diff options
543 files changed, 7899 insertions, 5316 deletions
@@ -198,6 +198,9 @@ Maxime Ripard <[email protected]> <[email protected]> Mayuresh Janorkar <[email protected]> Michael Buesch <[email protected]> Michel Dänzer <[email protected]> +Mike Rapoport <[email protected]> <[email protected]> +Mike Rapoport <[email protected]> <[email protected]> +Mike Rapoport <[email protected]> <[email protected]> Miodrag Dinic <[email protected]> <[email protected]> Miquel Raynal <[email protected]> <[email protected]> Mitesh shah <[email protected]> diff --git a/Documentation/ABI/testing/debugfs-driver-habanalabs b/Documentation/ABI/testing/debugfs-driver-habanalabs index f6d9c2a8d528..2e9ae311e02d 100644 --- a/Documentation/ABI/testing/debugfs-driver-habanalabs +++ b/Documentation/ABI/testing/debugfs-driver-habanalabs @@ -16,7 +16,16 @@ Description: Allow the root user to disable/enable in runtime the clock gating mechanism in Gaudi. Due to how Gaudi is built, the clock gating needs to be disabled in order to access the registers of the TPC and MME engines. This is sometimes needed - during debug by the user and hence the user needs this option + during debug by the user and hence the user needs this option. + The user can supply a bitmask value, each bit represents + a different engine to disable/enable its clock gating feature. + The bitmask is composed of 20 bits: + 0 - 7 : DMA channels + 8 - 11 : MME engines + 12 - 19 : TPC engines + The bit's location of a specific engine can be determined + using (1 << GAUDI_ENGINE_ID_*). GAUDI_ENGINE_ID_* values + are defined in uapi habanalabs.h file in enum gaudi_engine_id What: /sys/kernel/debug/habanalabs/hl<n>/command_buffers Date: Jan 2019 diff --git a/Documentation/admin-guide/ext4.rst b/Documentation/admin-guide/ext4.rst index 9443fcef1876..2162d7909970 100644 --- a/Documentation/admin-guide/ext4.rst +++ b/Documentation/admin-guide/ext4.rst @@ -395,6 +395,13 @@ When mounting an ext4 filesystem, the following option are accepted: Documentation/filesystems/dax.txt. Note that this option is incompatible with data=journal. + inlinecrypt + When possible, encrypt/decrypt the contents of encrypted files using the + blk-crypto framework rather than filesystem-layer encryption. This + allows the use of inline encryption hardware. The on-disk format is + unaffected. For more details, see + Documentation/block/inline-encryption.rst. + Data Mode ========= There are 3 different data modes: diff --git a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml index 526593c8c614..4cc1a670c986 100644 --- a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml +++ b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml @@ -47,6 +47,9 @@ properties: $ref: /schemas/types.yaml#/definitions/phandle-array description: Phandle to the device SRAM + iommus: + maxItems: 1 + memory-region: description: CMA pool to use for buffers allocation instead of the default diff --git a/Documentation/devicetree/bindings/sound/simple-card.yaml b/Documentation/devicetree/bindings/sound/simple-card.yaml index 8132d0c0f00a..35e669020296 100644 --- a/Documentation/devicetree/bindings/sound/simple-card.yaml +++ b/Documentation/devicetree/bindings/sound/simple-card.yaml @@ -378,6 +378,8 @@ examples: - | sound { compatible = "simple-audio-card"; + #address-cells = <1>; + #size-cells = <0>; simple-audio-card,name = "rsnd-ak4643"; simple-audio-card,format = "left_j"; @@ -391,10 +393,12 @@ examples: "ak4642 Playback", "DAI1 Playback"; dpcmcpu: simple-audio-card,cpu@0 { + reg = <0>; sound-dai = <&rcar_sound 0>; }; simple-audio-card,cpu@1 { + reg = <1>; sound-dai = <&rcar_sound 1>; }; @@ -418,6 +422,8 @@ examples: - | sound { compatible = "simple-audio-card"; + #address-cells = <1>; + #size-cells = <0>; simple-audio-card,routing = "pcm3168a Playback", "DAI1 Playback", @@ -426,6 +432,7 @@ examples: "pcm3168a Playback", "DAI4 Playback"; simple-audio-card,dai-link@0 { + reg = <0>; format = "left_j"; bitclock-master = <&sndcpu0>; frame-master = <&sndcpu0>; @@ -439,22 +446,23 @@ examples: }; simple-audio-card,dai-link@1 { + reg = <1>; format = "i2s"; bitclock-master = <&sndcpu1>; frame-master = <&sndcpu1>; convert-channels = <8>; /* TDM Split */ - sndcpu1: cpu@0 { + sndcpu1: cpu0 { sound-dai = <&rcar_sound 1>; }; - cpu@1 { + cpu1 { sound-dai = <&rcar_sound 2>; }; - cpu@2 { + cpu2 { sound-dai = <&rcar_sound 3>; }; - cpu@3 { + cpu3 { sound-dai = <&rcar_sound 4>; }; codec { @@ -466,6 +474,7 @@ examples: }; simple-audio-card,dai-link@2 { + reg = <2>; format = "i2s"; bitclock-master = <&sndcpu2>; frame-master = <&sndcpu2>; diff --git a/Documentation/driver-api/ptp.rst b/Documentation/driver-api/ptp.rst index a15192e32347..664838ae7776 100644 --- a/Documentation/driver-api/ptp.rst +++ b/Documentation/driver-api/ptp.rst @@ -23,6 +23,7 @@ PTP hardware clock infrastructure for Linux + Ancillary clock features - Time stamp external events - Period output signals configurable from user space + - Low Pass Filter (LPF) access from user space - Synchronization of the Linux system time via the PPS subsystem PTP hardware clock kernel API @@ -94,3 +95,14 @@ Supported hardware - Auxiliary Slave/Master Mode Snapshot (optional interrupt) - Target Time (optional interrupt) + + * Renesas (IDT) ClockMatrix™ + + - Up to 4 independent PHC channels + - Integrated low pass filter (LPF), access via .adjPhase (compliant to ITU-T G.8273.2) + - Programmable output periodic signals + - Programmable inputs can time stamp external triggers + - Driver and/or hardware configuration through firmware (idtcm.bin) + - LPF settings (bandwidth, phase limiting, automatic holdover, physical layer assist (per ITU-T G.8273.2)) + - Programmable output PTP clocks, any frequency up to 1GHz (to other PHY/MAC time stampers, refclk to ASSPs/SoCs/FPGAs) + - Lock to GNSS input, automatic switching between GNSS and user-space PHC control (optional) diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst index 099d45ac8d8f..8b4fac44f4e1 100644 --- a/Documentation/filesystems/f2fs.rst +++ b/Documentation/filesystems/f2fs.rst @@ -258,6 +258,13 @@ compress_extension=%s Support adding specified extension, so that f2fs can enab on compression extension list and enable compression on these file by default rather than to enable it via ioctl. For other files, we can still enable compression via ioctl. +inlinecrypt + When possible, encrypt/decrypt the contents of encrypted + files using the blk-crypto framework rather than + filesystem-layer encryption. This allows the use of + inline encryption hardware. The on-disk format is + unaffected. For more details, see + Documentation/block/inline-encryption.rst. ====================== ============================================================ Debugfs Entries diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index f517af8ec11c..423c5a0daf45 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -1158,7 +1158,7 @@ setxattr() because of the special semantics of the encryption xattr. were to be added to or removed from anything other than an empty directory.) These structs are defined as follows:: - #define FS_KEY_DERIVATION_NONCE_SIZE 16 + #define FSCRYPT_FILE_NONCE_SIZE 16 #define FSCRYPT_KEY_DESCRIPTOR_SIZE 8 struct fscrypt_context_v1 { @@ -1167,7 +1167,7 @@ directory.) These structs are defined as follows:: u8 filenames_encryption_mode; u8 flags; u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE]; - u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE]; + u8 nonce[FSCRYPT_FILE_NONCE_SIZE]; }; #define FSCRYPT_KEY_IDENTIFIER_SIZE 16 @@ -1178,7 +1178,7 @@ directory.) These structs are defined as follows:: u8 flags; u8 __reserved[4]; u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]; - u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE]; + u8 nonce[FSCRYPT_FILE_NONCE_SIZE]; }; The context structs contain the same information as the corresponding @@ -1204,6 +1204,18 @@ buffer. Some filesystems, such as UBIFS, already use temporary buffers regardless of encryption. Other filesystems, such as ext4 and F2FS, have to allocate bounce pages specially for encryption. +Fscrypt is also able to use inline encryption hardware instead of the +kernel crypto API for en/decryption of file contents. When possible, +and if directed to do so (by specifying the 'inlinecrypt' mount option +for an ext4/F2FS filesystem), it adds encryption contexts to bios and +uses blk-crypto to perform the en/decryption instead of making use of +the above read/write path changes. Of course, even if directed to +make use of inline encryption, fscrypt will only be able to do so if +either hardware inline encryption support is available for the +selected encryption algorithm or CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK +is selected. If neither is the case, fscrypt will fall back to using +the above mentioned read/write path changes for en/decryption. + Filename hashing and encoding ----------------------------- @@ -1250,11 +1262,14 @@ Tests To test fscrypt, use xfstests, which is Linux's de facto standard filesystem test suite. First, run all the tests in the "encrypt" -group on the relevant filesystem(s). For example, to test ext4 and +group on the relevant filesystem(s). One can also run the tests +with the 'inlinecrypt' mount option to test the implementation for +inline encryption support. For example, to test ext4 and f2fs encryption using `kvm-xfstests <https://github.com/tytso/xfstests-bld/blob/master/Documentation/kvm-quickstart.md>`_:: kvm-xfstests -c ext4,f2fs -g encrypt + kvm-xfstests -c ext4,f2fs -g encrypt -m inlinecrypt UBIFS encryption can also be tested this way, but it should be done in a separate command, and it takes some time for kvm-xfstests to set up @@ -1276,6 +1291,7 @@ This tests the encrypted I/O paths more thoroughly. To do this with kvm-xfstests, use the "encrypt" filesystem configuration:: kvm-xfstests -c ext4/encrypt,f2fs/encrypt -g auto + kvm-xfstests -c ext4/encrypt,f2fs/encrypt -g auto -m inlinecrypt Because this runs many more tests than "-g encrypt" does, it takes much longer to run; so also consider using `gce-xfstests @@ -1283,3 +1299,4 @@ much longer to run; so also consider using `gce-xfstests instead of kvm-xfstests:: gce-xfstests -c ext4/encrypt,f2fs/encrypt -g auto + gce-xfstests -c ext4/encrypt,f2fs/encrypt -g auto -m inlinecrypt diff --git a/Documentation/networking/bareudp.rst b/Documentation/networking/bareudp.rst index 465a8b251bfe..b9d04ee6dac1 100644 --- a/Documentation/networking/bareudp.rst +++ b/Documentation/networking/bareudp.rst @@ -8,9 +8,8 @@ There are various L3 encapsulation standards using UDP being discussed to leverage the UDP based load balancing capability of different networks. MPLSoUDP (__ https://tools.ietf.org/html/rfc7510) is one among them. -The Bareudp tunnel module provides a generic L3 encapsulation tunnelling -support for tunnelling different L3 protocols like MPLS, IP, NSH etc. inside -a UDP tunnel. +The Bareudp tunnel module provides a generic L3 encapsulation support for +tunnelling different L3 protocols like MPLS, IP, NSH etc. inside a UDP tunnel. Special Handling ---------------- @@ -26,7 +25,7 @@ Usage 1) Device creation & deletion - a) ip link add dev bareudp0 type bareudp dstport 6635 ethertype 0x8847. + a) ip link add dev bareudp0 type bareudp dstport 6635 ethertype mpls_uc This creates a bareudp tunnel device which tunnels L3 traffic with ethertype 0x8847 (MPLS traffic). The destination port of the UDP header will be set to @@ -34,14 +33,21 @@ Usage b) ip link delete bareudp0 -2) Device creation with multiple proto mode enabled +2) Device creation with multiproto mode enabled -There are two ways to create a bareudp device for MPLS & IP with multiproto mode -enabled. +The multiproto mode allows bareudp tunnels to handle several protocols of the +same family. It is currently only available for IP and MPLS. This mode has to +be enabled explicitly with the "multiproto" flag. - a) ip link add dev bareudp0 type bareudp dstport 6635 ethertype 0x8847 multiproto + a) ip link add dev bareudp0 type bareudp dstport 6635 ethertype ipv4 multiproto - b) ip link add dev bareudp0 type bareudp dstport 6635 ethertype mpls + For an IPv4 tunnel the multiproto mode allows the tunnel to also handle + IPv6. + + b) ip link add dev bareudp0 type bareudp dstport 6635 ethertype mpls_uc multiproto + + For MPLS, the multiproto mode allows the tunnel to handle both unicast + and multicast MPLS packets. 3) Device Usage diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst index 1e3f3ffee248..2014307fbe63 100644 --- a/Documentation/networking/devlink/devlink-trap.rst +++ b/Documentation/networking/devlink/devlink-trap.rst @@ -486,6 +486,10 @@ narrow. The description of these groups must be added to the following table: - Contains packet traps for packets that should be locally delivered after routing, but do not match more specific packet traps (e.g., ``ipv4_bgp``) + * - ``external_delivery`` + - Contains packet traps for packets that should be routed through an + external interface (e.g., management interface) that does not belong to + the same device (e.g., switch ASIC) as the ingress interface * - ``ipv6`` - Contains packet traps for various IPv6 control packets (e.g., Router Advertisements) diff --git a/MAINTAINERS b/MAINTAINERS index d53db30d1365..4e2698cc7e23 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -782,7 +782,7 @@ F: include/dt-bindings/reset/altr,rst-mgr-a10sr.h F: include/linux/mfd/altera-a10sr.h ALTERA TRIPLE SPEED ETHERNET DRIVER -M: Thor Thayer <[email protected]> +M: Joyce Ooi <[email protected]> S: Maintained F: drivers/net/ethernet/altera/ @@ -1425,7 +1425,7 @@ F: arch/arm*/include/asm/perf_event.h F: arch/arm*/kernel/hw_breakpoint.c F: arch/arm*/kernel/perf_* F: arch/arm/oprofile/common.c -F: drivers/perf/* +F: drivers/perf/ F: include/linux/perf/arm_pmu.h ARM PORT @@ -6956,6 +6956,7 @@ M: Timur Tabi <[email protected]> M: Nicolin Chen <[email protected]> M: Xiubo Li <[email protected]> R: Fabio Estevam <[email protected]> +R: Shengjiu Wang <[email protected]> L: [email protected] (moderated for non-subscribers) S: Maintained @@ -9305,6 +9306,17 @@ F: Documentation/kbuild/kconfig* F: scripts/Kconfig.include F: scripts/kconfig/ +KCOV +R: Dmitry Vyukov <[email protected]> +R: Andrey Konovalov <[email protected]> +S: Maintained +F: Documentation/dev-tools/kcov.rst +F: include/linux/kcov.h +F: include/uapi/linux/kcov.h +F: kernel/kcov.c +F: scripts/Makefile.kcov + KCSAN M: Marco Elver <[email protected]> R: Dmitry Vyukov <[email protected]> @@ -11240,7 +11252,7 @@ S: Maintained F: drivers/crypto/atmel-ecc.* MICROCHIP I2C DRIVER -M: Ludovic Desroches <[email protected]> +M: Codrin Ciubotariu <[email protected]> S: Supported F: drivers/i2c/busses/i2c-at91-*.c @@ -11333,17 +11345,17 @@ F: drivers/iio/adc/at91-sama5d2_adc.c F: include/dt-bindings/iio/adc/at91-sama5d2_adc.h MICROCHIP SAMA5D2-COMPATIBLE SHUTDOWN CONTROLLER -M: Nicolas Ferre <[email protected]> +M: Claudiu Beznea <[email protected]> S: Supported F: drivers/power/reset/at91-sama5d2_shdwc.c MICROCHIP SPI DRIVER -M: Nicolas Ferre <[email protected]> +M: Tudor Ambarus <[email protected]> S: Supported F: drivers/spi/spi-atmel.* MICROCHIP SSC DRIVER -M: Nicolas Ferre <[email protected]> +M: Codrin Ciubotariu <[email protected]> L: [email protected] (moderated for non-subscribers) S: Supported F: drivers/misc/atmel-ssc.c @@ -14176,7 +14188,8 @@ F: Documentation/devicetree/bindings/net/qcom,ethqos.txt F: drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c QUALCOMM GENERIC INTERFACE I2C DRIVER -M: Alok Chauhan <[email protected]> +M: Akash Asthana <[email protected]> +M: Mukesh Savaliya <[email protected]> S: Supported @@ -14862,6 +14875,7 @@ F: drivers/s390/block/dasd* F: include/linux/dasd_mod.h S390 IOMMU (PCI) +M: Matthew Rosato <[email protected]> M: Gerald Schaefer <[email protected]> S: Supported @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 8 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -567,7 +567,7 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) ifneq ($(CROSS_COMPILE),) CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%)) GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit)) -CLANG_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR) +CLANG_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE)) GCC_TOOLCHAIN := $(realpath $(GCC_TOOLCHAIN_DIR)/..) endif ifneq ($(GCC_TOOLCHAIN),) @@ -1754,7 +1754,7 @@ PHONY += descend $(build-dirs) descend: $(build-dirs) $(build-dirs): prepare $(Q)$(MAKE) $(build)=$@ \ - single-build=$(if $(filter-out $@/, $(filter $@/%, $(single-no-ko))),1) \ + single-build=$(if $(filter-out $@/, $(filter $@/%, $(KBUILD_SINGLE_TARGETS))),1) \ need-builtin=1 need-modorder=1 clean-dirs := $(addprefix _clean_, $(clean-dirs)) diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi index 348116501aa2..9b1a24cc5e91 100644 --- a/arch/arm/boot/dts/armada-38x.dtsi +++ b/arch/arm/boot/dts/armada-38x.dtsi @@ -342,7 +342,8 @@ comphy: phy@18300 { compatible = "marvell,armada-380-comphy"; - reg = <0x18300 0x100>; + reg-names = "comphy", "conf"; + reg = <0x18300 0x100>, <0x18460 4>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/imx6qdl-icore.dtsi b/arch/arm/boot/dts/imx6qdl-icore.dtsi index 756f3a9f1b4f..12997dae35d9 100644 --- a/arch/arm/boot/dts/imx6qdl-icore.dtsi +++ b/arch/arm/boot/dts/imx6qdl-icore.dtsi @@ -397,7 +397,7 @@ pinctrl_usbotg: usbotggrp { fsl,pins = < - MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x17059 + MX6QDL_PAD_ENET_RX_ER__USB_OTG_ID 0x17059 >; }; @@ -409,6 +409,7 @@ MX6QDL_PAD_SD1_DAT1__SD1_DATA1 0x17070 MX6QDL_PAD_SD1_DAT2__SD1_DATA2 0x17070 MX6QDL_PAD_SD1_DAT3__SD1_DATA3 0x17070 + MX6QDL_PAD_GPIO_1__GPIO1_IO01 0x1b0b0 >; }; diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts index 825924448ab4..14fd1de52a68 100644 --- a/arch/arm/boot/dts/imx6sx-sabreauto.dts +++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts @@ -99,7 +99,7 @@ &fec2 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet2>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <ðphy0>; fsl,magic-packet; status = "okay"; diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi index 3e5fb72f21fc..c99aa273c296 100644 --- a/arch/arm/boot/dts/imx6sx-sdb.dtsi +++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi @@ -213,7 +213,7 @@ &fec2 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet2>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <ðphy2>; status = "okay"; }; diff --git a/arch/arm/boot/dts/keystone-k2g-evm.dts b/arch/arm/boot/dts/keystone-k2g-evm.dts index db640bab8c1d..8b3d64c913d8 100644 --- a/arch/arm/boot/dts/keystone-k2g-evm.dts +++ b/arch/arm/boot/dts/keystone-k2g-evm.dts @@ -402,7 +402,7 @@ &gbe0 { phy-handle = <ðphy0>; - phy-mode = "rgmii-id"; + phy-mode = "rgmii-rxid"; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index bf531efc0610..0f95a6ef8543 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -198,7 +198,7 @@ default-pool { compatible = "shared-dma-pool"; size = <0x6000000>; - alloc-ranges = <0x4a000000 0x6000000>; + alloc-ranges = <0x40000000 0x10000000>; reusable; linux,cma-default; }; diff --git a/arch/arm/boot/dts/sun5i.dtsi b/arch/arm/boot/dts/sun5i.dtsi index e6b036734a64..c2b4fbf552a3 100644 --- a/arch/arm/boot/dts/sun5i.dtsi +++ b/arch/arm/boot/dts/sun5i.dtsi @@ -117,7 +117,7 @@ default-pool { compatible = "shared-dma-pool"; size = <0x6000000>; - alloc-ranges = <0x4a000000 0x6000000>; + alloc-ranges = <0x40000000 0x10000000>; reusable; linux,cma-default; }; diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index ffe1d10a1a84..6d6a37940db2 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -181,7 +181,7 @@ default-pool { compatible = "shared-dma-pool"; size = <0x6000000>; - alloc-ranges = <0x4a000000 0x6000000>; + alloc-ranges = <0x40000000 0x10000000>; reusable; linux,cma-default; }; diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h index f44f448537f2..1a3eedbac4a2 100644 --- a/arch/arm/include/asm/percpu.h +++ b/arch/arm/include/asm/percpu.h @@ -5,6 +5,8 @@ #ifndef _ASM_ARM_PERCPU_H_ #define _ASM_ARM_PERCPU_H_ +#include <asm/thread_info.h> + /* * Same as asm-generic/percpu.h, except that we store the per cpu offset * in the TPIDRPRW. TPIDRPRW only exists on V6K and V7 diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 02ca7adf5375..7fff88e61252 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -683,6 +683,12 @@ static void disable_single_step(struct perf_event *bp) arch_install_hw_breakpoint(bp); } +static int watchpoint_fault_on_uaccess(struct pt_regs *regs, + struct arch_hw_breakpoint *info) +{ + return !user_mode(regs) && info->ctrl.privilege == ARM_BREAKPOINT_USER; +} + static void watchpoint_handler(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { @@ -742,16 +748,27 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr, } pr_debug("watchpoint fired: address = 0x%x\n", info->trigger); + + /* + * If we triggered a user watchpoint from a uaccess routine, + * then handle the stepping ourselves since userspace really + * can't help us with this. + */ + if (watchpoint_fault_on_uaccess(regs, info)) + goto step; + perf_bp_event(wp, regs); /* - * If no overflow handler is present, insert a temporary - * mismatch breakpoint so we can single-step over the - * watchpoint trigger. + * Defer stepping to the overflow handler if one is installed. + * Otherwise, insert a temporary mismatch breakpoint so that + * we can single-step over the watchpoint trigger. */ - if (is_default_overflow_handler(wp)) - enable_single_step(wp, instruction_pointer(regs)); + if (!is_default_overflow_handler(wp)) + goto unlock; +step: + enable_single_step(wp, instruction_pointer(regs)); unlock: rcu_read_unlock(); } diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c index 6bfdca4769a7..fddd08a6e063 100644 --- a/arch/arm/kernel/vdso.c +++ b/arch/arm/kernel/vdso.c @@ -184,6 +184,7 @@ static void __init patch_vdso(void *ehdr) if (!cntvct_ok) { vdso_nullpatch_one(&einfo, "__vdso_gettimeofday"); vdso_nullpatch_one(&einfo, "__vdso_clock_gettime"); + vdso_nullpatch_one(&einfo, "__vdso_clock_gettime64"); } } diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 628028bfbb92..bcd82614c25d 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -966,7 +966,7 @@ void __init create_mapping_late(struct mm_struct *mm, struct map_desc *md, pud_t *pud; p4d = p4d_alloc(mm, pgd_offset(mm, md->virtual), md->virtual); - if (!WARN_ON(!p4d)) + if (WARN_ON(!p4d)) return; pud = pud_alloc(mm, p4d, md->virtual); if (WARN_ON(!pud)) diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index a0d94d063fa8..70f5905954dd 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -137,7 +137,7 @@ export TEXT_OFFSET core-y += arch/arm64/ libs-y := arch/arm64/lib/ $(libs-y) -core-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a +libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a # Default target when executing plain make boot := arch/arm64/boot diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi index 78b1361dfbb9..9ce78a7b117d 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi @@ -161,6 +161,7 @@ resets = <&ccu RST_BUS_VE>; interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>; allwinner,sram = <&ve_sram 1>; + iommus = <&iommu 3>; }; gpu: gpu@1800000 { diff --git a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts index c8243da71041..eb01cc96ba7a 100644 --- a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts +++ b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts @@ -454,10 +454,7 @@ status = "okay"; phy-mode = "2500base-x"; phys = <&cp1_comphy5 2>; - fixed-link { - speed = <2500>; - full-duplex; - }; + managed = "in-band-status"; }; &cp1_spi1 { diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 12f0eb56a1cc..619db9b4c9d5 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -77,9 +77,9 @@ static inline void apply_alternatives_module(void *start, size_t length) { } "663:\n\t" \ newinstr "\n" \ "664:\n\t" \ - ".previous\n\t" \ ".org . - (664b-663b) + (662b-661b)\n\t" \ - ".org . - (662b-661b) + (664b-663b)\n" \ + ".org . - (662b-661b) + (664b-663b)\n\t" \ + ".previous\n" \ ".endif\n" #define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb) \ diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h index b6f7bc6da5fb..93a161b3bf3f 100644 --- a/arch/arm64/include/asm/checksum.h +++ b/arch/arm64/include/asm/checksum.h @@ -24,16 +24,17 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { __uint128_t tmp; u64 sum; + int n = ihl; /* we want it signed */ tmp = *(const __uint128_t *)iph; iph += 16; - ihl -= 4; + n -= 4; tmp += ((tmp >> 64) | (tmp << 64)); sum = tmp >> 64; do { sum += *(const u32 *)iph; iph += 4; - } while (--ihl); + } while (--n > 0); sum += ((sum >> 32) | (sum << 32)); return csum_fold((__force u32)(sum >> 32)); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index c3e6fcc664b1..e21d4a01372f 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -380,9 +380,14 @@ struct kvm_vcpu_arch { #define vcpu_has_sve(vcpu) (system_supports_sve() && \ ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_SVE)) -#define vcpu_has_ptrauth(vcpu) ((system_supports_address_auth() || \ - system_supports_generic_auth()) && \ - ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_PTRAUTH)) +#ifdef CONFIG_ARM64_PTR_AUTH +#define vcpu_has_ptrauth(vcpu) \ + ((cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH) || \ + cpus_have_final_cap(ARM64_HAS_GENERIC_AUTH)) && \ + (vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_PTRAUTH) +#else +#define vcpu_has_ptrauth(vcpu) false +#endif #define vcpu_gp_regs(v) (&(v)->arch.ctxt.gp_regs) diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index ea268d88b6f7..a0c8a0b65259 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -30,7 +30,6 @@ #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/thread_info.h> -#include <asm/pointer_auth.h> DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index d88148bef6b0..5139a5f19256 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -14,7 +14,7 @@ COMPAT_GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE_COMPAT)elfedit)) COMPAT_GCC_TOOLCHAIN := $(realpath $(COMPAT_GCC_TOOLCHAIN_DIR)/..) CC_COMPAT_CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%)) -CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR) +CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE_COMPAT)) CC_COMPAT_CLANG_FLAGS += -no-integrated-as -Qunused-arguments ifneq ($(COMPAT_GCC_TOOLCHAIN),) CC_COMPAT_CLANG_FLAGS += --gcc-toolchain=$(COMPAT_GCC_TOOLCHAIN) diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 8c0035cab6b6..31058e6e7c2a 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1326,7 +1326,7 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr, return true; } -static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr) +static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr, unsigned long sz) { pud_t *pudp; pmd_t *pmdp; @@ -1338,11 +1338,11 @@ static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr) return false; if (pudp) - return kvm_s2pud_exec(pudp); + return sz <= PUD_SIZE && kvm_s2pud_exec(pudp); else if (pmdp) - return kvm_s2pmd_exec(pmdp); + return sz <= PMD_SIZE && kvm_s2pmd_exec(pmdp); else - return kvm_s2pte_exec(ptep); + return sz == PAGE_SIZE && kvm_s2pte_exec(ptep); } static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, @@ -1958,7 +1958,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * execute permissions, and we preserve whatever we have. */ needs_exec = exec_fault || - (fault_status == FSC_PERM && stage2_is_exec(kvm, fault_ipa)); + (fault_status == FSC_PERM && + stage2_is_exec(kvm, fault_ipa, vma_pagesize)); if (vma_pagesize == PUD_SIZE) { pud_t new_pud = kvm_pfn_pud(pfn, mem_type); diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 118953d41763..6dd4171c9530 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -212,6 +212,8 @@ atomic64_set(atomic64_t *v, s64 i) _atomic_spin_unlock_irqrestore(v, flags); } +#define atomic64_set_release(v, i) atomic64_set((v), (i)) + static __inline__ s64 atomic64_read(const atomic64_t *v) { diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h index ab5c215cf46c..068958575871 100644 --- a/arch/parisc/include/asm/cmpxchg.h +++ b/arch/parisc/include/asm/cmpxchg.h @@ -60,6 +60,7 @@ extern void __cmpxchg_called_with_bad_pointer(void); extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old, unsigned int new_); extern u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new_); +extern u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new_); /* don't worry...optimizer will get rid of most of this */ static inline unsigned long @@ -71,6 +72,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size) #endif case 4: return __cmpxchg_u32((unsigned int *)ptr, (unsigned int)old, (unsigned int)new_); + case 1: return __cmpxchg_u8((u8 *)ptr, (u8)old, (u8)new_); } __cmpxchg_called_with_bad_pointer(); return old; diff --git a/arch/parisc/lib/bitops.c b/arch/parisc/lib/bitops.c index 70ffbcf889b8..2e4d1f05a926 100644 --- a/arch/parisc/lib/bitops.c +++ b/arch/parisc/lib/bitops.c @@ -79,3 +79,15 @@ unsigned long __cmpxchg_u32(volatile unsigned int *ptr, unsigned int old, unsign _atomic_spin_unlock_irqrestore(ptr, flags); return (unsigned long)prev; } + +u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new) +{ + unsigned long flags; + u8 prev; + + _atomic_spin_lock_irqsave(ptr, flags); + if ((prev = *ptr) == old) + *ptr = new; + _atomic_spin_unlock_irqrestore(ptr, flags); + return prev; +} diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 0fc8bad878b2..446e54c3f71e 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -3072,10 +3072,18 @@ do_hash_page: ori r0,r0,DSISR_BAD_FAULT_64S@l and. r0,r5,r0 /* weird error? */ bne- handle_page_fault /* if not, try to insert a HPTE */ + + /* + * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then + * don't call hash_page, just fail the fault. This is required to + * prevent re-entrancy problems in the hash code, namely perf + * interrupts hitting while something holds H_PAGE_BUSY, and taking a + * hash fault. See the comment in hash_preload(). + */ ld r11, PACA_THREAD_INFO(r13) - lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */ - andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */ - bne 77f /* then don't call hash_page now */ + lwz r0,TI_PREEMPT(r11) + andis. r0,r0,NMI_MASK@h + bne 77f /* * r3 contains the trap number diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 468169e33c86..9b9f92ad0e7a 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1559,6 +1559,7 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea, pgd_t *pgdir; int rc, ssize, update_flags = 0; unsigned long access = _PAGE_PRESENT | _PAGE_READ | (is_exec ? _PAGE_EXEC : 0); + unsigned long flags; BUG_ON(get_region_id(ea) != USER_REGION_ID); @@ -1592,6 +1593,28 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea, return; #endif /* CONFIG_PPC_64K_PAGES */ + /* + * __hash_page_* must run with interrupts off, as it sets the + * H_PAGE_BUSY bit. It's possible for perf interrupts to hit at any + * time and may take a hash fault reading the user stack, see + * read_user_stack_slow() in the powerpc/perf code. + * + * If that takes a hash fault on the same page as we lock here, it + * will bail out when seeing H_PAGE_BUSY set, and retry the access + * leading to an infinite loop. + * + * Disabling interrupts here does not prevent perf interrupts, but it + * will prevent them taking hash faults (see the NMI test in + * do_hash_page), then read_user_stack's copy_from_user_nofault will + * fail and perf will fall back to read_user_stack_slow(), which + * walks the Linux page tables. + * + * Interrupts must also be off for the duration of the + * mm_is_thread_local test and update, to prevent preempt running the + * mm on another CPU (XXX: this may be racy vs kthread_use_mm). + */ + local_irq_save(flags); + /* Is that local to this CPU ? */ if (mm_is_thread_local(mm)) update_flags |= HPTE_LOCAL_UPDATE; @@ -1614,6 +1637,8 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea, mm_ctx_user_psize(&mm->context), mm_ctx_user_psize(&mm->context), pte_val(*ptep)); + + local_irq_restore(flags); } /* diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index cd6a742ac6ef..01d70280d287 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2179,6 +2179,12 @@ static void __perf_event_interrupt(struct pt_regs *regs) perf_read_regs(regs); + /* + * If perf interrupts hit in a local_irq_disable (soft-masked) region, + * we consider them as NMIs. This is required to prevent hash faults on + * user addresses when reading callchains. See the NMI test in + * do_hash_page. + */ nmi = perf_intr_is_nmi(regs); if (nmi) nmi_enter(); diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index f4adb3684f3d..79e9d55bdf1a 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -95,19 +95,40 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD static void __init setup_initrd(void) { + phys_addr_t start; unsigned long size; - if (initrd_start >= initrd_end) { - pr_info("initrd not found or empty"); + /* Ignore the virtul address computed during device tree parsing */ + initrd_start = initrd_end = 0; + + if (!phys_initrd_size) + return; + /* + * Round the memory region to page boundaries as per free_initrd_mem() + * This allows us to detect whether the pages overlapping the initrd + * are in use, but more importantly, reserves the entire set of pages + * as we don't want these pages allocated for other purposes. + */ + start = round_down(phys_initrd_start, PAGE_SIZE); + size = phys_initrd_size + (phys_initrd_start - start); + size = round_up(size, PAGE_SIZE); + + if (!memblock_is_region_memory(start, size)) { + pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region", + (u64)start, size); goto disable; } - if (__pa_symbol(initrd_end) > PFN_PHYS(max_low_pfn)) { - pr_err("initrd extends beyond end of memory"); + + if (memblock_is_region_reserved(start, size)) { + pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region\n", + (u64)start, size); goto disable; } - size = initrd_end - initrd_start; - memblock_reserve(__pa_symbol(initrd_start), size); + memblock_reserve(start, size); + /* Now convert initrd to virtual addresses */ + initrd_start = (unsigned long)__va(phys_initrd_start); + initrd_end = initrd_start + phys_initrd_size; initrd_below_start_ok = 1; pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n", @@ -126,33 +147,36 @@ void __init setup_bootmem(void) { struct memblock_region *reg; phys_addr_t mem_size = 0; + phys_addr_t total_mem = 0; + phys_addr_t mem_start, end = 0; phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); /* Find the memory region containing the kernel */ for_each_memblock(memory, reg) { - phys_addr_t end = reg->base + reg->size; - - if (reg->base <= vmlinux_start && vmlinux_end <= end) { - mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET); - - /* - * Remove memblock from the end of usable area to the - * end of region - */ - if (reg->base + mem_size < end) - memblock_remove(reg->base + mem_size, - end - reg->base - mem_size); - } + end = reg->base + reg->size; + if (!total_mem) + mem_start = reg->base; + if (reg->base <= vmlinux_start && vmlinux_end <= end) + BUG_ON(reg->size == 0); + total_mem = total_mem + reg->size; } - BUG_ON(mem_size == 0); + + /* + * Remove memblock from the end of usable area to the + * end of region + */ + mem_size = min(total_mem, (phys_addr_t)-PAGE_OFFSET); + if (mem_start + mem_size < end) + memblock_remove(mem_start + mem_size, + end - mem_start - mem_size); /* Reserve from the start of the kernel to the end of the kernel */ memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); - set_max_mapnr(PFN_DOWN(mem_size)); max_pfn = PFN_DOWN(memblock_end_of_DRAM()); max_low_pfn = max_pfn; + set_max_mapnr(max_low_pfn); #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 4a8b61806633..87b4ab3d3c77 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -44,7 +44,7 @@ asmlinkage void __init kasan_early_init(void) (__pa(((uintptr_t) kasan_early_shadow_pmd))), __pgprot(_PAGE_TABLE))); - flush_tlb_all(); + local_flush_tlb_all(); } static void __init populate(void *start, void *end) @@ -79,7 +79,7 @@ static void __init populate(void *start, void *end) pfn_pgd(PFN_DOWN(__pa(&pmd[offset])), __pgprot(_PAGE_TABLE))); - flush_tlb_all(); + local_flush_tlb_all(); memset(start, 0, end - start); } diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c index 1e3df52b2b65..37265f551a11 100644 --- a/arch/s390/kernel/perf_cpum_cf_events.c +++ b/arch/s390/kernel/perf_cpum_cf_events.c @@ -292,7 +292,7 @@ CPUMF_EVENT_ATTR(cf_z15, TX_C_TABORT_SPECIAL, 0x00f5); CPUMF_EVENT_ATTR(cf_z15, DFLT_ACCESS, 0x00f7); CPUMF_EVENT_ATTR(cf_z15, DFLT_CYCLES, 0x00fc); CPUMF_EVENT_ATTR(cf_z15, DFLT_CC, 0x00108); -CPUMF_EVENT_ATTR(cf_z15, DFLT_CCERROR, 0x00109); +CPUMF_EVENT_ATTR(cf_z15, DFLT_CCFINISH, 0x00109); CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0); CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1); @@ -629,7 +629,7 @@ static struct attribute *cpumcf_z15_pmu_event_attr[] __initdata = { CPUMF_EVENT_PTR(cf_z15, DFLT_ACCESS), CPUMF_EVENT_PTR(cf_z15, DFLT_CYCLES), CPUMF_EVENT_PTR(cf_z15, DFLT_CC), - CPUMF_EVENT_PTR(cf_z15, DFLT_CCERROR), + CPUMF_EVENT_PTR(cf_z15, DFLT_CCFINISH), CPUMF_EVENT_PTR(cf_z15, MT_DIAG_CYCLES_ONE_THR_ACTIVE), CPUMF_EVENT_PTR(cf_z15, MT_DIAG_CYCLES_TWO_THR_ACTIVE), NULL, diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h index 22d968bfe9bb..d770da3f8b6f 100644 --- a/arch/sh/include/asm/pgalloc.h +++ b/arch/sh/include/asm/pgalloc.h @@ -12,6 +12,7 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd); extern pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address); extern void pmd_free(struct mm_struct *mm, pmd_t *pmd); +#define __pmd_free_tlb(tlb, pmdp, addr) pmd_free((tlb)->mm, (pmdp)) #endif static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, @@ -33,13 +34,4 @@ do { \ tlb_remove_page((tlb), (pte)); \ } while (0) -#if CONFIG_PGTABLE_LEVELS > 2 -#define __pmd_free_tlb(tlb, pmdp, addr) \ -do { \ - struct page *page = virt_to_page(pmdp); \ - pgtable_pmd_page_dtor(page); \ - tlb_remove_page((tlb), page); \ -} while (0); -#endif - #endif /* __ASM_SH_PGALLOC_H */ diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S index 956a7a03b0c8..9bac5bbb67f3 100644 --- a/arch/sh/kernel/entry-common.S +++ b/arch/sh/kernel/entry-common.S @@ -199,7 +199,7 @@ syscall_trace_entry: mov.l @(OFF_R7,r15), r7 ! arg3 mov.l @(OFF_R3,r15), r3 ! syscall_nr ! - mov.l 2f, r10 ! Number of syscalls + mov.l 6f, r10 ! Number of syscalls cmp/hs r10, r3 bf syscall_call mov #-ENOSYS, r0 @@ -353,7 +353,7 @@ ENTRY(system_call) tst r9, r8 bf syscall_trace_entry ! - mov.l 2f, r8 ! Number of syscalls + mov.l 6f, r8 ! Number of syscalls cmp/hs r8, r3 bt syscall_badsys ! @@ -392,7 +392,7 @@ syscall_exit: #if !defined(CONFIG_CPU_SH2) 1: .long TRA #endif -2: .long NR_syscalls +6: .long NR_syscalls 3: .long sys_call_table 7: .long do_syscall_trace_enter 8: .long do_syscall_trace_leave diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index 5270ff39b9af..a1911fea8739 100644 --- a/arch/x86/include/asm/iosf_mbi.h +++ b/arch/x86/include/asm/iosf_mbi.h @@ -39,6 +39,7 @@ #define BT_MBI_UNIT_PMC 0x04 #define BT_MBI_UNIT_GFX 0x06 #define BT_MBI_UNIT_SMI 0x0C +#define BT_MBI_UNIT_CCK 0x14 #define BT_MBI_UNIT_USB 0x43 #define BT_MBI_UNIT_SATA 0xA3 #define BT_MBI_UNIT_PCIE 0xA6 diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index b037cfa7c0c5..7401cc12c3cc 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -71,6 +71,22 @@ static void printk_stack_address(unsigned long address, int reliable, printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address); } +static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src, + unsigned int nbytes) +{ + if (!user_mode(regs)) + return copy_from_kernel_nofault(buf, (u8 *)src, nbytes); + + /* + * Make sure userspace isn't trying to trick us into dumping kernel + * memory by pointing the userspace instruction pointer at it. + */ + if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX)) + return -EINVAL; + + return copy_from_user_nmi(buf, (void __user *)src, nbytes); +} + /* * There are a couple of reasons for the 2/3rd prologue, courtesy of Linus: * @@ -97,17 +113,8 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) #define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE) u8 opcodes[OPCODE_BUFSIZE]; unsigned long prologue = regs->ip - PROLOGUE_SIZE; - bool bad_ip; - - /* - * Make sure userspace isn't trying to trick us into dumping kernel - * memory by pointing the userspace instruction pointer at it. - */ - bad_ip = user_mode(regs) && - __chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX); - if (bad_ip || copy_from_kernel_nofault(opcodes, (u8 *)prologue, - OPCODE_BUFSIZE)) { + if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { printk("%sCode: Bad RIP value.\n", loglvl); } else { printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index bda2e5eaca0e..ad3a2b37927d 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1074,7 +1074,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of copy_part(offsetof(struct fxregs_state, st_space), 128, &xsave->i387.st_space, &kbuf, &offset_start, &count); if (header.xfeatures & XFEATURE_MASK_SSE) - copy_part(xstate_offsets[XFEATURE_MASK_SSE], 256, + copy_part(xstate_offsets[XFEATURE_SSE], 256, &xsave->i387.xmm_space, &kbuf, &offset_start, &count); /* * Fill xsave->i387.sw_reserved value for ptrace frame: diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index f3c76252247d..282b4ee1339f 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -207,7 +207,7 @@ spurious_8259A_irq: * lets ACK and report it. [once per IRQ] */ if (!(spurious_irq_mask & irqmask)) { - printk(KERN_DEBUG + printk_deferred(KERN_DEBUG "spurious 8259A interrupt: IRQ%d.\n", irq); spurious_irq_mask |= irqmask; } diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 6ad43fc44556..2fd698e28e4d 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -58,7 +58,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, * or a page fault), which can make frame pointers * unreliable. */ - if (IS_ENABLED(CONFIG_FRAME_POINTER)) return -EINVAL; } @@ -81,10 +80,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, if (unwind_error(&state)) return -EINVAL; - /* Success path for non-user tasks, i.e. kthreads and idle tasks */ - if (!(task->flags & (PF_KTHREAD | PF_IDLE))) - return -EINVAL; - return 0; } diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 7f969b2d240f..ec88bbe08a32 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -440,8 +440,11 @@ bool unwind_next_frame(struct unwind_state *state) /* * Find the orc_entry associated with the text address. * - * Decrement call return addresses by one so they work for sibling - * calls and calls to noreturn functions. + * For a call frame (as opposed to a signal frame), state->ip points to + * the instruction after the call. That instruction's stack layout + * could be different from the call instruction's layout, for example + * if the call was to a noreturn function. So get the ORC data for the + * call instruction itself. */ orc = orc_find(state->signal ? state->ip : state->ip - 1); if (!orc) { @@ -662,6 +665,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, state->sp = task->thread.sp; state->bp = READ_ONCE_NOCHECK(frame->bp); state->ip = READ_ONCE_NOCHECK(frame->ret_addr); + state->signal = (void *)state->ip == ret_from_fork; } if (get_stack_info((unsigned long *)state->sp, state->task, diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 3bfc8dd8a43d..9a03e5b23135 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -358,6 +358,7 @@ SECTIONS .bss : AT(ADDR(.bss) - LOAD_OFFSET) { __bss_start = .; *(.bss..page_aligned) + . = ALIGN(PAGE_SIZE); *(BSS_MAIN) BSS_DECRYPTED . = ALIGN(PAGE_SIZE); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 5bf72fc86a8e..4ce2ddd26c0b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2195,7 +2195,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data) { struct kvm_lapic *apic = vcpu->arch.apic; - if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) || + if (!kvm_apic_present(vcpu) || apic_lvtt_oneshot(apic) || apic_lvtt_period(apic)) return; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index c0da4dd78ac5..5bbf76189afa 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1090,7 +1090,7 @@ static void init_vmcb(struct vcpu_svm *svm) svm->nested.vmcb = 0; svm->vcpu.arch.hflags = 0; - if (pause_filter_count) { + if (!kvm_pause_in_guest(svm->vcpu.kvm)) { control->pause_filter_count = pause_filter_count; if (pause_filter_thresh) control->pause_filter_thresh = pause_filter_thresh; @@ -2693,7 +2693,7 @@ static int pause_interception(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; bool in_kernel = (svm_get_cpl(vcpu) == 0); - if (pause_filter_thresh) + if (!kvm_pause_in_guest(vcpu->kvm)) grow_ple_window(vcpu); kvm_vcpu_on_spin(vcpu, in_kernel); @@ -3780,7 +3780,7 @@ static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) { - if (pause_filter_thresh) + if (!kvm_pause_in_guest(vcpu->kvm)) shrink_ple_window(vcpu); } @@ -3958,6 +3958,9 @@ static void svm_vm_destroy(struct kvm *kvm) static int svm_vm_init(struct kvm *kvm) { + if (!pause_filter_count || !pause_filter_thresh) + kvm->arch.pause_in_guest = true; + if (avic) { int ret = avic_vm_init(kvm); if (ret) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d4a4cec034d0..11e4df560018 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -6079,6 +6079,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON)) return -EINVAL; + if (kvm_state->hdr.vmx.flags & ~KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE) + return -EINVAL; + /* * SMM temporarily disables VMX, so we cannot be in guest mode, * nor can VMLAUNCH/VMRESUME be pending. Outside SMM, SMM flags @@ -6108,9 +6111,16 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, if (ret) return ret; - /* Empty 'VMXON' state is permitted */ - if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12)) - return 0; + /* Empty 'VMXON' state is permitted if no VMCS loaded */ + if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12)) { + /* See vmx_has_valid_vmcs12. */ + if ((kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE) || + (kvm_state->flags & KVM_STATE_NESTED_EVMCS) || + (kvm_state->hdr.vmx.vmcs12_pa != -1ull)) + return -EINVAL; + else + return 0; + } if (kvm_state->hdr.vmx.vmcs12_pa != -1ull) { if (kvm_state->hdr.vmx.vmcs12_pa == kvm_state->hdr.vmx.vmxon_pa || diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 758bccc26cf9..197148d76b8f 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -47,6 +47,11 @@ static inline struct vmcs12 *get_shadow_vmcs12(struct kvm_vcpu *vcpu) return to_vmx(vcpu)->nested.cached_shadow_vmcs12; } +/* + * Note: the same condition is checked against the state provided by userspace + * in vmx_set_nested_state; if it is satisfied, the nested state must include + * the VMCS12. + */ static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); diff --git a/arch/xtensa/include/asm/checksum.h b/arch/xtensa/include/asm/checksum.h index d8292cc9ebdf..243a5fe79d3c 100644 --- a/arch/xtensa/include/asm/checksum.h +++ b/arch/xtensa/include/asm/checksum.h @@ -57,7 +57,7 @@ static inline __wsum csum_and_copy_from_user(const void __user *src, void *dst, int len, __wsum sum, int *err_ptr) { - if (access_ok(dst, len)) + if (access_ok(src, len)) return csum_partial_copy_generic((__force const void *)src, dst, len, sum, err_ptr, NULL); if (len) diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 42c672f1584e..cbe6aa77d50d 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -947,7 +947,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, trace_binder_unmap_user_end(alloc, index); } mmap_read_unlock(mm); - mmput(mm); + mmput_async(mm); trace_binder_unmap_kernel_start(alloc, index); diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c index d9fd70280482..7f814da3c2d0 100644 --- a/drivers/atm/atmtcp.c +++ b/drivers/atm/atmtcp.c @@ -433,9 +433,15 @@ static int atmtcp_remove_persistent(int itf) return -EMEDIUMTYPE; } dev_data = PRIV(dev); - if (!dev_data->persist) return 0; + if (!dev_data->persist) { + atm_dev_put(dev); + return 0; + } dev_data->persist = 0; - if (PRIV(dev)->vcc) return 0; + if (PRIV(dev)->vcc) { + atm_dev_put(dev); + return 0; + } kfree(dev_data); atm_dev_put(dev); atm_dev_deregister(dev); diff --git a/drivers/base/property.c b/drivers/base/property.c index 1e6d75e65938..d58aa98fe964 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -721,7 +721,7 @@ struct fwnode_handle *device_get_next_child_node(struct device *dev, return next; /* When no more children in primary, continue with secondary */ - if (!IS_ERR_OR_NULL(fwnode->secondary)) + if (fwnode && !IS_ERR_OR_NULL(fwnode->secondary)) next = fwnode_get_next_child_node(fwnode->secondary, child); return next; diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 4f513fa3362f..191c97b84715 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -2865,6 +2865,24 @@ static int sysc_check_disabled_devices(struct sysc *ddata) return error; } +/* + * Ignore timers tagged with no-reset and no-idle. These are likely in use, + * for example by drivers/clocksource/timer-ti-dm-systimer.c. If more checks + * are needed, we could also look at the timer register configuration. + */ +static int sysc_check_active_timer(struct sysc *ddata) +{ + if (ddata->cap->type != TI_SYSC_OMAP2_TIMER && + ddata->cap->type != TI_SYSC_OMAP4_TIMER) + return 0; + + if ((ddata->cfg.quirks & SYSC_QUIRK_NO_RESET_ON_INIT) && + (ddata->cfg.quirks & SYSC_QUIRK_NO_IDLE)) + return -EBUSY; + + return 0; +} + static const struct of_device_id sysc_match_table[] = { { .compatible = "simple-bus", }, { /* sentinel */ }, @@ -2921,6 +2939,10 @@ static int sysc_probe(struct platform_device *pdev) if (error) return error; + error = sysc_check_active_timer(ddata); + if (error) + return error; + error = sysc_get_clocks(ddata); if (error) return error; diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 934c92dcb9ab..687d4af6945d 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -814,7 +814,8 @@ static struct inode *devmem_inode; #ifdef CONFIG_IO_STRICT_DEVMEM void revoke_devmem(struct resource *res) { - struct inode *inode = READ_ONCE(devmem_inode); + /* pairs with smp_store_release() in devmem_init_inode() */ + struct inode *inode = smp_load_acquire(&devmem_inode); /* * Check that the initialization has completed. Losing the race @@ -1028,8 +1029,11 @@ static int devmem_init_inode(void) return rc; } - /* publish /dev/mem initialized */ - WRITE_ONCE(devmem_inode, inode); + /* + * Publish /dev/mem initialized. + * Pairs with smp_load_acquire() in revoke_devmem(). + */ + smp_store_release(&devmem_inode, inode); return 0; } diff --git a/drivers/char/random.c b/drivers/char/random.c index 2a41b21623ae..d20ba1b104ca 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1277,6 +1277,7 @@ void add_interrupt_randomness(int irq, int irq_flags) fast_mix(fast_pool); add_interrupt_bench(cycles); + this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]); if (unlikely(crng_init == 0)) { if ((fast_pool->count >= 64) && diff --git a/drivers/char/tpm/eventlog/acpi.c b/drivers/char/tpm/eventlog/acpi.c index 63ada5e53f13..3633ed70f48f 100644 --- a/drivers/char/tpm/eventlog/acpi.c +++ b/drivers/char/tpm/eventlog/acpi.c @@ -49,9 +49,9 @@ int tpm_read_log_acpi(struct tpm_chip *chip) void __iomem *virt; u64 len, start; struct tpm_bios_log *log; - - if (chip->flags & TPM_CHIP_FLAG_TPM2) - return -ENODEV; + struct acpi_table_tpm2 *tbl; + struct acpi_tpm2_phy *tpm2_phy; + int format; log = &chip->log; @@ -61,23 +61,44 @@ int tpm_read_log_acpi(struct tpm_chip *chip) if (!chip->acpi_dev_handle) return -ENODEV; - /* Find TCPA entry in RSDT (ACPI_LOGICAL_ADDRESSING) */ - status = acpi_get_table(ACPI_SIG_TCPA, 1, - (struct acpi_table_header **)&buff); - - if (ACPI_FAILURE(status)) - return -ENODEV; - - switch(buff->platform_class) { - case BIOS_SERVER: - len = buff->server.log_max_len; - start = buff->server.log_start_addr; - break; - case BIOS_CLIENT: - default: - len = buff->client.log_max_len; - start = buff->client.log_start_addr; - break; + if (chip->flags & TPM_CHIP_FLAG_TPM2) { + status = acpi_get_table("TPM2", 1, + (struct acpi_table_header **)&tbl); + if (ACPI_FAILURE(status)) + return -ENODEV; + + if (tbl->header.length < + sizeof(*tbl) + sizeof(struct acpi_tpm2_phy)) + return -ENODEV; + + tpm2_phy = (void *)tbl + sizeof(*tbl); + len = tpm2_phy->log_area_minimum_length; + + start = tpm2_phy->log_area_start_address; + if (!start || !len) + return -ENODEV; + + format = EFI_TCG2_EVENT_LOG_FORMAT_TCG_2; + } else { + /* Find TCPA entry in RSDT (ACPI_LOGICAL_ADDRESSING) */ + status = acpi_get_table(ACPI_SIG_TCPA, 1, + (struct acpi_table_header **)&buff); + if (ACPI_FAILURE(status)) + return -ENODEV; + + switch (buff->platform_class) { + case BIOS_SERVER: + len = buff->server.log_max_len; + start = buff->server.log_start_addr; + break; + case BIOS_CLIENT: + default: + len = buff->client.log_max_len; + start = buff->client.log_start_addr; + break; + } + + format = EFI_TCG2_EVENT_LOG_FORMAT_TCG_1_2; } if (!len) { dev_warn(&chip->dev, "%s: TCPA log area empty\n", __func__); @@ -98,7 +119,7 @@ int tpm_read_log_acpi(struct tpm_chip *chip) memcpy_fromio(log->bios_event_log, virt, len); acpi_os_unmap_iomem(virt, len); - return EFI_TCG2_EVENT_LOG_FORMAT_TCG_1_2; + return format; err: kfree(log->bios_event_log); diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index 8c77e88012e9..ddaeceb7e109 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -386,13 +386,8 @@ struct tpm_chip *tpm_chip_alloc(struct device *pdev, chip->cdev.owner = THIS_MODULE; chip->cdevs.owner = THIS_MODULE; - chip->work_space.context_buf = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!chip->work_space.context_buf) { - rc = -ENOMEM; - goto out; - } - chip->work_space.session_buf = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!chip->work_space.session_buf) { + rc = tpm2_init_space(&chip->work_space, TPM2_SPACE_BUFFER_SIZE); + if (rc) { rc = -ENOMEM; goto out; } diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index 0fbcede241ea..947d1db0a5cc 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -59,6 +59,9 @@ enum tpm_addr { #define TPM_TAG_RQU_COMMAND 193 +/* TPM2 specific constants. */ +#define TPM2_SPACE_BUFFER_SIZE 16384 /* 16 kB */ + struct stclear_flags_t { __be16 tag; u8 deactivated; @@ -228,7 +231,7 @@ unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal); int tpm2_probe(struct tpm_chip *chip); int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip); int tpm2_find_cc(struct tpm_chip *chip, u32 cc); -int tpm2_init_space(struct tpm_space *space); +int tpm2_init_space(struct tpm_space *space, unsigned int buf_size); void tpm2_del_space(struct tpm_chip *chip, struct tpm_space *space); void tpm2_flush_space(struct tpm_chip *chip); int tpm2_prepare_space(struct tpm_chip *chip, struct tpm_space *space, u8 *cmd, diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c index 982d341d8837..784b8b3cb903 100644 --- a/drivers/char/tpm/tpm2-space.c +++ b/drivers/char/tpm/tpm2-space.c @@ -38,18 +38,21 @@ static void tpm2_flush_sessions(struct tpm_chip *chip, struct tpm_space *space) } } -int tpm2_init_space(struct tpm_space *space) +int tpm2_init_space(struct tpm_space *space, unsigned int buf_size) { - space->context_buf = kzalloc(PAGE_SIZE, GFP_KERNEL); + space->context_buf = kzalloc(buf_size, GFP_KERNEL); if (!space->context_buf) return -ENOMEM; - space->session_buf = kzalloc(PAGE_SIZE, GFP_KERNEL); + space->session_buf = kzalloc(buf_size, GFP_KERNEL); if (space->session_buf == NULL) { kfree(space->context_buf); + /* Prevent caller getting a dangling pointer. */ + space->context_buf = NULL; return -ENOMEM; } + space->buf_size = buf_size; return 0; } @@ -311,8 +314,10 @@ int tpm2_prepare_space(struct tpm_chip *chip, struct tpm_space *space, u8 *cmd, sizeof(space->context_tbl)); memcpy(&chip->work_space.session_tbl, &space->session_tbl, sizeof(space->session_tbl)); - memcpy(chip->work_space.context_buf, space->context_buf, PAGE_SIZE); - memcpy(chip->work_space.session_buf, space->session_buf, PAGE_SIZE); + memcpy(chip->work_space.context_buf, space->context_buf, + space->buf_size); + memcpy(chip->work_space.session_buf, space->session_buf, + space->buf_size); rc = tpm2_load_space(chip); if (rc) { @@ -492,7 +497,7 @@ static int tpm2_save_space(struct tpm_chip *chip) continue; rc = tpm2_save_context(chip, space->context_tbl[i], - space->context_buf, PAGE_SIZE, + space->context_buf, space->buf_size, &offset); if (rc == -ENOENT) { space->context_tbl[i] = 0; @@ -509,9 +514,8 @@ static int tpm2_save_space(struct tpm_chip *chip) continue; rc = tpm2_save_context(chip, space->session_tbl[i], - space->session_buf, PAGE_SIZE, + space->session_buf, space->buf_size, &offset); - if (rc == -ENOENT) { /* handle error saving session, just forget it */ space->session_tbl[i] = 0; @@ -557,8 +561,10 @@ int tpm2_commit_space(struct tpm_chip *chip, struct tpm_space *space, sizeof(space->context_tbl)); memcpy(&space->session_tbl, &chip->work_space.session_tbl, sizeof(space->session_tbl)); - memcpy(space->context_buf, chip->work_space.context_buf, PAGE_SIZE); - memcpy(space->session_buf, chip->work_space.session_buf, PAGE_SIZE); + memcpy(space->context_buf, chip->work_space.context_buf, + space->buf_size); + memcpy(space->session_buf, chip->work_space.session_buf, + space->buf_size); return 0; out: diff --git a/drivers/char/tpm/tpmrm-dev.c b/drivers/char/tpm/tpmrm-dev.c index 7a0a7051a06f..eef0fb06ea83 100644 --- a/drivers/char/tpm/tpmrm-dev.c +++ b/drivers/char/tpm/tpmrm-dev.c @@ -21,7 +21,7 @@ static int tpmrm_open(struct inode *inode, struct file *file) if (priv == NULL) return -ENOMEM; - rc = tpm2_init_space(&priv->space); + rc = tpm2_init_space(&priv->space, TPM2_SPACE_BUFFER_SIZE); if (rc) { kfree(priv); return -ENOMEM; diff --git a/drivers/clocksource/timer-ti-dm-systimer.c b/drivers/clocksource/timer-ti-dm-systimer.c index 6fd1f219a512..f6fd1c1cc527 100644 --- a/drivers/clocksource/timer-ti-dm-systimer.c +++ b/drivers/clocksource/timer-ti-dm-systimer.c @@ -19,7 +19,7 @@ /* For type1, set SYSC_OMAP2_CLOCKACTIVITY for fck off on idle, l4 clock on */ #define DMTIMER_TYPE1_ENABLE ((1 << 9) | (SYSC_IDLE_SMART << 3) | \ SYSC_OMAP2_ENAWAKEUP | SYSC_OMAP2_AUTOIDLE) - +#define DMTIMER_TYPE1_DISABLE (SYSC_OMAP2_SOFTRESET | SYSC_OMAP2_AUTOIDLE) #define DMTIMER_TYPE2_ENABLE (SYSC_IDLE_SMART_WKUP << 2) #define DMTIMER_RESET_WAIT 100000 @@ -44,6 +44,8 @@ struct dmtimer_systimer { u8 ctrl; u8 wakeup; u8 ifctrl; + struct clk *fck; + struct clk *ick; unsigned long rate; }; @@ -298,16 +300,20 @@ static void __init dmtimer_systimer_select_best(void) } /* Interface clocks are only available on some SoCs variants */ -static int __init dmtimer_systimer_init_clock(struct device_node *np, +static int __init dmtimer_systimer_init_clock(struct dmtimer_systimer *t, + struct device_node *np, const char *name, unsigned long *rate) { struct clk *clock; unsigned long r; + bool is_ick = false; int error; + is_ick = !strncmp(name, "ick", 3); + clock = of_clk_get_by_name(np, name); - if ((PTR_ERR(clock) == -EINVAL) && !strncmp(name, "ick", 3)) + if ((PTR_ERR(clock) == -EINVAL) && is_ick) return 0; else if (IS_ERR(clock)) return PTR_ERR(clock); @@ -320,6 +326,11 @@ static int __init dmtimer_systimer_init_clock(struct device_node *np, if (!r) return -ENODEV; + if (is_ick) + t->ick = clock; + else + t->fck = clock; + *rate = r; return 0; @@ -339,7 +350,10 @@ static void dmtimer_systimer_enable(struct dmtimer_systimer *t) static void dmtimer_systimer_disable(struct dmtimer_systimer *t) { - writel_relaxed(0, t->base + t->sysc); + if (!dmtimer_systimer_revision1(t)) + return; + + writel_relaxed(DMTIMER_TYPE1_DISABLE, t->base + t->sysc); } static int __init dmtimer_systimer_setup(struct device_node *np, @@ -366,13 +380,13 @@ static int __init dmtimer_systimer_setup(struct device_node *np, pr_err("%s: clock source init failed: %i\n", __func__, error); /* For ti-sysc, we have timer clocks at the parent module level */ - error = dmtimer_systimer_init_clock(np->parent, "fck", &rate); + error = dmtimer_systimer_init_clock(t, np->parent, "fck", &rate); if (error) goto err_unmap; t->rate = rate; - error = dmtimer_systimer_init_clock(np->parent, "ick", &rate); + error = dmtimer_systimer_init_clock(t, np->parent, "ick", &rate); if (error) goto err_unmap; @@ -496,12 +510,18 @@ static void omap_clockevent_idle(struct clock_event_device *evt) struct dmtimer_systimer *t = &clkevt->t; dmtimer_systimer_disable(t); + clk_disable(t->fck); } static void omap_clockevent_unidle(struct clock_event_device *evt) { struct dmtimer_clockevent *clkevt = to_dmtimer_clockevent(evt); struct dmtimer_systimer *t = &clkevt->t; + int error; + + error = clk_enable(t->fck); + if (error) + pr_err("could not enable timer fck on resume: %i\n", error); dmtimer_systimer_enable(t); writel_relaxed(OMAP_TIMER_INT_OVERFLOW, t->base + t->irq_ena); @@ -570,8 +590,8 @@ static int __init dmtimer_clockevent_init(struct device_node *np) 3, /* Timer internal resynch latency */ 0xffffffff); - if (of_device_is_compatible(np, "ti,am33xx") || - of_device_is_compatible(np, "ti,am43")) { + if (of_machine_is_compatible("ti,am33xx") || + of_machine_is_compatible("ti,am43")) { dev->suspend = omap_clockevent_idle; dev->resume = omap_clockevent_unidle; } @@ -616,12 +636,18 @@ static void dmtimer_clocksource_suspend(struct clocksource *cs) clksrc->loadval = readl_relaxed(t->base + t->counter); dmtimer_systimer_disable(t); + clk_disable(t->fck); } static void dmtimer_clocksource_resume(struct clocksource *cs) { struct dmtimer_clocksource *clksrc = to_dmtimer_clocksource(cs); struct dmtimer_systimer *t = &clksrc->t; + int error; + + error = clk_enable(t->fck); + if (error) + pr_err("could not enable timer fck on resume: %i\n", error); dmtimer_systimer_enable(t); writel_relaxed(clksrc->loadval, t->base + t->counter); @@ -653,8 +679,8 @@ static int __init dmtimer_clocksource_init(struct device_node *np) dev->mask = CLOCKSOURCE_MASK(32); dev->flags = CLOCK_SOURCE_IS_CONTINUOUS; - if (of_device_is_compatible(np, "ti,am33xx") || - of_device_is_compatible(np, "ti,am43")) { + /* Unlike for clockevent, legacy code sets suspend only for am4 */ + if (of_machine_is_compatible("ti,am43")) { dev->suspend = dmtimer_clocksource_suspend; dev->resume = dmtimer_clocksource_resume; } diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c index f200fae6f7cb..54093115eb95 100644 --- a/drivers/crypto/chelsio/chtls/chtls_cm.c +++ b/drivers/crypto/chelsio/chtls/chtls_cm.c @@ -102,7 +102,7 @@ static struct net_device *chtls_find_netdev(struct chtls_dev *cdev, case PF_INET: if (likely(!inet_sk(sk)->inet_rcv_saddr)) return ndev; - ndev = ip_dev_find(&init_net, inet_sk(sk)->inet_rcv_saddr); + ndev = __ip_dev_find(&init_net, inet_sk(sk)->inet_rcv_saddr, false); break; #if IS_ENABLED(CONFIG_IPV6) case PF_INET6: diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c index e1401d9cc756..2e9acae1cba3 100644 --- a/drivers/crypto/chelsio/chtls/chtls_io.c +++ b/drivers/crypto/chelsio/chtls/chtls_io.c @@ -1052,14 +1052,15 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) &record_type); if (err) goto out_err; + + /* Avoid appending tls handshake, alert to tls data */ + if (skb) + tx_skb_finalize(skb); } recordsz = size; csk->tlshws.txleft = recordsz; csk->tlshws.type = record_type; - - if (skb) - ULP_SKB_CB(skb)->ulp.tls.type = record_type; } if (!skb || (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) || diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c index c2f1d4e6630b..feb7fe6f2da7 100644 --- a/drivers/firmware/efi/efi-pstore.c +++ b/drivers/firmware/efi/efi-pstore.c @@ -356,10 +356,7 @@ static struct pstore_info efi_pstore_info = { static __init int efivars_pstore_init(void) { - if (!efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES)) - return 0; - - if (!efivars_kobject()) + if (!efivars_kobject() || !efivar_supports_writes()) return 0; if (efivars_pstore_disable) diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 5114cae4ec97..fdd1db025dbf 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -176,11 +176,13 @@ static struct efivar_operations generic_ops; static int generic_ops_register(void) { generic_ops.get_variable = efi.get_variable; - generic_ops.set_variable = efi.set_variable; - generic_ops.set_variable_nonblocking = efi.set_variable_nonblocking; generic_ops.get_next_variable = efi.get_next_variable; generic_ops.query_variable_store = efi_query_variable_store; + if (efi_rt_services_supported(EFI_RT_SUPPORTED_SET_VARIABLE)) { + generic_ops.set_variable = efi.set_variable; + generic_ops.set_variable_nonblocking = efi.set_variable_nonblocking; + } return efivars_register(&generic_efivars, &generic_ops, efi_kobj); } @@ -382,7 +384,8 @@ static int __init efisubsys_init(void) return -ENOMEM; } - if (efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES)) { + if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE | + EFI_RT_SUPPORTED_GET_NEXT_VARIABLE_NAME)) { efivar_ssdt_load(); error = generic_ops_register(); if (error) @@ -416,7 +419,8 @@ static int __init efisubsys_init(void) err_remove_group: sysfs_remove_group(efi_kobj, &efi_subsys_attr_group); err_unregister: - if (efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES)) + if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE | + EFI_RT_SUPPORTED_GET_NEXT_VARIABLE_NAME)) generic_ops_unregister(); err_put: kobject_put(efi_kobj); diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index 26528a46d99e..dcea137142b3 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -680,11 +680,8 @@ int efivars_sysfs_init(void) struct kobject *parent_kobj = efivars_kobject(); int error = 0; - if (!efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES)) - return -ENODEV; - /* No efivars has been registered yet */ - if (!parent_kobj) + if (!parent_kobj || !efivar_supports_writes()) return 0; printk(KERN_INFO "EFI Variables Facility v%s %s\n", EFIVARS_VERSION, diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index 4cce372edaf4..75daaf20374e 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -6,8 +6,7 @@ # enabled, even if doing so doesn't break the build. # cflags-$(CONFIG_X86_32) := -march=i386 -cflags-$(CONFIG_X86_64) := -mcmodel=small \ - $(call cc-option,-maccumulate-outgoing-args) +cflags-$(CONFIG_X86_64) := -mcmodel=small cflags-$(CONFIG_X86) += -m$(BITS) -D__KERNEL__ \ -fPIC -fno-strict-aliasing -mno-red-zone \ -mno-mmx -mno-sse -fshort-wchar \ diff --git a/drivers/firmware/efi/libstub/alignedmem.c b/drivers/firmware/efi/libstub/alignedmem.c index cc89c4d6196f..1de9878ddd3a 100644 --- a/drivers/firmware/efi/libstub/alignedmem.c +++ b/drivers/firmware/efi/libstub/alignedmem.c @@ -44,7 +44,7 @@ efi_status_t efi_allocate_pages_aligned(unsigned long size, unsigned long *addr, *addr = ALIGN((unsigned long)alloc_addr, align); if (slack > 0) { - int l = (alloc_addr % align) / EFI_PAGE_SIZE; + int l = (alloc_addr & (align - 1)) / EFI_PAGE_SIZE; if (l) { efi_bs_call(free_pages, alloc_addr, slack - l + 1); diff --git a/drivers/firmware/efi/libstub/efi-stub.c b/drivers/firmware/efi/libstub/efi-stub.c index 3318ec3f8e5b..a5a405d8ab44 100644 --- a/drivers/firmware/efi/libstub/efi-stub.c +++ b/drivers/firmware/efi/libstub/efi-stub.c @@ -122,23 +122,6 @@ static unsigned long get_dram_base(void) } /* - * This function handles the architcture specific differences between arm and - * arm64 regarding where the kernel image must be loaded and any memory that - * must be reserved. On failure it is required to free all - * all allocations it has made. - */ -efi_status_t handle_kernel_image(unsigned long *image_addr, - unsigned long *image_size, - unsigned long *reserve_addr, - unsigned long *reserve_size, - unsigned long dram_base, - efi_loaded_image_t *image); - -asmlinkage void __noreturn efi_enter_kernel(unsigned long entrypoint, - unsigned long fdt_addr, - unsigned long fdt_size); - -/* * EFI entry point for the arm/arm64 EFI stubs. This is the entrypoint * that is described in the PE/COFF header. Most of the code is the same * for both archictectures, with the arch-specific code provided in the diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 2c9d42264c29..85050f5a1b28 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -776,6 +776,22 @@ efi_status_t efi_load_initrd(efi_loaded_image_t *image, unsigned long *load_size, unsigned long soft_limit, unsigned long hard_limit); +/* + * This function handles the architcture specific differences between arm and + * arm64 regarding where the kernel image must be loaded and any memory that + * must be reserved. On failure it is required to free all + * all allocations it has made. + */ +efi_status_t handle_kernel_image(unsigned long *image_addr, + unsigned long *image_size, + unsigned long *reserve_addr, + unsigned long *reserve_size, + unsigned long dram_base, + efi_loaded_image_t *image); + +asmlinkage void __noreturn efi_enter_kernel(unsigned long entrypoint, + unsigned long fdt_addr, + unsigned long fdt_size); void efi_handle_post_ebs_state(void); diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 5a48d996ed71..3672539cb96e 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -8,6 +8,7 @@ #include <linux/efi.h> #include <linux/pci.h> +#include <linux/stddef.h> #include <asm/efi.h> #include <asm/e820/types.h> @@ -361,8 +362,6 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, int options_size = 0; efi_status_t status; char *cmdline_ptr; - unsigned long ramdisk_addr; - unsigned long ramdisk_size; efi_system_table = sys_table_arg; @@ -390,8 +389,9 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, hdr = &boot_params->hdr; - /* Copy the second sector to boot_params */ - memcpy(&hdr->jump, image_base + 512, 512); + /* Copy the setup header from the second sector to boot_params */ + memcpy(&hdr->jump, image_base + 512, + sizeof(struct setup_header) - offsetof(struct setup_header, jump)); /* * Fill out some of the header fields ourselves because the diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 5f2a4d162795..973eef234b36 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -1229,3 +1229,9 @@ out: return rv; } EXPORT_SYMBOL_GPL(efivars_unregister); + +int efivar_supports_writes(void) +{ + return __efivars && __efivars->ops->set_variable; +} +EXPORT_SYMBOL_GPL(efivar_supports_writes); diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c index 039e0f91dba8..6945c3c96637 100644 --- a/drivers/firmware/qemu_fw_cfg.c +++ b/drivers/firmware/qemu_fw_cfg.c @@ -605,8 +605,10 @@ static int fw_cfg_register_file(const struct fw_cfg_file *f) /* register entry under "/sys/firmware/qemu_fw_cfg/by_key/" */ err = kobject_init_and_add(&entry->kobj, &fw_cfg_sysfs_entry_ktype, fw_cfg_sel_ko, "%d", entry->select); - if (err) - goto err_register; + if (err) { + kobject_put(&entry->kobj); + return err; + } /* add raw binary content access */ err = sysfs_create_bin_file(&entry->kobj, &fw_cfg_sysfs_attr_raw); @@ -622,7 +624,6 @@ static int fw_cfg_register_file(const struct fw_cfg_file *f) err_add_raw: kobject_del(&entry->kobj); -err_register: kfree(entry); return err; } diff --git a/drivers/fpga/dfl-afu-main.c b/drivers/fpga/dfl-afu-main.c index b0c31789a909..3fa2c5992173 100644 --- a/drivers/fpga/dfl-afu-main.c +++ b/drivers/fpga/dfl-afu-main.c @@ -83,7 +83,8 @@ int __afu_port_disable(struct platform_device *pdev) * on this port and minimum soft reset pulse width has elapsed. * Driver polls port_soft_reset_ack to determine if reset done by HW. */ - if (readq_poll_timeout(base + PORT_HDR_CTRL, v, v & PORT_CTRL_SFTRST, + if (readq_poll_timeout(base + PORT_HDR_CTRL, v, + v & PORT_CTRL_SFTRST_ACK, RST_POLL_INVL, RST_POLL_TIMEOUT)) { dev_err(&pdev->dev, "timeout, fail to reset device\n"); return -ETIMEDOUT; diff --git a/drivers/fpga/dfl-pci.c b/drivers/fpga/dfl-pci.c index 538755062ab7..a78c409bf2c4 100644 --- a/drivers/fpga/dfl-pci.c +++ b/drivers/fpga/dfl-pci.c @@ -227,7 +227,6 @@ static int cci_pci_sriov_configure(struct pci_dev *pcidev, int num_vfs) { struct cci_drvdata *drvdata = pci_get_drvdata(pcidev); struct dfl_fpga_cdev *cdev = drvdata->cdev; - int ret = 0; if (!num_vfs) { /* @@ -239,6 +238,8 @@ static int cci_pci_sriov_configure(struct pci_dev *pcidev, int num_vfs) dfl_fpga_cdev_config_ports_pf(cdev); } else { + int ret; + /* * before enable SRIOV, put released ports into VF access mode * first of all. