - regdb = "const struct ieee80211_regdomain *reg_regdb[] = {\n" -} - -function parse_country_head() { - country=$2 - sub(/:/, "", country) - printf "static const struct ieee80211_regdomain regdom_%s = {\n", country - printf "\t.alpha2 = \"%s\",\n", country - if ($NF ~ /DFS-ETSI/) - printf "\t.dfs_region = NL80211_DFS_ETSI,\n" - else if ($NF ~ /DFS-FCC/) - printf "\t.dfs_region = NL80211_DFS_FCC,\n" - else if ($NF ~ /DFS-JP/) - printf "\t.dfs_region = NL80211_DFS_JP,\n" - printf "\t.reg_rules = {\n" - active = 1 - regdb = regdb "\t®dom_" country ",\n" -} - -function parse_reg_rule() -{ - flag_starts_at = 7 - - start = $1 - sub(/\(/, "", start) - end = $3 - bw = $5 - sub(/\),/, "", bw) - gain = 0 - power = $6 - # power might be in mW... - units = $7 - dfs_cac = 0 - - sub(/\(/, "", power) - sub(/\),/, "", power) - sub(/\),/, "", units) - sub(/\)/, "", units) - - if (units == "mW") { - flag_starts_at = 8 - power = 10 * log(power)/log(10) - if ($8 ~ /[[:digit:]]/) { - flag_starts_at = 9 - dfs_cac = $8 - } - } else { - if ($7 ~ /[[:digit:]]/) { - flag_starts_at = 8 - dfs_cac = $7 - } - } - sub(/\(/, "", dfs_cac) - sub(/\),/, "", dfs_cac) - flagstr = "" - for (i=flag_starts_at; i<=NF; i++) - flagstr = flagstr $i - split(flagstr, flagarray, ",") - flags = "" - for (arg in flagarray) { - if (flagarray[arg] == "NO-OFDM") { - flags = flags "\n\t\t\tNL80211_RRF_NO_OFDM | " - } else if (flagarray[arg] == "NO-CCK") { - flags = flags "\n\t\t\tNL80211_RRF_NO_CCK | " - } else if (flagarray[arg] == "NO-INDOOR") { - flags = flags "\n\t\t\tNL80211_RRF_NO_INDOOR | " - } else if (flagarray[arg] == "NO-OUTDOOR") { - flags = flags "\n\t\t\tNL80211_RRF_NO_OUTDOOR | " - } else if (flagarray[arg] == "DFS") { - flags = flags "\n\t\t\tNL80211_RRF_DFS | " - } else if (flagarray[arg] == "PTP-ONLY") { - flags = flags "\n\t\t\tNL80211_RRF_PTP_ONLY | " - } else if (flagarray[arg] == "PTMP-ONLY") { - flags = flags "\n\t\t\tNL80211_RRF_PTMP_ONLY | " - } else if (flagarray[arg] == "PASSIVE-SCAN") { - flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " - } else if (flagarray[arg] == "NO-IBSS") { - flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " - } else if (flagarray[arg] == "NO-IR") { - flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " - } else if (flagarray[arg] == "AUTO-BW") { - flags = flags "\n\t\t\tNL80211_RRF_AUTO_BW | " - } - - } - flags = flags "0" - printf "\t\tREG_RULE_EXT(%d, %d, %d, %d, %.0f, %d, %s),\n", start, end, bw, gain, power, dfs_cac, flags - rules++ -} - -function print_tail_country() -{ - active = 0 - printf "\t},\n" - printf "\t.n_reg_rules = %d\n", rules - printf "};\n\n" - rules = 0; -} - -/^[ \t]*#/ { - # Ignore -} - -!active && /^[ \t]*$/ { - # Ignore -} - -!active && /country/ { - parse_country_head() -} - -active && /^[ \t]*\(/ { - parse_reg_rule() -} - -active && /^[ \t]*$/ { - print_tail_country() -} - -END { - if (active) - print_tail_country() - print regdb "};" - print "" - print "int reg_regdb_size = ARRAY_SIZE(reg_regdb);" -} diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 690874293cfc..fce2cbe6a193 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -549,6 +549,14 @@ nl80211_nan_srf_policy[NL80211_NAN_SRF_ATTR_MAX + 1] = { [NL80211_NAN_SRF_MAC_ADDRS] = { .type = NLA_NESTED }, }; +/* policy for packet pattern attributes */ +static const struct nla_policy +nl80211_packet_pattern_policy[MAX_NL80211_PKTPAT + 1] = { + [NL80211_PKTPAT_MASK] = { .type = NLA_BINARY, }, + [NL80211_PKTPAT_PATTERN] = { .type = NLA_BINARY, }, + [NL80211_PKTPAT_OFFSET] = { .type = NLA_U32 }, +}; + static int nl80211_prepare_wdev_dump(struct sk_buff *skb, struct netlink_callback *cb, struct cfg80211_registered_device **rdev, @@ -2122,6 +2130,15 @@ static int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, case NL80211_CHAN_HT40MINUS: cfg80211_chandef_create(chandef, chandef->chan, chantype); + /* user input for center_freq is incorrect */ + if (info->attrs[NL80211_ATTR_CENTER_FREQ1] && + chandef->center_freq1 != nla_get_u32( + info->attrs[NL80211_ATTR_CENTER_FREQ1])) + return -EINVAL; + /* center_freq2 must be zero */ + if (info->attrs[NL80211_ATTR_CENTER_FREQ2] && + nla_get_u32(info->attrs[NL80211_ATTR_CENTER_FREQ2])) + return -EINVAL; break; default: return -EINVAL; @@ -5669,6 +5686,11 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) } } +static int nl80211_reload_regdb(struct sk_buff *skb, struct genl_info *info) +{ + return reg_reload_regdb(); +} + static int nl80211_get_mesh_config(struct sk_buff *skb, struct genl_info *info) { @@ -6610,6 +6632,77 @@ static bool cfg80211_off_channel_oper_allowed(struct wireless_dev *wdev) return regulatory_pre_cac_allowed(wdev->wiphy); } +static int +nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev, + void *request, struct nlattr **attrs, + bool is_sched_scan) +{ + u8 *mac_addr, *mac_addr_mask; + u32 *flags; + enum nl80211_feature_flags randomness_flag; + + if (!attrs[NL80211_ATTR_SCAN_FLAGS]) + return 0; + + if (is_sched_scan) { + struct cfg80211_sched_scan_request *req = request; + + randomness_flag = wdev ? + NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR : + NL80211_FEATURE_ND_RANDOM_MAC_ADDR; + flags = &req->flags; + mac_addr = req->mac_addr; + mac_addr_mask = req->mac_addr_mask; + } else { + struct cfg80211_scan_request *req = request; + + randomness_flag = NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR; + flags = &req->flags; + mac_addr = req->mac_addr; + mac_addr_mask = req->mac_addr_mask; + } + + *flags = nla_get_u32(attrs[NL80211_ATTR_SCAN_FLAGS]); + + if ((*flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && + !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) + return -EOPNOTSUPP; + + if (*flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { + int err; + + if (!(wiphy->features & randomness_flag) || + (wdev && wdev->current_bss)) + return -EOPNOTSUPP; + + err = nl80211_parse_random_mac(attrs, mac_addr, mac_addr_mask); + if (err) + return err; + } + + if ((*flags & NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME)) + return -EOPNOTSUPP; + + if ((*flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP)) + return -EOPNOTSUPP; + + if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION)) + return -EOPNOTSUPP; + + if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE)) + return -EOPNOTSUPP; + + return 0; +} + static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -6815,34 +6908,10 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) nla_get_flag(info->attrs[NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY]); } - if (info->attrs[NL80211_ATTR_SCAN_FLAGS]) { - request->flags = nla_get_u32( - info->attrs[NL80211_ATTR_SCAN_FLAGS]); - if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && - !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { - if (!(wiphy->features & - NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (wdev->current_bss) { - err = -EOPNOTSUPP; - goto out_free; - } - - err = nl80211_parse_random_mac(info->attrs, - request->mac_addr, - request->mac_addr_mask); - if (err) - goto out_free; - } - } + err = nl80211_check_scan_flags(wiphy, wdev, request, info->attrs, + false); + if (err) + goto out_free; request->no_cck = nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]); @@ -7290,37 +7359,9 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, request->ie_len); } - if (attrs[NL80211_ATTR_SCAN_FLAGS]) { - request->flags = nla_get_u32( - attrs[NL80211_ATTR_SCAN_FLAGS]); - if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && - !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { - u32 flg = NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR; - - if (!wdev) /* must be net-detect */ - flg = NL80211_FEATURE_ND_RANDOM_MAC_ADDR; - - if (!(wiphy->features & flg)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (wdev && wdev->current_bss) { - err = -EOPNOTSUPP; - goto out_free; - } - - err = nl80211_parse_random_mac(attrs, request->mac_addr, - request->mac_addr_mask); - if (err) - goto out_free; - } - } + err = nl80211_check_scan_flags(wiphy, wdev, request, attrs, true); + if (err) + goto out_free; if (attrs[NL80211_ATTR_SCHED_SCAN_DELAY]) request->delay = @@ -8924,8 +8965,14 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_USE_MFP]) { connect.mfp = nla_get_u32(info->attrs[NL80211_ATTR_USE_MFP]); + if (connect.mfp == NL80211_MFP_OPTIONAL && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_MFP_OPTIONAL)) + return -EOPNOTSUPP; + if (connect.mfp != NL80211_MFP_REQUIRED && - connect.mfp != NL80211_MFP_NO) + connect.mfp != NL80211_MFP_NO && + connect.mfp != NL80211_MFP_OPTIONAL) return -EINVAL; } else { connect.mfp = NL80211_MFP_NO; @@ -10532,7 +10579,8 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) u8 *mask_pat; nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, - NULL, info->extack); + nl80211_packet_pattern_policy, + info->extack); err = -EINVAL; if (!pat_tb[NL80211_PKTPAT_MASK] || !pat_tb[NL80211_PKTPAT_PATTERN]) @@ -10781,7 +10829,8 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev, rem) { u8 *mask_pat; - nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, NULL, NULL); + nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, + nl80211_packet_pattern_policy, NULL); if (!pat_tb[NL80211_PKTPAT_MASK] || !pat_tb[NL80211_PKTPAT_PATTERN]) return -EINVAL; @@ -12675,6 +12724,12 @@ static const struct genl_ops nl80211_ops[] = { .flags = GENL_ADMIN_PERM, }, { + .cmd = NL80211_CMD_RELOAD_REGDB, + .doit = nl80211_reload_regdb, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + }, + { .cmd = NL80211_CMD_GET_MESH_CONFIG, .doit = nl80211_get_mesh_config, .policy = nl80211_policy, @@ -13802,9 +13857,7 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, info->req_ie)) || (info->resp_ie && nla_put(msg, NL80211_ATTR_RESP_IE, info->resp_ie_len, - info->resp_ie)) || - (info->authorized && - nla_put_flag(msg, NL80211_ATTR_PORT_AUTHORIZED))) + info->resp_ie))) goto nla_put_failure; genlmsg_end(msg, hdr); @@ -13818,6 +13871,36 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, nlmsg_free(msg); } +void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_PORT_AUTHORIZED); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, + NL80211_MCGRP_MLME, GFP_KERNEL); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, struct net_device *netdev, u16 reason, const u8 *ie, size_t ie_len, bool from_ap) diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index b96933322077..bf9e772a30b9 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -58,6 +58,8 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, void nl80211_send_roamed(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_roam_info *info, gfp_t gfp); +void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid); void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, struct net_device *netdev, u16 reason, const u8 *ie, size_t ie_len, bool from_ap); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 6e94f6934a0e..3871998059de 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -53,12 +53,13 @@ #include <linux/ctype.h> #include <linux/nl80211.h> #include <linux/platform_device.h> +#include <linux/verification.h> #include <linux/moduleparam.h> +#include <linux/firmware.h> #include <net/cfg80211.h> #include "core.h" #include "reg.h" #include "rdev-ops.h" -#include "regdb.h" #include "nl80211.h" /* @@ -100,7 +101,7 @@ static struct regulatory_request core_request_world = { static struct regulatory_request __rcu *last_request = (void __force __rcu *)&core_request_world; -/* To trigger userspace events */ +/* To trigger userspace events and load firmware */ static struct platform_device *reg_pdev; /* @@ -443,7 +444,6 @@ reg_copy_regd(const struct ieee80211_regdomain *src_regd) return regd; } -#ifdef CONFIG_CFG80211_INTERNAL_REGDB struct reg_regdb_apply_request { struct list_head list; const struct ieee80211_regdomain *regdom; @@ -475,55 +475,26 @@ static void reg_regdb_apply(struct work_struct *work) static DECLARE_WORK(reg_regdb_work, reg_regdb_apply); -static int reg_query_builtin(const char *alpha2) +static int reg_schedule_apply(const struct ieee80211_regdomain *regdom) { - const struct ieee80211_regdomain *regdom = NULL; struct reg_regdb_apply_request *request; - unsigned int i; - - for (i = 0; i < reg_regdb_size; i++) { - if (alpha2_equal(alpha2, reg_regdb[i]->alpha2)) { - regdom = reg_regdb[i]; - break; - } - } - - if (!regdom) - return -ENODATA; request = kzalloc(sizeof(struct reg_regdb_apply_request), GFP_KERNEL); - if (!request) - return -ENOMEM; - - request->regdom = reg_copy_regd(regdom); - if (IS_ERR_OR_NULL(request->regdom)) { - kfree(request); + if (!request) { + kfree(regdom); return -ENOMEM; } + request->regdom = regdom; + mutex_lock(®_regdb_apply_mutex); list_add_tail(&request->list, ®_regdb_apply_list); mutex_unlock(®_regdb_apply_mutex); schedule_work(®_regdb_work); - return 0; } -/* Feel free to add any other sanity checks here */ -static void reg_regdb_size_check(void) -{ - /* We should ideally BUILD_BUG_ON() but then random builds would fail */ - WARN_ONCE(!reg_regdb_size, "db.txt is empty, you should update it..."); -} -#else -static inline void reg_regdb_size_check(void) {} -static inline int reg_query_builtin(const char *alpha2) -{ - return -ENODATA; -} -#endif /* CONFIG_CFG80211_INTERNAL_REGDB */ - #ifdef CONFIG_CFG80211_CRDA_SUPPORT /* Max number of consecutive attempts to communicate with CRDA */ #define REG_MAX_CRDA_TIMEOUTS 10 @@ -599,10 +570,402 @@ static inline int call_crda(const char *alpha2) } #endif /* CONFIG_CFG80211_CRDA_SUPPORT */ +/* code to directly load a firmware database through request_firmware */ +static const struct fwdb_header *regdb; + +struct fwdb_country { + u8 alpha2[2]; + __be16 coll_ptr; + /* this struct cannot be extended */ +} __packed __aligned(4); + +struct fwdb_collection { + u8 len; + u8 n_rules; + u8 dfs_region; + /* no optional data yet */ + /* aligned to 2, then followed by __be16 array of rule pointers */ +} __packed __aligned(4); + +enum fwdb_flags { + FWDB_FLAG_NO_OFDM = BIT(0), + FWDB_FLAG_NO_OUTDOOR = BIT(1), + FWDB_FLAG_DFS = BIT(2), + FWDB_FLAG_NO_IR = BIT(3), + FWDB_FLAG_AUTO_BW = BIT(4), +}; + +struct fwdb_rule { + u8 len; + u8 flags; + __be16 max_eirp; + __be32 start, end, max_bw; + /* start of optional data */ + __be16 cac_timeout; +} __packed __aligned(4); + +#define FWDB_MAGIC 0x52474442 +#define FWDB_VERSION 20 + +struct fwdb_header { + __be32 magic; + __be32 version; + struct fwdb_country country[]; +} __packed __aligned(4); + +static bool valid_rule(const u8 *data, unsigned int size, u16 rule_ptr) +{ + struct fwdb_rule *rule = (void *)(data + (rule_ptr << 2)); + + if ((u8 *)rule + sizeof(rule->len) > data + size) + return false; + + /* mandatory fields */ + if (rule->len < offsetofend(struct fwdb_rule, max_bw)) + return false; + + return true; +} + +static bool valid_country(const u8 *data, unsigned int size, + const struct fwdb_country *country) +{ + unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2; + struct fwdb_collection *coll = (void *)(data + ptr); + __be16 *rules_ptr; + unsigned int i; + + /* make sure we can read len/n_rules */ + if ((u8 *)coll + offsetofend(typeof(*coll), n_rules) > data + size) + return false; + + /* make sure base struct and all rules fit */ + if ((u8 *)coll + ALIGN(coll->len, 2) + + (coll->n_rules * 2) > data + size) + return false; + + /* mandatory fields must exist */ + if (coll->len < offsetofend(struct fwdb_collection, dfs_region)) + return false; + + rules_ptr = (void *)((u8 *)coll + ALIGN(coll->len, 2)); + + for (i = 0; i < coll->n_rules; i++) { + u16 rule_ptr = be16_to_cpu(rules_ptr[i]); + + if (!valid_rule(data, size, rule_ptr)) + return false; + } + + return true; +} + +#ifdef CONFIG_CFG80211_REQUIRE_SIGNED_REGDB +static struct key *builtin_regdb_keys; + +static void __init load_keys_from_buffer(const u8 *p, unsigned int buflen) +{ + const u8 *end = p + buflen; + size_t plen; + key_ref_t key; + + while (p < end) { + /* Each cert begins with an ASN.1 SEQUENCE tag and must be more + * than 256 bytes in size. + */ + if (end - p < 4) + goto dodgy_cert; + if (p[0] != 0x30 && + p[1] != 0x82) + goto dodgy_cert; + plen = (p[2] << 8) | p[3]; + plen += 4; + if (plen > end - p) + goto dodgy_cert; + + key = key_create_or_update(make_key_ref(builtin_regdb_keys, 1), + "asymmetric", NULL, p, plen, + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ), + KEY_ALLOC_NOT_IN_QUOTA | + KEY_ALLOC_BUILT_IN | + KEY_ALLOC_BYPASS_RESTRICTION); + if (IS_ERR(key)) { + pr_err("Problem loading in-kernel X.509 certificate (%ld)\n", + PTR_ERR(key)); + } else { + pr_notice("Loaded X.509 cert '%s'\n", + key_ref_to_ptr(key)->description); + key_ref_put(key); + } + p += plen; + } + + return; + +dodgy_cert: + pr_err("Problem parsing in-kernel X.509 certificate list\n"); +} + +static int __init load_builtin_regdb_keys(void) +{ + builtin_regdb_keys = + keyring_alloc(".builtin_regdb_keys", + KUIDT_INIT(0), KGIDT_INIT(0), current_cred(), + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH), + KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL); + if (IS_ERR(builtin_regdb_keys)) + return PTR_ERR(builtin_regdb_keys); + + pr_notice("Loading compiled-in X.509 certificates for regulatory database\n"); + +#ifdef CONFIG_CFG80211_USE_KERNEL_REGDB_KEYS + load_keys_from_buffer(shipped_regdb_certs, shipped_regdb_certs_len); +#endif +#ifdef CONFIG_CFG80211_EXTRA_REGDB_KEYDIR + if (CONFIG_CFG80211_EXTRA_REGDB_KEYDIR[0] != '\0') + load_keys_from_buffer(extra_regdb_certs, extra_regdb_certs_len); +#endif + + return 0; +} + +static bool regdb_has_valid_signature(const u8 *data, unsigned int size) +{ + const struct firmware *sig; + bool result; + + if (request_firmware(&sig, "regulatory.db.p7s", ®_pdev->dev)) + return false; + + result = verify_pkcs7_signature(data, size, sig->data, sig->size, + builtin_regdb_keys, + VERIFYING_UNSPECIFIED_SIGNATURE, + NULL, NULL) == 0; + + release_firmware(sig); + + return result; +} + +static void free_regdb_keyring(void) +{ + key_put(builtin_regdb_keys); +} +#else +static int load_builtin_regdb_keys(void) +{ + return 0; +} + +static bool regdb_has_valid_signature(const u8 *data, unsigned int size) +{ + return true; +} + +static void free_regdb_keyring(void) +{ +} +#endif /* CONFIG_CFG80211_REQUIRE_SIGNED_REGDB */ + +static bool valid_regdb(const u8 *data, unsigned int size) +{ + const struct fwdb_header *hdr = (void *)data; + const struct fwdb_country *country; + + if (size < sizeof(*hdr)) + return false; + + if (hdr->magic != cpu_to_be32(FWDB_MAGIC)) + return false; + + if (hdr->version != cpu_to_be32(FWDB_VERSION)) + return false; + + if (!regdb_has_valid_signature(data, size)) + return false; + + country = &hdr->country[0]; + while ((u8 *)(country + 1) <= data + size) { + if (!country->coll_ptr) + break; + if (!valid_country(data, size, country)) + return false; + country++; + } + + return true; +} + +static int regdb_query_country(const struct fwdb_header *db, + const struct fwdb_country *country) +{ + unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2; + struct fwdb_collection *coll = (void *)((u8 *)db + ptr); + struct ieee80211_regdomain *regdom; + unsigned int size_of_regd; + unsigned int i; + + size_of_regd = + sizeof(struct ieee80211_regdomain) + + coll->n_rules * sizeof(struct ieee80211_reg_rule); + + regdom = kzalloc(size_of_regd, GFP_KERNEL); + if (!regdom) + return -ENOMEM; + + regdom->n_reg_rules = coll->n_rules; + regdom->alpha2[0] = country->alpha2[0]; + regdom->alpha2[1] = country->alpha2[1]; + regdom->dfs_region = coll->dfs_region; + + for (i = 0; i < regdom->n_reg_rules; i++) { + __be16 *rules_ptr = (void *)((u8 *)coll + ALIGN(coll->len, 2)); + unsigned int rule_ptr = be16_to_cpu(rules_ptr[i]) << 2; + struct fwdb_rule *rule = (void *)((u8 *)db + rule_ptr); + struct ieee80211_reg_rule *rrule = ®dom->reg_rules[i]; + + rrule->freq_range.start_freq_khz = be32_to_cpu(rule->start); + rrule->freq_range.end_freq_khz = be32_to_cpu(rule->end); + rrule->freq_range.max_bandwidth_khz = be32_to_cpu(rule->max_bw); + + rrule->power_rule.max_antenna_gain = 0; + rrule->power_rule.max_eirp = be16_to_cpu(rule->max_eirp); + + rrule->flags = 0; + if (rule->flags & FWDB_FLAG_NO_OFDM) + rrule->flags |= NL80211_RRF_NO_OFDM; + if (rule->flags & FWDB_FLAG_NO_OUTDOOR) + rrule->flags |= NL80211_RRF_NO_OUTDOOR; + if (rule->flags & FWDB_FLAG_DFS) + rrule->flags |= NL80211_RRF_DFS; + if (rule->flags & FWDB_FLAG_NO_IR) + rrule->flags |= NL80211_RRF_NO_IR; + if (rule->flags & FWDB_FLAG_AUTO_BW) + rrule->flags |= NL80211_RRF_AUTO_BW; + + rrule->dfs_cac_ms = 0; + + /* handle optional data */ + if (rule->len >= offsetofend(struct fwdb_rule, cac_timeout)) + rrule->dfs_cac_ms = + 1000 * be16_to_cpu(rule->cac_timeout); + } + + return reg_schedule_apply(regdom); +} + +static int query_regdb(const char *alpha2) +{ + const struct fwdb_header *hdr = regdb; + const struct fwdb_country *country; + + ASSERT_RTNL(); + + if (IS_ERR(regdb)) + return PTR_ERR(regdb); + + country = &hdr->country[0]; + while (country->coll_ptr) { + if (alpha2_equal(alpha2, country->alpha2)) + return regdb_query_country(regdb, country); + country++; + } + + return -ENODATA; +} + +static void regdb_fw_cb(const struct firmware *fw, void *context) +{ + int set_error = 0; + bool restore = true; + void *db; + + if (!fw) { + pr_info("failed to load regulatory.db\n"); + set_error = -ENODATA; + } else if (!valid_regdb(fw->data, fw->size)) { + pr_info("loaded regulatory.db is malformed or signature is missing/invalid\n"); + set_error = -EINVAL; + } + + rtnl_lock(); + if (WARN_ON(regdb && !IS_ERR(regdb))) { + /* just restore and free new db */ + } else if (set_error) { + regdb = ERR_PTR(set_error); + } else if (fw) { + db = kmemdup(fw->data, fw->size, GFP_KERNEL); + if (db) { + regdb = db; + restore = context && query_regdb(context); + } else { + restore = true; + } + } + + if (restore) + restore_regulatory_settings(true); + + rtnl_unlock(); + + kfree(context); + + release_firmware(fw); +} + +static int query_regdb_file(const char *alpha2) +{ + ASSERT_RTNL(); + + if (regdb) + return query_regdb(alpha2); + + alpha2 = kmemdup(alpha2, 2, GFP_KERNEL); + if (!alpha2) + return -ENOMEM; + + return request_firmware_nowait(THIS_MODULE, true, "regulatory.db", + ®_pdev->dev, GFP_KERNEL, + (void *)alpha2, regdb_fw_cb); +} + +int reg_reload_regdb(void) +{ + const struct firmware *fw; + void *db; + int err; + + err = request_firmware(&fw, "regulatory.db", ®_pdev->dev); + if (err) + return err; + + if (!valid_regdb(fw->data, fw->size)) { + err = -ENODATA; + goto out; + } + + db = kmemdup(fw->data, fw->size, GFP_KERNEL); + if (!db) { + err = -ENOMEM; + goto out; + } + + rtnl_lock(); + if (!IS_ERR_OR_NULL(regdb)) + kfree(regdb); + regdb = db; + rtnl_unlock(); + + out: + release_firmware(fw); + return err; +} + static bool reg_query_database(struct regulatory_request *request) { - /* query internal regulatory database (if it exists) */ - if (reg_query_builtin(request->alpha2) == 0) + if (query_regdb_file(request->alpha2) == 0) return true; if (call_crda(request->alpha2) == 0) @@ -3285,6 +3648,10 @@ int __init regulatory_init(void) { int err = 0; + err = load_builtin_regdb_keys(); + if (err) + return err; + reg_pdev = platform_device_register_simple("regulatory", 0, NULL, 0); if (IS_ERR(reg_pdev)) return PTR_ERR(reg_pdev); @@ -3293,8 +3660,6 @@ int __init regulatory_init(void) spin_lock_init(®_pending_beacons_lock); spin_lock_init(®_indoor_lock); - reg_regdb_size_check(); - rcu_assign_pointer(cfg80211_regdomain, cfg80211_world_regdom); user_alpha2[0] = '9'; @@ -3360,4 +3725,9 @@ void regulatory_exit(void) list_del(®_request->list); kfree(reg_request); } + + if (!IS_ERR_OR_NULL(regdb)) + kfree(regdb); + + free_regdb_keyring(); } diff --git a/net/wireless/reg.h b/net/wireless/reg.h index ca7fedf2e7a1..9ceeb5f3a7cb 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -1,5 +1,8 @@ #ifndef __NET_WIRELESS_REG_H #define __NET_WIRELESS_REG_H + +#include <net/cfg80211.h> + /* * Copyright 2008-2011 Luis R. Rodriguez <mcgrof@qca.qualcomm.com> * @@ -179,4 +182,15 @@ void regulatory_propagate_dfs_state(struct wiphy *wiphy, * @wiphy2 - wiphy it's dfs_region to be checked against that of wiphy1 */ bool reg_dfs_domain_same(struct wiphy *wiphy1, struct wiphy *wiphy2); + +/** + * reg_reload_regdb - reload the regulatory.db firmware file + */ +int reg_reload_regdb(void); + +extern const u8 shipped_regdb_certs[]; +extern unsigned int shipped_regdb_certs_len; +extern const u8 extra_regdb_certs[]; +extern unsigned int extra_regdb_certs_len; + #endif /* __NET_WIRELESS_REG_H */ diff --git a/net/wireless/regdb.h b/net/wireless/regdb.h deleted file mode 100644 index 3279cfcefb0c..000000000000 --- a/net/wireless/regdb.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef __REGDB_H__ -#define __REGDB_H__ - -/* - * Copyright 2009 John W. Linville <linville@tuxdriver.com> - * - * Permission to use, copy, modify, and/or distribute this software for any - * purpose with or without fee is hereby granted, provided that the above - * copyright notice and this permission notice appear in all copies. - * - * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES - * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR - * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES - * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN - * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF - * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - */ - -extern const struct ieee80211_regdomain *reg_regdb[]; -extern int reg_regdb_size; - -#endif /* __REGDB_H__ */ diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 0a49b88070d0..f38ed490e42b 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -960,7 +960,6 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, ev->rm.resp_ie_len = info->resp_ie_len; memcpy((void *)ev->rm.resp_ie, info->resp_ie, info->resp_ie_len); ev->rm.bss = info->bss; - ev->rm.authorized = info->authorized; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); @@ -969,6 +968,50 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, } EXPORT_SYMBOL(cfg80211_roamed); +void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid) +{ + ASSERT_WDEV_LOCK(wdev); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + return; + + if (WARN_ON(!wdev->current_bss) || + WARN_ON(!ether_addr_equal(wdev->current_bss->pub.bssid, bssid))) + return; + + nl80211_send_port_authorized(wiphy_to_rdev(wdev->wiphy), wdev->netdev, + bssid); +} + +void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, + gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_event *ev; + unsigned long flags; + + if (WARN_ON(!bssid)) + return; + + ev = kzalloc(sizeof(*ev), gfp); + if (!ev) + return; + + ev->type = EVENT_PORT_AUTHORIZED; + memcpy(ev->pa.bssid, bssid, ETH_ALEN); + + /* + * Use the wdev event list so that if there are pending + * connected/roamed events, they will be reported first. + */ + spin_lock_irqsave(&wdev->event_lock, flags); + list_add_tail(&ev->list, &wdev->event_list); + spin_unlock_irqrestore(&wdev->event_lock, flags); + queue_work(cfg80211_wq, &rdev->event_work); +} +EXPORT_SYMBOL(cfg80211_port_authorized); + void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, size_t ie_len, u16 reason, bool from_ap) { diff --git a/net/wireless/util.c b/net/wireless/util.c index bcb1284c3415..ff21c314a609 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -157,32 +157,30 @@ static void set_mandatory_flags_band(struct ieee80211_supported_band *sband) case NL80211_BAND_2GHZ: want = 7; for (i = 0; i < sband->n_bitrates; i++) { - if (sband->bitrates[i].bitrate == 10) { + switch (sband->bitrates[i].bitrate) { + case 10: + case 20: + case 55: + case 110: sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_B | IEEE80211_RATE_MANDATORY_G; want--; - } - - if (sband->bitrates[i].bitrate == 20 || - sband->bitrates[i].bitrate == 55 || - sband->bitrates[i].bitrate == 110 || - sband->bitrates[i].bitrate == 60 || - sband->bitrates[i].bitrate == 120 || - sband->bitrates[i].bitrate == 240) { + break; + case 60: + case 120: + case 240: sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_G; want--; - } - - if (sband->bitrates[i].bitrate != 10 && - sband->bitrates[i].bitrate != 20 && - sband->bitrates[i].bitrate != 55 && - sband->bitrates[i].bitrate != 110) + /* fall through */ + default: sband->bitrates[i].flags |= IEEE80211_RATE_ERP_G; + break; + } } - WARN_ON(want != 0 && want != 3 && want != 6); + WARN_ON(want != 0 && want != 3); break; case NL80211_BAND_60GHZ: /* check for mandatory HT MCS 1..4 */ @@ -529,121 +527,6 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, } EXPORT_SYMBOL(ieee80211_data_to_8023_exthdr); -int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr, - enum nl80211_iftype iftype, - const u8 *bssid, bool qos) -{ - struct ieee80211_hdr hdr; - u16 hdrlen, ethertype; - __le16 fc; - const u8 *encaps_data; - int encaps_len, skip_header_bytes; - int nh_pos, h_pos; - int head_need; - - if (unlikely(skb->len < ETH_HLEN)) - return -EINVAL; - - nh_pos = skb_network_header(skb) - skb->data; - h_pos = skb_transport_header(skb) - skb->data; - - /* convert Ethernet header to proper 802.11 header (based on - * operation mode) */ - ethertype = (skb->data[12] << 8) | skb->data[13]; - fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA); - - switch (iftype) { - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_AP_VLAN: - case NL80211_IFTYPE_P2P_GO: - fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS); - /* DA BSSID SA */ - memcpy(hdr.addr1, skb->data, ETH_ALEN); - memcpy(hdr.addr2, addr, ETH_ALEN); - memcpy(hdr.addr3, skb->data + ETH_ALEN, ETH_ALEN); - hdrlen = 24; - break; - case NL80211_IFTYPE_STATION: - case NL80211_IFTYPE_P2P_CLIENT: - fc |= cpu_to_le16(IEEE80211_FCTL_TODS); - /* BSSID SA DA */ - memcpy(hdr.addr1, bssid, ETH_ALEN); - memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN); - memcpy(hdr.addr3, skb->data, ETH_ALEN); - hdrlen = 24; - break; - case NL80211_IFTYPE_OCB: - case NL80211_IFTYPE_ADHOC: - /* DA SA BSSID */ - memcpy(hdr.addr1, skb->data, ETH_ALEN); - memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN); - memcpy(hdr.addr3, bssid, ETH_ALEN); - hdrlen = 24; - break; - default: - return -EOPNOTSUPP; - } - - if (qos) { - fc |= cpu_to_le16(IEEE80211_STYPE_QOS_DATA); - hdrlen += 2; - } - - hdr.frame_control = fc; - hdr.duration_id = 0; - hdr.seq_ctrl = 0; - - skip_header_bytes = ETH_HLEN; - if (ethertype == ETH_P_AARP || ethertype == ETH_P_IPX) { - encaps_data = bridge_tunnel_header; - encaps_len = sizeof(bridge_tunnel_header); - skip_header_bytes -= 2; - } else if (ethertype >= ETH_P_802_3_MIN) { - encaps_data = rfc1042_header; - encaps_len = sizeof(rfc1042_header); - skip_header_bytes -= 2; - } else { - encaps_data = NULL; - encaps_len = 0; - } - - skb_pull(skb, skip_header_bytes); - nh_pos -= skip_header_bytes; - h_pos -= skip_header_bytes; - - head_need = hdrlen + encaps_len - skb_headroom(skb); - - if (head_need > 0 || skb_cloned(skb)) { - head_need = max(head_need, 0); - if (head_need) - skb_orphan(skb); - - if (pskb_expand_head(skb, head_need, 0, GFP_ATOMIC)) - return -ENOMEM; - } - - if (encaps_data) { - memcpy(skb_push(skb, encaps_len), encaps_data, encaps_len); - nh_pos += encaps_len; - h_pos += encaps_len; - } - - memcpy(skb_push(skb, hdrlen), &hdr, hdrlen); - - nh_pos += hdrlen; - h_pos += hdrlen; - - /* Update skb pointers to various headers since this modified frame - * is going to go through Linux networking code that may potentially - * need things like pointer to IP header. */ - skb_reset_mac_header(skb); - skb_set_network_header(skb, nh_pos); - skb_set_transport_header(skb, h_pos); - - return 0; -} -EXPORT_SYMBOL(ieee80211_data_from_8023); - static void __frame_add_frag(struct sk_buff *skb, struct page *page, void *ptr, int len, int size) @@ -963,6 +846,9 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev) case EVENT_STOPPED: __cfg80211_leave(wiphy_to_rdev(wdev->wiphy), wdev); break; + case EVENT_PORT_AUTHORIZED: + __cfg80211_port_authorized(wdev, ev->pa.bssid); + break; } wdev_unlock(wdev); @@ -1367,13 +1253,29 @@ int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len, } EXPORT_SYMBOL(cfg80211_get_p2p_attr); -static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id) +static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id, bool id_ext) { int i; - for (i = 0; i < n_ids; i++) - if (ids[i] == id) + /* Make sure array values are legal */ + if (WARN_ON(ids[n_ids - 1] == WLAN_EID_EXTENSION)) + return false; + + i = 0; + while (i < n_ids) { + if (ids[i] == WLAN_EID_EXTENSION) { + if (id_ext && (ids[i + 1] == id)) + return true; + + i += 2; + continue; + } + + if (ids[i] == id && !id_ext) return true; + + i++; + } return false; } @@ -1403,14 +1305,36 @@ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, { size_t pos = offset; - while (pos < ielen && ieee80211_id_in_list(ids, n_ids, ies[pos])) { + while (pos < ielen) { + u8 ext = 0; + + if (ies[pos] == WLAN_EID_EXTENSION) + ext = 2; + if ((pos + ext) >= ielen) + break; + + if (!ieee80211_id_in_list(ids, n_ids, ies[pos + ext], + ies[pos] == WLAN_EID_EXTENSION)) + break; + if (ies[pos] == WLAN_EID_RIC_DATA && n_after_ric) { pos = skip_ie(ies, ielen, pos); - while (pos < ielen && - !ieee80211_id_in_list(after_ric, n_after_ric, - ies[pos])) - pos = skip_ie(ies, ielen, pos); + while (pos < ielen) { + if (ies[pos] == WLAN_EID_EXTENSION) + ext = 2; + else + ext = 0; + + if ((pos + ext) >= ielen) + break; + + if (!ieee80211_id_in_list(after_ric, + n_after_ric, + ies[pos + ext], + ext == 2)) + pos = skip_ie(ies, ielen, pos); + } } else { pos = skip_ie(ies, ielen, pos); } diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index ac095936552d..ea87143314f3 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -374,9 +374,11 @@ static void __x25_destroy_socket(struct sock *); /* * handler for deferred kills. */ -static void x25_destroy_timer(unsigned long data) +static void x25_destroy_timer(struct timer_list *t) { - x25_destroy_socket_from_timer((struct sock *)data); + struct sock *sk = from_timer(sk, t, sk_timer); + + x25_destroy_socket_from_timer(sk); } /* @@ -413,8 +415,7 @@ static void __x25_destroy_socket(struct sock *sk) if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ sk->sk_timer.expires = jiffies + 10 * HZ; - sk->sk_timer.function = x25_destroy_timer; - sk->sk_timer.data = (unsigned long)sk; + sk->sk_timer.function = (TIMER_FUNC_TYPE)x25_destroy_timer; add_timer(&sk->sk_timer); } else { /* drop last reference so sock_put will free */ diff --git a/net/x25/x25_timer.c b/net/x25/x25_timer.c index 5c5db1a36399..1dfba3c23459 100644 --- a/net/x25/x25_timer.c +++ b/net/x25/x25_timer.c @@ -26,18 +26,17 @@ #include <net/tcp_states.h> #include <net/x25.h> -static void x25_heartbeat_expiry(unsigned long); -static void x25_timer_expiry(unsigned long); +static void x25_heartbeat_expiry(struct timer_list *t); +static void x25_timer_expiry(struct timer_list *t); void x25_init_timers(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - setup_timer(&x25->timer, x25_timer_expiry, (unsigned long)sk); + timer_setup(&x25->timer, x25_timer_expiry, 0); /* initialized by sock_init_data */ - sk->sk_timer.data = (unsigned long)sk; - sk->sk_timer.function = &x25_heartbeat_expiry; + sk->sk_timer.function = (TIMER_FUNC_TYPE)x25_heartbeat_expiry; } void x25_start_heartbeat(struct sock *sk) @@ -93,9 +92,9 @@ unsigned long x25_display_timer(struct sock *sk) return x25->timer.expires - jiffies; } -static void x25_heartbeat_expiry(unsigned long param) +static void x25_heartbeat_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct sock *sk = from_timer(sk, t, sk_timer); bh_lock_sock(sk); if (sock_owned_by_user(sk)) /* can currently only occur in state 3 */ @@ -160,9 +159,10 @@ static inline void x25_do_timer_expiry(struct sock * sk) } } -static void x25_timer_expiry(unsigned long param) +static void x25_timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct x25_sock *x25 = from_timer(x25, t, timer); + struct sock *sk = &x25->sk; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* can currently only occur in state 3 */ diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index acf00104ef31..30e5746085b8 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -91,6 +91,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, } if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) { + xso->dev = NULL; dev_put(dev); return 0; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 2515cd2bc5db..8ac9d32fb79d 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -429,7 +429,8 @@ resume: nf_reset(skb); if (decaps) { - skb->sp->olen = 0; + if (skb->sp) + skb->sp->olen = 0; skb_dst_drop(skb); gro_cells_receive(&gro_cells, skb); return 0; @@ -440,7 +441,8 @@ resume: err = x->inner_mode->afinfo->transport_finish(skb, xfrm_gro || async); if (xfrm_gro) { - skb->sp->olen = 0; + if (skb->sp) + skb->sp->olen = 0; skb_dst_drop(skb); gro_cells_receive(&gro_cells, skb); return err; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index f06253969972..4838329bb43a 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -57,7 +57,7 @@ static __read_mostly seqcount_t xfrm_policy_hash_generation; static void xfrm_init_pmtu(struct dst_entry *dst); static int stale_bundle(struct dst_entry *dst); static int xfrm_bundle_ok(struct xfrm_dst *xdst); -static void xfrm_policy_queue_process(unsigned long arg); +static void xfrm_policy_queue_process(struct timer_list *t); static void __xfrm_policy_link(struct xfrm_policy *pol, int dir); static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, @@ -179,9 +179,9 @@ static inline unsigned long make_jiffies(long secs) return secs*HZ; } -static void xfrm_policy_timer(unsigned long data) +static void xfrm_policy_timer(struct timer_list *t) { - struct xfrm_policy *xp = (struct xfrm_policy *)data; + struct xfrm_policy *xp = from_timer(xp, t, timer); unsigned long now = get_seconds(); long next = LONG_MAX; int warn = 0; @@ -267,10 +267,9 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) rwlock_init(&policy->lock); refcount_set(&policy->refcnt, 1); skb_queue_head_init(&policy->polq.hold_queue); - setup_timer(&policy->timer, xfrm_policy_timer, - (unsigned long)policy); - setup_timer(&policy->polq.hold_timer, xfrm_policy_queue_process, - (unsigned long)policy); + timer_setup(&policy->timer, xfrm_policy_timer, 0); + timer_setup(&policy->polq.hold_timer, + xfrm_policy_queue_process, 0); } return policy; } @@ -1852,12 +1851,12 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, return xdst; } -static void xfrm_policy_queue_process(unsigned long arg) +static void xfrm_policy_queue_process(struct timer_list *t) { struct sk_buff *skb; struct sock *sk; struct dst_entry *dst; - struct xfrm_policy *pol = (struct xfrm_policy *)arg; + struct xfrm_policy *pol = from_timer(pol, t, polq.hold_timer); struct net *net = xp_net(pol); struct xfrm_policy_queue *pq = &pol->polq; struct flowi fl; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 0dab1cd79ce4..12213477cd3a 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -732,12 +732,12 @@ restart: } } } +out: + spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (cnt) { err = 0; xfrm_policy_cache_flush(); } -out: - spin_unlock_bh(&net->xfrm.xfrm_state_lock); return err; } EXPORT_SYMBOL(xfrm_state_flush); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 2bfbd9121e3b..b997f1395357 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -657,6 +657,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) { x->km.state = XFRM_STATE_DEAD; + xfrm_dev_state_delete(x); __xfrm_state_put(x); goto out; } diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index ebc2ad69b62c..3534ccfb5920 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -39,6 +39,7 @@ hostprogs-y += per_socket_stats_example hostprogs-y += load_sock_ops hostprogs-y += xdp_redirect hostprogs-y += xdp_redirect_map +hostprogs-y += xdp_redirect_cpu hostprogs-y += xdp_monitor hostprogs-y += syscall_tp @@ -84,6 +85,7 @@ test_map_in_map-objs := bpf_load.o $(LIBBPF) test_map_in_map_user.o per_socket_stats_example-objs := $(LIBBPF) cookie_uid_helper_example.o xdp_redirect-objs := bpf_load.o $(LIBBPF) xdp_redirect_user.o xdp_redirect_map-objs := bpf_load.o $(LIBBPF) xdp_redirect_map_user.o +xdp_redirect_cpu-objs := bpf_load.o $(LIBBPF) xdp_redirect_cpu_user.o xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o @@ -129,6 +131,7 @@ always += tcp_iw_kern.o always += tcp_clamp_kern.o always += xdp_redirect_kern.o always += xdp_redirect_map_kern.o +always += xdp_redirect_cpu_kern.o always += xdp_monitor_kern.o always += syscall_tp_kern.o @@ -169,6 +172,7 @@ HOSTLOADLIBES_xdp_tx_iptunnel += -lelf HOSTLOADLIBES_test_map_in_map += -lelf HOSTLOADLIBES_xdp_redirect += -lelf HOSTLOADLIBES_xdp_redirect_map += -lelf +HOSTLOADLIBES_xdp_redirect_cpu += -lelf HOSTLOADLIBES_xdp_monitor += -lelf HOSTLOADLIBES_syscall_tp += -lelf @@ -180,6 +184,7 @@ CLANG ?= clang # Detect that we're cross compiling and use the cross compiler ifdef CROSS_COMPILE HOSTCC = $(CROSS_COMPILE)gcc +CLANG_ARCH_ARGS = -target $(ARCH) endif # Trick to allow make to be run from this directory @@ -229,9 +234,9 @@ $(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h $(obj)/%.o: $(src)/%.c $(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \ -I$(srctree)/tools/testing/selftests/bpf/ \ - -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \ + -D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \ -D__TARGET_ARCH_$(ARCH) -Wno-compare-distinct-pointer-types \ -Wno-gnu-variable-sized-type-not-at-end \ -Wno-address-of-packed-member -Wno-tautological-compare \ - -Wno-unknown-warning-option \ + -Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \ -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@ diff --git a/samples/bpf/trace_event_kern.c b/samples/bpf/trace_event_kern.c index 41b6115a32eb..a77a583d94d4 100644 --- a/samples/bpf/trace_event_kern.c +++ b/samples/bpf/trace_event_kern.c @@ -37,10 +37,14 @@ struct bpf_map_def SEC("maps") stackmap = { SEC("perf_event") int bpf_prog1(struct bpf_perf_event_data *ctx) { + char time_fmt1[] = "Time Enabled: %llu, Time Running: %llu"; + char time_fmt2[] = "Get Time Failed, ErrCode: %d"; char fmt[] = "CPU-%d period %lld ip %llx"; u32 cpu = bpf_get_smp_processor_id(); + struct bpf_perf_event_value value_buf; struct key_t key; u64 *val, one = 1; + int ret; if (ctx->sample_period < 10000) /* ignore warmup */ @@ -54,6 +58,12 @@ int bpf_prog1(struct bpf_perf_event_data *ctx) return 0; } + ret = bpf_perf_prog_read_value(ctx, (void *)&value_buf, sizeof(struct bpf_perf_event_value)); + if (!ret) + bpf_trace_printk(time_fmt1, sizeof(time_fmt1), value_buf.enabled, value_buf.running); + else + bpf_trace_printk(time_fmt2, sizeof(time_fmt2), ret); + val = bpf_map_lookup_elem(&counts, &key); if (val) (*val)++; diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c index 7bd827b84a67..bf4f1b6d9a52 100644 --- a/samples/bpf/trace_event_user.c +++ b/samples/bpf/trace_event_user.c @@ -127,6 +127,9 @@ static void test_perf_event_all_cpu(struct perf_event_attr *attr) int *pmu_fd = malloc(nr_cpus * sizeof(int)); int i, error = 0; + /* system wide perf event, no need to inherit */ + attr->inherit = 0; + /* open perf_event on all cpus */ for (i = 0; i < nr_cpus; i++) { pmu_fd[i] = sys_perf_event_open(attr, -1, i, -1, 0); @@ -154,6 +157,11 @@ static void test_perf_event_task(struct perf_event_attr *attr) { int pmu_fd; + /* per task perf event, enable inherit so the "dd ..." command can be traced properly. + * Enabling inherit will cause bpf_perf_prog_read_time helper failure. + */ + attr->inherit = 1; + /* open task bound event */ pmu_fd = sys_perf_event_open(attr, 0, -1, -1, 0); if (pmu_fd < 0) { @@ -175,14 +183,12 @@ static void test_bpf_perf_event(void) .freq = 1, .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, - .inherit = 1, }; struct perf_event_attr attr_type_sw = { .sample_freq = SAMPLE_FREQ, .freq = 1, .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_CLOCK, - .inherit = 1, }; struct perf_event_attr attr_hw_cache_l1d = { .sample_freq = SAMPLE_FREQ, @@ -192,7 +198,6 @@ static void test_bpf_perf_event(void) PERF_COUNT_HW_CACHE_L1D | (PERF_COUNT_HW_CACHE_OP_READ << 8) | (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16), - .inherit = 1, }; struct perf_event_attr attr_hw_cache_branch_miss = { .sample_freq = SAMPLE_FREQ, @@ -202,7 +207,6 @@ static void test_bpf_perf_event(void) PERF_COUNT_HW_CACHE_BPU | (PERF_COUNT_HW_CACHE_OP_READ << 8) | (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), - .inherit = 1, }; struct perf_event_attr attr_type_raw = { .sample_freq = SAMPLE_FREQ, @@ -210,7 +214,6 @@ static void test_bpf_perf_event(void) .type = PERF_TYPE_RAW, /* Intel Instruction Retired */ .config = 0xc0, - .inherit = 1, }; printf("Test HW_CPU_CYCLES\n"); diff --git a/samples/bpf/tracex6_kern.c b/samples/bpf/tracex6_kern.c index e7d180305974..46c557afac73 100644 --- a/samples/bpf/tracex6_kern.c +++ b/samples/bpf/tracex6_kern.c @@ -15,6 +15,12 @@ struct bpf_map_def SEC("maps") values = { .value_size = sizeof(u64), .max_entries = 64, }; +struct bpf_map_def SEC("maps") values2 = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(int), + .value_size = sizeof(struct bpf_perf_event_value), + .max_entries = 64, +}; SEC("kprobe/htab_map_get_next_key") int bpf_prog1(struct pt_regs *ctx) @@ -37,5 +43,25 @@ int bpf_prog1(struct pt_regs *ctx) return 0; } +SEC("kprobe/htab_map_lookup_elem") +int bpf_prog2(struct pt_regs *ctx) +{ + u32 key = bpf_get_smp_processor_id(); + struct bpf_perf_event_value *val, buf; + int error; + + error = bpf_perf_event_read_value(&counters, key, &buf, sizeof(buf)); + if (error) + return 0; + + val = bpf_map_lookup_elem(&values2, &key); + if (val) + *val = buf; + else + bpf_map_update_elem(&values2, &key, &buf, BPF_NOEXIST); + + return 0; +} + char _license[] SEC("license") = "GPL"; u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/tracex6_user.c b/samples/bpf/tracex6_user.c index a05a99a0752f..3341a96fc046 100644 --- a/samples/bpf/tracex6_user.c +++ b/samples/bpf/tracex6_user.c @@ -22,6 +22,7 @@ static void check_on_cpu(int cpu, struct perf_event_attr *attr) { + struct bpf_perf_event_value value2; int pmu_fd, error = 0; cpu_set_t set; __u64 value; @@ -46,8 +47,18 @@ static void check_on_cpu(int cpu, struct perf_event_attr *attr) fprintf(stderr, "Value missing for CPU %d\n", cpu); error = 1; goto on_exit; + } else { + fprintf(stderr, "CPU %d: %llu\n", cpu, value); + } + /* The above bpf_map_lookup_elem should trigger the second kprobe */ + if (bpf_map_lookup_elem(map_fd[2], &cpu, &value2)) { + fprintf(stderr, "Value2 missing for CPU %d\n", cpu); + error = 1; + goto on_exit; + } else { + fprintf(stderr, "CPU %d: counter: %llu, enabled: %llu, running: %llu\n", cpu, + value2.counter, value2.enabled, value2.running); } - fprintf(stderr, "CPU %d: %llu\n", cpu, value); on_exit: assert(bpf_map_delete_elem(map_fd[0], &cpu) == 0 || error); diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c new file mode 100644 index 000000000000..303e9e7161f3 --- /dev/null +++ b/samples/bpf/xdp_redirect_cpu_kern.c @@ -0,0 +1,609 @@ +/* XDP redirect to CPUs via cpumap (BPF_MAP_TYPE_CPUMAP) + * + * GPLv2, Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc. + */ +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/if_vlan.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/ipv6.h> +#include <uapi/linux/in.h> +#include <uapi/linux/tcp.h> +#include <uapi/linux/udp.h> + +#include <uapi/linux/bpf.h> +#include "bpf_helpers.h" + +#define MAX_CPUS 12 /* WARNING - sync with _user.c */ + +/* Special map type that can XDP_REDIRECT frames to another CPU */ +struct bpf_map_def SEC("maps") cpu_map = { + .type = BPF_MAP_TYPE_CPUMAP, + .key_size = sizeof(u32), + .value_size = sizeof(u32), + .max_entries = MAX_CPUS, +}; + +/* Common stats data record to keep userspace more simple */ +struct datarec { + __u64 processed; + __u64 dropped; + __u64 issue; +}; + +/* Count RX packets, as XDP bpf_prog doesn't get direct TX-success + * feedback. Redirect TX errors can be caught via a tracepoint. + */ +struct bpf_map_def SEC("maps") rx_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = 1, +}; + +/* Used by trace point */ +struct bpf_map_def SEC("maps") redirect_err_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = 2, + /* TODO: have entries for all possible errno's */ +}; + +/* Used by trace point */ +struct bpf_map_def SEC("maps") cpumap_enqueue_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = MAX_CPUS, +}; + +/* Used by trace point */ +struct bpf_map_def SEC("maps") cpumap_kthread_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = 1, +}; + +/* Set of maps controlling available CPU, and for iterating through + * selectable redirect CPUs. + */ +struct bpf_map_def SEC("maps") cpus_available = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u32), + .max_entries = MAX_CPUS, +}; +struct bpf_map_def SEC("maps") cpus_count = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u32), + .max_entries = 1, +}; +struct bpf_map_def SEC("maps") cpus_iterator = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u32), + .max_entries = 1, +}; + +/* Used by trace point */ +struct bpf_map_def SEC("maps") exception_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = 1, +}; + +/* Helper parse functions */ + +/* Parse Ethernet layer 2, extract network layer 3 offset and protocol + * + * Returns false on error and non-supported ether-type + */ +struct vlan_hdr { + __be16 h_vlan_TCI; + __be16 h_vlan_encapsulated_proto; +}; + +static __always_inline +bool parse_eth(struct ethhdr *eth, void *data_end, + u16 *eth_proto, u64 *l3_offset) +{ + u16 eth_type; + u64 offset; + + offset = sizeof(*eth); + if ((void *)eth + offset > data_end) + return false; + + eth_type = eth->h_proto; + + /* Skip non 802.3 Ethertypes */ + if (unlikely(ntohs(eth_type) < ETH_P_802_3_MIN)) + return false; + + /* Handle VLAN tagged packet */ + if (eth_type == htons(ETH_P_8021Q) || eth_type == htons(ETH_P_8021AD)) { + struct vlan_hdr *vlan_hdr; + + vlan_hdr = (void *)eth + offset; + offset += sizeof(*vlan_hdr); + if ((void *)eth + offset > data_end) + return false; + eth_type = vlan_hdr->h_vlan_encapsulated_proto; + } + /* TODO: Handle double VLAN tagged packet */ + + *eth_proto = ntohs(eth_type); + *l3_offset = offset; + return true; +} + +static __always_inline +u16 get_dest_port_ipv4_udp(struct xdp_md *ctx, u64 nh_off) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct iphdr *iph = data + nh_off; + struct udphdr *udph; + u16 dport; + + if (iph + 1 > data_end) + return 0; + if (!(iph->protocol == IPPROTO_UDP)) + return 0; + + udph = (void *)(iph + 1); + if (udph + 1 > data_end) + return 0; + + dport = ntohs(udph->dest); + return dport; +} + +static __always_inline +int get_proto_ipv4(struct xdp_md *ctx, u64 nh_off) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct iphdr *iph = data + nh_off; + + if (iph + 1 > data_end) + return 0; + return iph->protocol; +} + +static __always_inline +int get_proto_ipv6(struct xdp_md *ctx, u64 nh_off) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ipv6hdr *ip6h = data + nh_off; + + if (ip6h + 1 > data_end) + return 0; + return ip6h->nexthdr; +} + +SEC("xdp_cpu_map0") +int xdp_prognum0_no_touch(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct datarec *rec; + u32 *cpu_selected; + u32 cpu_dest; + u32 key = 0; + + /* Only use first entry in cpus_available */ + cpu_selected = bpf_map_lookup_elem(&cpus_available, &key); + if (!cpu_selected) + return XDP_ABORTED; + cpu_dest = *cpu_selected; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map1_touch_data") +int xdp_prognum1_touch_data(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + struct datarec *rec; + u32 *cpu_selected; + u32 cpu_dest; + u16 eth_type; + u32 key = 0; + + /* Only use first entry in cpus_available */ + cpu_selected = bpf_map_lookup_elem(&cpus_available, &key); + if (!cpu_selected) + return XDP_ABORTED; + cpu_dest = *cpu_selected; + + /* Validate packet length is minimum Eth header size */ + if (eth + 1 > data_end) + return XDP_ABORTED; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + /* Read packet data, and use it (drop non 802.3 Ethertypes) */ + eth_type = eth->h_proto; + if (ntohs(eth_type) < ETH_P_802_3_MIN) { + rec->dropped++; + return XDP_DROP; + } + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map2_round_robin") +int xdp_prognum2_round_robin(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + struct datarec *rec; + u32 cpu_dest; + u32 *cpu_lookup; + u32 key0 = 0; + + u32 *cpu_selected; + u32 *cpu_iterator; + u32 *cpu_max; + u32 cpu_idx; + + cpu_max = bpf_map_lookup_elem(&cpus_count, &key0); + if (!cpu_max) + return XDP_ABORTED; + + cpu_iterator = bpf_map_lookup_elem(&cpus_iterator, &key0); + if (!cpu_iterator) + return XDP_ABORTED; + cpu_idx = *cpu_iterator; + + *cpu_iterator += 1; + if (*cpu_iterator == *cpu_max) + *cpu_iterator = 0; + + cpu_selected = bpf_map_lookup_elem(&cpus_available, &cpu_idx); + if (!cpu_selected) + return XDP_ABORTED; + cpu_dest = *cpu_selected; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key0); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map3_proto_separate") +int xdp_prognum3_proto_separate(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + u8 ip_proto = IPPROTO_UDP; + struct datarec *rec; + u16 eth_proto = 0; + u64 l3_offset = 0; + u32 cpu_dest = 0; + u32 cpu_idx = 0; + u32 *cpu_lookup; + u32 key = 0; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + if (!(parse_eth(eth, data_end, ð_proto, &l3_offset))) + return XDP_PASS; /* Just skip */ + + /* Extract L4 protocol */ + switch (eth_proto) { + case ETH_P_IP: + ip_proto = get_proto_ipv4(ctx, l3_offset); + break; + case ETH_P_IPV6: + ip_proto = get_proto_ipv6(ctx, l3_offset); + break; + case ETH_P_ARP: + cpu_idx = 0; /* ARP packet handled on separate CPU */ + break; + default: + cpu_idx = 0; + } + + /* Choose CPU based on L4 protocol */ + switch (ip_proto) { + case IPPROTO_ICMP: + case IPPROTO_ICMPV6: + cpu_idx = 2; + break; + case IPPROTO_TCP: + cpu_idx = 0; + break; + case IPPROTO_UDP: + cpu_idx = 1; + break; + default: + cpu_idx = 0; + } + + cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx); + if (!cpu_lookup) + return XDP_ABORTED; + cpu_dest = *cpu_lookup; + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map4_ddos_filter_pktgen") +int xdp_prognum4_ddos_filter_pktgen(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + u8 ip_proto = IPPROTO_UDP; + struct datarec *rec; + u16 eth_proto = 0; + u64 l3_offset = 0; + u32 cpu_dest = 0; + u32 cpu_idx = 0; + u16 dest_port; + u32 *cpu_lookup; + u32 key = 0; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + if (!