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index d7e17e34fee1..21292098bc02 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -692,9 +692,10 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file return n ? -EFAULT : 0; } case AMDGPU_INFO_DEV_INFO: { - struct drm_amdgpu_info_device dev_info = {}; + struct drm_amdgpu_info_device dev_info; uint64_t vm_size; + memset(&dev_info, 0, sizeof(dev_info)); dev_info.device_id = dev->pdev->device; dev_info.chip_rev = adev->rev_id; dev_info.external_rev = adev->external_rev_id; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 86ffa0c2880f..710edc70e37e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8717,20 +8717,38 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, * the same resource. If we have a new DC context as part of * the DM atomic state from validation we need to free it and * retain the existing one instead. + * + * Furthermore, since the DM atomic state only contains the DC + * context and can safely be annulled, we can free the state + * and clear the associated private object now to free + * some memory and avoid a possible use-after-free later. */ - struct dm_atomic_state *new_dm_state, *old_dm_state; - new_dm_state = dm_atomic_get_new_state(state); - old_dm_state = dm_atomic_get_old_state(state); + for (i = 0; i < state->num_private_objs; i++) { + struct drm_private_obj *obj = state->private_objs[i].ptr; - if (new_dm_state && old_dm_state) { - if (new_dm_state->context) - dc_release_state(new_dm_state->context); + if (obj->funcs == adev->dm.atomic_obj.funcs) { + int j = state->num_private_objs-1; - new_dm_state->context = old_dm_state->context; + dm_atomic_destroy_state(obj, + state->private_objs[i].state); + + /* If i is not at the end of the array then the + * last element needs to be moved to where i was + * before the array can safely be truncated. + */ + if (i != j) + state->private_objs[i] = + state->private_objs[j]; - if (old_dm_state->context) - dc_retain_state(old_dm_state->context); + state->private_objs[j].ptr = NULL; + state->private_objs[j].state = NULL; + state->private_objs[j].old_state = NULL; + state->private_objs[j].new_state = NULL; + + state->num_private_objs = j; + break; + } } } diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c index 3da71a088b92..0ecc18b55ffb 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c @@ -644,9 +644,6 @@ static int vegam_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr, /* sclk is bigger than max sclk in the dependence table */ *voltage |= (dep_table->entries[i - 1].vddc * VOLTAGE_SCALE) << VDDC_SHIFT; - vddci = phm_find_closest_vddci(&(data->vddci_voltage_table), - (dep_table->entries[i - 1].vddc - - (uint16_t)VDDC_VDDCI_DELTA)); if (SMU7_VOLTAGE_CONTROL_NONE == data->vddci_control) *voltage |= (data->vbios_boot_state.vddci_bootup_value * @@ -654,8 +651,13 @@ static int vegam_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr, else if (dep_table->entries[i - 1].vddci) *voltage |= (dep_table->entries[i - 1].vddci * VOLTAGE_SCALE) << VDDC_SHIFT; - else + else { + vddci = phm_find_closest_vddci(&(data->vddci_voltage_table), + (dep_table->entries[i - 1].vddc - + (uint16_t)VDDC_VDDCI_DELTA)); + *voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT; + } if (SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control) *mvdd = data->vbios_boot_state.mvdd_bootup_value * VOLTAGE_SCALE; diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c index 05d8373888e8..079f46f5cdb6 100644 --- a/drivers/gpu/drm/bochs/bochs_kms.c +++ b/drivers/gpu/drm/bochs/bochs_kms.c @@ -146,6 +146,7 @@ int bochs_kms_init(struct bochs_device *bochs) bochs->dev->mode_config.preferred_depth = 24; bochs->dev->mode_config.prefer_shadow = 0; bochs->dev->mode_config.prefer_shadow_fbdev = 1; + bochs->dev->mode_config.fbdev_use_iomem = true; bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true; bochs->dev->mode_config.funcs = &bochs_mode_funcs; diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 87b58c1acff4..648eb23d0784 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -1224,6 +1224,7 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id) adv7511->bridge.funcs = &adv7511_bridge_funcs; adv7511->bridge.of_node = dev->of_node; + adv7511->bridge.type = DRM_MODE_CONNECTOR_HDMIA; drm_bridge_add(&adv7511->bridge); diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c index b14d725bf609..c7bc194bbce3 100644 --- a/drivers/gpu/drm/bridge/nwl-dsi.c +++ b/drivers/gpu/drm/bridge/nwl-dsi.c @@ -917,11 +917,6 @@ static int nwl_dsi_bridge_attach(struct drm_bridge *bridge, struct drm_panel *panel; int ret; - if (flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR) { - DRM_ERROR("Fix bridge driver to make connector optional!"); - return -EINVAL; - } - ret = drm_of_find_panel_or_bridge(dsi->dev->of_node, 1, 0, &panel, &panel_bridge); if (ret) diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 5609e164805f..89cfd68ef400 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -399,7 +399,11 @@ static void drm_fb_helper_dirty_blit_real(struct drm_fb_helper *fb_helper, unsigned int y; for (y = clip->y1; y < clip->y2; y++) { - memcpy(dst, src, len); + if (!fb_helper->dev->mode_config.fbdev_use_iomem) + memcpy(dst, src, len); + else + memcpy_toio((void __iomem *)dst, src, len); + src += fb->pitches[0]; dst += fb->pitches[0]; } diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 7bf628e13023..ee2058ad482c 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -871,9 +871,6 @@ err: * @file_priv: drm file-private structure * * Open an object using the global name, returning a handle and the size. - * - * This handle (of course) holds a reference to the object, so the object - * will not go away until the handle is deleted. */ int drm_gem_open_ioctl(struct drm_device *dev, void *data, @@ -898,14 +895,15 @@ drm_gem_open_ioctl(struct drm_device *dev, void *data, /* drm_gem_handle_create_tail unlocks dev->object_name_lock. */ ret = drm_gem_handle_create_tail(file_priv, obj, &handle); - drm_gem_object_put_unlocked(obj); if (ret) - return ret; + goto err; args->handle = handle; args->size = obj->size; - return 0; +err: + drm_gem_object_put_unlocked(obj); + return ret; } /** diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c index bb27c82757f1..bf7888ad9ad4 100644 --- a/drivers/gpu/drm/drm_mipi_dbi.c +++ b/drivers/gpu/drm/drm_mipi_dbi.c @@ -923,7 +923,7 @@ static int mipi_dbi_spi1_transfer(struct mipi_dbi *dbi, int dc, } } - tr.len = chunk; + tr.len = chunk * 2; len -= chunk; ret = spi_sync(spi, &m); diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c index b50b44e76279..8fc3f67e3e76 100644 --- a/drivers/gpu/drm/drm_of.c +++ b/drivers/gpu/drm/drm_of.c @@ -322,10 +322,8 @@ static int drm_of_lvds_get_remote_pixels_type( * configurations by passing the endpoints explicitly to * drm_of_lvds_get_dual_link_pixel_order(). */ - if (!current_pt || pixels_type != current_pt) { - of_node_put(remote_port); + if (!current_pt || pixels_type != current_pt) return -EINVAL; - } } return pixels_type; diff --git a/drivers/gpu/drm/lima/lima_pp.c b/drivers/gpu/drm/lima/lima_pp.c index 33f01383409c..a5c95bed08c0 100644 --- a/drivers/gpu/drm/lima/lima_pp.c +++ b/drivers/gpu/drm/lima/lima_pp.c @@ -271,6 +271,8 @@ void lima_pp_fini(struct lima_ip *ip) int lima_pp_bcast_resume(struct lima_ip *ip) { + /* PP has been reset by individual PP resume */ + ip->data.async_reset = false; return 0; } diff --git a/drivers/gpu/drm/mcde/mcde_display.c b/drivers/gpu/drm/mcde/mcde_display.c index 08802e5177f6..4d2290f88edb 100644 --- a/drivers/gpu/drm/mcde/mcde_display.c +++ b/drivers/gpu/drm/mcde/mcde_display.c @@ -1060,9 +1060,14 @@ static void mcde_display_update(struct drm_simple_display_pipe *pipe, */ if (fb) { mcde_set_extsrc(mcde, drm_fb_cma_get_gem_addr(fb, pstate, 0)); - if (!mcde->video_mode) - /* Send a single frame using software sync */ - mcde_display_send_one_frame(mcde); + if (!mcde->video_mode) { + /* + * Send a single frame using software sync if the flow + * is not active yet. + */ + if (mcde->flow_active == 0) + mcde_display_send_one_frame(mcde); + } dev_info_once(mcde->dev, "sent first display update\n"); } else { /* diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 519f99868e35..800b7757252e 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -2073,7 +2073,7 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) */ if (core->assign_windows) { core->func->wndw.owner(core); - core->func->update(core, interlock, false); + nv50_disp_atomic_commit_core(state, interlock); core->assign_windows = false; interlock[NV50_DISP_INTERLOCK_CORE] = 0; } @@ -2506,7 +2506,7 @@ nv50_display_create(struct drm_device *dev) if (disp->disp->object.oclass >= TU102_DISP) nouveau_display(dev)->format_modifiers = wndwc57e_modifiers; else - if (disp->disp->object.oclass >= GF110_DISP) + if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_FERMI) nouveau_display(dev)->format_modifiers = disp90xx_modifiers; else nouveau_display(dev)->format_modifiers = disp50xx_modifiers; diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 496c4621cc78..07373bbc2acf 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -191,6 +191,7 @@ nouveau_decode_mod(struct nouveau_drm *drm, uint32_t *tile_mode, uint8_t *kind) { + struct nouveau_display *disp = nouveau_display(drm->dev); BUG_ON(!tile_mode || !kind); if (modifier == DRM_FORMAT_MOD_LINEAR) { @@ -202,6 +203,12 @@ nouveau_decode_mod(struct nouveau_drm *drm, * Extract the block height and kind from the corresponding * modifier fields. See drm_fourcc.h for details. */ + + if ((modifier & (0xffull << 12)) == 0ull) { + /* Legacy modifier. Translate to this dev's 'kind.' */ + modifier |= disp->format_modifiers[0] & (0xffull << 12); + } + *tile_mode = (uint32_t)(modifier & 0xF); *kind = (uint8_t)((modifier >> 12) & 0xFF); @@ -227,6 +234,16 @@ nouveau_framebuffer_get_layout(struct drm_framebuffer *fb, } } +static const u64 legacy_modifiers[] = { + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(0), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(1), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(2), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(3), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(4), + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(5), + DRM_FORMAT_MOD_INVALID +}; + static int nouveau_validate_decode_mod(struct nouveau_drm *drm, uint64_t modifier, @@ -247,8 +264,14 @@ nouveau_validate_decode_mod(struct nouveau_drm *drm, (disp->format_modifiers[mod] != modifier); mod++); - if (disp->format_modifiers[mod] == DRM_FORMAT_MOD_INVALID) - return -EINVAL; + if (disp->format_modifiers[mod] == DRM_FORMAT_MOD_INVALID) { + for (mod = 0; + (legacy_modifiers[mod] != DRM_FORMAT_MOD_INVALID) && + (legacy_modifiers[mod] != modifier); + mod++); + if (legacy_modifiers[mod] == DRM_FORMAT_MOD_INVALID) + return -EINVAL; + } nouveau_decode_mod(drm, modifier, tile_mode, kind); diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 3d11b84d4cf9..d5c23d1c20d8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -315,7 +315,7 @@ nouveau_fbcon_create(struct drm_fb_helper *helper, struct drm_framebuffer *fb; struct nouveau_channel *chan; struct nouveau_bo *nvbo; - struct drm_mode_fb_cmd2 mode_cmd; + struct drm_mode_fb_cmd2 mode_cmd = {}; int ret; mode_cmd.width = sizes->surface_width; @@ -590,6 +590,7 @@ fini: drm_fb_helper_fini(&fbcon->helper); free: kfree(fbcon); + drm->fbcon = NULL; return ret; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c index dcf08249374a..dffcac249211 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c @@ -117,15 +117,6 @@ nvkm_outp_acquire_hda(struct nvkm_outp *outp, enum nvkm_ior_type type, { struct nvkm_ior *ior; - /* First preference is to reuse the OR that is currently armed - * on HW, if any, in order to prevent unnecessary switching. - */ - list_for_each_entry(ior, &outp->disp->ior, head) { - if (!ior->identity && !!ior->func->hda.hpd == hda && - !ior->asy.outp && ior->arm.outp == outp) - return nvkm_outp_acquire_ior(outp, user, ior); - } - /* Failing that, a completely unused OR is the next best thing. */ list_for_each_entry(ior, &outp->disp->ior, head) { if (!ior->identity && !!ior->func->hda.hpd == hda && @@ -173,6 +164,27 @@ nvkm_outp_acquire(struct nvkm_outp *outp, u8 user, bool hda) return nvkm_outp_acquire_ior(outp, user, ior); } + /* First preference is to reuse the OR that is currently armed + * on HW, if any, in order to prevent unnecessary switching. + */ + list_for_each_entry(ior, &outp->disp->ior, head) { + if (!ior->identity && !ior->asy.outp && ior->arm.outp == outp) { + /*XXX: For various complicated reasons, we can't outright switch + * the boot-time OR on the first modeset without some fairly + * invasive changes. + * + * The systems that were fixed by modifying the OR selection + * code to account for HDA support shouldn't regress here as + * the HDA-enabled ORs match the relevant output's pad macro + * index, and the firmware seems to select an OR this way. + * + * This warning is to make it obvious if that proves wrong. + */ + WARN_ON(hda && !ior->func->hda.hpd); + return nvkm_outp_acquire_ior(outp, user, ior); + } + } + /* If we don't need HDA, first try to acquire an OR that doesn't * support it to leave free the ones that do. */ diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index 46fe1805c588..2649469070aa 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -615,9 +615,9 @@ static const struct panel_desc boe_tv101wum_nl6_desc = { static const struct drm_display_mode auo_kd101n80_45na_default_mode = { .clock = 157000, .hdisplay = 1200, - .hsync_start = 1200 + 80, - .hsync_end = 1200 + 80 + 24, - .htotal = 1200 + 80 + 24 + 36, + .hsync_start = 1200 + 60, + .hsync_end = 1200 + 60 + 24, + .htotal = 1200 + 60 + 24 + 56, .vdisplay = 1920, .vsync_start = 1920 + 16, .vsync_end = 1920 + 16 + 4, diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 5178f87d6574..4aeb960ccf15 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -1250,7 +1250,21 @@ static const struct panel_desc boe_nv133fhm_n61 = { .height = 165, }, .delay = { - .hpd_absent_delay = 200, + /* + * When power is first given to the panel there's a short + * spike on the HPD line. It was explained that this spike + * was until the TCON data download was complete. On + * one system this was measured at 8 ms. We'll put 15 ms + * in the prepare delay just to be safe and take it away + * from the hpd_absent_delay (which would otherwise be 200 ms) + * to handle this. That means: + * - If HPD isn't hooked up you still have 200 ms delay. + * - If HPD is hooked up we won't try to look at it for the + * first 15 ms. + */ + .prepare = 15, + .hpd_absent_delay = 185, + .unprepare = 500, }, .bus_format = MEDIA_BUS_FMT_RGB888_1X24, diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c index 557cbe5ab35f..2f2c9f0a1071 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c @@ -260,7 +260,7 @@ sun4i_hdmi_connector_detect(struct drm_connector *connector, bool force) unsigned long reg; reg = readl(hdmi->base + SUN4I_HDMI_HPD_REG); - if (reg & SUN4I_HDMI_HPD_HIGH) { + if (!(reg & SUN4I_HDMI_HPD_HIGH)) { cec_phys_addr_invalidate(hdmi->cec_adap); return connector_status_disconnected; } diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c index 4b72398af505..e4b7f2a951ad 100644 --- a/drivers/i2c/busses/i2c-cadence.c +++ b/drivers/i2c/busses/i2c-cadence.c @@ -421,20 +421,21 @@ static irqreturn_t cdns_i2c_master_isr(void *ptr) /* Read data if receive data valid is set */ while (cdns_i2c_readreg(CDNS_I2C_SR_OFFSET) & CDNS_I2C_SR_RXDV) { - /* - * Clear hold bit that was set for FIFO control if - * RX data left is less than FIFO depth, unless - * repeated start is selected. - */ - if ((id->recv_count < CDNS_I2C_FIFO_DEPTH) && - !id->bus_hold_flag) - cdns_i2c_clear_bus_hold(id); - if (id->recv_count > 0) { *(id->p_recv_buf)++ = cdns_i2c_readreg(CDNS_I2C_DATA_OFFSET); id->recv_count--; id->curr_recv_count--; + + /* + * Clear hold bit that was set for FIFO control + * if RX data left is less than or equal to + * FIFO DEPTH unless repeated start is selected + */ + if (id->recv_count <= CDNS_I2C_FIFO_DEPTH && + !id->bus_hold_flag) + cdns_i2c_clear_bus_hold(id); + } else { dev_err(id->adap.dev.parent, "xfer_size reg rollover. xfer aborted!\n"); @@ -594,10 +595,8 @@ static void cdns_i2c_mrecv(struct cdns_i2c *id) * Check for the message size against FIFO depth and set the * 'hold bus' bit if it is greater than FIFO depth. */ - if ((id->recv_count > CDNS_I2C_FIFO_DEPTH) || id->bus_hold_flag) + if (id->recv_count > CDNS_I2C_FIFO_DEPTH) ctrl_reg |= CDNS_I2C_CR_HOLD; - else - ctrl_reg = ctrl_reg & ~CDNS_I2C_CR_HOLD; cdns_i2c_writereg(ctrl_reg, CDNS_I2C_CR_OFFSET); @@ -654,11 +653,8 @@ static void cdns_i2c_msend(struct cdns_i2c *id) * Check for the message size against FIFO depth and set the * 'hold bus' bit if it is greater than FIFO depth. */ - if ((id->send_count > CDNS_I2C_FIFO_DEPTH) || id->bus_hold_flag) + if (id->send_count > CDNS_I2C_FIFO_DEPTH) ctrl_reg |= CDNS_I2C_CR_HOLD; - else - ctrl_reg = ctrl_reg & ~CDNS_I2C_CR_HOLD; - cdns_i2c_writereg(ctrl_reg, CDNS_I2C_CR_OFFSET); /* Clear the interrupts in interrupt status register. */ diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 18d1e4fd4cf3..7f130829bf01 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -367,7 +367,6 @@ static int geni_i2c_rx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, geni_se_select_mode(se, GENI_SE_FIFO); writel_relaxed(len, se->base + SE_I2C_RX_TRANS_LEN); - geni_se_setup_m_cmd(se, I2C_READ, m_param); if (dma_buf && geni_se_rx_dma_prep(se, dma_buf, len, &rx_dma)) { geni_se_select_mode(se, GENI_SE_FIFO); @@ -375,6 +374,8 @@ static int geni_i2c_rx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, dma_buf = NULL; } + geni_se_setup_m_cmd(se, I2C_READ, m_param); + time_left = wait_for_completion_timeout(&gi2c->done, XFER_TIMEOUT); if (!time_left) geni_i2c_abort_xfer(gi2c); @@ -408,7 +409,6 @@ static int geni_i2c_tx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, geni_se_select_mode(se, GENI_SE_FIFO); writel_relaxed(len, se->base + SE_I2C_TX_TRANS_LEN); - geni_se_setup_m_cmd(se, I2C_WRITE, m_param); if (dma_buf && geni_se_tx_dma_prep(se, dma_buf, len, &tx_dma)) { geni_se_select_mode(se, GENI_SE_FIFO); @@ -416,6 +416,8 @@ static int geni_i2c_tx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, dma_buf = NULL; } + geni_se_setup_m_cmd(se, I2C_WRITE, m_param); + if (!dma_buf) /* Get FIFO IRQ */ writel_relaxed(1, se->base + SE_GENI_TX_WATERMARK_REG); diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index a45c4bf1ec01..2e3e1bb75013 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -868,6 +868,7 @@ static int rcar_unreg_slave(struct i2c_client *slave) /* disable irqs and ensure none is running before clearing ptr */ rcar_i2c_write(priv, ICSIER, 0); rcar_i2c_write(priv, ICSCR, 0); + rcar_i2c_write(priv, ICSAR, 0); /* Gen2: must be 0 if not using slave */ synchronize_irq(priv->irq); priv->slave = NULL; @@ -969,6 +970,8 @@ static int rcar_i2c_probe(struct platform_device *pdev) if (ret < 0) goto out_pm_put; + rcar_i2c_write(priv, ICSAR, 0); /* Gen2: must be 0 if not using slave */ + if (priv->devtype == I2C_RCAR_GEN3) { priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); if (!IS_ERR(priv->rstc)) { diff --git a/drivers/i2c/i2c-core-slave.c b/drivers/i2c/i2c-core-slave.c index 5427f047faf0..1589179d5eb9 100644 --- a/drivers/i2c/i2c-core-slave.c +++ b/drivers/i2c/i2c-core-slave.c @@ -18,10 +18,8 @@ int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb) { int ret; - if (!client || !slave_cb) { - WARN(1, "insufficient data\n"); + if (WARN(IS_ERR_OR_NULL(client) || !slave_cb, "insufficient data\n")) return -EINVAL; - } if (!(client->flags & I2C_CLIENT_SLAVE)) dev_warn(&client->dev, "%s: client slave flag not set. You might see address collisions\n", @@ -60,6 +58,9 @@ int i2c_slave_unregister(struct i2c_client *client) { int ret; + if (IS_ERR_OR_NULL(client)) + return -EINVAL; + if (!client->adapter->algo->unreg_slave) { dev_err(&client->dev, "%s: not supported by adapter\n", __func__); return -EOPNOTSUPP; diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 0d1377232933..dc0558b23158 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -3676,10 +3676,12 @@ static int cm_send_sidr_rep_locked(struct cm_id_private *cm_id_priv, return ret; } cm_id_priv->id.state = IB_CM_IDLE; + spin_lock_irq(&cm.lock); if (!RB_EMPTY_NODE(&cm_id_priv->sidr_id_node)) { rb_erase(&cm_id_priv->sidr_id_node, &cm.remote_sidr_table); RB_CLEAR_NODE(&cm_id_priv->sidr_id_node); } + spin_unlock_irq(&cm.lock); return 0; } diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c index 655795bfa0ee..513825e424bf 100644 --- a/drivers/infiniband/core/cq.c +++ b/drivers/infiniband/core/cq.c @@ -72,6 +72,15 @@ static void rdma_dim_init(struct ib_cq *cq) INIT_WORK(&dim->work, ib_cq_rdma_dim_work); } +static void rdma_dim_destroy(struct ib_cq *cq) +{ + if (!cq->dim) + return; + + cancel_work_sync(&cq->dim->work); + kfree(cq->dim); +} + static int __poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc) { int rc; @@ -266,6 +275,7 @@ struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private, return cq; out_destroy_cq: + rdma_dim_destroy(cq); rdma_restrack_del(&cq->res); cq->device->ops.destroy_cq(cq, udata); out_free_wc: @@ -331,12 +341,10 @@ void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata) WARN_ON_ONCE(1); } + rdma_dim_destroy(cq); trace_cq_free(cq); rdma_restrack_del(&cq->res); cq->device->ops.destroy_cq(cq, udata); - if (cq->dim) - cancel_work_sync(&cq->dim->work); - kfree(cq->dim); kfree(cq->wc); kfree(cq); } diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index 3027cd2fb247..6d3ed7c6e19e 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -649,9 +649,6 @@ void rdma_alloc_commit_uobject(struct ib_uobject *uobj, { struct ib_uverbs_file *ufile = attrs->ufile; - /* alloc_commit consumes the uobj kref */ - uobj->uapi_object->type_class->alloc_commit(uobj); - /* kref is held so long as the uobj is on the uobj list. */ uverbs_uobject_get(uobj); spin_lock_irq(&ufile->uobjects_lock); @@ -661,6 +658,9 @@ void rdma_alloc_commit_uobject(struct ib_uobject *uobj, /* matches atomic_set(-1) in alloc_uobj */ atomic_set(&uobj->usecnt, 0); + /* alloc_commit consumes the uobj kref */ + uobj->uapi_object->type_class->alloc_commit(uobj); + /* Matches the down_read in rdma_alloc_begin_uobject */ up_read(&ufile->hw_destroy_rwsem); } diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 5b87eee8ccc8..d03dacaef788 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1084,6 +1084,8 @@ static ssize_t ucma_connect(struct ucma_file *file, const char __user *inbuf, size_t in_size; int ret; + if (in_len < offsetofend(typeof(cmd), reserved)) + return -EINVAL; in_size = min_t(size_t, in_len, sizeof(cmd)); if (copy_from_user(&cmd, inbuf, in_size)) return -EFAULT; @@ -1141,6 +1143,8 @@ static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf, size_t in_size; int ret; + if (in_len < offsetofend(typeof(cmd), reserved)) + return -EINVAL; in_size = min_t(size_t, in_len, sizeof(cmd)); if (copy_from_user(&cmd, inbuf, in_size)) return -EFAULT; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index dd01a51816cc..0618ced45bf8 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -3954,6 +3954,15 @@ static int config_qp_sq_buf(struct hns_roce_dev *hr_dev, return 0; } +static inline enum ib_mtu get_mtu(struct ib_qp *ibqp, + const struct ib_qp_attr *attr) +{ + if (ibqp->qp_type == IB_QPT_GSI || ibqp->qp_type == IB_QPT_UD) + return IB_MTU_4096; + + return attr->path_mtu; +} + static int modify_qp_init_to_rtr(struct ib_qp *ibqp, const struct ib_qp_attr *attr, int attr_mask, struct hns_roce_v2_qp_context *context, @@ -3965,6 +3974,7 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp, struct ib_device *ibdev = &hr_dev->ib_dev; dma_addr_t trrl_ba; dma_addr_t irrl_ba; + enum ib_mtu mtu; u8 port_num; u64 *mtts; u8 *dmac; @@ -4062,23 +4072,23 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp, roce_set_field(qpc_mask->byte_52_udpspn_dmac, V2_QPC_BYTE_52_DMAC_M, V2_QPC_BYTE_52_DMAC_S, 0); - /* mtu*(2^LP_PKTN_INI) should not bigger than 1 message length 64kb */ + mtu = get_mtu(ibqp, attr); + + if (attr_mask & IB_QP_PATH_MTU) { + roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_MTU_M, + V2_QPC_BYTE_24_MTU_S, mtu); + roce_set_field(qpc_mask->byte_24_mtu_tc, V2_QPC_BYTE_24_MTU_M, + V2_QPC_BYTE_24_MTU_S, 0); + } + +#define MAX_LP_MSG_LEN 65536 + /* MTU*(2^LP_PKTN_INI) shouldn't be bigger than 64kb */ roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_LP_PKTN_INI_M, V2_QPC_BYTE_56_LP_PKTN_INI_S, - ilog2(hr_dev->caps.max_sq_inline / IB_MTU_4096)); + ilog2(MAX_LP_MSG_LEN / ib_mtu_enum_to_int(mtu))); roce_set_field(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_LP_PKTN_INI_M, V2_QPC_BYTE_56_LP_PKTN_INI_S, 0); - if (ibqp->qp_type == IB_QPT_GSI || ibqp->qp_type == IB_QPT_UD) - roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_MTU_M, - V2_QPC_BYTE_24_MTU_S, IB_MTU_4096); - else if (attr_mask & IB_QP_PATH_MTU) - roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_MTU_M, - V2_QPC_BYTE_24_MTU_S, attr->path_mtu); - - roce_set_field(qpc_mask->byte_24_mtu_tc, V2_QPC_BYTE_24_MTU_M, - V2_QPC_BYTE_24_MTU_S, 0); - roce_set_bit(qpc_mask->byte_108_rx_reqepsn, V2_QPC_BYTE_108_RX_REQ_PSN_ERR_S, 0); roce_set_field(qpc_mask->byte_96_rx_reqmsn, V2_QPC_BYTE_96_RX_REQ_MSN_M, diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index 0e71ebee9e52..6b226a5eb7db 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -120,7 +120,7 @@ static int alloc_mr_pbl(struct hns_roce_dev *hr_dev, struct hns_roce_mr *mr, mr->pbl_hop_num = is_fast ? 1 : hr_dev->caps.pbl_hop_num; buf_attr.page_shift = is_fast ? PAGE_SHIFT : - hr_dev->caps.pbl_buf_pg_sz + HNS_HW_PAGE_SHIFT; + hr_dev->caps.pbl_buf_pg_sz + PAGE_SHIFT; buf_attr.region[0].size = length; buf_attr.region[0].hopnum = mr->pbl_hop_num; buf_attr.region_count = 1; diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 7d2ec9ee5097..77dca1e05bba 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -601,6 +601,23 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) */ synchronize_srcu(&dev->odp_srcu); + /* + * All work on the prefetch list must be completed, xa_erase() prevented + * new work from being created. + */ + wait_event(imr->q_deferred_work, !atomic_read(&imr->num_deferred_work)); + + /* + * At this point it is forbidden for any other thread to enter + * pagefault_mr() on this imr. It is already forbidden to call + * pagefault_mr() on an implicit child. Due to this additions to + * implicit_children are prevented. + */ + + /* + * Block destroy_unused_implicit_child_mr() from incrementing + * num_deferred_work. + */ xa_lock(&imr->implicit_children); xa_for_each (&imr->implicit_children, idx, mtt) { __xa_erase(&imr->implicit_children, idx); @@ -609,9 +626,8 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) xa_unlock(&imr->implicit_children); /* - * num_deferred_work can only be incremented inside the odp_srcu, or - * under xa_lock while the child is in the xarray. Thus at this point - * it is only decreasing, and all work holding it is now on the wq. + * Wait for any concurrent destroy_unused_implicit_child_mr() to + * complete. */ wait_event(imr->q_deferred_work, !atomic_read(&imr->num_deferred_work)); @@ -1781,9 +1797,7 @@ static bool init_prefetch_work(struct ib_pd *pd, work->frags[i].mr = get_prefetchable_mr(pd, advice, sg_list[i].lkey); if (!work->frags[i].mr) { - work->num_sge = i - 1; - if (i) - destroy_prefetch_work(work); + work->num_sge = i; return false; } @@ -1849,6 +1863,7 @@ int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd, srcu_key = srcu_read_lock(&dev->odp_srcu); if (!init_prefetch_work(pd, advice, pf_flags, work, sg_list, num_sge)) { srcu_read_unlock(&dev->odp_srcu, srcu_key); + destroy_prefetch_work(work); return -EINVAL; } queue_work(system_unbound_wq, &work->work); diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index e050eade97a1..1225b8d77510 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1766,15 +1766,14 @@ err: } static void configure_requester_scat_cqe(struct mlx5_ib_dev *dev, + struct mlx5_ib_qp *qp, struct ib_qp_init_attr *init_attr, - struct mlx5_ib_create_qp *ucmd, void *qpc) { int scqe_sz; bool allow_scat_cqe = false; - if (ucmd) - allow_scat_cqe = ucmd->flags & MLX5_QP_FLAG_ALLOW_SCATTER_CQE; + allow_scat_cqe = qp->flags_en & MLX5_QP_FLAG_ALLOW_SCATTER_CQE; if (!allow_scat_cqe && init_attr->sq_sig_type != IB_SIGNAL_ALL_WR) return; @@ -1853,8 +1852,6 @@ static int create_xrc_tgt_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, u32 *in; int err; - mutex_init(&qp->mutex); - if (attr->sq_sig_type == IB_SIGNAL_ALL_WR) qp->sq_signal_bits = MLX5_WQE_CTRL_CQ_UPDATE; @@ -1938,7 +1935,6 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, u32 *in; int err; - mutex_init(&qp->mutex); spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); @@ -2012,7 +2008,7 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, } if ((qp->flags_en & MLX5_QP_FLAG_SCATTER_CQE) && (qp->type == MLX5_IB_QPT_DCI || qp->type == IB_QPT_RC)) - configure_requester_scat_cqe(dev, init_attr, ucmd, qpc); + configure_requester_scat_cqe(dev, qp, init_attr, qpc); if (qp->rq.wqe_cnt) { MLX5_SET(qpc, qpc, log_rq_stride, qp->rq.wqe_shift - 4); @@ -2129,7 +2125,6 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, u32 *in; int err; - mutex_init(&qp->mutex); spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); @@ -2543,13 +2538,18 @@ static void process_vendor_flag(struct mlx5_ib_dev *dev, int *flags, int flag, return; } - if (flag == MLX5_QP_FLAG_SCATTER_CQE) { + switch (flag) { + case MLX5_QP_FLAG_SCATTER_CQE: + case MLX5_QP_FLAG_ALLOW_SCATTER_CQE: /* - * We don't return error if this flag was provided, - * and mlx5 doesn't have right capability. - */ - *flags &= ~MLX5_QP_FLAG_SCATTER_CQE; + * We don't return error if these flags were provided, + * and mlx5 doesn't have right capability. + */ + *flags &= ~(MLX5_QP_FLAG_SCATTER_CQE | + MLX5_QP_FLAG_ALLOW_SCATTER_CQE); return; + default: + break; } mlx5_ib_dbg(dev, "Vendor create QP flag 0x%X is not supported\n", flag); } @@ -2589,6 +2589,8 @@ static int process_vendor_flags(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, process_vendor_flag(dev, &flags, MLX5_QP_FLAG_SIGNATURE, true, qp); process_vendor_flag(dev, &flags, MLX5_QP_FLAG_SCATTER_CQE, MLX5_CAP_GEN(mdev, sctr_data_cqe), qp); + process_vendor_flag(dev, &flags, MLX5_QP_FLAG_ALLOW_SCATTER_CQE, + MLX5_CAP_GEN(mdev, sctr_data_cqe), qp); if (qp->type == IB_QPT_RAW_PACKET) { cond = MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) || @@ -2963,6 +2965,7 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attr, goto free_ucmd; } + mutex_init(&qp->mutex); qp->type = type; if (udata) { err = process_vendor_flags(dev, qp, params.ucmd, attr); diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c index 6f5eadc4d183..37aaacebd3f2 100644 --- a/drivers/infiniband/hw/mlx5/srq_cmd.c +++ b/drivers/infiniband/hw/mlx5/srq_cmd.c @@ -83,11 +83,11 @@ struct mlx5_core_srq *mlx5_cmd_get_srq(struct mlx5_ib_dev *dev, u32 srqn) struct mlx5_srq_table *table = &dev->srq_table; struct mlx5_core_srq *srq; - xa_lock(&table->array); + xa_lock_irq(&table->array); srq = xa_load(&table->array, srqn); if (srq) refcount_inc(&srq->common.refcount); - xa_unlock(&table->array); + xa_unlock_irq(&table->array); return srq; } diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 7db35dd6ad74..332a8ba94b81 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -901,8 +901,6 @@ static void rvt_init_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, qp->s_tail_ack_queue = 0; qp->s_acked_ack_queue = 0; qp->s_num_rd_atomic = 0; - if (qp->r_rq.kwq) - qp->r_rq.kwq->count = qp->r_rq.size; qp->r_sge.num_sge = 0; atomic_set(&qp->s_reserved_used, 0); } @@ -2367,31 +2365,6 @@ bad_lkey: } /** - * get_count - count numbers of request work queue entries - * in circular buffer - * @rq: data structure for request queue entry - * @tail: tail indices of the circular buffer - * @head: head indices of the circular buffer - * - * Return - total number of entries in the circular buffer - */ -static u32 get_count(struct rvt_rq *rq, u32 tail, u32 head) -{ - u32 count; - - count = head; - - if (count >= rq->size) - count = 0; - if (count < tail) - count += rq->size - tail; - else - count -= tail; - - return count; -} - -/** * get_rvt_head - get head indices of the circular buffer * @rq: data structure for request queue entry * @ip: the QP @@ -2465,7 +2438,7 @@ int rvt_get_rwqe(struct rvt_qp *qp, bool wr_id_only) if (kwq->count < RVT_RWQ_COUNT_THRESHOLD) { head = get_rvt_head(rq, ip); - kwq->count = get_count(rq, tail, head); + kwq->count = rvt_get_rq_count(rq, head, tail); } if (unlikely(kwq->count == 0)) { ret = 0; @@ -2500,7 +2473,9 @@ int rvt_get_rwqe(struct rvt_qp *qp, bool wr_id_only) * the number of remaining WQEs. */ if (kwq->count < srq->limit) { - kwq->count = get_count(rq, tail, get_rvt_head(rq, ip)); + kwq->count = + rvt_get_rq_count(rq, + get_rvt_head(rq, ip), tail); if (kwq->count < srq->limit) { struct ib_event ev; diff --git a/drivers/infiniband/sw/rdmavt/rc.c b/drivers/infiniband/sw/rdmavt/rc.c index 977906cc0d11..c58735f4c94a 100644 --- a/drivers/infiniband/sw/rdmavt/rc.c +++ b/drivers/infiniband/sw/rdmavt/rc.c @@ -127,9 +127,7 @@ __be32 rvt_compute_aeth(struct rvt_qp *qp) * not atomic, which is OK, since the fuzziness is * resolved as further ACKs go out. */ - credits = head - tail; - if ((int)credits < 0) - credits += qp->r_rq.size; + credits = rvt_get_rq_count(&qp->r_rq, head, tail); } /* * Binary search the credit table to find the code to diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index e5f998744501..9e1ab701785c 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -243,6 +243,7 @@ static int aggregate_requests(struct icc_node *node) { struct icc_provider *p = node->provider; struct icc_req *r; + u32 avg_bw, peak_bw; node->avg_bw = 0; node->peak_bw = 0; @@ -251,9 +252,14 @@ static int aggregate_requests(struct icc_node *node) p->pre_aggregate(node); hlist_for_each_entry(r, &node->req_list, req_node) { - if (!r->enabled) - continue; - p->aggregate(node, r->tag, r->avg_bw, r->peak_bw, + if (r->enabled) { + avg_bw = r->avg_bw; + peak_bw = r->peak_bw; + } else { + avg_bw = 0; + peak_bw = 0; + } + p->aggregate(node, r->tag, avg_bw, peak_bw, &node->avg_bw, &node->peak_bw); } diff --git a/drivers/interconnect/qcom/msm8916.c b/drivers/interconnect/qcom/msm8916.c index e94f3c5228b7..42c6c5581662 100644 --- a/drivers/interconnect/qcom/msm8916.c +++ b/drivers/interconnect/qcom/msm8916.c @@ -197,13 +197,13 @@ DEFINE_QNODE(pcnoc_int_0, MSM8916_PNOC_INT_0, 8, -1, -1, MSM8916_PNOC_SNOC_MAS, DEFINE_QNODE(pcnoc_int_1, MSM8916_PNOC_INT_1, 8, -1, -1, MSM8916_PNOC_SNOC_MAS); DEFINE_QNODE(pcnoc_m_0, MSM8916_PNOC_MAS_0, 8, -1, -1, MSM8916_PNOC_INT_0); DEFINE_QNODE(pcnoc_m_1, MSM8916_PNOC_MAS_1, 8, -1, -1, MSM8916_PNOC_SNOC_MAS); -DEFINE_QNODE(pcnoc_s_0, MSM8916_PNOC_SLV_0, 8, -1, -1, MSM8916_SLAVE_CLK_CTL, MSM8916_SLAVE_TLMM, MSM8916_SLAVE_TCSR, MSM8916_SLAVE_SECURITY, MSM8916_SLAVE_MSS); -DEFINE_QNODE(pcnoc_s_1, MSM8916_PNOC_SLV_1, 8, -1, -1, MSM8916_SLAVE_IMEM_CFG, MSM8916_SLAVE_CRYPTO_0_CFG, MSM8916_SLAVE_MSG_RAM, MSM8916_SLAVE_PDM, MSM8916_SLAVE_PRNG); -DEFINE_QNODE(pcnoc_s_2, MSM8916_PNOC_SLV_2, 8, -1, -1, MSM8916_SLAVE_SPDM, MSM8916_SLAVE_BOOT_ROM, MSM8916_SLAVE_BIMC_CFG, MSM8916_SLAVE_PNOC_CFG, MSM8916_SLAVE_PMIC_ARB); -DEFINE_QNODE(pcnoc_s_3, MSM8916_PNOC_SLV_3, 8, -1, -1, MSM8916_SLAVE_MPM, MSM8916_SLAVE_SNOC_CFG, MSM8916_SLAVE_RBCPR_CFG, MSM8916_SLAVE_QDSS_CFG, MSM8916_SLAVE_DEHR_CFG); -DEFINE_QNODE(pcnoc_s_4, MSM8916_PNOC_SLV_4, 8, -1, -1, MSM8916_SLAVE_VENUS_CFG, MSM8916_SLAVE_CAMERA_CFG, MSM8916_SLAVE_DISPLAY_CFG); -DEFINE_QNODE(pcnoc_s_8, MSM8916_PNOC_SLV_8, 8, -1, -1, MSM8916_SLAVE_USB_HS, MSM8916_SLAVE_SDCC_1, MSM8916_SLAVE_BLSP_1); -DEFINE_QNODE(pcnoc_s_9, MSM8916_PNOC_SLV_9, 8, -1, -1, MSM8916_SLAVE_SDCC_2, MSM8916_SLAVE_LPASS, MSM8916_SLAVE_GRAPHICS_3D_CFG); +DEFINE_QNODE(pcnoc_s_0, MSM8916_PNOC_SLV_0, 4, -1, -1, MSM8916_SLAVE_CLK_CTL, MSM8916_SLAVE_TLMM, MSM8916_SLAVE_TCSR, MSM8916_SLAVE_SECURITY, MSM8916_SLAVE_MSS); +DEFINE_QNODE(pcnoc_s_1, MSM8916_PNOC_SLV_1, 4, -1, -1, MSM8916_SLAVE_IMEM_CFG, MSM8916_SLAVE_CRYPTO_0_CFG, MSM8916_SLAVE_MSG_RAM, MSM8916_SLAVE_PDM, MSM8916_SLAVE_PRNG); +DEFINE_QNODE(pcnoc_s_2, MSM8916_PNOC_SLV_2, 4, -1, -1, MSM8916_SLAVE_SPDM, MSM8916_SLAVE_BOOT_ROM, MSM8916_SLAVE_BIMC_CFG, MSM8916_SLAVE_PNOC_CFG, MSM8916_SLAVE_PMIC_ARB); +DEFINE_QNODE(pcnoc_s_3, MSM8916_PNOC_SLV_3, 4, -1, -1, MSM8916_SLAVE_MPM, MSM8916_SLAVE_SNOC_CFG, MSM8916_SLAVE_RBCPR_CFG, MSM8916_SLAVE_QDSS_CFG, MSM8916_SLAVE_DEHR_CFG); +DEFINE_QNODE(pcnoc_s_4, MSM8916_PNOC_SLV_4, 4, -1, -1, MSM8916_SLAVE_VENUS_CFG, MSM8916_SLAVE_CAMERA_CFG, MSM8916_SLAVE_DISPLAY_CFG); +DEFINE_QNODE(pcnoc_s_8, MSM8916_PNOC_SLV_8, 4, -1, -1, MSM8916_SLAVE_USB_HS, MSM8916_SLAVE_SDCC_1, MSM8916_SLAVE_BLSP_1); +DEFINE_QNODE(pcnoc_s_9, MSM8916_PNOC_SLV_9, 4, -1, -1, MSM8916_SLAVE_SDCC_2, MSM8916_SLAVE_LPASS, MSM8916_SLAVE_GRAPHICS_3D_CFG); DEFINE_QNODE(pcnoc_snoc_mas, MSM8916_PNOC_SNOC_MAS, 8, 29, -1, MSM8916_PNOC_SNOC_SLV); DEFINE_QNODE(pcnoc_snoc_slv, MSM8916_PNOC_SNOC_SLV, 8, -1, 45, MSM8916_SNOC_INT_0, MSM8916_SNOC_INT_BIMC, MSM8916_SNOC_INT_1); DEFINE_QNODE(qdss_int, MSM8916_SNOC_QDSS_INT, 8, -1, -1, MSM8916_SNOC_INT_0, MSM8916_SNOC_INT_BIMC); diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index c3e1fbd1988c..d176df569af8 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -65,6 +65,7 @@ struct qcom_iommu_domain { struct mutex init_mutex; /* Protects iommu pointer */ struct iommu_domain domain; struct qcom_iommu_dev *iommu; + struct iommu_fwspec *fwspec; }; static struct qcom_iommu_domain *to_qcom_iommu_domain(struct iommu_domain *dom) @@ -84,9 +85,9 @@ static struct qcom_iommu_dev * to_iommu(struct device *dev) return dev_iommu_priv_get(dev); } -static struct qcom_iommu_ctx * to_ctx(struct device *dev, unsigned asid) +static struct qcom_iommu_ctx * to_ctx(struct qcom_iommu_domain *d, unsigned asid) { - struct qcom_iommu_dev *qcom_iommu = to_iommu(dev); + struct qcom_iommu_dev *qcom_iommu = d->iommu; if (!qcom_iommu) return NULL; return qcom_iommu->ctxs[asid - 1]; @@ -118,14 +119,12 @@ iommu_readq(struct qcom_iommu_ctx *ctx, unsigned reg) static void qcom_iommu_tlb_sync(void *cookie) { - struct iommu_fwspec *fwspec; - struct device *dev = cookie; + struct qcom_iommu_domain *qcom_domain = cookie; + struct iommu_fwspec *fwspec = qcom_domain->fwspec; unsigned i; - fwspec = dev_iommu_fwspec_get(dev); - for (i = 0; i < fwspec->num_ids; i++) { - struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]); + struct qcom_iommu_ctx *ctx = to_ctx(qcom_domain, fwspec->ids[i]); unsigned int val, ret; iommu_writel(ctx, ARM_SMMU_CB_TLBSYNC, 0); @@ -139,14 +138,12 @@ static void qcom_iommu_tlb_sync(void *cookie) static void qcom_iommu_tlb_inv_context(void *cookie) { - struct device *dev = cookie; - struct iommu_fwspec *fwspec; + struct qcom_iommu_domain *qcom_domain = cookie; + struct iommu_fwspec *fwspec = qcom_domain->fwspec; unsigned i; - fwspec = dev_iommu_fwspec_get(dev); - for (i = 0; i < fwspec->num_ids; i++) { - struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]); + struct qcom_iommu_ctx *ctx = to_ctx(qcom_domain, fwspec->ids[i]); iommu_writel(ctx, ARM_SMMU_CB_S1_TLBIASID, ctx->asid); } @@ -156,16 +153,14 @@ static void qcom_iommu_tlb_inv_context(void *cookie) static void qcom_iommu_tlb_inv_range_nosync(unsigned long iova, size_t size, size_t granule, bool leaf, void *cookie) { - struct device *dev = cookie; - struct iommu_fwspec *fwspec; + struct qcom_iommu_domain *qcom_domain = cookie; + struct iommu_fwspec *fwspec = qcom_domain->fwspec; unsigned i, reg; reg = leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA; - fwspec = dev_iommu_fwspec_get(dev); - for (i = 0; i < fwspec->num_ids; i++) { - struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]); + struct qcom_iommu_ctx *ctx = to_ctx(qcom_domain, fwspec->ids[i]); size_t s = size; iova = (iova >> 12) << 12; @@ -256,7 +251,9 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain, }; qcom_domain->iommu = qcom_iommu; - pgtbl_ops = alloc_io_pgtable_ops(ARM_32_LPAE_S1, &pgtbl_cfg, dev); + qcom_domain->fwspec = fwspec; + + pgtbl_ops = alloc_io_pgtable_ops(ARM_32_LPAE_S1, &pgtbl_cfg, qcom_domain); if (!pgtbl_ops) { dev_err(qcom_iommu->dev, "failed to allocate pagetable ops\n"); ret = -ENOMEM; @@ -269,7 +266,7 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain, domain->geometry.force_aperture = true; for (i = 0; i < fwspec->num_ids; i++) { - struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]); + struct qcom_iommu_ctx *ctx = to_ctx(qcom_domain, fwspec->ids[i]); if (!ctx->secure_init) { ret = qcom_scm_restore_sec_cfg(qcom_iommu->sec_id, ctx->asid); @@ -419,7 +416,7 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de pm_runtime_get_sync(qcom_iommu->dev); for (i = 0; i < fwspec->num_ids; i++) { - struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]); + struct qcom_iommu_ctx *ctx = to_ctx(qcom_domain, fwspec->ids[i]); /* Disable the context bank: */ iommu_writel(ctx, ARM_SMMU_CB_SCTLR, 0); diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 81dc5ff08909..a83a1de1e03f 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -2420,7 +2420,7 @@ static void integrity_writer(struct work_struct *w) unsigned prev_free_sectors; /* the following test is not needed, but it tests the replay code */ - if (unlikely(dm_suspended(ic->ti)) && !ic->meta_dev) + if (unlikely(dm_post_suspending(ic->ti)) && !ic->meta_dev) return; spin_lock_irq(&ic->endio_wait.lock); @@ -2481,7 +2481,7 @@ static void integrity_recalc(struct work_struct *w) next_chunk: - if (unlikely(dm_suspended(ic->ti))) + if (unlikely(dm_post_suspending(ic->ti))) goto unlock_ret; range.logical_sector = le64_to_cpu(ic->sb->recalc_sector); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 52449afd58eb..5b9de2f71bb0 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -143,6 +143,7 @@ EXPORT_SYMBOL_GPL(dm_bio_get_target_bio_nr); #define DMF_NOFLUSH_SUSPENDING 5 #define DMF_DEFERRED_REMOVE 6 #define DMF_SUSPENDED_INTERNALLY 7 +#define DMF_POST_SUSPENDING 8 #define DM_NUMA_NODE NUMA_NO_NODE static int dm_numa_node = DM_NUMA_NODE; @@ -2408,6 +2409,7 @@ static void __dm_destroy(struct mapped_device *md, bool wait) if (!dm_suspended_md(md)) { dm_table_presuspend_targets(map); set_bit(DMF_SUSPENDED, &md->flags); + set_bit(DMF_POST_SUSPENDING, &md->flags); dm_table_postsuspend_targets(map); } /* dm_put_live_table must be before msleep, otherwise deadlock is possible */ @@ -2766,7 +2768,9 @@ retry: if (r) goto out_unlock; + set_bit(DMF_POST_SUSPENDING, &md->flags); dm_table_postsuspend_targets(map); + clear_bit(DMF_POST_SUSPENDING, &md->flags); out_unlock: mutex_unlock(&md->suspend_lock); @@ -2863,7 +2867,9 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_fla (void) __dm_suspend(md, map, suspend_flags, TASK_UNINTERRUPTIBLE, DMF_SUSPENDED_INTERNALLY); + set_bit(DMF_POST_SUSPENDING, &md->flags); dm_table_postsuspend_targets(map); + clear_bit(DMF_POST_SUSPENDING, &md->flags); } static void __dm_internal_resume(struct mapped_device *md) @@ -3024,6 +3030,11 @@ int dm_suspended_md(struct mapped_device *md) return test_bit(DMF_SUSPENDED, &md->flags); } +static int dm_post_suspending_md(struct mapped_device *md) +{ + return test_bit(DMF_POST_SUSPENDING, &md->flags); +} + int dm_suspended_internally_md(struct mapped_device *md) { return test_bit(DMF_SUSPENDED_INTERNALLY, &md->flags); @@ -3040,6 +3051,12 @@ int dm_suspended(struct dm_target *ti) } EXPORT_SYMBOL_GPL(dm_suspended); +int dm_post_suspending(struct dm_target *ti) +{ + return dm_post_suspending_md(dm_table_get_md(ti->table)); +} +EXPORT_SYMBOL_GPL(dm_post_suspending); + int dm_noflush_suspending(struct dm_target *ti) { return __noflush_suspending(dm_table_get_md(ti->table)); diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c index b0f62cbbdc87..f3a8f113865d 100644 --- a/drivers/misc/habanalabs/command_submission.c +++ b/drivers/misc/habanalabs/command_submission.c @@ -499,11 +499,19 @@ static int validate_queue_index(struct hl_device *hdev, struct asic_fixed_properties *asic = &hdev->asic_prop; struct hw_queue_properties *hw_queue_prop; + /* This must be checked here to prevent out-of-bounds access to + * hw_queues_props array + */ + if (chunk->queue_index >= HL_MAX_QUEUES) { + dev_err(hdev->dev, "Queue index %d is invalid\n", + chunk->queue_index); + return -EINVAL; + } + hw_queue_prop = &asic->hw_queues_props[chunk->queue_index]; - if ((chunk->queue_index >= HL_MAX_QUEUES) || - (hw_queue_prop->type == QUEUE_TYPE_NA)) { - dev_err(hdev->dev, "Queue index %d is invalid\n", + if (hw_queue_prop->type == QUEUE_TYPE_NA) { + dev_err(hdev->dev, "Queue index %d is not applicable\n", chunk->queue_index); return -EINVAL; } diff --git a/drivers/misc/habanalabs/debugfs.c b/drivers/misc/habanalabs/debugfs.c index fc4372c18ce2..0bc036e01ee8 100644 --- a/drivers/misc/habanalabs/debugfs.c +++ b/drivers/misc/habanalabs/debugfs.c @@ -36,7 +36,7 @@ static int hl_debugfs_i2c_read(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr, pkt.i2c_reg = i2c_reg; rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, (long *) val); + 0, (long *) val); if (rc) dev_err(hdev->dev, "Failed to read from I2C, error %d\n", rc); @@ -63,7 +63,7 @@ static int hl_debugfs_i2c_write(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr, pkt.value = cpu_to_le64(val); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, "Failed to write to I2C, error %d\n", rc); @@ -87,7 +87,7 @@ static void hl_debugfs_led_set(struct hl_device *hdev, u8 led, u8 state) pkt.value = cpu_to_le64(state); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, "Failed to set LED %d, error %d\n", led, rc); @@ -981,7 +981,7 @@ static ssize_t hl_clk_gate_read(struct file *f, char __user *buf, if (*ppos) return 0; - sprintf(tmp_buf, "%d\n", hdev->clock_gating); + sprintf(tmp_buf, "0x%llx\n", hdev->clock_gating_mask); rc = simple_read_from_buffer(buf, strlen(tmp_buf) + 1, ppos, tmp_buf, strlen(tmp_buf) + 1); @@ -993,7 +993,7 @@ static ssize_t hl_clk_gate_write(struct file *f, const char __user *buf, { struct hl_dbg_device_entry *entry = file_inode(f)->i_private; struct hl_device *hdev = entry->hdev; - u32 value; + u64 value; ssize_t rc; if (atomic_read(&hdev->in_reset)) { @@ -1002,19 +1002,12 @@ static ssize_t hl_clk_gate_write(struct file *f, const char __user *buf, return 0; } - rc = kstrtouint_from_user(buf, count, 10, &value); + rc = kstrtoull_from_user(buf, count, 16, &value); if (rc) return rc; - if (value) { - hdev->clock_gating = 1; - if (hdev->asic_funcs->enable_clock_gating) - hdev->asic_funcs->enable_clock_gating(hdev); - } else { - if (hdev->asic_funcs->disable_clock_gating) - hdev->asic_funcs->disable_clock_gating(hdev); - hdev->clock_gating = 0; - } + hdev->clock_gating_mask = value; + hdev->asic_funcs->set_clock_gating(hdev); return count; } diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index 2b38a119704c..59608d1bac88 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -608,7 +608,7 @@ int hl_device_set_debug_mode(struct hl_device *hdev, bool enable) hdev->in_debug = 0; if (!hdev->hard_reset_pending) - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); goto out; } diff --git a/drivers/misc/habanalabs/firmware_if.c b/drivers/misc/habanalabs/firmware_if.c index baf790cf4b78..d27841cb5bcb 100644 --- a/drivers/misc/habanalabs/firmware_if.c +++ b/drivers/misc/habanalabs/firmware_if.c @@ -61,7 +61,7 @@ int hl_fw_send_pci_access_msg(struct hl_device *hdev, u32 opcode) pkt.ctl = cpu_to_le32(opcode << ARMCP_PKT_CTL_OPCODE_SHIFT); return hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, - sizeof(pkt), HL_DEVICE_TIMEOUT_USEC, NULL); + sizeof(pkt), 0, NULL); } int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg, @@ -144,7 +144,7 @@ int hl_fw_unmask_irq(struct hl_device *hdev, u16 event_type) pkt.value = cpu_to_le64(event_type); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, &result); + 0, &result); if (rc) dev_err(hdev->dev, "failed to unmask RAZWI IRQ %d", event_type); @@ -183,7 +183,7 @@ int hl_fw_unmask_irq_arr(struct hl_device *hdev, const u32 *irq_arr, ARMCP_PKT_CTL_OPCODE_SHIFT); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) pkt, - total_pkt_size, HL_DEVICE_TIMEOUT_USEC, &result); + total_pkt_size, 0, &result); if (rc) dev_err(hdev->dev, "failed to unmask IRQ array\n"); @@ -204,7 +204,7 @@ int hl_fw_test_cpu_queue(struct hl_device *hdev) test_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &test_pkt, - sizeof(test_pkt), HL_DEVICE_TIMEOUT_USEC, &result); + sizeof(test_pkt), 0, &result); if (!rc) { if (result != ARMCP_PACKET_FENCE_VAL) @@ -248,7 +248,7 @@ int hl_fw_send_heartbeat(struct hl_device *hdev) hb_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &hb_pkt, - sizeof(hb_pkt), HL_DEVICE_TIMEOUT_USEC, &result); + sizeof(hb_pkt), 0, &result); if ((rc) || (result != ARMCP_PACKET_FENCE_VAL)) rc = -EIO; diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 834470d10b46..637a9d608707 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -80,6 +80,7 @@ #define GAUDI_PLDM_QMAN0_TIMEOUT_USEC (HL_DEVICE_TIMEOUT_USEC * 30) #define GAUDI_PLDM_TPC_KERNEL_WAIT_USEC (HL_DEVICE_TIMEOUT_USEC * 30) #define GAUDI_BOOT_FIT_REQ_TIMEOUT_USEC 1000000 /* 1s */ +#define GAUDI_MSG_TO_CPU_TIMEOUT_USEC 4000000 /* 4s */ #define GAUDI_QMAN0_FENCE_VAL 0x72E91AB9 @@ -98,6 +99,11 @@ #define GAUDI_ARB_WDT_TIMEOUT 0x1000000 +#define GAUDI_CLK_GATE_DEBUGFS_MASK (\ + BIT(GAUDI_ENGINE_ID_MME_0) |\ + BIT(GAUDI_ENGINE_ID_MME_2) |\ + GENMASK_ULL(GAUDI_ENGINE_ID_TPC_7, GAUDI_ENGINE_ID_TPC_0)) + static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = { "gaudi cq 0_0", "gaudi cq 0_1", "gaudi cq 0_2", "gaudi cq 0_3", "gaudi cq 1_0", "gaudi cq 1_1", "gaudi cq 1_2", "gaudi cq 1_3", @@ -106,14 +112,14 @@ static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = { }; static const u8 gaudi_dma_assignment[GAUDI_DMA_MAX] = { - [GAUDI_PCI_DMA_1] = 0, - [GAUDI_PCI_DMA_2] = 1, - [GAUDI_PCI_DMA_3] = 5, - [GAUDI_HBM_DMA_1] = 2, - [GAUDI_HBM_DMA_2] = 3, - [GAUDI_HBM_DMA_3] = 4, - [GAUDI_HBM_DMA_4] = 6, - [GAUDI_HBM_DMA_5] = 7 + [GAUDI_PCI_DMA_1] = GAUDI_ENGINE_ID_DMA_0, + [GAUDI_PCI_DMA_2] = GAUDI_ENGINE_ID_DMA_1, + [GAUDI_PCI_DMA_3] = GAUDI_ENGINE_ID_DMA_5, + [GAUDI_HBM_DMA_1] = GAUDI_ENGINE_ID_DMA_2, + [GAUDI_HBM_DMA_2] = GAUDI_ENGINE_ID_DMA_3, + [GAUDI_HBM_DMA_3] = GAUDI_ENGINE_ID_DMA_4, + [GAUDI_HBM_DMA_4] = GAUDI_ENGINE_ID_DMA_6, + [GAUDI_HBM_DMA_5] = GAUDI_ENGINE_ID_DMA_7 }; static const u8 gaudi_cq_assignment[NUMBER_OF_CMPLT_QUEUES] = { @@ -1819,7 +1825,7 @@ static void gaudi_init_golden_registers(struct hl_device *hdev) gaudi_init_rate_limiter(hdev); - gaudi_disable_clock_gating(hdev); + hdev->asic_funcs->disable_clock_gating(hdev); for (tpc_id = 0, tpc_offset = 0; tpc_id < TPC_NUMBER_OF_ENGINES; @@ -2531,46 +2537,55 @@ static void gaudi_tpc_stall(struct hl_device *hdev) WREG32(mmTPC7_CFG_TPC_STALL, 1 << TPC0_CFG_TPC_STALL_V_SHIFT); } -static void gaudi_enable_clock_gating(struct hl_device *hdev) +static void gaudi_set_clock_gating(struct hl_device *hdev) { struct gaudi_device *gaudi = hdev->asic_specific; u32 qman_offset; int i; - if (!hdev->clock_gating) - return; - - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) - return; - /* In case we are during debug session, don't enable the clock gate * as it may interfere */ if (hdev->in_debug) return; - for (i = 0, qman_offset = 0 ; i < PCI_DMA_NUMBER_OF_CHNLS ; i++) { + for (i = GAUDI_PCI_DMA_1, qman_offset = 0 ; i < GAUDI_HBM_DMA_1 ; i++) { + if (!(hdev->clock_gating_mask & + (BIT_ULL(gaudi_dma_assignment[i])))) + continue; + qman_offset = gaudi_dma_assignment[i] * DMA_QMAN_OFFSET; WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN); WREG32(mmDMA0_QM_CGM_CFG + qman_offset, QMAN_UPPER_CP_CGM_PWR_GATE_EN); } - for (; i < HBM_DMA_NUMBER_OF_CHNLS ; i++) { + for (i = GAUDI_HBM_DMA_1 ; i < GAUDI_DMA_MAX ; i++) { + if (!(hdev->clock_gating_mask & + (BIT_ULL(gaudi_dma_assignment[i])))) + continue; + qman_offset = gaudi_dma_assignment[i] * DMA_QMAN_OFFSET; WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN); WREG32(mmDMA0_QM_CGM_CFG + qman_offset, QMAN_COMMON_CP_CGM_PWR_GATE_EN); } - WREG32(mmMME0_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN); - WREG32(mmMME0_QM_CGM_CFG, - QMAN_COMMON_CP_CGM_PWR_GATE_EN); - WREG32(mmMME2_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN); - WREG32(mmMME2_QM_CGM_CFG, - QMAN_COMMON_CP_CGM_PWR_GATE_EN); + if (hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_0))) { + WREG32(mmMME0_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN); + WREG32(mmMME0_QM_CGM_CFG, QMAN_COMMON_CP_CGM_PWR_GATE_EN); + } + + if (hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_2))) { + WREG32(mmMME2_QM_CGM_CFG1, QMAN_CGM1_PWR_GATE_EN); + WREG32(mmMME2_QM_CGM_CFG, QMAN_COMMON_CP_CGM_PWR_GATE_EN); + } for (i = 0, qman_offset = 0 ; i < TPC_NUMBER_OF_ENGINES ; i++) { + if (!(hdev->clock_gating_mask & + (BIT_ULL(GAUDI_ENGINE_ID_TPC_0 + i)))) + continue; + WREG32(mmTPC0_QM_CGM_CFG1 + qman_offset, QMAN_CGM1_PWR_GATE_EN); WREG32(mmTPC0_QM_CGM_CFG + qman_offset, @@ -2663,7 +2678,7 @@ static void gaudi_halt_engines(struct hl_device *hdev, bool hard_reset) gaudi_stop_hbm_dma_qmans(hdev); gaudi_stop_pci_dma_qmans(hdev); - gaudi_disable_clock_gating(hdev); + hdev->asic_funcs->disable_clock_gating(hdev); msleep(wait_timeout_ms); @@ -3003,7 +3018,7 @@ static int gaudi_hw_init(struct hl_device *hdev) gaudi_init_tpc_qmans(hdev); - gaudi_enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); gaudi_enable_timestamp(hdev); @@ -3112,7 +3127,9 @@ static void gaudi_hw_fini(struct hl_device *hdev, bool hard_reset) HW_CAP_HBM_DMA | HW_CAP_PLL | HW_CAP_MMU | HW_CAP_SRAM_SCRAMBLER | - HW_CAP_HBM_SCRAMBLER); + HW_CAP_HBM_SCRAMBLER | + HW_CAP_CLK_GATE); + memset(gaudi->events_stat, 0, sizeof(gaudi->events_stat)); } @@ -3463,6 +3480,9 @@ static int gaudi_send_cpu_message(struct hl_device *hdev, u32 *msg, return 0; } + if (!timeout) + timeout = GAUDI_MSG_TO_CPU_TIMEOUT_USEC; + return hl_fw_send_cpu_message(hdev, GAUDI_QUEUE_ID_CPU_PQ, msg, len, timeout, result); } @@ -3865,6 +3885,12 @@ static int gaudi_validate_cb(struct hl_device *hdev, rc = -EPERM; break; + case PACKET_WREG_BULK: + dev_err(hdev->dev, + "User not allowed to use WREG_BULK\n"); + rc = -EPERM; + break; + case PACKET_LOAD_AND_EXE: rc = gaudi_validate_load_and_exe_pkt(hdev, parser, (struct packet_load_and_exe *) user_pkt); @@ -3880,7 +3906,6 @@ static int gaudi_validate_cb(struct hl_device *hdev, break; case PACKET_WREG_32: - case PACKET_WREG_BULK: case PACKET_MSG_LONG: case PACKET_MSG_SHORT: case PACKET_REPEAT: @@ -4521,13 +4546,18 @@ static int gaudi_debugfs_read32(struct hl_device *hdev, u64 addr, u32 *val) int rc = 0; if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) { - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) { + + if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && + (hdev->clock_gating_mask & + GAUDI_CLK_GATE_DEBUGFS_MASK)) { + dev_err_ratelimited(hdev->dev, "Can't read register - clock gating is enabled!\n"); rc = -EFAULT; } else { *val = RREG32(addr - CFG_BASE); } + } else if ((addr >= SRAM_BASE_ADDR) && (addr < SRAM_BASE_ADDR + SRAM_BAR_SIZE)) { *val = readl(hdev->pcie_bar[SRAM_BAR_ID] + @@ -4563,13 +4593,18 @@ static int gaudi_debugfs_write32(struct hl_device *hdev, u64 addr, u32 val) int rc = 0; if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) { - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) { + + if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && + (hdev->clock_gating_mask & + GAUDI_CLK_GATE_DEBUGFS_MASK)) { + dev_err_ratelimited(hdev->dev, "Can't write register - clock gating is enabled!\n"); rc = -EFAULT; } else { WREG32(addr - CFG_BASE, val); } + } else if ((addr >= SRAM_BASE_ADDR) && (addr < SRAM_BASE_ADDR + SRAM_BAR_SIZE)) { writel(val, hdev->pcie_bar[SRAM_BAR_ID] + @@ -4605,7 +4640,11 @@ static int gaudi_debugfs_read64(struct hl_device *hdev, u64 addr, u64 *val) int rc = 0; if ((addr >= CFG_BASE) && (addr <= CFG_BASE + CFG_SIZE - sizeof(u64))) { - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) { + + if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && + (hdev->clock_gating_mask & + GAUDI_CLK_GATE_DEBUGFS_MASK)) { + dev_err_ratelimited(hdev->dev, "Can't read register - clock gating is enabled!\n"); rc = -EFAULT; @@ -4615,6 +4654,7 @@ static int gaudi_debugfs_read64(struct hl_device *hdev, u64 addr, u64 *val) *val = (((u64) val_h) << 32) | val_l; } + } else if ((addr >= SRAM_BASE_ADDR) && (addr <= SRAM_BASE_ADDR + SRAM_BAR_SIZE - sizeof(u64))) { *val = readq(hdev->pcie_bar[SRAM_BAR_ID] + @@ -4651,7 +4691,11 @@ static int gaudi_debugfs_write64(struct hl_device *hdev, u64 addr, u64 val) int rc = 0; if ((addr >= CFG_BASE) && (addr <= CFG_BASE + CFG_SIZE - sizeof(u64))) { - if (gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) { + + if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && + (hdev->clock_gating_mask & + GAUDI_CLK_GATE_DEBUGFS_MASK)) { + dev_err_ratelimited(hdev->dev, "Can't write register - clock gating is enabled!\n"); rc = -EFAULT; @@ -4660,6 +4704,7 @@ static int gaudi_debugfs_write64(struct hl_device *hdev, u64 addr, u64 val) WREG32(addr + sizeof(u32) - CFG_BASE, upper_32_bits(val)); } + } else if ((addr >= SRAM_BASE_ADDR) && (addr <= SRAM_BASE_ADDR + SRAM_BAR_SIZE - sizeof(u64))) { writeq(val, hdev->pcie_bar[SRAM_BAR_ID] + @@ -4881,7 +4926,7 @@ static void gaudi_mmu_prepare(struct hl_device *hdev, u32 asid) gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, asid); gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, asid); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); } @@ -5262,7 +5307,7 @@ static void gaudi_print_ecc_info_generic(struct hl_device *hdev, } if (disable_clock_gating) { - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); } } @@ -5749,7 +5794,7 @@ static bool gaudi_tpc_read_interrupts(struct hl_device *hdev, u8 tpc_id, /* Clear interrupts */ WREG32(mmTPC0_CFG_TPC_INTR_CAUSE + tpc_offset, 0); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); @@ -6265,7 +6310,7 @@ static bool gaudi_is_device_idle(struct hl_device *hdev, u32 *mask, if (s) seq_puts(s, "\n"); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); @@ -6366,7 +6411,7 @@ static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel, dev_err(hdev->dev, "Timeout while waiting for TPC%d icache prefetch\n", tpc_id); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); return -EIO; } @@ -6395,7 +6440,7 @@ static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel, 1000, kernel_timeout); - hdev->asic_funcs->enable_clock_gating(hdev); + hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); if (rc) { @@ -6736,7 +6781,7 @@ static const struct hl_asic_funcs gaudi_funcs = { .mmu_invalidate_cache = gaudi_mmu_invalidate_cache, .mmu_invalidate_cache_range = gaudi_mmu_invalidate_cache_range, .send_heartbeat = gaudi_send_heartbeat, - .enable_clock_gating = gaudi_enable_clock_gating, + .set_clock_gating = gaudi_set_clock_gating, .disable_clock_gating = gaudi_disable_clock_gating, .debug_coresight = gaudi_debug_coresight, .is_device_idle = gaudi_is_device_idle, diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 0d2952bb58df..88460b2138d8 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -88,6 +88,7 @@ #define GOYA_PLDM_MMU_TIMEOUT_USEC (MMU_CONFIG_TIMEOUT_USEC * 100) #define GOYA_PLDM_QMAN0_TIMEOUT_USEC (HL_DEVICE_TIMEOUT_USEC * 30) #define GOYA_BOOT_FIT_REQ_TIMEOUT_USEC 1000000 /* 1s */ +#define GOYA_MSG_TO_CPU_TIMEOUT_USEC 4000000 /* 4s */ #define GOYA_QMAN0_FENCE_VAL 0xD169B243 @@ -2830,6 +2831,9 @@ int goya_send_cpu_message(struct hl_device *hdev, u32 *msg, u16 len, return 0; } + if (!timeout) + timeout = GOYA_MSG_TO_CPU_TIMEOUT_USEC; + return hl_fw_send_cpu_message(hdev, GOYA_QUEUE_ID_CPU_PQ, msg, len, timeout, result); } @@ -4431,8 +4435,8 @@ static int goya_unmask_irq_arr(struct hl_device *hdev, u32 *irq_arr, pkt->armcp_pkt.ctl = cpu_to_le32(ARMCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY << ARMCP_PKT_CTL_OPCODE_SHIFT); - rc = goya_send_cpu_message(hdev, (u32 *) pkt, total_pkt_size, - HL_DEVICE_TIMEOUT_USEC, &result); + rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) pkt, + total_pkt_size, 0, &result); if (rc) dev_err(hdev->dev, "failed to unmask IRQ array\n"); @@ -4464,8 +4468,8 @@ static int goya_unmask_irq(struct hl_device *hdev, u16 event_type) ARMCP_PKT_CTL_OPCODE_SHIFT); pkt.value = cpu_to_le64(event_type); - rc = goya_send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, &result); + rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), + 0, &result); if (rc) dev_err(hdev->dev, "failed to unmask RAZWI IRQ %d", event_type); @@ -5028,14 +5032,14 @@ int goya_armcp_info_get(struct hl_device *hdev) return 0; } -static void goya_enable_clock_gating(struct hl_device *hdev) +static void goya_set_clock_gating(struct hl_device *hdev) { - + /* clock gating not supported in Goya */ } static void goya_disable_clock_gating(struct hl_device *hdev) { - + /* clock gating not supported in Goya */ } static bool goya_is_device_idle(struct hl_device *hdev, u32 *mask, @@ -5259,7 +5263,7 @@ static const struct hl_asic_funcs goya_funcs = { .mmu_invalidate_cache = goya_mmu_invalidate_cache, .mmu_invalidate_cache_range = goya_mmu_invalidate_cache_range, .send_heartbeat = goya_send_heartbeat, - .enable_clock_gating = goya_enable_clock_gating, + .set_clock_gating = goya_set_clock_gating, .disable_clock_gating = goya_disable_clock_gating, .debug_coresight = goya_debug_coresight, .is_device_idle = goya_is_device_idle, diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 1ecdcf8b763a..194d83352696 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -578,8 +578,9 @@ enum hl_pll_frequency { * @mmu_invalidate_cache_range: flush specific MMU STLB cache lines with * ASID-VA-size mask. * @send_heartbeat: send is-alive packet to ArmCP and verify response. - * @enable_clock_gating: enable clock gating for reducing power consumption. - * @disable_clock_gating: disable clock for accessing registers on HBW. + * @set_clock_gating: enable/disable clock gating per engine according to + * clock gating mask in hdev + * @disable_clock_gating: disable clock gating completely * @debug_coresight: perform certain actions on Coresight for debugging. * @is_device_idle: return true if device is idle, false otherwise. * @soft_reset_late_init: perform certain actions needed after soft reset. @@ -587,7 +588,11 @@ enum hl_pll_frequency { * @hw_queues_unlock: release H/W queues lock. * @get_pci_id: retrieve PCI ID. * @get_eeprom_data: retrieve EEPROM data from F/W. - * @send_cpu_message: send buffer to ArmCP. + * @send_cpu_message: send message to F/W. If the message is timedout, the + * driver will eventually reset the device. The timeout can + * be determined by the calling function or it can be 0 and + * then the timeout is the default timeout for the specific + * ASIC * @get_hw_state: retrieve the H/W state * @pci_bars_map: Map PCI BARs. * @set_dram_bar_base: Set DRAM BAR to map specific device address. Returns @@ -680,7 +685,7 @@ struct hl_asic_funcs { int (*mmu_invalidate_cache_range)(struct hl_device *hdev, bool is_hard, u32 asid, u64 va, u64 size); int (*send_heartbeat)(struct hl_device *hdev); - void (*enable_clock_gating)(struct hl_device *hdev); + void (*set_clock_gating)(struct hl_device *hdev); void (*disable_clock_gating)(struct hl_device *hdev); int (*debug_coresight)(struct hl_device *hdev, void *data); bool (*is_device_idle)(struct hl_device *hdev, u32 *mask, @@ -1398,6 +1403,9 @@ struct hl_device_idle_busy_ts { * @max_power: the max power of the device, as configured by the sysadmin. This * value is saved so in case of hard-reset, the driver will restore * this value and update the F/W after the re-initialization + * @clock_gating_mask: is clock gating enabled. bitmask that represents the + * different engines. See debugfs-driver-habanalabs for + * details. * @in_reset: is device in reset flow. * @curr_pll_profile: current PLL profile. * @cs_active_cnt: number of active command submissions on this device (active @@ -1425,7 +1433,6 @@ struct hl_device_idle_busy_ts { * @init_done: is the initialization of the device done. * @mmu_enable: is MMU enabled. * @mmu_huge_page_opt: is MMU huge pages optimization enabled. - * @clock_gating: is clock gating enabled. * @device_cpu_disabled: is the device CPU disabled (due to timeouts) * @dma_mask: the dma mask that was set for this device * @in_debug: is device under debug. This, together with fpriv_list, enforces @@ -1493,6 +1500,7 @@ struct hl_device { atomic64_t dram_used_mem; u64 timeout_jiffies; u64 max_power; + u64 clock_gating_mask; atomic_t in_reset; enum hl_pll_frequency curr_pll_profile; int cs_active_cnt; @@ -1514,7 +1522,6 @@ struct hl_device { u8 dram_default_page_mapping; u8 pmmu_huge_range; u8 init_done; - u8 clock_gating; u8 device_cpu_disabled; u8 dma_mask; u8 in_debug; diff --git a/drivers/misc/habanalabs/habanalabs_drv.c b/drivers/misc/habanalabs/habanalabs_drv.c index 8652c7e5d7f1..22716da9f85f 100644 --- a/drivers/misc/habanalabs/habanalabs_drv.c +++ b/drivers/misc/habanalabs/habanalabs_drv.c @@ -232,7 +232,7 @@ static void set_driver_behavior_per_device(struct hl_device *hdev) hdev->fw_loading = 1; hdev->cpu_queues_enable = 1; hdev->heartbeat = 1; - hdev->clock_gating = 1; + hdev->clock_gating_mask = ULONG_MAX; hdev->reset_pcilink = 0; hdev->axi_drain = 0; diff --git a/drivers/misc/habanalabs/hwmon.c b/drivers/misc/habanalabs/hwmon.c index 8c6cd77e6af6..b997336fa75f 100644 --- a/drivers/misc/habanalabs/hwmon.c +++ b/drivers/misc/habanalabs/hwmon.c @@ -10,7 +10,6 @@ #include <linux/pci.h> #include <linux/hwmon.h> -#define SENSORS_PKT_TIMEOUT 1000000 /* 1s */ #define HWMON_NR_SENSOR_TYPES (hwmon_pwm + 1) int hl_build_hwmon_channel_info(struct hl_device *hdev, @@ -323,7 +322,7 @@ int hl_get_temperature(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -350,7 +349,7 @@ int hl_set_temperature(struct hl_device *hdev, pkt.value = __cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, @@ -374,7 +373,7 @@ int hl_get_voltage(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -400,7 +399,7 @@ int hl_get_current(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -426,7 +425,7 @@ int hl_get_fan_speed(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -452,7 +451,7 @@ int hl_get_pwm_info(struct hl_device *hdev, pkt.type = __cpu_to_le16(attr); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, value); + 0, value); if (rc) { dev_err(hdev->dev, @@ -479,7 +478,7 @@ void hl_set_pwm_info(struct hl_device *hdev, int sensor_index, u32 attr, pkt.value = cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, @@ -502,7 +501,7 @@ int hl_set_voltage(struct hl_device *hdev, pkt.value = __cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, @@ -527,7 +526,7 @@ int hl_set_current(struct hl_device *hdev, pkt.value = __cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SENSORS_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, diff --git a/drivers/misc/habanalabs/sysfs.c b/drivers/misc/habanalabs/sysfs.c index 5d78d5e1c782..70b6b1863c2e 100644 --- a/drivers/misc/habanalabs/sysfs.c +++ b/drivers/misc/habanalabs/sysfs.c @@ -9,9 +9,6 @@ #include <linux/pci.h> -#define SET_CLK_PKT_TIMEOUT 1000000 /* 1s */ -#define SET_PWR_PKT_TIMEOUT 1000000 /* 1s */ - long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr) { struct armcp_packet pkt; @@ -29,7 +26,7 @@ long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr) pkt.pll_index = cpu_to_le32(pll_index); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SET_CLK_PKT_TIMEOUT, &result); + 0, &result); if (rc) { dev_err(hdev->dev, @@ -54,7 +51,7 @@ void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq) pkt.value = cpu_to_le64(freq); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SET_CLK_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, @@ -74,7 +71,7 @@ u64 hl_get_max_power(struct hl_device *hdev) ARMCP_PKT_CTL_OPCODE_SHIFT); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SET_PWR_PKT_TIMEOUT, &result); + 0, &result); if (rc) { dev_err(hdev->dev, "Failed to get max power, error %d\n", rc); @@ -96,7 +93,7 @@ void hl_set_max_power(struct hl_device *hdev, u64 value) pkt.value = cpu_to_le64(value); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - SET_PWR_PKT_TIMEOUT, NULL); + 0, NULL); if (rc) dev_err(hdev->dev, "Failed to set max power, error %d\n", rc); diff --git a/drivers/mmc/host/sdhci-of-aspeed.c b/drivers/mmc/host/sdhci-of-aspeed.c index 56912e30c47e..a1bcc0f4ba9e 100644 --- a/drivers/mmc/host/sdhci-of-aspeed.c +++ b/drivers/mmc/host/sdhci-of-aspeed.c @@ -68,7 +68,7 @@ static void aspeed_sdhci_set_clock(struct sdhci_host *host, unsigned int clock) if (WARN_ON(clock > host->max_clk)) clock = host->max_clk; - for (div = 1; div < 256; div *= 2) { + for (div = 2; div < 256; div *= 2) { if ((parent / div) <= clock) break; } diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index 3dd46cd55114..88e7900853db 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -407,19 +407,34 @@ free_dst: return err; } +static bool bareudp_proto_valid(struct bareudp_dev *bareudp, __be16 proto) +{ + if (bareudp->ethertype == proto) + return true; + + if (!bareudp->multi_proto_mode) + return false; + + if (bareudp->ethertype == htons(ETH_P_MPLS_UC) && + proto == htons(ETH_P_MPLS_MC)) + return true; + + if (bareudp->ethertype == htons(ETH_P_IP) && + proto == htons(ETH_P_IPV6)) + return true; + + return false; +} + static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev) { struct bareudp_dev *bareudp = netdev_priv(dev); struct ip_tunnel_info *info = NULL; int err; - if (skb->protocol != bareudp->ethertype) { - if (!bareudp->multi_proto_mode || - (skb->protocol != htons(ETH_P_MPLS_MC) && - skb->protocol != htons(ETH_P_IPV6))) { - err = -EINVAL; - goto tx_error; - } + if (!bareudp_proto_valid(bareudp, skb->protocol)) { + err = -EINVAL; + goto tx_error; } info = skb_tunnel_info(skb); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 004919aea5fb..f88cb097b022 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -5053,15 +5053,19 @@ int bond_create(struct net *net, const char *name) bond_dev->rtnl_link_ops = &bond_link_ops; res = register_netdevice(bond_dev); + if (res < 0) { + free_netdev(bond_dev); + rtnl_unlock(); + + return res; + } netif_carrier_off(bond_dev); bond_work_init_all(bond); rtnl_unlock(); - if (res < 0) - free_netdev(bond_dev); - return res; + return 0; } static int __net_init bond_net_init(struct net *net) diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index b43b51646b11..f0f9138e967f 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -456,11 +456,10 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev, return err; err = register_netdevice(bond_dev); - - netif_carrier_off(bond_dev); if (!err) { struct bonding *bond = netdev_priv(bond_dev); + netif_carrier_off(bond_dev); bond_work_init_all(bond); } diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 8d15c3016024..4a9239b2c2e4 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -974,23 +974,6 @@ static void ksz9477_port_mirror_del(struct dsa_switch *ds, int port, PORT_MIRROR_SNIFFER, false); } -static void ksz9477_phy_setup(struct ksz_device *dev, int port, - struct phy_device *phy) -{ - /* Only apply to port with PHY. */ - if (port >= dev->phy_port_cnt) - return; - - /* The MAC actually cannot run in 1000 half-duplex mode. */ - phy_remove_link_mode(phy, - ETHTOOL_LINK_MODE_1000baseT_Half_BIT); - - /* PHY does not support gigabit. */ - if (!(dev->features & GBIT_SUPPORT)) - phy_remove_link_mode(phy, - ETHTOOL_LINK_MODE_1000baseT_Full_BIT); -} - static bool ksz9477_get_gbit(struct ksz_device *dev, u8 data) { bool gbit; @@ -1603,7 +1586,6 @@ static const struct ksz_dev_ops ksz9477_dev_ops = { .get_port_addr = ksz9477_get_port_addr, .cfg_port_member = ksz9477_cfg_port_member, .flush_dyn_mac_table = ksz9477_flush_dyn_mac_table, - .phy_setup = ksz9477_phy_setup, .port_setup = ksz9477_port_setup, .r_mib_cnt = ksz9477_r_mib_cnt, .r_mib_pkt = ksz9477_r_mib_pkt, @@ -1617,7 +1599,29 @@ static const struct ksz_dev_ops ksz9477_dev_ops = { int ksz9477_switch_register(struct ksz_device *dev) { - return ksz_switch_register(dev, &ksz9477_dev_ops); + int ret, i; + struct phy_device *phydev; + + ret = ksz_switch_register(dev, &ksz9477_dev_ops); + if (ret) + return ret; + + for (i = 0; i < dev->phy_port_cnt; ++i) { + if (!dsa_is_user_port(dev->ds, i)) + continue; + + phydev = dsa_to_port(dev->ds, i)->slave->phydev; + + /* The MAC actually cannot run in 1000 half-duplex mode. */ + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + + /* PHY does not support gigabit. */ + if (!(dev->features & GBIT_SUPPORT)) + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT); + } + return ret; } EXPORT_SYMBOL(ksz9477_switch_register); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index fd1d6676ae4f..7b6c0dce7536 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -358,8 +358,6 @@ int ksz_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) /* setup slave port */ dev->dev_ops->port_setup(dev, port, false); - if (dev->dev_ops->phy_setup) - dev->dev_ops->phy_setup(dev, port, phy); /* port_stp_state_set() will be called after to enable the port so * there is no need to do anything. diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index f2c9bb68fd33..7d11dd32ec0d 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -119,8 +119,6 @@ struct ksz_dev_ops { u32 (*get_port_addr)(int port, int offset); void (*cfg_port_member)(struct ksz_device *dev, int port, u8 member); void (*flush_dyn_mac_table)(struct ksz_device *dev, int port); - void (*phy_setup)(struct ksz_device *dev, int port, - struct phy_device *phy); void (*port_cleanup)(struct ksz_device *dev, int port); void (*port_setup)(struct ksz_device *dev, int port, bool cpu_port); void (*r_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 *val); diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 7627ea61e0ea..fee16c947c2e 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -664,8 +664,11 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, const struct phylink_link_state *state) { struct mv88e6xxx_chip *chip = ds->priv; + struct mv88e6xxx_port *p; int err; + p = &chip->ports[port]; + /* FIXME: is this the correct test? If we're in fixed mode on an * internal port, why should we process this any different from * PHY mode? On the other hand, the port may be automedia between @@ -675,10 +678,14 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, return; mv88e6xxx_reg_lock(chip); - /* FIXME: should we force the link down here - but if we do, how - * do we restore the link force/unforce state? The driver layering - * gets in the way. + /* In inband mode, the link may come up at any time while the link + * is not forced down. Force the link down while we reconfigure the + * interface mode. */ + if (mode == MLO_AN_INBAND && p->interface != state->interface && + chip->info->ops->port_set_link) + chip->info->ops->port_set_link(chip, port, LINK_FORCED_DOWN); + err = mv88e6xxx_port_config_interface(chip, port, state->interface); if (err && err != -EOPNOTSUPP) goto err_unlock; @@ -691,6 +698,15 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, if (err > 0) err = 0; + /* Undo the forced down state above after completing configuration + * irrespective of its state on entry, which allows the link to come up. + */ + if (mode == MLO_AN_INBAND && p->interface != state->interface && + chip->info->ops->port_set_link) + chip->info->ops->port_set_link(chip, port, LINK_UNFORCED); + + p->interface = state->interface; + err_unlock: mv88e6xxx_reg_unlock(chip); diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index e5430cf2ad71..6476524e8239 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -232,6 +232,7 @@ struct mv88e6xxx_port { u64 atu_full_violation; u64 vtu_member_violation; u64 vtu_miss_violation; + phy_interface_t interface; u8 cmode; bool mirror_ingress; bool mirror_egress; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index ed5b465bc664..992fedbe4ce3 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -64,6 +64,7 @@ struct aq_hw_caps_s { u8 rx_rings; bool flow_control; bool is_64_dma; + u32 quirks; u32 priv_data_len; }; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 4435c6374f7e..7c7bf6bf163f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -415,6 +415,15 @@ int aq_nic_init(struct aq_nic_s *self) self->aq_nic_cfg.aq_hw_caps->media_type == AQ_HW_MEDIA_TYPE_TP) { self->aq_hw->phy_id = HW_ATL_PHY_ID_MAX; err = aq_phy_init(self->aq_hw); + + /* Disable the PTP on NICs where it's known to cause datapath + * problems. + * Ideally this should have been done by PHY provisioning, but + * many units have been shipped with enabled PTP block already. + */ + if (self->aq_nic_cfg.aq_hw_caps->quirks & AQ_NIC_QUIRK_BAD_PTP) + if (self->aq_hw->phy_id != HW_ATL_PHY_ID_MAX) + aq_phy_disable_ptp(self->aq_hw); } for (i = 0U; i < self->aq_vecs; i++) { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index 2ab003065e62..439ce9692dac 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -81,6 +81,8 @@ struct aq_nic_cfg_s { #define AQ_NIC_FLAG_ERR_UNPLUG 0x40000000U #define AQ_NIC_FLAG_ERR_HW 0x80000000U +#define AQ_NIC_QUIRK_BAD_PTP BIT(0) + #define AQ_NIC_WOL_MODES (WAKE_MAGIC |\ WAKE_PHY) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_phy.c b/drivers/net/ethernet/aquantia/atlantic/aq_phy.c index 51ae921e3e1f..949ac2351701 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_phy.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_phy.c @@ -1,10 +1,14 @@ // SPDX-License-Identifier: GPL-2.0-only -/* aQuantia Corporation Network Driver - * Copyright (C) 2018-2019 aQuantia Corporation. All rights reserved +/* Atlantic Network Driver + * + * Copyright (C) 2018-2019 aQuantia Corporation + * Copyright (C) 2019-2020 Marvell International Ltd. */ #include "aq_phy.h" +#define HW_ATL_PTP_DISABLE_MSK BIT(10) + bool aq_mdio_busy_wait(struct aq_hw_s *aq_hw) { int err = 0; @@ -145,3 +149,24 @@ bool aq_phy_init(struct aq_hw_s *aq_hw) return true; } + +void aq_phy_disable_ptp(struct aq_hw_s *aq_hw) +{ + static const u16 ptp_registers[] = { + 0x031e, + 0x031d, + 0x031c, + 0x031b, + }; + u16 val; + int i; + + for (i = 0; i < ARRAY_SIZE(ptp_registers); i++) { + val = aq_phy_read_reg(aq_hw, MDIO_MMD_VEND1, + ptp_registers[i]); + + aq_phy_write_reg(aq_hw, MDIO_MMD_VEND1, + ptp_registers[i], + val & ~HW_ATL_PTP_DISABLE_MSK); + } +} diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_phy.h b/drivers/net/ethernet/aquantia/atlantic/aq_phy.h index 84b72ad04a4a..86cc1ee836e2 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_phy.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_phy.h @@ -1,6 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/* aQuantia Corporation Network Driver - * Copyright (C) 2018-2019 aQuantia Corporation. All rights reserved +/* Atlantic Network Driver + * + * Copyright (C) 2018-2019 aQuantia Corporation + * Copyright (C) 2019-2020 Marvell International Ltd. */ #ifndef AQ_PHY_H @@ -29,4 +31,6 @@ bool aq_phy_init_phy_id(struct aq_hw_s *aq_hw); bool aq_phy_init(struct aq_hw_s *aq_hw); +void aq_phy_disable_ptp(struct aq_hw_s *aq_hw); + #endif /* AQ_PHY_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 14d79f70cad7..2125bc20ab6a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -93,6 +93,25 @@ const struct aq_hw_caps_s hw_atl_b0_caps_aqc109 = { AQ_NIC_RATE_100M, }; +const struct aq_hw_caps_s hw_atl_b0_caps_aqc111 = { + DEFAULT_B0_BOARD_BASIC_CAPABILITIES, + .media_type = AQ_HW_MEDIA_TYPE_TP, + .link_speed_msk = AQ_NIC_RATE_5G | + AQ_NIC_RATE_2G5 | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, + .quirks = AQ_NIC_QUIRK_BAD_PTP, +}; + +const struct aq_hw_caps_s hw_atl_b0_caps_aqc112 = { + DEFAULT_B0_BOARD_BASIC_CAPABILITIES, + .media_type = AQ_HW_MEDIA_TYPE_TP, + .link_speed_msk = AQ_NIC_RATE_2G5 | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, + .quirks = AQ_NIC_QUIRK_BAD_PTP, +}; + static int hw_atl_b0_hw_reset(struct aq_hw_s *self) { int err = 0; @@ -354,8 +373,13 @@ static int hw_atl_b0_hw_init_tx_tc_rate_limit(struct aq_hw_s *self) /* WSP, if min_rate is set for at least one TC. * RR otherwise. + * + * NB! MAC FW sets arb mode itself if PTP is enabled. We shouldn't + * overwrite it here in that case. */ - hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, min_rate_msk ? 1U : 0U); + if (!nic_cfg->is_ptp) + hw_atl_tps_tx_pkt_shed_data_arb_mode_set(self, min_rate_msk ? 1U : 0U); + /* Data TC Arbiter takes precedence over Descriptor TC Arbiter, * leave Descriptor TC Arbiter as RR. */ diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h index 30f468f2084d..16091af17980 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h @@ -18,17 +18,15 @@ extern const struct aq_hw_caps_s hw_atl_b0_caps_aqc100; extern const struct aq_hw_caps_s hw_atl_b0_caps_aqc107; extern const struct aq_hw_caps_s hw_atl_b0_caps_aqc108; extern const struct aq_hw_caps_s hw_atl_b0_caps_aqc109; - -#define hw_atl_b0_caps_aqc111 hw_atl_b0_caps_aqc108 -#define hw_atl_b0_caps_aqc112 hw_atl_b0_caps_aqc109 +extern const struct aq_hw_caps_s hw_atl_b0_caps_aqc111; +extern const struct aq_hw_caps_s hw_atl_b0_caps_aqc112; #define hw_atl_b0_caps_aqc100s hw_atl_b0_caps_aqc100 #define hw_atl_b0_caps_aqc107s hw_atl_b0_caps_aqc107 #define hw_atl_b0_caps_aqc108s hw_atl_b0_caps_aqc108 #define hw_atl_b0_caps_aqc109s hw_atl_b0_caps_aqc109 - -#define hw_atl_b0_caps_aqc111s hw_atl_b0_caps_aqc108 -#define hw_atl_b0_caps_aqc112s hw_atl_b0_caps_aqc109 +#define hw_atl_b0_caps_aqc111s hw_atl_b0_caps_aqc111 +#define hw_atl_b0_caps_aqc112s hw_atl_b0_caps_aqc112 extern const struct aq_hw_ops hw_atl_ops_b0; diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 112edbd30823..38cce66ef212 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -556,7 +556,8 @@ static int ag71xx_mdio_probe(struct ag71xx *ag) ag->mdio_reset = of_reset_control_get_exclusive(np, "mdio"); if (IS_ERR(ag->mdio_reset)) { netif_err(ag, probe, ndev, "Failed to get reset mdio.\n"); - return PTR_ERR(ag->mdio_reset); + err = PTR_ERR(ag->mdio_reset); + goto mdio_err_put_clk; } mii_bus->name = "ag71xx_mdio"; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6a884df44612..7463a1847ceb 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3418,7 +3418,7 @@ void bnxt_set_tpa_flags(struct bnxt *bp) */ void bnxt_set_ring_params(struct bnxt *bp) { - u32 ring_size, rx_size, rx_space; + u32 ring_size, rx_size, rx_space, max_rx_cmpl; u32 agg_factor = 0, agg_ring_size = 0; /* 8 for CRC and VLAN */ @@ -3474,7 +3474,15 @@ void bnxt_set_ring_params(struct bnxt *bp) bp->tx_nr_pages = bnxt_calc_nr_ring_pages(ring_size, TX_DESC_CNT); bp->tx_ring_mask = (bp->tx_nr_pages * TX_DESC_CNT) - 1; - ring_size = bp->rx_ring_size * (2 + agg_factor) + bp->tx_ring_size; + max_rx_cmpl = bp->rx_ring_size; + /* MAX TPA needs to be added because TPA_START completions are + * immediately recycled, so the TPA completions are not bound by + * the RX ring size. + */ + if (bp->flags & BNXT_FLAG_TPA) + max_rx_cmpl += bp->max_tpa; + /* RX and TPA completions are 32-byte, all others are 16-byte */ + ring_size = max_rx_cmpl * 2 + agg_ring_size + bp->tx_ring_size; bp->cp_ring_size = ring_size; bp->cp_nr_pages = bnxt_calc_nr_ring_pages(ring_size, CP_DESC_CNT); @@ -10385,15 +10393,15 @@ static void bnxt_sp_task(struct work_struct *work) &bp->sp_event)) bnxt_hwrm_phy_qcaps(bp); - if (test_and_clear_bit(BNXT_LINK_CFG_CHANGE_SP_EVENT, - &bp->sp_event)) - bnxt_init_ethtool_link_settings(bp); - rc = bnxt_update_link(bp, true); - mutex_unlock(&bp->link_lock); if (rc) netdev_err(bp->dev, "SP task can't update link (rc: %x)\n", rc); + + if (test_and_clear_bit(BNXT_LINK_CFG_CHANGE_SP_EVENT, + &bp->sp_event)) + bnxt_init_ethtool_link_settings(bp); + mutex_unlock(&bp->link_lock); } if (test_and_clear_bit(BNXT_UPDATE_PHY_SP_EVENT, &bp->sp_event)) { int rc; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 6b88143af5ea..b4aa56dc4f9f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -1765,8 +1765,11 @@ static int bnxt_set_pauseparam(struct net_device *dev, if (epause->tx_pause) link_info->req_flow_ctrl |= BNXT_LINK_PAUSE_TX; - if (netif_running(dev)) + if (netif_running(dev)) { + mutex_lock(&bp->link_lock); rc = bnxt_hwrm_set_pause(bp); + mutex_unlock(&bp->link_lock); + } return rc; } diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index af924a8b885f..e471b14fc6e9 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -543,14 +543,14 @@ static int bcmgenet_hfb_validate_mask(void *mask, size_t size) #define VALIDATE_MASK(x) \ bcmgenet_hfb_validate_mask(&(x), sizeof(x)) -static int bcmgenet_hfb_insert_data(u32 *f, int offset, - void *val, void *mask, size_t size) +static int bcmgenet_hfb_insert_data(struct bcmgenet_priv *priv, u32 f_index, + u32 offset, void *val, void *mask, + size_t size) { - int index; - u32 tmp; + u32 index, tmp; - index = offset / 2; - tmp = f[index]; + index = f_index * priv->hw_params->hfb_filter_size + offset / 2; + tmp = bcmgenet_hfb_readl(priv, index * sizeof(u32)); while (size--) { if (offset++ & 1) { @@ -567,9 +567,10 @@ static int bcmgenet_hfb_insert_data(u32 *f, int offset, tmp |= 0x10000; break; } - f[index++] = tmp; + bcmgenet_hfb_writel(priv, tmp, index++ * sizeof(u32)); if (size) - tmp = f[index]; + tmp = bcmgenet_hfb_readl(priv, + index * sizeof(u32)); } else { tmp &= ~0xCFF00; tmp |= (*(unsigned char *)val++) << 8; @@ -585,44 +586,26 @@ static int bcmgenet_hfb_insert_data(u32 *f, int offset, break; } if (!size) - f[index] = tmp; + bcmgenet_hfb_writel(priv, tmp, index * sizeof(u32)); } } return 0; } -static void bcmgenet_hfb_set_filter(struct bcmgenet_priv *priv, u32 *f_data, - u32 f_length, u32 rx_queue, int f_index) -{ - u32 base = f_index * priv->hw_params->hfb_filter_size; - int i; - - for (i = 0; i < f_length; i++) - bcmgenet_hfb_writel(priv, f_data[i], (base + i) * sizeof(u32)); - - bcmgenet_hfb_set_filter_length(priv, f_index, 2 * f_length); - bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f_index, rx_queue); -} - -static int bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv, - struct bcmgenet_rxnfc_rule *rule) +static void bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv, + struct bcmgenet_rxnfc_rule *rule) { struct ethtool_rx_flow_spec *fs = &rule->fs; - int err = 0, offset = 0, f_length = 0; + u32 offset = 0, f_length = 0, f; u8 val_8, mask_8; __be16 val_16; u16 mask_16; size_t size; - u32 *f_data; - - f_data = kcalloc(priv->hw_params->hfb_filter_size, sizeof(u32), - GFP_KERNEL); - if (!f_data) - return -ENOMEM; + f = fs->location; if (fs->flow_type & FLOW_MAC_EXT) { - bcmgenet_hfb_insert_data(f_data, 0, + bcmgenet_hfb_insert_data(priv, f, 0, &fs->h_ext.h_dest, &fs->m_ext.h_dest, sizeof(fs->h_ext.h_dest)); } @@ -630,11 +613,11 @@ static int bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv, if (fs->flow_type & FLOW_EXT) { if (fs->m_ext.vlan_etype || fs->m_ext.vlan_tci) { - bcmgenet_hfb_insert_data(f_data, 12, + bcmgenet_hfb_insert_data(priv, f, 12, &fs->h_ext.vlan_etype, &fs->m_ext.vlan_etype, sizeof(fs->h_ext.vlan_etype)); - bcmgenet_hfb_insert_data(f_data, 14, + bcmgenet_hfb_insert_data(priv, f, 14, &fs->h_ext.vlan_tci, &fs->m_ext.vlan_tci, sizeof(fs->h_ext.vlan_tci)); @@ -646,15 +629,15 @@ static int bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv, switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) { case ETHER_FLOW: f_length += DIV_ROUND_UP(ETH_HLEN, 2); - bcmgenet_hfb_insert_data(f_data, 0, + bcmgenet_hfb_insert_data(priv, f, 0, &fs->h_u.ether_spec.h_dest, &fs->m_u.ether_spec.h_dest, sizeof(fs->h_u.ether_spec.h_dest)); - bcmgenet_hfb_insert_data(f_data, ETH_ALEN, + bcmgenet_hfb_insert_data(priv, f, ETH_ALEN, &fs->h_u.ether_spec.h_source, &fs->m_u.ether_spec.h_source, sizeof(fs->h_u.ether_spec.h_source)); - bcmgenet_hfb_insert_data(f_data, (2 * ETH_ALEN) + offset, + bcmgenet_hfb_insert_data(priv, f, (2 * ETH_ALEN) + offset, &fs->h_u.ether_spec.h_proto, &fs->m_u.ether_spec.h_proto, sizeof(fs->h_u.ether_spec.h_proto)); @@ -664,21 +647,21 @@ static int bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv, /* Specify IP Ether Type */ val_16 = htons(ETH_P_IP); mask_16 = 0xFFFF; - bcmgenet_hfb_insert_data(f_data, (2 * ETH_ALEN) + offset, + bcmgenet_hfb_insert_data(priv, f, (2 * ETH_ALEN) + offset, &val_16, &mask_16, sizeof(val_16)); - bcmgenet_hfb_insert_data(f_data, 15 + offset, + bcmgenet_hfb_insert_data(priv, f, 15 + offset, &fs->h_u.usr_ip4_spec.tos, &fs->m_u.usr_ip4_spec.tos, sizeof(fs->h_u.usr_ip4_spec.tos)); - bcmgenet_hfb_insert_data(f_data, 23 + offset, + bcmgenet_hfb_insert_data(priv, f, 23 + offset, &fs->h_u.usr_ip4_spec.proto, &fs->m_u.usr_ip4_spec.proto, sizeof(fs->h_u.usr_ip4_spec.proto)); - bcmgenet_hfb_insert_data(f_data, 26 + offset, + bcmgenet_hfb_insert_data(priv, f, 26 + offset, &fs->h_u.usr_ip4_spec.ip4src, &fs->m_u.usr_ip4_spec.ip4src, sizeof(fs->h_u.usr_ip4_spec.ip4src)); - bcmgenet_hfb_insert_data(f_data, 30 + offset, + bcmgenet_hfb_insert_data(priv, f, 30 + offset, &fs->h_u.usr_ip4_spec.ip4dst, &fs->m_u.usr_ip4_spec.ip4dst, sizeof(fs->h_u.usr_ip4_spec.ip4dst)); @@ -688,11 +671,11 @@ static int bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv, /* Only supports 20 byte IPv4 header */ val_8 = 0x45; mask_8 = 0xFF; - bcmgenet_hfb_insert_data(f_data, ETH_HLEN + offset, + bcmgenet_hfb_insert_data(priv, f, ETH_HLEN + offset, &val_8, &mask_8, sizeof(val_8)); size = sizeof(fs->h_u.usr_ip4_spec.l4_4_bytes); - bcmgenet_hfb_insert_data(f_data, + bcmgenet_hfb_insert_data(priv, f, ETH_HLEN + 20 + offset, &fs->h_u.usr_ip4_spec.l4_4_bytes, &fs->m_u.usr_ip4_spec.l4_4_bytes, @@ -701,34 +684,42 @@ static int bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv, break; } + bcmgenet_hfb_set_filter_length(priv, f, 2 * f_length); if (!fs->ring_cookie || fs->ring_cookie == RX_CLS_FLOW_WAKE) { /* Ring 0 flows can be handled by the default Descriptor Ring * We'll map them to ring 0, but don't enable the filter */ - bcmgenet_hfb_set_filter(priv, f_data, f_length, 0, - fs->location); + bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f, 0); rule->state = BCMGENET_RXNFC_STATE_DISABLED; } else { /* Other Rx rings are direct mapped here */ - bcmgenet_hfb_set_filter(priv, f_data, f_length, - fs->ring_cookie, fs->location); - bcmgenet_hfb_enable_filter(priv, fs->location); + bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f, + fs->ring_cookie); + bcmgenet_hfb_enable_filter(priv, f); rule->state = BCMGENET_RXNFC_STATE_ENABLED; } - - kfree(f_data); - - return err; } /* bcmgenet_hfb_clear * * Clear Hardware Filter Block and disable all filtering. */ +static void bcmgenet_hfb_clear_filter(struct bcmgenet_priv *priv, u32 f_index) +{ + u32 base, i; + + base = f_index * priv->hw_params->hfb_filter_size; + for (i = 0; i < priv->hw_params->hfb_filter_size; i++) + bcmgenet_hfb_writel(priv, 0x0, (base + i) * sizeof(u32)); +} + static void bcmgenet_hfb_clear(struct bcmgenet_priv *priv) { u32 i; + if (GENET_IS_V1(priv) || GENET_IS_V2(priv)) + return; + bcmgenet_hfb_reg_writel(priv, 0x0, HFB_CTRL); bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS); bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS + 4); @@ -740,19 +731,18 @@ static void bcmgenet_hfb_clear(struct bcmgenet_priv *priv) bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_LEN_V3PLUS + i * sizeof(u32)); - for (i = 0; i < priv->hw_params->hfb_filter_cnt * - priv->hw_params->hfb_filter_size; i++) - bcmgenet_hfb_writel(priv, 0x0, i * sizeof(u32)); + for (i = 0; i < priv->hw_params->hfb_filter_cnt; i++) + bcmgenet_hfb_clear_filter(priv, i); } static void bcmgenet_hfb_init(struct bcmgenet_priv *priv) { int i; + INIT_LIST_HEAD(&priv->rxnfc_list); if (GENET_IS_V1(priv) || GENET_IS_V2(priv)) return; - INIT_LIST_HEAD(&priv->rxnfc_list); for (i = 0; i < MAX_NUM_OF_FS_RULES; i++) { INIT_LIST_HEAD(&priv->rxnfc_rules[i].list); priv->rxnfc_rules[i].state = BCMGENET_RXNFC_STATE_UNUSED; @@ -1437,18 +1427,15 @@ static int bcmgenet_insert_flow(struct net_device *dev, loc_rule = &priv->rxnfc_rules[cmd->fs.location]; if (loc_rule->state == BCMGENET_RXNFC_STATE_ENABLED) bcmgenet_hfb_disable_filter(priv, cmd->fs.location); - if (loc_rule->state != BCMGENET_RXNFC_STATE_UNUSED) + if (loc_rule->state != BCMGENET_RXNFC_STATE_UNUSED) { list_del(&loc_rule->list); + bcmgenet_hfb_clear_filter(priv, cmd->fs.location); + } loc_rule->state = BCMGENET_RXNFC_STATE_UNUSED; memcpy(&loc_rule->fs, &cmd->fs, sizeof(struct ethtool_rx_flow_spec)); - err = bcmgenet_hfb_create_rxnfc_filter(priv, loc_rule); - if (err) { - netdev_err(dev, "rxnfc: Could not install rule (%d)\n", - err); - return err; - } + bcmgenet_hfb_create_rxnfc_filter(priv, loc_rule); list_add_tail(&loc_rule->list, &priv->rxnfc_list); @@ -1473,8 +1460,10 @@ static int bcmgenet_delete_flow(struct net_device *dev, if (rule->state == BCMGENET_RXNFC_STATE_ENABLED) bcmgenet_hfb_disable_filter(priv, cmd->fs.location); - if (rule->state != BCMGENET_RXNFC_STATE_UNUSED) + if (rule->state != BCMGENET_RXNFC_STATE_UNUSED) { list_del(&rule->list); + bcmgenet_hfb_clear_filter(priv, cmd->fs.location); + } rule->state = BCMGENET_RXNFC_STATE_UNUSED; memset(&rule->fs, 0, sizeof(struct ethtool_rx_flow_spec)); @@ -3999,7 +3988,7 @@ static int bcmgenet_probe(struct platform_device *pdev) if (err) err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) - goto err; + goto err_clk_disable; /* Mii wait queue */ init_waitqueue_head(&priv->wq); @@ -4011,14 +4000,14 @@ static int bcmgenet_probe(struct platform_device *pdev) if (IS_ERR(priv->clk_wol)) { dev_dbg(&priv->pdev->dev, "failed to get enet-wol clock\n"); err = PTR_ERR(priv->clk_wol); - goto err; + goto err_clk_disable; } priv->clk_eee = devm_clk_get_optional(&priv->pdev->dev, "enet-eee"); if (IS_ERR(priv->clk_eee)) { dev_dbg(&priv->pdev->dev, "failed to get enet-eee clock\n"); err = PTR_ERR(priv->clk_eee); - goto err; + goto err_clk_disable; } /* If this is an internal GPHY, power it on now, before UniMAC is @@ -4129,8 +4118,9 @@ static int bcmgenet_resume(struct device *d) { struct net_device *dev = dev_get_drvdata(d); struct bcmgenet_priv *priv = netdev_priv(dev); + struct bcmgenet_rxnfc_rule *rule; unsigned long dma_ctrl; - u32 offset, reg; + u32 reg; int ret; if (!netif_running(dev)) @@ -4161,10 +4151,11 @@ static int bcmgenet_resume(struct device *d) bcmgenet_set_hw_addr(priv, dev->dev_addr); - offset = HFB_FLT_ENABLE_V3PLUS; - bcmgenet_hfb_reg_writel(priv, priv->hfb_en[1], offset); - bcmgenet_hfb_reg_writel(priv, priv->hfb_en[2], offset + sizeof(u32)); - bcmgenet_hfb_reg_writel(priv, priv->hfb_en[0], HFB_CTRL); + /* Restore hardware filters */ + bcmgenet_hfb_clear(priv); + list_for_each_entry(rule, &priv->rxnfc_list, list) + if (rule->state != BCMGENET_RXNFC_STATE_UNUSED) + bcmgenet_hfb_create_rxnfc_filter(priv, rule); if (priv->internal_phy) { reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); @@ -4208,7 +4199,6 @@ static int bcmgenet_suspend(struct device *d) { struct net_device *dev = dev_get_drvdata(d); struct bcmgenet_priv *priv = netdev_priv(dev); - u32 offset; if (!netif_running(dev)) return 0; @@ -4220,11 +4210,7 @@ static int bcmgenet_suspend(struct device *d) if (!device_may_wakeup(d)) phy_suspend(dev->phydev); - /* Preserve filter state and disable filtering */ - priv->hfb_en[0] = bcmgenet_hfb_reg_readl(priv, HFB_CTRL); - offset = HFB_FLT_ENABLE_V3PLUS; - priv->hfb_en[1] = bcmgenet_hfb_reg_readl(priv, offset); - priv->hfb_en[2] = bcmgenet_hfb_reg_readl(priv, offset + sizeof(u32)); + /* Disable filtering */ bcmgenet_hfb_reg_writel(priv, 0, HFB_CTRL); return 0; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index a12cb59298f4..f6ca01da141d 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -696,7 +696,6 @@ struct bcmgenet_priv { u32 wolopts; u8 sopass[SOPASS_MAX]; bool wol_active; - u32 hfb_en[3]; struct bcmgenet_mib_counters mib; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c index 4ea6a26b04f7..1c86eddb1b51 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c @@ -217,20 +217,28 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv, priv->wol_active = 0; clk_disable_unprepare(priv->clk_wol); + priv->crc_fwd_en = 0; /* Disable Magic Packet Detection */ - reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL); - reg &= ~(MPD_EN | MPD_PW_EN); - bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL); + if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) { + reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL); + if (!(reg & MPD_EN)) + return; /* already reset so skip the rest */ + reg &= ~(MPD_EN | MPD_PW_EN); + bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL); + } /* Disable WAKE_FILTER Detection */ - reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL); - reg &= ~(RBUF_HFB_EN | RBUF_ACPI_EN); - bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL); + if (priv->wolopts & WAKE_FILTER) { + reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL); + if (!(reg & RBUF_ACPI_EN)) + return; /* already reset so skip the rest */ + reg &= ~(RBUF_HFB_EN | RBUF_ACPI_EN); + bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL); + } /* Disable CRC Forward */ reg = bcmgenet_umac_readl(priv, UMAC_CMD); reg &= ~CMD_CRC_FWD; bcmgenet_umac_writel(priv, reg, UMAC_CMD); - priv->crc_fwd_en = 0; } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index f1f0976e7669..2213e6ab8151 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -3736,7 +3736,7 @@ static int macb_init(struct platform_device *pdev) if (!(bp->caps & MACB_CAPS_USRIO_DISABLED)) { val = 0; - if (bp->phy_interface == PHY_INTERFACE_MODE_RGMII) + if (phy_interface_mode_is_rgmii(bp->phy_interface)) val = GEM_BIT(RGMII); else if (bp->phy_interface == PHY_INTERFACE_MODE_RMII && (bp->caps & MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII)) diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 32a45dc51ed7..92eee66cbc84 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2938,6 +2938,7 @@ static inline int uld_send(struct adapter *adap, struct sk_buff *skb, txq_info = adap->sge.uld_txq_info[tx_uld_type]; if (unlikely(!txq_info)) { WARN_ON(true); + kfree_skb(skb); return NET_XMIT_DROP; } diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 8d13ea370db1..66e67b24a887 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2446,6 +2446,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) port->reset = devm_reset_control_get_exclusive(dev, NULL); if (IS_ERR(port->reset)) { dev_err(dev, "no reset\n"); + clk_disable_unprepare(port->pclk); return PTR_ERR(port->reset); } reset_control_reset(port->reset); @@ -2501,8 +2502,10 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) IRQF_SHARED, port_names[port->id], port); - if (ret) + if (ret) { + clk_disable_unprepare(port->pclk); return ret; + } ret = register_netdev(netdev); if (!ret) { diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 2972244e6eb0..43570f4911ea 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2938,7 +2938,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) DMA_BIT_MASK(40)); if (err) { netdev_err(net_dev, "dma_coerce_mask_and_coherent() failed\n"); - return err; + goto free_netdev; } /* If fsl_fm_max_frm is set to a higher value than the all-common 1500, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index f150cd454fa4..0998ceb1a26e 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -3632,7 +3632,7 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv) dpni_dev = to_fsl_mc_device(priv->net_dev->dev.parent); dpmac_dev = fsl_mc_get_endpoint(dpni_dev); - if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) + if (IS_ERR_OR_NULL(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) return 0; if (dpaa2_mac_is_type_fixed(dpmac_dev, priv->mc_io)) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 4fac57dbb3c8..7a9675bd36e8 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -906,6 +906,7 @@ static int enetc_pf_probe(struct pci_dev *pdev, return 0; err_reg_netdev: + enetc_mdio_remove(pf); enetc_of_put_phy(priv); enetc_free_msix(priv); err_alloc_msix: diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index d8d76da51c5e..832a2175636d 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -590,6 +590,7 @@ struct fec_enet_private { void fec_ptp_init(struct platform_device *pdev, int irq_idx); void fec_ptp_stop(struct platform_device *pdev); void fec_ptp_start_cyclecounter(struct net_device *ndev); +void fec_ptp_disable_hwts(struct net_device *ndev); int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr); int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 3982285ed020..cc7fbfc09354 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1294,8 +1294,13 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) ndev->stats.tx_bytes += skb->len; } - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) && - fep->bufdesc_ex) { + /* NOTE: SKBTX_IN_PROGRESS being set does not imply it's we who + * are to time stamp the packet, so we still need to check time + * stamping enabled flag. + */ + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS && + fep->hwts_tx_en) && + fep->bufdesc_ex) { struct skb_shared_hwtstamps shhwtstamps; struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp; @@ -2723,10 +2728,16 @@ static int fec_enet_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd) return -ENODEV; if (fep->bufdesc_ex) { - if (cmd == SIOCSHWTSTAMP) - return fec_ptp_set(ndev, rq); - if (cmd == SIOCGHWTSTAMP) - return fec_ptp_get(ndev, rq); + bool use_fec_hwts = !phy_has_hwtstamp(phydev); + + if (cmd == SIOCSHWTSTAMP) { + if (use_fec_hwts) + return fec_ptp_set(ndev, rq); + fec_ptp_disable_hwts(ndev); + } else if (cmd == SIOCGHWTSTAMP) { + if (use_fec_hwts) + return fec_ptp_get(ndev, rq); + } } return phy_mii_ioctl(phydev, rq, cmd); diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 945643c02615..f8a592c96beb 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -452,6 +452,18 @@ static int fec_ptp_enable(struct ptp_clock_info *ptp, return -EOPNOTSUPP; } +/** + * fec_ptp_disable_hwts - disable hardware time stamping + * @ndev: pointer to net_device + */ +void fec_ptp_disable_hwts(struct net_device *ndev) +{ + struct fec_enet_private *fep = netdev_priv(ndev); + + fep->hwts_tx_en = 0; + fep->hwts_rx_en = 0; +} + int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr) { struct fec_enet_private *fep = netdev_priv(ndev); diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index b3c69e9038ea..b513b8c5c3b5 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -779,8 +779,12 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) mac_addr = of_get_mac_address(np); - if (!IS_ERR(mac_addr)) + if (!IS_ERR(mac_addr)) { ether_addr_copy(dev->dev_addr, mac_addr); + } else { + eth_hw_addr_random(dev); + dev_info(&ofdev->dev, "Using random MAC address: %pM\n", dev->dev_addr); + } if (model && !strcasecmp(model, "TSEC")) priv->device_flags |= FSL_GIANFAR_DEV_HAS_GIGABIT | diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index d041cac9a487..088550db2de7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -77,6 +77,7 @@ ((ring)->p = ((ring)->p - 1 + (ring)->desc_num) % (ring)->desc_num) enum hns_desc_type { + DESC_TYPE_UNKNOWN, DESC_TYPE_SKB, DESC_TYPE_FRAGLIST_SKB, DESC_TYPE_PAGE, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index c38f3bbe7d97..71ed4c54f6d5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1093,16 +1093,8 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, int k, sizeoflast; dma_addr_t dma; - if (type == DESC_TYPE_SKB) { - struct sk_buff *skb = (struct sk_buff *)priv; - int ret; - - ret = hns3_fill_skb_desc(ring, skb, desc); - if (unlikely(ret < 0)) - return ret; - - dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); - } else if (type == DESC_TYPE_FRAGLIST_SKB) { + if (type == DESC_TYPE_FRAGLIST_SKB || + type == DESC_TYPE_SKB) { struct sk_buff *skb = (struct sk_buff *)priv; dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); @@ -1118,12 +1110,12 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, return -ENOMEM; } + desc_cb->priv = priv; desc_cb->length = size; + desc_cb->dma = dma; + desc_cb->type = type; if (likely(size <= HNS3_MAX_BD_SIZE)) { - desc_cb->priv = priv; - desc_cb->dma = dma; - desc_cb->type = type; desc->addr = cpu_to_le64(dma); desc->tx.send_size = cpu_to_le16(size); desc->tx.bdtp_fe_sc_vld_ra_ri = @@ -1135,18 +1127,11 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, } frag_buf_num = hns3_tx_bd_count(size); - sizeoflast = size & HNS3_TX_LAST_SIZE_M; + sizeoflast = size % HNS3_MAX_BD_SIZE; sizeoflast = sizeoflast ? sizeoflast : HNS3_MAX_BD_SIZE; /* When frag size is bigger than hardware limit, split this frag */ for (k = 0; k < frag_buf_num; k++) { - /* The txbd's baseinfo of DESC_TYPE_PAGE & DESC_TYPE_SKB */ - desc_cb->priv = priv; - desc_cb->dma = dma + HNS3_MAX_BD_SIZE * k; - desc_cb->type = ((type == DESC_TYPE_FRAGLIST_SKB || - type == DESC_TYPE_SKB) && !k) ? - type : DESC_TYPE_PAGE; - /* now, fill the descriptor */ desc->addr = cpu_to_le64(dma + HNS3_MAX_BD_SIZE * k); desc->tx.send_size = cpu_to_le16((k == frag_buf_num - 1) ? @@ -1158,7 +1143,6 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, /* move ring pointer to next */ ring_ptr_move_fw(ring, next_to_use); - desc_cb = &ring->desc_cb[ring->next_to_use]; desc = &ring->desc[ring->next_to_use]; } @@ -1346,6 +1330,10 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig) unsigned int i; for (i = 0; i < ring->desc_num; i++) { + struct hns3_desc *desc = &ring->desc[ring->next_to_use]; + + memset(desc, 0, sizeof(*desc)); + /* check if this is where we started */ if (ring->next_to_use == next_to_use_orig) break; @@ -1353,6 +1341,9 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig) /* rollback one */ ring_ptr_move_bw(ring, next_to_use); + if (!ring->desc_cb[ring->next_to_use].dma) + continue; + /* unmap the descriptor dma address */ if (ring->desc_cb[ring->next_to_use].type == DESC_TYPE_SKB || ring->desc_cb[ring->next_to_use].type == @@ -1369,6 +1360,7 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig) ring->desc_cb[ring->next_to_use].length = 0; ring->desc_cb[ring->next_to_use].dma = 0; + ring->desc_cb[ring->next_to_use].type = DESC_TYPE_UNKNOWN; } } @@ -1439,6 +1431,10 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) next_to_use_head = ring->next_to_use; + ret = hns3_fill_skb_desc(ring, skb, &ring->desc[ring->next_to_use]); + if (unlikely(ret < 0)) + goto fill_err; + ret = hns3_fill_skb_to_desc(ring, skb, DESC_TYPE_SKB); if (unlikely(ret < 0)) goto fill_err; @@ -4140,8 +4136,8 @@ static void hns3_link_status_change(struct hnae3_handle *handle, bool linkup) return; if (linkup) { - netif_carrier_on(netdev); netif_tx_wake_all_queues(netdev); + netif_carrier_on(netdev); if (netif_msg_link(handle)) netdev_info(netdev, "link up\n"); } else { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 66cd4395f781..a8776620acbc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -165,8 +165,6 @@ enum hns3_nic_state { #define HNS3_TXD_MSS_S 0 #define HNS3_TXD_MSS_M (0x3fff << HNS3_TXD_MSS_S) -#define HNS3_TX_LAST_SIZE_M 0xffff - #define HNS3_VECTOR_TX_IRQ BIT_ULL(0) #define HNS3_VECTOR_RX_IRQ BIT_ULL(1) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index d6bfdc6520df..36575e72a915 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2673,11 +2673,10 @@ void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time) delay_time); } -static int hclge_get_mac_link_status(struct hclge_dev *hdev) +static int hclge_get_mac_link_status(struct hclge_dev *hdev, int *link_status) { struct hclge_link_status_cmd *req; struct hclge_desc desc; - int link_status; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_LINK_STATUS, true); @@ -2689,33 +2688,25 @@ static int hclge_get_mac_link_status(struct hclge_dev *hdev) } req = (struct hclge_link_status_cmd *)desc.data; - link_status = req->status & HCLGE_LINK_STATUS_UP_M; + *link_status = (req->status & HCLGE_LINK_STATUS_UP_M) > 0 ? + HCLGE_LINK_STATUS_UP : HCLGE_LINK_STATUS_DOWN; - return !!link_status; + return 0; } -static int hclge_get_mac_phy_link(struct hclge_dev *hdev) +static int hclge_get_mac_phy_link(struct hclge_dev *hdev, int *link_status) { - unsigned int mac_state; - int link_stat; + struct phy_device *phydev = hdev->hw.mac.phydev; + + *link_status = HCLGE_LINK_STATUS_DOWN; if (test_bit(HCLGE_STATE_DOWN, &hdev->state)) return 0; - mac_state = hclge_get_mac_link_status(hdev); - - if (hdev->hw.mac.phydev) { - if (hdev->hw.mac.phydev->state == PHY_RUNNING) - link_stat = mac_state & - hdev->hw.mac.phydev->link; - else - link_stat = 0; - - } else { - link_stat = mac_state; - } + if (phydev && (phydev->state != PHY_RUNNING || !phydev->link)) + return 0; - return !!link_stat; + return hclge_get_mac_link_status(hdev, link_status); } static void hclge_update_link_status(struct hclge_dev *hdev) @@ -2725,6 +2716,7 @@ static void hclge_update_link_status(struct hclge_dev *hdev) struct hnae3_handle *rhandle; struct hnae3_handle *handle; int state; + int ret; int i; if (!client) @@ -2733,7 +2725,12 @@ static void hclge_update_link_status(struct hclge_dev *hdev) if (test_and_set_bit(HCLGE_STATE_LINK_UPDATING, &hdev->state)) return; - state = hclge_get_mac_phy_link(hdev); + ret = hclge_get_mac_phy_link(hdev, &state); + if (ret) { + clear_bit(HCLGE_STATE_LINK_UPDATING, &hdev->state); + return; + } + if (state != hdev->hw.mac.link) { for (i = 0; i < hdev->num_vmdq_vport + 1; i++) { handle = &hdev->vport[i].nic; @@ -5809,9 +5806,9 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle, /* to avoid rule conflict, when user configure rule by ethtool, * we need to clear all arfs rules */ + spin_lock_bh(&hdev->fd_rule_lock); hclge_clear_arfs_rules(handle); - spin_lock_bh(&hdev->fd_rule_lock); ret = hclge_fd_config_rule(hdev, rule); spin_unlock_bh(&hdev->fd_rule_lock); @@ -5854,6 +5851,7 @@ static int hclge_del_fd_entry(struct hnae3_handle *handle, return ret; } +/* make sure being called after lock up with fd_rule_lock */ static void hclge_del_all_fd_entries(struct hnae3_handle *handle, bool clear_list) { @@ -5866,7 +5864,6 @@ static void hclge_del_all_fd_entries(struct hnae3_handle *handle, if (!hnae3_dev_fd_supported(hdev)) return; - spin_lock_bh(&hdev->fd_rule_lock); for_each_set_bit(location, hdev->fd_bmap, hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]) hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true, location, @@ -5883,8 +5880,6 @@ static void hclge_del_all_fd_entries(struct hnae3_handle *handle, bitmap_zero(hdev->fd_bmap, hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]); } - - spin_unlock_bh(&hdev->fd_rule_lock); } static int hclge_restore_fd_entries(struct hnae3_handle *handle) @@ -6266,7 +6261,7 @@ static int hclge_add_fd_entry_by_arfs(struct hnae3_handle *handle, u16 queue_id, u16 flow_id, struct flow_keys *fkeys) { struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_fd_rule_tuples new_tuples; + struct hclge_fd_rule_tuples new_tuples = {}; struct hclge_dev *hdev = vport->back; struct hclge_fd_rule *rule; u16 tmp_queue_id; @@ -6276,19 +6271,17 @@ static int hclge_add_fd_entry_by_arfs(struct hnae3_handle *handle, u16 queue_id, if (!hnae3_dev_fd_supported(hdev)) return -EOPNOTSUPP; - memset(&new_tuples, 0, sizeof(new_tuples)); - hclge_fd_get_flow_tuples(fkeys, &new_tuples); - - spin_lock_bh(&hdev->fd_rule_lock); - /* when there is already fd rule existed add by user, * arfs should not work */ + spin_lock_bh(&hdev->fd_rule_lock); if (hdev->fd_active_type == HCLGE_FD_EP_ACTIVE) { spin_unlock_bh(&hdev->fd_rule_lock); return -EOPNOTSUPP; } + hclge_fd_get_flow_tuples(fkeys, &new_tuples); + /* check is there flow director filter existed for this flow, * if not, create a new filter for it; * if filter exist with different queue id, modify the filter; @@ -6371,6 +6364,7 @@ static void hclge_rfs_filter_expire(struct hclge_dev *hdev) #endif } +/* make sure being called after lock up with fd_rule_lock */ static void hclge_clear_arfs_rules(struct hnae3_handle *handle) { #ifdef CONFIG_RFS_ACCEL @@ -6423,10 +6417,14 @@ static void hclge_enable_fd(struct hnae3_handle *handle, bool enable) hdev->fd_en = enable; clear = hdev->fd_active_type == HCLGE_FD_ARFS_ACTIVE; - if (!enable) + + if (!enable) { + spin_lock_bh(&hdev->fd_rule_lock); hclge_del_all_fd_entries(handle, clear); - else + spin_unlock_bh(&hdev->fd_rule_lock); + } else { hclge_restore_fd_entries(handle); + } } static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) @@ -6524,14 +6522,15 @@ static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret) { #define HCLGE_MAC_LINK_STATUS_NUM 100 + int link_status; int i = 0; int ret; do { - ret = hclge_get_mac_link_status(hdev); - if (ret < 0) + ret = hclge_get_mac_link_status(hdev, &link_status); + if (ret) return ret; - else if (ret == link_ret) + if (link_status == link_ret) return 0; msleep(HCLGE_LINK_STATUS_MS); @@ -6542,9 +6541,6 @@ static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret) static int hclge_mac_phy_link_status_wait(struct hclge_dev *hdev, bool en, bool is_phy) { -#define HCLGE_LINK_STATUS_DOWN 0 -#define HCLGE_LINK_STATUS_UP 1 - int link_ret; link_ret = en ? HCLGE_LINK_STATUS_UP : HCLGE_LINK_STATUS_DOWN; @@ -6891,8 +6887,9 @@ static void hclge_ae_stop(struct hnae3_handle *handle) int i; set_bit(HCLGE_STATE_DOWN, &hdev->state); - + spin_lock_bh(&hdev->fd_rule_lock); hclge_clear_arfs_rules(handle); + spin_unlock_bh(&hdev->fd_rule_lock); /* If it is not PF reset, the firmware will disable the MAC, * so it only need to stop phy here. @@ -9045,11 +9042,12 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, bool writen_to_tbl = false; int ret = 0; - /* When device is resetting, firmware is unable to handle - * mailbox. Just record the vlan id, and remove it after + /* When device is resetting or reset failed, firmware is unable to + * handle mailbox. Just record the vlan id, and remove it after * reset finished. */ - if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) && is_kill) { + if ((test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) || + test_bit(HCLGE_STATE_RST_FAIL, &hdev->state)) && is_kill) { set_bit(vlan_id, vport->vlan_del_fail_bmap); return -EBUSY; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 46e6e0fef3ba..9bbdd4557c27 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -317,6 +317,9 @@ enum hclge_link_fail_code { HCLGE_LF_XSFP_ABSENT, }; +#define HCLGE_LINK_STATUS_DOWN 0 +#define HCLGE_LINK_STATUS_UP 1 + #define HCLGE_PG_NUM 4 #define HCLGE_SCH_MODE_SP 0 #define HCLGE_SCH_MODE_DWRR 1 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index a10b022d1951..9162856de1b1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1592,11 +1592,12 @@ static int hclgevf_set_vlan_filter(struct hnae3_handle *handle, if (proto != htons(ETH_P_8021Q)) return -EPROTONOSUPPORT; - /* When device is resetting, firmware is unable to handle - * mailbox. Just record the vlan id, and remove it after + /* When device is resetting or reset failed, firmware is unable to + * handle mailbox. Just record the vlan id, and remove it after * reset finished. */ - if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state) && is_kill) { + if ((test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state) || + test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state)) && is_kill) { set_bit(vlan_id, hdev->vlan_del_fail_bmap); return -EBUSY; } @@ -3439,23 +3440,36 @@ void hclgevf_update_port_base_vlan_info(struct hclgevf_dev *hdev, u16 state, { struct hnae3_handle *nic = &hdev->nic; struct hclge_vf_to_pf_msg send_msg; + int ret; rtnl_lock(); - hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT); - rtnl_unlock(); + + if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state) || + test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state)) { + dev_warn(&hdev->pdev->dev, + "is resetting when updating port based vlan info\n"); + rtnl_unlock(); + return; + } + + ret = hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT); + if (ret) { + rtnl_unlock(); + return; + } /* send msg to PF and wait update port based vlan info */ hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN, HCLGE_MBX_PORT_BASE_VLAN_CFG); memcpy(send_msg.data, port_base_vlan_info, data_size); - hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0); - - if (state == HNAE3_PORT_BASE_VLAN_DISABLE) - nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_DISABLE; - else - nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_ENABLE; + ret = hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0); + if (!ret) { + if (state == HNAE3_PORT_BASE_VLAN_DISABLE) + nic->port_base_vlan_state = state; + else + nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_ENABLE; + } - rtnl_lock(); hclgevf_notify_client(hdev, HNAE3_UP_CLIENT); rtnl_unlock(); } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 0fd7eae25fe9..5afb3c9c52d2 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3206,7 +3206,7 @@ req_rx_irq_failed: req_tx_irq_failed: for (j = 0; j < i; j++) { free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]); - irq_dispose_mapping(adapter->rx_scrq[j]->irq); + irq_dispose_mapping(adapter->tx_scrq[j]->irq); } release_sub_crqs(adapter, 1); return rc; diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index f999cca37a8a..489bb5b59475 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -301,10 +301,8 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) */ hw->dev_spec.ich8lan.ulp_state = e1000_ulp_state_unknown; ret_val = e1000_disable_ulp_lpt_lp(hw, true); - if (ret_val) { + if (ret_val) e_warn("Failed to disable ULP\n"); - goto out; - } ret_val = hw->phy.ops.acquire(hw); if (ret_val) { diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 8bb3db2cbd41..6e5861bfb0fa 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6224,9 +6224,18 @@ static void igb_reset_task(struct work_struct *work) struct igb_adapter *adapter; adapter = container_of(work, struct igb_adapter, reset_task); + rtnl_lock(); + /* If we're already down or resetting, just bail */ + if (test_bit(__IGB_DOWN, &adapter->state) || + test_bit(__IGB_RESETTING, &adapter->state)) { + rtnl_unlock(); + return; + } + igb_dump(adapter); netdev_err(adapter->netdev, "Reset adapter\n"); igb_reinit_locked(adapter); + rtnl_unlock(); } /** diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 64786568af0d..75a8c407e815 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1730,10 +1730,12 @@ static void otx2_reset_task(struct work_struct *work) if (!netif_running(pf->netdev)) return; + rtnl_lock(); otx2_stop(pf->netdev); pf->reset_count++; otx2_open(pf->netdev); netif_trans_update(pf->netdev); + rtnl_unlock(); } static const struct net_device_ops otx2_netdev_ops = { @@ -2111,6 +2113,7 @@ static void otx2_remove(struct pci_dev *pdev) pf = netdev_priv(netdev); + cancel_work_sync(&pf->reset_task); /* Disable link notifications */ otx2_cgx_config_linkevents(pf, false); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index f4227517dc8e..92a3db69a6cd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -617,6 +617,8 @@ static void otx2vf_remove(struct pci_dev *pdev) vf = netdev_priv(netdev); + cancel_work_sync(&vf->reset_task); + unregister_netdev(netdev); otx2vf_disable_mbox_intr(vf); otx2_detach_resources(&vf->mbox); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index f6a1f8666f95..a1c45b39a230 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -171,11 +171,21 @@ static int mt7621_gmac0_rgmii_adjust(struct mtk_eth *eth, return 0; } -static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth, int speed) +static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth, + phy_interface_t interface, int speed) { u32 val; int ret; + if (interface == PHY_INTERFACE_MODE_TRGMII) { + mtk_w32(eth, TRGMII_MODE, INTF_MODE); + val = 500000000; + ret = clk_set_rate(eth->clks[MTK_CLK_TRGPLL], val); + if (ret) + dev_err(eth->dev, "Failed to set trgmii pll: %d\n", ret); + return; + } + val = (speed == SPEED_1000) ? INTF_MODE_RGMII_1000 : INTF_MODE_RGMII_10_100; mtk_w32(eth, val, INTF_MODE); @@ -262,10 +272,9 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode, state->interface)) goto err_phy; } else { - if (state->interface != - PHY_INTERFACE_MODE_TRGMII) - mtk_gmac0_rgmii_adjust(mac->hw, - state->speed); + mtk_gmac0_rgmii_adjust(mac->hw, + state->interface, + state->speed); /* mt7623_pad_clk_setup */ for (i = 0 ; i < NUM_TRGMII_CTRL; i++) @@ -2882,6 +2891,8 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) eth->netdev[id]->irq = eth->irq[0]; eth->netdev[id]->dev.of_node = np; + eth->netdev[id]->max_mtu = MTK_MAX_RX_LENGTH - MTK_RX_ETH_HLEN; + return 0; free_netdev: diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 3d9aa7da95e9..2d3e45780719 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4356,12 +4356,14 @@ end: static void mlx4_shutdown(struct pci_dev *pdev) { struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev); + struct mlx4_dev *dev = persist->dev; mlx4_info(persist->dev, "mlx4_shutdown was called\n"); mutex_lock(&persist->interface_state_mutex); if (persist->interface_state & MLX4_INTERFACE_STATE_UP) mlx4_unload_one(pdev); mutex_unlock(&persist->interface_state_mutex); + mlx4_pci_disable_device(dev); } static const struct pci_error_handlers mlx4_err_handler = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c index bdb71332cbf2..3e44e4d820c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c @@ -183,13 +183,16 @@ void mlx5e_rep_bond_unslave(struct mlx5_eswitch *esw, static bool mlx5e_rep_is_lag_netdev(struct net_device *netdev) { - struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5e_rep_priv *rpriv; + struct mlx5e_priv *priv; /* A given netdev is not a representor or not a slave of LAG configuration */ if (!mlx5e_eswitch_rep(netdev) || !bond_slave_get_rtnl(netdev)) return false; + priv = netdev_priv(netdev); + rpriv = priv->ppriv; + /* Egress acl forward to vport is supported only non-uplink representor */ return rpriv->rep->vport != MLX5_VPORT_UPLINK; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index eefeb1cdc2ee..245a99f69641 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -551,19 +551,31 @@ static bool mlx5e_restore_tunnel(struct mlx5e_priv *priv, struct sk_buff *skb, } } - tun_dst = tun_rx_dst(enc_opts.key.len); + if (key.enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + tun_dst = __ip_tun_set_dst(key.enc_ipv4.src, key.enc_ipv4.dst, + key.enc_ip.tos, key.enc_ip.ttl, + key.enc_tp.dst, TUNNEL_KEY, + key32_to_tunnel_id(key.enc_key_id.keyid), + enc_opts.key.len); + } else if (key.enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + tun_dst = __ipv6_tun_set_dst(&key.enc_ipv6.src, &key.enc_ipv6.dst, + key.enc_ip.tos, key.enc_ip.ttl, + key.enc_tp.dst, 0, TUNNEL_KEY, + key32_to_tunnel_id(key.enc_key_id.keyid), + enc_opts.key.len); + } else { + netdev_dbg(priv->netdev, + "Couldn't restore tunnel, unsupported addr_type: %d\n", + key.enc_control.addr_type); + return false; + } + if (!tun_dst) { - WARN_ON_ONCE(true); + netdev_dbg(priv->netdev, "Couldn't restore tunnel, no tun_dst\n"); return false; } - ip_tunnel_key_init(&tun_dst->u.tun_info.key, - key.enc_ipv4.src, key.enc_ipv4.dst, - key.enc_ip.tos, key.enc_ip.ttl, - 0, /* label */ - key.enc_tp.src, key.enc_tp.dst, - key32_to_tunnel_id(key.enc_key_id.keyid), - TUNNEL_KEY); + tun_dst->u.tun_info.key.tp_src = key.enc_tp.src; if (enc_opts.key.len) ip_tunnel_info_opts_set(&tun_dst->u.tun_info, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c index 951ea26d96bc..e472ed0eacfb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c @@ -301,6 +301,8 @@ static int mlx5e_tc_tun_parse_geneve_params(struct mlx5e_priv *priv, MLX5_SET(fte_match_set_misc, misc_v, geneve_protocol_type, ETH_P_TEB); } + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c index 58b13192df23..2805416c32a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c @@ -80,6 +80,8 @@ static int mlx5e_tc_tun_parse_gretap(struct mlx5e_priv *priv, gre_key.key, be32_to_cpu(enc_keyid.key->keyid)); } + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c index 37b176801bcc..038a0f1cecec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c @@ -136,6 +136,8 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv, MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni, be32_to_cpu(enc_keyid.key->keyid)); + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 081f15074cac..3b892ec301b4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -419,7 +419,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq, &rq->wq_ctrl); if (err) - return err; + goto err_rq_wq_destroy; rq->mpwqe.wq.db = &rq->mpwqe.wq.db[MLX5_RCV_DBR]; @@ -470,7 +470,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq, &rq->wq_ctrl); if (err) - return err; + goto err_rq_wq_destroy; rq->wqe.wq.db = &rq->wqe.wq.db[MLX5_RCV_DBR]; @@ -3069,6 +3069,25 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv) priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE; } +static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev, + enum mlx5_port_status state) +{ + struct mlx5_eswitch *esw = mdev->priv.eswitch; + int vport_admin_state; + + mlx5_set_port_admin_status(mdev, state); + + if (!MLX5_ESWITCH_MANAGER(mdev) || mlx5_eswitch_mode(esw) == MLX5_ESWITCH_OFFLOADS) + return; + + if (state == MLX5_PORT_UP) + vport_admin_state = MLX5_VPORT_ADMIN_STATE_AUTO; + else + vport_admin_state = MLX5_VPORT_ADMIN_STATE_DOWN; + + mlx5_eswitch_set_vport_state(esw, MLX5_VPORT_UPLINK, vport_admin_state); +} + int mlx5e_open_locked(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -3101,7 +3120,7 @@ int mlx5e_open(struct net_device *netdev) mutex_lock(&priv->state_lock); err = mlx5e_open_locked(netdev); if (!err) - mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP); + mlx5e_modify_admin_state(priv->mdev, MLX5_PORT_UP); mutex_unlock(&priv->state_lock); return err; @@ -3135,7 +3154,7 @@ int mlx5e_close(struct net_device *netdev) return -ENODEV; mutex_lock(&priv->state_lock); - mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_DOWN); + mlx5e_modify_admin_state(priv->mdev, MLX5_PORT_DOWN); err = mlx5e_close_locked(netdev); mutex_unlock(&priv->state_lock); @@ -5182,7 +5201,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) /* Marking the link as currently not needed by the Driver */ if (!netif_running(netdev)) - mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN); + mlx5e_modify_admin_state(mdev, MLX5_PORT_DOWN); mlx5e_set_netdev_mtu_boundaries(priv); mlx5e_set_dev_port_mtu(priv); @@ -5390,6 +5409,8 @@ err_cleanup_tx: profile->cleanup_tx(priv); out: + set_bit(MLX5E_STATE_DESTROYING, &priv->state); + cancel_work_sync(&priv->update_stats_work); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 006807e04eda..9519a61bd8ec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -936,6 +936,7 @@ err_close_drop_rq: static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) { + mlx5e_ethtool_cleanup_steering(priv); rep_vport_rx_rule_destroy(priv); mlx5e_destroy_rep_root_ft(priv); mlx5e_destroy_ttc_table(priv, &priv->fs.ttc); @@ -1080,6 +1081,8 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) mlx5e_rep_tc_enable(priv); + mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK, + 0, 0, MLX5_VPORT_ADMIN_STATE_AUTO); mlx5_lag_add(mdev, netdev); priv->events_nb.notifier_call = uplink_rep_async_event; mlx5_notifier_register(mdev, &priv->events_nb); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index cc8412151ca0..fcedb5bdca9e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2356,6 +2356,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, match.key->vlan_priority); *match_level = MLX5_MATCH_L2; + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 1116ab9bea6c..43005caff09e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1608,7 +1608,7 @@ abort: mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); } - + esw_destroy_tsar(esw); return err; } @@ -1653,8 +1653,6 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf) else if (esw->mode == MLX5_ESWITCH_OFFLOADS) esw_offloads_disable(esw); - esw_destroy_tsar(esw); - old_mode = esw->mode; esw->mode = MLX5_ESWITCH_NONE; @@ -1664,6 +1662,8 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf) mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); } + esw_destroy_tsar(esw); + if (clear_vf) mlx5_eswitch_clear_vf_vports_info(esw); } @@ -1826,6 +1826,8 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport); + int opmod = MLX5_VPORT_STATE_OP_MOD_ESW_VPORT; + int other_vport = 1; int err = 0; if (!ESW_ALLOWED(esw)) @@ -1833,15 +1835,17 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, if (IS_ERR(evport)) return PTR_ERR(evport); + if (vport == MLX5_VPORT_UPLINK) { + opmod = MLX5_VPORT_STATE_OP_MOD_UPLINK; + other_vport = 0; + vport = 0; + } mutex_lock(&esw->state_lock); - err = mlx5_modify_vport_admin_state(esw->dev, - MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - vport, 1, link_state); + err = mlx5_modify_vport_admin_state(esw->dev, opmod, vport, other_vport, link_state); if (err) { - mlx5_core_warn(esw->dev, - "Failed to set vport %d link state, err = %d", - vport, err); + mlx5_core_warn(esw->dev, "Failed to set vport %d link state, opmod = %d, err = %d", + vport, opmod, err); goto unlock; } @@ -1883,8 +1887,6 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport); int err = 0; - if (!ESW_ALLOWED(esw)) - return -EPERM; if (IS_ERR(evport)) return PTR_ERR(evport); if (vlan > 4095 || qos > 7) @@ -1912,6 +1914,9 @@ int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, u8 set_flags = 0; int err; + if (!ESW_ALLOWED(esw)) + return -EPERM; + if (vlan || qos) set_flags = SET_VLAN_STRIP | SET_VLAN_INSERT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index a5175e98c0b3..5785596f13f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -680,6 +680,8 @@ static inline int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) { r static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf) {} static inline bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1) { return true; } static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; } +static inline +int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { return 0; } static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev) { return ERR_PTR(-EOPNOTSUPP); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 060354bb211a..ed75353c56b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -236,6 +236,15 @@ static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw, return &esw->offloads.vport_reps[idx]; } +static void +mlx5_eswitch_set_rule_flow_source(struct mlx5_eswitch *esw, + struct mlx5_flow_spec *spec, + struct mlx5_esw_flow_attr *attr) +{ + if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source) && + attr && attr->in_rep && attr->in_rep->vport == MLX5_VPORT_UPLINK) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; +} static void mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, @@ -259,9 +268,6 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, mlx5_eswitch_get_vport_metadata_mask()); spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2; - misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); - if (memchr_inv(misc, 0, MLX5_ST_SZ_BYTES(fte_match_set_misc))) - spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; } else { misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport); @@ -279,10 +285,6 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; } - - if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source) && - attr->in_rep->vport == MLX5_VPORT_UPLINK) - spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; } struct mlx5_flow_handle * @@ -396,6 +398,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, goto err_esw_get; } + mlx5_eswitch_set_rule_flow_source(esw, spec, attr); + if (mlx5_eswitch_termtbl_required(esw, attr, &flow_act, spec)) rule = mlx5_eswitch_add_termtbl_rule(esw, fdb, spec, attr, &flow_act, dest, i); @@ -462,6 +466,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, i++; mlx5_eswitch_set_rule_source_port(esw, spec, attr); + mlx5_eswitch_set_rule_flow_source(esw, spec, attr); if (attr->outer_match_level != MLX5_MATCH_NONE) spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 13e2fb79c21a..2569bb6228b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -797,7 +797,7 @@ static struct mlx5_flow_table *find_closest_ft_recursive(struct fs_node *root, return ft; } -/* If reverse if false then return the first flow table in next priority of +/* If reverse is false then return the first flow table in next priority of * prio in the tree, else return the last flow table in the previous priority * of prio in the tree. */ @@ -829,34 +829,16 @@ static struct mlx5_flow_table *find_prev_chained_ft(struct fs_prio *prio) return find_closest_ft(prio, true); } -static struct fs_prio *find_fwd_ns_prio(struct mlx5_flow_root_namespace *root, - struct mlx5_flow_namespace *ns) -{ - struct mlx5_flow_namespace *root_ns = &root->ns; - struct fs_prio *iter_prio; - struct fs_prio *prio; - - fs_get_obj(prio, ns->node.parent); - list_for_each_entry(iter_prio, &root_ns->node.children, node.list) { - if (iter_prio == prio && - !list_is_last(&prio->node.children, &iter_prio->node.list)) - return list_next_entry(iter_prio, node.list); - } - return NULL; -} - static struct mlx5_flow_table *find_next_fwd_ft(struct mlx5_flow_table *ft, struct mlx5_flow_act *flow_act) { - struct mlx5_flow_root_namespace *root = find_root(&ft->node); struct fs_prio *prio; + bool next_ns; - if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS) - prio = find_fwd_ns_prio(root, ft->ns); - else - fs_get_obj(prio, ft->node.parent); + next_ns = flow_act->action & MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_NS; + fs_get_obj(prio, next_ns ? ft->ns->node.parent : ft->node.parent); - return (prio) ? find_next_chained_ft(prio) : NULL; + return find_next_chained_ft(prio); } static int connect_fts_in_prio(struct mlx5_core_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index ef0706d15a5b..2d55b7c22c03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -273,17 +273,17 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp, if (rq->extts.index >= clock->ptp_info.n_pins) return -EINVAL; + pin = ptp_find_pin(clock->ptp, PTP_PF_EXTTS, rq->extts.index); + if (pin < 0) + return -EBUSY; + 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; } @@ -331,12 +331,12 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, 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 = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, + rq->perout.index); + if (pin < 0) + return -EBUSY; + if (on) { pin_mode = MLX5_PIN_MODE_OUT; pattern = MLX5_OUT_PATTERN_PERIODIC; ts.tv_sec = rq->perout.period.sec; @@ -362,7 +362,6 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, MLX5_MTPPS_FS_ENABLE | MLX5_MTPPS_FS_TIME_STAMP; } else { - pin = rq->perout.index; field_select = MLX5_MTPPS_FS_ENABLE; } @@ -409,10 +408,31 @@ static int mlx5_ptp_enable(struct ptp_clock_info *ptp, return 0; } +enum { + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_IN = BIT(0), + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_OUT = BIT(1), +}; + 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; + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); + + switch (func) { + case PTP_PF_NONE: + return 0; + case PTP_PF_EXTTS: + return !(clock->pps_info.pin_caps[pin] & + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_IN); + case PTP_PF_PEROUT: + return !