(parse_eth(eth, data_end, ð_proto, &l3_offset))) + return XDP_PASS; /* Just skip */ + + /* Extract L4 protocol */ + switch (eth_proto) { + case ETH_P_IP: + ip_proto = get_proto_ipv4(ctx, l3_offset); + break; + case ETH_P_IPV6: + ip_proto = get_proto_ipv6(ctx, l3_offset); + break; + case ETH_P_ARP: + cpu_idx = 0; /* ARP packet handled on separate CPU */ + break; + default: + cpu_idx = 0; + } + + /* Choose CPU based on L4 protocol */ + switch (ip_proto) { + case IPPROTO_ICMP: + case IPPROTO_ICMPV6: + cpu_idx = 2; + break; + case IPPROTO_TCP: + cpu_idx = 0; + break; + case IPPROTO_UDP: + cpu_idx = 1; + /* DDoS filter UDP port 9 (pktgen) */ + dest_port = get_dest_port_ipv4_udp(ctx, l3_offset); + if (dest_port == 9) { + if (rec) + rec->dropped++; + return XDP_DROP; + } + break; + default: + cpu_idx = 0; + } + + cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx); + if (!cpu_lookup) + return XDP_ABORTED; + cpu_dest = *cpu_lookup; + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + + +char _license[] SEC("license") = "GPL"; + +/*** Trace point code ***/ + +/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_redirect/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct xdp_redirect_ctx { + u64 __pad; // First 8 bytes are not accessible by bpf code + int prog_id; // offset:8; size:4; signed:1; + u32 act; // offset:12 size:4; signed:0; + int ifindex; // offset:16 size:4; signed:1; + int err; // offset:20 size:4; signed:1; + int to_ifindex; // offset:24 size:4; signed:1; + u32 map_id; // offset:28 size:4; signed:0; + int map_index; // offset:32 size:4; signed:1; +}; // offset:36 + +enum { + XDP_REDIRECT_SUCCESS = 0, + XDP_REDIRECT_ERROR = 1 +}; + +static __always_inline +int xdp_redirect_collect_stat(struct xdp_redirect_ctx *ctx) +{ + u32 key = XDP_REDIRECT_ERROR; + struct datarec *rec; + int err = ctx->err; + + if (!err) + key = XDP_REDIRECT_SUCCESS; + + rec = bpf_map_lookup_elem(&redirect_err_cnt, &key); + if (!rec) + return 0; + rec->dropped += 1; + + return 0; /* Indicate event was filtered (no further processing)*/ + /* + * Returning 1 here would allow e.g. a perf-record tracepoint + * to see and record these events, but it doesn't work well + * in-practice as stopping perf-record also unload this + * bpf_prog. Plus, there is additional overhead of doing so. + */ +} + +SEC("tracepoint/xdp/xdp_redirect_err") +int trace_xdp_redirect_err(struct xdp_redirect_ctx *ctx) +{ + return xdp_redirect_collect_stat(ctx); +} + +SEC("tracepoint/xdp/xdp_redirect_map_err") +int trace_xdp_redirect_map_err(struct xdp_redirect_ctx *ctx) +{ + return xdp_redirect_collect_stat(ctx); +} + +/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_exception/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct xdp_exception_ctx { + u64 __pad; // First 8 bytes are not accessible by bpf code + int prog_id; // offset:8; size:4; signed:1; + u32 act; // offset:12; size:4; signed:0; + int ifindex; // offset:16; size:4; signed:1; +}; + +SEC("tracepoint/xdp/xdp_exception") +int trace_xdp_exception(struct xdp_exception_ctx *ctx) +{ + struct datarec *rec; + u32 key = 0; + + rec = bpf_map_lookup_elem(&exception_cnt, &key); + if (!rec) + return 1; + rec->dropped += 1; + + return 0; +} + +/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_enqueue/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct cpumap_enqueue_ctx { + u64 __pad; // First 8 bytes are not accessible by bpf code + int map_id; // offset:8; size:4; signed:1; + u32 act; // offset:12; size:4; signed:0; + int cpu; // offset:16; size:4; signed:1; + unsigned int drops; // offset:20; size:4; signed:0; + unsigned int processed; // offset:24; size:4; signed:0; + int to_cpu; // offset:28; size:4; signed:1; +}; + +SEC("tracepoint/xdp/xdp_cpumap_enqueue") +int trace_xdp_cpumap_enqueue(struct cpumap_enqueue_ctx *ctx) +{ + u32 to_cpu = ctx->to_cpu; + struct datarec *rec; + + if (to_cpu >= MAX_CPUS) + return 1; + + rec = bpf_map_lookup_elem(&cpumap_enqueue_cnt, &to_cpu); + if (!rec) + return 0; + rec->processed += ctx->processed; + rec->dropped += ctx->drops; + + /* Record bulk events, then userspace can calc average bulk size */ + if (ctx->processed > 0) + rec->issue += 1; + + /* Inception: It's possible to detect overload situations, via + * this tracepoint. This can be used for creating a feedback + * loop to XDP, which can take appropriate actions to mitigate + * this overload situation. + */ + return 0; +} + +/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_kthread/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct cpumap_kthread_ctx { + u64 __pad; // First 8 bytes are not accessible by bpf code + int map_id; // offset:8; size:4; signed:1; + u32 act; // offset:12; size:4; signed:0; + int cpu; // offset:16; size:4; signed:1; + unsigned int drops; // offset:20; size:4; signed:0; + unsigned int processed; // offset:24; size:4; signed:0; + int sched; // offset:28; size:4; signed:1; +}; + +SEC("tracepoint/xdp/xdp_cpumap_kthread") +int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx) +{ + struct datarec *rec; + u32 key = 0; + + rec = bpf_map_lookup_elem(&cpumap_kthread_cnt, &key); + if (!rec) + return 0; + rec->processed += ctx->processed; + rec->dropped += ctx->drops; + + /* Count times kthread yielded CPU via schedule call */ + if (ctx->sched) + rec->issue++; + + return 0; +} diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c new file mode 100644 index 000000000000..35fec9fecb57 --- /dev/null +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -0,0 +1,697 @@ +/* GPLv2 Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc. + */ +static const char *__doc__ = + " XDP redirect with a CPU-map type \"BPF_MAP_TYPE_CPUMAP\""; + +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <unistd.h> +#include <locale.h> +#include <sys/resource.h> +#include <getopt.h> +#include <net/if.h> +#include <time.h> + +#include <arpa/inet.h> +#include <linux/if_link.h> + +#define MAX_CPUS 12 /* WARNING - sync with _kern.c */ + +/* How many xdp_progs are defined in _kern.c */ +#define MAX_PROG 5 + +/* Wanted to get rid of bpf_load.h and fake-"libbpf.h" (and instead + * use bpf/libbpf.h), but cannot as (currently) needed for XDP + * attaching to a device via set_link_xdp_fd() + */ +#include "libbpf.h" +#include "bpf_load.h" + +#include "bpf_util.h" + +static int ifindex = -1; +static char ifname_buf[IF_NAMESIZE]; +static char *ifname; + +static __u32 xdp_flags; + +/* Exit return codes */ +#define EXIT_OK 0 +#define EXIT_FAIL 1 +#define EXIT_FAIL_OPTION 2 +#define EXIT_FAIL_XDP 3 +#define EXIT_FAIL_BPF 4 +#define EXIT_FAIL_MEM 5 + +static const struct option long_options[] = { + {"help", no_argument, NULL, 'h' }, + {"dev", required_argument, NULL, 'd' }, + {"skb-mode", no_argument, NULL, 'S' }, + {"debug", no_argument, NULL, 'D' }, + {"sec", required_argument, NULL, 's' }, + {"prognum", required_argument, NULL, 'p' }, + {"qsize", required_argument, NULL, 'q' }, + {"cpu", required_argument, NULL, 'c' }, + {"stress-mode", no_argument, NULL, 'x' }, + {"no-separators", no_argument, NULL, 'z' }, + {0, 0, NULL, 0 } +}; + +static void int_exit(int sig) +{ + fprintf(stderr, + "Interrupted: Removing XDP program on ifindex:%d device:%s\n", + ifindex, ifname); + if (ifindex > -1) + set_link_xdp_fd(ifindex, -1, xdp_flags); + exit(EXIT_OK); +} + +static void usage(char *argv[]) +{ + int i; + + printf("\nDOCUMENTATION:\n%s\n", __doc__); + printf("\n"); + printf(" Usage: %s (options-see-below)\n", argv[0]); + printf(" Listing options:\n"); + for (i = 0; long_options[i].name != 0; i++) { + printf(" --%-12s", long_options[i].name); + if (long_options[i].flag != NULL) + printf(" flag (internal value:%d)", + *long_options[i].flag); + else + printf(" short-option: -%c", + long_options[i].val); + printf("\n"); + } + printf("\n"); +} + +/* gettime returns the current time of day in nanoseconds. + * Cost: clock_gettime (ns) => 26ns (CLOCK_MONOTONIC) + * clock_gettime (ns) => 9ns (CLOCK_MONOTONIC_COARSE) + */ +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ +static __u64 gettime(void) +{ + struct timespec t; + int res; + + res = clock_gettime(CLOCK_MONOTONIC, &t); + if (res < 0) { + fprintf(stderr, "Error with gettimeofday! (%i)\n", res); + exit(EXIT_FAIL); + } + return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec; +} + +/* Common stats data record shared with _kern.c */ +struct datarec { + __u64 processed; + __u64 dropped; + __u64 issue; +}; +struct record { + __u64 timestamp; + struct datarec total; + struct datarec *cpu; +}; +struct stats_record { + struct record rx_cnt; + struct record redir_err; + struct record kthread; + struct record exception; + struct record enq[MAX_CPUS]; +}; + +static bool map_collect_percpu(int fd, __u32 key, struct record *rec) +{ + /* For percpu maps, userspace gets a value per possible CPU */ + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct datarec values[nr_cpus]; + __u64 sum_processed = 0; + __u64 sum_dropped = 0; + __u64 sum_issue = 0; + int i; + + if ((bpf_map_lookup_elem(fd, &key, values)) != 0) { + fprintf(stderr, + "ERR: bpf_map_lookup_elem failed key:0x%X\n", key); + return false; + } + /* Get time as close as possible to reading map contents */ + rec->timestamp = gettime(); + + /* Record and sum values from each CPU */ + for (i = 0; i < nr_cpus; i++) { + rec->cpu[i].processed = values[i].processed; + sum_processed += values[i].processed; + rec->cpu[i].dropped = values[i].dropped; + sum_dropped += values[i].dropped; + rec->cpu[i].issue = values[i].issue; + sum_issue += values[i].issue; + } + rec->total.processed = sum_processed; + rec->total.dropped = sum_dropped; + rec->total.issue = sum_issue; + return true; +} + +static struct datarec *alloc_record_per_cpu(void) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct datarec *array; + size_t size; + + size = sizeof(struct datarec) * nr_cpus; + array = malloc(size); + memset(array, 0, size); + if (!array) { + fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus); + exit(EXIT_FAIL_MEM); + } + return array; +} + +static struct stats_record *alloc_stats_record(void) +{ + struct stats_record *rec; + int i; + + rec = malloc(sizeof(*rec)); + memset(rec, 0, sizeof(*rec)); + if (!rec) { + fprintf(stderr, "Mem alloc error\n"); + exit(EXIT_FAIL_MEM); + } + rec->rx_cnt.cpu = alloc_record_per_cpu(); + rec->redir_err.cpu = alloc_record_per_cpu(); + rec->kthread.cpu = alloc_record_per_cpu(); + rec->exception.cpu = alloc_record_per_cpu(); + for (i = 0; i < MAX_CPUS; i++) + rec->enq[i].cpu = alloc_record_per_cpu(); + + return rec; +} + +static void free_stats_record(struct stats_record *r) +{ + int i; + + for (i = 0; i < MAX_CPUS; i++) + free(r->enq[i].cpu); + free(r->exception.cpu); + free(r->kthread.cpu); + free(r->redir_err.cpu); + free(r->rx_cnt.cpu); + free(r); +} + +static double calc_period(struct record *r, struct record *p) +{ + double period_ = 0; + __u64 period = 0; + + period = r->timestamp - p->timestamp; + if (period > 0) + period_ = ((double) period / NANOSEC_PER_SEC); + + return period_; +} + +static __u64 calc_pps(struct datarec *r, struct datarec *p, double period_) +{ + __u64 packets = 0; + __u64 pps = 0; + + if (period_ > 0) { + packets = r->processed - p->processed; + pps = packets / period_; + } + return pps; +} + +static __u64 calc_drop_pps(struct datarec *r, struct datarec *p, double period_) +{ + __u64 packets = 0; + __u64 pps = 0; + + if (period_ > 0) { + packets = r->dropped - p->dropped; + pps = packets / period_; + } + return pps; +} + +static __u64 calc_errs_pps(struct datarec *r, + struct datarec *p, double period_) +{ + __u64 packets = 0; + __u64 pps = 0; + + if (period_ > 0) { + packets = r->issue - p->issue; + pps = packets / period_; + } + return pps; +} + +static void stats_print(struct stats_record *stats_rec, + struct stats_record *stats_prev, + int prog_num) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + double pps = 0, drop = 0, err = 0; + struct record *rec, *prev; + int to_cpu; + double t; + int i; + + /* Header */ + printf("Running XDP/eBPF prog_num:%d\n", prog_num); + printf("%-15s %-7s %-14s %-11s %-9s\n", + "XDP-cpumap", "CPU:to", "pps", "drop-pps", "extra-info"); + + /* XDP rx_cnt */ + { + char *fmt_rx = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n"; + char *fm2_rx = "%-15s %-7s %'-14.0f %'-11.0f\n"; + char *errstr = ""; + + rec = &stats_rec->rx_cnt; + prev = &stats_prev->rx_cnt; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + err = calc_errs_pps(r, p, t); + if (err > 0) + errstr = "cpu-dest/err"; + if (pps > 0) + printf(fmt_rx, "XDP-RX", + i, pps, drop, err, errstr); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + err = calc_errs_pps(&rec->total, &prev->total, t); + printf(fm2_rx, "XDP-RX", "total", pps, drop); + } + + /* cpumap enqueue stats */ + for (to_cpu = 0; to_cpu < MAX_CPUS; to_cpu++) { + char *fmt = "%-15s %3d:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n"; + char *fm2 = "%-15s %3s:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n"; + char *errstr = ""; + + rec = &stats_rec->enq[to_cpu]; + prev = &stats_prev->enq[to_cpu]; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + err = calc_errs_pps(r, p, t); + if (err > 0) { + errstr = "bulk-average"; + err = pps / err; /* calc average bulk size */ + } + if (pps > 0) + printf(fmt, "cpumap-enqueue", + i, to_cpu, pps, drop, err, errstr); + } + pps = calc_pps(&rec->total, &prev->total, t); + if (pps > 0) { + drop = calc_drop_pps(&rec->total, &prev->total, t); + err = calc_errs_pps(&rec->total, &prev->total, t); + if (err > 0) { + errstr = "bulk-average"; + err = pps / err; /* calc average bulk size */ + } + printf(fm2, "cpumap-enqueue", + "sum", to_cpu, pps, drop, err, errstr); + } + } + + /* cpumap kthread stats */ + { + char *fmt_k = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n"; + char *fm2_k = "%-15s %-7s %'-14.0f %'-11.0f %'-10.0f %s\n"; + char *e_str = ""; + + rec = &stats_rec->kthread; + prev = &stats_prev->kthread; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + err = calc_errs_pps(r, p, t); + if (err > 0) + e_str = "sched"; + if (pps > 0) + printf(fmt_k, "cpumap_kthread", + i, pps, drop, err, e_str); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + err = calc_errs_pps(&rec->total, &prev->total, t); + if (err > 0) + e_str = "sched-sum"; + printf(fm2_k, "cpumap_kthread", "total", pps, drop, err, e_str); + } + + /* XDP redirect err tracepoints (very unlikely) */ + { + char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n"; + char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n"; + + rec = &stats_rec->redir_err; + prev = &stats_prev->redir_err; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + if (pps > 0) + printf(fmt_err, "redirect_err", i, pps, drop); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + printf(fm2_err, "redirect_err", "total", pps, drop); + } + + /* XDP general exception tracepoints */ + { + char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n"; + char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n"; + + rec = &stats_rec->exception; + prev = &stats_prev->exception; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + if (pps > 0) + printf(fmt_err, "xdp_exception", i, pps, drop); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + printf(fm2_err, "xdp_exception", "total", pps, drop); + } + + printf("\n"); + fflush(stdout); +} + +static void stats_collect(struct stats_record *rec) +{ + int fd, i; + + fd = map_fd[1]; /* map: rx_cnt */ + map_collect_percpu(fd, 0, &rec->rx_cnt); + + fd = map_fd[2]; /* map: redirect_err_cnt */ + map_collect_percpu(fd, 1, &rec->redir_err); + + fd = map_fd[3]; /* map: cpumap_enqueue_cnt */ + for (i = 0; i < MAX_CPUS; i++) + map_collect_percpu(fd, i, &rec->enq[i]); + + fd = map_fd[4]; /* map: cpumap_kthread_cnt */ + map_collect_percpu(fd, 0, &rec->kthread); + + fd = map_fd[8]; /* map: exception_cnt */ + map_collect_percpu(fd, 0, &rec->exception); +} + + +/* Pointer swap trick */ +static inline void swap(struct stats_record **a, struct stats_record **b) +{ + struct stats_record *tmp; + + tmp = *a; + *a = *b; + *b = tmp; +} + +static int create_cpu_entry(__u32 cpu, __u32 queue_size, + __u32 avail_idx, bool new) +{ + __u32 curr_cpus_count = 0; + __u32 key = 0; + int ret; + + /* Add a CPU entry to cpumap, as this allocate a cpu entry in + * the kernel for the cpu. + */ + ret = bpf_map_update_elem(map_fd[0], &cpu, &queue_size, 0); + if (ret) { + fprintf(stderr, "Create CPU entry failed (err:%d)\n", ret); + exit(EXIT_FAIL_BPF); + } + + /* Inform bpf_prog's that a new CPU is available to select + * from via some control maps. + */ + /* map_fd[5] = cpus_available */ + ret = bpf_map_update_elem(map_fd[5], &avail_idx, &cpu, 0); + if (ret) { + fprintf(stderr, "Add to avail CPUs failed\n"); + exit(EXIT_FAIL_BPF); + } + + /* When not replacing/updating existing entry, bump the count */ + /* map_fd[6] = cpus_count */ + ret = bpf_map_lookup_elem(map_fd[6], &key, &curr_cpus_count); + if (ret) { + fprintf(stderr, "Failed reading curr cpus_count\n"); + exit(EXIT_FAIL_BPF); + } + if (new) { + curr_cpus_count++; + ret = bpf_map_update_elem(map_fd[6], &key, &curr_cpus_count, 0); + if (ret) { + fprintf(stderr, "Failed write curr cpus_count\n"); + exit(EXIT_FAIL_BPF); + } + } + /* map_fd[7] = cpus_iterator */ + printf("%s CPU:%u as idx:%u queue_size:%d (total cpus_count:%u)\n", + new ? "Add-new":"Replace", cpu, avail_idx, + queue_size, curr_cpus_count); + + return 0; +} + +/* CPUs are zero-indexed. Thus, add a special sentinel default value + * in map cpus_available to mark CPU index'es not configured + */ +static void mark_cpus_unavailable(void) +{ + __u32 invalid_cpu = MAX_CPUS; + int ret, i; + + for (i = 0; i < MAX_CPUS; i++) { + /* map_fd[5] = cpus_available */ + ret = bpf_map_update_elem(map_fd[5], &i, &invalid_cpu, 0); + if (ret) { + fprintf(stderr, "Failed marking CPU unavailable\n"); + exit(EXIT_FAIL_BPF); + } + } +} + +/* Stress cpumap management code by concurrently changing underlying cpumap */ +static void stress_cpumap(void) +{ + /* Changing qsize will cause kernel to free and alloc a new + * bpf_cpu_map_entry, with an associated/complicated tear-down + * procedure. + */ + create_cpu_entry(1, 1024, 0, false); + create_cpu_entry(1, 128, 0, false); + create_cpu_entry(1, 16000, 0, false); +} + +static void stats_poll(int interval, bool use_separators, int prog_num, + bool stress_mode) +{ + struct stats_record *record, *prev; + + record = alloc_stats_record(); + prev = alloc_stats_record(); + stats_collect(record); + + /* Trick to pretty printf with thousands separators use %' */ + if (use_separators) + setlocale(LC_NUMERIC, "en_US"); + + while (1) { + swap(&prev, &record); + stats_collect(record); + stats_print(record, prev, prog_num); + sleep(interval); + if (stress_mode) + stress_cpumap(); + } + + free_stats_record(record); + free_stats_record(prev); +} + +int main(int argc, char **argv) +{ + struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; + bool use_separators = true; + bool stress_mode = false; + char filename[256]; + bool debug = false; + int added_cpus = 0; + int longindex = 0; + int interval = 2; + int prog_num = 0; + int add_cpu = -1; + __u32 qsize; + int opt; + + /* Notice: choosing he queue size is very important with the + * ixgbe driver, because it's driver page recycling trick is + * dependend on pages being returned quickly. The number of + * out-standing packets in the system must be less-than 2x + * RX-ring size. + */ + qsize = 128+64; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + if (load_bpf_file(filename)) { + fprintf(stderr, "ERR in load_bpf_file(): %s", bpf_log_buf); + return EXIT_FAIL; + } + + if (!prog_fd[0]) { + fprintf(stderr, "ERR: load_bpf_file: %s\n", strerror(errno)); + return EXIT_FAIL; + } + + mark_cpus_unavailable(); + + /* Parse commands line args */ + while ((opt = getopt_long(argc, argv, "hSd:", + long_options, &longindex)) != -1) { + switch (opt) { + case 'd': + if (strlen(optarg) >= IF_NAMESIZE) { + fprintf(stderr, "ERR: --dev name too long\n"); + goto error; + } + ifname = (char *)&ifname_buf; + strncpy(ifname, optarg, IF_NAMESIZE); + ifindex = if_nametoindex(ifname); + if (ifindex == 0) { + fprintf(stderr, + "ERR: --dev name unknown err(%d):%s\n", + errno, strerror(errno)); + goto error; + } + break; + case 's': + interval = atoi(optarg); + break; + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'D': + debug = true; + break; + case 'x': + stress_mode = true; + break; + case 'z': + use_separators = false; + break; + case 'p': + /* Selecting eBPF prog to load */ + prog_num = atoi(optarg); + if (prog_num < 0 || prog_num >= MAX_PROG) { + fprintf(stderr, + "--prognum too large err(%d):%s\n", + errno, strerror(errno)); + goto error; + } + break; + case 'c': + /* Add multiple CPUs */ + add_cpu = strtoul(optarg, NULL, 0); + if (add_cpu >= MAX_CPUS) { + fprintf(stderr, + "--cpu nr too large for cpumap err(%d):%s\n", + errno, strerror(errno)); + goto error; + } + create_cpu_entry(add_cpu, qsize, added_cpus, true); + added_cpus++; + break; + case 'q': + qsize = atoi(optarg); + break; + case 'h': + error: + default: + usage(argv); + return EXIT_FAIL_OPTION; + } + } + /* Required option */ + if (ifindex == -1) { + fprintf(stderr, "ERR: required option --dev missing\n"); + usage(argv); + return EXIT_FAIL_OPTION; + } + /* Required option */ + if (add_cpu == -1) { + fprintf(stderr, "ERR: required option --cpu missing\n"); + fprintf(stderr, " Specify multiple --cpu option to add more\n"); + usage(argv); + return EXIT_FAIL_OPTION; + } + + /* Remove XDP program when program is interrupted */ + signal(SIGINT, int_exit); + + if (set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) { + fprintf(stderr, "link set xdp fd failed\n"); + return EXIT_FAIL_XDP; + } + + if (debug) { + printf("Debug-mode reading trace pipe (fix #define DEBUG)\n"); + read_trace_pipe(); + } + + stats_poll(interval, use_separators, prog_num, stress_mode); + return EXIT_OK; +} diff --git a/security/security.c b/security/security.c index 4bf0f571b4ef..1cd8526cb0b7 100644 --- a/security/security.c +++ b/security/security.c @@ -12,6 +12,7 @@ * (at your option) any later version. */ +#include <linux/bpf.h> #include <linux/capability.h> #include <linux/dcache.h> #include <linux/module.h> @@ -1703,3 +1704,34 @@ int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule, actx); } #endif /* CONFIG_AUDIT */ + +#ifdef CONFIG_BPF_SYSCALL +int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) +{ + return call_int_hook(bpf, 0, cmd, attr, size); +} +int security_bpf_map(struct bpf_map *map, fmode_t fmode) +{ + return call_int_hook(bpf_map, 0, map, fmode); +} +int security_bpf_prog(struct bpf_prog *prog) +{ + return call_int_hook(bpf_prog, 0, prog); +} +int security_bpf_map_alloc(struct bpf_map *map) +{ + return call_int_hook(bpf_map_alloc_security, 0, map); +} +int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +{ + return call_int_hook(bpf_prog_alloc_security, 0, aux); +} +void security_bpf_map_free(struct bpf_map *map) +{ + call_void_hook(bpf_map_free_security, map); +} +void security_bpf_prog_free(struct bpf_prog_aux *aux) +{ + call_void_hook(bpf_prog_free_security, aux); +} +#endif /* CONFIG_BPF_SYSCALL */ diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index f5d304736852..2e3a627fc0b1 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -85,6 +85,7 @@ #include <linux/export.h> #include <linux/msg.h> #include <linux/shm.h> +#include <linux/bpf.h> #include "avc.h" #include "objsec.h" @@ -1814,6 +1815,10 @@ static inline int file_path_has_perm(const struct cred *cred, return inode_has_perm(cred, file_inode(file), av, &ad); } +#ifdef CONFIG_BPF_SYSCALL +static int bpf_fd_pass(struct file *file, u32 sid); +#endif + /* Check whether a task can use an open file descriptor to access an inode in a given way. Check access to the descriptor itself, and then use dentry_has_perm to @@ -1844,6 +1849,12 @@ static int file_has_perm(const struct cred *cred, goto out; } +#ifdef CONFIG_BPF_SYSCALL + rc = bpf_fd_pass(file, cred_sid(cred)); + if (rc) + return rc; +#endif + /* av is zero if only checking access to the descriptor. */ rc = 0; if (av) @@ -2164,6 +2175,12 @@ static int selinux_binder_transfer_file(struct task_struct *from, return rc; } +#ifdef CONFIG_BPF_SYSCALL + rc = bpf_fd_pass(file, sid); + if (rc) + return rc; +#endif + if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; @@ -6252,6 +6269,139 @@ static void selinux_ib_free_security(void *ib_sec) } #endif +#ifdef CONFIG_BPF_SYSCALL +static int selinux_bpf(int cmd, union bpf_attr *attr, + unsigned int size) +{ + u32 sid = current_sid(); + int ret; + + switch (cmd) { + case BPF_MAP_CREATE: + ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__MAP_CREATE, + NULL); + break; + case BPF_PROG_LOAD: + ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__PROG_LOAD, + NULL); + break; + default: + ret = 0; + break; + } + + return ret; +} + +static u32 bpf_map_fmode_to_av(fmode_t fmode) +{ + u32 av = 0; + + if (fmode & FMODE_READ) + av |= BPF__MAP_READ; + if (fmode & FMODE_WRITE) + av |= BPF__MAP_WRITE; + return av; +} + +/* This function will check the file pass through unix socket or binder to see + * if it is a bpf related object. And apply correspinding checks on the bpf + * object based on the type. The bpf maps and programs, not like other files and + * socket, are using a shared anonymous inode inside the kernel as their inode. + * So checking that inode cannot identify if the process have privilege to + * access the bpf object and that's why we have to add this additional check in + * selinux_file_receive and selinux_binder_transfer_files. + */ +static int bpf_fd_pass(struct file *file, u32 sid) +{ + struct bpf_security_struct *bpfsec; + struct bpf_prog *prog; + struct bpf_map *map; + int ret; + + if (file->f_op == &bpf_map_fops) { + map = file->private_data; + bpfsec = map->security; + ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, + bpf_map_fmode_to_av(file->f_mode), NULL); + if (ret) + return ret; + } else if (file->f_op == &bpf_prog_fops) { + prog = file->private_data; + bpfsec = prog->aux->security; + ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, + BPF__PROG_RUN, NULL); + if (ret) + return ret; + } + return 0; +} + +static int selinux_bpf_map(struct bpf_map *map, fmode_t fmode) +{ + u32 sid = current_sid(); + struct bpf_security_struct *bpfsec; + + bpfsec = map->security; + return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, + bpf_map_fmode_to_av(fmode), NULL); +} + +static int selinux_bpf_prog(struct bpf_prog *prog) +{ + u32 sid = current_sid(); + struct bpf_security_struct *bpfsec; + + bpfsec = prog->aux->security; + return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, + BPF__PROG_RUN, NULL); +} + +static int selinux_bpf_map_alloc(struct bpf_map *map) +{ + struct bpf_security_struct *bpfsec; + + bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); + if (!bpfsec) + return -ENOMEM; + + bpfsec->sid = current_sid(); + map->security = bpfsec; + + return 0; +} + +static void selinux_bpf_map_free(struct bpf_map *map) +{ + struct bpf_security_struct *bpfsec = map->security; + + map->security = NULL; + kfree(bpfsec); +} + +static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux) +{ + struct bpf_security_struct *bpfsec; + + bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); + if (!bpfsec) + return -ENOMEM; + + bpfsec->sid = current_sid(); + aux->security = bpfsec; + + return 0; +} + +static void selinux_bpf_prog_free(struct bpf_prog_aux *aux) +{ + struct bpf_security_struct *bpfsec = aux->security; + + aux->security = NULL; + kfree(bpfsec); +} +#endif + static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(binder_set_context_mgr, selinux_binder_set_context_mgr), LSM_HOOK_INIT(binder_transaction, selinux_binder_transaction), @@ -6471,6 +6621,16 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(audit_rule_match, selinux_audit_rule_match), LSM_HOOK_INIT(audit_rule_free, selinux_audit_rule_free), #endif + +#ifdef CONFIG_BPF_SYSCALL + LSM_HOOK_INIT(bpf, selinux_bpf), + LSM_HOOK_INIT(bpf_map, selinux_bpf_map), + LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), + LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc), + LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc), + LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free), + LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free), +#endif }; static __init int selinux_init(void) diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index 35ffb29a69cb..0a7023b5f000 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -237,6 +237,8 @@ struct security_class_mapping secclass_map[] = { { "access", NULL } }, { "infiniband_endport", { "manage_subnet", NULL } }, + { "bpf", + {"map_create", "map_read", "map_write", "prog_load", "prog_run"} }, { NULL } }; diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index 1649cd18eb0b..3d54468ce334 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -150,6 +150,10 @@ struct pkey_security_struct { u32 sid; /* SID of pkey */ }; +struct bpf_security_struct { + u32 sid; /*SID of bpf obj creater*/ +}; + extern unsigned int selinux_checkreqprot; #endif /* _SELINUX_OBJSEC_H_ */ diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 57fc4b9924ea..3968f0bd37db 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -11,7 +11,7 @@ SYNOPSIS ======== | **bpftool** prog show [*PROG*] -| **bpftool** prog dump xlated *PROG* file *FILE* +| **bpftool** prog dump xlated *PROG* [file *FILE*] [opcodes] | **bpftool** prog dump jited *PROG* [file *FILE*] [opcodes] | **bpftool** prog pin *PROG* *FILE* | **bpftool** prog help @@ -28,9 +28,12 @@ DESCRIPTION Output will start with program ID followed by program type and zero or more named attributes (depending on kernel version). - **bpftool prog dump xlated** *PROG* **file** *FILE* - Dump eBPF instructions of the program from the kernel to a - file. + **bpftool prog dump xlated** *PROG* [**file** *FILE*] [**opcodes**] + Dump eBPF instructions of the program from the kernel. + If *FILE* is specified image will be written to a file, + otherwise it will be disassembled and printed to stdout. + + **opcodes** controls if raw opcodes will be printed. **bpftool prog dump jited** *PROG* [**file** *FILE*] [**opcodes**] Dump jited image (host machine code) of the program. @@ -52,7 +55,7 @@ EXAMPLES **# bpftool prog show** :: - 10: xdp name some_prog tag 00:5a:3d:21:23:62:0c:8b + 10: xdp name some_prog tag 005a3d2123620c8b loaded_at Sep 29/20:11 uid 0 xlated 528B jited 370B memlock 4096B map_ids 10 diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 8705ee44664d..4f339824ca57 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -51,7 +51,7 @@ CC = gcc CFLAGS += -O2 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow -CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf +CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf -I$(srctree)/kernel/bpf/ LIBS = -lelf -lbfd -lopcodes $(LIBBPF) include $(wildcard *.d) @@ -59,7 +59,10 @@ include $(wildcard *.d) all: $(OUTPUT)bpftool SRCS=$(wildcard *.c) -OBJS=$(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) +OBJS=$(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o + +$(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c + $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $< $(OUTPUT)bpftool: $(OBJS) $(LIBBPF) $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^ $(LIBS) diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 85d2d7870a58..844e4ef6db56 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -36,11 +36,12 @@ #ifndef __BPF_TOOL_H #define __BPF_TOOL_H +/* BFD and kernel.h both define GCC_VERSION, differently */ +#undef GCC_VERSION #include <stdbool.h> #include <stdio.h> #include <linux/bpf.h> - -#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) +#include <linux/kernel.h> #define err(msg...) fprintf(stderr, "Error: " msg) #define warn(msg...) fprintf(stderr, "Warning: " msg) @@ -48,17 +49,11 @@ #define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) -#define min(a, b) \ - ({ typeof(a) _a = (a); typeof(b) _b = (b); _a > _b ? _b : _a; }) -#define max(a, b) \ - ({ typeof(a) _a = (a); typeof(b) _b = (b); _a < _b ? _b : _a; }) - #define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); }) #define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); }) #define BAD_ARG() ({ err("what is '%s'?\n", *argv); -1; }) -#define BPF_TAG_FMT "%02hhx:%02hhx:%02hhx:%02hhx:" \ - "%02hhx:%02hhx:%02hhx:%02hhx" +#define BPF_TAG_FMT "%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx" #define HELP_SPEC_PROGRAM \ "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }" diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 421ba89ce86a..d60f5307b6e2 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -35,6 +35,7 @@ #include <errno.h> #include <fcntl.h> +#include <stdarg.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -46,6 +47,7 @@ #include <bpf.h> #include "main.h" +#include "disasm.h" static const char * const prog_type_name[] = { [BPF_PROG_TYPE_UNSPEC] = "unspec", @@ -222,7 +224,7 @@ static int show_prog(int fd) printf("name %s ", info.name); printf("tag "); - print_hex(info.tag, BPF_TAG_SIZE, ":"); + print_hex(info.tag, BPF_TAG_SIZE, ""); printf("\n"); if (info.load_time) { @@ -297,11 +299,39 @@ static int do_show(int argc, char **argv) return 0; } +static void print_insn(struct bpf_verifier_env *env, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vprintf(fmt, args); + va_end(args); +} + +static void dump_xlated(void *buf, unsigned int len, bool opcodes) +{ + struct bpf_insn *insn = buf; + unsigned int i; + + for (i = 0; i < len / sizeof(*insn); i++) { + printf("% 4d: ", i); + print_bpf_insn(print_insn, NULL, insn + i, true); + + if (opcodes) { + printf(" "); + print_hex(insn + i, 8, " "); + printf("\n"); + } + + if (insn[i].code == (BPF_LD | BPF_IMM | BPF_DW)) + i++; + } +} + static int do_dump(int argc, char **argv) { struct bpf_prog_info info = {}; __u32 len = sizeof(info); - bool can_disasm = false; unsigned int buf_size; char *filepath = NULL; bool opcodes = false; @@ -315,7 +345,6 @@ static int do_dump(int argc, char **argv) if (is_prefix(*argv, "jited")) { member_len = &info.jited_prog_len; member_ptr = &info.jited_prog_insns; - can_disasm = true; } else if (is_prefix(*argv, "xlated")) { member_len = &info.xlated_prog_len; member_ptr = &info.xlated_prog_insns; @@ -346,10 +375,6 @@ static int do_dump(int argc, char **argv) NEXT_ARG(); } - if (!filepath && !can_disasm) { - err("expected 'file' got %s\n", *argv); - return -1; - } if (argc) { usage(); return -1; @@ -409,7 +434,10 @@ static int do_dump(int argc, char **argv) goto err_free; } } else { - disasm_print_insn(buf, *member_len, opcodes); + if (member_len == &info.jited_prog_len) + disasm_print_insn(buf, *member_len, opcodes); + else + dump_xlated(buf, *member_len, opcodes); } free(buf); @@ -430,7 +458,7 @@ static int do_help(int argc, char **argv) { fprintf(stderr, "Usage: %s %s show [PROG]\n" - " %s %s dump xlated PROG file FILE\n" + " %s %s dump xlated PROG [file FILE] [opcodes]\n" " %s %s dump jited PROG [file FILE] [opcodes]\n" " %s %s pin PROG FILE\n" " %s %s help\n" diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index cb2b9f95160a..fa93033dc521 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -112,6 +112,7 @@ enum bpf_map_type { BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_DEVMAP, BPF_MAP_TYPE_SOCKMAP, + BPF_MAP_TYPE_CPUMAP, }; enum bpf_prog_type { @@ -230,7 +231,7 @@ union bpf_attr { __u32 numa_node; /* numa node (effective only if * BPF_F_NUMA_NODE is set). */ - __u8 map_name[BPF_OBJ_NAME_LEN]; + char map_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -253,7 +254,7 @@ union bpf_attr { __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ __u32 prog_flags; - __u8 prog_name[BPF_OBJ_NAME_LEN]; + char prog_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -697,7 +698,9 @@ union bpf_attr { FN(redirect_map), \ FN(sk_redirect_map), \ FN(sock_map_update), \ - FN(xdp_adjust_meta), + FN(xdp_adjust_meta), \ + FN(perf_event_read_value), \ + FN(perf_prog_read_value), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -869,7 +872,7 @@ struct bpf_prog_info { __u32 created_by_uid; __u32 nr_map_ids; __aligned_u64 map_ids; - __u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); struct bpf_map_info { @@ -879,7 +882,7 @@ struct bpf_map_info { __u32 value_size; __u32 max_entries; __u32 map_flags; - __u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); /* User bpf_sock_ops struct to access socket values and specify request ops diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 924af8d79bde..2e7880ea0add 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -12,7 +12,7 @@ CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../i LDLIBS += -lcap -lelf TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ - test_align + test_align test_verifier_log TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \ test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \ diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index a56053db26f5..e25dbf6038cf 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -72,6 +72,12 @@ static int (*bpf_sk_redirect_map)(void *map, int key, int flags) = static int (*bpf_sock_map_update)(void *map, void *key, void *value, unsigned long long flags) = (void *) BPF_FUNC_sock_map_update; +static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags, + void *buf, unsigned int buf_size) = + (void *) BPF_FUNC_perf_event_read_value; +static int (*bpf_perf_prog_read_value)(void *ctx, void *buf, + unsigned int buf_size) = + (void *) BPF_FUNC_perf_prog_read_value; /* llvm builtin functions that eBPF C program may use to diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index fe3a443a1102..896f23cfe918 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -1033,6 +1033,51 @@ static void test_map_parallel(void) assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT); } +static void test_map_rdonly(void) +{ + int i, fd, key = 0, value = 0; + + fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), + MAP_SIZE, map_flags | BPF_F_RDONLY); + if (fd < 0) { + printf("Failed to create map for read only test '%s'!