(clock->pps_info.pin_caps[pin] & + MLX5_MTPPS_REG_CAP_PIN_X_MODE_SUPPORT_PPS_OUT); + default: + return -EOPNOTSUPP; + } + + return -EOPNOTSUPP; } static const struct ptp_clock_info mlx5_ptp_clock_info = { @@ -432,6 +452,38 @@ static const struct ptp_clock_info mlx5_ptp_clock_info = { .verify = NULL, }; +static int mlx5_query_mtpps_pin_mode(struct mlx5_core_dev *mdev, u8 pin, + u32 *mtpps, u32 mtpps_size) +{ + u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {}; + + MLX5_SET(mtpps_reg, in, pin, pin); + + return mlx5_core_access_reg(mdev, in, sizeof(in), mtpps, + mtpps_size, MLX5_REG_MTPPS, 0, 0); +} + +static int mlx5_get_pps_pin_mode(struct mlx5_clock *clock, u8 pin) +{ + struct mlx5_core_dev *mdev = clock->mdev; + u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {}; + u8 mode; + int err; + + err = mlx5_query_mtpps_pin_mode(mdev, pin, out, sizeof(out)); + if (err || !MLX5_GET(mtpps_reg, out, enable)) + return PTP_PF_NONE; + + mode = MLX5_GET(mtpps_reg, out, pin_mode); + + if (mode == MLX5_PIN_MODE_IN) + return PTP_PF_EXTTS; + else if (mode == MLX5_PIN_MODE_OUT) + return PTP_PF_PEROUT; + + return PTP_PF_NONE; +} + static int mlx5_init_pin_config(struct mlx5_clock *clock) { int i; @@ -451,8 +503,8 @@ static int mlx5_init_pin_config(struct mlx5_clock *clock) 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; + clock->ptp_info.pin_config[i].func = mlx5_get_pps_pin_mode(clock, i); + clock->ptp_info.pin_config[i].chan = 0; } return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index e9ccd333f61d..71b6185b4904 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -710,7 +710,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core) err = mlxsw_core_trap_register(mlxsw_core, &mlxsw_emad_rx_listener, mlxsw_core); if (err) - return err; + goto err_trap_register; err = mlxsw_core->driver->basic_trap_groups_set(mlxsw_core); if (err) @@ -722,6 +722,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core) err_emad_trap_set: mlxsw_core_trap_unregister(mlxsw_core, &mlxsw_emad_rx_listener, mlxsw_core); +err_trap_register: destroy_workqueue(mlxsw_core->emad_wq); return err; } @@ -1813,7 +1814,7 @@ static int mlxsw_core_reg_access_emad(struct mlxsw_core *mlxsw_core, err = mlxsw_emad_reg_access(mlxsw_core, reg, payload, type, trans, bulk_list, cb, cb_priv, tid); if (err) { - kfree(trans); + kfree_rcu(trans, rcu); return err; } return 0; @@ -2050,11 +2051,13 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, break; } } - rcu_read_unlock(); - if (!found) + if (!found) { + rcu_read_unlock(); goto drop; + } rxl->func(skb, local_port, rxl_item->priv); + rcu_read_unlock(); return; drop: diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c index 08215fed193d..a7d86df7123f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c @@ -45,7 +45,7 @@ static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id, static int mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module, u16 offset, u16 size, void *data, - unsigned int *p_read_size) + bool qsfp, unsigned int *p_read_size) { char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE]; char mcia_pl[MLXSW_REG_MCIA_LEN]; @@ -54,6 +54,10 @@ mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module, int status; int err; + /* MCIA register accepts buffer size <= 48. Page of size 128 should be + * read by chunks of size 48, 48, 32. Align the size of the last chunk + * to avoid reading after the end of the page. + */ size = min_t(u16, size, MLXSW_REG_MCIA_EEPROM_SIZE); if (offset < MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH && @@ -63,18 +67,25 @@ mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module, i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_LOW; if (offset >= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH) { - page = MLXSW_REG_MCIA_PAGE_GET(offset); - offset -= MLXSW_REG_MCIA_EEPROM_UP_PAGE_LENGTH * page; - /* When reading upper pages 1, 2 and 3 the offset starts at - * 128. Please refer to "QSFP+ Memory Map" figure in SFF-8436 - * specification for graphical depiction. - * MCIA register accepts buffer size <= 48. Page of size 128 - * should be read by chunks of size 48, 48, 32. Align the size - * of the last chunk to avoid reading after the end of the - * page. - */ - if (offset + size > MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH) - size = MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH - offset; + if (qsfp) { + /* When reading upper pages 1, 2 and 3 the offset + * starts at 128. Please refer to "QSFP+ Memory Map" + * figure in SFF-8436 specification for graphical + * depiction. + */ + page = MLXSW_REG_MCIA_PAGE_GET(offset); + offset -= MLXSW_REG_MCIA_EEPROM_UP_PAGE_LENGTH * page; + if (offset + size > MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH) + size = MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH - offset; + } else { + /* When reading upper pages 1, 2 and 3 the offset + * starts at 0 and I2C high address is used. Please refer + * refer to "Memory Organization" figure in SFF-8472 + * specification for graphical depiction. + */ + i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_HIGH; + offset -= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH; + } } mlxsw_reg_mcia_pack(mcia_pl, module, 0, page, offset, size, i2c_addr); @@ -166,7 +177,7 @@ int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module, int err; err = mlxsw_env_query_module_eeprom(mlxsw_core, module, 0, offset, - module_info, &read_size); + module_info, false, &read_size); if (err) return err; @@ -197,7 +208,7 @@ int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module, /* Verify if transceiver provides diagnostic monitoring page */ err = mlxsw_env_query_module_eeprom(mlxsw_core, module, SFP_DIAGMON, 1, &diag_mon, - &read_size); + false, &read_size); if (err) return err; @@ -225,17 +236,22 @@ int mlxsw_env_get_module_eeprom(struct net_device *netdev, int offset = ee->offset; unsigned int read_size; int i = 0; + bool qsfp; int err; if (!ee->len) return -EINVAL; memset(data, 0, ee->len); + /* Validate module identifier value. */ + err = mlxsw_env_validate_cable_ident(mlxsw_core, module, &qsfp); + if (err) + return err; while (i < ee->len) { err = mlxsw_env_query_module_eeprom(mlxsw_core, module, offset, ee->len - i, data + i, - &read_size); + qsfp, &read_size); if (err) { netdev_err(netdev, "Eeprom query failed\n"); return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index fcb88d4271bf..8ac987c8c8bc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -5536,6 +5536,7 @@ enum mlxsw_reg_htgt_trap_group { MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST, MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY, MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP, + MLXSW_REG_HTGT_TRAP_GROUP_SP_EXTERNAL_ROUTE, MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME, MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP, MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 019ed503aadf..0521e9d48c45 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -5001,15 +5001,6 @@ static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, static bool mlxsw_sp_fib6_rt_should_ignore(const struct fib6_info *rt) { - /* Packets with link-local destination IP arriving to the router - * are trapped to the CPU, so no need to program specific routes - * for them. Only allow prefix routes (usually one fe80::/64) so - * that packets are trapped for the right reason. - */ - if ((ipv6_addr_type(&rt->fib6_dst.addr) & IPV6_ADDR_LINKLOCAL) && - (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST))) - return true; - /* Multicast routes aren't supported, so ignore them. Neighbour * Discovery packets are specifically trapped. */ @@ -8078,16 +8069,6 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, mlxsw_sp->router = router; router->mlxsw_sp = mlxsw_sp; - router->inetaddr_nb.notifier_call = mlxsw_sp_inetaddr_event; - err = register_inetaddr_notifier(&router->inetaddr_nb); - if (err) - goto err_register_inetaddr_notifier; - - router->inet6addr_nb.notifier_call = mlxsw_sp_inet6addr_event; - err = register_inet6addr_notifier(&router->inet6addr_nb); - if (err) - goto err_register_inet6addr_notifier; - INIT_LIST_HEAD(&mlxsw_sp->router->nexthop_neighs_list); err = __mlxsw_sp_router_init(mlxsw_sp); if (err) @@ -8128,12 +8109,6 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_neigh_init; - mlxsw_sp->router->netevent_nb.notifier_call = - mlxsw_sp_router_netevent_event; - err = register_netevent_notifier(&mlxsw_sp->router->netevent_nb); - if (err) - goto err_register_netevent_notifier; - err = mlxsw_sp_mp_hash_init(mlxsw_sp); if (err) goto err_mp_hash_init; @@ -8142,6 +8117,22 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_dscp_init; + router->inetaddr_nb.notifier_call = mlxsw_sp_inetaddr_event; + err = register_inetaddr_notifier(&router->inetaddr_nb); + if (err) + goto err_register_inetaddr_notifier; + + router->inet6addr_nb.notifier_call = mlxsw_sp_inet6addr_event; + err = register_inet6addr_notifier(&router->inet6addr_nb); + if (err) + goto err_register_inet6addr_notifier; + + mlxsw_sp->router->netevent_nb.notifier_call = + mlxsw_sp_router_netevent_event; + err = register_netevent_notifier(&mlxsw_sp->router->netevent_nb); + if (err) + goto err_register_netevent_notifier; + mlxsw_sp->router->fib_nb.notifier_call = mlxsw_sp_router_fib_event; err = register_fib_notifier(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->router->fib_nb, @@ -8152,10 +8143,15 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, return 0; err_register_fib_notifier: -err_dscp_init: -err_mp_hash_init: unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); err_register_netevent_notifier: + unregister_inet6addr_notifier(&router->inet6addr_nb); +err_register_inet6addr_notifier: + unregister_inetaddr_notifier(&router->inetaddr_nb); +err_register_inetaddr_notifier: + mlxsw_core_flush_owq(); +err_dscp_init: +err_mp_hash_init: mlxsw_sp_neigh_fini(mlxsw_sp); err_neigh_init: mlxsw_sp_vrs_fini(mlxsw_sp); @@ -8174,10 +8170,6 @@ err_ipips_init: err_rifs_init: __mlxsw_sp_router_fini(mlxsw_sp); err_router_init: - unregister_inet6addr_notifier(&router->inet6addr_nb); -err_register_inet6addr_notifier: - unregister_inetaddr_notifier(&router->inetaddr_nb); -err_register_inetaddr_notifier: mutex_destroy(&mlxsw_sp->router->lock); kfree(mlxsw_sp->router); return err; @@ -8188,6 +8180,9 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->router->fib_nb); unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); + unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb); + unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb); + mlxsw_core_flush_owq(); mlxsw_sp_neigh_fini(mlxsw_sp); mlxsw_sp_vrs_fini(mlxsw_sp); mlxsw_sp_mr_fini(mlxsw_sp); @@ -8197,8 +8192,6 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_sp_ipips_fini(mlxsw_sp); mlxsw_sp_rifs_fini(mlxsw_sp); __mlxsw_sp_router_fini(mlxsw_sp); - unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb); - unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb); mutex_destroy(&mlxsw_sp->router->lock); kfree(mlxsw_sp->router); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index 157a42c63066..1e38dfe7cf64 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -328,6 +328,9 @@ mlxsw_sp_trap_policer_items_arr[] = { { .policer = MLXSW_SP_TRAP_POLICER(18, 1024, 128), }, + { + .policer = MLXSW_SP_TRAP_POLICER(19, 1024, 512), + }, }; static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = { @@ -422,6 +425,11 @@ static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = { .priority = 2, }, { + .group = DEVLINK_TRAP_GROUP_GENERIC(EXTERNAL_DELIVERY, 19), + .hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_EXTERNAL_ROUTE, + .priority = 1, + }, + { .group = DEVLINK_TRAP_GROUP_GENERIC(IPV6, 15), .hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6, .priority = 2, @@ -882,11 +890,11 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = { }, }, { - .trap = MLXSW_SP_TRAP_CONTROL(EXTERNAL_ROUTE, LOCAL_DELIVERY, + .trap = MLXSW_SP_TRAP_CONTROL(EXTERNAL_ROUTE, EXTERNAL_DELIVERY, TRAP), .listeners_arr = { - MLXSW_SP_RXL_MARK(RTR_INGRESS0, IP2ME, TRAP_TO_CPU, - false), + MLXSW_SP_RXL_MARK(RTR_INGRESS0, EXTERNAL_ROUTE, + TRAP_TO_CPU, false), }, }, { diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 9cfe1fd98c30..f17da67a4622 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -748,21 +748,21 @@ void ocelot_get_txtstamp(struct ocelot *ocelot) spin_unlock_irqrestore(&port->tx_skbs.lock, flags); - /* Next ts */ - ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT); + /* Get the h/w timestamp */ + ocelot_get_hwtimestamp(ocelot, &ts); if (unlikely(!skb_match)) continue; - /* Get the h/w timestamp */ - ocelot_get_hwtimestamp(ocelot, &ts); - /* Set the timestamp into the skb */ memset(&shhwtstamps, 0, sizeof(shhwtstamps)); shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec); skb_tstamp_tx(skb_match, &shhwtstamps); dev_kfree_skb_any(skb_match); + + /* Next ts */ + ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT); } } EXPORT_SYMBOL(ocelot_get_txtstamp); diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 9b63574b6202..b5f1849fd280 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -98,7 +98,7 @@ static inline void VXGE_COMPLETE_VPATH_TX(struct vxge_fifo *fifo) { struct sk_buff **skb_ptr = NULL; struct sk_buff **temp; -#define NR_SKB_COMPLETED 128 +#define NR_SKB_COMPLETED 16 struct sk_buff *completed[NR_SKB_COMPLETED]; int more; diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index d2708a57f2ff..4075f5e59955 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -1299,19 +1299,21 @@ static int nixge_probe(struct platform_device *pdev) netif_napi_add(ndev, &priv->napi, nixge_poll, NAPI_POLL_WEIGHT); err = nixge_of_get_resources(pdev); if (err) - return err; + goto free_netdev; __nixge_hw_set_mac_address(ndev); priv->tx_irq = platform_get_irq_byname(pdev, "tx"); if (priv->tx_irq < 0) { netdev_err(ndev, "could not find 'tx' irq"); - return priv->tx_irq; + err = priv->tx_irq; + goto free_netdev; } priv->rx_irq = platform_get_irq_byname(pdev, "rx"); if (priv->rx_irq < 0) { netdev_err(ndev, "could not find 'rx' irq"); - return priv->rx_irq; + err = priv->rx_irq; + goto free_netdev; } priv->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index e03ea9b18f95..095561924bdc 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -103,15 +103,18 @@ static void ionic_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) { struct ionic_lif *lif = netdev_priv(netdev); + unsigned int offset; unsigned int size; regs->version = IONIC_DEV_CMD_REG_VERSION; + offset = 0; size = IONIC_DEV_INFO_REG_COUNT * sizeof(u32); - memcpy_fromio(p, lif->ionic->idev.dev_info_regs->words, size); + memcpy_fromio(p + offset, lif->ionic->idev.dev_info_regs->words, size); + offset += size; size = IONIC_DEV_CMD_REG_COUNT * sizeof(u32); - memcpy_fromio(p, lif->ionic->idev.dev_cmd_regs->words, size); + memcpy_fromio(p + offset, lif->ionic->idev.dev_cmd_regs->words, size); } static int ionic_get_link_ksettings(struct net_device *netdev, diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index f49486b6d04d..e55d41546cff 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -96,8 +96,7 @@ static void ionic_link_status_check(struct ionic_lif *lif) u16 link_status; bool link_up; - if (!test_bit(IONIC_LIF_F_LINK_CHECK_REQUESTED, lif->state) || - test_bit(IONIC_LIF_F_QUEUE_RESET, lif->state)) + if (!test_bit(IONIC_LIF_F_LINK_CHECK_REQUESTED, lif->state)) return; link_status = le16_to_cpu(lif->info->status.link_status); @@ -114,16 +113,22 @@ static void ionic_link_status_check(struct ionic_lif *lif) netif_carrier_on(netdev); } - if (lif->netdev->flags & IFF_UP && netif_running(lif->netdev)) + if (lif->netdev->flags & IFF_UP && netif_running(lif->netdev)) { + mutex_lock(&lif->queue_lock); ionic_start_queues(lif); + mutex_unlock(&lif->queue_lock); + } } else { if (netif_carrier_ok(netdev)) { netdev_info(netdev, "Link down\n"); netif_carrier_off(netdev); } - if (lif->netdev->flags & IFF_UP && netif_running(lif->netdev)) + if (lif->netdev->flags & IFF_UP && netif_running(lif->netdev)) { + mutex_lock(&lif->queue_lock); ionic_stop_queues(lif); + mutex_unlock(&lif->queue_lock); + } } clear_bit(IONIC_LIF_F_LINK_CHECK_REQUESTED, lif->state); @@ -863,8 +868,7 @@ static int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr) if (f) return 0; - netdev_dbg(lif->netdev, "rx_filter add ADDR %pM (id %d)\n", addr, - ctx.comp.rx_filter_add.filter_id); + netdev_dbg(lif->netdev, "rx_filter add ADDR %pM\n", addr); memcpy(ctx.cmd.rx_filter_add.mac.addr, addr, ETH_ALEN); err = ionic_adminq_post_wait(lif, &ctx); @@ -893,6 +897,9 @@ static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr) return -ENOENT; } + netdev_dbg(lif->netdev, "rx_filter del ADDR %pM (id %d)\n", + addr, f->filter_id); + ctx.cmd.rx_filter_del.filter_id = cpu_to_le32(f->filter_id); ionic_rx_filter_free(lif, f); spin_unlock_bh(&lif->rx_filters.lock); @@ -901,9 +908,6 @@ static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr) if (err && err != -EEXIST) return err; - netdev_dbg(lif->netdev, "rx_filter del ADDR %pM (id %d)\n", addr, - ctx.cmd.rx_filter_del.filter_id); - return 0; } @@ -1351,13 +1355,11 @@ static int ionic_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, }; int err; + netdev_dbg(netdev, "rx_filter add VLAN %d\n", vid); err = ionic_adminq_post_wait(lif, &ctx); if (err) return err; - netdev_dbg(netdev, "rx_filter add VLAN %d (id %d)\n", vid, - ctx.comp.rx_filter_add.filter_id); - return ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx); } @@ -1382,8 +1384,8 @@ static int ionic_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, return -ENOENT; } - netdev_dbg(netdev, "rx_filter del VLAN %d (id %d)\n", vid, - le32_to_cpu(ctx.cmd.rx_filter_del.filter_id)); + netdev_dbg(netdev, "rx_filter del VLAN %d (id %d)\n", + vid, f->filter_id); ctx.cmd.rx_filter_del.filter_id = cpu_to_le32(f->filter_id); ionic_rx_filter_free(lif, f); @@ -1993,10 +1995,7 @@ int ionic_reset_queues(struct ionic_lif *lif, ionic_reset_cb cb, void *arg) bool running; int err = 0; - err = ionic_wait_for_bit(lif, IONIC_LIF_F_QUEUE_RESET); - if (err) - return err; - + mutex_lock(&lif->queue_lock); running = netif_running(lif->netdev); if (running) { netif_device_detach(lif->netdev); @@ -2014,7 +2013,7 @@ int ionic_reset_queues(struct ionic_lif *lif, ionic_reset_cb cb, void *arg) } reset_out: - clear_bit(IONIC_LIF_F_QUEUE_RESET, lif->state); + mutex_unlock(&lif->queue_lock); return err; } @@ -2161,7 +2160,9 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif) if (test_bit(IONIC_LIF_F_UP, lif->state)) { dev_info(ionic->dev, "Surprise FW stop, stopping queues\n"); + mutex_lock(&lif->queue_lock); ionic_stop_queues(lif); + mutex_unlock(&lif->queue_lock); } if (netif_running(lif->netdev)) { @@ -2280,15 +2281,15 @@ static void ionic_lif_deinit(struct ionic_lif *lif) cancel_work_sync(&lif->deferred.work); cancel_work_sync(&lif->tx_timeout_work); ionic_rx_filters_deinit(lif); + if (lif->netdev->features & NETIF_F_RXHASH) + ionic_lif_rss_deinit(lif); } - if (lif->netdev->features & NETIF_F_RXHASH) - ionic_lif_rss_deinit(lif); - napi_disable(&lif->adminqcq->napi); ionic_lif_qcq_deinit(lif, lif->notifyqcq); ionic_lif_qcq_deinit(lif, lif->adminqcq); + mutex_destroy(&lif->queue_lock); ionic_lif_reset(lif); } @@ -2465,6 +2466,7 @@ static int ionic_lif_init(struct ionic_lif *lif) return err; lif->hw_index = le16_to_cpu(comp.hw_index); + mutex_init(&lif->queue_lock); /* now that we have the hw_index we can figure out our doorbell page */ lif->dbid_count = le32_to_cpu(lif->ionic->ident.dev.ndbpgs_per_lif); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index ed126dd74e01..8dc2c5d77424 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -135,7 +135,6 @@ enum ionic_lif_state_flags { IONIC_LIF_F_SW_DEBUG_STATS, IONIC_LIF_F_UP, IONIC_LIF_F_LINK_CHECK_REQUESTED, - IONIC_LIF_F_QUEUE_RESET, IONIC_LIF_F_FW_RESET, /* leave this as last */ @@ -165,6 +164,7 @@ struct ionic_lif { unsigned int hw_index; unsigned int kern_pid; u64 __iomem *kern_dbpage; + struct mutex queue_lock; /* lock for queue structures */ spinlock_t adminq_lock; /* lock for AdminQ operations */ struct ionic_qcq *adminqcq; struct ionic_qcq *notifyqcq; @@ -213,12 +213,6 @@ struct ionic_lif { #define lif_to_txq(lif, i) (&lif_to_txqcq((lif), i)->q) #define lif_to_rxq(lif, i) (&lif_to_txqcq((lif), i)->q) -/* return 0 if successfully set the bit, else non-zero */ -static inline int ionic_wait_for_bit(struct ionic_lif *lif, int bitname) -{ - return wait_on_bit_lock(lif->state, bitname, TASK_INTERRUPTIBLE); -} - static inline u32 ionic_coal_usec_to_hw(struct ionic *ionic, u32 usecs) { u32 mult = le32_to_cpu(ionic->ident.dev.intr_coal_mult); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c index 80eeb7696e01..cd0076fc3044 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c @@ -21,13 +21,16 @@ void ionic_rx_filter_free(struct ionic_lif *lif, struct ionic_rx_filter *f) void ionic_rx_filter_replay(struct ionic_lif *lif) { struct ionic_rx_filter_add_cmd *ac; + struct hlist_head new_id_list; struct ionic_admin_ctx ctx; struct ionic_rx_filter *f; struct hlist_head *head; struct hlist_node *tmp; + unsigned int key; unsigned int i; int err; + INIT_HLIST_HEAD(&new_id_list); ac = &ctx.cmd.rx_filter_add; for (i = 0; i < IONIC_RX_FILTER_HLISTS; i++) { @@ -58,9 +61,30 @@ void ionic_rx_filter_replay(struct ionic_lif *lif) ac->mac.addr); break; } + spin_lock_bh(&lif->rx_filters.lock); + ionic_rx_filter_free(lif, f); + spin_unlock_bh(&lif->rx_filters.lock); + + continue; } + + /* remove from old id list, save new id in tmp list */ + spin_lock_bh(&lif->rx_filters.lock); + hlist_del(&f->by_id); + spin_unlock_bh(&lif->rx_filters.lock); + f->filter_id = le32_to_cpu(ctx.comp.rx_filter_add.filter_id); + hlist_add_head(&f->by_id, &new_id_list); } } + + /* rebuild the by_id hash lists with the new filter ids */ + spin_lock_bh(&lif->rx_filters.lock); + hlist_for_each_entry_safe(f, tmp, &new_id_list, by_id) { + key = f->filter_id & IONIC_RX_FILTER_HLISTS_MASK; + head = &lif->rx_filters.by_id[key]; + hlist_add_head(&f->by_id, head); + } + spin_unlock_bh(&lif->rx_filters.lock); } int ionic_rx_filters_init(struct ionic_lif *lif) @@ -69,10 +93,12 @@ int ionic_rx_filters_init(struct ionic_lif *lif) spin_lock_init(&lif->rx_filters.lock); + spin_lock_bh(&lif->rx_filters.lock); for (i = 0; i < IONIC_RX_FILTER_HLISTS; i++) { INIT_HLIST_HEAD(&lif->rx_filters.by_hash[i]); INIT_HLIST_HEAD(&lif->rx_filters.by_id[i]); } + spin_unlock_bh(&lif->rx_filters.lock); return 0; } @@ -84,11 +110,13 @@ void ionic_rx_filters_deinit(struct ionic_lif *lif) struct hlist_node *tmp; unsigned int i; + spin_lock_bh(&lif->rx_filters.lock); for (i = 0; i < IONIC_RX_FILTER_HLISTS; i++) { head = &lif->rx_filters.by_id[i]; hlist_for_each_entry_safe(f, tmp, head, by_id) ionic_rx_filter_free(lif, f); } + spin_unlock_bh(&lif->rx_filters.lock); } int ionic_rx_filter_save(struct ionic_lif *lif, u32 flow_id, u16 rxq_index, @@ -124,6 +152,7 @@ int ionic_rx_filter_save(struct ionic_lif *lif, u32 flow_id, u16 rxq_index, f->filter_id = le32_to_cpu(ctx->comp.rx_filter_add.filter_id); f->rxq_index = rxq_index; memcpy(&f->cmd, ac, sizeof(f->cmd)); + netdev_dbg(lif->netdev, "rx_filter add filter_id %d\n", f->filter_id); INIT_HLIST_NODE(&f->by_hash); INIT_HLIST_NODE(&f->by_id); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index b7f900c11834..85eb8f276a37 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -161,12 +161,6 @@ static void ionic_rx_clean(struct ionic_queue *q, return; } - /* no packet processing while resetting */ - if (unlikely(test_bit(IONIC_LIF_F_QUEUE_RESET, q->lif->state))) { - stats->dropped++; - return; - } - stats->pkts++; stats->bytes += le16_to_cpu(comp->len); diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 08ba9d54ab63..d13ec88313c3 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -2008,8 +2008,8 @@ static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn, enum protocol_type proto; if (p_hwfn->mcp_info->func_info.protocol == QED_PCI_ETH_RDMA) { - DP_NOTICE(p_hwfn, - "Current day drivers don't support RoCE & iWARP simultaneously on the same PF. Default to RoCE-only\n"); + DP_VERBOSE(p_hwfn, QED_MSG_SP, + "Current day drivers don't support RoCE & iWARP simultaneously on the same PF. Default to RoCE-only\n"); p_hwfn->hw_info.personality = QED_PCI_ETH_ROCE; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 9c26fde663b3..dbdac983ccde 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -3102,7 +3102,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params) } /* Log and clear previous pglue_b errors if such exist */ - qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_main_ptt); + qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_main_ptt, true); /* Enable the PF's internal FID_enable in the PXP */ rc = qed_pglueb_set_pfid_enable(p_hwfn, p_hwfn->p_main_ptt, diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index b7b974f0ef21..5eec1fc6229d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -257,9 +257,10 @@ out: #define PGLUE_ATTENTION_ZLR_VALID (1 << 25) #define PGLUE_ATTENTION_ILT_VALID (1 << 23) -int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt) +int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + bool hw_init) { + char msg[256]; u32 tmp; tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS2); @@ -273,22 +274,23 @@ int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, details = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS); - DP_NOTICE(p_hwfn, - "Illegal write by chip to [%08x:%08x] blocked.\n" - "Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n" - "Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n", - addr_hi, addr_lo, details, - (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID), - (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID), - GET_FIELD(details, - PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0, - tmp, - GET_FIELD(tmp, - PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0, - GET_FIELD(tmp, - PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0, - GET_FIELD(tmp, - PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0); + snprintf(msg, sizeof(msg), + "Illegal write by chip to [%08x:%08x] blocked.\n" + "Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n" + "Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]", + addr_hi, addr_lo, details, + (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID), + (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID), + !!GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VF_VALID), + tmp, + !!GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_WAS_ERR), + !!GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_BME), + !!GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_FID_EN)); + + if (hw_init) + DP_VERBOSE(p_hwfn, NETIF_MSG_INTR, "%s\n", msg); + else + DP_NOTICE(p_hwfn, "%s\n", msg); } tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_RD_DETAILS2); @@ -321,8 +323,14 @@ int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, } tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS_ICPL); - if (tmp & PGLUE_ATTENTION_ICPL_VALID) - DP_NOTICE(p_hwfn, "ICPL error - %08x\n", tmp); + if (tmp & PGLUE_ATTENTION_ICPL_VALID) { + snprintf(msg, sizeof(msg), "ICPL error - %08x", tmp); + + if (hw_init) + DP_VERBOSE(p_hwfn, NETIF_MSG_INTR, "%s\n", msg); + else + DP_NOTICE(p_hwfn, "%s\n", msg); + } tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_MASTER_ZLR_ERR_DETAILS); if (tmp & PGLUE_ATTENTION_ZLR_VALID) { @@ -361,7 +369,7 @@ int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, static int qed_pglueb_rbc_attn_cb(struct qed_hwfn *p_hwfn) { - return qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_dpc_ptt); + return qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_dpc_ptt, false); } static int qed_fw_assertion(struct qed_hwfn *p_hwfn) @@ -1193,7 +1201,8 @@ static int qed_int_attentions(struct qed_hwfn *p_hwfn) index, attn_bits, attn_acks, asserted_bits, deasserted_bits, p_sb_attn_sw->known_attn); } else if (asserted_bits == 0x100) { - DP_INFO(p_hwfn, "MFW indication via attention\n"); + DP_VERBOSE(p_hwfn, NETIF_MSG_INTR, + "MFW indication via attention\n"); } else { DP_VERBOSE(p_hwfn, NETIF_MSG_INTR, "MFW indication [deassertion]\n"); diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h index e09db3386367..110169e90121 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.h +++ b/drivers/net/ethernet/qlogic/qed/qed_int.h @@ -442,7 +442,7 @@ int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, #define QED_MAPPING_MEMORY_SIZE(dev) (NUM_OF_SBS(dev)) -int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt); +int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + bool hw_init); #endif diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index a442bcf64b9c..99f7aae102ce 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1450,6 +1450,7 @@ static void ravb_tx_timeout_work(struct work_struct *work) struct ravb_private *priv = container_of(work, struct ravb_private, work); struct net_device *ndev = priv->ndev; + int error; netif_tx_stop_all_queues(ndev); @@ -1458,15 +1459,36 @@ static void ravb_tx_timeout_work(struct work_struct *work) ravb_ptp_stop(ndev); /* Wait for DMA stopping */ - ravb_stop_dma(ndev); + if (ravb_stop_dma(ndev)) { + /* If ravb_stop_dma() fails, the hardware is still operating + * for TX and/or RX. So, this should not call the following + * functions because ravb_dmac_init() is possible to fail too. + * Also, this should not retry ravb_stop_dma() again and again + * here because it's possible to wait forever. So, this just + * re-enables the TX and RX and skip the following + * re-initialization procedure. + */ + ravb_rcv_snd_enable(ndev); + goto out; + } ravb_ring_free(ndev, RAVB_BE); ravb_ring_free(ndev, RAVB_NC); /* Device init */ - ravb_dmac_init(ndev); + error = ravb_dmac_init(ndev); + if (error) { + /* If ravb_dmac_init() fails, descriptors are freed. So, this + * should return here to avoid re-enabling the TX and RX in + * ravb_emac_init(). + */ + netdev_err(ndev, "%s: ravb_dmac_init() failed, error %d\n", + __func__, error); + return; + } ravb_emac_init(ndev); +out: /* Initialise PTP Clock driver */ if (priv->chip_id == RCAR_GEN2) ravb_ptp_init(ndev, priv->pdev); diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 90410f9d3b1a..1c4fea9c3ec4 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -2274,7 +2274,7 @@ static int smc_drv_probe(struct platform_device *pdev) ret = try_toggle_control_gpio(&pdev->dev, &lp->power_gpio, "power", 0, 0, 100); if (ret) - return ret; + goto out_free_netdev; /* * Optional reset GPIO configured? Minimum 100 ns reset needed @@ -2283,7 +2283,7 @@ static int smc_drv_probe(struct platform_device *pdev) ret = try_toggle_control_gpio(&pdev->dev, &lp->reset_gpio, "reset", 0, 0, 100); if (ret) - return ret; + goto out_free_netdev; /* * Need to wait for optional EEPROM to load, max 750 us according diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index f2638446b62e..81b554dd7221 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1191,7 +1191,7 @@ static int ave_init(struct net_device *ndev) ret = regmap_update_bits(priv->regmap, SG_ETPINMODE, priv->pinmode_mask, priv->pinmode_val); if (ret) - return ret; + goto out_reset_assert; ave_global_reset(ndev); diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 1492648247d9..6d778bc3d012 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1850,7 +1850,8 @@ static int am65_cpsw_nuss_init_ndev_2g(struct am65_cpsw_common *common) port->ndev->max_mtu = AM65_CPSW_MAX_PACKET_SIZE; port->ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | - NETIF_F_HW_CSUM; + NETIF_F_HW_CSUM | + NETIF_F_HW_TC; port->ndev->features = port->ndev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; port->ndev->vlan_features |= NETIF_F_SG; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 4661ef865807..dec52b763d50 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1615,11 +1615,11 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct geneve_dev *geneve = netdev_priv(dev); + enum ifla_geneve_df df = geneve->df; struct geneve_sock *gs4, *gs6; struct ip_tunnel_info info; bool metadata; bool use_udp6_rx_checksums; - enum ifla_geneve_df df; bool ttl_inherit; int err; diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c index 2a6ec5394966..a4b3fce69ecd 100644 --- a/drivers/net/hippi/rrunner.c +++ b/drivers/net/hippi/rrunner.c @@ -1242,7 +1242,7 @@ static int rr_open(struct net_device *dev) rrpriv->info = NULL; } if (rrpriv->rx_ctrl) { - pci_free_consistent(pdev, sizeof(struct ring_ctrl), + pci_free_consistent(pdev, 256 * sizeof(struct ring_ctrl), rrpriv->rx_ctrl, rrpriv->rx_ctrl_dma); rrpriv->rx_ctrl = NULL; } diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c index 5a37514e4234..c11f32f644db 100644 --- a/drivers/net/ieee802154/adf7242.c +++ b/drivers/net/ieee802154/adf7242.c @@ -4,7 +4,7 @@ * * Copyright 2009-2017 Analog Devices Inc. * - * http://www.analog.com/ADF7242 + * https://www.analog.com/ADF7242 */ #include <linux/kernel.h> @@ -1262,7 +1262,7 @@ static int adf7242_probe(struct spi_device *spi) WQ_MEM_RECLAIM); if (unlikely(!lp->wqueue)) { ret = -ENOMEM; - goto err_hw_init; + goto err_alloc_wq; } ret = adf7242_hw_init(lp); @@ -1294,6 +1294,8 @@ static int adf7242_probe(struct spi_device *spi) return ret; err_hw_init: + destroy_workqueue(lp->wqueue); +err_alloc_wq: mutex_destroy(&lp->bmux); ieee802154_free_hw(lp->hw); diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 2908e0a0d6e1..23950e7a0f81 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -302,7 +302,7 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) rtnl_lock(); err = nsim_bpf_init(ns); if (err) - goto err_free_netdev; + goto err_rtnl_unlock; nsim_ipsec_init(ns); @@ -316,8 +316,8 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) err_ipsec_teardown: nsim_ipsec_teardown(ns); nsim_bpf_uninit(ns); +err_rtnl_unlock: rtnl_unlock(); -err_free_netdev: free_netdev(dev); return ERR_PTR(err); } diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index ecbd5e0d685c..acb0aae60755 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1260,6 +1260,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr) dp83640->hwts_rx_en = 1; dp83640->layer = PTP_CLASS_L4; dp83640->version = PTP_CLASS_V1; + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; break; case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: @@ -1267,6 +1268,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr) dp83640->hwts_rx_en = 1; dp83640->layer = PTP_CLASS_L4; dp83640->version = PTP_CLASS_V2; + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT; break; case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: @@ -1274,6 +1276,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr) dp83640->hwts_rx_en = 1; dp83640->layer = PTP_CLASS_L2; dp83640->version = PTP_CLASS_V2; + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; break; case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_SYNC: @@ -1281,6 +1284,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr) dp83640->hwts_rx_en = 1; dp83640->layer = PTP_CLASS_L4 | PTP_CLASS_L2; dp83640->version = PTP_CLASS_V2; + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; break; default: return -ERANGE; diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index 4e514f5d7c6c..fd3a04d98dc1 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -187,6 +187,7 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf) ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, buf, 0); if (ret < ETH_ALEN) { netdev_err(dev->net, "Failed to read MAC address: %d\n", ret); + ret = -EIO; goto free; } memcpy(dev->net->dev_addr, buf, ETH_ALEN); diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index bb8c34d746ab..d2fdb5430d27 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -1390,8 +1390,9 @@ static void hso_serial_set_termios(struct tty_struct *tty, struct ktermios *old) unsigned long flags; if (old) - hso_dbg(0x16, "Termios called with: cflags new[%d] - old[%d]\n", - tty->termios.c_cflag, old->c_cflag); + hso_dbg(0x16, "Termios called with: cflags new[%u] - old[%u]\n", + (unsigned int)tty->termios.c_cflag, + (unsigned int)old->c_cflag); /* the actual setup */ spin_lock_irqsave(&serial->serial_lock, flags); @@ -2260,12 +2261,14 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs, minor = get_free_serial_index(); if (minor < 0) - goto exit; + goto exit2; /* register our minor number */ serial->parent->dev = tty_port_register_device_attr(&serial->port, tty_drv, minor, &serial->parent->interface->dev, serial->parent, hso_serial_dev_groups); + if (IS_ERR(serial->parent->dev)) + goto exit2; /* fill in specific data for later use */ serial->minor = minor; @@ -2310,6 +2313,7 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs, return 0; exit: hso_serial_tty_unregister(serial); +exit2: hso_serial_common_free(serial); return -1; } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index eccbf4cd7149..442507f25aad 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -377,10 +377,6 @@ struct lan78xx_net { struct tasklet_struct bh; struct delayed_work wq; - struct usb_host_endpoint *ep_blkin; - struct usb_host_endpoint *ep_blkout; - struct usb_host_endpoint *ep_intr; - int msg_enable; struct urb *urb_intr; @@ -2860,78 +2856,12 @@ lan78xx_start_xmit(struct sk_buff *skb, struct net_device *net) return NETDEV_TX_OK; } -static int -lan78xx_get_endpoints(struct lan78xx_net *dev, struct usb_interface *intf) -{ - int tmp; - struct usb_host_interface *alt = NULL; - struct usb_host_endpoint *in = NULL, *out = NULL; - struct usb_host_endpoint *status = NULL; - - for (tmp = 0; tmp < intf->num_altsetting; tmp++) { - unsigned ep; - - in = NULL; - out = NULL; - status = NULL; - alt = intf->altsetting + tmp; - - for (ep = 0; ep < alt->desc.bNumEndpoints; ep++) { - struct usb_host_endpoint *e; - int intr = 0; - - e = alt->endpoint + ep; - switch (e->desc.bmAttributes) { - case USB_ENDPOINT_XFER_INT: - if (!usb_endpoint_dir_in(&e->desc)) - continue; - intr = 1; - /* FALLTHROUGH */ - case USB_ENDPOINT_XFER_BULK: - break; - default: - continue; - } - if (usb_endpoint_dir_in(&e->desc)) { - if (!intr && !in) - in = e; - else if (intr && !status) - status = e; - } else { - if (!out) - out = e; - } - } - if (in && out) - break; - } - if (!alt || !in || !out) - return -EINVAL; - - dev->pipe_in = usb_rcvbulkpipe(dev->udev, - in->desc.bEndpointAddress & - USB_ENDPOINT_NUMBER_MASK); - dev->pipe_out = usb_sndbulkpipe(dev->udev, - out->desc.bEndpointAddress & - USB_ENDPOINT_NUMBER_MASK); - dev->ep_intr = status; - - return 0; -} - static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf) { struct lan78xx_priv *pdata = NULL; int ret; int i; - ret = lan78xx_get_endpoints(dev, intf); - if (ret) { - netdev_warn(dev->net, "lan78xx_get_endpoints failed: %d\n", - ret); - return ret; - } - dev->data[0] = (unsigned long)kzalloc(sizeof(*pdata), GFP_KERNEL); pdata = (struct lan78xx_priv *)(dev->data[0]); @@ -3700,6 +3630,7 @@ static void lan78xx_stat_monitor(struct timer_list *t) static int lan78xx_probe(struct usb_interface *intf, const struct usb_device_id *id) { + struct usb_host_endpoint *ep_blkin, *ep_blkout, *ep_intr; struct lan78xx_net *dev; struct net_device *netdev; struct usb_device *udev; @@ -3748,6 +3679,34 @@ static int lan78xx_probe(struct usb_interface *intf, mutex_init(&dev->stats.access_lock); + if (intf->cur_altsetting->desc.bNumEndpoints < 3) { + ret = -ENODEV; + goto out2; + } + + dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE); + ep_blkin = usb_pipe_endpoint(udev, dev->pipe_in); + if (!ep_blkin || !usb_endpoint_is_bulk_in(&ep_blkin->desc)) { + ret = -ENODEV; + goto out2; + } + + dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE); + ep_blkout = usb_pipe_endpoint(udev, dev->pipe_out); + if (!ep_blkout || !usb_endpoint_is_bulk_out(&ep_blkout->desc)) { + ret = -ENODEV; + goto out2; + } + + ep_intr = &intf->cur_altsetting->endpoint[2]; + if (!usb_endpoint_is_int_in(&ep_intr->desc)) { + ret = -ENODEV; + goto out2; + } + + dev->pipe_intr = usb_rcvintpipe(dev->udev, + usb_endpoint_num(&ep_intr->desc)); + ret = lan78xx_bind(dev, intf); if (ret < 0) goto out2; @@ -3759,18 +3718,7 @@ static int lan78xx_probe(struct usb_interface *intf, netdev->max_mtu = MAX_SINGLE_PACKET_SIZE; netif_set_gso_max_size(netdev, MAX_SINGLE_PACKET_SIZE - MAX_HEADER); - dev->ep_blkin = (intf->cur_altsetting)->endpoint + 0; - dev->ep_blkout = (intf->cur_altsetting)->endpoint + 1; - dev->ep_intr = (intf->cur_altsetting)->endpoint + 2; - - dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE); - dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE); - - dev->pipe_intr = usb_rcvintpipe(dev->udev, - dev->ep_intr->desc.bEndpointAddress & - USB_ENDPOINT_NUMBER_MASK); - period = dev->ep_intr->desc.bInterval; - + period = ep_intr->desc.bInterval; maxp = usb_maxpacket(dev->udev, dev->pipe_intr, 0); buf = kmalloc(maxp, GFP_KERNEL); if (buf) { @@ -3783,6 +3731,7 @@ static int lan78xx_probe(struct usb_interface *intf, usb_fill_int_urb(dev->urb_intr, dev->udev, dev->pipe_intr, buf, maxp, intr_complete, dev, period); + dev->urb_intr->transfer_flags |= URB_FREE_BUFFER; } } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 89d85dcb200e..a7c3939264b0 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1376,6 +1376,7 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, for (h = 0; h < FDB_HASH_SIZE; ++h) { struct vxlan_fdb *f; + rcu_read_lock(); hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) { struct vxlan_rdst *rd; @@ -1387,8 +1388,10 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, NULL); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); goto out; + } skip_nh: *idx += 1; continue; @@ -1403,12 +1406,15 @@ skip_nh: cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, rd); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); goto out; + } skip: *idx += 1; } } + rcu_read_unlock(); } out: return err; @@ -3070,8 +3076,10 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all) if (!do_all && (f->state & (NUD_PERMANENT | NUD_NOARP))) continue; /* the all_zeros_mac entry is deleted at vxlan_uninit */ - if (!is_zero_ether_addr(f->eth_addr)) - vxlan_fdb_destroy(vxlan, f, true, true); + if (is_zero_ether_addr(f->eth_addr) && + f->vni == vxlan->cfg.vni) + continue; + vxlan_fdb_destroy(vxlan, f, true, true); } spin_unlock_bh(&vxlan->hash_lock[h]); } diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c index c84536b03aa8..f70336bb6f52 100644 --- a/drivers/net/wan/hdlc_x25.c +++ b/drivers/net/wan/hdlc_x25.c @@ -71,8 +71,10 @@ static int x25_data_indication(struct net_device *dev, struct sk_buff *skb) { unsigned char *ptr; - if (skb_cow(skb, 1)) + if (skb_cow(skb, 1)) { + kfree_skb(skb); return NET_RX_DROP; + } skb_push(skb, 1); skb_reset_network_header(skb); diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index 284832314f31..b2868433718f 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -128,10 +128,12 @@ static int lapbeth_data_indication(struct net_device *dev, struct sk_buff *skb) { unsigned char *ptr; - skb_push(skb, 1); - - if (skb_cow(skb, 1)) + if (skb_cow(skb, 1)) { + kfree_skb(skb); return NET_RX_DROP; + } + + skb_push(skb, 1); ptr = skb->data; *ptr = X25_IFACE_DATA; diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c index 69773d228ec1..84640a0c13f3 100644 --- a/drivers/net/wan/x25_asy.c +++ b/drivers/net/wan/x25_asy.c @@ -183,7 +183,7 @@ static inline void x25_asy_unlock(struct x25_asy *sl) netif_wake_queue(sl->dev); } -/* Send one completely decapsulated IP datagram to the IP layer. */ +/* Send an LAPB frame to the LAPB module to process. */ static void x25_asy_bump(struct x25_asy *sl) { @@ -195,13 +195,12 @@ static void x25_asy_bump(struct x25_asy *sl) count = sl->rcount; dev->stats.rx_bytes += count; - skb = dev_alloc_skb(count+1); + skb = dev_alloc_skb(count); if (skb == NULL) { netdev_warn(sl->dev, "memory squeeze, dropping packet\n"); dev->stats.rx_dropped++; return; } - skb_push(skb, 1); /* LAPB internal control */ skb_put_data(skb, sl->rbuff, count); skb->protocol = x25_type_trans(skb, sl->dev); err = lapb_data_received(skb->dev, skb); @@ -209,7 +208,6 @@ static void x25_asy_bump(struct x25_asy *sl) kfree_skb(skb); printk(KERN_DEBUG "x25_asy: data received err - %d\n", err); } else { - netif_rx(skb); dev->stats.rx_packets++; } } @@ -356,12 +354,21 @@ static netdev_tx_t x25_asy_xmit(struct sk_buff *skb, */ /* - * Called when I frame data arrives. We did the work above - throw it - * at the net layer. + * Called when I frame data arrive. We add a pseudo header for upper + * layers and pass it to upper layers. */ static int x25_asy_data_indication(struct net_device *dev, struct sk_buff *skb) { + if (skb_cow(skb, 1)) { + kfree_skb(skb); + return NET_RX_DROP; + } + skb_push(skb, 1); + skb->data[0] = X25_IFACE_DATA; + + skb->protocol = x25_type_trans(skb, dev); + return netif_rx(skb); } @@ -657,7 +664,7 @@ static void x25_asy_unesc(struct x25_asy *sl, unsigned char s) switch (s) { case X25_END: if (!test_and_clear_bit(SLF_ERROR, &sl->flags) && - sl->rcount > 2) + sl->rcount >= 2) x25_asy_bump(sl); clear_bit(SLF_ESCAPE, &sl->flags); sl->rcount = 0; diff --git a/drivers/net/wireless/ath/ath10k/ahb.c b/drivers/net/wireless/ath/ath10k/ahb.c index 342a7e58018a..05a61975c83f 100644 --- a/drivers/net/wireless/ath/ath10k/ahb.c +++ b/drivers/net/wireless/ath/ath10k/ahb.c @@ -820,7 +820,7 @@ err_free_irq: ath10k_ahb_release_irq_legacy(ar); err_free_pipes: - ath10k_pci_free_pipes(ar); + ath10k_pci_release_resource(ar); err_resource_deinit: ath10k_ahb_resource_deinit(ar); diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c index 1d941d53fdc9..cfde7791291a 100644 --- a/drivers/net/wireless/ath/ath10k/pci.c +++ b/drivers/net/wireless/ath/ath10k/pci.c @@ -3473,6 +3473,28 @@ int ath10k_pci_setup_resource(struct ath10k *ar) timer_setup(&ar_pci->rx_post_retry, ath10k_pci_rx_replenish_retry, 0); + ar_pci->attr = kmemdup(pci_host_ce_config_wlan, + sizeof(pci_host_ce_config_wlan), + GFP_KERNEL); + if (!ar_pci->attr) + return -ENOMEM; + + ar_pci->pipe_config = kmemdup(pci_target_ce_config_wlan, + sizeof(pci_target_ce_config_wlan), + GFP_KERNEL); + if (!ar_pci->pipe_config) { + ret = -ENOMEM; + goto err_free_attr; + } + + ar_pci->serv_to_pipe = kmemdup(pci_target_service_to_ce_map_wlan, + sizeof(pci_target_service_to_ce_map_wlan), + GFP_KERNEL); + if (!ar_pci->serv_to_pipe) { + ret = -ENOMEM; + goto err_free_pipe_config; + } + if (QCA_REV_6174(ar) || QCA_REV_9377(ar)) ath10k_pci_override_ce_config(ar); @@ -3480,18 +3502,31 @@ int ath10k_pci_setup_resource(struct ath10k *ar) if (ret) { ath10k_err(ar, "failed to allocate copy engine pipes: %d\n", ret); - return ret; + goto err_free_serv_to_pipe; } return 0; + +err_free_serv_to_pipe: + kfree(ar_pci->serv_to_pipe); +err_free_pipe_config: + kfree(ar_pci->pipe_config); +err_free_attr: + kfree(ar_pci->attr); + return ret; } void ath10k_pci_release_resource(struct ath10k *ar) { + struct ath10k_pci *ar_pci = ath10k_pci_priv(ar); + ath10k_pci_rx_retry_sync(ar); netif_napi_del(&ar->napi); ath10k_pci_ce_deinit(ar); ath10k_pci_free_pipes(ar); + kfree(ar_pci->attr); + kfree(ar_pci->pipe_config); + kfree(ar_pci->serv_to_pipe); } static const struct ath10k_bus_ops ath10k_pci_bus_ops = { @@ -3601,30 +3636,6 @@ static int ath10k_pci_probe(struct pci_dev *pdev, timer_setup(&ar_pci->ps_timer, ath10k_pci_ps_timer, 0); - ar_pci->attr = kmemdup(pci_host_ce_config_wlan, - sizeof(pci_host_ce_config_wlan), - GFP_KERNEL); - if (!ar_pci->attr) { - ret = -ENOMEM; - goto err_free; - } - - ar_pci->pipe_config = kmemdup(pci_target_ce_config_wlan, - sizeof(pci_target_ce_config_wlan), - GFP_KERNEL); - if (!ar_pci->pipe_config) { - ret = -ENOMEM; - goto err_free; - } - - ar_pci->serv_to_pipe = kmemdup(pci_target_service_to_ce_map_wlan, - sizeof(pci_target_service_to_ce_map_wlan), - GFP_KERNEL); - if (!ar_pci->serv_to_pipe) { - ret = -ENOMEM; - goto err_free; - } - ret = ath10k_pci_setup_resource(ar); if (ret) { ath10k_err(ar, "failed to setup resource: %d\n", ret); @@ -3705,10 +3716,9 @@ err_unsupported: err_free_irq: ath10k_pci_free_irq(ar); - ath10k_pci_rx_retry_sync(ar); err_deinit_irq: - ath10k_pci_deinit_irq(ar); + ath10k_pci_release_resource(ar); err_sleep: ath10k_pci_sleep_sync(ar); @@ -3720,29 +3730,18 @@ err_free_pipes: err_core_destroy: ath10k_core_destroy(ar); -err_free: - kfree(ar_pci->attr); - kfree(ar_pci->pipe_config); - kfree(ar_pci->serv_to_pipe); - return ret; } static void ath10k_pci_remove(struct pci_dev *pdev) { struct ath10k *ar = pci_get_drvdata(pdev); - struct ath10k_pci *ar_pci; ath10k_dbg(ar, ATH10K_DBG_PCI, "pci remove\n"); if (!ar) return; - ar_pci = ath10k_pci_priv(ar); - - if (!ar_pci) - return; - ath10k_core_unregister(ar); ath10k_pci_free_irq(ar); ath10k_pci_deinit_irq(ar); @@ -3750,9 +3749,6 @@ static void ath10k_pci_remove(struct pci_dev *pdev) ath10k_pci_sleep_sync(ar); ath10k_pci_release(ar); ath10k_core_destroy(ar); - kfree(ar_pci->attr); - kfree(ar_pci->pipe_config); - kfree(ar_pci->serv_to_pipe); } MODULE_DEVICE_TABLE(pci, ath10k_pci_id_table); diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index 4ed21dad6a8e..3f563e02d17d 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -733,11 +733,13 @@ static void ath9k_hif_usb_reg_in_cb(struct urb *urb) return; } + rx_buf->skb = nskb; + usb_fill_int_urb(urb, hif_dev->udev, usb_rcvintpipe(hif_dev->udev, USB_REG_IN_PIPE), nskb->data, MAX_REG_IN_BUF_SIZE, - ath9k_hif_usb_reg_in_cb, nskb, 1); + ath9k_hif_usb_reg_in_cb, rx_buf, 1); } resubmit: diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index 7987a288917b..27116c7d3f4f 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -271,6 +271,8 @@ static int iwl_dbg_tlv_alloc_trigger(struct iwl_trans *trans, { struct iwl_fw_ini_trigger_tlv *trig = (void *)tlv->data; u32 tp = le32_to_cpu(trig->time_point); + struct iwl_ucode_tlv *dup = NULL; + int ret; if (le32_to_cpu(tlv->length) < sizeof(*trig)) return -EINVAL; @@ -283,10 +285,20 @@ static int iwl_dbg_tlv_alloc_trigger(struct iwl_trans *trans, return -EINVAL; } - if (!le32_to_cpu(trig->occurrences)) + if (!le32_to_cpu(trig->occurrences)) { + dup = kmemdup(tlv, sizeof(*tlv) + le32_to_cpu(tlv->length), + GFP_KERNEL); + if (!dup) + return -ENOMEM; + trig = (void *)dup->data; trig->occurrences = cpu_to_le32(-1); + tlv = dup; + } + + ret = iwl_dbg_tlv_add(tlv, &trans->dbg.time_point[tp].trig_list); + kfree(dup); - return iwl_dbg_tlv_add(tlv, &trans->dbg.time_point[tp].trig_list); + return ret; } static int (*dbg_tlv_alloc[])(struct iwl_trans *trans, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index fee01cbbd3ac..27977992fd7f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -1189,17 +1189,15 @@ static int iwl_mvm_inactivity_check(struct iwl_mvm *mvm, u8 alloc_for_sta) for_each_set_bit(i, &changetid_queues, IWL_MAX_HW_QUEUES) iwl_mvm_change_queue_tid(mvm, i); + rcu_read_unlock(); + if (free_queue >= 0 && alloc_for_sta != IWL_MVM_INVALID_STA) { ret = iwl_mvm_free_inactive_queue(mvm, free_queue, queue_owner, alloc_for_sta); - if (ret) { - rcu_read_unlock(); + if (ret) return ret; - } } - rcu_read_unlock(); - return free_queue; } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 65d65c6baf4c..e02bafb8921f 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -582,6 +582,8 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_DEV_INFO(0x30DC, 0x1552, iwl9560_2ac_cfg_soc, iwl9560_killer_1550i_name), IWL_DEV_INFO(0x31DC, 0x1551, iwl9560_2ac_cfg_soc, iwl9560_killer_1550s_name), IWL_DEV_INFO(0x31DC, 0x1552, iwl9560_2ac_cfg_soc, iwl9560_killer_1550i_name), + IWL_DEV_INFO(0xA370, 0x1551, iwl9560_2ac_cfg_soc, iwl9560_killer_1550s_name), + IWL_DEV_INFO(0xA370, 0x1552, iwl9560_2ac_cfg_soc, iwl9560_killer_1550i_name), IWL_DEV_INFO(0x271C, 0x0214, iwl9260_2ac_cfg, iwl9260_1_name), diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index dfe625a53c63..3d7db6ffb599 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -301,6 +301,7 @@ struct mt76_hw_cap { #define MT_DRV_TX_ALIGNED4_SKBS BIT(1) #define MT_DRV_SW_RX_AIRTIME BIT(2) #define MT_DRV_RX_DMA_HDR BIT(3) +#define MT_DRV_HW_MGMT_TXQ BIT(4) struct mt76_driver_ops { u32 drv_flags; diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c index 26cb711b465f..83dfa6da4761 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c @@ -642,8 +642,10 @@ mt7603_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class) { struct mt7603_dev *dev = hw->priv; + mutex_lock(&dev->mt76.mutex); dev->coverage_class = max_t(s16, coverage_class, 0); mt7603_mac_set_timing(dev); + mutex_unlock(&dev->mt76.mutex); } static void mt7603_tx(struct ieee80211_hw *hw, diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c index fd3ef483a87c..d06afcf46d67 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c @@ -234,10 +234,11 @@ mt7615_queues_acq(struct seq_file *s, void *data) int i; for (i = 0; i < 16; i++) { - int j, acs = i / 4, index = i % 4; + int j, wmm_idx = i % MT7615_MAX_WMM_SETS; + int acs = i / MT7615_MAX_WMM_SETS; u32 ctrl, val, qlen = 0; - val = mt76_rr(dev, MT_PLE_AC_QEMPTY(acs, index)); + val = mt76_rr(dev, MT_PLE_AC_QEMPTY(acs, wmm_idx)); ctrl = BIT(31) | BIT(15) | (acs << 8); for (j = 0; j < 32; j++) { @@ -245,11 +246,11 @@ mt7615_queues_acq(struct seq_file *s, void *data) continue; mt76_wr(dev, MT_PLE_FL_Q0_CTRL, - ctrl | (j + (index << 5))); + ctrl | (j + (wmm_idx << 5))); qlen += mt76_get_field(dev, MT_PLE_FL_Q3_CTRL, GENMASK(11, 0)); } - seq_printf(s, "AC%d%d: queued=%d\n", acs, index, qlen); + seq_printf(s, "AC%d%d: queued=%d\n", wmm_idx, acs, qlen); } return 0; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/dma.c b/drivers/net/wireless/mediatek/mt76/mt7615/dma.c index 5a124610d4af..e5a965df899a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/dma.c @@ -36,10 +36,10 @@ static int mt7622_init_tx_queues_multi(struct mt7615_dev *dev) { static const u8 wmm_queue_map[] = { - MT7622_TXQ_AC0, - MT7622_TXQ_AC1, - MT7622_TXQ_AC2, - MT7622_TXQ_AC3, + [IEEE80211_AC_BK] = MT7622_TXQ_AC0, + [IEEE80211_AC_BE] = MT7622_TXQ_AC1, + [IEEE80211_AC_VI] = MT7622_TXQ_AC2, + [IEEE80211_AC_VO] = MT7622_TXQ_AC3, }; int ret; int i; @@ -100,6 +100,7 @@ mt7615_tx_cleanup(struct mt7615_dev *dev) int i; mt76_queue_tx_cleanup(dev, MT_TXQ_MCU, false); + mt76_queue_tx_cleanup(dev, MT_TXQ_PSD, false); if (is_mt7615(&dev->mt76)) { mt76_queue_tx_cleanup(dev, MT_TXQ_BE, false); } else { diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c index edac37e7847b..22e4eabe6578 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c @@ -72,8 +72,7 @@ static int mt7615_eeprom_load(struct mt7615_dev *dev, u32 addr) { int ret; - ret = mt76_eeprom_init(&dev->mt76, MT7615_EEPROM_SIZE + - MT7615_EEPROM_EXTRA_DATA); + ret = mt76_eeprom_init(&dev->mt76, MT7615_EEPROM_FULL_SIZE); if (ret < 0) return ret; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.h b/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.h index 40fed7adc58a..a024dee10362 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.h +++ b/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.h @@ -17,7 +17,7 @@ #define MT7615_EEPROM_TXDPD_SIZE 216 #define MT7615_EEPROM_TXDPD_COUNT (44 + 3) -#define MT7615_EEPROM_EXTRA_DATA (MT7615_EEPROM_TXDPD_OFFSET + \ +#define MT7615_EEPROM_FULL_SIZE (MT7615_EEPROM_TXDPD_OFFSET + \ MT7615_EEPROM_TXDPD_COUNT * \ MT7615_EEPROM_TXDPD_SIZE) diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c index 9f1c6ca7a665..d97315ec7265 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c @@ -526,22 +526,16 @@ int mt7615_mac_write_txwi(struct mt7615_dev *dev, __le32 *txwi, fc_type = (le16_to_cpu(fc) & IEEE80211_FCTL_FTYPE) >> 2; fc_stype = (le16_to_cpu(fc) & IEEE80211_FCTL_STYPE) >> 4; - if (ieee80211_is_data(fc) || ieee80211_is_bufferable_mmpdu(fc)) { - q_idx = wmm_idx * MT7615_MAX_WMM_SETS + - skb_get_queue_mapping(skb); - p_fmt = is_usb ? MT_TX_TYPE_SF : MT_TX_TYPE_CT; - } else if (beacon) { - if (ext_phy) - q_idx = MT_LMAC_BCN1; - else - q_idx = MT_LMAC_BCN0; + if (beacon) { p_fmt = MT_TX_TYPE_FW; + q_idx = ext_phy ? MT_LMAC_BCN1 : MT_LMAC_BCN0; + } else if (skb_get_queue_mapping(skb) >= MT_TXQ_PSD) { + p_fmt = is_usb ? MT_TX_TYPE_SF : MT_TX_TYPE_CT; + q_idx = ext_phy ? MT_LMAC_ALTX1 : MT_LMAC_ALTX0; } else { - if (ext_phy) - q_idx = MT_LMAC_ALTX1; - else - q_idx = MT_LMAC_ALTX0; p_fmt = is_usb ? MT_TX_TYPE_SF : MT_TX_TYPE_CT; + q_idx = wmm_idx * MT7615_MAX_WMM_SETS + + mt7615_lmac_mapping(dev, skb_get_queue_mapping(skb)); } val = FIELD_PREP(MT_TXD0_TX_BYTES, skb->len + sz_txd) | diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.h b/drivers/net/wireless/mediatek/mt76/mt7615/mac.h index f0d4b29a52a2..81608ab656b8 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.h +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.h @@ -124,21 +124,6 @@ enum tx_pkt_type { MT_TX_TYPE_FW, }; -enum tx_pkt_queue_idx { - MT_LMAC_AC00, - MT_LMAC_AC01, - MT_LMAC_AC02, - MT_LMAC_AC03, - MT_LMAC_ALTX0 = 0x10, - MT_LMAC_BMC0, - MT_LMAC_BCN0, - MT_LMAC_PSMP0, - MT_LMAC_ALTX1, - MT_LMAC_BMC1, - MT_LMAC_BCN1, - MT_LMAC_PSMP1, -}; - enum tx_port_idx { MT_TX_PORT_IDX_LMAC, MT_TX_PORT_IDX_MCU diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c index c26f99b368d9..beaca8127680 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c @@ -397,6 +397,7 @@ mt7615_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 queue, struct mt7615_vif *mvif = (struct mt7615_vif *)vif->drv_priv; struct mt7615_dev *dev = mt7615_hw_dev(hw); + queue = mt7615_lmac_mapping(dev, queue); queue += mvif->wmm_idx * MT7615_MAX_WMM_SETS; return mt7615_mcu_set_wmm(dev, queue, params); @@ -735,9 +736,12 @@ static void mt7615_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class) { struct mt7615_phy *phy = mt7615_hw_phy(hw); + struct mt7615_dev *dev = phy->dev; + mutex_lock(&dev->mt76.mutex); phy->coverage_class = max_t(s16, coverage_class, 0); mt7615_mac_set_timing(phy); + mutex_unlock(&dev->mt76.mutex); } static int diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c index e670393506f0..2e99845b9c96 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c @@ -146,7 +146,7 @@ int mt7615_mmio_probe(struct device *pdev, void __iomem *mem_base, static const struct mt76_driver_ops drv_ops = { /* txwi_size = txd size + txp size */ .txwi_size = MT_TXD_SIZE + sizeof(struct mt7615_txp_common), - .drv_flags = MT_DRV_TXWI_NO_FREE, + .drv_flags = MT_DRV_TXWI_NO_FREE | MT_DRV_HW_MGMT_TXQ, .survey_flags = SURVEY_INFO_TIME_TX | SURVEY_INFO_TIME_RX | SURVEY_INFO_TIME_BSS_RX, diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h index d6176d316bee..3e7d51bf42a4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h @@ -282,6 +282,21 @@ struct mt7615_dev { struct list_head wd_head; }; +enum tx_pkt_queue_idx { + MT_LMAC_AC00, + MT_LMAC_AC01, + MT_LMAC_AC02, + MT_LMAC_AC03, + MT_LMAC_ALTX0 = 0x10, + MT_LMAC_BMC0, + MT_LMAC_BCN0, + MT_LMAC_PSMP0, + MT_LMAC_ALTX1, + MT_LMAC_BMC1, + MT_LMAC_BCN1, + MT_LMAC_PSMP1, +}; + enum { HW_BSSID_0 = 0x0, HW_BSSID_1, @@ -447,6 +462,21 @@ static inline u16 mt7615_wtbl_size(struct mt7615_dev *dev) return MT7615_WTBL_SIZE; } +static inline u8 mt7615_lmac_mapping(struct mt7615_dev *dev, u8 ac) +{ + static const u8 lmac_queue_map[] = { + [IEEE80211_AC_BK] = MT_LMAC_AC00, + [IEEE80211_AC_BE] = MT_LMAC_AC01, + [IEEE80211_AC_VI] = MT_LMAC_AC02, + [IEEE80211_AC_VO] = MT_LMAC_AC03, + }; + + if (WARN_ON_ONCE(ac >= ARRAY_SIZE(lmac_queue_map))) + return MT_LMAC_AC01; /* BE */ + + return lmac_queue_map[ac]; +} + void mt7615_dma_reset(struct mt7615_dev *dev); void mt7615_scan_work(struct work_struct *work); void mt7615_roc_work(struct work_struct *work); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c index a50077eb24d7..5be6704770ad 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c @@ -270,7 +270,7 @@ static int mt7663u_probe(struct usb_interface *usb_intf, { static const struct mt76_driver_ops drv_ops = { .txwi_size = MT_USB_TXD_SIZE, - .drv_flags = MT_DRV_RX_DMA_HDR, + .drv_flags = MT_DRV_RX_DMA_HDR | MT_DRV_HW_MGMT_TXQ, .tx_prepare_skb = mt7663u_tx_prepare_skb, .tx_complete_skb = mt7663u_tx_complete_skb, .tx_status_data = mt7663u_tx_status_data, @@ -329,25 +329,26 @@ static int mt7663u_probe(struct usb_interface *usb_intf, if (!mt76_poll_msec(dev, MT_CONN_ON_MISC, MT_TOP_MISC2_FW_PWR_ON, FW_STATE_PWR_ON << 1, 500)) { dev_err(dev->mt76.dev, "Timeout for power on\n"); - return -EIO; + ret = -EIO; + goto error; } alloc_queues: ret = mt76u_alloc_mcu_queue(&dev->mt76); if (ret) - goto error; + goto error_free_q; ret = mt76u_alloc_queues(&dev->mt76); if (ret) - goto error; + goto error_free_q; ret = mt7663u_register_device(dev); if (ret) - goto error_freeq; + goto error_free_q; return 0; -error_freeq: +error_free_q: mt76u_queues_deinit(&dev->mt76); error: mt76u_deinit(&dev->mt76); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c index cbbe986655fe..5fda6e7b120c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c @@ -456,8 +456,9 @@ static void mt76x02_watchdog_reset(struct mt76x02_dev *dev) tasklet_disable(&dev->mt76.tx_tasklet); napi_disable(&dev->mt76.tx_napi); - for (i = 0; i < ARRAY_SIZE(dev->mt76.napi); i++) + mt76_for_each_q_rx(&dev->mt76, i) { napi_disable(&dev->mt76.napi[i]); + } mutex_lock(&dev->mt76.mutex); @@ -515,7 +516,7 @@ static void mt76x02_watchdog_reset(struct mt76x02_dev *dev) tasklet_enable(&dev->mt76.pre_tbtt_tasklet); - for (i = 0; i < ARRAY_SIZE(dev->mt76.napi); i++) { + mt76_for_each_q_rx(&dev->mt76, i) { napi_enable(&dev->mt76.napi[i]); napi_schedule(&dev->mt76.napi[i]); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c index 0575c259f245..05b5650c56c8 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c @@ -716,9 +716,12 @@ static void mt7915_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class) { struct mt7915_phy *phy = mt7915_hw_phy(hw); + struct mt7915_dev *dev = phy->dev; + mutex_lock(&dev->mt76.mutex); phy->coverage_class = max_t(s16, coverage_class, 0); mt7915_mac_set_timing(phy); + mutex_unlock(&dev->mt76.mutex); } static int diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c index fca38ea2441f..f10c98aa883c 100644 --- a/drivers/net/wireless/mediatek/mt76/tx.c +++ b/drivers/net/wireless/mediatek/mt76/tx.c @@ -264,6 +264,13 @@ mt76_tx(struct mt76_phy *phy, struct ieee80211_sta *sta, skb_set_queue_mapping(skb, qid); } + if ((dev->drv->drv_flags & MT_DRV_HW_MGMT_TXQ) && + !ieee80211_is_data(hdr->frame_control) && + !ieee80211_is_bufferable_mmpdu(hdr->frame_control)) { + qid = MT_TXQ_PSD; + skb_set_queue_mapping(skb, qid); + } + if (!(wcid->tx_info & MT_WCID_TX_INFO_SET)) ieee80211_get_tx_rates(info->control.vif, sta, skb, info->control.rates, 1); diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c index fb97ea25b4d4..87382b2f7443 100644 --- a/drivers/net/wireless/mediatek/mt76/usb.c +++ b/drivers/net/wireless/mediatek/mt76/usb.c @@ -1010,17 +1010,18 @@ static void mt76u_tx_kick(struct mt76_dev *dev, struct mt76_queue *q) static u8 mt76u_ac_to_hwq(struct mt76_dev *dev, u8 ac) { if (mt76_chip(dev) == 0x7663) { - static const u8 wmm_queue_map[] = { - [IEEE80211_AC_VO] = 0, - [IEEE80211_AC_VI] = 1, - [IEEE80211_AC_BE] = 2, - [IEEE80211_AC_BK] = 4, + static const u8 lmac_queue_map[] = { + /* ac to lmac mapping */ + [IEEE80211_AC_BK] = 0, + [IEEE80211_AC_BE] = 1, + [IEEE80211_AC_VI] = 2, + [IEEE80211_AC_VO] = 4, }; - if (WARN_ON(ac >= ARRAY_SIZE(wmm_queue_map))) - return 2; /* BE */ + if (WARN_ON(ac >= ARRAY_SIZE(lmac_queue_map))) + return 1; /* BE */ - return wmm_queue_map[ac]; + return lmac_queue_map[ac]; } return mt76_ac_to_hwq(ac); @@ -1066,11 +1067,16 @@ static int mt76u_alloc_tx(struct mt76_dev *dev) static void mt76u_free_tx(struct mt76_dev *dev) { - struct mt76_queue *q; - int i, j; + int i; for (i = 0; i < IEEE80211_NUM_ACS; i++) { + struct mt76_queue *q; + int j; + q = dev->q_tx[i].q; + if (!q) + continue; + for (j = 0; j < q->ndesc; j++) usb_free_urb(q->entry[j].urb); } @@ -1078,17 +1084,22 @@ static void mt76u_free_tx(struct mt76_dev *dev) void mt76u_stop_tx(struct mt76_dev *dev) { - struct mt76_queue_entry entry; - struct mt76_queue *q; - int i, j, ret; + int ret; ret = wait_event_timeout(dev->tx_wait, !mt76_has_tx_pending(&dev->phy), HZ / 5); if (!ret) { + struct mt76_queue_entry entry; + struct mt76_queue *q; + int i, j; + dev_err(dev->dev, "timed out waiting for pending tx\n"); for (i = 0; i < IEEE80211_NUM_ACS; i++) { q = dev->q_tx[i].q; + if (!q) + continue; + for (j = 0; j < q->ndesc; j++) usb_kill_urb(q->entry[j].urb); } @@ -1100,6 +1111,8 @@ void mt76u_stop_tx(struct mt76_dev *dev) */ for (i = 0; i < IEEE80211_NUM_ACS; i++) { q = dev->q_tx[i].q; + if (!q) + continue; /* Assure we are in sync with killed tasklet. */ spin_lock_bh(&q->lock); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 482c6c8b0fb7..88280057e032 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -63,6 +63,8 @@ module_param_named(max_queues, xennet_max_queues, uint, 0644); MODULE_PARM_DESC(max_queues, "Maximum number of queues per virtual interface"); +#define XENNET_TIMEOUT (5 * HZ) + static const struct ethtool_ops xennet_ethtool_ops; struct netfront_cb { @@ -1334,12 +1336,15 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev) netif_carrier_off(netdev); - xenbus_switch_state(dev, XenbusStateInitialising); - wait_event(module_wq, - xenbus_read_driver_state(dev->otherend) != - XenbusStateClosed && - xenbus_read_driver_state(dev->otherend) != - XenbusStateUnknown); + do { + xenbus_switch_state(dev, XenbusStateInitialising); + err = wait_event_timeout(module_wq, + xenbus_read_driver_state(dev->otherend) != + XenbusStateClosed && + xenbus_read_driver_state(dev->otherend) != + XenbusStateUnknown, XENNET_TIMEOUT); + } while (!err); + return netdev; exit: @@ -2139,28 +2144,43 @@ static const struct attribute_group xennet_dev_group = { }; #endif /* CONFIG_SYSFS */ -static int xennet_remove(struct xenbus_device *dev) +static void xennet_bus_close(struct xenbus_device *dev) { - struct netfront_info *info = dev_get_drvdata(&dev->dev); - - dev_dbg(&dev->dev, "%s\n", dev->nodename); + int ret; - if (xenbus_read_driver_state(dev->otherend) != XenbusStateClosed) { + if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed) + return; + do { xenbus_switch_state(dev, XenbusStateClosing); - wait_event(module_wq, - xenbus_read_driver_state(dev->otherend) == - XenbusStateClosing || - xenbus_read_driver_state(dev->otherend) == - XenbusStateUnknown); + ret = wait_event_timeout(module_wq, + xenbus_read_driver_state(dev->otherend) == + XenbusStateClosing || + xenbus_read_driver_state(dev->otherend) == + XenbusStateClosed || + xenbus_read_driver_state(dev->otherend) == + XenbusStateUnknown, + XENNET_TIMEOUT); + } while (!ret); + + if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed) + return; + do { xenbus_switch_state(dev, XenbusStateClosed); - wait_event(module_wq, - xenbus_read_driver_state(dev->otherend) == - XenbusStateClosed || - xenbus_read_driver_state(dev->otherend) == - XenbusStateUnknown); - } + ret = wait_event_timeout(module_wq, + xenbus_read_driver_state(dev->otherend) == + XenbusStateClosed || + xenbus_read_driver_state(dev->otherend) == + XenbusStateUnknown, + XENNET_TIMEOUT); + } while (!ret); +} + +static int xennet_remove(struct xenbus_device *dev) +{ + struct netfront_info *info = dev_get_drvdata(&dev->dev); + xennet_bus_close(dev); xennet_disconnect_backend(info); if (info->netdev->reg_state == NETREG_REGISTERED) diff --git a/drivers/nfc/s3fwrn5/core.c b/drivers/nfc/s3fwrn5/core.c index 91d4d5b28a7d..ba6c486d6465 100644 --- a/drivers/nfc/s3fwrn5/core.c +++ b/drivers/nfc/s3fwrn5/core.c @@ -198,6 +198,7 @@ int s3fwrn5_recv_frame(struct nci_dev *ndev, struct sk_buff *skb, case S3FWRN5_MODE_FW: return s3fwrn5_fw_recv_frame(ndev, skb); default: + kfree_skb(skb); return -ENODEV; } } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index add040168e67..4ee2330c603e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1102,6 +1102,9 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, int pos; int len; + if (ctrl->quirks & NVME_QUIRK_NO_NS_DESC_LIST) + return 0; + c.identify.opcode = nvme_admin_identify; c.identify.nsid = cpu_to_le32(nsid); c.identify.cns = NVME_ID_CNS_NS_DESC_LIST; @@ -1115,18 +1118,6 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, if (status) { dev_warn(ctrl->device, "Identify Descriptors failed (%d)\n", status); - /* - * Don't treat non-retryable errors as fatal, as we potentially - * already have a NGUID or EUI-64. If we failed with DNR set, - * we want to silently ignore the error as we can still - * identify the device, but if the status has DNR set, we want - * to propagate the error back specifically for the disk - * revalidation flow to make sure we don't abandon the - * device just because of a temporal retry-able error (such - * as path of transport errors). - */ - if (status > 0 && (status & NVME_SC_DNR)) - status = 0; goto free_data; } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 1de3f9b827aa..09ffc3246f60 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -129,6 +129,13 @@ enum nvme_quirks { * Don't change the value of the temperature threshold feature */ NVME_QUIRK_NO_TEMP_THRESH_CHANGE = (1 << 14), + + /* + * The controller doesn't handle the Identify Namespace + * Identification Descriptor list subcommand despite claiming + * NVMe 1.3 compliance. + */ + NVME_QUIRK_NO_NS_DESC_LIST = (1 << 15), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index b1d18f0633c7..d4b1ff747123 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3099,6 +3099,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_IDENTIFY_CNS | NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + { PCI_DEVICE(0x126f, 0x2263), /* Silicon Motion unidentified */ + .driver_data = NVME_QUIRK_NO_NS_DESC_LIST, }, { PCI_DEVICE(0x1bb1, 0x0100), /* Seagate Nytro Flash Storage */ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, { PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */ @@ -3122,6 +3124,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(0x1cc1, 0x8201), /* ADATA SX8200PNP 512GB */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_IGNORE_DEV_SUBNQN, }, + { PCI_DEVICE(0x1c5c, 0x1504), /* SK Hynix PC400 */ + .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001), .driver_data = NVME_QUIRK_SINGLE_VECTOR }, diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 79ef2b8e2b3c..f3a91818167b 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1382,6 +1382,9 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, if (nctrl->opts->tos >= 0) ip_sock_set_tos(queue->sock->sk, nctrl->opts->tos); + /* Set 10 seconds timeout for icresp recvmsg */ + queue->sock->sk->sk_rcvtimeo = 10 * HZ; + queue->sock->sk->sk_allocation = GFP_ATOMIC; nvme_tcp_set_queue_io_cpu(queue); queue->request = NULL; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index ce096272f52b..c9338f914a0e 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4638,8 +4638,7 @@ static int pci_pm_reset(struct pci_dev *dev, int probe) * pcie_wait_for_link_delay - Wait until link is active or inactive * @pdev: Bridge device * @active: waiting for active or inactive? - * @delay: Delay to wait after link has become active (in ms). Specify %0 - * for no delay. + * @delay: Delay to wait after link has become active (in ms) * * Use this to wait till link becomes active or inactive. */ @@ -4680,7 +4679,7 @@ static bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, msleep(10); timeout -= 10; } - if (active && ret && delay) + if (active && ret) msleep(delay); else if (ret != active) pci_info(pdev, "Data Link Layer Link Active not %s in 1000 msec\n", @@ -4801,28 +4800,17 @@ void pci_bridge_wait_for_secondary_bus(struct pci_dev *dev) if (!pcie_downstream_port(dev)) return; - /* - * Per PCIe r5.0, sec 6.6.1, for downstream ports that support - * speeds > 5 GT/s, we must wait for link training to complete - * before the mandatory delay. - * - * We can only tell when link training completes via DLL Link - * Active, which is required for downstream ports that support - * speeds > 5 GT/s (sec 7.5.3.6). Unfortunately some common - * devices do not implement Link Active reporting even when it's - * required, so we'll check for that directly instead of checking - * the supported link speed. We assume devices without Link Active - * reporting can train in 100 ms regardless of speed. - */ - if (dev->link_active_reporting) { - pci_dbg(dev, "waiting for link to train\n"); - if (!pcie_wait_for_link_delay(dev, true, 0)) { + if (pcie_get_speed_cap(dev) <= PCIE_SPEED_5_0GT) { + pci_dbg(dev, "waiting %d ms for downstream link\n", delay); + msleep(delay); + } else { + pci_dbg(dev, "waiting %d ms for downstream link, after activation\n", + delay); + if (!pcie_wait_for_link_delay(dev, true, delay)) { /* Did not train, no need to wait any further */ return; } } - pci_dbg(child, "waiting %d ms to become accessible\n", delay); - msleep(delay); if (!pci_device_is_present(child)) { pci_dbg(child, "waiting additional %d ms to become accessible\n", delay); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 812bfc32ecb8..2ea61abd5830 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -2330,6 +2330,19 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f1, quirk_disable_aspm_l0s); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f4, quirk_disable_aspm_l0s); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1508, quirk_disable_aspm_l0s); +static void quirk_disable_aspm_l0s_l1(struct pci_dev *dev) +{ + pci_info(dev, "Disabling ASPM L0s/L1\n"); + pci_disable_link_state(dev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1); +} + +/* + * ASM1083/1085 PCIe-PCI bridge devices cause AER timeout errors on the + * upstream PCIe root port when ASPM is enabled. At least L0s mode is affected; + * disable both L0s and L1 for now to be safe. + */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ASMEDIA, 0x1080, quirk_disable_aspm_l0s_l1); + /* * Some Pericom PCIe-to-PCI bridges in reverse mode need the PCIe Retrain * Link bit cleared after starting the link retrain process to allow this diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig index ff1ee159dca2..f8ff30cdafa6 100644 --- a/drivers/pinctrl/qcom/Kconfig +++ b/drivers/pinctrl/qcom/Kconfig @@ -7,6 +7,8 @@ config PINCTRL_MSM select PINCONF select GENERIC_PINCONF select GPIOLIB_IRQCHIP + select IRQ_DOMAIN_HIERARCHY + select IRQ_FASTEOI_HIERARCHY_HANDLERS config PINCTRL_APQ8064 tristate "Qualcomm APQ8064 pin controller driver" diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 83b7d64bc4c1..c322f30a2064 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -832,6 +832,52 @@ static void msm_gpio_irq_unmask(struct irq_data *d) msm_gpio_irq_clear_unmask(d, false); } +/** + * msm_gpio_update_dual_edge_parent() - Prime next edge for IRQs handled by parent. + * @d: The irq dta. + * + * This is much like msm_gpio_update_dual_edge_pos() but for IRQs that are + * normally handled by the parent irqchip. The logic here is slightly + * different due to what's easy to do with our parent, but in principle it's + * the same. + */ +static void msm_gpio_update_dual_edge_parent(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + const struct msm_pingroup *g = &pctrl->soc->groups[d->hwirq]; + int loop_limit = 100; + unsigned int val; + unsigned int type; + + /* Read the value and make a guess about what edge we need to catch */ + val = msm_readl_io(pctrl, g) & BIT(g->in_bit); + type = val ? IRQ_TYPE_EDGE_FALLING : IRQ_TYPE_EDGE_RISING; + + do { + /* Set the parent to catch the next edge */ + irq_chip_set_type_parent(d, type); + + /* + * Possibly the line changed between when we last read "val" + * (and decided what edge we needed) and when set the edge. + * If the value didn't change (or changed and then changed + * back) then we're done. + */ + val = msm_readl_io(pctrl, g) & BIT(g->in_bit); + if (type == IRQ_TYPE_EDGE_RISING) { + if (!val) + return; + type = IRQ_TYPE_EDGE_FALLING; + } else if (type == IRQ_TYPE_EDGE_FALLING) { + if (val) + return; + type = IRQ_TYPE_EDGE_RISING; + } + } while (loop_limit-- > 0); + dev_warn_once(pctrl->dev, "dual-edge irq failed to stabilize\n"); +} + static void msm_gpio_irq_ack(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); @@ -840,8 +886,11 @@ static void msm_gpio_irq_ack(struct irq_data *d) unsigned long flags; u32 val; - if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) + if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) { + if (test_bit(d->hwirq, pctrl->dual_edge_irqs)) + msm_gpio_update_dual_edge_parent(d); return; + } g = &pctrl->soc->groups[d->hwirq]; @@ -860,6 +909,17 @@ static void msm_gpio_irq_ack(struct irq_data *d) raw_spin_unlock_irqrestore(&pctrl->lock, flags); } +static bool msm_gpio_needs_dual_edge_parent_workaround(struct irq_data *d, + unsigned int type) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + + return type == IRQ_TYPE_EDGE_BOTH && + pctrl->soc->wakeirq_dual_edge_errata && d->parent_data && + test_bit(d->hwirq, pctrl->skip_wake_irqs); +} + static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); @@ -868,11 +928,21 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type) unsigned long flags; u32 val; + if (msm_gpio_needs_dual_edge_parent_workaround(d, type)) { + set_bit(d->hwirq, pctrl->dual_edge_irqs); + irq_set_handler_locked(d, handle_fasteoi_ack_irq); + msm_gpio_update_dual_edge_parent(d); + return 0; + } + if (d->parent_data) irq_chip_set_type_parent(d, type); - if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) + if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) { + clear_bit(d->hwirq, pctrl->dual_edge_irqs); + irq_set_handler_locked(d, handle_fasteoi_irq); return 0; + } g = &pctrl->soc->groups[d->hwirq]; diff --git a/drivers/pinctrl/qcom/pinctrl-msm.h b/drivers/pinctrl/qcom/pinctrl-msm.h index 9452da18a78b..7486fe08eb9b 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.h +++ b/drivers/pinctrl/qcom/pinctrl-msm.h @@ -113,6 +113,9 @@ struct msm_gpio_wakeirq_map { * @pull_no_keeper: The SoC does not support keeper bias. * @wakeirq_map: The map of wakeup capable GPIOs and the pin at PDC/MPM * @nwakeirq_map: The number of entries in @wakeirq_map + * @wakeirq_dual_edge_errata: If true then GPIOs using the wakeirq_map need + * to be aware that their parent can't handle dual + * edge interrupts. */ struct msm_pinctrl_soc_data { const struct pinctrl_pin_desc *pins; @@ -128,6 +131,7 @@ struct msm_pinctrl_soc_data { const int *reserved_gpios; const struct msm_gpio_wakeirq_map *wakeirq_map; unsigned int nwakeirq_map; + bool wakeirq_dual_edge_errata; }; extern const struct dev_pm_ops msm_pinctrl_dev_pm_ops; diff --git a/drivers/pinctrl/qcom/pinctrl-sc7180.c b/drivers/pinctrl/qcom/pinctrl-sc7180.c index 1b6465a882f2..1d9acad3c1ce 100644 --- a/drivers/pinctrl/qcom/pinctrl-sc7180.c +++ b/drivers/pinctrl/qcom/pinctrl-sc7180.c @@ -1147,6 +1147,7 @@ static const struct msm_pinctrl_soc_data sc7180_pinctrl = { .ntiles = ARRAY_SIZE(sc7180_tiles), .wakeirq_map = sc7180_pdc_map, .nwakeirq_map = ARRAY_SIZE(sc7180_pdc_map), + .wakeirq_dual_edge_errata = true, }; static int sc7180_pinctrl_probe(struct platform_device *pdev) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 0ba7a65e7c8d..06056e9ec333 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -547,6 +547,15 @@ static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd) scsi_uninit_cmd(cmd); } +static void scsi_run_queue_async(struct scsi_device *sdev) +{ + if (scsi_target(sdev)->single_lun || + !list_empty(&sdev->host->starved_list)) + kblockd_schedule_work(&sdev->requeue_work); + else + blk_mq_run_hw_queues(sdev->request_queue, true); +} + /* Returns false when no more bytes to process, true if there are more */ static bool scsi_end_request(struct request *req, blk_status_t error, unsigned int bytes) @@ -591,11 +600,7 @@ static bool scsi_end_request(struct request *req, blk_status_t error, __blk_mq_end_request(req, error); - if (scsi_target(sdev)->single_lun || - !list_empty(&sdev->host->starved_list)) - kblockd_schedule_work(&sdev->requeue_work); - else - blk_mq_run_hw_queues(q, true); + scsi_run_queue_async(sdev); percpu_ref_put(&q->q_usage_counter); return false; @@ -1702,6 +1707,7 @@ out_put_budget: */ if (req->rq_flags & RQF_DONTPREP) scsi_mq_uninit_cmd(cmd); + scsi_run_queue_async(sdev); break; } return ret; diff --git a/drivers/staging/comedi/drivers/addi_apci_1032.c b/drivers/staging/comedi/drivers/addi_apci_1032.c index 560649be9d13..e035c9f757a1 100644 --- a/drivers/staging/comedi/drivers/addi_apci_1032.c +++ b/drivers/staging/comedi/drivers/addi_apci_1032.c @@ -106,14 +106,22 @@ static int apci1032_cos_insn_config(struct comedi_device *dev, unsigned int *data) { struct apci1032_private *devpriv = dev->private; - unsigned int shift, oldmask; + unsigned int shift, oldmask, himask, lomask; switch (data[0]) { case INSN_CONFIG_DIGITAL_TRIG: if (data[1] != 0) return -EINVAL; shift = data[3]; - oldmask = (1U << shift) - 1; + if (shift < 32) { + oldmask = (1U << shift) - 1; + himask = data[4] << shift; + lomask = data[5] << shift; + } else { + oldmask = 0xffffffffu; + himask = 0; + lomask = 0; + } switch (data[2]) { case COMEDI_DIGITAL_TRIG_DISABLE: devpriv->ctrl = 0; @@ -136,8 +144,8 @@ static int apci1032_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; case COMEDI_DIGITAL_TRIG_ENABLE_LEVELS: if (devpriv->ctrl != (APCI1032_CTRL_INT_ENA | @@ -154,8 +162,8 @@ static int apci1032_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; default: return -EINVAL; diff --git a/drivers/staging/comedi/drivers/addi_apci_1500.c b/drivers/staging/comedi/drivers/addi_apci_1500.c index 689acd69a1b9..816dd25b9d0e 100644 --- a/drivers/staging/comedi/drivers/addi_apci_1500.c +++ b/drivers/staging/comedi/drivers/addi_apci_1500.c @@ -452,13 +452,14 @@ static int apci1500_di_cfg_trig(struct comedi_device *dev, struct apci1500_private *devpriv = dev->private; unsigned int trig = data[1]; unsigned int shift = data[3]; - unsigned int hi_mask = data[4] << shift; - unsigned int lo_mask = data[5] << shift; - unsigned int chan_mask = hi_mask | lo_mask; - unsigned int old_mask = (1 << shift) - 1; + unsigned int hi_mask; + unsigned int lo_mask; + unsigned int chan_mask; + unsigned int old_mask; unsigned int pm; unsigned int pt; unsigned int pp; + unsigned int invalid_chan; if (trig > 1) { dev_dbg(dev->class_dev, @@ -466,7 +467,20 @@ static int apci1500_di_cfg_trig(struct comedi_device *dev, return -EINVAL; } - if (chan_mask > 0xffff) { + if (shift <= 16) { + hi_mask = data[4] << shift; + lo_mask = data[5] << shift; + old_mask = (1U << shift) - 1; + invalid_chan = (data[4] | data[5]) >> (16 - shift); + } else { + hi_mask = 0; + lo_mask = 0; + old_mask = 0xffff; + invalid_chan = data[4] | data[5]; + } + chan_mask = hi_mask | lo_mask; + + if (invalid_chan) { dev_dbg(dev->class_dev, "invalid digital trigger channel\n"); return -EINVAL; } diff --git a/drivers/staging/comedi/drivers/addi_apci_1564.c b/drivers/staging/comedi/drivers/addi_apci_1564.c index 10501fe6bb25..1268ba34be5f 100644 --- a/drivers/staging/comedi/drivers/addi_apci_1564.c +++ b/drivers/staging/comedi/drivers/addi_apci_1564.c @@ -331,14 +331,22 @@ static int apci1564_cos_insn_config(struct comedi_device *dev, unsigned int *data) { struct apci1564_private *devpriv = dev->private; - unsigned int shift, oldmask; + unsigned int shift, oldmask, himask, lomask; switch (data[0]) { case INSN_CONFIG_DIGITAL_TRIG: if (data[1] != 0) return -EINVAL; shift = data[3]; - oldmask = (1U << shift) - 1; + if (shift < 32) { + oldmask = (1U << shift) - 1; + himask = data[4] << shift; + lomask = data[5] << shift; + } else { + oldmask = 0xffffffffu; + himask = 0; + lomask = 0; + } switch (data[2]) { case COMEDI_DIGITAL_TRIG_DISABLE: devpriv->ctrl = 0; @@ -362,8 +370,8 @@ static int apci1564_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; case COMEDI_DIGITAL_TRIG_ENABLE_LEVELS: if (devpriv->ctrl != (APCI1564_DI_IRQ_ENA | @@ -380,8 +388,8 @@ static int apci1564_cos_insn_config(struct comedi_device *dev, devpriv->mode2 &= oldmask; } /* configure specified channels */ - devpriv->mode1 |= data[4] << shift; - devpriv->mode2 |= data[5] << shift; + devpriv->mode1 |= himask; + devpriv->mode2 |= lomask; break; default: return -EINVAL; diff --git a/drivers/staging/comedi/drivers/ni_6527.c b/drivers/staging/comedi/drivers/ni_6527.c index 4d1eccb5041d..4518c2680b7c 100644 --- a/drivers/staging/comedi/drivers/ni_6527.c +++ b/drivers/staging/comedi/drivers/ni_6527.c @@ -332,7 +332,7 @@ static int ni6527_intr_insn_config(struct comedi_device *dev, case COMEDI_DIGITAL_TRIG_ENABLE_EDGES: /* check shift amount */ shift = data[3]; - if (shift >= s->n_chan) { + if (shift >= 32) { mask = 0; rising = 0; falling = 0; diff --git a/drivers/staging/media/atomisp/Kconfig b/drivers/staging/media/atomisp/Kconfig index fea06cb0eb48..37577bb72998 100644 --- a/drivers/staging/media/atomisp/Kconfig +++ b/drivers/staging/media/atomisp/Kconfig @@ -22,7 +22,7 @@ config VIDEO_ATOMISP module will be called atomisp config VIDEO_ATOMISP_ISP2401 - bool "VIDEO_ATOMISP_ISP2401" + bool "Use Intel Atom ISP on Cherrytail/Anniedale (ISP2401)" depends on VIDEO_ATOMISP help Enable support for Atom ISP2401-based boards. diff --git a/drivers/staging/media/atomisp/Makefile b/drivers/staging/media/atomisp/Makefile index 9dc8072799e3..205d0f8cc2e1 100644 --- a/drivers/staging/media/atomisp/Makefile +++ b/drivers/staging/media/atomisp/Makefile @@ -156,6 +156,7 @@ atomisp-objs += \ pci/hive_isp_css_common/host/timed_ctrl.o \ pci/hive_isp_css_common/host/vmem.o \ pci/hive_isp_css_shared/host/tag.o \ + pci/system_local.o \ obj-byt = \ pci/css_2400_system/hive/ia_css_isp_configs.o \ @@ -182,7 +183,6 @@ INCLUDES += \ -I$(atomisp)/include/hmm/ \ -I$(atomisp)/include/mmu/ \ -I$(atomisp)/pci/ \ - -I$(atomisp)/pci/hrt/ \ -I$(atomisp)/pci/base/circbuf/interface/ \ -I$(atomisp)/pci/base/refcount/interface/ \ -I$(atomisp)/pci/camera/pipe/interface/ \ @@ -192,7 +192,6 @@ INCLUDES += \ -I$(atomisp)/pci/hive_isp_css_include/ \ -I$(atomisp)/pci/hive_isp_css_include/device_access/ \ -I$(atomisp)/pci/hive_isp_css_include/host/ \ - -I$(atomisp)/pci/hive_isp_css_include/memory_access/ \ -I$(atomisp)/pci/hive_isp_css_shared/ \ -I$(atomisp)/pci/hive_isp_css_shared/host/ \ -I$(atomisp)/pci/isp/kernels/ \ @@ -311,9 +310,7 @@ INCLUDES += \ -I$(atomisp)/pci/runtime/tagger/interface/ INCLUDES_byt += \ - -I$(atomisp)/pci/css_2400_system/ \ -I$(atomisp)/pci/css_2400_system/hive/ \ - -I$(atomisp)/pci/css_2400_system/hrt/ \ INCLUDES_cht += \ -I$(atomisp)/pci/css_2401_system/ \ @@ -321,7 +318,6 @@ INCLUDES_cht += \ -I$(atomisp)/pci/css_2401_system/hive/ \ -I$(atomisp)/pci/css_2401_system/hrt/ \ -# -I$(atomisp)/pci/css_2401_system/hrt/ \ # -I$(atomisp)/pci/css_2401_system/hive_isp_css_2401_system_generated/ \ DEFINES := -DHRT_HW -DHRT_ISP_CSS_CUSTOM_HOST -DHRT_USE_VIR_ADDRS -D__HOST__ diff --git a/drivers/staging/media/atomisp/i2c/atomisp-ov2680.c b/drivers/staging/media/atomisp/i2c/atomisp-ov2680.c index 90d125ba080f..c90730513438 100644 --- a/drivers/staging/media/atomisp/i2c/atomisp-ov2680.c +++ b/drivers/staging/media/atomisp/i2c/atomisp-ov2680.c @@ -495,11 +495,11 @@ static int ov2680_h_flip(struct v4l2_subdev *sd, s32 value) ret = ov2680_read_reg(client, 1, OV2680_MIRROR_REG, &val); if (ret) return ret; - if (value) { + if (value) val |= OV2680_FLIP_MIRROR_BIT_ENABLE; - } else { + else val &= ~OV2680_FLIP_MIRROR_BIT_ENABLE; - } + ret = ov2680_write_reg(client, 1, OV2680_MIRROR_REG, val); if (ret) diff --git a/drivers/staging/media/atomisp/i2c/ov5693/atomisp-ov5693.c b/drivers/staging/media/atomisp/i2c/ov5693/atomisp-ov5693.c index 97ab10bc45ca..e698b63d6cb7 100644 --- a/drivers/staging/media/atomisp/i2c/ov5693/atomisp-ov5693.c +++ b/drivers/staging/media/atomisp/i2c/ov5693/atomisp-ov5693.c @@ -1899,7 +1899,7 @@ static int ov5693_probe(struct i2c_client *client) { struct ov5693_device *dev; int i2c; - int ret = 0; + int ret; void *pdata; unsigned int i; @@ -1929,8 +1929,10 @@ static int ov5693_probe(struct i2c_client *client) pdata = gmin_camera_platform_data(&dev->sd, ATOMISP_INPUT_FORMAT_RAW_10, atomisp_bayer_order_bggr); - if (!pdata) + if (!pdata) { + ret = -EINVAL; goto out_free; + } ret = ov5693_s_config(&dev->sd, client->irq, pdata); if (ret) diff --git a/drivers/staging/media/atomisp/include/linux/atomisp_platform.h b/drivers/staging/media/atomisp/include/linux/atomisp_platform.h index 873344a02ccf..5a5121d958ed 100644 --- a/drivers/staging/media/atomisp/include/linux/atomisp_platform.h +++ b/drivers/staging/media/atomisp/include/linux/atomisp_platform.h @@ -250,6 +250,7 @@ const struct atomisp_camera_caps *atomisp_get_default_camera_caps(void); #define IS_MFLD __IS_SOC(INTEL_FAM6_ATOM_SALTWELL_MID) #define IS_BYT __IS_SOC(INTEL_FAM6_ATOM_SILVERMONT) #define IS_CHT __IS_SOC(INTEL_FAM6_ATOM_AIRMONT) +#define IS_MRFD __IS_SOC(INTEL_FAM6_ATOM_SILVERMONT_MID) #define IS_MOFD __IS_SOC(INTEL_FAM6_ATOM_AIRMONT_MID) /* Both CHT and MOFD come with ISP2401 */ diff --git a/drivers/staging/media/atomisp/pci/atomisp-regs.h b/drivers/staging/media/atomisp/pci/atomisp-regs.h index de34ee28e390..022997f47121 100644 --- a/drivers/staging/media/atomisp/pci/atomisp-regs.h +++ b/drivers/staging/media/atomisp/pci/atomisp-regs.h @@ -20,9 +20,6 @@ #define ATOMISP_REGS_H /* common register definitions */ -#define PUNIT_PORT 0x04 -#define CCK_PORT 0x14 - #define PCICMDSTS 0x01 #define INTR 0x0f #define MSI_CAPID 0x24 diff --git a/drivers/staging/media/atomisp/pci/atomisp_acc.c b/drivers/staging/media/atomisp/pci/atomisp_acc.c index 76861396ba86..f638d0bd09fe 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_acc.c +++ b/drivers/staging/media/atomisp/pci/atomisp_acc.c @@ -355,11 +355,11 @@ int atomisp_acc_map(struct atomisp_sub_device *asd, struct atomisp_acc_map *map) pgnr = DIV_ROUND_UP(map->length, PAGE_SIZE); if (pgnr < ((PAGE_ALIGN(map->length)) >> PAGE_SHIFT)) { - dev_err(atomisp_dev, + dev_err(asd->isp->dev, "user space memory size is less than the expected size..\n"); return -ENOMEM; } else if (pgnr > ((PAGE_ALIGN(map->length)) >> PAGE_SHIFT)) { - dev_err(atomisp_dev, + dev_err(asd->isp->dev, "user space memory size is large than the expected size..\n"); return -ENOMEM; } diff --git a/drivers/staging/media/atomisp/pci/atomisp_cmd.c b/drivers/staging/media/atomisp/pci/atomisp_cmd.c index 7b936e5a5f03..8ea65bef35d2 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_cmd.c +++ b/drivers/staging/media/atomisp/pci/atomisp_cmd.c @@ -21,6 +21,7 @@ #include <linux/firmware.h> #include <linux/pci.h> #include <linux/interrupt.h> +#include <linux/io.h> #include <linux/kernel.h> #include <linux/kfifo.h> #include <linux/pm_runtime.h> @@ -109,7 +110,7 @@ struct atomisp_acc_pipe *atomisp_to_acc_pipe(struct video_device *dev) static unsigned short atomisp_get_sensor_fps(struct atomisp_sub_device *asd) { - struct v4l2_subdev_frame_interval fi; + struct v4l2_subdev_frame_interval fi = { 0 }; struct atomisp_device *isp = asd->isp; unsigned short fps = 0; @@ -206,6 +207,7 @@ int atomisp_freq_scaling(struct atomisp_device *isp, enum atomisp_dfs_mode mode, bool force) { + struct pci_dev *pdev = to_pci_dev(isp->dev); /* FIXME! Only use subdev[0] status yet */ struct atomisp_sub_device *asd = &isp->asd[0]; const struct atomisp_dfs_config *dfs; @@ -219,7 +221,7 @@ int atomisp_freq_scaling(struct atomisp_device *isp, return -EINVAL; } - if ((isp->pdev->device & ATOMISP_PCI_DEVICE_SOC_MASK) == + if ((pdev->device & ATOMISP_PCI_DEVICE_SOC_MASK) == ATOMISP_PCI_DEVICE_SOC_CHT && ATOMISP_USE_YUVPP(asd)) isp->dfs = &dfs_config_cht_soc; @@ -357,39 +359,41 @@ static void clear_isp_irq(enum hrt_isp_css_irq irq) irq_clear_all(IRQ0_ID); } -void atomisp_msi_irq_init(struct atomisp_device *isp, struct pci_dev *dev) +void atomisp_msi_irq_init(struct atomisp_device *isp) { + struct pci_dev *pdev = to_pci_dev(isp->dev); u32 msg32; u16 msg16; - pci_read_config_dword(dev, PCI_MSI_CAPID, &msg32); + pci_read_config_dword(pdev, PCI_MSI_CAPID, &msg32); msg32 |= 1 << MSI_ENABLE_BIT; - pci_write_config_dword(dev, PCI_MSI_CAPID, msg32); + pci_write_config_dword(pdev, PCI_MSI_CAPID, msg32); msg32 = (1 << INTR_IER) | (1 << INTR_IIR); - pci_write_config_dword(dev, PCI_INTERRUPT_CTRL, msg32); + pci_write_config_dword(pdev, PCI_INTERRUPT_CTRL, msg32); - pci_read_config_word(dev, PCI_COMMAND, &msg16); + pci_read_config_word(pdev, PCI_COMMAND, &msg16); msg16 |= (PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER | PCI_COMMAND_INTX_DISABLE); - pci_write_config_word(dev, PCI_COMMAND, msg16); + pci_write_config_word(pdev, PCI_COMMAND, msg16); } -void atomisp_msi_irq_uninit(struct atomisp_device *isp, struct pci_dev *dev) +void atomisp_msi_irq_uninit(struct atomisp_device *isp) { + struct pci_dev *pdev = to_pci_dev(isp->dev); u32 msg32; u16 msg16; - pci_read_config_dword(dev, PCI_MSI_CAPID, &msg32); + pci_read_config_dword(pdev, PCI_MSI_CAPID, &msg32); msg32 &= ~(1 << MSI_ENABLE_BIT); - pci_write_config_dword(dev, PCI_MSI_CAPID, msg32); + pci_write_config_dword(pdev, PCI_MSI_CAPID, msg32); msg32 = 0x0; - pci_write_config_dword(dev, PCI_INTERRUPT_CTRL, msg32); + pci_write_config_dword(pdev, PCI_INTERRUPT_CTRL, msg32); - pci_read_config_word(dev, PCI_COMMAND, &msg16); + pci_read_config_word(pdev, PCI_COMMAND, &msg16); msg16 &= ~(PCI_COMMAND_MASTER); - pci_write_config_word(dev, PCI_COMMAND, msg16); + pci_write_config_word(pdev, PCI_COMMAND, msg16); } static void atomisp_sof_event(struct atomisp_sub_device *asd) @@ -480,11 +484,12 @@ static void print_csi_rx_errors(enum mipi_port_id port, /* Clear irq reg */ static void clear_irq_reg(struct atomisp_device *isp) { + struct pci_dev *pdev = to_pci_dev(isp->dev); u32 msg_ret; - pci_read_config_dword(isp->pdev, PCI_INTERRUPT_CTRL, &msg_ret); + pci_read_config_dword(pdev, PCI_INTERRUPT_CTRL, &msg_ret); msg_ret |= 1 << INTR_IIR; - pci_write_config_dword(isp->pdev, PCI_INTERRUPT_CTRL, msg_ret); + pci_write_config_dword(pdev, PCI_INTERRUPT_CTRL, msg_ret); } static struct atomisp_sub_device * @@ -665,11 +670,10 @@ bool atomisp_buffers_queued_pipe(struct atomisp_video_pipe *pipe) void dump_sp_dmem(struct atomisp_device *isp, unsigned int addr, unsigned int size) { - u32 __iomem *io_virt_addr; unsigned int data = 0; unsigned int size32 = DIV_ROUND_UP(size, sizeof(u32)); - dev_dbg(isp->dev, "atomisp_io_base:%p\n", atomisp_io_base); + dev_dbg(isp->dev, "atomisp mmio base: %p\n", isp->base); dev_dbg(isp->dev, "%s, addr:0x%x, size: %d, size32: %d\n", __func__, addr, size, size32); if (size32 * 4 + addr > 0x4000) { @@ -678,13 +682,12 @@ void dump_sp_dmem(struct atomisp_device *isp, unsigned int addr, return; } addr += SP_DMEM_BASE; - io_virt_addr = atomisp_io_base + (addr & 0x003FFFFF); + addr &= 0x003FFFFF; do { - data = *io_virt_addr; + data = readl(isp->base + addr); dev_dbg(isp->dev, "%s, \t [0x%x]:0x%x\n", __func__, addr, data); - io_virt_addr += sizeof(u32); - size32 -= 1; - } while (size32 > 0); + addr += sizeof(u32); + } while (--size32); } static struct videobuf_buffer *atomisp_css_frame_to_vbuf( @@ -1289,6 +1292,7 @@ void atomisp_delayed_init_work(struct work_struct *work) static void __atomisp_css_recover(struct atomisp_device *isp, bool isp_timeout) { + struct pci_dev *pdev = to_pci_dev(isp->dev); enum ia_css_pipe_id css_pipe_id; bool stream_restart[MAX_STREAM_NUM] = {0}; bool depth_mode = false; @@ -1372,8 +1376,8 @@ static void __atomisp_css_recover(struct atomisp_device *isp, bool isp_timeout) clear_isp_irq(hrt_isp_css_irq_sp); /* Set the SRSE to 3 before resetting */ - pci_write_config_dword(isp->pdev, PCI_I_CONTROL, isp->saved_regs.i_control | - MRFLD_PCI_I_CONTROL_SRSE_RESET_MASK); + pci_write_config_dword(pdev, PCI_I_CONTROL, + isp->saved_regs.i_control | MRFLD_PCI_I_CONTROL_SRSE_RESET_MASK); /* reset ISP and restore its state */ isp->isp_timeout = true; @@ -6158,6 +6162,7 @@ out: /*Turn off ISP dphy */ int atomisp_ospm_dphy_down(struct atomisp_device *isp) { + struct pci_dev *pdev = to_pci_dev(isp->dev); unsigned long flags; u32 reg; @@ -6179,9 +6184,9 @@ done: * MRFLD HW design need all CSI ports are disabled before * powering down the IUNIT. */ - pci_read_config_dword(isp->pdev, MRFLD_PCI_CSI_CONTROL, ®); + pci_read_config_dword(pdev, MRFLD_PCI_CSI_CONTROL, ®); reg |= MRFLD_ALL_CSI_PORTS_OFF_MASK; - pci_write_config_dword(isp->pdev, MRFLD_PCI_CSI_CONTROL, reg); + pci_write_config_dword(pdev, MRFLD_PCI_CSI_CONTROL, reg); return 0; } diff --git a/drivers/staging/media/atomisp/pci/atomisp_cmd.h b/drivers/staging/media/atomisp/pci/atomisp_cmd.h index 0bde995f1a8d..1c0d464c2ac1 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_cmd.h +++ b/drivers/staging/media/atomisp/pci/atomisp_cmd.h @@ -68,8 +68,8 @@ bool atomisp_buffers_queued_pipe(struct atomisp_video_pipe *pipe); /* * Interrupt functions */ -void atomisp_msi_irq_init(struct atomisp_device *isp, struct pci_dev *dev); -void atomisp_msi_irq_uninit(struct atomisp_device *isp, struct pci_dev *dev); +void atomisp_msi_irq_init(struct atomisp_device *isp); +void atomisp_msi_irq_uninit(struct atomisp_device *isp); void atomisp_wdt_work(struct work_struct *work); void atomisp_wdt(struct timer_list *t); void atomisp_setup_flash(struct atomisp_sub_device *asd); diff --git a/drivers/staging/media/atomisp/pci/atomisp_compat.h b/drivers/staging/media/atomisp/pci/atomisp_compat.h index b2ed83c2f337..6a2a81a3eb23 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_compat.h +++ b/drivers/staging/media/atomisp/pci/atomisp_compat.h @@ -29,8 +29,6 @@ struct atomisp_sub_device; struct video_device; enum atomisp_input_stream_id; -extern void __iomem *atomisp_io_base; - struct atomisp_metadata_buf { struct ia_css_metadata *metadata; void *md_vptr; diff --git a/drivers/staging/media/atomisp/pci/atomisp_compat_css20.c b/drivers/staging/media/atomisp/pci/atomisp_compat_css20.c index c1e282a974d0..cccc5bfa1057 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_compat_css20.c +++ b/drivers/staging/media/atomisp/pci/atomisp_compat_css20.c @@ -33,13 +33,12 @@ #include "atomisp_ioctl.h" #include "atomisp_acc.h" -#include <asm/intel-mid.h> - #include "ia_css_debug.h" #include "ia_css_isp_param.h" #include "sh_css_hrt.h" #include "ia_css_isys.h" +#include <linux/io.h> #include <linux/pm_runtime.h> /* Assume max number of ACC stages */ @@ -69,92 +68,94 @@ struct bayer_ds_factor { static void atomisp_css2_hw_store_8(hrt_address addr, uint8_t data) { - s8 __iomem *io_virt_addr = atomisp_io_base + (addr & 0x003FFFFF); + struct atomisp_device *isp = dev_get_drvdata(atomisp_dev); unsigned long flags; spin_lock_irqsave(&mmio_lock, flags); - *io_virt_addr = data; + writeb(data, isp->base + (addr & 0x003FFFFF)); spin_unlock_irqrestore(&mmio_lock, flags); } static void atomisp_css2_hw_store_16(hrt_address addr, uint16_t data) { - s16 __iomem *io_virt_addr = atomisp_io_base + (addr & 0x003FFFFF); + struct atomisp_device *isp = dev_get_drvdata(atomisp_dev); unsigned long flags; spin_lock_irqsave(&mmio_lock, flags); - *io_virt_addr = data; + writew(data, isp->base + (addr & 0x003FFFFF)); spin_unlock_irqrestore(&mmio_lock, flags); } void atomisp_css2_hw_store_32(hrt_address addr, uint32_t data) { - s32 __iomem *io_virt_addr = atomisp_io_base + (addr & 0x003FFFFF); + struct atomisp_device *isp = dev_get_drvdata(atomisp_dev); unsigned long flags; spin_lock_irqsave(&mmio_lock, flags); - *io_virt_addr = data; + writel(data, isp->base + (addr & 0x003FFFFF)); spin_unlock_irqrestore(&mmio_lock, flags); } static uint8_t atomisp_css2_hw_load_8(hrt_address addr) { - s8 __iomem *io_virt_addr = atomisp_io_base + (addr & 0x003FFFFF); + struct atomisp_device *isp = dev_get_drvdata(atomisp_dev); unsigned long flags; u8 ret; spin_lock_irqsave(&mmio_lock, flags); - ret = *io_virt_addr; + ret = readb(isp->base + (addr & 0x003FFFFF)); spin_unlock_irqrestore(&mmio_lock, flags); return ret; } static uint16_t atomisp_css2_hw_load_16(hrt_address addr) { - s16 __iomem *io_virt_addr = atomisp_io_base + (addr & 0x003FFFFF); + struct atomisp_device *isp = dev_get_drvdata(atomisp_dev); unsigned long flags; u16 ret; spin_lock_irqsave(&mmio_lock, flags); - ret = *io_virt_addr; + ret = readw(isp->base + (addr & 0x003FFFFF)); spin_unlock_irqrestore(&mmio_lock, flags); return ret; } static uint32_t atomisp_css2_hw_load_32(hrt_address addr) { - s32 __iomem *io_virt_addr = atomisp_io_base + (addr & 0x003FFFFF); + struct atomisp_device *isp = dev_get_drvdata(atomisp_dev); unsigned long flags; u32 ret; spin_lock_irqsave(&mmio_lock, flags); - ret = *io_virt_addr; + ret = readl(isp->base + (addr & 0x003FFFFF)); spin_unlock_irqrestore(&mmio_lock, flags); return ret; } -static void atomisp_css2_hw_store(hrt_address addr, - const void *from, uint32_t n) +static void atomisp_css2_hw_store(hrt_address addr, const void *from, uint32_t n) { - s8 __iomem *io_virt_addr = atomisp_io_base + (addr & 0x003FFFFF); + struct atomisp_device *isp = dev_get_drvdata(atomisp_dev); unsigned long flags; unsigned int i; + addr &= 0x003FFFFF; spin_lock_irqsave(&mmio_lock, flags); - for (i = 0; i < n; i++, io_virt_addr++, from++) - *io_virt_addr = *(s8 *)from; + for (i = 0; i < n; i++, from++) + writeb(*(s8 *)from, isp->base + addr + i); + spin_unlock_irqrestore(&mmio_lock, flags); } static void atomisp_css2_hw_load(hrt_address addr, void *to, uint32_t n) { - s8 __iomem *io_virt_addr = atomisp_io_base + (addr & 0x003FFFFF); + struct atomisp_device *isp = dev_get_drvdata(atomisp_dev); unsigned long flags; unsigned int i; + addr &= 0x003FFFFF; spin_lock_irqsave(&mmio_lock, flags); - for (i = 0; i < n; i++, to++, io_virt_addr++) - *(s8 *)to = *io_virt_addr; + for (i = 0; i < n; i++, to++) + *(s8 *)to = readb(isp->base + addr + i); spin_unlock_irqrestore(&mmio_lock, flags); } @@ -181,10 +182,10 @@ void atomisp_load_uint32(hrt_address addr, uint32_t *data) *data = atomisp_css2_hw_load_32(addr); } -static int hmm_get_mmu_base_addr(unsigned int *mmu_base_addr) +static int hmm_get_mmu_base_addr(struct device *dev, unsigned int *mmu_base_addr) { if (!sh_mmu_mrfld.get_pd_base) { - dev_err(atomisp_dev, "get mmu base address failed.\n"); + dev_err(dev, "get mmu base address failed.\n"); return -EINVAL; } @@ -839,7 +840,7 @@ int atomisp_css_init(struct atomisp_device *isp) int ret; int err; - ret = hmm_get_mmu_base_addr(&mmu_base_addr); + ret = hmm_get_mmu_base_addr(isp->dev, &mmu_base_addr); if (ret) return ret; @@ -941,7 +942,7 @@ int atomisp_css_resume(struct atomisp_device *isp) unsigned int mmu_base_addr; int ret; - ret = hmm_get_mmu_base_addr(&mmu_base_addr); + ret = hmm_get_mmu_base_addr(isp->dev, &mmu_base_addr); if (ret) { dev_err(isp->dev, "get base address error.\n"); return -EINVAL; @@ -1966,8 +1967,7 @@ void atomisp_css_input_set_mode(struct atomisp_sub_device *asd, true, 0x13000, &size_mem_words) != 0) { - if (intel_mid_identify_cpu() == - INTEL_MID_CPU_CHIP_TANGIER) + if (IS_MRFD) size_mem_words = CSS_MIPI_FRAME_BUFFER_SIZE_2; else size_mem_words = CSS_MIPI_FRAME_BUFFER_SIZE_1; @@ -2414,13 +2414,13 @@ static void __configure_preview_pp_input(struct atomisp_sub_device *asd, struct ia_css_resolution *effective_res = &stream_config->input_config.effective_res; - const struct bayer_ds_factor bds_fct[] = {{2, 1}, {3, 2}, {5, 4} }; + static const struct bayer_ds_factor bds_fct[] = {{2, 1}, {3, 2}, {5, 4} }; /* * BZ201033: YUV decimation factor of 4 causes couple of rightmost * columns to be shaded. Remove this factor to work around the CSS bug. * const unsigned int yuv_dec_fct[] = {4, 2}; */ - const unsigned int yuv_dec_fct[] = { 2 }; + static const unsigned int yuv_dec_fct[] = { 2 }; unsigned int i; if (width == 0 && height == 0) @@ -2540,7 +2540,7 @@ static void __configure_video_pp_input(struct atomisp_sub_device *asd, struct ia_css_resolution *effective_res = &stream_config->input_config.effective_res; - const struct bayer_ds_factor bds_factors[] = { + static const struct bayer_ds_factor bds_factors[] = { {8, 1}, {6, 1}, {4, 1}, {3, 1}, {2, 1}, {3, 2} }; unsigned int i; @@ -4337,7 +4337,7 @@ static const char * const fw_acc_type_name[] = { [IA_CSS_ACC_STANDALONE] = "Stand-alone acceleration", }; -int atomisp_css_dump_blob_infor(void) +int atomisp_css_dump_blob_infor(struct atomisp_device *isp) { struct ia_css_blob_descr *bd = sh_css_blob_info; unsigned int i, nm = sh_css_num_binaries; @@ -4354,8 +4354,7 @@ int atomisp_css_dump_blob_infor(void) for (i = 0; i < sh_css_num_binaries - NUM_OF_SPS; i++) { switch (bd[i].header.type) { case ia_css_isp_firmware: - dev_dbg(atomisp_dev, - "Num%2d type %s (%s), binary id is %2d, name is %s\n", + dev_dbg(isp->dev, "Num%2d type %s (%s), binary id is %2d, name is %s\n", i + NUM_OF_SPS, fw_type_name[bd[i].header.type], fw_acc_type_name[bd[i].header.info.isp.type], @@ -4363,8 +4362,7 @@ int atomisp_css_dump_blob_infor(void) bd[i].name); break; default: - dev_dbg(atomisp_dev, - "Num%2d type %s, name is %s\n", + dev_dbg(isp->dev, "Num%2d type %s, name is %s\n", i + NUM_OF_SPS, fw_type_name[bd[i].header.type], bd[i].name); } diff --git a/drivers/staging/media/atomisp/pci/atomisp_compat_css20.h b/drivers/staging/media/atomisp/pci/atomisp_compat_css20.h index 8376aec18e3e..e0601534380f 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_compat_css20.h +++ b/drivers/staging/media/atomisp/pci/atomisp_compat_css20.h @@ -153,7 +153,7 @@ int atomisp_css_debug_dump_isp_binary(void); int atomisp_css_dump_sp_raw_copy_linecount(bool reduced); -int atomisp_css_dump_blob_infor(void); +int atomisp_css_dump_blob_infor(struct atomisp_device *isp); void atomisp_css_set_isp_config_id(struct atomisp_sub_device *asd, uint32_t isp_config_id); diff --git a/drivers/staging/media/atomisp/pci/atomisp_drvfs.c b/drivers/staging/media/atomisp/pci/atomisp_drvfs.c index fe0e2bfde27f..f670faf978e6 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_drvfs.c +++ b/drivers/staging/media/atomisp/pci/atomisp_drvfs.c @@ -62,9 +62,9 @@ static inline int iunit_dump_dbgopt(struct atomisp_device *isp, if (opt & OPTION_VALID) { if (opt & OPTION_BIN_LIST) { - ret = atomisp_css_dump_blob_infor(); + ret = atomisp_css_dump_blob_infor(isp); if (ret) { - dev_err(atomisp_dev, "%s dump blob infor err[ret:%d]\n", + dev_err(isp->dev, "%s dump blob infor err[ret:%d]\n", __func__, ret); goto opt_err; } @@ -76,7 +76,7 @@ static inline int iunit_dump_dbgopt(struct atomisp_device *isp, atomisp_css_debug_dump_isp_binary(); } else { ret = -EPERM; - dev_err(atomisp_dev, "%s dump running bin err[ret:%d]\n", + dev_err(isp->dev, "%s dump running bin err[ret:%d]\n", __func__, ret); goto opt_err; } @@ -86,8 +86,7 @@ static inline int iunit_dump_dbgopt(struct atomisp_device *isp, hmm_show_mem_stat(__func__, __LINE__); } else { ret = -EINVAL; - dev_err(atomisp_dev, "%s dump nothing[ret=%d]\n", __func__, - ret); + dev_err(isp->dev, "%s dump nothing[ret=%d]\n", __func__, ret); } opt_err: @@ -185,8 +184,9 @@ static void iunit_drvfs_remove_files(struct device_driver *drv) driver_remove_file(drv, &iunit_drvfs_attrs[i]); } -int atomisp_drvfs_init(struct device_driver *drv, struct atomisp_device *isp) +int atomisp_drvfs_init(struct atomisp_device *isp) { + struct device_driver *drv = isp->dev->driver; int ret; iunit_debug.isp = isp; @@ -194,7 +194,7 @@ int atomisp_drvfs_init(struct device_driver *drv, struct atomisp_device *isp) ret = iunit_drvfs_create_files(iunit_debug.drv); if (ret) { - dev_err(atomisp_dev, "drvfs_create_files error: %d\n", ret); + dev_err(isp->dev, "drvfs_create_files error: %d\n", ret); iunit_drvfs_remove_files(iunit_debug.drv); } diff --git a/drivers/staging/media/atomisp/pci/atomisp_drvfs.h b/drivers/staging/media/atomisp/pci/atomisp_drvfs.h index 4911037231fb..8f4cc722b881 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_drvfs.h +++ b/drivers/staging/media/atomisp/pci/atomisp_drvfs.h @@ -19,7 +19,7 @@ #ifndef __ATOMISP_DRVFS_H__ #define __ATOMISP_DRVFS_H__ -int atomisp_drvfs_init(struct device_driver *drv, struct atomisp_device *isp); +int atomisp_drvfs_init(struct atomisp_device *isp); void atomisp_drvfs_exit(void); #endif /* __ATOMISP_DRVFS_H__ */ diff --git a/drivers/staging/media/atomisp/pci/atomisp_gmin_platform.c b/drivers/staging/media/atomisp/pci/atomisp_gmin_platform.c index 1af9da8acf4c..0df46a1af5f0 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_gmin_platform.c +++ b/drivers/staging/media/atomisp/pci/atomisp_gmin_platform.c @@ -26,6 +26,9 @@ enum clock_rate { #define CLK_RATE_19_2MHZ 19200000 #define CLK_RATE_25_0MHZ 25000000 +/* Valid clock number range from 0 to 5 */ +#define MAX_CLK_COUNT 5 + /* X-Powers AXP288 register set */ #define ALDO1_SEL_REG 0x28 #define ALDO1_CTRL3_REG 0x13 @@ -61,9 +64,7 @@ enum clock_rate { struct gmin_subdev { struct v4l2_subdev *subdev; - int clock_num; enum clock_rate clock_src; - bool clock_on; struct clk *pmc_clk; struct gpio_desc *gpio0; struct gpio_desc *gpio1; @@ -75,11 +76,16 @@ struct gmin_subdev { unsigned int csi_lanes; enum atomisp_input_format csi_fmt; enum atomisp_bayer_order csi_bayer; + + bool clock_on; bool v1p8_on; bool v2p8_on; bool v1p2_on; bool v2p8_vcm_on; + int v1p8_gpio; + int v2p8_gpio; + u8 pwm_i2c_addr; /* For PMIC AXP */ @@ -90,9 +96,9 @@ struct gmin_subdev { static struct gmin_subdev gmin_subdevs[MAX_SUBDEVS]; /* ACPI HIDs for the PMICs that could be used by this driver */ -#define PMIC_ACPI_AXP "INT33F4:00" /* XPower AXP288 PMIC */ -#define PMIC_ACPI_TI "INT33F5:00" /* Dollar Cove TI PMIC */ -#define PMIC_ACPI_CRYSTALCOVE "INT33FD:00" /* Crystal Cove PMIC */ +#define PMIC_ACPI_AXP "INT33F4" /* XPower AXP288 PMIC */ +#define PMIC_ACPI_TI "INT33F5" /* Dollar Cove TI PMIC */ +#define PMIC_ACPI_CRYSTALCOVE "INT33FD" /* Crystal Cove PMIC */ #define PMIC_PLATFORM_TI "intel_soc_pmic_chtdc_ti" @@ -105,7 +111,7 @@ static enum { } pmic_id; static const char *pmic_name[] = { - [PMIC_UNSET] = "unset", + [PMIC_UNSET] = "ACPI device PM", [PMIC_REGULATOR] = "regulator driver", [PMIC_AXP] = "XPower AXP288 PMIC", [PMIC_TI] = "Dollar Cove TI PMIC", @@ -119,24 +125,6 @@ static const struct atomisp_platform_data pdata = { .subdevs = pdata_subdevs, }; -/* - * Something of a hack. The ECS E7 board drives camera 2.8v from an - * external regulator instead of the PMIC. There's a gmin_CamV2P8 - * config variable that specifies the GPIO to handle this particular - * case, but this needs a broader architecture for handling camera - * power. - */ -enum { V2P8_GPIO_UNSET = -2, V2P8_GPIO_NONE = -1 }; -static int v2p8_gpio = V2P8_GPIO_UNSET; - -/* - * Something of a hack. The CHT RVP board drives camera 1.8v from an - * external regulator instead of the PMIC just like ECS E7 board, see the - * comments above. - */ -enum { V1P8_GPIO_UNSET = -2, V1P8_GPIO_NONE = -1 }; -static int v1p8_gpio = V1P8_GPIO_UNSET; - static LIST_HEAD(vcm_devices); static DEFINE_MUTEX(vcm_lock); @@ -199,6 +187,8 @@ int atomisp_register_i2c_module(struct v4l2_subdev *subdev, * gmin_subdev struct is already initialized for us. */ gs = find_gmin_subdev(subdev); + if (!gs) + return -ENODEV; pdata.subdevs[i].type = type; pdata.subdevs[i].port = gs->csi_port; @@ -294,6 +284,7 @@ static struct gmin_cfg_var mrd7_vars[] = { {"INT33F8:00_CsiFmt", "13"}, {"INT33F8:00_CsiBayer", "0"}, {"INT33F8:00_CamClk", "0"}, + {"INT33F9:00_CamType", "1"}, {"INT33F9:00_CsiPort", "0"}, {"INT33F9:00_CsiLanes", "1"}, @@ -309,6 +300,7 @@ static struct gmin_cfg_var ecs7_vars[] = { {"INT33BE:00_CsiFmt", "13"}, {"INT33BE:00_CsiBayer", "2"}, {"INT33BE:00_CamClk", "0"}, + {"INT33F0:00_CsiPort", "0"}, {"INT33F0:00_CsiLanes", "1"}, {"INT33F0:00_CsiFmt", "13"}, @@ -322,6 +314,7 @@ static struct gmin_cfg_var i8880_vars[] = { {"XXOV2680:00_CsiPort", "1"}, {"XXOV2680:00_CsiLanes", "1"}, {"XXOV2680:00_CamClk", "0"}, + {"XXGC0310:00_CsiPort", "0"}, {"XXGC0310:00_CsiLanes", "1"}, {"XXGC0310:00_CamClk", "1"}, @@ -381,34 +374,27 @@ static const guid_t atomisp_dsm_guid = GUID_INIT(0xdc2f6c4f, 0x045b, 0x4f1d, #define GMIN_PMC_CLK_NAME 14 /* "pmc_plt_clk_[0..5]" */ static char gmin_pmc_clk_name[GMIN_PMC_CLK_NAME]; -static int gmin_i2c_match_one(struct device *dev, const void *data) -{ - const char *name = data; - struct i2c_client *client; - - if (dev->type != &i2c_client_type) - return 0; - - client = to_i2c_client(dev); - - return (!strcmp(name, client->name)); -} - static struct i2c_client *gmin_i2c_dev_exists(struct device *dev, char *name, struct i2c_client **client) { + struct acpi_device *adev; struct device *d; - while ((d = bus_find_device(&i2c_bus_type, NULL, name, - gmin_i2c_match_one))) { - *client = to_i2c_client(d); - dev_dbg(dev, "found '%s' at address 0x%02x, adapter %d\n", - (*client)->name, (*client)->addr, - (*client)->adapter->nr); - return *client; - } + adev = acpi_dev_get_first_match_dev(name, NULL, -1); + if (!adev) + return NULL; - return NULL; + d = bus_find_device_by_acpi_dev(&i2c_bus_type, adev); + acpi_dev_put(adev); + if (!d) + return NULL; + + *client = i2c_verify_client(d); + put_device(d); + + dev_dbg(dev, "found '%s' at address 0x%02x, adapter %d\n", + (*client)->name, (*client)->addr, (*client)->adapter->nr); + return *client; } static int gmin_i2c_write(struct device *dev, u16 i2c_addr, u8 reg, @@ -427,94 +413,222 @@ static int gmin_i2c_write(struct device *dev, u16 i2c_addr, u8 reg, "I2C write, addr: 0x%02x, reg: 0x%02x, value: 0x%02x, mask: 0x%02x\n", i2c_addr, reg, value, mask); - ret = intel_soc_pmic_exec_mipi_pmic_seq_element(i2c_addr, reg, - value, mask); - - if (ret == -EOPNOTSUPP) { + ret = intel_soc_pmic_exec_mipi_pmic_seq_element(i2c_addr, reg, value, mask); + if (ret == -EOPNOTSUPP) dev_err(dev, "ACPI didn't mapped the OpRegion needed to access I2C address 0x%02x.\n" - "Need to compile the Kernel using CONFIG_*_PMIC_OPREGION settings\n", + "Need to compile the kernel using CONFIG_*_PMIC_OPREGION settings\n", i2c_addr); - return ret; - } return ret; } -static struct gmin_subdev *gmin_subdev_add(struct v4l2_subdev *subdev) +static int atomisp_get_acpi_power(struct device *dev) { - struct i2c_client *power = NULL, *client = v4l2_get_subdevdata(subdev); - struct acpi_device *adev; - acpi_handle handle; - struct device *dev; - int i, ret; + char name[5]; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + struct acpi_buffer b_name = { sizeof(name), name }; + union acpi_object *package, *element; + acpi_handle handle = ACPI_HANDLE(dev); + acpi_handle rhandle; + acpi_status status; + int clock_num = -1; + int i; - if (!client) - return NULL; + status = acpi_evaluate_object(handle, "_PR0", NULL, &buffer); + if (!ACPI_SUCCESS(status)) + return -1; - dev = &client->dev; + package = buffer.pointer; - handle = ACPI_HANDLE(dev); + if (!buffer.length || !package + || package->type != ACPI_TYPE_PACKAGE + || !package->package.count) + goto fail; - // FIXME: may need to release resources allocated by acpi_bus_get_device() - if (!handle || acpi_bus_get_device(handle, &adev)) { - dev_err(dev, "Error could not get ACPI device\n"); - return NULL; - } + for (i = 0; i < package->package.count; i++) { + element = &package->package.elements[i]; - dev_info(&client->dev, "%s: ACPI detected it on bus ID=%s, HID=%s\n", - __func__, acpi_device_bid(adev), acpi_device_hid(adev)); + if (element->type != ACPI_TYPE_LOCAL_REFERENCE) + continue; - if (!pmic_id) { - if (gmin_i2c_dev_exists(dev, PMIC_ACPI_TI, &power)) - pmic_id = PMIC_TI; - else if (gmin_i2c_dev_exists(dev, PMIC_ACPI_AXP, &power)) - pmic_id = PMIC_AXP; - else if (gmin_i2c_dev_exists(dev, PMIC_ACPI_CRYSTALCOVE, &power)) - pmic_id = PMIC_CRYSTALCOVE; - else - pmic_id = PMIC_REGULATOR; + rhandle = element->reference.handle; + if (!rhandle) + goto fail; + + acpi_get_name(rhandle, ACPI_SINGLE_NAME, &b_name); + + dev_dbg(dev, "Found PM resource '%s'\n", name); + if (strlen(name) == 4 && !strncmp(name, "CLK", 3)) { + if (name[3] >= '0' && name[3] <= '4') + clock_num = name[3] - '0'; +#if 0 + /* + * We could abort here, but let's parse all resources, + * as this is helpful for debugging purposes + */ + if (clock_num >= 0) + break; +#endif + } } - for (i = 0; i < MAX_SUBDEVS && gmin_subdevs[i].subdev; i++) - ; - if (i >= MAX_SUBDEVS) - return NULL; +fail: + ACPI_FREE(buffer.pointer); + + return clock_num; +} + +static u8 gmin_get_pmic_id_and_addr(struct device *dev) +{ + struct i2c_client *power; + static u8 pmic_i2c_addr; + + if (pmic_id) + return pmic_i2c_addr; + + if (gmin_i2c_dev_exists(dev, PMIC_ACPI_TI, &power)) + pmic_id = PMIC_TI; + else if (gmin_i2c_dev_exists(dev, PMIC_ACPI_AXP, &power)) + pmic_id = PMIC_AXP; + else if (gmin_i2c_dev_exists(dev, PMIC_ACPI_CRYSTALCOVE, &power)) + pmic_id = PMIC_CRYSTALCOVE; + else + pmic_id = PMIC_REGULATOR; + + pmic_i2c_addr = power ? power->addr : 0; + return pmic_i2c_addr; +} + +static int gmin_detect_pmic(struct v4l2_subdev *subdev) +{ + struct i2c_client *client = v4l2_get_subdevdata(subdev); + struct device *dev = &client->dev; + u8 pmic_i2c_addr; + + pmic_i2c_addr = gmin_get_pmic_id_and_addr(dev); + dev_info(dev, "gmin: power management provided via %s (i2c addr 0x%02x)\n", + pmic_name[pmic_id], pmic_i2c_addr); + return pmic_i2c_addr; +} + +static int gmin_subdev_add(struct gmin_subdev *gs) +{ + struct i2c_client *client = v4l2_get_subdevdata(gs->subdev); + struct device *dev = &client->dev; + struct acpi_device *adev = ACPI_COMPANION(dev); + int ret, clock_num = -1; + + dev_info(dev, "%s: ACPI path is %pfw\n", __func__, dev_fwnode(dev)); + + /*WA:CHT requires XTAL clock as PLL is not stable.*/ + gs->clock_src = gmin_get_var_int(dev, false, "ClkSrc", + VLV2_CLK_PLL_19P2MHZ); + + gs->csi_port = gmin_get_var_int(dev, false, "CsiPort", 0); + gs->csi_lanes = gmin_get_var_int(dev, false, "CsiLanes", 1); + + gs->gpio0 = gpiod_get_index(dev, NULL, 0, GPIOD_OUT_LOW); + if (IS_ERR(gs->gpio0)) + gs->gpio0 = NULL; + else + dev_info(dev, "will handle gpio0 via ACPI\n"); + + gs->gpio1 = gpiod_get_index(dev, NULL, 1, GPIOD_OUT_LOW); + if (IS_ERR(gs->gpio1)) + gs->gpio1 = NULL; + else + dev_info(dev, "will handle gpio1 via ACPI\n"); + + /* + * Those are used only when there is an external regulator apart + * from the PMIC that would be providing power supply, like on the + * two cases below: + * + * The ECS E7 board drives camera 2.8v from an external regulator + * instead of the PMIC. There's a gmin_CamV2P8 config variable + * that specifies the GPIO to handle this particular case, + * but this needs a broader architecture for handling camera power. + * + * The CHT RVP board drives camera 1.8v from an* external regulator + * instead of the PMIC just like ECS E7 board. + */ - if (power) { - gmin_subdevs[i].pwm_i2c_addr = power->addr; + gs->v1p8_gpio = gmin_get_var_int(dev, true, "V1P8GPIO", -1); + gs->v2p8_gpio = gmin_get_var_int(dev, true, "V2P8GPIO", -1); + + /* + * FIXME: + * + * The ACPI handling code checks for the _PR? tables in order to + * know what is required to switch the device from power state + * D0 (_PR0) up to D3COLD (_PR3). + * + * The adev->flags.power_manageable is set to true if the device + * has a _PR0 table, which can be checked by calling + * acpi_device_power_manageable(adev). + * + * However, this only says that the device can be set to power off + * mode. + * + * At least on the DSDT tables we've seen so far, there's no _PR3, + * nor _PS3 (which would have a somewhat similar effect). + * So, using ACPI for power management won't work, except if adding + * an ACPI override logic somewhere. + * + * So, at least for the existing devices we know, the check below + * will always be false. + */ + if (acpi_device_can_wakeup(adev) && + acpi_device_can_poweroff(adev)) { dev_info(dev, - "gmin: power management provided via %s (i2c addr 0x%02x)\n", - pmic_name[pmic_id], power->addr); - } else { - dev_info(dev, "gmin: power management provided via %s\n", - pmic_name[pmic_id]); + "gmin: power management provided via device PM\n"); + return 0; } - gmin_subdevs[i].subdev = subdev; - gmin_subdevs[i].clock_num = gmin_get_var_int(dev, false, "CamClk", 0); - /*WA:CHT requires XTAL clock as PLL is not stable.*/ - gmin_subdevs[i].clock_src = gmin_get_var_int(dev, false, "ClkSrc", - VLV2_CLK_PLL_19P2MHZ); - gmin_subdevs[i].csi_port = gmin_get_var_int(dev, false, "CsiPort", 0); - gmin_subdevs[i].csi_lanes = gmin_get_var_int(dev, false, "CsiLanes", 1); + /* + * The code below is here due to backward compatibility with devices + * whose ACPI BIOS may not contain everything that would be needed + * in order to set clocks and do power management. + */ + + /* + * According with : + * https://github.com/projectceladon/hardware-intel-kernelflinger/blob/master/doc/fastboot.md + * + * The "CamClk" EFI var is set via fastboot on some Android devices, + * and seems to contain the number of the clock used to feed the + * sensor. + * + * On systems with a proper ACPI table, this is given via the _PR0 + * power resource table. The logic below should first check if there + * is a power resource already, falling back to the EFI vars detection + * otherwise. + */ - /* get PMC clock with clock framework */ - snprintf(gmin_pmc_clk_name, - sizeof(gmin_pmc_clk_name), - "%s_%d", "pmc_plt_clk", gmin_subdevs[i].clock_num); + /* Try first to use ACPI to get the clock resource */ + if (acpi_device_power_manageable(adev)) + clock_num = atomisp_get_acpi_power(dev); - gmin_subdevs[i].pmc_clk = devm_clk_get(dev, gmin_pmc_clk_name); - if (IS_ERR(gmin_subdevs[i].pmc_clk)) { - ret = PTR_ERR(gmin_subdevs[i].pmc_clk); + /* Fall-back use EFI and/or DMI match */ + if (clock_num < 0) + clock_num = gmin_get_var_int(dev, false, "CamClk", 0); - dev_err(dev, - "Failed to get clk from %s : %d\n", - gmin_pmc_clk_name, - ret); + if (clock_num < 0 || clock_num > MAX_CLK_COUNT) { + dev_err(dev, "Invalid clock number\n"); + return -EINVAL; + } - return NULL; + snprintf(gmin_pmc_clk_name, sizeof(gmin_pmc_clk_name), + "%s_%d", "pmc_plt_clk", clock_num); + + gs->pmc_clk = devm_clk_get(dev, gmin_pmc_clk_name); + if (IS_ERR(gs->pmc_clk)) { + ret = PTR_ERR(gs->pmc_clk); + dev_err(dev, "Failed to get clk from %s: %d\n", gmin_pmc_clk_name, ret); + return ret; } + dev_info(dev, "Will use CLK%d (%s)\n", clock_num, gmin_pmc_clk_name); /* * The firmware might enable the clock at @@ -526,25 +640,17 @@ static struct gmin_subdev *gmin_subdev_add(struct v4l2_subdev *subdev) * to disable a clock that has not been enabled, * we need to enable the clock first. */ - ret = clk_prepare_enable(gmin_subdevs[i].pmc_clk); + ret = clk_prepare_enable(gs->pmc_clk); if (!ret) - clk_disable_unprepare(gmin_subdevs[i].pmc_clk); - - gmin_subdevs[i].gpio0 = gpiod_get_index(dev, NULL, 0, GPIOD_OUT_LOW); - if (IS_ERR(gmin_subdevs[i].gpio0)) - gmin_subdevs[i].gpio0 = NULL; - - gmin_subdevs[i].gpio1 = gpiod_get_index(dev, NULL, 1, GPIOD_OUT_LOW); - if (IS_ERR(gmin_subdevs[i].gpio1)) - gmin_subdevs[i].gpio1 = NULL; + clk_disable_unprepare(gs->pmc_clk); switch (pmic_id) { case PMIC_REGULATOR: - gmin_subdevs[i].v1p8_reg = regulator_get(dev, "V1P8SX"); - gmin_subdevs[i].v2p8_reg = regulator_get(dev, "V2P8SX"); + gs->v1p8_reg = regulator_get(dev, "V1P8SX"); + gs->v2p8_reg = regulator_get(dev, "V2P8SX"); - gmin_subdevs[i].v1p2_reg = regulator_get(dev, "V1P2A"); - gmin_subdevs[i].v2p8_vcm_reg = regulator_get(dev, "VPROG4B"); + gs->v1p2_reg = regulator_get(dev, "V1P2A"); + gs->v2p8_vcm_reg = regulator_get(dev, "VPROG4B"); /* Note: ideally we would initialize v[12]p8_on to the * output of regulator_is_enabled(), but sadly that @@ -556,32 +662,31 @@ static struct gmin_subdev *gmin_subdev_add(struct v4l2_subdev *subdev) break; case PMIC_AXP: - gmin_subdevs[i].eldo1_1p8v = gmin_get_var_int(dev, false, - "eldo1_1p8v", - ELDO1_1P8V); - gmin_subdevs[i].eldo1_sel_reg = gmin_get_var_int(dev, false, - "eldo1_sel_reg", - ELDO1_SEL_REG); - gmin_subdevs[i].eldo1_ctrl_shift = gmin_get_var_int(dev, false, - "eldo1_ctrl_shift", - ELDO1_CTRL_SHIFT); - gmin_subdevs[i].eldo2_1p8v = gmin_get_var_int(dev, false, - "eldo2_1p8v", - ELDO2_1P8V); - gmin_subdevs[i].eldo2_sel_reg = gmin_get_var_int(dev, false, - "eldo2_sel_reg", - ELDO2_SEL_REG); - gmin_subdevs[i].eldo2_ctrl_shift = gmin_get_var_int(dev, false, - "eldo2_ctrl_shift", - ELDO2_CTRL_SHIFT); - gmin_subdevs[i].pwm_i2c_addr = power->addr; + gs->eldo1_1p8v = gmin_get_var_int(dev, false, + "eldo1_1p8v", + ELDO1_1P8V); + gs->eldo1_sel_reg = gmin_get_var_int(dev, false, + "eldo1_sel_reg", + ELDO1_SEL_REG); + gs->eldo1_ctrl_shift = gmin_get_var_int(dev, false, + "eldo1_ctrl_shift", + ELDO1_CTRL_SHIFT); + gs->eldo2_1p8v = gmin_get_var_int(dev, false, + "eldo2_1p8v", + ELDO2_1P8V); + gs->eldo2_sel_reg = gmin_get_var_int(dev, false, + "eldo2_sel_reg", + ELDO2_SEL_REG); + gs->eldo2_ctrl_shift = gmin_get_var_int(dev, false, + "eldo2_ctrl_shift", + ELDO2_CTRL_SHIFT); break; default: break; } - return &gmin_subdevs[i]; + return 0; } static struct gmin_subdev *find_gmin_subdev(struct v4l2_subdev *subdev) @@ -591,7 +696,17 @@ static struct gmin_subdev *find_gmin_subdev(struct v4l2_subdev *subdev) for (i = 0; i < MAX_SUBDEVS; i++) if (gmin_subdevs[i].subdev == subdev) return &gmin_subdevs[i]; - return gmin_subdev_add(subdev); + return NULL; +} + +static struct gmin_subdev *find_free_gmin_subdev_slot(void) +{ + unsigned int i; + + for (i = 0; i < MAX_SUBDEVS; i++) + if (gmin_subdevs[i].subdev == NULL) + return &gmin_subdevs[i]; + return NULL; } static int axp_regulator_set(struct device *dev, struct gmin_subdev *gs, @@ -700,32 +815,24 @@ static int gmin_v1p8_ctrl(struct v4l2_subdev *subdev, int on) { struct gmin_subdev *gs = find_gmin_subdev(subdev); int ret; - struct device *dev; - struct i2c_client *client = v4l2_get_subdevdata(subdev); int value; - dev = &client->dev; - - if (v1p8_gpio == V1P8_GPIO_UNSET) { - v1p8_gpio = gmin_get_var_int(dev, true, - "V1P8GPIO", V1P8_GPIO_NONE); - if (v1p8_gpio != V1P8_GPIO_NONE) { - pr_info("atomisp_gmin_platform: 1.8v power on GPIO %d\n", - v1p8_gpio); - ret = gpio_request(v1p8_gpio, "camera_v1p8_en"); - if (!ret) - ret = gpio_direction_output(v1p8_gpio, 0); - if (ret) - pr_err("V1P8 GPIO initialization failed\n"); - } + if (gs->v1p8_gpio >= 0) { + pr_info("atomisp_gmin_platform: 1.8v power on GPIO %d\n", + gs->v1p8_gpio); + ret = gpio_request(gs->v1p8_gpio, "camera_v1p8_en"); + if (!ret) + ret = gpio_direction_output(gs->v1p8_gpio, 0); + if (ret) + pr_err("V1P8 GPIO initialization failed\n"); } if (!gs || gs->v1p8_on == on) return 0; gs->v1p8_on = on; - if (v1p8_gpio >= 0) - gpio_set_value(v1p8_gpio, on); + if (gs->v1p8_gpio >= 0) + gpio_set_value(gs->v1p8_gpio, on); if (gs->v1p8_reg) { regulator_set_voltage(gs->v1p8_reg, 1800000, 1800000); @@ -762,32 +869,24 @@ static int gmin_v2p8_ctrl(struct v4l2_subdev *subdev, int on) { struct gmin_subdev *gs = find_gmin_subdev(subdev); int ret; - struct device *dev; - struct i2c_client *client = v4l2_get_subdevdata(subdev); int value; - dev = &client->dev; - - if (v2p8_gpio == V2P8_GPIO_UNSET) { - v2p8_gpio = gmin_get_var_int(dev, true, - "V2P8GPIO", V2P8_GPIO_NONE); - if (v2p8_gpio != V2P8_GPIO_NONE) { - pr_info("atomisp_gmin_platform: 2.8v power on GPIO %d\n", - v2p8_gpio); - ret = gpio_request(v2p8_gpio, "camera_v2p8"); - if (!ret) - ret = gpio_direction_output(v2p8_gpio, 0); - if (ret) - pr_err("V2P8 GPIO initialization failed\n"); - } + if (gs->v2p8_gpio >= 0) { + pr_info("atomisp_gmin_platform: 2.8v power on GPIO %d\n", + gs->v2p8_gpio); + ret = gpio_request(gs->v2p8_gpio, "camera_v2p8"); + if (!ret) + ret = gpio_direction_output(gs->v2p8_gpio, 0); + if (ret) + pr_err("V2P8 GPIO initialization failed\n"); } if (!gs || gs->v2p8_on == on) return 0; gs->v2p8_on = on; - if (v2p8_gpio >= 0) - gpio_set_value(v2p8_gpio, on); + if (gs->v2p8_gpio >= 0) + gpio_set_value(gs->v2p8_gpio, on); if (gs->v2p8_reg) { regulator_set_voltage(gs->v2p8_reg, 2900000, 2900000); @@ -819,6 +918,37 @@ static int gmin_v2p8_ctrl(struct v4l2_subdev *subdev, int on) return -EINVAL; } +static int gmin_acpi_pm_ctrl(struct v4l2_subdev *subdev, int on) +{ + int ret = 0; + struct gmin_subdev *gs = find_gmin_subdev(subdev); + struct i2c_client *client = v4l2_get_subdevdata(subdev); + struct acpi_device *adev = ACPI_COMPANION(&client->dev); + + /* Use the ACPI power management to control it */ + on = !!on; + if (gs->clock_on == on) + return 0; + + dev_dbg(subdev->dev, "Setting power state to %s\n", + on ? "on" : "off"); + + if (on) + ret = acpi_device_set_power(adev, + ACPI_STATE_D0); + else + ret = acpi_device_set_power(adev, + ACPI_STATE_D3_COLD); + + if (!ret) + gs->clock_on = on; + else + dev_err(subdev->dev, "Couldn't set power state to %s\n", + on ? "on" : "off"); + + return ret; +} + static int gmin_flisclk_ctrl(struct v4l2_subdev *subdev, int on) { int ret = 0; @@ -884,7 +1014,7 @@ static struct camera_vcm_control *gmin_get_vcm_ctrl(struct v4l2_subdev *subdev, return NULL; } -static struct camera_sensor_platform_data gmin_plat = { +static struct camera_sensor_platform_data pmic_gmin_plat = { .gpio0_ctrl = gmin_gpio0_ctrl, .gpio1_ctrl = gmin_gpio1_ctrl, .v1p8_ctrl = gmin_v1p8_ctrl, @@ -895,17 +1025,36 @@ static struct camera_sensor_platform_data gmin_plat = { .get_vcm_ctrl = gmin_get_vcm_ctrl, }; +static struct camera_sensor_platform_data acpi_gmin_plat = { + .gpio0_ctrl = gmin_gpio0_ctrl, + .gpio1_ctrl = gmin_gpio1_ctrl, + .v1p8_ctrl = gmin_acpi_pm_ctrl, + .v2p8_ctrl = gmin_acpi_pm_ctrl, + .v1p2_ctrl = gmin_acpi_pm_ctrl, + .flisclk_ctrl = gmin_acpi_pm_ctrl, + .csi_cfg = gmin_csi_cfg, + .get_vcm_ctrl = gmin_get_vcm_ctrl, +}; + struct camera_sensor_platform_data *gmin_camera_platform_data( struct v4l2_subdev *subdev, enum atomisp_input_format csi_format, enum atomisp_bayer_order csi_bayer) { - struct gmin_subdev *gs = find_gmin_subdev(subdev); + u8 pmic_i2c_addr = gmin_detect_pmic(subdev); + struct gmin_subdev *gs; + gs = find_free_gmin_subdev_slot(); + gs->subdev = subdev; gs->csi_fmt = csi_format; gs->csi_bayer = csi_bayer; + gs->pwm_i2c_addr = pmic_i2c_addr; - return &gmin_plat; + gmin_subdev_add(gs); + if (gs->pmc_clk) + return &pmic_gmin_plat; + else + return &acpi_gmin_plat; } EXPORT_SYMBOL_GPL(gmin_camera_platform_data); @@ -957,12 +1106,28 @@ static int gmin_get_config_dsm_var(struct device *dev, union acpi_object *obj, *cur = NULL; int i; + /* + * The data reported by "CamClk" seems to be either 0 or 1 at the + * _DSM table. + * + * At the ACPI tables we looked so far, this is not related to the + * actual clock source for the sensor, which is given by the + * _PR0 ACPI table. So, ignore it, as otherwise this will be + * set to a wrong value. + */ + if (!strcmp(var, "CamClk")) + return -EINVAL; + obj = acpi_evaluate_dsm(handle, &atomisp_dsm_guid, 0, 0, NULL); if (!obj) { dev_info_once(dev, "Didn't find ACPI _DSM table.\n"); return -EINVAL; } + /* Return on unexpected object type */ + if (obj->type != ACPI_TYPE_PACKAGE) + return -EINVAL; + #if 0 /* Just for debugging purposes */ for (i = 0; i < obj->package.count; i++) { union acpi_object *cur = &obj->package.elements[i]; @@ -1155,10 +1320,10 @@ EXPORT_SYMBOL_GPL(camera_sensor_csi); * trying. The driver itself does direct calls to the PUNIT to manage * ISP power. */ -static void isp_pm_cap_fixup(struct pci_dev *dev) +static void isp_pm_cap_fixup(struct pci_dev *pdev) { - dev_info(&dev->dev, "Disabling PCI power management on camera ISP\n"); - dev->pm_cap = 0; + dev_info(&pdev->dev, "Disabling PCI power management on camera ISP\n"); + pdev->pm_cap = 0; } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0f38, isp_pm_cap_fixup); diff --git a/drivers/staging/media/atomisp/pci/atomisp_internal.h b/drivers/staging/media/atomisp/pci/atomisp_internal.h index ff3becd41110..c01db10bb735 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_internal.h +++ b/drivers/staging/media/atomisp/pci/atomisp_internal.h @@ -216,12 +216,12 @@ struct atomisp_sw_contex { * ci device struct */ struct atomisp_device { - struct pci_dev *pdev; struct device *dev; struct v4l2_device v4l2_dev; struct media_device media_dev; struct atomisp_platform_data *pdata; void *mmu_l1_base; + void __iomem *base; const struct firmware *firmware; struct pm_qos_request pm_qos; diff --git a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c index 9404a678fa6f..f8d616f08b51 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c +++ b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c @@ -549,8 +549,7 @@ static int atomisp_querycap(struct file *file, void *fh, strscpy(cap->driver, DRIVER, sizeof(cap->driver)); strscpy(cap->card, CARD, sizeof(cap->card)); - snprintf(cap->bus_info, sizeof(cap->bus_info), "PCI:%s", - pci_name(isp->pdev)); + snprintf(cap->bus_info, sizeof(cap->bus_info), "PCI:%s", dev_name(isp->dev)); return 0; } @@ -1635,6 +1634,7 @@ static int atomisp_streamon(struct file *file, void *fh, struct atomisp_video_pipe *pipe = atomisp_to_video_pipe(vdev); struct atomisp_sub_device *asd = pipe->asd; struct atomisp_device *isp = video_get_drvdata(vdev); + struct pci_dev *pdev = to_pci_dev(isp->dev); enum ia_css_pipe_id css_pipe_id; unsigned int sensor_start_stream; unsigned int wdt_duration = ATOMISP_ISP_TIMEOUT_DURATION; @@ -1844,9 +1844,8 @@ start_sensor: /* Enable the CSI interface on ANN B0/K0 */ if (isp->media_dev.hw_revision >= ((ATOMISP_HW_REVISION_ISP2401 << ATOMISP_HW_REVISION_SHIFT) | ATOMISP_HW_STEPPING_B0)) { - pci_write_config_word(isp->pdev, MRFLD_PCI_CSI_CONTROL, - isp->saved_regs.csi_control | - MRFLD_PCI_CSI_CONTROL_CSI_READY); + pci_write_config_word(pdev, MRFLD_PCI_CSI_CONTROL, + isp->saved_regs.csi_control | MRFLD_PCI_CSI_CONTROL_CSI_READY); } /* stream on the sensor */ @@ -1891,6 +1890,7 @@ int __atomisp_streamoff(struct file *file, void *fh, enum v4l2_buf_type type) { struct video_device *vdev = video_devdata(file); struct atomisp_device *isp = video_get_drvdata(vdev); + struct pci_dev *pdev = to_pci_dev(isp->dev); struct atomisp_video_pipe *pipe = atomisp_to_video_pipe(vdev); struct atomisp_sub_device *asd = pipe->asd; struct atomisp_video_pipe *capture_pipe = NULL; @@ -2076,9 +2076,8 @@ stopsensor: /* Disable the CSI interface on ANN B0/K0 */ if (isp->media_dev.hw_revision >= ((ATOMISP_HW_REVISION_ISP2401 << ATOMISP_HW_REVISION_SHIFT) | ATOMISP_HW_STEPPING_B0)) { - pci_write_config_word(isp->pdev, MRFLD_PCI_CSI_CONTROL, - isp->saved_regs.csi_control & - ~MRFLD_PCI_CSI_CONTROL_CSI_READY); + pci_write_config_word(pdev, MRFLD_PCI_CSI_CONTROL, + isp->saved_regs.csi_control & ~MRFLD_PCI_CSI_CONTROL_CSI_READY); } if (atomisp_freq_scaling(isp, ATOMISP_DFS_MODE_LOW, false)) @@ -2111,8 +2110,8 @@ stopsensor: } /* disable PUNIT/ISP acknowlede/handshake - SRSE=3 */ - pci_write_config_dword(isp->pdev, PCI_I_CONTROL, isp->saved_regs.i_control | - MRFLD_PCI_I_CONTROL_SRSE_RESET_MASK); + pci_write_config_dword(pdev, PCI_I_CONTROL, + isp->saved_regs.i_control | MRFLD_PCI_I_CONTROL_SRSE_RESET_MASK); dev_err(isp->dev, "atomisp_reset"); atomisp_reset(isp); for (i = 0; i < isp->num_of_streams; i++) { diff --git a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c index d36809a0182c..a000a1e316f7 100644 --- a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c +++ b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c @@ -127,8 +127,6 @@ MODULE_PARM_DESC(pad_h, "extra data for ISP processing"); struct device *atomisp_dev; -void __iomem *atomisp_io_base; - static const struct atomisp_freq_scaling_rule dfs_rules_merr[] = { { .width = ISP_FREQ_RULE_ANY, @@ -512,30 +510,27 @@ void atomisp_acc_unregister(struct atomisp_acc_pipe *video) static int atomisp_save_iunit_reg(struct atomisp_device *isp) { - struct pci_dev *dev = isp->pdev; + struct pci_dev *pdev = to_pci_dev(isp->dev); dev_dbg(isp->dev, "%s\n", __func__); - pci_read_config_word(dev, PCI_COMMAND, &isp->saved_regs.pcicmdsts); + pci_read_config_word(pdev, PCI_COMMAND, &isp->saved_regs.pcicmdsts); /* isp->saved_regs.ispmmadr is set from the atomisp_pci_probe() */ - pci_read_config_dword(dev, PCI_MSI_CAPID, &isp->saved_regs.msicap); - pci_read_config_dword(dev, PCI_MSI_ADDR, &isp->saved_regs.msi_addr); - pci_read_config_word(dev, PCI_MSI_DATA, &isp->saved_regs.msi_data); - pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &isp->saved_regs.intr); - pci_read_config_dword(dev, PCI_INTERRUPT_CTRL, - &isp->saved_regs.interrupt_control); - - pci_read_config_dword(dev, MRFLD_PCI_PMCS, - &isp->saved_regs.pmcs); + pci_read_config_dword(pdev, PCI_MSI_CAPID, &isp->saved_regs.msicap); + pci_read_config_dword(pdev, PCI_MSI_ADDR, &isp->saved_regs.msi_addr); + pci_read_config_word(pdev, PCI_MSI_DATA, &isp->saved_regs.msi_data); + pci_read_config_byte(pdev, PCI_INTERRUPT_LINE, &isp->saved_regs.intr); + pci_read_config_dword(pdev, PCI_INTERRUPT_CTRL, &isp->saved_regs.interrupt_control); + + pci_read_config_dword(pdev, MRFLD_PCI_PMCS, &isp->saved_regs.pmcs); /* Ensure read/write combining is enabled. */ - pci_read_config_dword(dev, PCI_I_CONTROL, - &isp->saved_regs.i_control); + pci_read_config_dword(pdev, PCI_I_CONTROL, &isp->saved_regs.i_control); isp->saved_regs.i_control |= MRFLD_PCI_I_CONTROL_ENABLE_READ_COMBINING | MRFLD_PCI_I_CONTROL_ENABLE_WRITE_COMBINING; - pci_read_config_dword(dev, MRFLD_PCI_CSI_ACCESS_CTRL_VIOL, + pci_read_config_dword(pdev, MRFLD_PCI_CSI_ACCESS_CTRL_VIOL, &isp->saved_regs.csi_access_viol); - pci_read_config_dword(dev, MRFLD_PCI_CSI_RCOMP_CONTROL, + pci_read_config_dword(pdev, MRFLD_PCI_CSI_RCOMP_CONTROL, &isp->saved_regs.csi_rcomp_config); /* * Hardware bugs require setting CSI_HS_OVR_CLK_GATE_ON_UPDATE. @@ -545,65 +540,58 @@ static int atomisp_save_iunit_reg(struct atomisp_device *isp) * is missed, and IUNIT can hang. * For both issues, setting this bit is a workaround. */ - isp->saved_regs.csi_rcomp_config |= - MRFLD_PCI_CSI_HS_OVR_CLK_GATE_ON_UPDATE; - pci_read_config_dword(dev, MRFLD_PCI_CSI_AFE_TRIM_CONTROL, + isp->saved_regs.csi_rcomp_config |= MRFLD_PCI_CSI_HS_OVR_CLK_GATE_ON_UPDATE; + pci_read_config_dword(pdev, MRFLD_PCI_CSI_AFE_TRIM_CONTROL, &isp->saved_regs.csi_afe_dly); - pci_read_config_dword(dev, MRFLD_PCI_CSI_CONTROL, + pci_read_config_dword(pdev, MRFLD_PCI_CSI_CONTROL, &isp->saved_regs.csi_control); if (isp->media_dev.hw_revision >= (ATOMISP_HW_REVISION_ISP2401 << ATOMISP_HW_REVISION_SHIFT)) - isp->saved_regs.csi_control |= - MRFLD_PCI_CSI_CONTROL_PARPATHEN; + isp->saved_regs.csi_control |= MRFLD_PCI_CSI_CONTROL_PARPATHEN; /* * On CHT CSI_READY bit should be enabled before stream on */ if (IS_CHT && (isp->media_dev.hw_revision >= ((ATOMISP_HW_REVISION_ISP2401 << ATOMISP_HW_REVISION_SHIFT) | ATOMISP_HW_STEPPING_B0))) - isp->saved_regs.csi_control |= - MRFLD_PCI_CSI_CONTROL_CSI_READY; - pci_read_config_dword(dev, MRFLD_PCI_CSI_AFE_RCOMP_CONTROL, + isp->saved_regs.csi_control |= MRFLD_PCI_CSI_CONTROL_CSI_READY; + pci_read_config_dword(pdev, MRFLD_PCI_CSI_AFE_RCOMP_CONTROL, &isp->saved_regs.csi_afe_rcomp_config); - pci_read_config_dword(dev, MRFLD_PCI_CSI_AFE_HS_CONTROL, + pci_read_config_dword(pdev, MRFLD_PCI_CSI_AFE_HS_CONTROL, &isp->saved_regs.csi_afe_hs_control); - pci_read_config_dword(dev, MRFLD_PCI_CSI_DEADLINE_CONTROL, + pci_read_config_dword(pdev, MRFLD_PCI_CSI_DEADLINE_CONTROL, &isp->saved_regs.csi_deadline_control); return 0; } static int __maybe_unused atomisp_restore_iunit_reg(struct atomisp_device *isp) { - struct pci_dev *dev = isp->pdev; + struct pci_dev *pdev = to_pci_dev(isp->dev); dev_dbg(isp->dev, "%s\n", __func__); - pci_write_config_word(dev, PCI_COMMAND, isp->saved_regs.pcicmdsts); - pci_write_config_dword(dev, PCI_BASE_ADDRESS_0, - isp->saved_regs.ispmmadr); - pci_write_config_dword(dev, PCI_MSI_CAPID, isp->saved_regs.msicap); - pci_write_config_dword(dev, PCI_MSI_ADDR, isp->saved_regs.msi_addr); - pci_write_config_word(dev, PCI_MSI_DATA, isp->saved_regs.msi_data); - pci_write_config_byte(dev, PCI_INTERRUPT_LINE, isp->saved_regs.intr); - pci_write_config_dword(dev, PCI_INTERRUPT_CTRL, - isp->saved_regs.interrupt_control); - pci_write_config_dword(dev, PCI_I_CONTROL, - isp->saved_regs.i_control); - - pci_write_config_dword(dev, MRFLD_PCI_PMCS, - isp->saved_regs.pmcs); - pci_write_config_dword(dev, MRFLD_PCI_CSI_ACCESS_CTRL_VIOL, + pci_write_config_word(pdev, PCI_COMMAND, isp->saved_regs.pcicmdsts); + pci_write_config_dword(pdev, PCI_BASE_ADDRESS_0, isp->saved_regs.ispmmadr); + pci_write_config_dword(pdev, PCI_MSI_CAPID, isp->saved_regs.msicap); + pci_write_config_dword(pdev, PCI_MSI_ADDR, isp->saved_regs.msi_addr); + pci_write_config_word(pdev, PCI_MSI_DATA, isp->saved_regs.msi_data); + pci_write_config_byte(pdev, PCI_INTERRUPT_LINE, isp->saved_regs.intr); + pci_write_config_dword(pdev, PCI_INTERRUPT_CTRL, isp->saved_regs.interrupt_control); + pci_write_config_dword(pdev, PCI_I_CONTROL, isp->saved_regs.i_control); + + pci_write_config_dword(pdev, MRFLD_PCI_PMCS, isp->saved_regs.pmcs); + pci_write_config_dword(pdev, MRFLD_PCI_CSI_ACCESS_CTRL_VIOL, isp->saved_regs.csi_access_viol); - pci_write_config_dword(dev, MRFLD_PCI_CSI_RCOMP_CONTROL, + pci_write_config_dword(pdev, MRFLD_PCI_CSI_RCOMP_CONTROL, isp->saved_regs.csi_rcomp_config); - pci_write_config_dword(dev, MRFLD_PCI_CSI_AFE_TRIM_CONTROL, + pci_write_config_dword(pdev, MRFLD_PCI_CSI_AFE_TRIM_CONTROL, isp->saved_regs.csi_afe_dly); - pci_write_config_dword(dev, MRFLD_PCI_CSI_CONTROL, + pci_write_config_dword(pdev, MRFLD_PCI_CSI_CONTROL, isp->saved_regs.csi_control); - pci_write_config_dword(dev, MRFLD_PCI_CSI_AFE_RCOMP_CONTROL, + pci_write_config_dword(pdev, MRFLD_PCI_CSI_AFE_RCOMP_CONTROL, isp->saved_regs.csi_afe_rcomp_config); - pci_write_config_dword(dev, MRFLD_PCI_CSI_AFE_HS_CONTROL, + pci_write_config_dword(pdev, MRFLD_PCI_CSI_AFE_HS_CONTROL, isp->saved_regs.csi_afe_hs_control); - pci_write_config_dword(dev, MRFLD_PCI_CSI_DEADLINE_CONTROL, + pci_write_config_dword(pdev, MRFLD_PCI_CSI_DEADLINE_CONTROL, isp->saved_regs.csi_deadline_control); /* @@ -619,7 +607,7 @@ static int __maybe_unused atomisp_restore_iunit_reg(struct atomisp_device *isp) static int atomisp_mrfld_pre_power_down(struct atomisp_device *isp) { - struct pci_dev *dev = isp->pdev; + struct pci_dev *pdev = to_pci_dev(isp->dev); u32 irq; unsigned long flags; @@ -635,11 +623,11 @@ static int atomisp_mrfld_pre_power_down(struct atomisp_device *isp) * So, here we need to check if there is any pending * IRQ, if so, waiting for it to be served */ - pci_read_config_dword(dev, PCI_INTERRUPT_CTRL, &irq); + pci_read_config_dword(pdev, PCI_INTERRUPT_CTRL, &irq); irq = irq & 1 << INTR_IIR; - pci_write_config_dword(dev, PCI_INTERRUPT_CTRL, irq); + pci_write_config_dword(pdev, PCI_INTERRUPT_CTRL, irq); - pci_read_config_dword(dev, PCI_INTERRUPT_CTRL, &irq); + pci_read_config_dword(pdev, PCI_INTERRUPT_CTRL, &irq); if (!