\n", + strerror(errno)); + exit(1); + } + + key = 1; + value = 1234; + /* Insert key=1 element. */ + assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == -1 && + errno == EPERM); + + /* Check that key=2 is not found. */ + assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT); + assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == ENOENT); +} + +static void test_map_wronly(void) +{ + int i, fd, key = 0, value = 0; + + fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), + MAP_SIZE, map_flags | BPF_F_WRONLY); + if (fd < 0) { + printf("Failed to create map for read only test '%s'!\n", + strerror(errno)); + exit(1); + } + + key = 1; + value = 1234; + /* Insert key=1 element. */ + assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0) + + /* Check that key=2 is not found. */ + assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == EPERM); + assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == EPERM); +} + static void run_all_tests(void) { test_hashmap(0, NULL); @@ -1050,6 +1095,9 @@ static void run_all_tests(void) test_map_large(); test_map_parallel(); test_map_stress(); + + test_map_rdonly(); + test_map_wronly(); } int main(void) diff --git a/tools/testing/selftests/bpf/test_verifier_log.c b/tools/testing/selftests/bpf/test_verifier_log.c new file mode 100644 index 000000000000..3cc0b561489e --- /dev/null +++ b/tools/testing/selftests/bpf/test_verifier_log.c @@ -0,0 +1,171 @@ +#include <errno.h> +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> + +#include <linux/bpf.h> +#include <linux/filter.h> +#include <linux/unistd.h> + +#include <bpf/bpf.h> + +#define LOG_SIZE (1 << 20) + +#define err(str...) printf("ERROR: " str) + +static const struct bpf_insn code_sample[] = { + /* We need a few instructions to pass the min log length */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), +}; + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64) (unsigned long) ptr; +} + +static int load(char *log, size_t log_len, int log_level) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insn_cnt = (__u32)(sizeof(code_sample) / sizeof(struct bpf_insn)); + attr.insns = ptr_to_u64(code_sample); + attr.license = ptr_to_u64("GPL"); + attr.log_buf = ptr_to_u64(log); + attr.log_size = log_len; + attr.log_level = log_level; + + return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); +} + +static void check_ret(int ret, int exp_errno) +{ + if (ret > 0) { + close(ret); + err("broken sample loaded successfully!?\n"); + exit(1); + } + + if (!ret || errno != exp_errno) { + err("Program load returned: ret:%d/errno:%d, expected ret:%d/errno:%d\n", + ret, errno, -1, exp_errno); + exit(1); + } +} + +static void check_ones(const char *buf, size_t len, const char *msg) +{ + while (len--) + if (buf[len] != 1) { + err("%s", msg); + exit(1); + } +} + +static void test_log_good(char *log, size_t buf_len, size_t log_len, + size_t exp_len, int exp_errno, const char *full_log) +{ + size_t len; + int ret; + + memset(log, 1, buf_len); + + ret = load(log, log_len, 1); + check_ret(ret, exp_errno); + + len = strnlen(log, buf_len); + if (len == buf_len) { + err("verifier did not NULL terminate the log\n"); + exit(1); + } + if (exp_len && len != exp_len) { + err("incorrect log length expected:%zd have:%zd\n", + exp_len, len); + exit(1); + } + + if (strchr(log, 1)) { + err("verifier leaked a byte through\n"); + exit(1); + } + + check_ones(log + len + 1, buf_len - len - 1, + "verifier wrote bytes past NULL termination\n"); + + if (memcmp(full_log, log, LOG_SIZE)) { + err("log did not match expected output\n"); + exit(1); + } +} + +static void test_log_bad(char *log, size_t log_len, int log_level) +{ + int ret; + + ret = load(log, log_len, log_level); + check_ret(ret, EINVAL); + if (log) + check_ones(log, LOG_SIZE, + "verifier touched log with bad parameters\n"); +} + +int main(int argc, char **argv) +{ + char full_log[LOG_SIZE]; + char log[LOG_SIZE]; + size_t want_len; + int i; + + memset(log, 1, LOG_SIZE); + + /* Test incorrect attr */ + printf("Test log_level 0...\n"); + test_log_bad(log, LOG_SIZE, 0); + + printf("Test log_size < 128...\n"); + test_log_bad(log, 15, 1); + + printf("Test log_buff = NULL...\n"); + test_log_bad(NULL, LOG_SIZE, 1); + + /* Test with log big enough */ + printf("Test oversized buffer...\n"); + test_log_good(full_log, LOG_SIZE, LOG_SIZE, 0, EACCES, full_log); + + want_len = strlen(full_log); + + printf("Test exact buffer...\n"); + test_log_good(log, LOG_SIZE, want_len + 2, want_len, EACCES, full_log); + + printf("Test undersized buffers...\n"); + for (i = 0; i < 64; i++) { + full_log[want_len - i + 1] = 1; + full_log[want_len - i] = 0; + + test_log_good(log, LOG_SIZE, want_len + 1 - i, want_len - i, + ENOSPC, full_log); + } + + printf("test_verifier_log: OK\n"); + return 0; +} diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index e8c86c416ed0..5215493166c9 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -37,6 +37,26 @@ kci_del_dummy() check_err $? } +kci_test_netconf() +{ + dev="$1" + r=$ret + + ip netconf show dev "$dev" > /dev/null + check_err $? + + for f in 4 6; do + ip -$f netconf show dev "$dev" > /dev/null + check_err $? + done + + if [ $ret -ne 0 ] ;then + echo "FAIL: ip netconf show $dev" + test $r -eq 0 && ret=0 + return 1 + fi +} + # add a bridge with vlans on top kci_test_bridge() { @@ -63,6 +83,11 @@ kci_test_bridge() check_err $? ip r s t all > /dev/null check_err $? + + for name in "$devbr" "$vlandev" "$devdummy" ; do + kci_test_netconf "$name" + done + ip -6 addr del dev "$vlandev" dead:42::1234/64 check_err $? @@ -100,6 +125,9 @@ kci_test_gre() check_err $? ip addr > /dev/null check_err $? + + kci_test_netconf "$gredev" + ip addr del dev "$devdummy" 10.23.7.11/24 check_err $? @@ -433,6 +461,47 @@ kci_test_encap() ip netns del "$testns" } +kci_test_macsec() +{ + msname="test_macsec0" + ret=0 + + ip macsec help 2>&1 | grep -q "^Usage: ip macsec" + if [ $? -ne 0 ]; then + echo "SKIP: macsec: iproute2 too old" + return 0 + fi + + ip link add link "$devdummy" "$msname" type macsec port 42 encrypt on + check_err $? + if [ $ret -ne 0 ];then + echo "FAIL: can't add macsec interface, skipping test" + return 1 + fi + + ip macsec add "$msname" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012 + check_err $? + + ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" + check_err $? + + ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on key 00 0123456789abcdef0123456789abcdef + check_err $? + + ip macsec show > /dev/null + check_err $? + + ip link del dev "$msname" + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: macsec" + return 1 + fi + + echo "PASS: macsec" +} + kci_test_rtnl() { kci_add_dummy @@ -450,6 +519,7 @@ kci_test_rtnl() kci_test_ifalias kci_test_vrf kci_test_encap + kci_test_macsec kci_del_dummy } diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/networking/timestamping/rxtimestamp.c index 00f286661dcd..dd4162fc0419 100644 --- a/tools/testing/selftests/networking/timestamping/rxtimestamp.c +++ b/tools/testing/selftests/networking/timestamping/rxtimestamp.c @@ -341,7 +341,7 @@ int main(int argc, char **argv) return 0; case 'n': t = atoi(optarg); - if (t > ARRAY_SIZE(test_cases)) + if (t >= ARRAY_SIZE(test_cases)) error(1, 0, "Invalid test case: %d", t); all_tests = false; test_cases[t].enabled = true; diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json new file mode 100644 index 000000000000..e2187b6e0b7a --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json @@ -0,0 +1,469 @@ +[ + { + "id": "e89a", + "name": "Add valid pass action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action pass index 8", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action pass.*index 8 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "a02c", + "name": "Add valid pipe action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action pipe index 6", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action pipe.*index 6 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "feef", + "name": "Add valid reclassify action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action reclassify index 5", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action reclassify.*index 5 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "8a7a", + "name": "Add valid drop action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action drop index 30", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 30 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "9a52", + "name": "Add valid continue action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action continue index 432", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action continue.*index 432 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "d700", + "name": "Add invalid action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action pump index 386", + "expExitCode": "255", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action.*index 386 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "9215", + "name": "Add action with duplicate index", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action pipe index 15" + ], + "cmdUnderTest": "$TC actions add action drop index 15", + "expExitCode": "255", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 15 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "798e", + "name": "Add action with index exceeding 32-bit maximum", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action drop index 4294967296", + "expExitCode": "255", + "verifyCmd": "actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 4294967296 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "22be", + "name": "Add action with index at 32-bit maximum", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action drop index 4294967295", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 4294967295 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "ac2a", + "name": "List actions", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action reclassify index 101", + "$TC actions add action reclassify index 102", + "$TC actions add action reclassify index 103", + "$TC actions add action reclassify index 104", + "$TC actions add action reclassify index 105" + ], + "cmdUnderTest": "$TC actions list action gact", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action reclassify", + "matchCount": "5", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "3edf", + "name": "Flush gact actions", + "category": [ + "actions", + "gact" + ], + "setup": [ + "$TC actions add action reclassify index 101", + "$TC actions add action reclassify index 102", + "$TC actions add action reclassify index 103", + "$TC actions add action reclassify index 104", + "$TC actions add action reclassify index 105" + ], + "cmdUnderTest": "$TC actions flush action gact", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action reclassify", + "matchCount": "0", + "teardown": [] + }, + { + "id": "63ec", + "name": "Delete pass action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action pass index 1" + ], + "cmdUnderTest": "$TC actions del action gact index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action pass.*index 1 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "46be", + "name": "Delete pipe action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action pipe index 9" + ], + "cmdUnderTest": "$TC actions del action gact index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action pipe.*index 9 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "2e08", + "name": "Delete reclassify action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action reclassify index 65536" + ], + "cmdUnderTest": "$TC actions del action gact index 65536", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action reclassify.*index 65536 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "99c4", + "name": "Delete drop action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action drop index 16" + ], + "cmdUnderTest": "$TC actions del action gact index 16", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 16 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "fb6b", + "name": "Delete continue action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action continue index 32" + ], + "cmdUnderTest": "$TC actions del action gact index 32", + "expExitCode": "0", + "verifyCmd": "actions list action gact", + "matchPattern": "action order [0-9]*: gact action continue.*index 32 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "0eb3", + "name": "Delete non-existent action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions del action gact index 2", + "expExitCode": "255", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "f02c", + "name": "Replace gact action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action drop index 10", + "$TC actions add action drop index 12" + ], + "cmdUnderTest": "$TC actions replace action ok index 12", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action gact", + "matchPattern": "action order [0-9]*: gact action pass", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "525f", + "name": "Get gact action by index", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action drop index 3900800700" + ], + "cmdUnderTest": "$TC actions get action gact index 3900800700", + "expExitCode": "0", + "verifyCmd": "$TC actions get action gact index 3900800700", + "matchPattern": "index 3900800700", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json new file mode 100644 index 000000000000..9f34f0753969 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json @@ -0,0 +1,52 @@ +[ + { + "id": "a568", + "name": "Add action with ife type", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife encode type 0xDEAD index 1" + ], + "cmdUnderTest": "$TC actions get action ife index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "type 0xDEAD", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "b983", + "name": "Add action without ife type", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife encode index 1" + ], + "cmdUnderTest": "$TC actions get action ife index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "type 0xED3E", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json new file mode 100644 index 000000000000..0fcccf18399b --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json @@ -0,0 +1,223 @@ +[ + { + "id": "5124", + "name": "Add mirred mirror to egress action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred egress mirror index 1 dev lo", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "6fb4", + "name": "Add mirred redirect to egress action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred egress redirect index 2 dev lo action pipe", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 2 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "ba38", + "name": "Get mirred actions", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred egress mirror index 1 dev lo", + "$TC actions add action mirred egress redirect index 2 dev lo" + ], + "cmdUnderTest": "$TC actions show action mirred", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "[Mirror|Redirect] to device lo", + "matchCount": "2", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "d7c0", + "name": "Add invalid mirred direction", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred inbound mirror index 20 dev lo", + "expExitCode": "255", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 20 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "e213", + "name": "Add invalid mirred action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred egress remirror index 20 dev lo", + "expExitCode": "255", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress.*to device lo\\).*index 20 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "2d89", + "name": "Add mirred action with invalid device", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred egress mirror index 20 dev eltoh", + "expExitCode": "255", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(.*to device eltoh\\).