(irq & (1 << INTR_IIR))) goto done; @@ -652,11 +640,11 @@ static int atomisp_mrfld_pre_power_down(struct atomisp_device *isp) spin_unlock_irqrestore(&isp->lock, flags); return -EAGAIN; } else { - pci_read_config_dword(dev, PCI_INTERRUPT_CTRL, &irq); + pci_read_config_dword(pdev, PCI_INTERRUPT_CTRL, &irq); irq = irq & 1 << INTR_IIR; - pci_write_config_dword(dev, PCI_INTERRUPT_CTRL, irq); + pci_write_config_dword(pdev, PCI_INTERRUPT_CTRL, irq); - pci_read_config_dword(dev, PCI_INTERRUPT_CTRL, &irq); + pci_read_config_dword(pdev, PCI_INTERRUPT_CTRL, &irq); if (!(irq & (1 << INTR_IIR))) { atomisp_css2_hw_store_32(MRFLD_INTR_ENABLE_REG, 0x0); goto done; @@ -675,11 +663,11 @@ done: * to IIR. It could block subsequent interrupt messages. * HW sighting:4568410. */ - pci_read_config_dword(dev, PCI_INTERRUPT_CTRL, &irq); + pci_read_config_dword(pdev, PCI_INTERRUPT_CTRL, &irq); irq &= ~(1 << INTR_IER); - pci_write_config_dword(dev, PCI_INTERRUPT_CTRL, irq); + pci_write_config_dword(pdev, PCI_INTERRUPT_CTRL, irq); - atomisp_msi_irq_uninit(isp, dev); + atomisp_msi_irq_uninit(isp); atomisp_freq_scaling(isp, ATOMISP_DFS_MODE_LOW, true); spin_unlock_irqrestore(&isp->lock, flags); @@ -755,7 +743,7 @@ static int atomisp_mrfld_power(struct atomisp_device *isp, bool enable) /* Wait until ISPSSPM0 bit[25:24] shows the right value */ iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ, MRFLD_ISPSSPM0, &tmp); - tmp = (tmp & MRFLD_ISPSSPM0_ISPSSC_MASK) >> MRFLD_ISPSSPM0_ISPSSS_OFFSET; + tmp = (tmp >> MRFLD_ISPSSPM0_ISPSSS_OFFSET) & MRFLD_ISPSSPM0_ISPSSC_MASK; if (tmp == val) { trace_ipu_cstate(enable); return 0; @@ -778,15 +766,13 @@ static int atomisp_mrfld_power(struct atomisp_device *isp, bool enable) /* Workaround for pmu_nc_set_power_state not ready in MRFLD */ int atomisp_mrfld_power_down(struct atomisp_device *isp) { -// FIXME: at least with ISP2401, enabling this code causes the driver to break - return 0 && atomisp_mrfld_power(isp, false); + return atomisp_mrfld_power(isp, false); } /* Workaround for pmu_nc_set_power_state not ready in MRFLD */ int atomisp_mrfld_power_up(struct atomisp_device *isp) { -// FIXME: at least with ISP2401, enabling this code causes the driver to break - return 0 && atomisp_mrfld_power(isp, true); + return atomisp_mrfld_power(isp, true); } int atomisp_runtime_suspend(struct device *dev) @@ -902,6 +888,7 @@ static int __maybe_unused atomisp_resume(struct device *dev) int atomisp_csi_lane_config(struct atomisp_device *isp) { + struct pci_dev *pdev = to_pci_dev(isp->dev); static const struct { u8 code; u8 lanes[MRFLD_PORT_NUM]; @@ -1003,7 +990,7 @@ int atomisp_csi_lane_config(struct atomisp_device *isp) return -EINVAL; } - pci_read_config_dword(isp->pdev, MRFLD_PCI_CSI_CONTROL, &csi_control); + pci_read_config_dword(pdev, MRFLD_PCI_CSI_CONTROL, &csi_control); csi_control &= ~port_config_mask; csi_control |= (portconfigs[i].code << MRFLD_PORT_CONFIGCODE_SHIFT) | (portconfigs[i].lanes[0] ? 0 : (1 << MRFLD_PORT1_ENABLE_SHIFT)) @@ -1013,7 +1000,7 @@ int atomisp_csi_lane_config(struct atomisp_device *isp) | (((1 << portconfigs[i].lanes[1]) - 1) << MRFLD_PORT2_LANES_SHIFT) | (((1 << portconfigs[i].lanes[2]) - 1) << port3_lanes_shift); - pci_write_config_dword(isp->pdev, MRFLD_PCI_CSI_CONTROL, csi_control); + pci_write_config_dword(pdev, MRFLD_PCI_CSI_CONTROL, csi_control); dev_dbg(isp->dev, "%s: the portconfig is %d-%d-%d, CSI_CONTROL is 0x%08X\n", @@ -1440,8 +1427,7 @@ atomisp_load_firmware(struct atomisp_device *isp) * Check for flags the driver was compiled with against the PCI * device. Always returns true on other than ISP 2400. */ -static bool is_valid_device(struct pci_dev *dev, - const struct pci_device_id *id) +static bool is_valid_device(struct pci_dev *pdev, const struct pci_device_id *id) { unsigned int a0_max_id = 0; const char *name; @@ -1465,14 +1451,14 @@ static bool is_valid_device(struct pci_dev *dev, name = "Cherrytrail"; break; default: - dev_err(&dev->dev, "%s: unknown device ID %x04:%x04\n", + dev_err(&pdev->dev, "%s: unknown device ID %x04:%x04\n", product, id->vendor, id->device); return false; } - if (dev->revision <= ATOMISP_PCI_REV_BYT_A0_MAX) { - dev_err(&dev->dev, "%s revision %d is not unsupported\n", - name, dev->revision); + if (pdev->revision <= ATOMISP_PCI_REV_BYT_A0_MAX) { + dev_err(&pdev->dev, "%s revision %d is not unsupported\n", + name, pdev->revision); return false; } @@ -1483,22 +1469,20 @@ static bool is_valid_device(struct pci_dev *dev, #if defined(ISP2400) if (IS_ISP2401) { - dev_err(&dev->dev, "Support for %s (ISP2401) was disabled at compile time\n", + dev_err(&pdev->dev, "Support for %s (ISP2401) was disabled at compile time\n", name); return false; } #else if (!IS_ISP2401) { - dev_err(&dev->dev, "Support for %s (ISP2400) was disabled at compile time\n", + dev_err(&pdev->dev, "Support for %s (ISP2400) was disabled at compile time\n", name); return false; } #endif - dev_info(&dev->dev, "Detected %s version %d (ISP240%c) on %s\n", - name, dev->revision, - IS_ISP2401 ? '1' : '0', - product); + dev_info(&pdev->dev, "Detected %s version %d (ISP240%c) on %s\n", + name, pdev->revision, IS_ISP2401 ? '1' : '0', product); return true; } @@ -1538,66 +1522,60 @@ alloc_fail: #define ATOM_ISP_PCI_BAR 0 -static int atomisp_pci_probe(struct pci_dev *dev, - const struct pci_device_id *id) +static int atomisp_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { const struct atomisp_platform_data *pdata; struct atomisp_device *isp; unsigned int start; - void __iomem *base; int err, val; u32 irq; - if (!is_valid_device(dev, id)) + if (!is_valid_device(pdev, id)) return -ENODEV; /* Pointer to struct device. */ - atomisp_dev = &dev->dev; + atomisp_dev = &pdev->dev; pdata = atomisp_get_platform_data(); if (!pdata) - dev_warn(&dev->dev, "no platform data available\n"); + dev_warn(&pdev->dev, "no platform data available\n"); - err = pcim_enable_device(dev); + err = pcim_enable_device(pdev); if (err) { - dev_err(&dev->dev, "Failed to enable CI ISP device (%d)\n", - err); + dev_err(&pdev->dev, "Failed to enable CI ISP device (%d)\n", err); return err; } - start = pci_resource_start(dev, ATOM_ISP_PCI_BAR); - dev_dbg(&dev->dev, "start: 0x%x\n", start); + start = pci_resource_start(pdev, ATOM_ISP_PCI_BAR); + dev_dbg(&pdev->dev, "start: 0x%x\n", start); - err = pcim_iomap_regions(dev, 1 << ATOM_ISP_PCI_BAR, pci_name(dev)); + err = pcim_iomap_regions(pdev, 1 << ATOM_ISP_PCI_BAR, pci_name(pdev)); if (err) { - dev_err(&dev->dev, "Failed to I/O memory remapping (%d)\n", - err); + dev_err(&pdev->dev, "Failed to I/O memory remapping (%d)\n", err); goto ioremap_fail; } - base = pcim_iomap_table(dev)[ATOM_ISP_PCI_BAR]; - dev_dbg(&dev->dev, "base: %p\n", base); - - atomisp_io_base = base; - - dev_dbg(&dev->dev, "atomisp_io_base: %p\n", atomisp_io_base); - - isp = devm_kzalloc(&dev->dev, sizeof(struct atomisp_device), GFP_KERNEL); + isp = devm_kzalloc(&pdev->dev, sizeof(*isp), GFP_KERNEL); if (!isp) { err = -ENOMEM; goto atomisp_dev_alloc_fail; } - isp->pdev = dev; - isp->dev = &dev->dev; + + isp->dev = &pdev->dev; + isp->base = pcim_iomap_table(pdev)[ATOM_ISP_PCI_BAR]; isp->sw_contex.power_state = ATOM_ISP_POWER_UP; isp->saved_regs.ispmmadr = start; + dev_dbg(&pdev->dev, "atomisp mmio base: %p\n", isp->base); + rt_mutex_init(&isp->mutex); mutex_init(&isp->streamoff_mutex); spin_lock_init(&isp->lock); /* This is not a true PCI device on SoC, so the delay is not needed. */ - isp->pdev->d3_delay = 0; + pdev->d3_delay = 0; + + pci_set_drvdata(pdev, isp); switch (id->device & ATOMISP_PCI_DEVICE_SOC_MASK) { case ATOMISP_PCI_DEVICE_SOC_MRFLD: @@ -1648,15 +1626,14 @@ static int atomisp_pci_probe(struct pci_dev *dev, * have specs yet for exactly how it varies. Default to * BYT-CR but let provisioning set it via EFI variable */ - isp->hpll_freq = gmin_get_var_int(&dev->dev, false, "HpllFreq", - HPLL_FREQ_2000MHZ); + isp->hpll_freq = gmin_get_var_int(&pdev->dev, false, "HpllFreq", HPLL_FREQ_2000MHZ); /* * for BYT/CHT we are put isp into D3cold to avoid pci registers access * in power off. Set d3cold_delay to 0 since default 100ms is not * necessary. */ - isp->pdev->d3cold_delay = 0; + pdev->d3cold_delay = 0; break; case ATOMISP_PCI_DEVICE_SOC_ANN: isp->media_dev.hw_revision = ( @@ -1666,7 +1643,7 @@ static int atomisp_pci_probe(struct pci_dev *dev, ATOMISP_HW_REVISION_ISP2401_LEGACY #endif << ATOMISP_HW_REVISION_SHIFT); - isp->media_dev.hw_revision |= isp->pdev->revision < 2 ? + isp->media_dev.hw_revision |= pdev->revision < 2 ? ATOMISP_HW_STEPPING_A0 : ATOMISP_HW_STEPPING_B0; isp->dfs = &dfs_config_merr; isp->hpll_freq = HPLL_FREQ_1600MHZ; @@ -1679,13 +1656,13 @@ static int atomisp_pci_probe(struct pci_dev *dev, ATOMISP_HW_REVISION_ISP2401_LEGACY #endif << ATOMISP_HW_REVISION_SHIFT); - isp->media_dev.hw_revision |= isp->pdev->revision < 2 ? + isp->media_dev.hw_revision |= pdev->revision < 2 ? ATOMISP_HW_STEPPING_A0 : ATOMISP_HW_STEPPING_B0; isp->dfs = &dfs_config_cht; - isp->pdev->d3cold_delay = 0; + pdev->d3cold_delay = 0; - iosf_mbi_read(CCK_PORT, MBI_REG_READ, CCK_FUSE_REG_0, &val); + iosf_mbi_read(BT_MBI_UNIT_CCK, MBI_REG_READ, CCK_FUSE_REG_0, &val); switch (val & CCK_FUSE_HPLL_FREQ_MASK) { case 0x00: isp->hpll_freq = HPLL_FREQ_800MHZ; @@ -1698,18 +1675,16 @@ static int atomisp_pci_probe(struct pci_dev *dev, break; default: isp->hpll_freq = HPLL_FREQ_1600MHZ; - dev_warn(isp->dev, - "read HPLL from cck failed. Default to 1600 MHz.\n"); + dev_warn(&pdev->dev, "read HPLL from cck failed. Default to 1600 MHz.\n"); } break; default: - dev_err(&dev->dev, "un-supported IUNIT device\n"); + dev_err(&pdev->dev, "un-supported IUNIT device\n"); err = -ENODEV; goto atomisp_dev_alloc_fail; } - dev_info(&dev->dev, "ISP HPLL frequency base = %d MHz\n", - isp->hpll_freq); + dev_info(&pdev->dev, "ISP HPLL frequency base = %d MHz\n", isp->hpll_freq); isp->max_isr_latency = ATOMISP_MAX_ISR_LATENCY; @@ -1718,30 +1693,28 @@ static int atomisp_pci_probe(struct pci_dev *dev, isp->firmware = atomisp_load_firmware(isp); if (!isp->firmware) { err = -ENOENT; - dev_dbg(&dev->dev, "Firmware load failed\n"); + dev_dbg(&pdev->dev, "Firmware load failed\n"); goto load_fw_fail; } - err = sh_css_check_firmware_version(isp->dev, - isp->firmware->data); + err = sh_css_check_firmware_version(isp->dev, isp->firmware->data); if (err) { - dev_dbg(&dev->dev, "Firmware version check failed\n"); + dev_dbg(&pdev->dev, "Firmware version check failed\n"); goto fw_validation_fail; } } else { - dev_info(&dev->dev, "Firmware load will be deferred\n"); + dev_info(&pdev->dev, "Firmware load will be deferred\n"); } - pci_set_master(dev); - pci_set_drvdata(dev, isp); + pci_set_master(pdev); - err = pci_enable_msi(dev); + err = pci_enable_msi(pdev); if (err) { - dev_err(&dev->dev, "Failed to enable msi (%d)\n", err); + dev_err(&pdev->dev, "Failed to enable msi (%d)\n", err); goto enable_msi_fail; } - atomisp_msi_irq_init(isp, dev); + atomisp_msi_irq_init(isp); cpu_latency_qos_add_request(&isp->pm_qos, PM_QOS_DEFAULT_VALUE); @@ -1762,8 +1735,7 @@ static int atomisp_pci_probe(struct pci_dev *dev, * Workaround for imbalance data eye issue which is observed * on TNG B0. */ - pci_read_config_dword(dev, MRFLD_PCI_CSI_AFE_TRIM_CONTROL, - &csi_afe_trim); + pci_read_config_dword(pdev, MRFLD_PCI_CSI_AFE_TRIM_CONTROL, &csi_afe_trim); csi_afe_trim &= ~((MRFLD_PCI_CSI_HSRXCLKTRIM_MASK << MRFLD_PCI_CSI1_HSRXCLKTRIM_SHIFT) | (MRFLD_PCI_CSI_HSRXCLKTRIM_MASK << @@ -1776,20 +1748,18 @@ static int atomisp_pci_probe(struct pci_dev *dev, MRFLD_PCI_CSI2_HSRXCLKTRIM_SHIFT) | (MRFLD_PCI_CSI3_HSRXCLKTRIM << MRFLD_PCI_CSI3_HSRXCLKTRIM_SHIFT); - pci_write_config_dword(dev, MRFLD_PCI_CSI_AFE_TRIM_CONTROL, - csi_afe_trim); + pci_write_config_dword(pdev, MRFLD_PCI_CSI_AFE_TRIM_CONTROL, csi_afe_trim); } err = atomisp_initialize_modules(isp); if (err < 0) { - dev_err(&dev->dev, "atomisp_initialize_modules (%d)\n", err); + dev_err(&pdev->dev, "atomisp_initialize_modules (%d)\n", err); goto initialize_modules_fail; } err = atomisp_register_entities(isp); if (err < 0) { - dev_err(&dev->dev, "atomisp_register_entities failed (%d)\n", - err); + dev_err(&pdev->dev, "atomisp_register_entities failed (%d)\n", err); goto register_entities_fail; } err = atomisp_create_pads_links(isp); @@ -1802,24 +1772,24 @@ static int atomisp_pci_probe(struct pci_dev *dev, /* save the iunit context only once after all the values are init'ed. */ atomisp_save_iunit_reg(isp); - pm_runtime_put_noidle(&dev->dev); - pm_runtime_allow(&dev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_allow(&pdev->dev); hmm_init_mem_stat(repool_pgnr, dypool_enable, dypool_pgnr); err = hmm_pool_register(repool_pgnr, HMM_POOL_TYPE_RESERVED); if (err) { - dev_err(&dev->dev, "Failed to register reserved memory pool.\n"); + dev_err(&pdev->dev, "Failed to register reserved memory pool.\n"); goto hmm_pool_fail; } /* Init ISP memory management */ hmm_init(); - err = devm_request_threaded_irq(&dev->dev, dev->irq, + err = devm_request_threaded_irq(&pdev->dev, pdev->irq, atomisp_isr, atomisp_isr_thread, IRQF_SHARED, "isp_irq", isp); if (err) { - dev_err(&dev->dev, "Failed to request irq (%d)\n", err); + dev_err(&pdev->dev, "Failed to request irq (%d)\n", err); goto request_irq_fail; } @@ -1827,23 +1797,23 @@ static int atomisp_pci_probe(struct pci_dev *dev, if (!defer_fw_load) { err = atomisp_css_load_firmware(isp); if (err) { - dev_err(&dev->dev, "Failed to init css.\n"); + dev_err(&pdev->dev, "Failed to init css.\n"); goto css_init_fail; } } else { - dev_dbg(&dev->dev, "Skip css init.\n"); + dev_dbg(&pdev->dev, "Skip css init.\n"); } /* Clear FW image from memory */ release_firmware(isp->firmware); isp->firmware = NULL; isp->css_env.isp_css_fw.data = NULL; - atomisp_drvfs_init(&dev->driver->driver, isp); + atomisp_drvfs_init(isp); return 0; css_init_fail: - devm_free_irq(&dev->dev, dev->irq, isp); + devm_free_irq(&pdev->dev, pdev->irq, isp); request_irq_fail: hmm_cleanup(); hmm_pool_unregister(HMM_POOL_TYPE_RESERVED); @@ -1856,8 +1826,8 @@ register_entities_fail: atomisp_uninitialize_modules(isp); initialize_modules_fail: cpu_latency_qos_remove_request(&isp->pm_qos); - atomisp_msi_irq_uninit(isp, dev); - pci_disable_msi(dev); + atomisp_msi_irq_uninit(isp); + pci_disable_msi(pdev); enable_msi_fail: fw_validation_fail: release_firmware(isp->firmware); @@ -1869,35 +1839,34 @@ load_fw_fail: * The following lines have been copied from atomisp suspend path */ - pci_read_config_dword(dev, PCI_INTERRUPT_CTRL, &irq); + pci_read_config_dword(pdev, PCI_INTERRUPT_CTRL, &irq); irq = irq & 1 << INTR_IIR; - pci_write_config_dword(dev, PCI_INTERRUPT_CTRL, irq); + pci_write_config_dword(pdev, PCI_INTERRUPT_CTRL, irq); - pci_read_config_dword(dev, PCI_INTERRUPT_CTRL, &irq); + pci_read_config_dword(pdev, PCI_INTERRUPT_CTRL, &irq); irq &= ~(1 << INTR_IER); - pci_write_config_dword(dev, PCI_INTERRUPT_CTRL, irq); + pci_write_config_dword(pdev, PCI_INTERRUPT_CTRL, irq); - atomisp_msi_irq_uninit(isp, dev); + atomisp_msi_irq_uninit(isp); atomisp_ospm_dphy_down(isp); /* Address later when we worry about the ...field chips */ if (IS_ENABLED(CONFIG_PM) && atomisp_mrfld_power_down(isp)) - dev_err(&dev->dev, "Failed to switch off ISP\n"); + dev_err(&pdev->dev, "Failed to switch off ISP\n"); atomisp_dev_alloc_fail: - pcim_iounmap_regions(dev, 1 << ATOM_ISP_PCI_BAR); + pcim_iounmap_regions(pdev, 1 << ATOM_ISP_PCI_BAR); ioremap_fail: return err; } -static void atomisp_pci_remove(struct pci_dev *dev) +static void atomisp_pci_remove(struct pci_dev *pdev) { - struct atomisp_device *isp = (struct atomisp_device *) - pci_get_drvdata(dev); + struct atomisp_device *isp = pci_get_drvdata(pdev); - dev_info(&dev->dev, "Removing atomisp driver\n"); + dev_info(&pdev->dev, "Removing atomisp driver\n"); atomisp_drvfs_exit(); @@ -1906,11 +1875,11 @@ static void atomisp_pci_remove(struct pci_dev *dev) ia_css_unload_firmware(); hmm_cleanup(); - pm_runtime_forbid(&dev->dev); - pm_runtime_get_noresume(&dev->dev); + pm_runtime_forbid(&pdev->dev); + pm_runtime_get_noresume(&pdev->dev); cpu_latency_qos_remove_request(&isp->pm_qos); - atomisp_msi_irq_uninit(isp, dev); + atomisp_msi_irq_uninit(isp); atomisp_unregister_entities(isp); destroy_workqueue(isp->wdt_work_queue); diff --git a/drivers/staging/media/atomisp/pci/base/refcount/src/refcount.c b/drivers/staging/media/atomisp/pci/base/refcount/src/refcount.c index cf02737cf8d4..a9c881631f4a 100644 --- a/drivers/staging/media/atomisp/pci/base/refcount/src/refcount.c +++ b/drivers/staging/media/atomisp/pci/base/refcount/src/refcount.c @@ -48,7 +48,7 @@ static struct ia_css_refcount_entry *refcount_find_entry(ia_css_ptr ptr, return NULL; if (!myrefcount.items) { ia_css_debug_dtrace(IA_CSS_DEBUG_ERROR, - "refcount_find_entry(): Ref count not initialized!\n"); + "%s(): Ref count not initialized!\n", __func__); return NULL; } @@ -73,12 +73,12 @@ int ia_css_refcount_init(uint32_t size) if (size == 0) { ia_css_debug_dtrace(IA_CSS_DEBUG_TRACE, - "ia_css_refcount_init(): Size of 0 for Ref count init!\n"); + "%s(): Size of 0 for Ref count init!\n", __func__); return -EINVAL; } if (myrefcount.items) { ia_css_debug_dtrace(IA_CSS_DEBUG_TRACE, - "ia_css_refcount_init(): Ref count is already initialized\n"); + "%s(): Ref count is already initialized\n", __func__); return -EINVAL; } myrefcount.items = @@ -99,7 +99,7 @@ void ia_css_refcount_uninit(void) u32 i; ia_css_debug_dtrace(IA_CSS_DEBUG_TRACE, - "ia_css_refcount_uninit() entry\n"); + "%s() entry\n", __func__); for (i = 0; i < myrefcount.size; i++) { /* driver verifier tool has issues with &arr[i] and prefers arr + i; as these are actually equivalent @@ -120,7 +120,7 @@ void ia_css_refcount_uninit(void) myrefcount.items = NULL; myrefcount.size = 0; ia_css_debug_dtrace(IA_CSS_DEBUG_TRACE, - "ia_css_refcount_uninit() leave\n"); + "%s() leave\n", __func__); } ia_css_ptr ia_css_refcount_increment(s32 id, ia_css_ptr ptr) @@ -133,7 +133,7 @@ ia_css_ptr ia_css_refcount_increment(s32 id, ia_css_ptr ptr) entry = refcount_find_entry(ptr, false); ia_css_debug_dtrace(IA_CSS_DEBUG_TRACE, - "ia_css_refcount_increment(%x) 0x%x\n", id, ptr); + "%s(%x) 0x%x\n", __func__, id, ptr); if (!entry) { entry = refcount_find_entry(ptr, true); @@ -145,7 +145,7 @@ ia_css_ptr ia_css_refcount_increment(s32 id, ia_css_ptr ptr) if (entry->id != id) { ia_css_debug_dtrace(IA_CSS_DEBUG_ERROR, - "ia_css_refcount_increment(): Ref count IDS do not match!\n"); + "%s(): Ref count IDS do not match!\n", __func__); return mmgr_NULL; } @@ -165,7 +165,7 @@ bool ia_css_refcount_decrement(s32 id, ia_css_ptr ptr) struct ia_css_refcount_entry *entry; ia_css_debug_dtrace(IA_CSS_DEBUG_TRACE, - "ia_css_refcount_decrement(%x) 0x%x\n", id, ptr); + "%s(%x) 0x%x\n", __func__, id, ptr); if (ptr == mmgr_NULL) return false; @@ -175,7 +175,7 @@ bool ia_css_refcount_decrement(s32 id, ia_css_ptr ptr) if (entry) { if (entry->id != id) { ia_css_debug_dtrace(IA_CSS_DEBUG_ERROR, - "ia_css_refcount_decrement(): Ref count IDS do not match!\n"); + "%s(): Ref count IDS do not match!\n", __func__); return false; } if (entry->count > 0) { @@ -225,8 +225,8 @@ void ia_css_refcount_clear(s32 id, clear_func clear_func_ptr) u32 count = 0; assert(clear_func_ptr); - ia_css_debug_dtrace(IA_CSS_DEBUG_TRACE, "ia_css_refcount_clear(%x)\n", - id); + ia_css_debug_dtrace(IA_CSS_DEBUG_TRACE, "%s(%x)\n", + __func__, id); for (i = 0; i < myrefcount.size; i++) { /* driver verifier tool has issues with &arr[i] @@ -236,14 +236,14 @@ void ia_css_refcount_clear(s32 id, clear_func clear_func_ptr) entry = myrefcount.items + i; if ((entry->data != mmgr_NULL) && (entry->id == id)) { ia_css_debug_dtrace(IA_CSS_DEBUG_TRACE, - "ia_css_refcount_clear: %x: 0x%x\n", + "%s: %x: 0x%x\n", __func__, id, entry->data); if (clear_func_ptr) { /* clear using provided function */ clear_func_ptr(entry->data); } else { ia_css_debug_dtrace(IA_CSS_DEBUG_TRACE, - "ia_css_refcount_clear: using hmm_free: no clear_func\n"); + "%s: using hmm_free: no clear_func\n", __func__); hmm_free(entry->data); } @@ -260,7 +260,7 @@ void ia_css_refcount_clear(s32 id, clear_func clear_func_ptr) } } ia_css_debug_dtrace(IA_CSS_DEBUG_TRACE, - "ia_css_refcount_clear(%x): cleared %d\n", id, + "%s(%x): cleared %d\n", __func__, id, count); } diff --git a/drivers/staging/media/atomisp/pci/hive_types.h b/drivers/staging/media/atomisp/pci/hive_types.h index addda9b81d7b..4b8a679fb672 100644 --- a/drivers/staging/media/atomisp/pci/hive_types.h +++ b/drivers/staging/media/atomisp/pci/hive_types.h @@ -52,32 +52,14 @@ typedef unsigned short hive_uint16; typedef unsigned int hive_uint32; typedef unsigned long long hive_uint64; -/* by default assume 32 bit master port (both data and address) */ -#ifndef HRT_DATA_WIDTH -#define HRT_DATA_WIDTH 32 -#endif -#ifndef HRT_ADDRESS_WIDTH -#define HRT_ADDRESS_WIDTH 32 -#endif - +#define HRT_DATA_WIDTH 32 +#define HRT_ADDRESS_WIDTH 64 #define HRT_DATA_BYTES (HRT_DATA_WIDTH / 8) #define HRT_ADDRESS_BYTES (HRT_ADDRESS_WIDTH / 8) +#define SIZEOF_HRT_REG (HRT_DATA_WIDTH >> 3) -#if HRT_DATA_WIDTH == 64 -typedef hive_uint64 hrt_data; -#elif HRT_DATA_WIDTH == 32 typedef hive_uint32 hrt_data; -#else -#error data width not supported -#endif - -#if HRT_ADDRESS_WIDTH == 64 typedef hive_uint64 hrt_address; -#elif HRT_ADDRESS_WIDTH == 32 -typedef hive_uint32 hrt_address; -#else -#error adddres width not supported -#endif /* use 64 bit addresses in simulation, where possible */ typedef hive_uint64 hive_sim_address; diff --git a/drivers/staging/media/atomisp/pci/hmm/hmm.c b/drivers/staging/media/atomisp/pci/hmm/hmm.c index 42fef1779862..2bd39b4939f1 100644 --- a/drivers/staging/media/atomisp/pci/hmm/hmm.c +++ b/drivers/staging/media/atomisp/pci/hmm/hmm.c @@ -735,11 +735,11 @@ ia_css_ptr hmm_host_vaddr_to_hrt_vaddr(const void *ptr) void hmm_show_mem_stat(const char *func, const int line) { - trace_printk("tol_cnt=%d usr_size=%d res_size=%d res_cnt=%d sys_size=%d dyc_thr=%d dyc_size=%d.\n", - hmm_mem_stat.tol_cnt, - hmm_mem_stat.usr_size, hmm_mem_stat.res_size, - hmm_mem_stat.res_cnt, hmm_mem_stat.sys_size, - hmm_mem_stat.dyc_thr, hmm_mem_stat.dyc_size); + pr_info("tol_cnt=%d usr_size=%d res_size=%d res_cnt=%d sys_size=%d dyc_thr=%d dyc_size=%d.\n", + hmm_mem_stat.tol_cnt, + hmm_mem_stat.usr_size, hmm_mem_stat.res_size, + hmm_mem_stat.res_cnt, hmm_mem_stat.sys_size, + hmm_mem_stat.dyc_thr, hmm_mem_stat.dyc_size); } void hmm_init_mem_stat(int res_pgnr, int dyc_en, int dyc_pgnr) diff --git a/drivers/staging/media/atomisp/pci/isp2400_system_global.h b/drivers/staging/media/atomisp/pci/isp2400_system_global.h index d87ddf1d2fe9..74fff465e8e8 100644 --- a/drivers/staging/media/atomisp/pci/isp2400_system_global.h +++ b/drivers/staging/media/atomisp/pci/isp2400_system_global.h @@ -13,306 +13,4 @@ * more details. */ -#ifndef __SYSTEM_GLOBAL_H_INCLUDED__ -#define __SYSTEM_GLOBAL_H_INCLUDED__ - -#include <hive_isp_css_defs.h> -#include <type_support.h> - -/* - * The longest allowed (uninteruptible) bus transfer, does not - * take stalling into account - */ -#define HIVE_ISP_MAX_BURST_LENGTH 1024 - -/* - * Maximum allowed burst length in words for the ISP DMA - */ -#define ISP_DMA_MAX_BURST_LENGTH 128 - -/* - * Create a list of HAS and IS properties that defines the system - * - * The configuration assumes the following - * - The system is hetereogeneous; Multiple cells and devices classes - * - The cell and device instances are homogeneous, each device type - * belongs to the same class - * - Device instances supporting a subset of the class capabilities are - * allowed - * - * We could manage different device classes through the enumerated - * lists (C) or the use of classes (C++), but that is presently not - * fully supported - * - * N.B. the 3 input formatters are of 2 different classess - */ - #define USE_INPUT_SYSTEM_VERSION_2 - -#define HAS_MMU_VERSION_2 -#define HAS_DMA_VERSION_2 -#define HAS_GDC_VERSION_2 -#define HAS_VAMEM_VERSION_2 -#define HAS_HMEM_VERSION_1 -#define HAS_BAMEM_VERSION_2 -#define HAS_IRQ_VERSION_2 -#define HAS_IRQ_MAP_VERSION_2 -#define HAS_INPUT_FORMATTER_VERSION_2 -/* 2401: HAS_INPUT_SYSTEM_VERSION_2401 */ -#define HAS_INPUT_SYSTEM_VERSION_2 -#define HAS_BUFFERED_SENSOR -#define HAS_FIFO_MONITORS_VERSION_2 -/* #define HAS_GP_REGS_VERSION_2 */ -#define HAS_GP_DEVICE_VERSION_2 -#define HAS_GPIO_VERSION_1 -#define HAS_TIMED_CTRL_VERSION_1 -#define HAS_RX_VERSION_2 - -#define DMA_DDR_TO_VAMEM_WORKAROUND -#define DMA_DDR_TO_HMEM_WORKAROUND - -/* - * Semi global. "HRT" is accessible from SP, but the HRT types do not fully apply - */ -#define HRT_VADDRESS_WIDTH 32 -//#define HRT_ADDRESS_WIDTH 64 /* Surprise, this is a local property*/ -#define HRT_DATA_WIDTH 32 - -#define SIZEOF_HRT_REG (HRT_DATA_WIDTH >> 3) -#define HIVE_ISP_CTRL_DATA_BYTES (HIVE_ISP_CTRL_DATA_WIDTH / 8) - -/* The main bus connecting all devices */ -#define HRT_BUS_WIDTH HIVE_ISP_CTRL_DATA_WIDTH -#define HRT_BUS_BYTES HIVE_ISP_CTRL_DATA_BYTES - -/* per-frame parameter handling support */ -#define SH_CSS_ENABLE_PER_FRAME_PARAMS - -typedef u32 hrt_bus_align_t; - -/* - * Enumerate the devices, device access through the API is by ID, through the DLI by address - * The enumerator terminators are used to size the wiring arrays and as an exception value. - */ -typedef enum { - DDR0_ID = 0, - N_DDR_ID -} ddr_ID_t; - -typedef enum { - ISP0_ID = 0, - N_ISP_ID -} isp_ID_t; - -typedef enum { - SP0_ID = 0, - N_SP_ID -} sp_ID_t; - -typedef enum { - MMU0_ID = 0, - MMU1_ID, - N_MMU_ID -} mmu_ID_t; - -typedef enum { - DMA0_ID = 0, - N_DMA_ID -} dma_ID_t; - -typedef enum { - GDC0_ID = 0, - GDC1_ID, - N_GDC_ID -} gdc_ID_t; - -#define N_GDC_ID_CPP 2 // this extra define is needed because we want to use it also in the preprocessor, and that doesn't work with enums. - -typedef enum { - VAMEM0_ID = 0, - VAMEM1_ID, - VAMEM2_ID, - N_VAMEM_ID -} vamem_ID_t; - -typedef enum { - BAMEM0_ID = 0, - N_BAMEM_ID -} bamem_ID_t; - -typedef enum { - HMEM0_ID = 0, - N_HMEM_ID -} hmem_ID_t; - -/* -typedef enum { - IRQ0_ID = 0, - N_IRQ_ID -} irq_ID_t; -*/ - -typedef enum { - IRQ0_ID = 0, // GP IRQ block - IRQ1_ID, // Input formatter - IRQ2_ID, // input system - IRQ3_ID, // input selector - N_IRQ_ID -} irq_ID_t; - -typedef enum { - FIFO_MONITOR0_ID = 0, - N_FIFO_MONITOR_ID -} fifo_monitor_ID_t; - -/* - * Deprecated: Since all gp_reg instances are different - * and put in the address maps of other devices we cannot - * enumerate them as that assumes the instrances are the - * same. - * - * We define a single GP_DEVICE containing all gp_regs - * w.r.t. a single base address - * -typedef enum { - GP_REGS0_ID = 0, - N_GP_REGS_ID -} gp_regs_ID_t; - */ -typedef enum { - GP_DEVICE0_ID = 0, - N_GP_DEVICE_ID -} gp_device_ID_t; - -typedef enum { - GP_TIMER0_ID = 0, - GP_TIMER1_ID, - GP_TIMER2_ID, - GP_TIMER3_ID, - GP_TIMER4_ID, - GP_TIMER5_ID, - GP_TIMER6_ID, - GP_TIMER7_ID, - N_GP_TIMER_ID -} gp_timer_ID_t; - -typedef enum { - GPIO0_ID = 0, - N_GPIO_ID -} gpio_ID_t; - -typedef enum { - TIMED_CTRL0_ID = 0, - N_TIMED_CTRL_ID -} timed_ctrl_ID_t; - -typedef enum { - INPUT_FORMATTER0_ID = 0, - INPUT_FORMATTER1_ID, - INPUT_FORMATTER2_ID, - INPUT_FORMATTER3_ID, - N_INPUT_FORMATTER_ID -} input_formatter_ID_t; - -/* The IF RST is outside the IF */ -#define INPUT_FORMATTER0_SRST_OFFSET 0x0824 -#define INPUT_FORMATTER1_SRST_OFFSET 0x0624 -#define INPUT_FORMATTER2_SRST_OFFSET 0x0424 -#define INPUT_FORMATTER3_SRST_OFFSET 0x0224 - -#define INPUT_FORMATTER0_SRST_MASK 0x0001 -#define INPUT_FORMATTER1_SRST_MASK 0x0002 -#define INPUT_FORMATTER2_SRST_MASK 0x0004 -#define INPUT_FORMATTER3_SRST_MASK 0x0008 - -typedef enum { - INPUT_SYSTEM0_ID = 0, - N_INPUT_SYSTEM_ID -} input_system_ID_t; - -typedef enum { - RX0_ID = 0, - N_RX_ID -} rx_ID_t; - -enum mipi_port_id { - MIPI_PORT0_ID = 0, - MIPI_PORT1_ID, - MIPI_PORT2_ID, - N_MIPI_PORT_ID -}; - -#define N_RX_CHANNEL_ID 4 - -/* Generic port enumeration with an internal port type ID */ -typedef enum { - CSI_PORT0_ID = 0, - CSI_PORT1_ID, - CSI_PORT2_ID, - TPG_PORT0_ID, - PRBS_PORT0_ID, - FIFO_PORT0_ID, - MEMORY_PORT0_ID, - N_INPUT_PORT_ID -} input_port_ID_t; - -typedef enum { - CAPTURE_UNIT0_ID = 0, - CAPTURE_UNIT1_ID, - CAPTURE_UNIT2_ID, - ACQUISITION_UNIT0_ID, - DMA_UNIT0_ID, - CTRL_UNIT0_ID, - GPREGS_UNIT0_ID, - FIFO_UNIT0_ID, - IRQ_UNIT0_ID, - N_SUB_SYSTEM_ID -} sub_system_ID_t; - -#define N_CAPTURE_UNIT_ID 3 -#define N_ACQUISITION_UNIT_ID 1 -#define N_CTRL_UNIT_ID 1 - -enum ia_css_isp_memories { - IA_CSS_ISP_PMEM0 = 0, - IA_CSS_ISP_DMEM0, - IA_CSS_ISP_VMEM0, - IA_CSS_ISP_VAMEM0, - IA_CSS_ISP_VAMEM1, - IA_CSS_ISP_VAMEM2, - IA_CSS_ISP_HMEM0, - IA_CSS_SP_DMEM0, - IA_CSS_DDR, - N_IA_CSS_MEMORIES -}; - -#define IA_CSS_NUM_MEMORIES 9 -/* For driver compatibility */ -#define N_IA_CSS_ISP_MEMORIES IA_CSS_NUM_MEMORIES -#define IA_CSS_NUM_ISP_MEMORIES IA_CSS_NUM_MEMORIES - -#if 0 -typedef enum { - dev_chn, /* device channels, external resource */ - ext_mem, /* external memories */ - int_mem, /* internal memories */ - int_chn /* internal channels, user defined */ -} resource_type_t; - -/* if this enum is extended with other memory resources, pls also extend the function resource_to_memptr() */ -typedef enum { - vied_nci_dev_chn_dma_ext0, - int_mem_vmem0, - int_mem_dmem0 -} resource_id_t; - -/* enum listing the different memories within a program group. - This enum is used in the mem_ptr_t type */ -typedef enum { - buf_mem_invalid = 0, - buf_mem_vmem_prog0, - buf_mem_dmem_prog0 -} buf_mem_t; - -#endif -#endif /* __SYSTEM_GLOBAL_H_INCLUDED__ */ diff --git a/drivers/staging/media/atomisp/pci/isp2400_system_local.h b/drivers/staging/media/atomisp/pci/isp2400_system_local.h deleted file mode 100644 index 675b8e5bdcc1..000000000000 --- a/drivers/staging/media/atomisp/pci/isp2400_system_local.h +++ /dev/null @@ -1,321 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Support for Intel Camera Imaging ISP subsystem. - * Copyright (c) 2010-2015, Intel Corporation. - * - * 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. - */ - -#ifndef __SYSTEM_LOCAL_H_INCLUDED__ -#define __SYSTEM_LOCAL_H_INCLUDED__ - -#ifdef HRT_ISP_CSS_CUSTOM_HOST -#ifndef HRT_USE_VIR_ADDRS -#define HRT_USE_VIR_ADDRS -#endif -#endif - -#include "system_global.h" - -/* HRT assumes 32 by default (see Linux/include/hive_types.h), overrule it in case it is different */ -#undef HRT_ADDRESS_WIDTH -#define HRT_ADDRESS_WIDTH 64 /* Surprise, this is a local property */ - -/* This interface is deprecated */ -#include "hive_types.h" - -/* - * Cell specific address maps - */ -#if HRT_ADDRESS_WIDTH == 64 - -#define GP_FIFO_BASE ((hrt_address)0x0000000000090104) /* This is NOT a base address */ - -/* DDR */ -static const hrt_address DDR_BASE[N_DDR_ID] = { - (hrt_address)0x0000000120000000ULL -}; - -/* ISP */ -static const hrt_address ISP_CTRL_BASE[N_ISP_ID] = { - (hrt_address)0x0000000000020000ULL -}; - -static const hrt_address ISP_DMEM_BASE[N_ISP_ID] = { - (hrt_address)0x0000000000200000ULL -}; - -static const hrt_address ISP_BAMEM_BASE[N_BAMEM_ID] = { - (hrt_address)0x0000000000100000ULL -}; - -static const hrt_address ISP_VAMEM_BASE[N_VAMEM_ID] = { - (hrt_address)0x00000000001C0000ULL, - (hrt_address)0x00000000001D0000ULL, - (hrt_address)0x00000000001E0000ULL -}; - -static const hrt_address ISP_HMEM_BASE[N_HMEM_ID] = { - (hrt_address)0x00000000001F0000ULL -}; - -/* SP */ -static const hrt_address SP_CTRL_BASE[N_SP_ID] = { - (hrt_address)0x0000000000010000ULL -}; - -static const hrt_address SP_DMEM_BASE[N_SP_ID] = { - (hrt_address)0x0000000000300000ULL -}; - -static const hrt_address SP_PMEM_BASE[N_SP_ID] = { - (hrt_address)0x00000000000B0000ULL -}; - -/* MMU */ -/* - * MMU0_ID: The data MMU - * MMU1_ID: The icache MMU - */ -static const hrt_address MMU_BASE[N_MMU_ID] = { - (hrt_address)0x0000000000070000ULL, - (hrt_address)0x00000000000A0000ULL -}; - -/* DMA */ -static const hrt_address DMA_BASE[N_DMA_ID] = { - (hrt_address)0x0000000000040000ULL -}; - -/* IRQ */ -static const hrt_address IRQ_BASE[N_IRQ_ID] = { - (hrt_address)0x0000000000000500ULL, - (hrt_address)0x0000000000030A00ULL, - (hrt_address)0x000000000008C000ULL, - (hrt_address)0x0000000000090200ULL -}; - -/* - (hrt_address)0x0000000000000500ULL}; - */ - -/* GDC */ -static const hrt_address GDC_BASE[N_GDC_ID] = { - (hrt_address)0x0000000000050000ULL, - (hrt_address)0x0000000000060000ULL -}; - -/* FIFO_MONITOR (not a subset of GP_DEVICE) */ -static const hrt_address FIFO_MONITOR_BASE[N_FIFO_MONITOR_ID] = { - (hrt_address)0x0000000000000000ULL -}; - -/* -static const hrt_address GP_REGS_BASE[N_GP_REGS_ID] = { - (hrt_address)0x0000000000000000ULL}; - -static const hrt_address GP_DEVICE_BASE[N_GP_DEVICE_ID] = { - (hrt_address)0x0000000000090000ULL}; -*/ - -/* GP_DEVICE (single base for all separate GP_REG instances) */ -static const hrt_address GP_DEVICE_BASE[N_GP_DEVICE_ID] = { - (hrt_address)0x0000000000000000ULL -}; - -/*GP TIMER , all timer registers are inter-twined, - * so, having multiple base addresses for - * different timers does not help*/ -static const hrt_address GP_TIMER_BASE = - (hrt_address)0x0000000000000600ULL; -/* GPIO */ -static const hrt_address GPIO_BASE[N_GPIO_ID] = { - (hrt_address)0x0000000000000400ULL -}; - -/* TIMED_CTRL */ -static const hrt_address TIMED_CTRL_BASE[N_TIMED_CTRL_ID] = { - (hrt_address)0x0000000000000100ULL -}; - -/* INPUT_FORMATTER */ -static const hrt_address INPUT_FORMATTER_BASE[N_INPUT_FORMATTER_ID] = { - (hrt_address)0x0000000000030000ULL, - (hrt_address)0x0000000000030200ULL, - (hrt_address)0x0000000000030400ULL, - (hrt_address)0x0000000000030600ULL -}; /* memcpy() */ - -/* INPUT_SYSTEM */ -static const hrt_address INPUT_SYSTEM_BASE[N_INPUT_SYSTEM_ID] = { - (hrt_address)0x0000000000080000ULL -}; - -/* (hrt_address)0x0000000000081000ULL, */ /* capture A */ -/* (hrt_address)0x0000000000082000ULL, */ /* capture B */ -/* (hrt_address)0x0000000000083000ULL, */ /* capture C */ -/* (hrt_address)0x0000000000084000ULL, */ /* Acquisition */ -/* (hrt_address)0x0000000000085000ULL, */ /* DMA */ -/* (hrt_address)0x0000000000089000ULL, */ /* ctrl */ -/* (hrt_address)0x000000000008A000ULL, */ /* GP regs */ -/* (hrt_address)0x000000000008B000ULL, */ /* FIFO */ -/* (hrt_address)0x000000000008C000ULL, */ /* IRQ */ - -/* RX, the MIPI lane control regs start at offset 0 */ -static const hrt_address RX_BASE[N_RX_ID] = { - (hrt_address)0x0000000000080100ULL -}; - -#elif HRT_ADDRESS_WIDTH == 32 - -#define GP_FIFO_BASE ((hrt_address)0x00090104) /* This is NOT a base address */ - -/* DDR : Attention, this value not defined in 32-bit */ -static const hrt_address DDR_BASE[N_DDR_ID] = { - (hrt_address)0x00000000UL -}; - -/* ISP */ -static const hrt_address ISP_CTRL_BASE[N_ISP_ID] = { - (hrt_address)0x00020000UL -}; - -static const hrt_address ISP_DMEM_BASE[N_ISP_ID] = { - (hrt_address)0x00200000UL -}; - -static const hrt_address ISP_BAMEM_BASE[N_BAMEM_ID] = { - (hrt_address)0x100000UL -}; - -static const hrt_address ISP_VAMEM_BASE[N_VAMEM_ID] = { - (hrt_address)0xffffffffUL, - (hrt_address)0xffffffffUL, - (hrt_address)0xffffffffUL -}; - -static const hrt_address ISP_HMEM_BASE[N_HMEM_ID] = { - (hrt_address)0xffffffffUL -}; - -/* SP */ -static const hrt_address SP_CTRL_BASE[N_SP_ID] = { - (hrt_address)0x00010000UL -}; - -static const hrt_address SP_DMEM_BASE[N_SP_ID] = { - (hrt_address)0x00300000UL -}; - -static const hrt_address SP_PMEM_BASE[N_SP_ID] = { - (hrt_address)0x000B0000UL -}; - -/* MMU */ -/* - * MMU0_ID: The data MMU - * MMU1_ID: The icache MMU - */ -static const hrt_address MMU_BASE[N_MMU_ID] = { - (hrt_address)0x00070000UL, - (hrt_address)0x000A0000UL -}; - -/* DMA */ -static const hrt_address DMA_BASE[N_DMA_ID] = { - (hrt_address)0x00040000UL -}; - -/* IRQ */ -static const hrt_address IRQ_BASE[N_IRQ_ID] = { - (hrt_address)0x00000500UL, - (hrt_address)0x00030A00UL, - (hrt_address)0x0008C000UL, - (hrt_address)0x00090200UL -}; - -/* - (hrt_address)0x00000500UL}; - */ - -/* GDC */ -static const hrt_address GDC_BASE[N_GDC_ID] = { - (hrt_address)0x00050000UL, - (hrt_address)0x00060000UL -}; - -/* FIFO_MONITOR (not a subset of GP_DEVICE) */ -static const hrt_address FIFO_MONITOR_BASE[N_FIFO_MONITOR_ID] = { - (hrt_address)0x00000000UL -}; - -/* -static const hrt_address GP_REGS_BASE[N_GP_REGS_ID] = { - (hrt_address)0x00000000UL}; - -static const hrt_address GP_DEVICE_BASE[N_GP_DEVICE_ID] = { - (hrt_address)0x00090000UL}; -*/ - -/* GP_DEVICE (single base for all separate GP_REG instances) */ -static const hrt_address GP_DEVICE_BASE[N_GP_DEVICE_ID] = { - (hrt_address)0x00000000UL -}; - -/*GP TIMER , all timer registers are inter-twined, - * so, having multiple base addresses for - * different timers does not help*/ -static const hrt_address GP_TIMER_BASE = - (hrt_address)0x00000600UL; - -/* GPIO */ -static const hrt_address GPIO_BASE[N_GPIO_ID] = { - (hrt_address)0x00000400UL -}; - -/* TIMED_CTRL */ -static const hrt_address TIMED_CTRL_BASE[N_TIMED_CTRL_ID] = { - (hrt_address)0x00000100UL -}; - -/* INPUT_FORMATTER */ -static const hrt_address INPUT_FORMATTER_BASE[N_INPUT_FORMATTER_ID] = { - (hrt_address)0x00030000UL, - (hrt_address)0x00030200UL, - (hrt_address)0x00030400UL -}; - -/* (hrt_address)0x00030600UL, */ /* memcpy() */ - -/* INPUT_SYSTEM */ -static const hrt_address INPUT_SYSTEM_BASE[N_INPUT_SYSTEM_ID] = { - (hrt_address)0x00080000UL -}; - -/* (hrt_address)0x00081000UL, */ /* capture A */ -/* (hrt_address)0x00082000UL, */ /* capture B */ -/* (hrt_address)0x00083000UL, */ /* capture C */ -/* (hrt_address)0x00084000UL, */ /* Acquisition */ -/* (hrt_address)0x00085000UL, */ /* DMA */ -/* (hrt_address)0x00089000UL, */ /* ctrl */ -/* (hrt_address)0x0008A000UL, */ /* GP regs */ -/* (hrt_address)0x0008B000UL, */ /* FIFO */ -/* (hrt_address)0x0008C000UL, */ /* IRQ */ - -/* RX, the MIPI lane control regs start at offset 0 */ -static const hrt_address RX_BASE[N_RX_ID] = { - (hrt_address)0x00080100UL -}; - -#else -#error "system_local.h: HRT_ADDRESS_WIDTH must be one of {32,64}" -#endif - -#endif /* __SYSTEM_LOCAL_H_INCLUDED__ */ diff --git a/drivers/staging/media/atomisp/pci/isp2401_system_global.h b/drivers/staging/media/atomisp/pci/isp2401_system_global.h index 8bb2a956f983..27cd2535bab8 100644 --- a/drivers/staging/media/atomisp/pci/isp2401_system_global.h +++ b/drivers/staging/media/atomisp/pci/isp2401_system_global.h @@ -13,415 +13,7 @@ * more details. */ -#ifndef __SYSTEM_GLOBAL_H_INCLUDED__ -#define __SYSTEM_GLOBAL_H_INCLUDED__ - -#include <hive_isp_css_defs.h> -#include <type_support.h> - -/* - * The longest allowed (uninteruptible) bus transfer, does not - * take stalling into account - */ -#define HIVE_ISP_MAX_BURST_LENGTH 1024 - -/* - * Maximum allowed burst length in words for the ISP DMA - * This value is set to 2 to prevent the ISP DMA from blocking - * the bus for too long; as the input system can only buffer - * 2 lines on Moorefield and Cherrytrail, the input system buffers - * may overflow if blocked for too long (BZ 2726). - */ -#define ISP_DMA_MAX_BURST_LENGTH 2 - -/* - * Create a list of HAS and IS properties that defines the system - * - * The configuration assumes the following - * - The system is hetereogeneous; Multiple cells and devices classes - * - The cell and device instances are homogeneous, each device type - * belongs to the same class - * - Device instances supporting a subset of the class capabilities are - * allowed - * - * We could manage different device classes through the enumerated - * lists (C) or the use of classes (C++), but that is presently not - * fully supported - * - * N.B. the 3 input formatters are of 2 different classess - */ - +#define HAS_NO_INPUT_FORMATTER #define USE_INPUT_SYSTEM_VERSION_2401 - -#define HAS_MMU_VERSION_2 -#define HAS_DMA_VERSION_2 -#define HAS_GDC_VERSION_2 -#define HAS_VAMEM_VERSION_2 -#define HAS_HMEM_VERSION_1 -#define HAS_BAMEM_VERSION_2 -#define HAS_IRQ_VERSION_2 -#define HAS_IRQ_MAP_VERSION_2 -#define HAS_INPUT_FORMATTER_VERSION_2 -/* 2401: HAS_INPUT_SYSTEM_VERSION_3 */ -/* 2400: HAS_INPUT_SYSTEM_VERSION_2 */ -#define HAS_INPUT_SYSTEM_VERSION_2 #define HAS_INPUT_SYSTEM_VERSION_2401 -#define HAS_BUFFERED_SENSOR -#define HAS_FIFO_MONITORS_VERSION_2 -/* #define HAS_GP_REGS_VERSION_2 */ -#define HAS_GP_DEVICE_VERSION_2 -#define HAS_GPIO_VERSION_1 -#define HAS_TIMED_CTRL_VERSION_1 -#define HAS_RX_VERSION_2 -#define HAS_NO_INPUT_FORMATTER -/*#define HAS_NO_PACKED_RAW_PIXELS*/ -/*#define HAS_NO_DVS_6AXIS_CONFIG_UPDATE*/ - -#define DMA_DDR_TO_VAMEM_WORKAROUND -#define DMA_DDR_TO_HMEM_WORKAROUND - -/* - * Semi global. "HRT" is accessible from SP, but - * the HRT types do not fully apply - */ -#define HRT_VADDRESS_WIDTH 32 -/* Surprise, this is a local property*/ -/*#define HRT_ADDRESS_WIDTH 64 */ -#define HRT_DATA_WIDTH 32 - -#define SIZEOF_HRT_REG (HRT_DATA_WIDTH >> 3) -#define HIVE_ISP_CTRL_DATA_BYTES (HIVE_ISP_CTRL_DATA_WIDTH / 8) - -/* The main bus connecting all devices */ -#define HRT_BUS_WIDTH HIVE_ISP_CTRL_DATA_WIDTH -#define HRT_BUS_BYTES HIVE_ISP_CTRL_DATA_BYTES - #define CSI2P_DISABLE_ISYS2401_ONLINE_MODE - -/* per-frame parameter handling support */ -#define SH_CSS_ENABLE_PER_FRAME_PARAMS - -typedef u32 hrt_bus_align_t; - -/* - * Enumerate the devices, device access through the API is by ID, - * through the DLI by address. The enumerator terminators are used - * to size the wiring arrays and as an exception value. - */ -typedef enum { - DDR0_ID = 0, - N_DDR_ID -} ddr_ID_t; - -typedef enum { - ISP0_ID = 0, - N_ISP_ID -} isp_ID_t; - -typedef enum { - SP0_ID = 0, - N_SP_ID -} sp_ID_t; - -typedef enum { - MMU0_ID = 0, - MMU1_ID, - N_MMU_ID -} mmu_ID_t; - -typedef enum { - DMA0_ID = 0, - N_DMA_ID -} dma_ID_t; - -typedef enum { - GDC0_ID = 0, - GDC1_ID, - N_GDC_ID -} gdc_ID_t; - -/* this extra define is needed because we want to use it also - in the preprocessor, and that doesn't work with enums. - */ -#define N_GDC_ID_CPP 2 - -typedef enum { - VAMEM0_ID = 0, - VAMEM1_ID, - VAMEM2_ID, - N_VAMEM_ID -} vamem_ID_t; - -typedef enum { - BAMEM0_ID = 0, - N_BAMEM_ID -} bamem_ID_t; - -typedef enum { - HMEM0_ID = 0, - N_HMEM_ID -} hmem_ID_t; - -typedef enum { - ISYS_IRQ0_ID = 0, /* port a */ - ISYS_IRQ1_ID, /* port b */ - ISYS_IRQ2_ID, /* port c */ - N_ISYS_IRQ_ID -} isys_irq_ID_t; - -typedef enum { - IRQ0_ID = 0, /* GP IRQ block */ - IRQ1_ID, /* Input formatter */ - IRQ2_ID, /* input system */ - IRQ3_ID, /* input selector */ - N_IRQ_ID -} irq_ID_t; - -typedef enum { - FIFO_MONITOR0_ID = 0, - N_FIFO_MONITOR_ID -} fifo_monitor_ID_t; - -/* - * Deprecated: Since all gp_reg instances are different - * and put in the address maps of other devices we cannot - * enumerate them as that assumes the instrances are the - * same. - * - * We define a single GP_DEVICE containing all gp_regs - * w.r.t. a single base address - * -typedef enum { - GP_REGS0_ID = 0, - N_GP_REGS_ID -} gp_regs_ID_t; - */ -typedef enum { - GP_DEVICE0_ID = 0, - N_GP_DEVICE_ID -} gp_device_ID_t; - -typedef enum { - GP_TIMER0_ID = 0, - GP_TIMER1_ID, - GP_TIMER2_ID, - GP_TIMER3_ID, - GP_TIMER4_ID, - GP_TIMER5_ID, - GP_TIMER6_ID, - GP_TIMER7_ID, - N_GP_TIMER_ID -} gp_timer_ID_t; - -typedef enum { - GPIO0_ID = 0, - N_GPIO_ID -} gpio_ID_t; - -typedef enum { - TIMED_CTRL0_ID = 0, - N_TIMED_CTRL_ID -} timed_ctrl_ID_t; - -typedef enum { - INPUT_FORMATTER0_ID = 0, - INPUT_FORMATTER1_ID, - INPUT_FORMATTER2_ID, - INPUT_FORMATTER3_ID, - N_INPUT_FORMATTER_ID -} input_formatter_ID_t; - -/* The IF RST is outside the IF */ -#define INPUT_FORMATTER0_SRST_OFFSET 0x0824 -#define INPUT_FORMATTER1_SRST_OFFSET 0x0624 -#define INPUT_FORMATTER2_SRST_OFFSET 0x0424 -#define INPUT_FORMATTER3_SRST_OFFSET 0x0224 - -#define INPUT_FORMATTER0_SRST_MASK 0x0001 -#define INPUT_FORMATTER1_SRST_MASK 0x0002 -#define INPUT_FORMATTER2_SRST_MASK 0x0004 -#define INPUT_FORMATTER3_SRST_MASK 0x0008 - -typedef enum { - INPUT_SYSTEM0_ID = 0, - N_INPUT_SYSTEM_ID -} input_system_ID_t; - -typedef enum { - RX0_ID = 0, - N_RX_ID -} rx_ID_t; - -enum mipi_port_id { - MIPI_PORT0_ID = 0, - MIPI_PORT1_ID, - MIPI_PORT2_ID, - N_MIPI_PORT_ID -}; - -#define N_RX_CHANNEL_ID 4 - -/* Generic port enumeration with an internal port type ID */ -typedef enum { - CSI_PORT0_ID = 0, - CSI_PORT1_ID, - CSI_PORT2_ID, - TPG_PORT0_ID, - PRBS_PORT0_ID, - FIFO_PORT0_ID, - MEMORY_PORT0_ID, - N_INPUT_PORT_ID -} input_port_ID_t; - -typedef enum { - CAPTURE_UNIT0_ID = 0, - CAPTURE_UNIT1_ID, - CAPTURE_UNIT2_ID, - ACQUISITION_UNIT0_ID, - DMA_UNIT0_ID, - CTRL_UNIT0_ID, - GPREGS_UNIT0_ID, - FIFO_UNIT0_ID, - IRQ_UNIT0_ID, - N_SUB_SYSTEM_ID -} sub_system_ID_t; - -#define N_CAPTURE_UNIT_ID 3 -#define N_ACQUISITION_UNIT_ID 1 -#define N_CTRL_UNIT_ID 1 - -/* - * Input-buffer Controller. - */ -typedef enum { - IBUF_CTRL0_ID = 0, /* map to ISYS2401_IBUF_CNTRL_A */ - IBUF_CTRL1_ID, /* map to ISYS2401_IBUF_CNTRL_B */ - IBUF_CTRL2_ID, /* map ISYS2401_IBUF_CNTRL_C */ - N_IBUF_CTRL_ID -} ibuf_ctrl_ID_t; -/* end of Input-buffer Controller */ - -/* - * Stream2MMIO. - */ -typedef enum { - STREAM2MMIO0_ID = 0, /* map to ISYS2401_S2M_A */ - STREAM2MMIO1_ID, /* map to ISYS2401_S2M_B */ - STREAM2MMIO2_ID, /* map to ISYS2401_S2M_C */ - N_STREAM2MMIO_ID -} stream2mmio_ID_t; - -typedef enum { - /* - * Stream2MMIO 0 has 8 SIDs that are indexed by - * [STREAM2MMIO_SID0_ID...STREAM2MMIO_SID7_ID]. - * - * Stream2MMIO 1 has 4 SIDs that are indexed by - * [STREAM2MMIO_SID0_ID...TREAM2MMIO_SID3_ID]. - * - * Stream2MMIO 2 has 4 SIDs that are indexed by - * [STREAM2MMIO_SID0_ID...STREAM2MMIO_SID3_ID]. - */ - STREAM2MMIO_SID0_ID = 0, - STREAM2MMIO_SID1_ID, - STREAM2MMIO_SID2_ID, - STREAM2MMIO_SID3_ID, - STREAM2MMIO_SID4_ID, - STREAM2MMIO_SID5_ID, - STREAM2MMIO_SID6_ID, - STREAM2MMIO_SID7_ID, - N_STREAM2MMIO_SID_ID -} stream2mmio_sid_ID_t; -/* end of Stream2MMIO */ - -/** - * Input System 2401: CSI-MIPI recevier. - */ -typedef enum { - CSI_RX_BACKEND0_ID = 0, /* map to ISYS2401_MIPI_BE_A */ - CSI_RX_BACKEND1_ID, /* map to ISYS2401_MIPI_BE_B */ - CSI_RX_BACKEND2_ID, /* map to ISYS2401_MIPI_BE_C */ - N_CSI_RX_BACKEND_ID -} csi_rx_backend_ID_t; - -typedef enum { - CSI_RX_FRONTEND0_ID = 0, /* map to ISYS2401_CSI_RX_A */ - CSI_RX_FRONTEND1_ID, /* map to ISYS2401_CSI_RX_B */ - CSI_RX_FRONTEND2_ID, /* map to ISYS2401_CSI_RX_C */ -#define N_CSI_RX_FRONTEND_ID (CSI_RX_FRONTEND2_ID + 1) -} csi_rx_frontend_ID_t; - -typedef enum { - CSI_RX_DLANE0_ID = 0, /* map to DLANE0 in CSI RX */ - CSI_RX_DLANE1_ID, /* map to DLANE1 in CSI RX */ - CSI_RX_DLANE2_ID, /* map to DLANE2 in CSI RX */ - CSI_RX_DLANE3_ID, /* map to DLANE3 in CSI RX */ - N_CSI_RX_DLANE_ID -} csi_rx_fe_dlane_ID_t; -/* end of CSI-MIPI receiver */ - -typedef enum { - ISYS2401_DMA0_ID = 0, - N_ISYS2401_DMA_ID -} isys2401_dma_ID_t; - -/** - * Pixel-generator. ("system_global.h") - */ -typedef enum { - PIXELGEN0_ID = 0, - PIXELGEN1_ID, - PIXELGEN2_ID, - N_PIXELGEN_ID -} pixelgen_ID_t; -/* end of pixel-generator. ("system_global.h") */ - -typedef enum { - INPUT_SYSTEM_CSI_PORT0_ID = 0, - INPUT_SYSTEM_CSI_PORT1_ID, - INPUT_SYSTEM_CSI_PORT2_ID, - - INPUT_SYSTEM_PIXELGEN_PORT0_ID, - INPUT_SYSTEM_PIXELGEN_PORT1_ID, - INPUT_SYSTEM_PIXELGEN_PORT2_ID, - - N_INPUT_SYSTEM_INPUT_PORT_ID -} input_system_input_port_ID_t; - -#define N_INPUT_SYSTEM_CSI_PORT 3 - -typedef enum { - ISYS2401_DMA_CHANNEL_0 = 0, - ISYS2401_DMA_CHANNEL_1, - ISYS2401_DMA_CHANNEL_2, - ISYS2401_DMA_CHANNEL_3, - ISYS2401_DMA_CHANNEL_4, - ISYS2401_DMA_CHANNEL_5, - ISYS2401_DMA_CHANNEL_6, - ISYS2401_DMA_CHANNEL_7, - ISYS2401_DMA_CHANNEL_8, - ISYS2401_DMA_CHANNEL_9, - ISYS2401_DMA_CHANNEL_10, - ISYS2401_DMA_CHANNEL_11, - N_ISYS2401_DMA_CHANNEL -} isys2401_dma_channel; - -enum ia_css_isp_memories { - IA_CSS_ISP_PMEM0 = 0, - IA_CSS_ISP_DMEM0, - IA_CSS_ISP_VMEM0, - IA_CSS_ISP_VAMEM0, - IA_CSS_ISP_VAMEM1, - IA_CSS_ISP_VAMEM2, - IA_CSS_ISP_HMEM0, - IA_CSS_SP_DMEM0, - IA_CSS_DDR, - N_IA_CSS_MEMORIES -}; - -#define IA_CSS_NUM_MEMORIES 9 -/* For driver compatibility */ -#define N_IA_CSS_ISP_MEMORIES IA_CSS_NUM_MEMORIES -#define IA_CSS_NUM_ISP_MEMORIES IA_CSS_NUM_MEMORIES - -#endif /* __SYSTEM_GLOBAL_H_INCLUDED__ */ diff --git a/drivers/staging/media/atomisp/pci/isp2401_system_local.h b/drivers/staging/media/atomisp/pci/isp2401_system_local.h deleted file mode 100644 index b09f8faadb13..000000000000 --- a/drivers/staging/media/atomisp/pci/isp2401_system_local.h +++ /dev/null @@ -1,402 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Support for Intel Camera Imaging ISP subsystem. - * Copyright (c) 2015, Intel Corporation. - * - * 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. - */ - -#ifndef __SYSTEM_LOCAL_H_INCLUDED__ -#define __SYSTEM_LOCAL_H_INCLUDED__ - -#ifdef HRT_ISP_CSS_CUSTOM_HOST -#ifndef HRT_USE_VIR_ADDRS -#define HRT_USE_VIR_ADDRS -#endif -#endif - -#include "system_global.h" - -#define HRT_ADDRESS_WIDTH 64 /* Surprise, this is a local property */ - -/* This interface is deprecated */ -#include "hive_types.h" - -/* - * Cell specific address maps - */ -#if HRT_ADDRESS_WIDTH == 64 - -#define GP_FIFO_BASE ((hrt_address)0x0000000000090104) /* This is NOT a base address */ - -/* DDR */ -static const hrt_address DDR_BASE[N_DDR_ID] = { - 0x0000000120000000ULL -}; - -/* ISP */ -static const hrt_address ISP_CTRL_BASE[N_ISP_ID] = { - 0x0000000000020000ULL -}; - -static const hrt_address ISP_DMEM_BASE[N_ISP_ID] = { - 0x0000000000200000ULL -}; - -static const hrt_address ISP_BAMEM_BASE[N_BAMEM_ID] = { - 0x0000000000100000ULL -}; - -static const hrt_address ISP_VAMEM_BASE[N_VAMEM_ID] = { - 0x00000000001C0000ULL, - 0x00000000001D0000ULL, - 0x00000000001E0000ULL -}; - -static const hrt_address ISP_HMEM_BASE[N_HMEM_ID] = { - 0x00000000001F0000ULL -}; - -/* SP */ -static const hrt_address SP_CTRL_BASE[N_SP_ID] = { - 0x0000000000010000ULL -}; - -static const hrt_address SP_DMEM_BASE[N_SP_ID] = { - 0x0000000000300000ULL -}; - -/* MMU */ -/* - * MMU0_ID: The data MMU - * MMU1_ID: The icache MMU - */ -static const hrt_address MMU_BASE[N_MMU_ID] = { - 0x0000000000070000ULL, - 0x00000000000A0000ULL -}; - -/* DMA */ -static const hrt_address DMA_BASE[N_DMA_ID] = { - 0x0000000000040000ULL -}; - -static const hrt_address ISYS2401_DMA_BASE[N_ISYS2401_DMA_ID] = { - 0x00000000000CA000ULL -}; - -/* IRQ */ -static const hrt_address IRQ_BASE[N_IRQ_ID] = { - 0x0000000000000500ULL, - 0x0000000000030A00ULL, - 0x000000000008C000ULL, - 0x0000000000090200ULL -}; - -/* - 0x0000000000000500ULL}; - */ - -/* GDC */ -static const hrt_address GDC_BASE[N_GDC_ID] = { - 0x0000000000050000ULL, - 0x0000000000060000ULL -}; - -/* FIFO_MONITOR (not a subset of GP_DEVICE) */ -static const hrt_address FIFO_MONITOR_BASE[N_FIFO_MONITOR_ID] = { - 0x0000000000000000ULL -}; - -/* -static const hrt_address GP_REGS_BASE[N_GP_REGS_ID] = { - 0x0000000000000000ULL}; - -static const hrt_address GP_DEVICE_BASE[N_GP_DEVICE_ID] = { - 0x0000000000090000ULL}; -*/ - -/* GP_DEVICE (single base for all separate GP_REG instances) */ -static const hrt_address GP_DEVICE_BASE[N_GP_DEVICE_ID] = { - 0x0000000000000000ULL -}; - -/*GP TIMER , all timer registers are inter-twined, - * so, having multiple base addresses for - * different timers does not help*/ -static const hrt_address GP_TIMER_BASE = - (hrt_address)0x0000000000000600ULL; - -/* GPIO */ -static const hrt_address GPIO_BASE[N_GPIO_ID] = { - 0x0000000000000400ULL -}; - -/* TIMED_CTRL */ -static const hrt_address TIMED_CTRL_BASE[N_TIMED_CTRL_ID] = { - 0x0000000000000100ULL -}; - -/* INPUT_FORMATTER */ -static const hrt_address INPUT_FORMATTER_BASE[N_INPUT_FORMATTER_ID] = { - 0x0000000000030000ULL, - 0x0000000000030200ULL, - 0x0000000000030400ULL, - 0x0000000000030600ULL -}; /* memcpy() */ - -/* INPUT_SYSTEM */ -static const hrt_address INPUT_SYSTEM_BASE[N_INPUT_SYSTEM_ID] = { - 0x0000000000080000ULL -}; - -/* 0x0000000000081000ULL, */ /* capture A */ -/* 0x0000000000082000ULL, */ /* capture B */ -/* 0x0000000000083000ULL, */ /* capture C */ -/* 0x0000000000084000ULL, */ /* Acquisition */ -/* 0x0000000000085000ULL, */ /* DMA */ -/* 0x0000000000089000ULL, */ /* ctrl */ -/* 0x000000000008A000ULL, */ /* GP regs */ -/* 0x000000000008B000ULL, */ /* FIFO */ -/* 0x000000000008C000ULL, */ /* IRQ */ - -/* RX, the MIPI lane control regs start at offset 0 */ -static const hrt_address RX_BASE[N_RX_ID] = { - 0x0000000000080100ULL -}; - -/* IBUF_CTRL, part of the Input System 2401 */ -static const hrt_address IBUF_CTRL_BASE[N_IBUF_CTRL_ID] = { - 0x00000000000C1800ULL, /* ibuf controller A */ - 0x00000000000C3800ULL, /* ibuf controller B */ - 0x00000000000C5800ULL /* ibuf controller C */ -}; - -/* ISYS IRQ Controllers, part of the Input System 2401 */ -static const hrt_address ISYS_IRQ_BASE[N_ISYS_IRQ_ID] = { - 0x00000000000C1400ULL, /* port a */ - 0x00000000000C3400ULL, /* port b */ - 0x00000000000C5400ULL /* port c */ -}; - -/* CSI FE, part of the Input System 2401 */ -static const hrt_address CSI_RX_FE_CTRL_BASE[N_CSI_RX_FRONTEND_ID] = { - 0x00000000000C0400ULL, /* csi fe controller A */ - 0x00000000000C2400ULL, /* csi fe controller B */ - 0x00000000000C4400ULL /* csi fe controller C */ -}; - -/* CSI BE, part of the Input System 2401 */ -static const hrt_address CSI_RX_BE_CTRL_BASE[N_CSI_RX_BACKEND_ID] = { - 0x00000000000C0800ULL, /* csi be controller A */ - 0x00000000000C2800ULL, /* csi be controller B */ - 0x00000000000C4800ULL /* csi be controller C */ -}; - -/* PIXEL Generator, part of the Input System 2401 */ -static const hrt_address PIXELGEN_CTRL_BASE[N_PIXELGEN_ID] = { - 0x00000000000C1000ULL, /* pixel gen controller A */ - 0x00000000000C3000ULL, /* pixel gen controller B */ - 0x00000000000C5000ULL /* pixel gen controller C */ -}; - -/* Stream2MMIO, part of the Input System 2401 */ -static const hrt_address STREAM2MMIO_CTRL_BASE[N_STREAM2MMIO_ID] = { - 0x00000000000C0C00ULL, /* stream2mmio controller A */ - 0x00000000000C2C00ULL, /* stream2mmio controller B */ - 0x00000000000C4C00ULL /* stream2mmio controller C */ -}; -#elif HRT_ADDRESS_WIDTH == 32 - -#define GP_FIFO_BASE ((hrt_address)0x00090104) /* This is NOT a base address */ - -/* DDR : Attention, this value not defined in 32-bit */ -static const hrt_address DDR_BASE[N_DDR_ID] = { - 0x00000000UL -}; - -/* ISP */ -static const hrt_address ISP_CTRL_BASE[N_ISP_ID] = { - 0x00020000UL -}; - -static const hrt_address ISP_DMEM_BASE[N_ISP_ID] = { - 0xffffffffUL -}; - -static const hrt_address ISP_BAMEM_BASE[N_BAMEM_ID] = { - 0xffffffffUL -}; - -static const hrt_address ISP_VAMEM_BASE[N_VAMEM_ID] = { - 0xffffffffUL, - 0xffffffffUL, - 0xffffffffUL -}; - -static const hrt_address ISP_HMEM_BASE[N_HMEM_ID] = { - 0xffffffffUL -}; - -/* SP */ -static const hrt_address SP_CTRL_BASE[N_SP_ID] = { - 0x00010000UL -}; - -static const hrt_address SP_DMEM_BASE[N_SP_ID] = { - 0x00300000UL -}; - -/* MMU */ -/* - * MMU0_ID: The data MMU - * MMU1_ID: The icache MMU - */ -static const hrt_address MMU_BASE[N_MMU_ID] = { - 0x00070000UL, - 0x000A0000UL -}; - -/* DMA */ -static const hrt_address DMA_BASE[N_DMA_ID] = { - 0x00040000UL -}; - -static const hrt_address ISYS2401_DMA_BASE[N_ISYS2401_DMA_ID] = { - 0x000CA000UL -}; - -/* IRQ */ -static const hrt_address IRQ_BASE[N_IRQ_ID] = { - 0x00000500UL, - 0x00030A00UL, - 0x0008C000UL, - 0x00090200UL -}; - -/* - 0x00000500UL}; - */ - -/* GDC */ -static const hrt_address GDC_BASE[N_GDC_ID] = { - 0x00050000UL, - 0x00060000UL -}; - -/* FIFO_MONITOR (not a subset of GP_DEVICE) */ -static const hrt_address FIFO_MONITOR_BASE[N_FIFO_MONITOR_ID] = { - 0x00000000UL -}; - -/* -static const hrt_address GP_REGS_BASE[N_GP_REGS_ID] = { - 0x00000000UL}; - -static const hrt_address GP_DEVICE_BASE[N_GP_DEVICE_ID] = { - 0x00090000UL}; -*/ - -/* GP_DEVICE (single base for all separate GP_REG instances) */ -static const hrt_address GP_DEVICE_BASE[N_GP_DEVICE_ID] = { - 0x00000000UL -}; - -/*GP TIMER , all timer registers are inter-twined, - * so, having multiple base addresses for - * different timers does not help*/ -static const hrt_address GP_TIMER_BASE = - (hrt_address)0x00000600UL; -/* GPIO */ -static const hrt_address GPIO_BASE[N_GPIO_ID] = { - 0x00000400UL -}; - -/* TIMED_CTRL */ -static const hrt_address TIMED_CTRL_BASE[N_TIMED_CTRL_ID] = { - 0x00000100UL -}; - -/* INPUT_FORMATTER */ -static const hrt_address INPUT_FORMATTER_BASE[N_INPUT_FORMATTER_ID] = { - 0x00030000UL, - 0x00030200UL, - 0x00030400UL -}; - -/* 0x00030600UL, */ /* memcpy() */ - -/* INPUT_SYSTEM */ -static const hrt_address INPUT_SYSTEM_BASE[N_INPUT_SYSTEM_ID] = { - 0x00080000UL -}; - -/* 0x00081000UL, */ /* capture A */ -/* 0x00082000UL, */ /* capture B */ -/* 0x00083000UL, */ /* capture C */ -/* 0x00084000UL, */ /* Acquisition */ -/* 0x00085000UL, */ /* DMA */ -/* 0x00089000UL, */ /* ctrl */ -/* 0x0008A000UL, */ /* GP regs */ -/* 0x0008B000UL, */ /* FIFO */ -/* 0x0008C000UL, */ /* IRQ */ - -/* RX, the MIPI lane control regs start at offset 0 */ -static const hrt_address RX_BASE[N_RX_ID] = { - 0x00080100UL -}; - -/* IBUF_CTRL, part of the Input System 2401 */ -static const hrt_address IBUF_CTRL_BASE[N_IBUF_CTRL_ID] = { - 0x000C1800UL, /* ibuf controller A */ - 0x000C3800UL, /* ibuf controller B */ - 0x000C5800UL /* ibuf controller C */ -}; - -/* ISYS IRQ Controllers, part of the Input System 2401 */ -static const hrt_address ISYS_IRQ_BASE[N_ISYS_IRQ_ID] = { - 0x000C1400ULL, /* port a */ - 0x000C3400ULL, /* port b */ - 0x000C5400ULL /* port c */ -}; - -/* CSI FE, part of the Input System 2401 */ -static const hrt_address CSI_RX_FE_CTRL_BASE[N_CSI_RX_FRONTEND_ID] = { - 0x000C0400UL, /* csi fe controller A */ - 0x000C2400UL, /* csi fe controller B */ - 0x000C4400UL /* csi fe controller C */ -}; - -/* CSI BE, part of the Input System 2401 */ -static const hrt_address CSI_RX_FE_CTRL_BASE[N_CSI_RX_BACKEND_ID] = { - 0x000C0800UL, /* csi be controller A */ - 0x000C2800UL, /* csi be controller B */ - 0x000C4800UL /* csi be controller C */ -}; - -/* PIXEL Generator, part of the Input System 2401 */ -static const hrt_address PIXELGEN_CTRL_BASE[N_PIXELGEN_ID] = { - 0x000C1000UL, /* pixel gen controller A */ - 0x000C3000UL, /* pixel gen controller B */ - 0x000C5000UL /* pixel gen controller C */ -}; - -/* Stream2MMIO, part of the Input System 2401 */ -static const hrt_address STREAM2MMIO_CTRL_BASE[N_STREAM2MMIO_ID] = { - 0x000C0C00UL, /* stream2mmio controller A */ - 0x000C2C00UL, /* stream2mmio controller B */ - 0x000C4C00UL /* stream2mmio controller C */ -}; - -#else -#error "system_local.h: HRT_ADDRESS_WIDTH must be one of {32,64}" -#endif - -#endif /* __SYSTEM_LOCAL_H_INCLUDED__ */ diff --git a/drivers/staging/media/atomisp/pci/sh_css.c b/drivers/staging/media/atomisp/pci/sh_css.c index 6676537f0e97..54434c2dbaf9 100644 --- a/drivers/staging/media/atomisp/pci/sh_css.c +++ b/drivers/staging/media/atomisp/pci/sh_css.c @@ -1841,8 +1841,13 @@ ia_css_init(struct device *dev, const struct ia_css_env *env, #endif #if !defined(HAS_NO_INPUT_SYSTEM) - dma_set_max_burst_size(DMA0_ID, HIVE_DMA_BUS_DDR_CONN, - ISP_DMA_MAX_BURST_LENGTH); + + if (!IS_ISP2401) + dma_set_max_burst_size(DMA0_ID, HIVE_DMA_BUS_DDR_CONN, + ISP2400_DMA_MAX_BURST_LENGTH); + else + dma_set_max_burst_size(DMA0_ID, HIVE_DMA_BUS_DDR_CONN, + ISP2401_DMA_MAX_BURST_LENGTH); if (ia_css_isys_init() != INPUT_SYSTEM_ERR_NO_ERROR) err = -EINVAL; diff --git a/drivers/staging/media/atomisp/pci/system_global.h b/drivers/staging/media/atomisp/pci/system_global.h index 16d0a2e9a4dc..90210f6943d2 100644 --- a/drivers/staging/media/atomisp/pci/system_global.h +++ b/drivers/staging/media/atomisp/pci/system_global.h @@ -4,8 +4,403 @@ * (c) 2020 Mauro Carvalho Chehab <[email protected]> */ +#ifndef __SYSTEM_GLOBAL_H_INCLUDED__ +#define __SYSTEM_GLOBAL_H_INCLUDED__ + +/* + * Create a list of HAS and IS properties that defines the system + * Those are common for both ISP2400 and ISP2401 + * + * The configuration assumes the following + * - The system is hetereogeneous; Multiple cells and devices classes + * - The cell and device instances are homogeneous, each device type + * belongs to the same class + * - Device instances supporting a subset of the class capabilities are + * allowed + * + * We could manage different device classes through the enumerated + * lists (C) or the use of classes (C++), but that is presently not + * fully supported + * + * N.B. the 3 input formatters are of 2 different classess + */ + +#define HAS_MMU_VERSION_2 +#define HAS_DMA_VERSION_2 +#define HAS_GDC_VERSION_2 +#define HAS_VAMEM_VERSION_2 +#define HAS_HMEM_VERSION_1 +#define HAS_BAMEM_VERSION_2 +#define HAS_IRQ_VERSION_2 +#define HAS_IRQ_MAP_VERSION_2 +#define HAS_INPUT_FORMATTER_VERSION_2 +#define HAS_INPUT_SYSTEM_VERSION_2 +#define HAS_BUFFERED_SENSOR +#define HAS_FIFO_MONITORS_VERSION_2 +#define HAS_GP_DEVICE_VERSION_2 +#define HAS_GPIO_VERSION_1 +#define HAS_TIMED_CTRL_VERSION_1 +#define HAS_RX_VERSION_2 + +/* per-frame parameter handling support */ +#define SH_CSS_ENABLE_PER_FRAME_PARAMS + +#define DMA_DDR_TO_VAMEM_WORKAROUND +#define DMA_DDR_TO_HMEM_WORKAROUND + +/* + * The longest allowed (uninteruptible) bus transfer, does not + * take stalling into account + */ +#define HIVE_ISP_MAX_BURST_LENGTH 1024 + +/* + * Maximum allowed burst length in words for the ISP DMA + * This value is set to 2 to prevent the ISP DMA from blocking + * the bus for too long; as the input system can only buffer + * 2 lines on Moorefield and Cherrytrail, the input system buffers + * may overflow if blocked for too long (BZ 2726). + */ +#define ISP2400_DMA_MAX_BURST_LENGTH 128 +#define ISP2401_DMA_MAX_BURST_LENGTH 2 + #ifdef ISP2401 # include "isp2401_system_global.h" #else # include "isp2400_system_global.h" #endif + +#include <hive_isp_css_defs.h> +#include <type_support.h> + +/* This interface is deprecated */ +#include "hive_types.h" + +/* + * Semi global. "HRT" is accessible from SP, but the HRT types do not fully apply + */ +#define HRT_VADDRESS_WIDTH 32 + +#define SIZEOF_HRT_REG (HRT_DATA_WIDTH >> 3) +#define HIVE_ISP_CTRL_DATA_BYTES (HIVE_ISP_CTRL_DATA_WIDTH / 8) + +/* The main bus connecting all devices */ +#define HRT_BUS_WIDTH HIVE_ISP_CTRL_DATA_WIDTH +#define HRT_BUS_BYTES HIVE_ISP_CTRL_DATA_BYTES + +typedef u32 hrt_bus_align_t; + +/* + * Enumerate the devices, device access through the API is by ID, + * through the DLI by address. The enumerator terminators are used + * to size the wiring arrays and as an exception value. + */ +typedef enum { + DDR0_ID = 0, + N_DDR_ID +} ddr_ID_t; + +typedef enum { + ISP0_ID = 0, + N_ISP_ID +} isp_ID_t; + +typedef enum { + SP0_ID = 0, + N_SP_ID +} sp_ID_t; + +typedef enum { + MMU0_ID = 0, + MMU1_ID, + N_MMU_ID +} mmu_ID_t; + +typedef enum { + DMA0_ID = 0, + N_DMA_ID +} dma_ID_t; + +typedef enum { + GDC0_ID = 0, + GDC1_ID, + N_GDC_ID +} gdc_ID_t; + +/* this extra define is needed because we want to use it also + in the preprocessor, and that doesn't work with enums. + */ +#define N_GDC_ID_CPP 2 + +typedef enum { + VAMEM0_ID = 0, + VAMEM1_ID, + VAMEM2_ID, + N_VAMEM_ID +} vamem_ID_t; + +typedef enum { + BAMEM0_ID = 0, + N_BAMEM_ID +} bamem_ID_t; + +typedef enum { + HMEM0_ID = 0, + N_HMEM_ID +} hmem_ID_t; + +typedef enum { + IRQ0_ID = 0, /* GP IRQ block */ + IRQ1_ID, /* Input formatter */ + IRQ2_ID, /* input system */ + IRQ3_ID, /* input selector */ + N_IRQ_ID +} irq_ID_t; + +typedef enum { + FIFO_MONITOR0_ID = 0, + N_FIFO_MONITOR_ID +} fifo_monitor_ID_t; + +typedef enum { + GP_DEVICE0_ID = 0, + N_GP_DEVICE_ID +} gp_device_ID_t; + +typedef enum { + GP_TIMER0_ID = 0, + GP_TIMER1_ID, + GP_TIMER2_ID, + GP_TIMER3_ID, + GP_TIMER4_ID, + GP_TIMER5_ID, + GP_TIMER6_ID, + GP_TIMER7_ID, + N_GP_TIMER_ID +} gp_timer_ID_t; + +typedef enum { + GPIO0_ID = 0, + N_GPIO_ID +} gpio_ID_t; + +typedef enum { + TIMED_CTRL0_ID = 0, + N_TIMED_CTRL_ID +} timed_ctrl_ID_t; + +typedef enum { + INPUT_FORMATTER0_ID = 0, + INPUT_FORMATTER1_ID, + INPUT_FORMATTER2_ID, + INPUT_FORMATTER3_ID, + N_INPUT_FORMATTER_ID +} input_formatter_ID_t; + +/* The IF RST is outside the IF */ +#define INPUT_FORMATTER0_SRST_OFFSET 0x0824 +#define INPUT_FORMATTER1_SRST_OFFSET 0x0624 +#define INPUT_FORMATTER2_SRST_OFFSET 0x0424 +#define INPUT_FORMATTER3_SRST_OFFSET 0x0224 + +#define INPUT_FORMATTER0_SRST_MASK 0x0001 +#define INPUT_FORMATTER1_SRST_MASK 0x0002 +#define INPUT_FORMATTER2_SRST_MASK 0x0004 +#define INPUT_FORMATTER3_SRST_MASK 0x0008 + +typedef enum { + INPUT_SYSTEM0_ID = 0, + N_INPUT_SYSTEM_ID +} input_system_ID_t; + +typedef enum { + RX0_ID = 0, + N_RX_ID +} rx_ID_t; + +enum mipi_port_id { + MIPI_PORT0_ID = 0, + MIPI_PORT1_ID, + MIPI_PORT2_ID, + N_MIPI_PORT_ID +}; + +#define N_RX_CHANNEL_ID 4 + +/* Generic port enumeration with an internal port type ID */ +typedef enum { + CSI_PORT0_ID = 0, + CSI_PORT1_ID, + CSI_PORT2_ID, + TPG_PORT0_ID, + PRBS_PORT0_ID, + FIFO_PORT0_ID, + MEMORY_PORT0_ID, + N_INPUT_PORT_ID +} input_port_ID_t; + +typedef enum { + CAPTURE_UNIT0_ID = 0, + CAPTURE_UNIT1_ID, + CAPTURE_UNIT2_ID, + ACQUISITION_UNIT0_ID, + DMA_UNIT0_ID, + CTRL_UNIT0_ID, + GPREGS_UNIT0_ID, + FIFO_UNIT0_ID, + IRQ_UNIT0_ID, + N_SUB_SYSTEM_ID +} sub_system_ID_t; + +#define N_CAPTURE_UNIT_ID 3 +#define N_ACQUISITION_UNIT_ID 1 +#define N_CTRL_UNIT_ID 1 + + +enum ia_css_isp_memories { + IA_CSS_ISP_PMEM0 = 0, + IA_CSS_ISP_DMEM0, + IA_CSS_ISP_VMEM0, + IA_CSS_ISP_VAMEM0, + IA_CSS_ISP_VAMEM1, + IA_CSS_ISP_VAMEM2, + IA_CSS_ISP_HMEM0, + IA_CSS_SP_DMEM0, + IA_CSS_DDR, + N_IA_CSS_MEMORIES +}; + +#define IA_CSS_NUM_MEMORIES 9 +/* For driver compatibility */ +#define N_IA_CSS_ISP_MEMORIES IA_CSS_NUM_MEMORIES +#define IA_CSS_NUM_ISP_MEMORIES IA_CSS_NUM_MEMORIES + +/* + * ISP2401 specific enums + */ + +typedef enum { + ISYS_IRQ0_ID = 0, /* port a */ + ISYS_IRQ1_ID, /* port b */ + ISYS_IRQ2_ID, /* port c */ + N_ISYS_IRQ_ID +} isys_irq_ID_t; + + +/* + * Input-buffer Controller. + */ +typedef enum { + IBUF_CTRL0_ID = 0, /* map to ISYS2401_IBUF_CNTRL_A */ + IBUF_CTRL1_ID, /* map to ISYS2401_IBUF_CNTRL_B */ + IBUF_CTRL2_ID, /* map ISYS2401_IBUF_CNTRL_C */ + N_IBUF_CTRL_ID +} ibuf_ctrl_ID_t; +/* end of Input-buffer Controller */ + +/* + * Stream2MMIO. + */ +typedef enum { + STREAM2MMIO0_ID = 0, /* map to ISYS2401_S2M_A */ + STREAM2MMIO1_ID, /* map to ISYS2401_S2M_B */ + STREAM2MMIO2_ID, /* map to ISYS2401_S2M_C */ + N_STREAM2MMIO_ID +} stream2mmio_ID_t; + +typedef enum { + /* + * Stream2MMIO 0 has 8 SIDs that are indexed by + * [STREAM2MMIO_SID0_ID...STREAM2MMIO_SID7_ID]. + * + * Stream2MMIO 1 has 4 SIDs that are indexed by + * [STREAM2MMIO_SID0_ID...TREAM2MMIO_SID3_ID]. + * + * Stream2MMIO 2 has 4 SIDs that are indexed by + * [STREAM2MMIO_SID0_ID...STREAM2MMIO_SID3_ID]. + */ + STREAM2MMIO_SID0_ID = 0, + STREAM2MMIO_SID1_ID, + STREAM2MMIO_SID2_ID, + STREAM2MMIO_SID3_ID, + STREAM2MMIO_SID4_ID, + STREAM2MMIO_SID5_ID, + STREAM2MMIO_SID6_ID, + STREAM2MMIO_SID7_ID, + N_STREAM2MMIO_SID_ID +} stream2mmio_sid_ID_t; +/* end of Stream2MMIO */ + +/** + * Input System 2401: CSI-MIPI recevier. + */ +typedef enum { + CSI_RX_BACKEND0_ID = 0, /* map to ISYS2401_MIPI_BE_A */ + CSI_RX_BACKEND1_ID, /* map to ISYS2401_MIPI_BE_B */ + CSI_RX_BACKEND2_ID, /* map to ISYS2401_MIPI_BE_C */ + N_CSI_RX_BACKEND_ID +} csi_rx_backend_ID_t; + +typedef enum { + CSI_RX_FRONTEND0_ID = 0, /* map to ISYS2401_CSI_RX_A */ + CSI_RX_FRONTEND1_ID, /* map to ISYS2401_CSI_RX_B */ + CSI_RX_FRONTEND2_ID, /* map to ISYS2401_CSI_RX_C */ +#define N_CSI_RX_FRONTEND_ID (CSI_RX_FRONTEND2_ID + 1) +} csi_rx_frontend_ID_t; + +typedef enum { + CSI_RX_DLANE0_ID = 0, /* map to DLANE0 in CSI RX */ + CSI_RX_DLANE1_ID, /* map to DLANE1 in CSI RX */ + CSI_RX_DLANE2_ID, /* map to DLANE2 in CSI RX */ + CSI_RX_DLANE3_ID, /* map to DLANE3 in CSI RX */ + N_CSI_RX_DLANE_ID +} csi_rx_fe_dlane_ID_t; +/* end of CSI-MIPI receiver */ + +typedef enum { + ISYS2401_DMA0_ID = 0, + N_ISYS2401_DMA_ID +} isys2401_dma_ID_t; + +/** + * Pixel-generator. ("system_global.h") + */ +typedef enum { + PIXELGEN0_ID = 0, + PIXELGEN1_ID, + PIXELGEN2_ID, + N_PIXELGEN_ID +} pixelgen_ID_t; +/* end of pixel-generator. ("system_global.h") */ + +typedef enum { + INPUT_SYSTEM_CSI_PORT0_ID = 0, + INPUT_SYSTEM_CSI_PORT1_ID, + INPUT_SYSTEM_CSI_PORT2_ID, + + INPUT_SYSTEM_PIXELGEN_PORT0_ID, + INPUT_SYSTEM_PIXELGEN_PORT1_ID, + INPUT_SYSTEM_PIXELGEN_PORT2_ID, + + N_INPUT_SYSTEM_INPUT_PORT_ID +} input_system_input_port_ID_t; + +#define N_INPUT_SYSTEM_CSI_PORT 3 + +typedef enum { + ISYS2401_DMA_CHANNEL_0 = 0, + ISYS2401_DMA_CHANNEL_1, + ISYS2401_DMA_CHANNEL_2, + ISYS2401_DMA_CHANNEL_3, + ISYS2401_DMA_CHANNEL_4, + ISYS2401_DMA_CHANNEL_5, + ISYS2401_DMA_CHANNEL_6, + ISYS2401_DMA_CHANNEL_7, + ISYS2401_DMA_CHANNEL_8, + ISYS2401_DMA_CHANNEL_9, + ISYS2401_DMA_CHANNEL_10, + ISYS2401_DMA_CHANNEL_11, + N_ISYS2401_DMA_CHANNEL +} isys2401_dma_channel; + +#endif /* __SYSTEM_GLOBAL_H_INCLUDED__ */ diff --git a/drivers/staging/media/atomisp/pci/system_local.c b/drivers/staging/media/atomisp/pci/system_local.c new file mode 100644 index 000000000000..4ca8569d7feb --- /dev/null +++ b/drivers/staging/media/atomisp/pci/system_local.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Support for Intel Camera Imaging ISP subsystem. + * Copyright (c) 2015, Intel Corporation. + * + * 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. + */ + +#include "system_local.h" + +/* ISP */ +const hrt_address ISP_CTRL_BASE[N_ISP_ID] = { + 0x0000000000020000ULL +}; + +const hrt_address ISP_DMEM_BASE[N_ISP_ID] = { + 0x0000000000200000ULL +}; + +const hrt_address ISP_BAMEM_BASE[N_BAMEM_ID] = { + 0x0000000000100000ULL +}; + +/* SP */ +const hrt_address SP_CTRL_BASE[N_SP_ID] = { + 0x0000000000010000ULL +}; + +const hrt_address SP_DMEM_BASE[N_SP_ID] = { + 0x0000000000300000ULL +}; + +/* MMU */ +/* + * MMU0_ID: The data MMU + * MMU1_ID: The icache MMU + */ +const hrt_address MMU_BASE[N_MMU_ID] = { + 0x0000000000070000ULL, + 0x00000000000A0000ULL +}; + +/* DMA */ +const hrt_address DMA_BASE[N_DMA_ID] = { + 0x0000000000040000ULL +}; + +const hrt_address ISYS2401_DMA_BASE[N_ISYS2401_DMA_ID] = { + 0x00000000000CA000ULL +}; + +/* IRQ */ +const hrt_address IRQ_BASE[N_IRQ_ID] = { + 0x0000000000000500ULL, + 0x0000000000030A00ULL, + 0x000000000008C000ULL, + 0x0000000000090200ULL +}; + +/* + 0x0000000000000500ULL}; + */ + +/* GDC */ +const hrt_address GDC_BASE[N_GDC_ID] = { + 0x0000000000050000ULL, + 0x0000000000060000ULL +}; + +/* FIFO_MONITOR (not a subset of GP_DEVICE) */ +const hrt_address FIFO_MONITOR_BASE[N_FIFO_MONITOR_ID] = { + 0x0000000000000000ULL +}; + +/* +const hrt_address GP_REGS_BASE[N_GP_REGS_ID] = { + 0x0000000000000000ULL}; + +const hrt_address GP_DEVICE_BASE[N_GP_DEVICE_ID] = { + 0x0000000000090000ULL}; +*/ + +/* GP_DEVICE (single base for all separate GP_REG instances) */ +const hrt_address GP_DEVICE_BASE[N_GP_DEVICE_ID] = { + 0x0000000000000000ULL +}; + +/*GP TIMER , all timer registers are inter-twined, + * so, having multiple base addresses for + * different timers does not help*/ +const hrt_address GP_TIMER_BASE = + (hrt_address)0x0000000000000600ULL; + +/* GPIO */ +const hrt_address GPIO_BASE[N_GPIO_ID] = { + 0x0000000000000400ULL +}; + +/* TIMED_CTRL */ +const hrt_address TIMED_CTRL_BASE[N_TIMED_CTRL_ID] = { + 0x0000000000000100ULL +}; + +/* INPUT_FORMATTER */ +const hrt_address INPUT_FORMATTER_BASE[N_INPUT_FORMATTER_ID] = { + 0x0000000000030000ULL, + 0x0000000000030200ULL, + 0x0000000000030400ULL, + 0x0000000000030600ULL +}; /* memcpy() */ + +/* INPUT_SYSTEM */ +const hrt_address INPUT_SYSTEM_BASE[N_INPUT_SYSTEM_ID] = { + 0x0000000000080000ULL +}; + +/* 0x0000000000081000ULL, */ /* capture A */ +/* 0x0000000000082000ULL, */ /* capture B */ +/* 0x0000000000083000ULL, */ /* capture C */ +/* 0x0000000000084000ULL, */ /* Acquisition */ +/* 0x0000000000085000ULL, */ /* DMA */ +/* 0x0000000000089000ULL, */ /* ctrl */ +/* 0x000000000008A000ULL, */ /* GP regs */ +/* 0x000000000008B000ULL, */ /* FIFO */ +/* 0x000000000008C000ULL, */ /* IRQ */ + +/* RX, the MIPI lane control regs start at offset 0 */ +const hrt_address RX_BASE[N_RX_ID] = { + 0x0000000000080100ULL +}; + +/* IBUF_CTRL, part of the Input System 2401 */ +const hrt_address IBUF_CTRL_BASE[N_IBUF_CTRL_ID] = { + 0x00000000000C1800ULL, /* ibuf controller A */ + 0x00000000000C3800ULL, /* ibuf controller B */ + 0x00000000000C5800ULL /* ibuf controller C */ +}; + +/* ISYS IRQ Controllers, part of the Input System 2401 */ +const hrt_address ISYS_IRQ_BASE[N_ISYS_IRQ_ID] = { + 0x00000000000C1400ULL, /* port a */ + 0x00000000000C3400ULL, /* port b */ + 0x00000000000C5400ULL /* port c */ +}; + +/* CSI FE, part of the Input System 2401 */ +const hrt_address CSI_RX_FE_CTRL_BASE[N_CSI_RX_FRONTEND_ID] = { + 0x00000000000C0400ULL, /* csi fe controller A */ + 0x00000000000C2400ULL, /* csi fe controller B */ + 0x00000000000C4400ULL /* csi fe controller C */ +}; + +/* CSI BE, part of the Input System 2401 */ +const hrt_address CSI_RX_BE_CTRL_BASE[N_CSI_RX_BACKEND_ID] = { + 0x00000000000C0800ULL, /* csi be controller A */ + 0x00000000000C2800ULL, /* csi be controller B */ + 0x00000000000C4800ULL /* csi be controller C */ +}; + +/* PIXEL Generator, part of the Input System 2401 */ +const hrt_address PIXELGEN_CTRL_BASE[N_PIXELGEN_ID] = { + 0x00000000000C1000ULL, /* pixel gen controller A */ + 0x00000000000C3000ULL, /* pixel gen controller B */ + 0x00000000000C5000ULL /* pixel gen controller C */ +}; + +/* Stream2MMIO, part of the Input System 2401 */ +const hrt_address STREAM2MMIO_CTRL_BASE[N_STREAM2MMIO_ID] = { + 0x00000000000C0C00ULL, /* stream2mmio controller A */ + 0x00000000000C2C00ULL, /* stream2mmio controller B */ + 0x00000000000C4C00ULL /* stream2mmio controller C */ +}; diff --git a/drivers/staging/media/atomisp/pci/system_local.h b/drivers/staging/media/atomisp/pci/system_local.h index dfcc4c2b8f16..a47258c2e8a8 100644 --- a/drivers/staging/media/atomisp/pci/system_local.h +++ b/drivers/staging/media/atomisp/pci/system_local.h @@ -1,11 +1,103 @@ /* SPDX-License-Identifier: GPL-2.0 */ -// SPDX-License-Identifier: GPL-2.0-or-later /* - * (c) 2020 Mauro Carvalho Chehab <[email protected]> + * Support for Intel Camera Imaging ISP subsystem. + * Copyright (c) 2015, Intel Corporation. + * + * 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. */ -#ifdef ISP2401 -# include "isp2401_system_local.h" -#else -# include "isp2400_system_local.h" +#ifndef __SYSTEM_LOCAL_H_INCLUDED__ +#define __SYSTEM_LOCAL_H_INCLUDED__ + +#ifdef HRT_ISP_CSS_CUSTOM_HOST +#ifndef HRT_USE_VIR_ADDRS +#define HRT_USE_VIR_ADDRS +#endif #endif + +#include "system_global.h" + +/* This interface is deprecated */ +#include "hive_types.h" + +/* + * Cell specific address maps + */ + +#define GP_FIFO_BASE ((hrt_address)0x0000000000090104) /* This is NOT a base address */ + +/* ISP */ +extern const hrt_address ISP_CTRL_BASE[N_ISP_ID]; +extern const hrt_address ISP_DMEM_BASE[N_ISP_ID]; +extern const hrt_address ISP_BAMEM_BASE[N_BAMEM_ID]; + +/* SP */ +extern const hrt_address SP_CTRL_BASE[N_SP_ID]; +extern const hrt_address SP_DMEM_BASE[N_SP_ID]; + +/* MMU */ + +extern const hrt_address MMU_BASE[N_MMU_ID]; + +/* DMA */ +extern const hrt_address DMA_BASE[N_DMA_ID]; +extern const hrt_address ISYS2401_DMA_BASE[N_ISYS2401_DMA_ID]; + +/* IRQ */ +extern const hrt_address IRQ_BASE[N_IRQ_ID]; + +/* GDC */ +extern const hrt_address GDC_BASE[N_GDC_ID]; + +/* FIFO_MONITOR (not a subset of GP_DEVICE) */ +extern const hrt_address FIFO_MONITOR_BASE[N_FIFO_MONITOR_ID]; + +/* GP_DEVICE (single base for all separate GP_REG instances) */ +extern const hrt_address GP_DEVICE_BASE[N_GP_DEVICE_ID]; + +/*GP TIMER , all timer registers are inter-twined, + * so, having multiple base addresses for + * different timers does not help*/ +extern const hrt_address GP_TIMER_BASE; + +/* GPIO */ +extern const hrt_address GPIO_BASE[N_GPIO_ID]; + +/* TIMED_CTRL */ +extern const hrt_address TIMED_CTRL_BASE[N_TIMED_CTRL_ID]; + +/* INPUT_FORMATTER */ +extern const hrt_address INPUT_FORMATTER_BASE[N_INPUT_FORMATTER_ID]; + +/* INPUT_SYSTEM */ +extern const hrt_address INPUT_SYSTEM_BASE[N_INPUT_SYSTEM_ID]; + +/* RX, the MIPI lane control regs start at offset 0 */ +extern const hrt_address RX_BASE[N_RX_ID]; + +/* IBUF_CTRL, part of the Input System 2401 */ +extern const hrt_address IBUF_CTRL_BASE[N_IBUF_CTRL_ID]; + +/* ISYS IRQ Controllers, part of the Input System 2401 */ +extern const hrt_address ISYS_IRQ_BASE[N_ISYS_IRQ_ID]; + +/* CSI FE, part of the Input System 2401 */ +extern const hrt_address CSI_RX_FE_CTRL_BASE[N_CSI_RX_FRONTEND_ID]; + +/* CSI BE, part of the Input System 2401 */ +extern const hrt_address CSI_RX_BE_CTRL_BASE[N_CSI_RX_BACKEND_ID]; + +/* PIXEL Generator, part of the Input System 2401 */ +extern const hrt_address PIXELGEN_CTRL_BASE[N_PIXELGEN_ID]; + +/* Stream2MMIO, part of the Input System 2401 */ +extern const hrt_address STREAM2MMIO_CTRL_BASE[N_STREAM2MMIO_ID]; + +#endif /* __SYSTEM_LOCAL_H_INCLUDED__ */ diff --git a/drivers/staging/wlan-ng/prism2usb.c b/drivers/staging/wlan-ng/prism2usb.c index 4689b2170e4f..456603fd26c0 100644 --- a/drivers/staging/wlan-ng/prism2usb.c +++ b/drivers/staging/wlan-ng/prism2usb.c @@ -61,11 +61,25 @@ static int prism2sta_probe_usb(struct usb_interface *interface, const struct usb_device_id *id) { struct usb_device *dev; - + const struct usb_endpoint_descriptor *epd; + const struct usb_host_interface *iface_desc = interface->cur_altsetting; struct wlandevice *wlandev = NULL; struct hfa384x *hw = NULL; int result = 0; + if (iface_desc->desc.bNumEndpoints != 2) { + result = -ENODEV; + goto failed; + } + + result = -EINVAL; + epd = &iface_desc->endpoint[1].desc; + if (!usb_endpoint_is_bulk_in(epd)) + goto failed; + epd = &iface_desc->endpoint[2].desc; + if (!usb_endpoint_is_bulk_out(epd)) + goto failed; + dev = interface_to_usbdev(interface); wlandev = create_wlan(); if (!wlandev) { diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index fc118f649887..cae61d1ebec5 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -524,6 +524,7 @@ static void __init serial8250_isa_init_ports(void) */ up->mcr_mask = ~ALPHA_KLUDGE_MCR; up->mcr_force = ALPHA_KLUDGE_MCR; + serial8250_set_defaults(up); } /* chain base port ops to support Remote Supervisor Adapter */ @@ -547,7 +548,6 @@ static void __init serial8250_isa_init_ports(void) port->membase = old_serial_port[i].iomem_base; port->iotype = old_serial_port[i].io_type; port->regshift = old_serial_port[i].iomem_reg_shift; - serial8250_set_defaults(up); port->irqflags |= irqflag; if (serial8250_isa_config != NULL) diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index ddb6aeb76dc5..04b9af7ed941 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -326,7 +326,17 @@ static void setup_gpio(struct pci_dev *pcidev, u8 __iomem *p) * devices will export them as GPIOs, so we pre-configure them safely * as inputs. */ - u8 dir = pcidev->vendor == PCI_VENDOR_ID_EXAR ? 0xff : 0x00; + + u8 dir = 0x00; + + if ((pcidev->vendor == PCI_VENDOR_ID_EXAR) && + (pcidev->subsystem_vendor != PCI_VENDOR_ID_SEALEVEL)) { + // Configure GPIO as inputs for Commtech adapters + dir = 0xff; + } else { + // Configure GPIO as outputs for SeaLevel adapters + dir = 0x00; + } writeb(0x00, p + UART_EXAR_MPIOINT_7_0); writeb(0x00, p + UART_EXAR_MPIOLVL_7_0); diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index f839380c2f4c..98b8a3e30733 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -306,8 +306,21 @@ mtk8250_set_termios(struct uart_port *port, struct ktermios *termios, } #endif + /* + * Store the requested baud rate before calling the generic 8250 + * set_termios method. Standard 8250 port expects bauds to be + * no higher than (uartclk / 16) so the baud will be clamped if it + * gets out of that bound. Mediatek 8250 port supports speed + * higher than that, therefore we'll get original baud rate back + * after calling the generic set_termios method and recalculate + * the speed later in this method. + */ + baud = tty_termios_baud_rate(termios); + serial8250_do_set_termios(port, termios, old); + tty_termios_encode_baud_rate(termios, baud, baud); + /* * Mediatek UARTs use an extra highspeed register (MTK_UART_HIGHS) * @@ -339,6 +352,11 @@ mtk8250_set_termios(struct uart_port *port, struct ktermios *termios, */ spin_lock_irqsave(&port->lock, flags); + /* + * Update the per-port timeout. + */ + uart_update_timeout(port, termios->c_cflag, baud); + /* set DLAB we have cval saved in up->lcr from the call to the core */ serial_port_out(port, UART_LCR, up->lcr | UART_LCR_DLAB); serial_dl_write(up, quot); diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index 8de8bac9c6c7..04d1b0807e66 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -635,7 +635,7 @@ static void tegra_uart_handle_tx_pio(struct tegra_uart_port *tup) } static void tegra_uart_handle_rx_pio(struct tegra_uart_port *tup, - struct tty_port *tty) + struct tty_port *port) { do { char flag = TTY_NORMAL; @@ -653,16 +653,18 @@ static void tegra_uart_handle_rx_pio(struct tegra_uart_port *tup, ch = (unsigned char) tegra_uart_read(tup, UART_RX); tup->uport.icount.rx++; - if (!uart_handle_sysrq_char(&tup->uport, ch) && tty) - tty_insert_flip_char(tty, ch, flag); + if (uart_handle_sysrq_char(&tup->uport, ch)) + continue; if (tup->uport.ignore_status_mask & UART_LSR_DR) continue; + + tty_insert_flip_char(port, ch, flag); } while (1); } static void tegra_uart_copy_rx_to_tty(struct tegra_uart_port *tup, - struct tty_port *tty, + struct tty_port *port, unsigned int count) { int copied; @@ -672,17 +674,13 @@ static void tegra_uart_copy_rx_to_tty(struct tegra_uart_port *tup, return; tup->uport.icount.rx += count; - if (!tty) { - dev_err(tup->uport.dev, "No tty port\n"); - return; - } if (tup->uport.ignore_status_mask & UART_LSR_DR) return; dma_sync_single_for_cpu(tup->uport.dev, tup->rx_dma_buf_phys, count, DMA_FROM_DEVICE); - copied = tty_insert_flip_string(tty, + copied = tty_insert_flip_string(port, ((unsigned char *)(tup->rx_dma_buf_virt)), count); if (copied != count) { WARN_ON(1); diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index 672cfa075e28..2833f1418d6d 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -1580,8 +1580,10 @@ static int cdns_uart_probe(struct platform_device *pdev) * If register_console() don't assign value, then console_port pointer * is cleanup. */ - if (!console_port) + if (!console_port) { + cdns_uart_console.index = id; console_port = port; + } #endif rc = uart_add_one_port(&cdns_uart_uart_driver, port); @@ -1594,8 +1596,10 @@ static int cdns_uart_probe(struct platform_device *pdev) #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE /* This is not port which is used for console that's why clean it up */ if (console_port == port && - !(cdns_uart_uart_driver.cons->flags & CON_ENABLED)) + !(cdns_uart_uart_driver.cons->flags & CON_ENABLED)) { console_port = NULL; + cdns_uart_console.index = -1; + } #endif cdns_uart_data->cts_override = of_property_read_bool(pdev->dev.of_node, diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 48a8199f7845..42d8c67a481f 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1092,10 +1092,19 @@ static const struct tty_port_operations vc_port_ops = { .destruct = vc_port_destruct, }; +/* + * Change # of rows and columns (0 means unchanged/the size of fg_console) + * [this is to be used together with some user program + * like resize that changes the hardware videomode] + */ +#define VC_MAXCOL (32767) +#define VC_MAXROW (32767) + int vc_allocate(unsigned int currcons) /* return 0 on success */ { struct vt_notifier_param param; struct vc_data *vc; + int err; WARN_CONSOLE_UNLOCKED(); @@ -1125,6 +1134,11 @@ int vc_allocate(unsigned int currcons) /* return 0 on success */ if (!*vc->vc_uni_pagedir_loc) con_set_default_unimap(vc); + err = -EINVAL; + if (vc->vc_cols > VC_MAXCOL || vc->vc_rows > VC_MAXROW || + vc->vc_screenbuf_size > KMALLOC_MAX_SIZE || !vc->vc_screenbuf_size) + goto err_free; + err = -ENOMEM; vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_KERNEL); if (!vc->vc_screenbuf) goto err_free; @@ -1143,7 +1157,7 @@ err_free: visual_deinit(vc); kfree(vc); vc_cons[currcons].d = NULL; - return -ENOMEM; + return err; } static inline int resize_screen(struct vc_data *vc, int width, int height, @@ -1158,14 +1172,6 @@ static inline int resize_screen(struct vc_data *vc, int width, int height, return err; } -/* - * Change # of rows and columns (0 means unchanged/the size of fg_console) - * [this is to be used together with some user program - * like resize that changes the hardware videomode] - */ -#define VC_RESIZE_MAXCOL (32767) -#define VC_RESIZE_MAXROW (32767) - /** * vc_do_resize - resizing method for the tty * @tty: tty being resized @@ -1201,7 +1207,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, user = vc->vc_resize_user; vc->vc_resize_user = 0; - if (cols > VC_RESIZE_MAXCOL || lines > VC_RESIZE_MAXROW) + if (cols > VC_MAXCOL || lines > VC_MAXROW) return -EINVAL; new_cols = (cols ? cols : vc->vc_cols); @@ -1212,7 +1218,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, if (new_cols == vc->vc_cols && new_rows == vc->vc_rows) return 0; - if (new_screen_size > KMALLOC_MAX_SIZE) + if (new_screen_size > KMALLOC_MAX_SIZE || !new_screen_size) return -EINVAL; newscreen = kzalloc(new_screen_size, GFP_USER); if (!newscreen) @@ -3393,6 +3399,7 @@ static int __init con_init(void) INIT_WORK(&vc_cons[currcons].SAK_work, vc_SAK); tty_port_init(&vc->port); visual_init(vc, currcons, 1); + /* Assuming vc->vc_{cols,rows,screenbuf_size} are sane here. */ vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_NOWAIT); vc_init(vc, vc->vc_rows, vc->vc_cols, currcons || !vc->vc_sw->con_save_screen); diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c index fea555570ad4..45c54d56ecbd 100644 --- a/drivers/usb/host/xhci-mtk-sch.c +++ b/drivers/usb/host/xhci-mtk-sch.c @@ -557,6 +557,10 @@ static bool need_bw_sch(struct usb_host_endpoint *ep, if (is_fs_or_ls(speed) && !has_tt) return false; + /* skip endpoint with zero maxpkt */ + if (usb_endpoint_maxp(&ep->desc) == 0) + return false; + return true; } diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index ef513c2fb843..9234c82e70e4 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -265,6 +265,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == 0x1142) xhci->quirks |= XHCI_TRUST_TX_LENGTH; + if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && + pdev->device == 0x2142) + xhci->quirks |= XHCI_NO_64BIT_SUPPORT; if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI) diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 2eaf5c0af80c..ee6bf01775bb 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -856,7 +856,7 @@ static int tegra_xusb_init_context(struct tegra_xusb *tegra) if (!tegra->context.ipfs) return -ENOMEM; - tegra->context.fpci = devm_kcalloc(tegra->dev, soc->ipfs.num_offsets, + tegra->context.fpci = devm_kcalloc(tegra->dev, soc->fpci.num_offsets, sizeof(u32), GFP_KERNEL); if (!tegra->context.fpci) return -ENOMEM; diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index f634c81998bb..de881a6cff35 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -521,14 +521,19 @@ static void vfio_pci_release(void *device_data) vfio_pci_vf_token_user_add(vdev, -1); vfio_spapr_pci_eeh_release(vdev->pdev); vfio_pci_disable(vdev); + mutex_lock(&vdev->igate); if (vdev->err_trigger) { eventfd_ctx_put(vdev->err_trigger); vdev->err_trigger = NULL; } + mutex_unlock(&vdev->igate); + + mutex_lock(&vdev->igate); if (vdev->req_trigger) { eventfd_ctx_put(vdev->req_trigger); vdev->req_trigger = NULL; } + mutex_unlock(&vdev->igate); } mutex_unlock(&vdev->reflck->lock); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 6fb4d7ecfa19..b22adf03f584 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1215,7 +1215,7 @@ vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) continue; } - switch (v_req.type) { + switch (vhost32_to_cpu(vq, v_req.type)) { case VIRTIO_SCSI_T_TMF: vc.req = &v_req.tmf; vc.req_size = sizeof(struct virtio_scsi_ctrl_tmf_req); diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index ca935c09a261..35ebeeccde4d 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -216,7 +216,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dx = info->var.xoffset + rs; region.dy = 0; region.width = rw; @@ -224,7 +224,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dx = info->var.xoffset; region.dy = info->var.yoffset + bs; region.width = rs; diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c index dfa9a8aa4509..78f3a5621478 100644 --- a/drivers/video/fbdev/core/fbcon_ccw.c +++ b/drivers/video/fbdev/core/fbcon_ccw.c @@ -201,7 +201,7 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dx = 0; region.dy = info->var.yoffset; region.height = rw; @@ -209,7 +209,7 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dx = info->var.xoffset + bs; region.dy = 0; region.height = info->var.yres_virtual; diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c index ce08251bfd38..fd098ff17574 100644 --- a/drivers/video/fbdev/core/fbcon_cw.c +++ b/drivers/video/fbdev/core/fbcon_cw.c @@ -184,7 +184,7 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dx = 0; region.dy = info->var.yoffset + rs; region.height = rw; @@ -192,7 +192,7 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dx = info->var.xoffset; region.dy = info->var.yoffset; region.height = info->var.yres; diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c index 1936afc78fec..e165a3fad29a 100644 --- a/drivers/video/fbdev/core/fbcon_ud.c +++ b/drivers/video/fbdev/core/fbcon_ud.c @@ -231,7 +231,7 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info, region.color = color; region.rop = ROP_COPY; - if (rw && !bottom_only) { + if ((int) rw > 0 && !bottom_only) { region.dy = 0; region.dx = info->var.xoffset; region.width = rw; @@ -239,7 +239,7 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info, info->fbops->fb_fillrect(info, ®ion); } - if (bh) { + if ((int) bh > 0) { region.dy = info->var.yoffset; region.dx = info->var.xoffset; region.height = bh; diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 5809e5f5b157..5c92e4a50882 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -85,7 +85,7 @@ config VIRTIO_MEM depends on VIRTIO depends on MEMORY_HOTPLUG_SPARSE depends on MEMORY_HOTREMOVE - select CONTIG_ALLOC + depends on CONTIG_ALLOC help This driver provides access to virtio-mem paravirtualized memory devices, allowing to hotplug and hotunplug memory. diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 1f157d2f4952..8be02f333b7a 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -578,10 +578,14 @@ static int init_vqs(struct virtio_balloon *vb) static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb) { if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID, - &vb->config_read_bitmap)) + &vb->config_read_bitmap)) { virtio_cread(vb->vdev, struct virtio_balloon_config, free_page_hint_cmd_id, &vb->cmd_id_received_cache); + /* Legacy balloon config space is LE, unlike all other devices. */ + if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1)) + vb->cmd_id_received_cache = le32_to_cpu((__force __le32)vb->cmd_id_received_cache); + } return vb->cmd_id_received_cache; } @@ -974,6 +978,11 @@ static int virtballoon_probe(struct virtio_device *vdev) /* * Let the hypervisor know that we are expecting a * specific value to be written back in balloon pages. + * + * If the PAGE_POISON value was larger than a byte we would + * need to byte swap poison_val here to guarantee it is + * little-endian. However for now it is a single byte so we + * can pass it as-is. */ if (!want_init_on_free()) memset(&poison_val, PAGE_POISON, sizeof(poison_val)); diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 9d16aaffca9d..627ac0487494 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -641,11 +641,11 @@ static int vm_cmdline_set(const char *device, &vm_cmdline_id, &consumed); /* - * sscanf() must processes at least 2 chunks; also there + * sscanf() must process at least 2 chunks; also there * must be no extra characters after the last chunk, so * str[consumed] must be '\0' */ - if (processed < 2 || str[consumed]) + if (processed < 2 || str[consumed] || irq == 0) return -EINVAL; resources[0].flags = IORESOURCE_MEM; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index d888e71e66b6..ea10f7bc99ab 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1461,6 +1461,7 @@ static int btrfs_find_all_roots_safe(struct btrfs_trans_handle *trans, if (ret < 0 && ret != -ENOENT) { ulist_free(tmp); ulist_free(*roots); + *roots = NULL; return ret; } node = ulist_next(tmp, &uiter); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index c037ef514b64..613920c17ac1 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -65,11 +65,8 @@ static u64 btrfs_reduce_alloc_profile(struct btrfs_fs_info *fs_info, u64 flags) spin_lock(&fs_info->balance_lock); target = get_restripe_target(fs_info, flags); if (target) { - /* Pick target profile only if it's already available */ - if ((flags & target) & BTRFS_EXTENDED_PROFILE_MASK) { - spin_unlock(&fs_info->balance_lock); - return extended_to_chunk(target); - } + spin_unlock(&fs_info->balance_lock); + return extended_to_chunk(target); } spin_unlock(&fs_info->balance_lock); @@ -118,12 +115,12 @@ u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags) void btrfs_get_block_group(struct btrfs_block_group *cache) { - atomic_inc(&cache->count); + refcount_inc(&cache->refs); } void btrfs_put_block_group(struct btrfs_block_group *cache) { - if (atomic_dec_and_test(&cache->count)) { + if (refcount_dec_and_test(&cache->refs)) { WARN_ON(cache->pinned > 0); WARN_ON(cache->reserved > 0); @@ -1111,7 +1108,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, if (ret < 0) goto out; - mutex_lock(&fs_info->chunk_mutex); spin_lock(&block_group->lock); block_group->removed = 1; /* @@ -1143,8 +1139,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, remove_em = (atomic_read(&block_group->frozen) == 0); spin_unlock(&block_group->lock); - mutex_unlock(&fs_info->chunk_mutex); - if (remove_em) { struct extent_map_tree *em_tree; @@ -1532,21 +1526,70 @@ void btrfs_mark_bg_unused(struct btrfs_block_group *bg) spin_unlock(&fs_info->unused_bgs_lock); } +static int read_bg_from_eb(struct btrfs_fs_info *fs_info, struct btrfs_key *key, + struct btrfs_path *path) +{ + struct extent_map_tree *em_tree; + struct extent_map *em; + struct btrfs_block_group_item bg; + struct extent_buffer *leaf; + int slot; + u64 flags; + int ret = 0; + + slot = path->slots[0]; + leaf = path->nodes[0]; + + em_tree = &fs_info->mapping_tree; + read_lock(&em_tree->lock); + em = lookup_extent_mapping(em_tree, key->objectid, key->offset); + read_unlock(&em_tree->lock); + if (!em) { + btrfs_err(fs_info, + "logical %llu len %llu found bg but no related chunk", + key->objectid, key->offset); + return -ENOENT; + } + + if (em->start != key->objectid || em->len != key->offset) { + btrfs_err(fs_info, + "block group %llu len %llu mismatch with chunk %llu len %llu", + key->objectid, key->offset, em->start, em->len); + ret = -EUCLEAN; + goto out_free_em; + } + + read_extent_buffer(leaf, &bg, btrfs_item_ptr_offset(leaf, slot), + sizeof(bg)); + flags = btrfs_stack_block_group_flags(&bg) & + BTRFS_BLOCK_GROUP_TYPE_MASK; + + if (flags != (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) { + btrfs_err(fs_info, +"block group %llu len %llu type flags 0x%llx mismatch with chunk type flags 0x%llx", + key->objectid, key->offset, flags, + (BTRFS_BLOCK_GROUP_TYPE_MASK & em->map_lookup->type)); + ret = -EUCLEAN; + } + +out_free_em: + free_extent_map(em); + return ret; +} + static int find_first_block_group(struct btrfs_fs_info *fs_info, struct btrfs_path *path, struct btrfs_key *key) { struct btrfs_root *root = fs_info->extent_root; - int ret = 0; + int ret; struct btrfs_key found_key; struct extent_buffer *leaf; - struct btrfs_block_group_item bg; - u64 flags; int slot; ret = btrfs_search_slot(NULL, root, key, path, 0, 0); if (ret < 0) - goto out; + return ret; while (1) { slot = path->slots[0]; @@ -1563,49 +1606,10 @@ static int find_first_block_group(struct btrfs_fs_info *fs_info, if (found_key.objectid >= key->objectid && found_key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) { - struct extent_map_tree *em_tree; - struct extent_map *em; - - em_tree = &root->fs_info->mapping_tree; - read_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, found_key.objectid, - found_key.offset); - read_unlock(&em_tree->lock); - if (!em) { - btrfs_err(fs_info, - "logical %llu len %llu found bg but no related chunk", - found_key.objectid, found_key.offset); - ret = -ENOENT; - } else if (em->start != found_key.objectid || - em->len != found_key.offset) { - btrfs_err(fs_info, - "block group %llu len %llu mismatch with chunk %llu len %llu", - found_key.objectid, found_key.offset, - em->start, em->len); - ret = -EUCLEAN; - } else { - read_extent_buffer(leaf, &bg, - btrfs_item_ptr_offset(leaf, slot), - sizeof(bg)); - flags = btrfs_stack_block_group_flags(&bg) & - BTRFS_BLOCK_GROUP_TYPE_MASK; - - if (flags != (em->map_lookup->type & - BTRFS_BLOCK_GROUP_TYPE_MASK)) { - btrfs_err(fs_info, -"block group %llu len %llu type flags 0x%llx mismatch with chunk type flags 0x%llx", - found_key.objectid, - found_key.offset, flags, - (BTRFS_BLOCK_GROUP_TYPE_MASK & - em->map_lookup->type)); - ret = -EUCLEAN; - } else { - ret = 0; - } - } - free_extent_map(em); - goto out; + ret = read_bg_from_eb(fs_info, &found_key, path); + break; } + path->slots[0]++; } out: @@ -1657,19 +1661,12 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, return -EIO; map = em->map_lookup; - data_stripe_length = em->len; + data_stripe_length = em->orig_block_len; io_stripe_size = map->stripe_len; - if (map->type & BTRFS_BLOCK_GROUP_RAID10) - data_stripe_length = div_u64(data_stripe_length, - map->num_stripes / map->sub_stripes); - else if (map->type & BTRFS_BLOCK_GROUP_RAID0) - data_stripe_length = div_u64(data_stripe_length, map->num_stripes); - else if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) { - data_stripe_length = div_u64(data_stripe_length, - nr_data_stripes(map)); + /* For RAID5/6 adjust to a full IO stripe length */ + if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) io_stripe_size = map->stripe_len * nr_data_stripes(map); - } buf = kcalloc(map->num_stripes, sizeof(u64), GFP_NOFS); if (!buf) { @@ -1748,25 +1745,12 @@ static int exclude_super_stripes(struct btrfs_block_group *cache) return ret; while (nr--) { - u64 start, len; - - if (logical[nr] > cache->start + cache->length) - continue; - - if (logical[nr] + stripe_len <= cache->start) - continue; - - start = logical[nr]; - if (start < cache->start) { - start = cache->start; - len = (logical[nr] + stripe_len) - start; - } else { - len = min_t(u64, stripe_len, - cache->start + cache->length - start); - } + u64 len = min_t(u64, stripe_len, + cache->start + cache->length - logical[nr]); cache->bytes_super += len; - ret = btrfs_add_excluded_extent(fs_info, start, len); + ret = btrfs_add_excluded_extent(fs_info, logical[nr], + len); if (ret) { kfree(logical); return ret; @@ -1818,7 +1802,7 @@ static struct btrfs_block_group *btrfs_create_block_group_cache( cache->discard_index = BTRFS_DISCARD_INDEX_UNUSED; - atomic_set(&cache->count, 1); + refcount_set(&cache->refs, 1); spin_lock_init(&cache->lock); init_rwsem(&cache->data_rwsem); INIT_LIST_HEAD(&cache->list); @@ -2207,54 +2191,6 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, return 0; } -static u64 update_block_group_flags(struct btrfs_fs_info *fs_info, u64 flags) -{ - u64 num_devices; - u64 stripped; - - /* - * if restripe for this chunk_type is on pick target profile and - * return, otherwise do the usual balance - */ - stripped = get_restripe_target(fs_info, flags); - if (stripped) - return extended_to_chunk(stripped); - - num_devices = fs_info->fs_devices->rw_devices; - - stripped = BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID56_MASK | - BTRFS_BLOCK_GROUP_RAID1_MASK | BTRFS_BLOCK_GROUP_RAID10; - - if (num_devices == 1) { - stripped |= BTRFS_BLOCK_GROUP_DUP; - stripped = flags & ~stripped; - - /* turn raid0 into single device chunks */ - if (flags & BTRFS_BLOCK_GROUP_RAID0) - return stripped; - - /* turn mirroring into duplication */ - if (flags & (BTRFS_BLOCK_GROUP_RAID1_MASK | - BTRFS_BLOCK_GROUP_RAID10)) - return stripped | BTRFS_BLOCK_GROUP_DUP; - } else { - /* they already had raid on here, just return */ - if (flags & stripped) - return flags; - - stripped |= BTRFS_BLOCK_GROUP_DUP; - stripped = flags & ~stripped; - - /* switch duplicated blocks with raid1 */ - if (flags & BTRFS_BLOCK_GROUP_DUP) - return stripped | BTRFS_BLOCK_GROUP_RAID1; - - /* this is drive concat, leave it alone */ - } - - return flags; -} - /* * Mark one block group RO, can be called several times for the same block * group. @@ -2300,7 +2236,7 @@ again: * If we are changing raid levels, try to allocate a * corresponding block group with the new raid level. */ - alloc_flags = update_block_group_flags(fs_info, cache->flags); + alloc_flags = btrfs_get_alloc_profile(fs_info, cache->flags); if (alloc_flags != cache->flags) { ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); @@ -2327,7 +2263,7 @@ again: ret = inc_block_group_ro(cache, 0); out: if (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM) { - alloc_flags = update_block_group_flags(fs_info, cache->flags); + alloc_flags = btrfs_get_alloc_profile(fs_info, cache->flags); mutex_lock(&fs_info->chunk_mutex); check_system_chunk(trans, alloc_flags); mutex_unlock(&fs_info->chunk_mutex); @@ -2521,7 +2457,8 @@ again: num_pages *= 16; num_pages *= PAGE_SIZE; - ret = btrfs_check_data_free_space(inode, &data_reserved, 0, num_pages); + ret = btrfs_check_data_free_space(BTRFS_I(inode), &data_reserved, 0, + num_pages); if (ret) goto out_put; @@ -3392,7 +3329,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) ASSERT(list_empty(&block_group->dirty_list)); ASSERT(list_empty(&block_group->io_list)); ASSERT(list_empty(&block_group->bg_list)); - ASSERT(atomic_read(&block_group->count) == 1); + ASSERT(refcount_read(&block_group->refs) == 1); btrfs_put_block_group(block_group); spin_lock(&info->block_group_cache_lock); @@ -3447,7 +3384,6 @@ void btrfs_unfreeze_block_group(struct btrfs_block_group *block_group) spin_unlock(&block_group->lock); if (cleanup) { - mutex_lock(&fs_info->chunk_mutex); em_tree = &fs_info->mapping_tree; write_lock(&em_tree->lock); em = lookup_extent_mapping(em_tree, block_group->start, @@ -3455,7 +3391,6 @@ void btrfs_unfreeze_block_group(struct btrfs_block_group *block_group) BUG_ON(!em); /* logic error, can't happen */ remove_extent_mapping(em_tree, em); write_unlock(&em_tree->lock); - mutex_unlock(&fs_info->chunk_mutex); /* once for us and once for the tree */ free_extent_map(em); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index b6ee70a039c7..adfd7583a17b 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -114,8 +114,7 @@ struct btrfs_block_group { /* For block groups in the same raid type */ struct list_head list; - /* Usage count */ - atomic_t count; + refcount_t refs; /* * List of struct btrfs_free_clusters for this block group. diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index e7d709505cb1..c47b6c6fea9f 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -152,6 +152,17 @@ struct btrfs_inode { u64 last_unlink_trans; /* + * The id/generation of the last transaction where this inode was + * either the source or the destination of a clone/dedupe operation. + * Used when logging an inode to know if there are shared extents that + * need special care when logging checksum items, to avoid duplicate + * checksum items in a log (which can lead to a corruption where we end + * up with missing checksum ranges after log replay). + * Protected by the vfs inode lock. + */ + u64 last_reflink_trans; + + /* * Number of bytes outstanding that are going to need csums. This is * used in ENOSPC accounting. */ diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 32e11a23b47f..81a8c87a5afb 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -631,10 +631,8 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, int pass; selected_super = kzalloc(sizeof(*selected_super), GFP_NOFS); - if (NULL == selected_super) { - pr_info("btrfsic: error, kmalloc failed!\n"); + if (!selected_super) return -ENOMEM; - } list_for_each_entry(device, dev_head, dev_list) { int i; @@ -795,7 +793,6 @@ static int btrfsic_process_superblock_dev_mirror( if (NULL == superblock_tmp) { superblock_tmp = btrfsic_block_alloc(); if (NULL == superblock_tmp) { - pr_info("btrfsic: error, kmalloc failed!\n"); ret = -1; goto out; } @@ -921,9 +918,7 @@ static struct btrfsic_stack_frame *btrfsic_stack_frame_alloc(void) struct btrfsic_stack_frame *sf; sf = kzalloc(sizeof(*sf), GFP_NOFS); - if (NULL == sf) - pr_info("btrfsic: alloc memory failed!\n"); - else + if (sf) sf->magic = BTRFSIC_BLOCK_STACK_FRAME_MAGIC_NUMBER; return sf; } @@ -1313,7 +1308,6 @@ static int btrfsic_create_link_to_next_block( if (NULL == l) { l = btrfsic_block_link_alloc(); if (NULL == l) { - pr_info("btrfsic: error, kmalloc failed!\n"); btrfsic_release_block_ctx(next_block_ctx); *next_blockp = NULL; return -1; @@ -1470,7 +1464,6 @@ static int btrfsic_handle_extent_data( mirror_num, &block_was_created); if (NULL == next_block) { - pr_info("btrfsic: error, kmalloc failed!\n"); btrfsic_release_block_ctx(&next_block_ctx); return -1; } @@ -2013,7 +2006,6 @@ again: block = btrfsic_block_alloc(); if (NULL == block) { - pr_info("btrfsic: error, kmalloc failed!\n"); btrfsic_release_block_ctx(&block_ctx); goto continue_loop; } @@ -2234,7 +2226,6 @@ static int btrfsic_process_written_superblock( mirror_num, &was_created); if (NULL == next_block) { - pr_info("btrfsic: error, kmalloc failed!\n"); btrfsic_release_block_ctx(&tmp_next_block_ctx); return -1; } @@ -2542,10 +2533,8 @@ static struct btrfsic_block_link *btrfsic_block_link_lookup_or_add( &state->block_link_hashtable); if (NULL == l) { l = btrfsic_block_link_alloc(); - if (NULL == l) { - pr_info("btrfsic: error, kmalloc failed!\n"); + if (!l) return NULL; - } l->block_ref_to = next_block; l->block_ref_from = from_block; @@ -2589,10 +2578,9 @@ static struct btrfsic_block *btrfsic_block_lookup_or_add( struct btrfsic_dev_state *dev_state; block = btrfsic_block_alloc(); - if (NULL == block) { - pr_info("btrfsic: error, kmalloc failed!\n"); + if (!block) return NULL; - } + dev_state = btrfsic_dev_state_lookup(block_ctx->dev->bdev->bd_dev); if (NULL == dev_state) { pr_info("btrfsic: error, lookup dev_state failed!\n"); @@ -2797,10 +2785,8 @@ int btrfsic_mount(struct btrfs_fs_info *fs_info, return -1; } state = kvzalloc(sizeof(*state), GFP_KERNEL); - if (!state) { - pr_info("btrfs check-integrity: allocation failed!\n"); + if (!state) return -ENOMEM; - } if (!btrfsic_is_initialized) { mutex_init(&btrfsic_mutex); @@ -2829,7 +2815,6 @@ int btrfsic_mount(struct btrfs_fs_info *fs_info, ds = btrfsic_dev_state_alloc(); if (NULL == ds) { - pr_info("btrfs check-integrity: kmalloc() failed!\n"); mutex_unlock(&btrfsic_mutex); return -ENOMEM; } diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index c6e648603f85..1ab56a734e70 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -172,18 +172,17 @@ static inline int compressed_bio_size(struct btrfs_fs_info *fs_info, (DIV_ROUND_UP(disk_size, fs_info->sectorsize)) * csum_size; } -static int check_compressed_csum(struct btrfs_inode *inode, - struct compressed_bio *cb, +static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio, u64 disk_start) { struct btrfs_fs_info *fs_info = inode->root->fs_info; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); - int ret; struct page *page; unsigned long i; char *kaddr; u8 csum[BTRFS_CSUM_SIZE]; + struct compressed_bio *cb = bio->bi_private; u8 *cb_sum = cb->sums; if (inode->flags & BTRFS_INODE_NODATASUM) @@ -201,15 +200,15 @@ static int check_compressed_csum(struct btrfs_inode *inode, if (memcmp(&csum, cb_sum, csum_size)) { btrfs_print_data_csum_error(inode, disk_start, csum, cb_sum, cb->mirror_num); - ret = -EIO; - goto fail; + if (btrfs_io_bio(bio)->device) + btrfs_dev_stat_inc_and_print( + btrfs_io_bio(bio)->device, + BTRFS_DEV_STAT_CORRUPTION_ERRS); + return -EIO; } cb_sum += csum_size; - } - ret = 0; -fail: - return ret; + return 0; } /* when we finish reading compressed pages from the disk, we @@ -244,7 +243,6 @@ static void end_compressed_bio_read(struct bio *bio) * Record the correct mirror_num in cb->orig_bio so that * read-repair can work properly. */ - ASSERT(btrfs_io_bio(cb->orig_bio)); btrfs_io_bio(cb->orig_bio)->mirror_num = mirror; cb->mirror_num = mirror; @@ -256,7 +254,7 @@ static void end_compressed_bio_read(struct bio *bio) goto csum_failed; inode = cb->inode; - ret = check_compressed_csum(BTRFS_I(inode), cb, + ret = check_compressed_csum(BTRFS_I(inode), bio, (u64)bio->bi_iter.bi_sector << 9); if (ret) goto csum_failed; @@ -405,7 +403,7 @@ out: * This also checksums the file bytes and gets things ready for * the end io hooks. */ -blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, +blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, unsigned long len, u64 disk_start, unsigned long compressed_len, struct page **compressed_pages, @@ -413,7 +411,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, unsigned int write_flags, struct cgroup_subsys_state *blkcg_css) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct bio *bio = NULL; struct compressed_bio *cb; unsigned long bytes_left; @@ -421,7 +419,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, struct page *page; u64 first_byte = disk_start; blk_status_t ret; - int skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; + int skip_sum = inode->flags & BTRFS_INODE_NODATASUM; WARN_ON(!PAGE_ALIGNED(start)); cb = kmalloc(compressed_bio_size(fs_info, compressed_len), GFP_NOFS); @@ -429,7 +427,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, return BLK_STS_RESOURCE; refcount_set(&cb->pending_bios, 0); cb->errors = 0; - cb->inode = inode; + cb->inode = &inode->vfs_inode; cb->start = start; cb->len = len; cb->mirror_num = 0; @@ -455,7 +453,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, int submit = 0; page = compressed_pages[pg_index]; - page->mapping = inode->i_mapping; + page->mapping = inode->vfs_inode.i_mapping; if (bio->bi_iter.bi_size) submit = btrfs_bio_fits_in_stripe(page, PAGE_SIZE, bio, 0); diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index 284a3ad31350..9f3dbe372631 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -8,6 +8,8 @@ #include <linux/sizes.h> +struct btrfs_inode; + /* * We want to make sure that amount of RAM required to uncompress an extent is * reasonable, so we limit the total size in ram of a compressed extent to @@ -88,7 +90,7 @@ int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start, unsigned long total_out, u64 disk_start, struct bio *bio); -blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, +blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, unsigned long len, u64 disk_start, unsigned long compressed_len, struct page **compressed_pages, diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 82ab6e5a386d..70e49d8d4f6c 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1501,6 +1501,22 @@ static int close_blocks(u64 blocknr, u64 other, u32 blocksize) return 0; } +#ifdef __LITTLE_ENDIAN + +/* + * Compare two keys, on little-endian the disk order is same as CPU order and + * we can avoid the conversion. + */ +static int comp_keys(const struct btrfs_disk_key *disk_key, + const struct btrfs_key *k2) +{ + const struct btrfs_key *k1 = (const struct btrfs_key *)disk_key; + + return btrfs_comp_cpu_keys(k1, k2); +} + +#else + /* * compare two keys in a memcmp fashion */ @@ -1513,6 +1529,7 @@ static int comp_keys(const struct btrfs_disk_key *disk, return btrfs_comp_cpu_keys(&k1, k2); } +#endif /* * same as comp_keys only with two btrfs_key's diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index d404cce8ae40..9c7e466f27a9 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -546,11 +546,6 @@ enum { */ BTRFS_FS_EXCL_OP, /* - * To info transaction_kthread we need an immediate commit so it - * doesn't need to wait for commit_interval - */ - BTRFS_FS_NEED_ASYNC_COMMIT, - /* * Indicate that balance has been set up from the ioctl and is in the * main phase. The fs_info::balance_ctl is initialized. * Set and cleared while holding fs_info::balance_mutex. @@ -779,6 +774,7 @@ struct btrfs_fs_info { u32 thread_pool_size; struct kobject *space_info_kobj; + struct kobject *qgroups_kobj; u64 total_pinned; @@ -1011,6 +1007,8 @@ enum { BTRFS_ROOT_DEAD_TREE, /* The root has a log tree. Used only for subvolume roots. */ BTRFS_ROOT_HAS_LOG_TREE, + /* Qgroup flushing is in progress */ + BTRFS_ROOT_QGROUP_FLUSHING, }; /* @@ -1059,8 +1057,10 @@ struct btrfs_root { wait_queue_head_t log_writer_wait; wait_queue_head_t log_commit_wait[2]; struct list_head log_ctxs[2]; + /* Used only for log trees of subvolumes, not for the log root tree */ atomic_t log_writers; atomic_t log_commit[2]; + /* Used only for log trees of subvolumes, not for the log root tree */ atomic_t log_batch; int log_transid; /* No matter the commit succeeds or not*/ @@ -1075,7 +1075,6 @@ struct btrfs_root { u64 highest_objectid; - u64 defrag_trans_start; struct btrfs_key defrag_progress; struct btrfs_key defrag_max; @@ -1162,6 +1161,7 @@ struct btrfs_root { spinlock_t qgroup_meta_rsv_lock; u64 qgroup_meta_rsv_pertrans; u64 qgroup_meta_rsv_prealloc; + wait_queue_head_t qgroup_flush_wait; /* Number of active swapfiles */ atomic_t nr_swapfiles; @@ -1277,18 +1277,18 @@ static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info) BTRFS_MOUNT_##opt) #define btrfs_set_and_info(fs_info, opt, fmt, args...) \ -{ \ +do { \ if (!btrfs_test_opt(fs_info, opt)) \ btrfs_info(fs_info, fmt, ##args); \ btrfs_set_opt(fs_info->mount_opt, opt); \ -} +} while (0) #define btrfs_clear_and_info(fs_info, opt, fmt, args...) \ -{ \ +do { \ if (btrfs_test_opt(fs_info, opt)) \ btrfs_info(fs_info, fmt, ##args); \ btrfs_clear_opt(fs_info->mount_opt, opt); \ -} +} while (0) /* * Requests for changes that need to be done during transaction commit. @@ -1895,6 +1895,52 @@ BTRFS_SETGET_STACK_FUNCS(disk_key_objectid, struct btrfs_disk_key, BTRFS_SETGET_STACK_FUNCS(disk_key_offset, struct btrfs_disk_key, offset, 64); BTRFS_SETGET_STACK_FUNCS(disk_key_type, struct btrfs_disk_key, type, 8); +#ifdef __LITTLE_ENDIAN + +/* + * Optimized helpers for little-endian architectures where CPU and on-disk + * structures have the same endianness and we can skip conversions. + */ + +static inline void btrfs_disk_key_to_cpu(struct btrfs_key *cpu_key, + const struct btrfs_disk_key *disk_key) +{ + memcpy(cpu_key, disk_key, sizeof(struct btrfs_key)); +} + +static inline void btrfs_cpu_key_to_disk(struct btrfs_disk_key *disk_key, + const struct btrfs_key *cpu_key) +{ + memcpy(disk_key, cpu_key, sizeof(struct btrfs_key)); +} + +static inline void btrfs_node_key_to_cpu(const struct extent_buffer *eb, + struct btrfs_key *cpu_key, int nr) +{ + struct btrfs_disk_key *disk_key = (struct btrfs_disk_key *)cpu_key; + + btrfs_node_key(eb, disk_key, nr); +} + +static inline void btrfs_item_key_to_cpu(const struct extent_buffer *eb, + struct btrfs_key *cpu_key, int nr) +{ + struct btrfs_disk_key *disk_key = (struct btrfs_disk_key *)cpu_key; + + btrfs_item_key(eb, disk_key, nr); +} + +static inline void btrfs_dir_item_key_to_cpu(const struct extent_buffer *eb, + const struct btrfs_dir_item *item, + struct btrfs_key *cpu_key) +{ + struct btrfs_disk_key *disk_key = (struct btrfs_disk_key *)cpu_key; + + btrfs_dir_item_key(eb, item, disk_key); +} + +#else + static inline void btrfs_disk_key_to_cpu(struct btrfs_key *cpu, const struct btrfs_disk_key *disk) { @@ -1936,6 +1982,8 @@ static inline void btrfs_dir_item_key_to_cpu(const struct extent_buffer *eb, btrfs_disk_key_to_cpu(key, &disk_key); } +#endif + /* struct btrfs_header */ BTRFS_SETGET_HEADER_FUNCS(header_bytenr, struct btrfs_header, bytenr, 64); BTRFS_SETGET_HEADER_FUNCS(header_generation, struct btrfs_header, @@ -2232,7 +2280,8 @@ static inline unsigned int leaf_data_end(const struct extent_buffer *leaf) } /* struct btrfs_file_extent_item */ -BTRFS_SETGET_FUNCS(file_extent_type, struct btrfs_file_extent_item, type, 8); +BTRFS_SETGET_STACK_FUNCS(stack_file_extent_type, struct btrfs_file_extent_item, + type, 8); BTRFS_SETGET_STACK_FUNCS(stack_file_extent_disk_bytenr, struct btrfs_file_extent_item, disk_bytenr, 64); BTRFS_SETGET_STACK_FUNCS(stack_file_extent_offset, @@ -2241,6 +2290,8 @@ BTRFS_SETGET_STACK_FUNCS(stack_file_extent_generation, struct btrfs_file_extent_item, generation, 64); BTRFS_SETGET_STACK_FUNCS(stack_file_extent_num_bytes, struct btrfs_file_extent_item, num_bytes, 64); +BTRFS_SETGET_STACK_FUNCS(stack_file_extent_ram_bytes, + struct btrfs_file_extent_item, ram_bytes, 64); BTRFS_SETGET_STACK_FUNCS(stack_file_extent_disk_num_bytes, struct btrfs_file_extent_item, disk_num_bytes, 64); BTRFS_SETGET_STACK_FUNCS(stack_file_extent_compression, @@ -2257,6 +2308,7 @@ static inline u32 btrfs_file_extent_calc_inline_size(u32 datasize) return BTRFS_FILE_EXTENT_INLINE_DATA_START + datasize; } +BTRFS_SETGET_FUNCS(file_extent_type, struct btrfs_file_extent_item, type, 8); BTRFS_SETGET_FUNCS(file_extent_disk_bytenr, struct btrfs_file_extent_item, disk_bytenr, 64); BTRFS_SETGET_FUNCS(file_extent_generation, struct btrfs_file_extent_item, @@ -2508,16 +2560,46 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr); void btrfs_clear_space_info_full(struct btrfs_fs_info *info); +/* + * Different levels for to flush space when doing space reservations. + * + * The higher the level, the more methods we try to reclaim space. + */ enum btrfs_reserve_flush_enum { /* If we are in the transaction, we can't flush anything.*/ BTRFS_RESERVE_NO_FLUSH, + /* - * Flushing delalloc may cause deadlock somewhere, in this - * case, use FLUSH LIMIT + * Flush space by: + * - Running delayed inode items + * - Allocating a new chunk */ BTRFS_RESERVE_FLUSH_LIMIT, + + /* + * Flush space by: + * - Running delayed inode items + * - Running delayed refs + * - Running delalloc and waiting for ordered extents + * - Allocating a new chunk + */ BTRFS_RESERVE_FLUSH_EVICT, + + /* + * Flush space by above mentioned methods and by: + * - Running delayed iputs + * - Commiting transaction + * + * Can be interruped by fatal signal. + */ BTRFS_RESERVE_FLUSH_ALL, + + /* + * Pretty much the same as FLUSH_ALL, but can also steal space from + * global rsv. + * + * Can be interruped by fatal signal. + */ BTRFS_RESERVE_FLUSH_ALL_STEAL, }; @@ -2831,8 +2913,8 @@ int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans, int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_ordered_sum *sums); -blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, - u64 file_start, int contig); +blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio, + u64 file_start, int contig); int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, struct list_head *list, int search_commit); void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode, @@ -2875,7 +2957,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, int btrfs_start_delalloc_snapshot(struct btrfs_root *root); int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr); -int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end, +int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state); int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, @@ -2928,7 +3010,7 @@ int btrfs_prealloc_file_range_trans(struct inode *inode, struct btrfs_trans_handle *trans, int mode, u64 start, u64 num_bytes, u64 min_size, loff_t actual_len, u64 *alloc_hint); -int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page, +int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page, u64 start, u64 end, int *page_started, unsigned long *nr_written, struct writeback_control *wbc); int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end); @@ -2962,7 +3044,7 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end, int skip_pinned); extern const struct file_operations btrfs_file_operations; int __btrfs_drop_extents(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode, + struct btrfs_root *root, struct btrfs_inode *inode, struct btrfs_path *path, u64 start, u64 end, u64 *drop_end, int drop_cache, int replace_extent, @@ -2978,10 +3060,13 @@ int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path, int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, u64 start, u64 end); int btrfs_release_file(struct inode *inode, struct file *file); -int btrfs_dirty_pages(struct inode *inode, struct page **pages, +int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, struct extent_state **cached); int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end); +int btrfs_check_nocow_lock(struct btrfs_inode *inode, loff_t pos, + size_t *write_bytes); +void btrfs_check_nocow_unlock(struct btrfs_inode *inode); /* tree-defrag.c */ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, @@ -3194,7 +3279,7 @@ do { \ /* Report first abort since mount */ \ if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, \ &((trans)->fs_info->fs_state))) { \ - if ((errno) != -EIO) { \ + if ((errno) != -EIO && (errno) != -EROFS) { \ WARN(1, KERN_DEBUG \ "BTRFS: Transaction aborted (error %d)\n", \ (errno)); \ @@ -3378,7 +3463,7 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans, int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_recover_relocation(struct btrfs_root *root); -int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len); +int btrfs_reloc_clone_csums(struct btrfs_inode *inode, u64 file_pos, u64 len); int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer *cow); diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index 1245739a3a6e..0e354e9e57d0 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -237,10 +237,10 @@ commit_trans: return 0; } -int btrfs_check_data_free_space(struct inode *inode, +int btrfs_check_data_free_space(struct btrfs_inode *inode, struct extent_changeset **reserved, u64 start, u64 len) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode->root->fs_info; int ret; /* align the range */ @@ -248,14 +248,14 @@ int btrfs_check_data_free_space(struct inode *inode, round_down(start, fs_info->sectorsize); start = round_down(start, fs_info->sectorsize); - ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), len); + ret = btrfs_alloc_data_chunk_ondemand(inode, len); if (ret < 0) return ret; /* Use new btrfs_qgroup_reserve_data to reserve precious data space. */ ret = btrfs_qgroup_reserve_data(inode, reserved, start, len); if (ret < 0) - btrfs_free_reserved_data_space_noquota(inode, start, len); + btrfs_free_reserved_data_space_noquota(fs_info, len); else ret = 0; return ret; @@ -269,16 +269,12 @@ int btrfs_check_data_free_space(struct inode *inode, * which we can't sleep and is sure it won't affect qgroup reserved space. * Like clear_bit_hook(). */ -void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start, +void btrfs_free_reserved_data_space_noquota(struct btrfs_fs_info *fs_info, u64 len) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_space_info *data_sinfo; - /* Make sure the range is aligned to sectorsize */ - len = round_up(start + len, fs_info->sectorsize) - - round_down(start, fs_info->sectorsize); - start = round_down(start, fs_info->sectorsize); + ASSERT(IS_ALIGNED(len, fs_info->sectorsize)); data_sinfo = fs_info->data_sinfo; spin_lock(&data_sinfo->lock); @@ -293,17 +289,17 @@ void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start, * This one will handle the per-inode data rsv map for accurate reserved * space framework. */ -void btrfs_free_reserved_data_space(struct inode *inode, +void btrfs_free_reserved_data_space(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len) { - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_fs_info *fs_info = inode->root->fs_info; /* Make sure the range is aligned to sectorsize */ - len = round_up(start + len, root->fs_info->sectorsize) - - round_down(start, root->fs_info->sectorsize); - start = round_down(start, root->fs_info->sectorsize); + len = round_up(start + len, fs_info->sectorsize) - + round_down(start, fs_info->sectorsize); + start = round_down(start, fs_info->sectorsize); - btrfs_free_reserved_data_space_noquota(inode, start, len); + btrfs_free_reserved_data_space_noquota(fs_info, len); btrfs_qgroup_free_data(inode, reserved, start, len); } @@ -557,7 +553,7 @@ void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes) * Return 0 for success * Return <0 for error(-ENOSPC or -EQUOT) */ -int btrfs_delalloc_reserve_space(struct inode *inode, +int btrfs_delalloc_reserve_space(struct btrfs_inode *inode, struct extent_changeset **reserved, u64 start, u64 len) { int ret; @@ -565,7 +561,7 @@ int btrfs_delalloc_reserve_space(struct inode *inode, ret = btrfs_check_data_free_space(inode, reserved, start, len); if (ret < 0) return ret; - ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len); + ret = btrfs_delalloc_reserve_metadata(inode, len); if (ret < 0) btrfs_free_reserved_data_space(inode, *reserved, start, len); return ret; @@ -583,10 +579,10 @@ int btrfs_delalloc_reserve_space(struct inode *inode, * list if there are no delalloc bytes left. * Also it will handle the qgroup reserved space. */ -void btrfs_delalloc_release_space(struct inode *inode, +void btrfs_delalloc_release_space(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len, bool qgroup_free) { - btrfs_delalloc_release_metadata(BTRFS_I(inode), len, qgroup_free); + btrfs_delalloc_release_metadata(inode, len, qgroup_free); btrfs_free_reserved_data_space(inode, reserved, start, len); } diff --git a/fs/btrfs/delalloc-space.h b/fs/btrfs/delalloc-space.h index 54466fbd7075..28bf5c3ef430 100644 --- a/fs/btrfs/delalloc-space.h +++ b/fs/btrfs/delalloc-space.h @@ -6,18 +6,18 @@ struct extent_changeset; int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes); -int btrfs_check_data_free_space(struct inode *inode, +int btrfs_check_data_free_space(struct btrfs_inode *inode, struct extent_changeset **reserved, u64 start, u64 len); -void btrfs_free_reserved_data_space(struct inode *inode, +void btrfs_free_reserved_data_space(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len); -void btrfs_delalloc_release_space(struct inode *inode, +void btrfs_delalloc_release_space(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len, bool qgroup_free); -void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start, +void btrfs_free_reserved_data_space_noquota(struct btrfs_fs_info *fs_info, u64 len); void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes, bool qgroup_free); -int btrfs_delalloc_reserve_space(struct inode *inode, +int btrfs_delalloc_reserve_space(struct btrfs_inode *inode, struct extent_changeset **reserved, u64 start, u64 len); #endif /* BTRFS_DELALLOC_SPACE_H */ diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b1a148058773..c850d7f44fbe 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1116,6 +1116,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, mutex_init(&root->log_mutex); mutex_init(&root->ordered_extent_mutex); mutex_init(&root->delalloc_mutex); + init_waitqueue_head(&root->qgroup_flush_wait); init_waitqueue_head(&root->log_writer_wait); init_waitqueue_head(&root->log_commit_wait[0]); init_waitqueue_head(&root->log_commit_wait[1]); @@ -1141,10 +1142,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, memset(&root->root_key, 0, sizeof(root->root_key)); memset(&root->root_item, 0, sizeof(root->root_item)); memset(&root->defrag_progress, 0, sizeof(root->defrag_progress)); - if (!dummy) - root->defrag_trans_start = fs_info->generation; - else - root->defrag_trans_start = 0; root->root_key.objectid = objectid; root->anon_dev = 0; @@ -1395,7 +1392,12 @@ alloc_fail: goto out; } -static int btrfs_init_fs_root(struct btrfs_root *root) +/* + * Initialize subvolume root in-memory structure + * + * @anon_dev: anonymous device to attach to the root, if zero, allocate new + */ +static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) { int ret; unsigned int nofs_flag; @@ -1428,9 +1430,20 @@ static int btrfs_init_fs_root(struct btrfs_root *root) spin_lock_init(&root->ino_cache_lock); init_waitqueue_head(&root->ino_cache_wait); - ret = get_anon_bdev(&root->anon_dev); - if (ret) - goto fail; + /* + * Don't assign anonymous block device to roots that are not exposed to + * userspace, the id pool is limited to 1M + */ + if (is_fstree(root->root_key.objectid) && + btrfs_root_refs(&root->root_item) > 0) { + if (!anon_dev) { + ret = get_anon_bdev(&root->anon_dev); + if (ret) + goto fail; + } else { + root->anon_dev = anon_dev; + } + } mutex_lock(&root->objectid_mutex); ret = btrfs_find_highest_objectid(root, @@ -1534,8 +1547,27 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) } -struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, bool check_ref) +/* + * Get an in-memory reference of a root structure. + * + * For essential trees like root/extent tree, we grab it from fs_info directly. + * For subvolume trees, we check the cached filesystem roots first. If not + * found, then read it from disk and add it to cached fs roots. + * + * Caller should release the root by calling btrfs_put_root() after the usage. + * + * NOTE: Reloc and log trees can't be read by this function as they share the + * same root objectid. + * + * @objectid: root id + * @anon_dev: preallocated anonymous block device number for new roots, + * pass 0 for new allocation. + * @check_ref: whether to check root item references, If true, return -ENOENT + * for orphan roots + */ +static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev, + bool check_ref) { struct btrfs_root *root; struct btrfs_path *path; @@ -1564,6 +1596,8 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { + /* Shouldn't get preallocated anon_dev for cached roots */ + ASSERT(!anon_dev); if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); @@ -1583,7 +1617,7 @@ again: goto fail; } - ret = btrfs_init_fs_root(root); + ret = btrfs_init_fs_root(root, anon_dev); if (ret) goto fail; @@ -1616,6 +1650,33 @@ fail: return ERR_PTR(ret); } +/* + * Get in-memory reference of a root structure + * + * @objectid: tree objectid + * @check_ref: if set, verify that the tree exists and the item has at least + * one reference + */ +struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, bool check_ref) +{ + return btrfs_get_root_ref(fs_info, objectid, 0, check_ref); +} + +/* + * Get in-memory reference of a root structure, created as new, optionally pass + * the anonymous block device id + * + * @objectid: tree objectid + * @anon_dev: if zero, allocate a new anonymous block device or use the + * parameter value + */ +struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev) +{ + return btrfs_get_root_ref(fs_info, objectid, anon_dev, true); +} + static int btrfs_congested_fn(void *congested_data, int bdi_bits) { struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data; @@ -1749,7 +1810,6 @@ static int transaction_kthread(void *arg) now = ktime_get_seconds(); if (cur->state < TRANS_STATE_COMMIT_START && - !