*index 20 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "300b", + "name": "Add mirred action with duplicate index", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred egress redirect index 15 dev lo" + ], + "cmdUnderTest": "$TC actions add action mirred egress mirror index 15 dev lo", + "expExitCode": "255", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 15 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "a70e", + "name": "Delete mirred mirror action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred egress mirror index 5 dev lo" + ], + "cmdUnderTest": "$TC actions del action mirred index 5", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 5 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "3fb3", + "name": "Delete mirred redirect action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred egress redirect index 5 dev lo" + ], + "cmdUnderTest": "$TC actions del action mirred index 5", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 5 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json new file mode 100644 index 000000000000..0e602a3f9393 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json @@ -0,0 +1,527 @@ +[ + { + "id": "49aa", + "name": "Add valid basic police action", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 1kbit burst 10k index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x1 rate 1Kbit burst 10Kb", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "3abe", + "name": "Add police action with duplicate index", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ], + "$TC actions add action police rate 4Mbit burst 120k index 9" + ], + "cmdUnderTest": "$TC actions add action police rate 8kbit burst 24k index 9", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "49fa", + "name": "Add valid police action with mtu", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 90kbit burst 10k mtu 1k index 98", + "expExitCode": "0", + "verifyCmd": "$TC actions get action police index 98", + "matchPattern": "action order [0-9]*: police 0x62 rate 90Kbit burst 10Kb mtu 1Kb", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "7943", + "name": "Add valid police action with peakrate", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 90kbit burst 10k mtu 2kb peakrate 100kbit index 3", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x3 rate 90Kbit burst 10Kb mtu 2Kb peakrate 100Kbit", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "055e", + "name": "Add police action with peakrate and no mtu", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 5kbit burst 6kb peakrate 10kbit index 9", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x9 rate 5Kb burst 10Kb", + "matchCount": "0", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "f057", + "name": "Add police action with valid overhead", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 1mbit burst 100k overhead 64 index 64", + "expExitCode": "0", + "verifyCmd": "$TC actions get action police index 64", + "matchPattern": "action order [0-9]*: police 0x40 rate 1Mbit burst 100Kb mtu 2Kb action reclassify overhead 64b", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "7ffb", + "name": "Add police action with ethernet linklayer type", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 2mbit burst 200k linklayer ethernet index 8", + "expExitCode": "0", + "verifyCmd": "$TC actions show action police", + "matchPattern": "action order [0-9]*: police 0x8 rate 2Mbit burst 200Kb mtu 2Kb action reclassify overhead 0b", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "3dda", + "name": "Add police action with atm linklayer type", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 2mbit burst 200k linklayer atm index 8", + "expExitCode": "0", + "verifyCmd": "$TC actions show action police", + "matchPattern": "action order [0-9]*: police 0x8 rate 2Mbit burst 200Kb mtu 2Kb action reclassify overhead 0b linklayer atm", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "551b", + "name": "Add police actions with conform-exceed control continue/drop", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed continue/drop index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action police index 1", + "matchPattern": "action order [0-9]*: police 0x1 rate 3Mbit burst 250Kb mtu 2Kb action continue/drop", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "0c70", + "name": "Add police actions with conform-exceed control pass/reclassify", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed pass/reclassify index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x4 rate 3Mbit burst 250Kb mtu 2Kb action pass/reclassify", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "d946", + "name": "Add police actions with conform-exceed control pass/pipe", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed pass/pipe index 5", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x5 rate 3Mbit burst 250Kb mtu 2Kb action pass/pipe", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "336e", + "name": "Delete police action", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ], + "$TC actions add action police rate 5mbit burst 2m index 12" + ], + "cmdUnderTest": "$TC actions delete action police index 12", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0xc rate 5Mb burst 2Mb", + "matchCount": "0", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "77fa", + "name": "Get single police action from many actions", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ], + "$TC actions add action police rate 1mbit burst 100k index 1", + "$TC actions add action police rate 2mbit burst 200k index 2", + "$TC actions add action police rate 3mbit burst 300k index 3", + "$TC actions add action police rate 4mbit burst 400k index 4", + "$TC actions add action police rate 5mbit burst 500k index 5", + "$TC actions add action police rate 6mbit burst 600k index 6", + "$TC actions add action police rate 7mbit burst 700k index 7", + "$TC actions add action police rate 8mbit burst 800k index 8" + ], + "cmdUnderTest": "$TC actions get action police index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions get action police index 4", + "matchPattern": "action order [0-9]*: police 0x4 rate 4Mbit burst 400Kb", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "aa43", + "name": "Get single police action without specifying index", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ], + "$TC actions add action police rate 1mbit burst 100k index 1" + ], + "cmdUnderTest": "$TC actions get action police", + "expExitCode": "255", + "verifyCmd": "$TC actions get action police", + "matchPattern": "action order [0-9]*: police", + "matchCount": "0", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "858b", + "name": "List police actions", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ], + "$TC actions add action police rate 1mbit burst 100k index 1", + "$TC actions add action police rate 2mbit burst 200k index 2", + "$TC actions add action police rate 3mbit burst 300k index 3", + "$TC actions add action police rate 4mbit burst 400k index 4", + "$TC actions add action police rate 5mbit burst 500k index 5", + "$TC actions add action police rate 6mbit burst 600k index 6", + "$TC actions add action police rate 7mbit burst 700k index 7", + "$TC actions add action police rate 8mbit burst 800k index 8" + ], + "cmdUnderTest": "$TC actions list action police", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x[1-8] rate [1-8]Mbit burst [1-8]00Kb", + "matchCount": "8", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "1c3a", + "name": "Flush police actions", + "category": [ + "actions", + "police" + ], + "setup": [ + "$TC actions add action police rate 1mbit burst 100k index 1", + "$TC actions add action police rate 2mbit burst 200k index 2", + "$TC actions add action police rate 3mbit burst 300k index 3", + "$TC actions add action police rate 4mbit burst 400k index 4", + "$TC actions add action police rate 5mbit burst 500k index 5", + "$TC actions add action police rate 6mbit burst 600k index 6", + "$TC actions add action police rate 7mbit burst 700k index 7", + "$TC actions add action police rate 8mbit burst 800k index 8" + ], + "cmdUnderTest": "$TC actions flush action police", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police", + "matchCount": "0", + "teardown": [ + "" + ] + }, + { + "id": "7326", + "name": "Add police action with control continue", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m continue index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action police index 1", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action continue", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "34fa", + "name": "Add police action with control drop", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m drop index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action drop", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "8dd5", + "name": "Add police action with control ok", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m ok index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action pass", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "b9d1", + "name": "Add police action with control reclassify", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m reclassify index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action police index 1", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action reclassify", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "c534", + "name": "Add police action with control pipe", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m pipe index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action pipe", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json new file mode 100644 index 000000000000..e89a7aa4012d --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json @@ -0,0 +1,130 @@ +[ + { + "id": "b078", + "name": "Add simple action", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action simple sdata \"A triumph\" index 60", + "expExitCode": "0", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple <A triumph>.*index 60 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action simple" + ] + }, + { + "id": "6d4c", + "name": "Add simple action with duplicate index", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ], + "$TC actions add action simple sdata \"Aruba\" index 4" + ], + "cmdUnderTest": "$TC actions add action simple sdata \"Jamaica\" index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple <Jamaica>.*ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action simple" + ] + }, + { + "id": "2542", + "name": "List simple actions", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ], + "$TC actions add action simple sdata \"Rock\"", + "$TC actions add action simple sdata \"Paper\"", + "$TC actions add action simple sdata \"Scissors\" index 98" + ], + "cmdUnderTest": "$TC actions list action simple", + "expExitCode": "0", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>", + "matchCount": "3", + "teardown": [ + "$TC actions flush action simple" + ] + }, + { + "id": "ea67", + "name": "Delete simple action", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ], + "$TC actions add action simple sdata \"Blinkenlights\" index 1" + ], + "cmdUnderTest": "$TC actions delete action simple index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple <Blinkenlights>.*index 1 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action simple" + ] + }, + { + "id": "8ff1", + "name": "Flush simple actions", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ], + "$TC actions add action simple sdata \"Kirk\"", + "$TC actions add action simple sdata \"Spock\" index 50", + "$TC actions add action simple sdata \"McCoy\" index 9" + ], + "cmdUnderTest": "$TC actions flush action simple", + "expExitCode": "0", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>", + "matchCount": "0", + "teardown": [ + "" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json new file mode 100644 index 000000000000..99635ea4722e --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json @@ -0,0 +1,320 @@ +[ + { + "id": "6236", + "name": "Add skbedit action with valid mark", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit mark 1", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit mark 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "407b", + "name": "Add skbedit action with invalid mark", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit mark 666777888999", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit mark", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "081d", + "name": "Add skbedit action with priority", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit prio 99", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit priority :99", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "cc37", + "name": "Add skbedit action with invalid priority", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit prio foo", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit priority", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "3c95", + "name": "Add skbedit action with queue_mapping", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit queue_mapping 909", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit queue_mapping 909", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "985c", + "name": "Add skbedit action with invalid queue_mapping", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit queue_mapping 67000", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit queue_mapping", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "224f", + "name": "Add skbedit action with ptype host", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit ptype host", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit ptype host", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "d1a3", + "name": "Add skbedit action with ptype otherhost", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit ptype otherhost", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit ptype otherhost", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "b9c6", + "name": "Add skbedit action with invalid ptype", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit ptype openair", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit ptype openair", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "5172", + "name": "List skbedit actions", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ], + "$TC actions add action skbedit ptype otherhost", + "$TC actions add action skbedit ptype broadcast", + "$TC actions add action skbedit mark 59", + "$TC actions add action skbedit mark 409" + ], + "cmdUnderTest": "$TC actions list action skbedit", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit", + "matchCount": "4", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "a6d6", + "name": "Add skbedit action with index", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit mark 808 index 4040404040", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "index 4040404040", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "38f3", + "name": "Delete skbedit action", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ], + "$TC actions add action skbedit mark 42 index 9009" + ], + "cmdUnderTest": "$TC actions del action skbedit index 9009", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit mark 42", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "ce97", + "name": "Flush skbedit actions", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + "$TC actions add action skbedit mark 500", + "$TC actions add action skbedit mark 501", + "$TC actions add action skbedit mark 502", + "$TC actions add action skbedit mark 503", + "$TC actions add action skbedit mark 504", + "$TC actions add action skbedit mark 505", + "$TC actions add action skbedit mark 506" + ], + "cmdUnderTest": "$TC actions flush action skbedit", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json new file mode 100644 index 000000000000..e34075059c26 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json @@ -0,0 +1,372 @@ +[ + { + "id": "7d50", + "name": "Add skbmod action to set destination mac", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set dmac 11:22:33:44:55:66 index 5", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pipe set dmac 11:22:33:44:55:66\\s+index 5", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "9b29", + "name": "Add skbmod action to set source mac", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set smac 77:88:99:AA:BB:CC index 7", + "expExitCode": "0", + "verifyCmd": "$TC actions get action skbmod index 7", + "matchPattern": "action order [0-9]*: skbmod pipe set smac 77:88:99:aa:bb:cc\\s+index 7", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "1724", + "name": "Add skbmod action with invalid mac", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set smac 00:44:55:44:55", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pipe set smac 00:44:55:44:55", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "3cf1", + "name": "Add skbmod action with valid etype", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set etype 0xfefe", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pipe set etype 0xFEFE", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "a749", + "name": "Add skbmod action with invalid etype", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set etype 0xfefef", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pipe set etype 0xFEFEF", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "bfe6", + "name": "Add skbmod action to swap mac", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod swap mac", + "expExitCode": "0", + "verifyCmd": "$TC actions get action skbmod index 1", + "matchPattern": "action order [0-9]*: skbmod pipe swap mac", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "839b", + "name": "Add skbmod action with control pipe", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod swap mac pipe", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pipe swap mac", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "c167", + "name": "Add skbmod action with control reclassify", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set etype 0xbeef reclassify", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod reclassify set etype 0xBEEF", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "0c2f", + "name": "Add skbmod action with control drop", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set etype 0x0001 drop", + "expExitCode": "0", + "verifyCmd": "$TC actions get action skbmod index 1", + "matchPattern": "action order [0-9]*: skbmod drop set etype 0x1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "d113", + "name": "Add skbmod action with control continue", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set etype 0x1 continue", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod continue set etype 0x1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "7242", + "name": "Add skbmod action with control pass", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set smac 00:00:00:00:00:01 pass", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pass set smac 00:00:00:00:00:01", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "58cb", + "name": "List skbmod actions", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ], + "$TC actions add action skbmod set etype 0x0001", + "$TC actions add action skbmod set etype 0x0011", + "$TC actions add action skbmod set etype 0x0021", + "$TC actions add action skbmod set etype 0x0031", + "$TC actions add action skbmod set etype 0x0041" + ], + "cmdUnderTest": "$TC actions ls action skbmod", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod", + "matchCount": "5", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "9aa8", + "name": "Get a single skbmod action from a list", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ], + "$TC actions add action skbmod set etype 0x0001", + "$TC actions add action skbmod set etype 0x0011", + "$TC actions add action skbmod set etype 0x0021", + "$TC actions add action skbmod set etype 0x0031", + "$TC actions add action skbmod set etype 0x0041" + ], + "cmdUnderTest": "$TC actions ls action skbmod", + "expExitCode": "0", + "verifyCmd": "$TC actions get action skbmod index 4", + "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x0031", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "e93a", + "name": "Delete an skbmod action", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ], + "$TC actions add action skbmod set etype 0x1111 index 909" + ], + "cmdUnderTest": "$TC actions del action skbmod index 909", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x1111\\s+index 909", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "40c2", + "name": "Flush skbmod actions", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + "$TC actions add action skbmod set etype 0x0001", + "$TC actions add action skbmod set etype 0x0011", + "$TC actions add action skbmod set etype 0x0021", + "$TC actions add action skbmod set etype 0x0031", + "$TC actions add action skbmod set etype 0x0041" + ], + "cmdUnderTest": "$TC actions flush action skbmod", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbmod" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json deleted file mode 100644 index 6973bdc5b5bf..000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json +++ /dev/null @@ -1,1165 +0,0 @@ -[ - { - "id": "e89a", - "name": "Add valid pass action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action pass index 8", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action pass.*index 8 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "a02c", - "name": "Add valid pipe action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action pipe index 6", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action pipe.*index 6 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "feef", - "name": "Add valid reclassify action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action reclassify index 5", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action reclassify.*index 5 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "8a7a", - "name": "Add valid drop action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action drop index 30", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action drop.*index 30 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "9a52", - "name": "Add valid continue action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action continue index 432", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action continue.*index 432 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "d700", - "name": "Add invalid action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action pump index 386", - "expExitCode": "255", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action.*index 386 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "9215", - "name": "Add action with duplicate index", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action pipe index 15" - ], - "cmdUnderTest": "$TC actions add action drop index 15", - "expExitCode": "255", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action drop.*index 15 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "798e", - "name": "Add action with index exceeding 32-bit maximum", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action drop index 4294967296", - "expExitCode": "255", - "verifyCmd": "actions list action gact", - "matchPattern": "action order [0-9]*: gact action drop.*index 4294967296 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "22be", - "name": "Add action with index at 32-bit maximum", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action drop index 4294967295", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action drop.*index 4294967295 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "ac2a", - "name": "List actions", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action reclassify index 101", - "$TC actions add action reclassify index 102", - "$TC actions add action reclassify index 103", - "$TC actions add action reclassify index 104", - "$TC actions add action reclassify index 105" - ], - "cmdUnderTest": "$TC actions list action gact", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action reclassify", - "matchCount": "5", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "63ec", - "name": "Delete pass action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action pass index 1" - ], - "cmdUnderTest": "$TC actions del action gact index 1", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action pass.*index 1 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "46be", - "name": "Delete pipe action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action pipe index 9" - ], - "cmdUnderTest": "$TC actions del action gact index 9", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action pipe.*index 9 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "2e08", - "name": "Delete reclassify action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action reclassify index 65536" - ], - "cmdUnderTest": "$TC actions del action gact index 65536", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action reclassify.*index 65536 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "99c4", - "name": "Delete drop action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action drop index 16" - ], - "cmdUnderTest": "$TC actions del action gact index 16", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action drop.*index 16 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "fb6b", - "name": "Delete continue action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action continue index 32" - ], - "cmdUnderTest": "$TC actions del action gact index 32", - "expExitCode": "0", - "verifyCmd": "actions list action gact", - "matchPattern": "action order [0-9]*: gact action continue.*index 32 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "0eb3", - "name": "Delete non-existent action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions del action gact index 2", - "expExitCode": "255", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "5124", - "name": "Add mirred mirror to egress action", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action mirred egress mirror index 1 dev lo", - "expExitCode": "0", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 1 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "6fb4", - "name": "Add mirred redirect to egress action", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action mirred egress redirect index 2 dev lo action pipe", - "expExitCode": "0", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 2 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "ba38", - "name": "Get mirred actions", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ], - "$TC actions add action mirred egress mirror index 1 dev lo", - "$TC actions add action mirred egress redirect index 2 dev lo" - ], - "cmdUnderTest": "$TC actions show action mirred", - "expExitCode": "0", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "[Mirror|Redirect] to device lo", - "matchCount": "2", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "d7c0", - "name": "Add invalid mirred direction", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action mirred inbound mirror index 20 dev lo", - "expExitCode": "255", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 20 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "e213", - "name": "Add invalid mirred action", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action mirred egress remirror index 20 dev lo", - "expExitCode": "255", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(Egress.*to device lo\\).*index 20 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "2d89", - "name": "Add mirred action with invalid device", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action mirred egress mirror index 20 dev eltoh", - "expExitCode": "255", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(.*to device eltoh\\).*index 20 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "300b", - "name": "Add mirred action with duplicate index", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ], - "$TC actions add action mirred egress redirect index 15 dev lo" - ], - "cmdUnderTest": "$TC actions add action mirred egress mirror index 15 dev lo", - "expExitCode": "255", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 15 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "a70e", - "name": "Delete mirred mirror action", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ], - "$TC actions add action mirred egress mirror index 5 dev lo" - ], - "cmdUnderTest": "$TC actions del action mirred index 5", - "expExitCode": "0", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 5 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "3fb3", - "name": "Delete mirred redirect action", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ], - "$TC actions add action mirred egress redirect index 5 dev lo" - ], - "cmdUnderTest": "$TC actions del action mirred index 5", - "expExitCode": "0", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 5 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "b078", - "name": "Add simple action", - "category": [ - "actions", - "simple" - ], - "setup": [ - [ - "$TC actions flush action simple", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action simple sdata \"A triumph\" index 60", - "expExitCode": "0", - "verifyCmd": "$TC actions list action simple", - "matchPattern": "action order [0-9]*: Simple <A triumph>.*index 60 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action simple" - ] - }, - { - "id": "6d4c", - "name": "Add simple action with duplicate index", - "category": [ - "actions", - "simple" - ], - "setup": [ - [ - "$TC actions flush action simple", - 0, - 1, - 255 - ], - "$TC actions add action simple sdata \"Aruba\" index 4" - ], - "cmdUnderTest": "$TC actions add action simple sdata \"Jamaica\" index 4", - "expExitCode": "255", - "verifyCmd": "$TC actions list action simple", - "matchPattern": "action order [0-9]*: Simple <Jamaica>.*ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action simple" - ] - }, - { - "id": "2542", - "name": "List simple actions", - "category": [ - "actions", - "simple" - ], - "setup": [ - [ - "$TC actions flush action simple", - 0, - 1, - 255 - ], - "$TC actions add action simple sdata \"Rock\"", - "$TC actions add action simple sdata \"Paper\"", - "$TC actions add action simple sdata \"Scissors\" index 98" - ], - "cmdUnderTest": "$TC actions list action simple", - "expExitCode": "0", - "verifyCmd": "$TC actions list action simple", - "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>", - "matchCount": "3", - "teardown": [ - "$TC actions flush action simple" - ] - }, - { - "id": "ea67", - "name": "Delete simple action", - "category": [ - "actions", - "simple" - ], - "setup": [ - [ - "$TC actions flush action simple", - 0, - 1, - 255 - ], - "$TC actions add action simple sdata \"Blinkenlights\" index 1" - ], - "cmdUnderTest": "$TC actions delete action simple index 1", - "expExitCode": "0", - "verifyCmd": "$TC actions list action simple", - "matchPattern": "action order [0-9]*: Simple <Blinkenlights>.*index 1 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action simple" - ] - }, - { - "id": "8ff1", - "name": "Flush simple actions", - "category": [ - "actions", - "simple" - ], - "setup": [ - [ - "$TC actions flush action simple", - 0, - 1, - 255 - ], - "$TC actions add action simple sdata \"Kirk\"", - "$TC actions add action simple sdata \"Spock\" index 50", - "$TC actions add action simple sdata \"McCoy\" index 9" - ], - "cmdUnderTest": "$TC actions flush action simple", - "expExitCode": "0", - "verifyCmd": "$TC actions list action simple", - "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>", - "matchCount": "0", - "teardown": [ - "" - ] - }, - { - "id": "6236", - "name": "Add skbedit action with valid mark", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit mark 1", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit mark 1", - "matchCount": "1", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "407b", - "name": "Add skbedit action with invalid mark", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit mark 666777888999", - "expExitCode": "255", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit mark", - "matchCount": "0", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "081d", - "name": "Add skbedit action with priority", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit prio 99", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit priority :99", - "matchCount": "1", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "cc37", - "name": "Add skbedit action with invalid priority", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit prio foo", - "expExitCode": "255", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit priority", - "matchCount": "0", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "3c95", - "name": "Add skbedit action with queue_mapping", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit queue_mapping 909", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit queue_mapping 909", - "matchCount": "1", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "985c", - "name": "Add skbedit action with invalid queue_mapping", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit queue_mapping 67000", - "expExitCode": "255", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit queue_mapping", - "matchCount": "0", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "224f", - "name": "Add skbedit action with ptype host", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit ptype host", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit ptype host", - "matchCount": "1", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "d1a3", - "name": "Add skbedit action with ptype otherhost", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit ptype otherhost", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit ptype otherhost", - "matchCount": "1", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "b9c6", - "name": "Add skbedit action with invalid ptype", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit ptype openair", - "expExitCode": "255", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit ptype openair", - "matchCount": "0", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "5172", - "name": "List skbedit actions", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ], - "$TC actions add action skbedit ptype otherhost", - "$TC actions add action skbedit ptype broadcast", - "$TC actions add action skbedit mark 59", - "$TC actions add action skbedit mark 409" - ], - "cmdUnderTest": "$TC actions list action skbedit", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit", - "matchCount": "4", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "a6d6", - "name": "Add skbedit action with index", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit mark 808 index 4040404040", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "index 4040404040", - "matchCount": "1", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "38f3", - "name": "Delete skbedit action", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ], - "$TC actions add action skbedit mark 42 index 9009" - ], - "cmdUnderTest": "$TC actions del action skbedit index 9009", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit mark 42", - "matchCount": "0", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "ce97", - "name": "Flush skbedit actions", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - "$TC actions add action skbedit mark 500", - "$TC actions add action skbedit mark 501", - "$TC actions add action skbedit mark 502", - "$TC actions add action skbedit mark 503", - "$TC actions add action skbedit mark 504", - "$TC actions add action skbedit mark 505", - "$TC actions add action skbedit mark 506" - ], - "cmdUnderTest": "$TC actions flush action skbedit", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit", - "matchCount": "0", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "f02c", - "name": "Replace gact action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action drop index 10", - "$TC actions add action drop index 12" - ], - "cmdUnderTest": "$TC actions replace action ok index 12", - "expExitCode": "0", - "verifyCmd": "$TC actions ls action gact", - "matchPattern": "action order [0-9]*: gact action pass", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "525f", - "name": "Get gact action by index", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action drop index 3900800700" - ], - "cmdUnderTest": "$TC actions get action gact index 3900800700", - "expExitCode": "0", - "verifyCmd": "$TC actions get action gact index 3900800700", - "matchPattern": "index 3900800700", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "a568", - "name": "Add action with ife type", - "category": [ - "actions", - "ife" - ], - "setup": [ - [ - "$TC actions flush action ife", - 0, - 1, - 255 - ], - "$TC actions add action ife encode type 0xDEAD index 1" - ], - "cmdUnderTest": "$TC actions get action ife index 1", - "expExitCode": "0", - "verifyCmd": "$TC actions get action ife index 1", - "matchPattern": "type 0xDEAD", - "matchCount": "1", - "teardown": [ - "$TC actions flush action ife" - ] - }, - { - "id": "b983", - "name": "Add action without ife type", - "category": [ - "actions", - "ife" - ], - "setup": [ - [ - "$TC actions flush action ife", - 0, - 1, - 255 - ], - "$TC actions add action ife encode index 1" - ], - "cmdUnderTest": "$TC actions get action ife index 1", - "expExitCode": "0", - "verifyCmd": "$TC actions get action ife index 1", - "matchPattern": "type 0xED3E", - "matchCount": "1", - "teardown": [ - "$TC actions flush action ife" - ] - } -]
\ No newline at end of file diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index cd61b7844c0d..d2391df2cf7d 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -49,7 +49,7 @@ def exec_cmd(command, nsonly=True): stderr=subprocess.PIPE) (rawout, serr) = proc.communicate() - if proc.returncode != 0: + if proc.returncode != 0 and len(serr) > 0: foutput = serr.decode("utf-8") else: foutput = rawout.decode("utf-8") @@ -203,7 +203,7 @@ def set_args(parser): help='Run tests only from the specified category, or if no category is specified, list known categories.') parser.add_argument('-f', '--file', type=str, help='Run tests from the specified file') - parser.add_argument('-l', '--list', type=str, nargs='?', const="", metavar='CATEGORY', + parser.add_argument('-l', '--list', type=str, nargs='?', const="++", metavar='CATEGORY', help='List all test cases, or those only within the specified category') parser.add_argument('-s', '--show', type=str, nargs=1, metavar='ID', dest='showID', help='Display the test case with specified id') @@ -357,10 +357,10 @@ def set_operation_mode(args): testcases = get_categorized_testlist(alltests, ucat) if args.list: - if (len(args.list) == 0): + if (args.list == "++"): list_test_cases(alltests) exit(0) - elif(len(args.list > 0)): + elif(len(args.list) > 0): if (args.list not in ucat): print("Unknown category " + args.list) print("Available categories:") |