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) && (now < cur->start_time || now - cur->start_time < fs_info->commit_interval)) { spin_unlock(&fs_info->trans_lock); @@ -2001,8 +2061,7 @@ void btrfs_put_root(struct btrfs_root *root) if (root->anon_dev) free_anon_bdev(root->anon_dev); btrfs_drew_lock_destroy(&root->snapshot_lock); - free_extent_buffer(root->node); - free_extent_buffer(root->commit_root); + free_root_extent_buffers(root); kfree(root->free_ino_ctl); kfree(root->free_ino_pinned); #ifdef CONFIG_BTRFS_DEBUG @@ -4058,6 +4117,11 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) ASSERT(list_empty(&fs_info->delayed_iputs)); set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags); + if (btrfs_check_quota_leak(fs_info)) { + WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); + btrfs_err(fs_info, "qgroup reserved space leaked"); + } + btrfs_free_qgroup_config(fs_info); ASSERT(list_empty(&fs_info->delalloc_roots)); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index bf43245406c4..00dc39d47ed3 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -67,6 +67,8 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref); +struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev); void btrfs_free_fs_info(struct btrfs_fs_info *fs_info); int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h index b6561455b3c4..f39d47a2d01a 100644 --- a/fs/btrfs/extent-io-tree.h +++ b/fs/btrfs/extent-io-tree.h @@ -233,14 +233,11 @@ bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start, struct extent_state **cached_state); /* This should be reworked in the future and put elsewhere. */ -int get_state_failrec(struct extent_io_tree *tree, u64 start, - struct io_failure_record **failrec); +struct io_failure_record *get_state_failrec(struct extent_io_tree *tree, u64 start); int set_state_failrec(struct extent_io_tree *tree, u64 start, struct io_failure_record *failrec); void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, u64 end); -int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, - struct io_failure_record **failrec_ret); int free_io_failure(struct extent_io_tree *failure_tree, struct extent_io_tree *io_tree, struct io_failure_record *rec); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index c0bc35f932bf..61ede335f6c3 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5298,7 +5298,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) goto out; } - trans = btrfs_start_transaction(tree_root, 0); + /* + * Use join to avoid potential EINTR from transaction start. See + * wait_reserve_ticket and the whole reservation callchain. + */ + if (for_reloc) + trans = btrfs_join_transaction(tree_root); + else + trans = btrfs_start_transaction(tree_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); goto out_free; @@ -5466,6 +5473,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) } } + /* + * This subvolume is going to be completely dropped, and won't be + * recorded as dirty roots, thus pertrans meta rsv will not be freed at + * commit transaction time. So free it here manually. + */ + btrfs_qgroup_convert_reserved_meta(root, INT_MAX); + btrfs_qgroup_free_meta_all_pertrans(root); + if (test_bit(BTRFS_ROOT_IN_RADIX, &root->state)) btrfs_add_dropped_root(trans, root); else diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 608f93438b29..617ea38e6fd7 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1999,7 +1999,8 @@ static int __process_pages_contig(struct address_space *mapping, if (!PageDirty(pages[i]) || pages[i]->mapping != mapping) { unlock_page(pages[i]); - put_page(pages[i]); + for (; i < ret; i++) + put_page(pages[i]); err = -EAGAIN; goto out; } @@ -2017,15 +2018,14 @@ out: return err; } -void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, +void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end, struct page *locked_page, unsigned clear_bits, unsigned long page_ops) { - clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, clear_bits, 1, 0, - NULL); + clear_extent_bit(&inode->io_tree, start, end, clear_bits, 1, 0, NULL); - __process_pages_contig(inode->i_mapping, locked_page, + __process_pages_contig(inode->vfs_inode.i_mapping, locked_page, start >> PAGE_SHIFT, end >> PAGE_SHIFT, page_ops, NULL); } @@ -2122,12 +2122,11 @@ out: return ret; } -int get_state_failrec(struct extent_io_tree *tree, u64 start, - struct io_failure_record **failrec) +struct io_failure_record *get_state_failrec(struct extent_io_tree *tree, u64 start) { struct rb_node *node; struct extent_state *state; - int ret = 0; + struct io_failure_record *failrec; spin_lock(&tree->lock); /* @@ -2136,18 +2135,19 @@ int get_state_failrec(struct extent_io_tree *tree, u64 start, */ node = tree_search(tree, start); if (!node) { - ret = -ENOENT; + failrec = ERR_PTR(-ENOENT); goto out; } state = rb_entry(node, struct extent_state, rb_node); if (state->start != start) { - ret = -ENOENT; + failrec = ERR_PTR(-ENOENT); goto out; } - *failrec = state->failrec; + + failrec = state->failrec; out: spin_unlock(&tree->lock); - return ret; + return failrec; } /* @@ -2377,8 +2377,8 @@ int clean_io_failure(struct btrfs_fs_info *fs_info, if (!ret) return 0; - ret = get_state_failrec(failure_tree, start, &failrec); - if (ret) + failrec = get_state_failrec(failure_tree, start); + if (IS_ERR(failrec)) return 0; BUG_ON(!failrec->this_mirror); @@ -2450,8 +2450,8 @@ void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, u64 end) spin_unlock(&failure_tree->lock); } -int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, - struct io_failure_record **failrec_ret) +static struct io_failure_record *btrfs_get_io_failure_record(struct inode *inode, + u64 start, u64 end) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct io_failure_record *failrec; @@ -2462,65 +2462,8 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, int ret; u64 logical; - ret = get_state_failrec(failure_tree, start, &failrec); - if (ret) { - failrec = kzalloc(sizeof(*failrec), GFP_NOFS); - if (!failrec) - return -ENOMEM; - - failrec->start = start; - failrec->len = end - start + 1; - failrec->this_mirror = 0; - failrec->bio_flags = 0; - failrec->in_validation = 0; - - read_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, start, failrec->len); - if (!em) { - read_unlock(&em_tree->lock); - kfree(failrec); - return -EIO; - } - - if (em->start > start || em->start + em->len <= start) { - free_extent_map(em); - em = NULL; - } - read_unlock(&em_tree->lock); - if (!em) { - kfree(failrec); - return -EIO; - } - - logical = start - em->start; - logical = em->block_start + logical; - if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) { - logical = em->block_start; - failrec->bio_flags = EXTENT_BIO_COMPRESSED; - extent_set_compress_type(&failrec->bio_flags, - em->compress_type); - } - - btrfs_debug(fs_info, - "Get IO Failure Record: (new) logical=%llu, start=%llu, len=%llu", - logical, start, failrec->len); - - failrec->logical = logical; - free_extent_map(em); - - /* set the bits in the private failure tree */ - ret = set_extent_bits(failure_tree, start, end, - EXTENT_LOCKED | EXTENT_DIRTY); - if (ret >= 0) - ret = set_state_failrec(failure_tree, start, failrec); - /* set the bits in the inode's tree */ - if (ret >= 0) - ret = set_extent_bits(tree, start, end, EXTENT_DAMAGED); - if (ret < 0) { - kfree(failrec); - return ret; - } - } else { + failrec = get_state_failrec(failure_tree, start); + if (!IS_ERR(failrec)) { btrfs_debug(fs_info, "Get IO Failure Record: (found) logical=%llu, start=%llu, len=%llu, validation=%d", failrec->logical, failrec->start, failrec->len, @@ -2530,11 +2473,66 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, * (e.g. with a list for failed_mirror) to make * clean_io_failure() clean all those errors at once. */ + + return failrec; } - *failrec_ret = failrec; + failrec = kzalloc(sizeof(*failrec), GFP_NOFS); + if (!failrec) + return ERR_PTR(-ENOMEM); - return 0; + failrec->start = start; + failrec->len = end - start + 1; + failrec->this_mirror = 0; + failrec->bio_flags = 0; + failrec->in_validation = 0; + + read_lock(&em_tree->lock); + em = lookup_extent_mapping(em_tree, start, failrec->len); + if (!em) { + read_unlock(&em_tree->lock); + kfree(failrec); + return ERR_PTR(-EIO); + } + + if (em->start > start || em->start + em->len <= start) { + free_extent_map(em); + em = NULL; + } + read_unlock(&em_tree->lock); + if (!em) { + kfree(failrec); + return ERR_PTR(-EIO); + } + + logical = start - em->start; + logical = em->block_start + logical; + if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) { + logical = em->block_start; + failrec->bio_flags = EXTENT_BIO_COMPRESSED; + extent_set_compress_type(&failrec->bio_flags, em->compress_type); + } + + btrfs_debug(fs_info, + "Get IO Failure Record: (new) logical=%llu, start=%llu, len=%llu", + logical, start, failrec->len); + + failrec->logical = logical; + free_extent_map(em); + + /* Set the bits in the private failure tree */ + ret = set_extent_bits(failure_tree, start, end, + EXTENT_LOCKED | EXTENT_DIRTY); + if (ret >= 0) { + ret = set_state_failrec(failure_tree, start, failrec); + /* Set the bits in the inode's tree */ + ret = set_extent_bits(tree, start, end, EXTENT_DAMAGED); + } else if (ret < 0) { + kfree(failrec); + return ERR_PTR(ret); + } + + return failrec; } static bool btrfs_check_repairable(struct inode *inode, bool needs_validation, @@ -2659,16 +2657,15 @@ blk_status_t btrfs_submit_read_repair(struct inode *inode, struct bio *repair_bio; struct btrfs_io_bio *repair_io_bio; blk_status_t status; - int ret; btrfs_debug(fs_info, "repair read error: read error at %llu", start); BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE); - ret = btrfs_get_io_failure_record(inode, start, end, &failrec); - if (ret) - return errno_to_blk_status(ret); + failrec = btrfs_get_io_failure_record(inode, start, end); + if (IS_ERR(failrec)) + return errno_to_blk_status(PTR_ERR(failrec)); need_validation = btrfs_io_needs_validation(inode, failed_bio); @@ -3419,7 +3416,7 @@ static void update_nr_written(struct writeback_control *wbc, * This returns 0 if all went well (page still locked) * This returns < 0 if there were errors (page still locked) */ -static noinline_for_stack int writepage_delalloc(struct inode *inode, +static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, struct page *page, struct writeback_control *wbc, u64 delalloc_start, unsigned long *nr_written) { @@ -3432,7 +3429,7 @@ static noinline_for_stack int writepage_delalloc(struct inode *inode, while (delalloc_end < page_end) { - found = find_lock_delalloc_range(inode, page, + found = find_lock_delalloc_range(&inode->vfs_inode, page, &delalloc_start, &delalloc_end); if (!found) { @@ -3449,8 +3446,7 @@ static noinline_for_stack int writepage_delalloc(struct inode *inode, * started, so we don't want to return > 0 unless * things are going well. */ - ret = ret < 0 ? ret : -EIO; - goto done; + return ret < 0 ? ret : -EIO; } /* * delalloc_end is already one less than the total length, so @@ -3482,10 +3478,7 @@ static noinline_for_stack int writepage_delalloc(struct inode *inode, return 1; } - ret = 0; - -done: - return ret; + return 0; } /* @@ -3496,7 +3489,7 @@ done: * 0 if all went well (page still locked) * < 0 if there were errors (page still locked) */ -static noinline_for_stack int __extent_writepage_io(struct inode *inode, +static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, struct page *page, struct writeback_control *wbc, struct extent_page_data *epd, @@ -3504,7 +3497,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, unsigned long nr_written, int *nr_ret) { - struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; + struct extent_io_tree *tree = &inode->io_tree; u64 start = page_offset(page); u64 page_end = start + PAGE_SIZE - 1; u64 end; @@ -3536,7 +3529,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, update_nr_written(wbc, nr_written + 1); end = page_end; - blocksize = inode->i_sb->s_blocksize; + blocksize = inode->vfs_inode.i_sb->s_blocksize; while (cur <= end) { u64 em_end; @@ -3547,8 +3540,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, page_end, 1); break; } - em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur, - end - cur + 1); + em = btrfs_get_extent(inode, NULL, 0, cur, end - cur + 1); if (IS_ERR_OR_NULL(em)) { SetPageError(page); ret = PTR_ERR_OR_ZERO(em); @@ -3585,7 +3577,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, btrfs_set_range_writeback(tree, cur, cur + iosize - 1); if (!PageWriteback(page)) { - btrfs_err(BTRFS_I(inode)->root->fs_info, + btrfs_err(inode->root->fs_info, "page %lu not writeback, cur %llu end %llu", page->index, cur, end); } @@ -3658,15 +3650,16 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, set_page_extent_mapped(page); if (!epd->extent_locked) { - ret = writepage_delalloc(inode, page, wbc, start, &nr_written); + ret = writepage_delalloc(BTRFS_I(inode), page, wbc, start, + &nr_written); if (ret == 1) return 0; if (ret) goto done; } - ret = __extent_writepage_io(inode, page, wbc, epd, - i_size, nr_written, &nr); + ret = __extent_writepage_io(BTRFS_I(inode), page, wbc, epd, i_size, + nr_written, &nr); if (ret == 1) return 0; @@ -4126,7 +4119,7 @@ retry: if (!test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { ret = flush_write_bio(&epd); } else { - ret = -EUCLEAN; + ret = -EROFS; end_write_bio(&epd, ret); } return ret; @@ -4488,6 +4481,9 @@ int try_release_extent_mapping(struct page *page, gfp_t mask) page->mapping->host->i_size > SZ_16M) { u64 len; while (start <= end) { + struct btrfs_fs_info *fs_info; + u64 cur_gen; + len = end - start + 1; write_lock(&map->lock); em = lookup_extent_mapping(map, start, len); @@ -4501,15 +4497,45 @@ int try_release_extent_mapping(struct page *page, gfp_t mask) free_extent_map(em); break; } - if (!test_range_bit(tree, em->start, - extent_map_end(em) - 1, - EXTENT_LOCKED, 0, NULL)) { - set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &btrfs_inode->runtime_flags); - remove_extent_mapping(map, em); - /* once for the rb tree */ - free_extent_map(em); - } + if (test_range_bit(tree, em->start, + extent_map_end(em) - 1, + EXTENT_LOCKED, 0, NULL)) + goto next; + /* + * If it's not in the list of modified extents, used + * by a fast fsync, we can remove it. If it's being + * logged we can safely remove it since fsync took an + * extra reference on the em. + */ + if (list_empty(&em->list) || + test_bit(EXTENT_FLAG_LOGGING, &em->flags)) + goto remove_em; + /* + * If it's in the list of modified extents, remove it + * only if its generation is older then the current one, + * in which case we don't need it for a fast fsync. + * Otherwise don't remove it, we could be racing with an + * ongoing fast fsync that could miss the new extent. + */ + fs_info = btrfs_inode->root->fs_info; + spin_lock(&fs_info->trans_lock); + cur_gen = fs_info->generation; + spin_unlock(&fs_info->trans_lock); + if (em->generation >= cur_gen) + goto next; +remove_em: + /* + * We only remove extent maps that are not in the list of + * modified extents or that are in the list but with a + * generation lower then the current generation, so there + * is no need to set the full fsync flag on the inode (it + * hurts the fsync performance for workloads with a data + * size that exceeds or is close to the system's memory). + */ + remove_extent_mapping(map, em); + /* once for the rb tree */ + free_extent_map(em); +next: start = extent_map_end(em); write_unlock(&map->lock); @@ -4669,7 +4695,7 @@ static int emit_last_fiemap_cache(struct fiemap_extent_info *fieinfo, } int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, - __u64 start, __u64 len) + u64 start, u64 len) { int ret = 0; u64 off = start; diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 87f60a48f750..00a88f2eb5ab 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -204,7 +204,7 @@ int btree_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc); void extent_readahead(struct readahead_control *rac); int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, - __u64 start, __u64 len); + u64 start, u64 len); void set_page_extent_mapped(struct page *page); struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, @@ -277,7 +277,7 @@ void clear_extent_buffer_uptodate(struct extent_buffer *eb); int extent_buffer_under_io(const struct extent_buffer *eb); void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end); void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end); -void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, +void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end, struct page *locked_page, unsigned bits_to_clear, unsigned long page_ops); diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 706a3128e192..7d5ec71615b8 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -522,10 +522,10 @@ fail: * means this bio can contains potentially discontigous bio vecs * so the logical offset of each should be calculated separately. */ -blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, +blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio, u64 file_start, int contig) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode->root->fs_info; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); struct btrfs_ordered_sum *sums; struct btrfs_ordered_extent *ordered = NULL; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index b0d2c976587e..841c516079a9 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -500,18 +500,18 @@ next: * this also makes the decision about creating an inline extent vs * doing real data extents, marking pages dirty and delalloc as required. */ -int btrfs_dirty_pages(struct inode *inode, struct page **pages, +int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, struct extent_state **cached) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode->root->fs_info; int err = 0; int i; u64 num_bytes; u64 start_pos; u64 end_of_last_block; u64 end_pos = pos + write_bytes; - loff_t isize = i_size_read(inode); + loff_t isize = i_size_read(&inode->vfs_inode); unsigned int extra_bits = 0; start_pos = pos & ~((u64) fs_info->sectorsize - 1); @@ -524,13 +524,13 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, * The pages may have already been dirty, clear out old accounting so * we can set things up properly */ - clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos, end_of_last_block, + clear_extent_bit(&inode->io_tree, start_pos, end_of_last_block, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, cached); - if (!btrfs_is_free_space_inode(BTRFS_I(inode))) { + if (!btrfs_is_free_space_inode(inode)) { if (start_pos >= isize && - !(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC)) { + !(inode->flags & BTRFS_INODE_PREALLOC)) { /* * There can't be any extents following eof in this case * so just set the delalloc new bit for the range @@ -538,8 +538,7 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, */ extra_bits |= EXTENT_DELALLOC_NEW; } else { - err = btrfs_find_new_delalloc_bytes(BTRFS_I(inode), - start_pos, + err = btrfs_find_new_delalloc_bytes(inode, start_pos, num_bytes, cached); if (err) return err; @@ -564,7 +563,7 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, * at this time. */ if (end_pos > isize) - i_size_write(inode, end_pos); + i_size_write(&inode->vfs_inode, end_pos); return 0; } @@ -731,7 +730,7 @@ next: * is deleted from the tree. */ int __btrfs_drop_extents(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode, + struct btrfs_root *root, struct btrfs_inode *inode, struct btrfs_path *path, u64 start, u64 end, u64 *drop_end, int drop_cache, int replace_extent, @@ -744,7 +743,8 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans, struct btrfs_ref ref = { 0 }; struct btrfs_key key; struct btrfs_key new_key; - u64 ino = btrfs_ino(BTRFS_I(inode)); + struct inode *vfs_inode = &inode->vfs_inode; + u64 ino = btrfs_ino(inode); u64 search_start = start; u64 disk_bytenr = 0; u64 num_bytes = 0; @@ -762,9 +762,9 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans, int leafs_visited = 0; if (drop_cache) - btrfs_drop_extent_cache(BTRFS_I(inode), start, end - 1, 0); + btrfs_drop_extent_cache(inode, start, end - 1, 0); - if (start >= BTRFS_I(inode)->disk_i_size && !replace_extent) + if (start >= inode->disk_i_size && !replace_extent) modify_tree = 0; update_refs = (test_bit(BTRFS_ROOT_SHAREABLE, &root->state) || @@ -935,7 +935,7 @@ next_slot: extent_end - end); btrfs_mark_buffer_dirty(leaf); if (update_refs && disk_bytenr > 0) - inode_sub_bytes(inode, end - key.offset); + inode_sub_bytes(vfs_inode, end - key.offset); break; } @@ -955,7 +955,7 @@ next_slot: start - key.offset); btrfs_mark_buffer_dirty(leaf); if (update_refs && disk_bytenr > 0) - inode_sub_bytes(inode, extent_end - start); + inode_sub_bytes(vfs_inode, extent_end - start); if (end == extent_end) break; @@ -979,7 +979,7 @@ delete_extent_item: if (update_refs && extent_type == BTRFS_FILE_EXTENT_INLINE) { - inode_sub_bytes(inode, + inode_sub_bytes(vfs_inode, extent_end - key.offset); extent_end = ALIGN(extent_end, fs_info->sectorsize); @@ -993,7 +993,7 @@ delete_extent_item: key.offset - extent_offset); ret = btrfs_free_extent(trans, &ref); BUG_ON(ret); /* -ENOMEM */ - inode_sub_bytes(inode, + inode_sub_bytes(vfs_inode, extent_end - key.offset); } @@ -1082,8 +1082,8 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) return -ENOMEM; - ret = __btrfs_drop_extents(trans, root, inode, path, start, end, NULL, - drop_cache, 0, 0, NULL); + ret = __btrfs_drop_extents(trans, root, BTRFS_I(inode), path, start, + end, NULL, drop_cache, 0, 0, NULL); btrfs_free_path(path); return ret; } @@ -1532,8 +1532,8 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, return ret; } -static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, - size_t *write_bytes, bool nowait) +static int check_can_nocow(struct btrfs_inode *inode, loff_t pos, + size_t *write_bytes, bool nowait) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_root *root = inode->root; @@ -1541,6 +1541,9 @@ static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, u64 num_bytes; int ret; + if (!(inode->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC))) + return 0; + if (!nowait && !btrfs_drew_try_write_lock(&root->snapshot_lock)) return -EAGAIN; @@ -1583,6 +1586,42 @@ out_unlock: return ret; } +static int check_nocow_nolock(struct btrfs_inode *inode, loff_t pos, + size_t *write_bytes) +{ + return check_can_nocow(inode, pos, write_bytes, true); +} + +/* + * Check if we can do nocow write into the range [@pos, @pos + @write_bytes) + * + * @pos: File offset + * @write_bytes: The length to write, will be updated to the nocow writeable + * range + * + * This function will flush ordered extents in the range to ensure proper + * nocow checks. + * + * Return: + * >0 and update @write_bytes if we can do nocow write + * 0 if we can't do nocow write + * -EAGAIN if we can't get the needed lock or there are ordered extents + * for * (nowait == true) case + * <0 if other error happened + * + * NOTE: Callers need to release the lock by btrfs_check_nocow_unlock(). + */ +int btrfs_check_nocow_lock(struct btrfs_inode *inode, loff_t pos, + size_t *write_bytes) +{ + return check_can_nocow(inode, pos, write_bytes, false); +} + +void btrfs_check_nocow_unlock(struct btrfs_inode *inode) +{ + btrfs_drew_write_unlock(&inode->root->snapshot_lock); +} + static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, struct iov_iter *i) { @@ -1590,7 +1629,6 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, loff_t pos = iocb->ki_pos; struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; struct page **pages = NULL; struct extent_changeset *data_reserved = NULL; u64 release_bytes = 0; @@ -1643,13 +1681,12 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, fs_info->sectorsize); extent_changeset_release(data_reserved); - ret = btrfs_check_data_free_space(inode, &data_reserved, pos, + ret = btrfs_check_data_free_space(BTRFS_I(inode), + &data_reserved, pos, write_bytes); if (ret < 0) { - if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | - BTRFS_INODE_PREALLOC)) && - check_can_nocow(BTRFS_I(inode), pos, - &write_bytes, false) > 0) { + if (btrfs_check_nocow_lock(BTRFS_I(inode), pos, + &write_bytes) > 0) { /* * For nodata cow case, no need to reserve * data space. @@ -1674,11 +1711,11 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, reserve_bytes); if (ret) { if (!only_release_metadata) - btrfs_free_reserved_data_space(inode, + btrfs_free_reserved_data_space(BTRFS_I(inode), data_reserved, pos, write_bytes); else - btrfs_drew_write_unlock(&root->snapshot_lock); + btrfs_check_nocow_unlock(BTRFS_I(inode)); break; } @@ -1748,7 +1785,7 @@ again: __pos = round_down(pos, fs_info->sectorsize) + (dirty_pages << PAGE_SHIFT); - btrfs_delalloc_release_space(inode, + btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, __pos, release_bytes, true); } @@ -1758,8 +1795,9 @@ again: fs_info->sectorsize); if (copied > 0) - ret = btrfs_dirty_pages(inode, pages, dirty_pages, - pos, copied, &cached_state); + ret = btrfs_dirty_pages(BTRFS_I(inode), pages, + dirty_pages, pos, copied, + &cached_state); /* * If we have not locked the extent range, because the range's @@ -1782,7 +1820,7 @@ again: release_bytes = 0; if (only_release_metadata) - btrfs_drew_write_unlock(&root->snapshot_lock); + btrfs_check_nocow_unlock(BTRFS_I(inode)); if (only_release_metadata && copied > 0) { lockstart = round_down(pos, @@ -1800,8 +1838,6 @@ again: cond_resched(); balance_dirty_pages_ratelimited(inode->i_mapping); - if (dirty_pages < (fs_info->nodesize >> PAGE_SHIFT) + 1) - btrfs_btree_balance_dirty(fs_info); pos += copied; num_written += copied; @@ -1811,11 +1847,12 @@ again: if (release_bytes) { if (only_release_metadata) { - btrfs_drew_write_unlock(&root->snapshot_lock); + btrfs_check_nocow_unlock(BTRFS_I(inode)); btrfs_delalloc_release_metadata(BTRFS_I(inode), release_bytes, true); } else { - btrfs_delalloc_release_space(inode, data_reserved, + btrfs_delalloc_release_space(BTRFS_I(inode), + data_reserved, round_down(pos, fs_info->sectorsize), release_bytes, true); } @@ -1926,10 +1963,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, * We will allocate space in case nodatacow is not set, * so bail */ - if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | - BTRFS_INODE_PREALLOC)) || - check_can_nocow(BTRFS_I(inode), pos, &nocow_bytes, - true) <= 0) { + if (check_nocow_nolock(BTRFS_I(inode), pos, &nocow_bytes) + <= 0) { inode_unlock(inode); return -EAGAIN; } @@ -2598,7 +2633,7 @@ int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path, cur_offset = start; while (cur_offset < end) { - ret = __btrfs_drop_extents(trans, root, inode, path, + ret = __btrfs_drop_extents(trans, root, BTRFS_I(inode), path, cur_offset, end + 1, &drop_end, 1, 0, 0, NULL); if (ret != -ENOSPC) { @@ -3176,14 +3211,14 @@ reserve_space: if (ret < 0) goto out; space_reserved = true; - ret = btrfs_qgroup_reserve_data(inode, &data_reserved, - alloc_start, bytes_to_reserve); - if (ret) - goto out; ret = btrfs_punch_hole_lock_range(inode, lockstart, lockend, &cached_state); if (ret) goto out; + ret = btrfs_qgroup_reserve_data(BTRFS_I(inode), &data_reserved, + alloc_start, bytes_to_reserve); + if (ret) + goto out; ret = btrfs_prealloc_file_range(inode, mode, alloc_start, alloc_end - alloc_start, i_blocksize(inode), @@ -3199,7 +3234,7 @@ reserve_space: ret = btrfs_fallocate_update_isize(inode, offset + len, mode); out: if (ret && space_reserved) - btrfs_free_reserved_data_space(inode, data_reserved, + btrfs_free_reserved_data_space(BTRFS_I(inode), data_reserved, alloc_start, bytes_to_reserve); extent_changeset_free(data_reserved); @@ -3350,8 +3385,9 @@ static long btrfs_fallocate(struct file *file, int mode, free_extent_map(em); break; } - ret = btrfs_qgroup_reserve_data(inode, &data_reserved, - cur_offset, last_byte - cur_offset); + ret = btrfs_qgroup_reserve_data(BTRFS_I(inode), + &data_reserved, cur_offset, + last_byte - cur_offset); if (ret < 0) { cur_offset = last_byte; free_extent_map(em); @@ -3363,8 +3399,9 @@ static long btrfs_fallocate(struct file *file, int mode, * range, free reserved data space first, otherwise * it'll result in false ENOSPC error. */ - btrfs_free_reserved_data_space(inode, data_reserved, - cur_offset, last_byte - cur_offset); + btrfs_free_reserved_data_space(BTRFS_I(inode), + data_reserved, cur_offset, + last_byte - cur_offset); } free_extent_map(em); cur_offset = last_byte; @@ -3381,7 +3418,7 @@ static long btrfs_fallocate(struct file *file, int mode, range->len, i_blocksize(inode), offset + len, &alloc_hint); else - btrfs_free_reserved_data_space(inode, + btrfs_free_reserved_data_space(BTRFS_I(inode), data_reserved, range->start, range->len); list_del(&range->list); @@ -3402,7 +3439,7 @@ out: inode_unlock(inode); /* Let go of our reservation. */ if (ret != 0 && !(mode & FALLOC_FL_ZERO_RANGE)) - btrfs_free_reserved_data_space(inode, data_reserved, + btrfs_free_reserved_data_space(BTRFS_I(inode), data_reserved, cur_offset, alloc_end - cur_offset); extent_changeset_free(data_reserved); return ret; diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 55955bd424d7..6d961e11639e 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1334,8 +1334,9 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, io_ctl_zero_remaining_pages(io_ctl); /* Everything is written out, now we dirty the pages in the file. */ - ret = btrfs_dirty_pages(inode, io_ctl->pages, io_ctl->num_pages, 0, - i_size_read(inode), &cached_state); + ret = btrfs_dirty_pages(BTRFS_I(inode), io_ctl->pages, + io_ctl->num_pages, 0, i_size_read(inode), + &cached_state); if (ret) goto out_nospc; @@ -2703,8 +2704,7 @@ void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group) * pointed to by the cluster, someone else raced in and freed the * cluster already. In that case, we just return without changing anything */ -static int -__btrfs_return_cluster_to_free_space( +static void __btrfs_return_cluster_to_free_space( struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster) { @@ -2756,7 +2756,6 @@ __btrfs_return_cluster_to_free_space( out: spin_unlock(&cluster->lock); btrfs_put_block_group(block_group); - return 0; } static void __btrfs_remove_free_space_cache_locked( @@ -2907,12 +2906,11 @@ out: * Otherwise, it'll get a reference on the block group pointed to by the * cluster and remove the cluster from it. */ -int btrfs_return_cluster_to_free_space( +void btrfs_return_cluster_to_free_space( struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster) { struct btrfs_free_space_ctl *ctl; - int ret; /* first, get a safe pointer to the block group */ spin_lock(&cluster->lock); @@ -2920,28 +2918,27 @@ int btrfs_return_cluster_to_free_space( block_group = cluster->block_group; if (!block_group) { spin_unlock(&cluster->lock); - return 0; + return; } } else if (cluster->block_group != block_group) { /* someone else has already freed it don't redo their work */ spin_unlock(&cluster->lock); - return 0; + return; } - atomic_inc(&block_group->count); + btrfs_get_block_group(block_group); spin_unlock(&cluster->lock); ctl = block_group->free_space_ctl; /* now return any extents the cluster had on it */ spin_lock(&ctl->tree_lock); - ret = __btrfs_return_cluster_to_free_space(block_group, cluster); + __btrfs_return_cluster_to_free_space(block_group, cluster); spin_unlock(&ctl->tree_lock); btrfs_discard_queue_work(&block_group->fs_info->discard_ctl, block_group); /* finally drop our ref */ btrfs_put_block_group(block_group); - return ret; } static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group *block_group, @@ -3358,7 +3355,7 @@ int btrfs_find_space_cluster(struct btrfs_block_group *block_group, list_del_init(&entry->list); if (!ret) { - atomic_inc(&block_group->count); + btrfs_get_block_group(block_group); list_add_tail(&cluster->block_group_list, &block_group->cluster_list); cluster->block_group = block_group; diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index 2e0a8077aa74..e3d5e0ad8f8e 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -136,7 +136,7 @@ void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster); u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, u64 bytes, u64 min_start, u64 *max_extent_size); -int btrfs_return_cluster_to_free_space( +void btrfs_return_cluster_to_free_space( struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster); int btrfs_trim_block_group(struct btrfs_block_group *block_group, diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 6009e0e939b5..76d2e43817ea 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -495,7 +495,8 @@ again: /* Just to make sure we have enough space */ prealloc += 8 * PAGE_SIZE; - ret = btrfs_delalloc_reserve_space(inode, &data_reserved, 0, prealloc); + ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved, 0, + prealloc); if (ret) goto out_put; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 43c803c16b48..611b3412fbfd 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -80,17 +80,17 @@ struct kmem_cache *btrfs_free_space_bitmap_cachep; static int btrfs_setsize(struct inode *inode, struct iattr *attr); static int btrfs_truncate(struct inode *inode, bool skip_writeback); static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent); -static noinline int cow_file_range(struct inode *inode, +static noinline int cow_file_range(struct btrfs_inode *inode, struct page *locked_page, u64 start, u64 end, int *page_started, unsigned long *nr_written, int unlock); -static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len, - u64 orig_start, u64 block_start, +static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start, + u64 len, u64 orig_start, u64 block_start, u64 block_len, u64 orig_block_len, u64 ram_bytes, int compress_type, int type); -static void __endio_write_update_ordered(struct inode *inode, +static void __endio_write_update_ordered(struct btrfs_inode *inode, const u64 offset, const u64 bytes, const bool uptodate); @@ -104,7 +104,7 @@ static void __endio_write_update_ordered(struct inode *inode, * to be released, which we want to happen only when finishing the ordered * extent (btrfs_finish_ordered_io()). */ -static inline void btrfs_cleanup_ordered_extents(struct inode *inode, +static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, struct page *locked_page, u64 offset, u64 bytes) { @@ -116,7 +116,7 @@ static inline void btrfs_cleanup_ordered_extents(struct inode *inode, struct page *page; while (index <= end_index) { - page = find_get_page(inode->i_mapping, index); + page = find_get_page(inode->vfs_inode.i_mapping, index); index++; if (!page) continue; @@ -274,15 +274,15 @@ fail: * does the checks required to make sure the data is small enough * to fit as an inline extent. */ -static noinline int cow_file_range_inline(struct inode *inode, u64 start, +static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 start, u64 end, size_t compressed_size, int compress_type, struct page **compressed_pages) { - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_trans_handle *trans; - u64 isize = i_size_read(inode); + u64 isize = i_size_read(&inode->vfs_inode); u64 actual_end = min(end + 1, isize); u64 inline_len = actual_end - start; u64 aligned_end = ALIGN(end, fs_info->sectorsize); @@ -314,7 +314,7 @@ static noinline int cow_file_range_inline(struct inode *inode, u64 start, btrfs_free_path(path); return PTR_ERR(trans); } - trans->block_rsv = &BTRFS_I(inode)->block_rsv; + trans->block_rsv = &inode->block_rsv; if (compressed_size && compressed_pages) extent_item_size = btrfs_file_extent_calc_inline_size( @@ -323,9 +323,9 @@ static noinline int cow_file_range_inline(struct inode *inode, u64 start, extent_item_size = btrfs_file_extent_calc_inline_size( inline_len); - ret = __btrfs_drop_extents(trans, root, inode, path, - start, aligned_end, NULL, - 1, 1, extent_item_size, &extent_inserted); + ret = __btrfs_drop_extents(trans, root, inode, path, start, aligned_end, + NULL, 1, 1, extent_item_size, + &extent_inserted); if (ret) { btrfs_abort_transaction(trans, ret); goto out; @@ -334,7 +334,7 @@ static noinline int cow_file_range_inline(struct inode *inode, u64 start, if (isize > actual_end) inline_len = min_t(u64, isize, actual_end); ret = insert_inline_extent(trans, path, extent_inserted, - root, inode, start, + root, &inode->vfs_inode, start, inline_len, compressed_size, compress_type, compressed_pages); if (ret && ret != -ENOSPC) { @@ -345,8 +345,8 @@ static noinline int cow_file_range_inline(struct inode *inode, u64 start, goto out; } - set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags); - btrfs_drop_extent_cache(BTRFS_I(inode), start, aligned_end - 1, 0); + set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags); + btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0); out: /* * Don't forget to free the reserved space, as for inlined extent @@ -412,10 +412,10 @@ static noinline int add_async_extent(struct async_chunk *cow, /* * Check if the inode has flags compatible with compression */ -static inline bool inode_can_compress(struct inode *inode) +static inline bool inode_can_compress(struct btrfs_inode *inode) { - if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW || - BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) + if (inode->flags & BTRFS_INODE_NODATACOW || + inode->flags & BTRFS_INODE_NODATASUM) return false; return true; } @@ -424,29 +424,30 @@ static inline bool inode_can_compress(struct inode *inode) * Check if the inode needs to be submitted to compression, based on mount * options, defragmentation, properties or heuristics. */ -static inline int inode_need_compress(struct inode *inode, u64 start, u64 end) +static inline int inode_need_compress(struct btrfs_inode *inode, u64 start, + u64 end) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode->root->fs_info; if (!inode_can_compress(inode)) { WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), KERN_ERR "BTRFS: unexpected compression for ino %llu\n", - btrfs_ino(BTRFS_I(inode))); + btrfs_ino(inode)); return 0; } /* force compress */ if (btrfs_test_opt(fs_info, FORCE_COMPRESS)) return 1; /* defrag ioctl */ - if (BTRFS_I(inode)->defrag_compress) + if (inode->defrag_compress) return 1; /* bad compression ratios */ - if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS) + if (inode->flags & BTRFS_INODE_NOCOMPRESS) return 0; if (btrfs_test_opt(fs_info, COMPRESS) || - BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS || - BTRFS_I(inode)->prop_compress) - return btrfs_compress_heuristic(inode, start, end); + inode->flags & BTRFS_INODE_COMPRESS || + inode->prop_compress) + return btrfs_compress_heuristic(&inode->vfs_inode, start, end); return 0; } @@ -552,7 +553,7 @@ again: * inode has not been flagged as nocompress. This flag can * change at any time if we discover bad compression ratios. */ - if (inode_need_compress(inode, start, end)) { + if (inode_need_compress(BTRFS_I(inode), start, end)) { WARN_ON(pages); pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS); if (!pages) { @@ -616,11 +617,12 @@ cont: /* we didn't compress the entire range, try * to make an uncompressed inline extent. */ - ret = cow_file_range_inline(inode, start, end, 0, - BTRFS_COMPRESS_NONE, NULL); + ret = cow_file_range_inline(BTRFS_I(inode), start, end, + 0, BTRFS_COMPRESS_NONE, + NULL); } else { /* try making a compressed inline extent */ - ret = cow_file_range_inline(inode, start, end, + ret = cow_file_range_inline(BTRFS_I(inode), start, end, total_compressed, compress_type, pages); } @@ -642,7 +644,8 @@ cont: * our outstanding extent for clearing delalloc for this * range. */ - extent_clear_unlock_delalloc(inode, start, end, NULL, + extent_clear_unlock_delalloc(BTRFS_I(inode), start, end, + NULL, clear_flags, PAGE_UNLOCK | PAGE_CLEAR_DIRTY | @@ -762,14 +765,14 @@ static void free_async_extent_pages(struct async_extent *async_extent) */ static noinline void submit_compressed_extents(struct async_chunk *async_chunk) { - struct inode *inode = async_chunk->inode; - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_inode *inode = BTRFS_I(async_chunk->inode); + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct async_extent *async_extent; u64 alloc_hint = 0; struct btrfs_key ins; struct extent_map *em; - struct btrfs_root *root = BTRFS_I(inode)->root; - struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + struct btrfs_root *root = inode->root; + struct extent_io_tree *io_tree = &inode->io_tree; int ret = 0; again: @@ -802,7 +805,7 @@ retry: * all those pages down to the drive. */ if (!page_started && !ret) - extent_write_locked_range(inode, + extent_write_locked_range(&inode->vfs_inode, async_extent->start, async_extent->start + async_extent->ram_size - 1, @@ -832,7 +835,7 @@ retry: * will not submit these pages down to lower * layers. */ - extent_range_redirty_for_io(inode, + extent_range_redirty_for_io(&inode->vfs_inode, async_extent->start, async_extent->start + async_extent->ram_size - 1); @@ -867,8 +870,7 @@ retry: BTRFS_ORDERED_COMPRESSED, async_extent->compress_type); if (ret) { - btrfs_drop_extent_cache(BTRFS_I(inode), - async_extent->start, + btrfs_drop_extent_cache(inode, async_extent->start, async_extent->start + async_extent->ram_size - 1, 0); goto out_free_reserve; @@ -884,8 +886,7 @@ retry: NULL, EXTENT_LOCKED | EXTENT_DELALLOC, PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK); - if (btrfs_submit_compressed_write(inode, - async_extent->start, + if (btrfs_submit_compressed_write(inode, async_extent->start, async_extent->ram_size, ins.objectid, ins.offset, async_extent->pages, @@ -896,12 +897,11 @@ retry: const u64 start = async_extent->start; const u64 end = start + async_extent->ram_size - 1; - p->mapping = inode->i_mapping; + p->mapping = inode->vfs_inode.i_mapping; btrfs_writepage_endio_finish_ordered(p, start, end, 0); p->mapping = NULL; - extent_clear_unlock_delalloc(inode, start, end, - NULL, 0, + extent_clear_unlock_delalloc(inode, start, end, NULL, 0, PAGE_END_WRITEBACK | PAGE_SET_ERROR); free_async_extent_pages(async_extent); @@ -929,10 +929,10 @@ out_free: goto again; } -static u64 get_extent_allocation_hint(struct inode *inode, u64 start, +static u64 get_extent_allocation_hint(struct btrfs_inode *inode, u64 start, u64 num_bytes) { - struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; + struct extent_map_tree *em_tree = &inode->extent_tree; struct extent_map *em; u64 alloc_hint = 0; @@ -974,13 +974,13 @@ static u64 get_extent_allocation_hint(struct inode *inode, u64 start, * required to start IO on it. It may be clean and already done with * IO when we return. */ -static noinline int cow_file_range(struct inode *inode, +static noinline int cow_file_range(struct btrfs_inode *inode, struct page *locked_page, u64 start, u64 end, int *page_started, unsigned long *nr_written, int unlock) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_root *root = inode->root; + struct btrfs_fs_info *fs_info = root->fs_info; u64 alloc_hint = 0; u64 num_bytes; unsigned long ram_size; @@ -994,7 +994,7 @@ static noinline int cow_file_range(struct inode *inode, bool extent_reserved = false; int ret = 0; - if (btrfs_is_free_space_inode(BTRFS_I(inode))) { + if (btrfs_is_free_space_inode(inode)) { WARN_ON_ONCE(1); ret = -EINVAL; goto out_unlock; @@ -1004,7 +1004,7 @@ static noinline int cow_file_range(struct inode *inode, num_bytes = max(blocksize, num_bytes); ASSERT(num_bytes <= btrfs_super_total_bytes(fs_info->super_copy)); - inode_should_defrag(BTRFS_I(inode), start, end, num_bytes, SZ_64K); + inode_should_defrag(inode, start, end, num_bytes, SZ_64K); if (start == 0) { /* lets try to make an inline extent */ @@ -1033,8 +1033,7 @@ static noinline int cow_file_range(struct inode *inode, } alloc_hint = get_extent_allocation_hint(inode, start, num_bytes); - btrfs_drop_extent_cache(BTRFS_I(inode), start, - start + num_bytes - 1, 0); + btrfs_drop_extent_cache(inode, start, start + num_bytes - 1, 0); /* * Relocation relies on the relocated extents to have exactly the same @@ -1098,7 +1097,7 @@ static noinline int cow_file_range(struct inode *inode, * skip current ordered extent. */ if (ret) - btrfs_drop_extent_cache(BTRFS_I(inode), start, + btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0); } @@ -1114,8 +1113,7 @@ static noinline int cow_file_range(struct inode *inode, page_ops = unlock ? PAGE_UNLOCK : 0; page_ops |= PAGE_SET_PRIVATE2; - extent_clear_unlock_delalloc(inode, start, - start + ram_size - 1, + extent_clear_unlock_delalloc(inode, start, start + ram_size - 1, locked_page, EXTENT_LOCKED | EXTENT_DELALLOC, page_ops); @@ -1139,7 +1137,7 @@ out: return ret; out_drop_extent_cache: - btrfs_drop_extent_cache(BTRFS_I(inode), start, start + ram_size - 1, 0); + btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0); out_reserve: btrfs_dec_block_group_reservations(fs_info, ins.objectid); btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1); @@ -1236,13 +1234,13 @@ static noinline void async_cow_free(struct btrfs_work *work) kvfree(async_chunk->pending); } -static int cow_file_range_async(struct inode *inode, +static int cow_file_range_async(struct btrfs_inode *inode, struct writeback_control *wbc, struct page *locked_page, u64 start, u64 end, int *page_started, unsigned long *nr_written) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct cgroup_subsys_state *blkcg_css = wbc_blkcg_css(wbc); struct async_cow *ctx; struct async_chunk *async_chunk; @@ -1254,9 +1252,9 @@ static int cow_file_range_async(struct inode *inode, unsigned nofs_flag; const unsigned int write_flags = wbc_to_write_flags(wbc); - unlock_extent(&BTRFS_I(inode)->io_tree, start, end); + unlock_extent(&inode->io_tree, start, end); - if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS && + if (inode->flags & BTRFS_INODE_NOCOMPRESS && !btrfs_test_opt(fs_info, FORCE_COMPRESS)) { num_chunks = 1; should_compress = false; @@ -1294,9 +1292,9 @@ static int cow_file_range_async(struct inode *inode, * igrab is called higher up in the call chain, take only the * lightweight reference for the callback lifetime */ - ihold(inode); + ihold(&inode->vfs_inode); async_chunk[i].pending = &ctx->num_chunks; - async_chunk[i].inode = inode; + async_chunk[i].inode = &inode->vfs_inode; async_chunk[i].start = start; async_chunk[i].end = cur_end; async_chunk[i].write_flags = write_flags; @@ -1373,15 +1371,15 @@ static noinline int csum_exist_in_range(struct btrfs_fs_info *fs_info, return 1; } -static int fallback_to_cow(struct inode *inode, struct page *locked_page, +static int fallback_to_cow(struct btrfs_inode *inode, struct page *locked_page, const u64 start, const u64 end, int *page_started, unsigned long *nr_written) { - const bool is_space_ino = btrfs_is_free_space_inode(BTRFS_I(inode)); - const bool is_reloc_ino = (BTRFS_I(inode)->root->root_key.objectid == + const bool is_space_ino = btrfs_is_free_space_inode(inode); + const bool is_reloc_ino = (inode->root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID); const u64 range_bytes = end + 1 - start; - struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + struct extent_io_tree *io_tree = &inode->io_tree; u64 range_start = start; u64 count; @@ -1421,7 +1419,7 @@ static int fallback_to_cow(struct inode *inode, struct page *locked_page, EXTENT_NORESERVE, 0); if (count > 0 || is_space_ino || is_reloc_ino) { u64 bytes = count; - struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_space_info *sinfo = fs_info->data_sinfo; if (is_space_ino || is_reloc_ino) @@ -1447,21 +1445,21 @@ static int fallback_to_cow(struct inode *inode, struct page *locked_page, * If no cow copies or snapshots exist, we write directly to the existing * blocks on disk */ -static noinline int run_delalloc_nocow(struct inode *inode, +static noinline int run_delalloc_nocow(struct btrfs_inode *inode, struct page *locked_page, const u64 start, const u64 end, int *page_started, int force, unsigned long *nr_written) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct btrfs_root *root = inode->root; struct btrfs_path *path; u64 cow_start = (u64)-1; u64 cur_offset = start; int ret; bool check_prev = true; - const bool freespace_inode = btrfs_is_free_space_inode(BTRFS_I(inode)); - u64 ino = btrfs_ino(BTRFS_I(inode)); + const bool freespace_inode = btrfs_is_free_space_inode(inode); + u64 ino = btrfs_ino(inode); bool nocow = false; u64 disk_bytenr = 0; @@ -1687,8 +1685,8 @@ out_check: * NOCOW, following one which needs to be COW'ed */ if (cow_start != (u64)-1) { - ret = fallback_to_cow(inode, locked_page, cow_start, - found_key.offset - 1, + ret = fallback_to_cow(inode, locked_page, + cow_start, found_key.offset - 1, page_started, nr_written); if (ret) goto error; @@ -1716,8 +1714,7 @@ out_check: num_bytes, BTRFS_ORDERED_PREALLOC); if (ret) { - btrfs_drop_extent_cache(BTRFS_I(inode), - cur_offset, + btrfs_drop_extent_cache(inode, cur_offset, cur_offset + num_bytes - 1, 0); goto error; @@ -1793,11 +1790,11 @@ error: return ret; } -static inline int need_force_cow(struct inode *inode, u64 start, u64 end) +static inline int need_force_cow(struct btrfs_inode *inode, u64 start, u64 end) { - if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) && - !(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC)) + if (!(inode->flags & BTRFS_INODE_NODATACOW) && + !(inode->flags & BTRFS_INODE_PREALLOC)) return 0; /* @@ -1805,9 +1802,8 @@ static inline int need_force_cow(struct inode *inode, u64 start, u64 end) * if is not zero, it means the file is defragging. * Force cow if given extent needs to be defragged. */ - if (BTRFS_I(inode)->defrag_bytes && - test_range_bit(&BTRFS_I(inode)->io_tree, start, end, - EXTENT_DEFRAG, 0, NULL)) + if (inode->defrag_bytes && + test_range_bit(&inode->io_tree, start, end, EXTENT_DEFRAG, 0, NULL)) return 1; return 0; @@ -1817,26 +1813,25 @@ static inline int need_force_cow(struct inode *inode, u64 start, u64 end) * Function to process delayed allocation (create CoW) for ranges which are * being touched for the first time. */ -int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page, +int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page, u64 start, u64 end, int *page_started, unsigned long *nr_written, struct writeback_control *wbc) { int ret; int force_cow = need_force_cow(inode, start, end); - if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW && !force_cow) { + if (inode->flags & BTRFS_INODE_NODATACOW && !force_cow) { ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 1, nr_written); - } else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC && !force_cow) { + } else if (inode->flags & BTRFS_INODE_PREALLOC && !force_cow) { ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 0, nr_written); } else if (!inode_can_compress(inode) || !inode_need_compress(inode, start, end)) { ret = cow_file_range(inode, locked_page, start, end, - page_started, nr_written, 1); + page_started, nr_written, 1); } else { - set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, - &BTRFS_I(inode)->runtime_flags); + set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &inode->runtime_flags); ret = cow_file_range_async(inode, wbc, locked_page, start, end, page_started, nr_written); } @@ -2085,9 +2080,7 @@ void btrfs_clear_delalloc_extent(struct inode *vfs_inode, if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID && do_list && !(state->state & EXTENT_NORESERVE) && (*bits & EXTENT_CLEAR_DATA_RESV)) - btrfs_free_reserved_data_space_noquota( - &inode->vfs_inode, - state->start, len); + btrfs_free_reserved_data_space_noquota(fs_info, len); percpu_counter_add_batch(&fs_info->delalloc_bytes, -len, fs_info->delalloc_batch); @@ -2163,7 +2156,7 @@ static blk_status_t btrfs_submit_bio_start(void *private_data, struct bio *bio, struct inode *inode = private_data; blk_status_t ret = 0; - ret = btrfs_csum_one_bio(inode, bio, 0, 0); + ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0); BUG_ON(ret); /* -ENOMEM */ return 0; } @@ -2228,7 +2221,7 @@ static blk_status_t btrfs_submit_bio_hook(struct inode *inode, struct bio *bio, 0, inode, btrfs_submit_bio_start); goto out; } else if (!skip_sum) { - ret = btrfs_csum_one_bio(inode, bio, 0, 0); + ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0); if (ret) goto out; } @@ -2265,13 +2258,13 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans, return 0; } -int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end, +int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state) { WARN_ON(PAGE_ALIGNED(end)); - return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end, - extra_bits, cached_state); + return set_extent_delalloc(&inode->io_tree, start, end, extra_bits, + cached_state); } /* see btrfs_writepage_start_hook for details on why this is required */ @@ -2288,7 +2281,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work) struct extent_state *cached_state = NULL; struct extent_changeset *data_reserved = NULL; struct page *page; - struct inode *inode; + struct btrfs_inode *inode; u64 page_start; u64 page_end; int ret = 0; @@ -2296,7 +2289,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work) fixup = container_of(work, struct btrfs_writepage_fixup, work); page = fixup->page; - inode = fixup->inode; + inode = BTRFS_I(fixup->inode); page_start = page_offset(page); page_end = page_offset(page) + PAGE_SIZE - 1; @@ -2333,8 +2326,7 @@ again: * when the page was already properly dealt with. */ if (!ret) { - btrfs_delalloc_release_extents(BTRFS_I(inode), - PAGE_SIZE); + btrfs_delalloc_release_extents(inode, PAGE_SIZE); btrfs_delalloc_release_space(inode, data_reserved, page_start, PAGE_SIZE, true); @@ -2350,20 +2342,18 @@ again: if (ret) goto out_page; - lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end, - &cached_state); + lock_extent_bits(&inode->io_tree, page_start, page_end, &cached_state); /* already ordered? We're done */ if (PagePrivate2(page)) goto out_reserved; - ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start, - PAGE_SIZE); + ordered = btrfs_lookup_ordered_range(inode, page_start, PAGE_SIZE); if (ordered) { - unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, - page_end, &cached_state); + unlock_extent_cached(&inode->io_tree, page_start, page_end, + &cached_state); unlock_page(page); - btrfs_start_ordered_extent(inode, ordered, 1); + btrfs_start_ordered_extent(&inode->vfs_inode, ordered, 1); btrfs_put_ordered_extent(ordered); goto again; } @@ -2383,11 +2373,11 @@ again: BUG_ON(!PageDirty(page)); free_delalloc_space = false; out_reserved: - btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); + btrfs_delalloc_release_extents(inode, PAGE_SIZE); if (free_delalloc_space) btrfs_delalloc_release_space(inode, data_reserved, page_start, PAGE_SIZE, true); - unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end, + unlock_extent_cached(&inode->io_tree, page_start, page_end, &cached_state); out_page: if (ret) { @@ -2410,7 +2400,7 @@ out_page: * that could need flushing space. Recursing back to fixup worker would * deadlock. */ - btrfs_add_delayed_iput(inode); + btrfs_add_delayed_iput(&inode->vfs_inode); } /* @@ -2466,18 +2456,18 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end) } static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, - struct inode *inode, u64 file_pos, - u64 disk_bytenr, u64 disk_num_bytes, - u64 num_bytes, u64 ram_bytes, - u8 compression, u8 encryption, - u16 other_encoding, int extent_type) + struct btrfs_inode *inode, u64 file_pos, + struct btrfs_file_extent_item *stack_fi, + u64 qgroup_reserved) { - struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_file_extent_item *fi; + struct btrfs_root *root = inode->root; struct btrfs_path *path; struct extent_buffer *leaf; struct btrfs_key ins; - u64 qg_released; + u64 disk_num_bytes = btrfs_stack_file_extent_disk_num_bytes(stack_fi); + u64 disk_bytenr = btrfs_stack_file_extent_disk_bytenr(stack_fi); + u64 num_bytes = btrfs_stack_file_extent_num_bytes(stack_fi); + u64 ram_bytes = btrfs_stack_file_extent_ram_bytes(stack_fi); int extent_inserted = 0; int ret; @@ -2496,60 +2486,42 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, */ ret = __btrfs_drop_extents(trans, root, inode, path, file_pos, file_pos + num_bytes, NULL, 0, - 1, sizeof(*fi), &extent_inserted); + 1, sizeof(*stack_fi), &extent_inserted); if (ret) goto out; if (!extent_inserted) { - ins.objectid = btrfs_ino(BTRFS_I(inode)); + ins.objectid = btrfs_ino(inode); ins.offset = file_pos; ins.type = BTRFS_EXTENT_DATA_KEY; path->leave_spinning = 1; ret = btrfs_insert_empty_item(trans, root, path, &ins, - sizeof(*fi)); + sizeof(*stack_fi)); if (ret) goto out; } leaf = path->nodes[0]; - fi = btrfs_item_ptr(leaf, path->slots[0], - struct btrfs_file_extent_item); - btrfs_set_file_extent_generation(leaf, fi, trans->transid); - btrfs_set_file_extent_type(leaf, fi, extent_type); - btrfs_set_file_extent_disk_bytenr(leaf, fi, disk_bytenr); - btrfs_set_file_extent_disk_num_bytes(leaf, fi, disk_num_bytes); - btrfs_set_file_extent_offset(leaf, fi, 0); - btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes); - btrfs_set_file_extent_ram_bytes(leaf, fi, ram_bytes); - btrfs_set_file_extent_compression(leaf, fi, compression); - btrfs_set_file_extent_encryption(leaf, fi, encryption); - btrfs_set_file_extent_other_encoding(leaf, fi, other_encoding); + btrfs_set_stack_file_extent_generation(stack_fi, trans->transid); + write_extent_buffer(leaf, stack_fi, + btrfs_item_ptr_offset(leaf, path->slots[0]), + sizeof(struct btrfs_file_extent_item)); btrfs_mark_buffer_dirty(leaf); btrfs_release_path(path); - inode_add_bytes(inode, num_bytes); + inode_add_bytes(&inode->vfs_inode, num_bytes); ins.objectid = disk_bytenr; ins.offset = disk_num_bytes; ins.type = BTRFS_EXTENT_ITEM_KEY; - ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode), file_pos, - ram_bytes); + ret = btrfs_inode_set_file_extent_range(inode, file_pos, ram_bytes); if (ret) goto out; - /* - * Release the reserved range from inode dirty range map, as it is - * already moved into delayed_ref_head - */ - ret = btrfs_qgroup_release_data(inode, file_pos, ram_bytes); - if (ret < 0) - goto out; - qg_released = ret; - ret = btrfs_alloc_reserved_file_extent(trans, root, - btrfs_ino(BTRFS_I(inode)), - file_pos, qg_released, &ins); + ret = btrfs_alloc_reserved_file_extent(trans, root, btrfs_ino(inode), + file_pos, qgroup_reserved, &ins); out: btrfs_free_path(path); @@ -2571,7 +2543,33 @@ static void btrfs_release_delalloc_bytes(struct btrfs_fs_info *fs_info, btrfs_put_block_group(cache); } -/* as ordered data IO finishes, this gets called so we can finish +static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans, + struct inode *inode, + struct btrfs_ordered_extent *oe) +{ + struct btrfs_file_extent_item stack_fi; + u64 logical_len; + + memset(&stack_fi, 0, sizeof(stack_fi)); + btrfs_set_stack_file_extent_type(&stack_fi, BTRFS_FILE_EXTENT_REG); + btrfs_set_stack_file_extent_disk_bytenr(&stack_fi, oe->disk_bytenr); + btrfs_set_stack_file_extent_disk_num_bytes(&stack_fi, + oe->disk_num_bytes); + if (test_bit(BTRFS_ORDERED_TRUNCATED, &oe->flags)) + logical_len = oe->truncated_len; + else + logical_len = oe->num_bytes; + btrfs_set_stack_file_extent_num_bytes(&stack_fi, logical_len); + btrfs_set_stack_file_extent_ram_bytes(&stack_fi, logical_len); + btrfs_set_stack_file_extent_compression(&stack_fi, oe->compress_type); + /* Encryption and other encoding is reserved and all 0 */ + + return insert_reserved_file_extent(trans, BTRFS_I(inode), oe->file_offset, + &stack_fi, oe->qgroup_rsv); +} + +/* + * As ordered data IO finishes, this gets called so we can finish * an ordered extent if the range of bytes in the file it covers are * fully written. */ @@ -2622,13 +2620,6 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) { BUG_ON(!list_empty(&ordered_extent->list)); /* Logic error */ - /* - * For mwrite(mmap + memset to write) case, we still reserve - * space for NOCOW range. - * As NOCOW won't cause a new delayed ref, just free the space - */ - btrfs_qgroup_free_data(inode, NULL, start, - ordered_extent->num_bytes); btrfs_inode_safe_disk_i_size_write(inode, 0); if (freespace_inode) trans = btrfs_join_transaction_spacecache(root); @@ -2665,20 +2656,14 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) compress_type = ordered_extent->compress_type; if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) { BUG_ON(compress_type); - btrfs_qgroup_free_data(inode, NULL, start, - ordered_extent->num_bytes); ret = btrfs_mark_extent_written(trans, BTRFS_I(inode), ordered_extent->file_offset, ordered_extent->file_offset + logical_len); } else { BUG_ON(root == fs_info->tree_root); - ret = insert_reserved_file_extent(trans, inode, start, - ordered_extent->disk_bytenr, - ordered_extent->disk_num_bytes, - logical_len, logical_len, - compress_type, 0, 0, - BTRFS_FILE_EXTENT_REG); + ret = insert_ordered_extent_file_extent(trans, inode, + ordered_extent); if (!ret) { clear_reserved_extent = false; btrfs_release_delalloc_bytes(fs_info, @@ -2830,6 +2815,9 @@ static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio, zeroit: btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected, io_bio->mirror_num); + if (io_bio->device) + btrfs_dev_stat_inc_and_print(io_bio->device, + BTRFS_DEV_STAT_CORRUPTION_ERRS); memset(kaddr + pgoff, 1, len); flush_dcache_page(page); kunmap_atomic(kaddr); @@ -3348,6 +3336,14 @@ cache_index: */ BTRFS_I(inode)->last_unlink_trans = BTRFS_I(inode)->last_trans; + /* + * Same logic as for last_unlink_trans. We don't persist the generation + * of the last transaction where this inode was used for a reflink + * operation, so after eviction and reloading the inode we must be + * pessimistic and assume the last transaction that modified the inode. + */ + BTRFS_I(inode)->last_reflink_trans = BTRFS_I(inode)->last_trans; + path->slots[0]++; if (inode->i_nlink != 1 || path->slots[0] >= btrfs_header_nritems(leaf)) @@ -3496,7 +3492,7 @@ static noinline int btrfs_update_inode_item(struct btrfs_trans_handle *trans, fill_inode_item(trans, leaf, inode_item, inode); btrfs_mark_buffer_dirty(leaf); - btrfs_set_inode_last_trans(trans, inode); + btrfs_set_inode_last_trans(trans, BTRFS_I(inode)); ret = 0; failed: btrfs_free_path(path); @@ -3526,7 +3522,7 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans, ret = btrfs_delayed_update_inode(trans, root, inode); if (!ret) - btrfs_set_inode_last_trans(trans, inode); + btrfs_set_inode_last_trans(trans, BTRFS_I(inode)); return ret; } @@ -4041,6 +4037,8 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) } } + free_anon_bdev(dest->anon_dev); + dest->anon_dev = 0; out_end_trans: trans->block_rsv = NULL; trans->bytes_reserved = 0; @@ -4511,11 +4509,13 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, struct extent_state *cached_state = NULL; struct extent_changeset *data_reserved = NULL; char *kaddr; + bool only_release_metadata = false; u32 blocksize = fs_info->sectorsize; pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (blocksize - 1); struct page *page; gfp_t mask = btrfs_alloc_write_mask(mapping); + size_t write_bytes = blocksize; int ret = 0; u64 block_start; u64 block_end; @@ -4527,15 +4527,28 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, block_start = round_down(from, blocksize); block_end = block_start + blocksize - 1; - ret = btrfs_delalloc_reserve_space(inode, &data_reserved, - block_start, blocksize); - if (ret) + ret = btrfs_check_data_free_space(BTRFS_I(inode), &data_reserved, + block_start, blocksize); + if (ret < 0) { + if (btrfs_check_nocow_lock(BTRFS_I(inode), block_start, + &write_bytes) > 0) { + /* For nocow case, no need to reserve data space */ + only_release_metadata = true; + } else { + goto out; + } + } + ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), blocksize); + if (ret < 0) { + if (!only_release_metadata) + btrfs_free_reserved_data_space(BTRFS_I(inode), + data_reserved, block_start, blocksize); goto out; - + } again: page = find_or_create_page(mapping, index, mask); if (!page) { - btrfs_delalloc_release_space(inode, data_reserved, + btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, block_start, blocksize, true); btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize); ret = -ENOMEM; @@ -4560,7 +4573,7 @@ again: lock_extent_bits(io_tree, block_start, block_end, &cached_state); set_page_extent_mapped(page); - ordered = btrfs_lookup_ordered_extent(inode, block_start); + ordered = btrfs_lookup_ordered_extent(BTRFS_I(inode), block_start); if (ordered) { unlock_extent_cached(io_tree, block_start, block_end, &cached_state); @@ -4575,7 +4588,7 @@ again: EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, &cached_state); - ret = btrfs_set_extent_delalloc(inode, block_start, block_end, 0, + ret = btrfs_set_extent_delalloc(BTRFS_I(inode), block_start, block_end, 0, &cached_state); if (ret) { unlock_extent_cached(io_tree, block_start, block_end, @@ -4600,14 +4613,26 @@ again: set_page_dirty(page); unlock_extent_cached(io_tree, block_start, block_end, &cached_state); + if (only_release_metadata) + set_extent_bit(&BTRFS_I(inode)->io_tree, block_start, + block_end, EXTENT_NORESERVE, NULL, NULL, + GFP_NOFS); + out_unlock: - if (ret) - btrfs_delalloc_release_space(inode, data_reserved, block_start, - blocksize, true); + if (ret) { + if (only_release_metadata) + btrfs_delalloc_release_metadata(BTRFS_I(inode), + blocksize, true); + else + btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, + block_start, blocksize, true); + } btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize); unlock_page(page); put_page(page); out: + if (only_release_metadata) + btrfs_check_nocow_unlock(BTRFS_I(inode)); extent_changeset_free(data_reserved); return ret; } @@ -4965,7 +4990,8 @@ static void evict_inode_truncate_pages(struct inode *inode) * Note, end is the bytenr of last byte, so we need + 1 here. */ if (state_flags & EXTENT_DELALLOC) - btrfs_qgroup_free_data(inode, NULL, start, end - start + 1); + btrfs_qgroup_free_data(BTRFS_I(inode), NULL, start, + end - start + 1); clear_extent_bit(io_tree, start, end, EXTENT_LOCKED | EXTENT_DELALLOC | @@ -6040,7 +6066,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, inode_tree_add(inode); trace_btrfs_inode_new(inode); - btrfs_set_inode_last_trans(trans, inode); + btrfs_set_inode_last_trans(trans, BTRFS_I(inode)); btrfs_update_root_times(trans, root); @@ -6849,7 +6875,7 @@ out: return em; } -static struct extent_map *btrfs_create_dio_extent(struct inode *inode, +static struct extent_map *btrfs_create_dio_extent(struct btrfs_inode *inode, const u64 start, const u64 len, const u64 orig_start, @@ -6863,21 +6889,19 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode, int ret; if (type != BTRFS_ORDERED_NOCOW) { - em = create_io_em(inode, start, len, orig_start, - block_start, block_len, orig_block_len, - ram_bytes, + em = create_io_em(inode, start, len, orig_start, block_start, + block_len, orig_block_len, ram_bytes, BTRFS_COMPRESS_NONE, /* compress_type */ type); if (IS_ERR(em)) goto out; } - ret = btrfs_add_ordered_extent_dio(inode, start, block_start, - len, block_len, type); + ret = btrfs_add_ordered_extent_dio(inode, start, block_start, len, + block_len, type); if (ret) { if (em) { free_extent_map(em); - btrfs_drop_extent_cache(BTRFS_I(inode), start, - start + len - 1, 0); + btrfs_drop_extent_cache(inode, start, start + len - 1, 0); } em = ERR_PTR(ret); } @@ -6886,11 +6910,11 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode, return em; } -static struct extent_map *btrfs_new_extent_direct(struct inode *inode, +static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode, u64 start, u64 len) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_root *root = inode->root; + struct btrfs_fs_info *fs_info = root->fs_info; struct extent_map *em; struct btrfs_key ins; u64 alloc_hint; @@ -6907,15 +6931,32 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, ins.offset, BTRFS_ORDERED_REGULAR); btrfs_dec_block_group_reservations(fs_info, ins.objectid); if (IS_ERR(em)) - btrfs_free_reserved_extent(fs_info, ins.objectid, - ins.offset, 1); + btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, + 1); return em; } /* - * returns 1 when the nocow is safe, < 1 on error, 0 if the - * block must be cow'd + * Check if we can do nocow write into the range [@offset, @offset + @len) + * + * @offset: File offset + * @len: The length to write, will be updated to the nocow writeable + * range + * @orig_start: (optional) Return the original file offset of the file extent + * @orig_len: (optional) Return the original on-disk length of the file extent + * @ram_bytes: (optional) Return the ram_bytes of the file extent + * + * This function will flush ordered extents in the range to ensure proper + * nocow checks for (nowait == false) case. + * + * Return: + * >0 and update @len if we can do nocow write + * 0 if we can't do nocow write + * <0 if error happened + * + * NOTE: This only checks the file extents, caller is responsible to wait for + * any ordered extents. */ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *orig_start, u64 *orig_block_len, @@ -7142,8 +7183,8 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, } /* The callers of this must take lock_extent() */ -static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len, - u64 orig_start, u64 block_start, +static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start, + u64 len, u64 orig_start, u64 block_start, u64 block_len, u64 orig_block_len, u64 ram_bytes, int compress_type, int type) @@ -7157,7 +7198,7 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len, type == BTRFS_ORDERED_NOCOW || type == BTRFS_ORDERED_REGULAR); - em_tree = &BTRFS_I(inode)->extent_tree; + em_tree = &inode->extent_tree; em = alloc_extent_map(); if (!em) return ERR_PTR(-ENOMEM); @@ -7179,8 +7220,8 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len, } do { - btrfs_drop_extent_cache(BTRFS_I(inode), em->start, - em->start + em->len - 1, 0); + btrfs_drop_extent_cache(inode, em->start, + em->start + em->len - 1, 0); write_lock(&em_tree->lock); ret = add_extent_mapping(em_tree, em, 1); write_unlock(&em_tree->lock); @@ -7259,7 +7300,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, btrfs_inc_nocow_writers(fs_info, block_start)) { struct extent_map *em2; - em2 = btrfs_create_dio_extent(inode, start, len, + em2 = btrfs_create_dio_extent(BTRFS_I(inode), start, len, orig_start, block_start, len, orig_block_len, ram_bytes, type); @@ -7278,8 +7319,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, * use the existing or preallocated extent, so does not * need to adjust btrfs_space_info's bytes_may_use. */ - btrfs_free_reserved_data_space_noquota(inode, start, - len); + btrfs_free_reserved_data_space_noquota(fs_info, len); goto skip_cow; } } @@ -7287,7 +7327,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, /* this will cow the extent */ len = bh_result->b_size; free_extent_map(em); - *map = em = btrfs_new_extent_direct(inode, start, len); + *map = em = btrfs_new_extent_direct(BTRFS_I(inode), start, len); if (IS_ERR(em)) { ret = PTR_ERR(em); goto out; @@ -7438,7 +7478,8 @@ static void btrfs_dio_private_put(struct btrfs_dio_private *dip) return; if (bio_op(dip->dio_bio) == REQ_OP_WRITE) { - __endio_write_update_ordered(dip->inode, dip->logical_offset, + __endio_write_update_ordered(BTRFS_I(dip->inode), + dip->logical_offset, dip->bytes, !dip->dio_bio->bi_status); } else { @@ -7524,18 +7565,18 @@ static blk_status_t btrfs_check_read_dio_bio(struct inode *inode, return err; } -static void __endio_write_update_ordered(struct inode *inode, +static void __endio_write_update_ordered(struct btrfs_inode *inode, const u64 offset, const u64 bytes, const bool uptodate) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_ordered_extent *ordered = NULL; struct btrfs_workqueue *wq; u64 ordered_offset = offset; u64 ordered_bytes = bytes; u64 last_offset; - if (btrfs_is_free_space_inode(BTRFS_I(inode))) + if (btrfs_is_free_space_inode(inode)) wq = fs_info->endio_freespace_worker; else wq = fs_info->endio_write_workers; @@ -7543,9 +7584,9 @@ static void __endio_write_update_ordered(struct inode *inode, while (ordered_offset < offset + bytes) { last_offset = ordered_offset; if (btrfs_dec_test_first_ordered_pending(inode, &ordered, - &ordered_offset, - ordered_bytes, - uptodate)) { + &ordered_offset, + ordered_bytes, + uptodate)) { btrfs_init_work(&ordered->work, finish_ordered_fn, NULL, NULL); btrfs_queue_work(wq, &ordered->work); @@ -7572,7 +7613,7 @@ static blk_status_t btrfs_submit_bio_start_direct_io(void *private_data, { struct inode *inode = private_data; blk_status_t ret; - ret = btrfs_csum_one_bio(inode, bio, offset, 1); + ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, offset, 1); BUG_ON(ret); /* -ENOMEM */ return 0; } @@ -7633,7 +7674,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio, * If we aren't doing async submit, calculate the csum of the * bio now. */ - ret = btrfs_csum_one_bio(inode, bio, file_offset, 1); + ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, file_offset, 1); if (ret) goto err; } else { @@ -7883,7 +7924,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) inode_unlock(inode); relock = true; } - ret = btrfs_delalloc_reserve_space(inode, &data_reserved, + ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved, offset, count); if (ret) goto out; @@ -7915,8 +7956,9 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) current->journal_info = NULL; if (ret < 0 && ret != -EIOCBQUEUED) { if (dio_data.reserve) - btrfs_delalloc_release_space(inode, data_reserved, - offset, dio_data.reserve, true); + btrfs_delalloc_release_space(BTRFS_I(inode), + data_reserved, offset, dio_data.reserve, + true); /* * On error we might have left some ordered extents * without submitting corresponding bios for them, so @@ -7925,13 +7967,13 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) */ if (dio_data.unsubmitted_oe_range_start < dio_data.unsubmitted_oe_range_end) - __endio_write_update_ordered(inode, + __endio_write_update_ordered(BTRFS_I(inode), dio_data.unsubmitted_oe_range_start, dio_data.unsubmitted_oe_range_end - dio_data.unsubmitted_oe_range_start, false); } else if (ret >= 0 && (size_t)ret < count) - btrfs_delalloc_release_space(inode, data_reserved, + btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, offset, count - (size_t)ret, true); btrfs_delalloc_release_extents(BTRFS_I(inode), count); } @@ -7946,7 +7988,7 @@ out: } static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, - __u64 start, __u64 len) + u64 start, u64 len) { int ret; @@ -8123,20 +8165,17 @@ again: /* * Qgroup reserved space handler * Page here will be either - * 1) Already written to disk - * In this case, its reserved space is released from data rsv map - * and will be freed by delayed_ref handler finally. - * So even we call qgroup_free_data(), it won't decrease reserved - * space. - * 2) Not written to disk - * This means the reserved space should be freed here. However, - * if a truncate invalidates the page (by clearing PageDirty) - * and the page is accounted for while allocating extent - * in btrfs_check_data_free_space() we let delayed_ref to - * free the entire extent. + * 1) Already written to disk or ordered extent already submitted + * Then its QGROUP_RESERVED bit in io_tree is already cleaned. + * Qgroup will be handled by its qgroup_record then. + * btrfs_qgroup_free_data() call will do nothing here. + * + * 2) Not written to disk yet + * Then btrfs_qgroup_free_data() call will clear the QGROUP_RESERVED + * bit of its io_tree, and free the qgroup reserved data space. + * Since the IO will never happen for this page. */ - if (PageDirty(page)) - btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE); + btrfs_qgroup_free_data(BTRFS_I(inode), NULL, page_start, PAGE_SIZE); if (!inode_evicting) { clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | @@ -8200,8 +8239,8 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf) * end up waiting indefinitely to get a lock on the page currently * being processed by btrfs_page_mkwrite() function. */ - ret2 = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start, - reserved_space); + ret2 = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved, + page_start, reserved_space); if (!ret2) { ret2 = file_update_time(vmf->vma->vm_file); reserved = 1; @@ -8248,9 +8287,9 @@ again: fs_info->sectorsize); if (reserved_space < PAGE_SIZE) { end = page_start + reserved_space - 1; - btrfs_delalloc_release_space(inode, data_reserved, - page_start, PAGE_SIZE - reserved_space, - true); + btrfs_delalloc_release_space(BTRFS_I(inode), + data_reserved, page_start, + PAGE_SIZE - reserved_space, true); } } @@ -8265,7 +8304,7 @@ again: EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, &cached_state); - ret2 = btrfs_set_extent_delalloc(inode, page_start, end, 0, + ret2 = btrfs_set_extent_delalloc(BTRFS_I(inode), page_start, end, 0, &cached_state); if (ret2) { unlock_extent_cached(io_tree, page_start, page_end, @@ -8305,7 +8344,7 @@ out_unlock: unlock_page(page); out: btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); - btrfs_delalloc_release_space(inode, data_reserved, page_start, + btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, page_start, reserved_space, (ret != 0)); out_noreserve: sb_end_pagefault(inode->i_sb); @@ -8519,6 +8558,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) ei->index_cnt = (u64)-1; ei->dir_index = 0; ei->last_unlink_trans = 0; + ei->last_reflink_trans = 0; ei->last_log_commit = 0; spin_lock_init(&ei->lock); @@ -8605,7 +8645,7 @@ void btrfs_destroy_inode(struct inode *inode) btrfs_put_ordered_extent(ordered); } } - btrfs_qgroup_check_reserved_leak(inode); + btrfs_qgroup_check_reserved_leak(BTRFS_I(inode)); inode_tree_del(inode); btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0); btrfs_inode_clear_file_extent_range(BTRFS_I(inode), 0, (u64)-1); @@ -9587,6 +9627,31 @@ out_unlock: return err; } +static int insert_prealloc_file_extent(struct btrfs_trans_handle *trans, + struct inode *inode, struct btrfs_key *ins, + u64 file_offset) +{ + struct btrfs_file_extent_item stack_fi; + u64 start = ins->objectid; + u64 len = ins->offset; + int ret; + + memset(&stack_fi, 0, sizeof(stack_fi)); + + btrfs_set_stack_file_extent_type(&stack_fi, BTRFS_FILE_EXTENT_PREALLOC); + btrfs_set_stack_file_extent_disk_bytenr(&stack_fi, start); + btrfs_set_stack_file_extent_disk_num_bytes(&stack_fi, len); + btrfs_set_stack_file_extent_num_bytes(&stack_fi, len); + btrfs_set_stack_file_extent_ram_bytes(&stack_fi, len); + btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE); + /* Encryption and other encoding is reserved and all 0 */ + + ret = btrfs_qgroup_release_data(BTRFS_I(inode), file_offset, len); + if (ret < 0) + return ret; + return insert_reserved_file_extent(trans, BTRFS_I(inode), file_offset, + &stack_fi, ret); +} static int __btrfs_prealloc_file_range(struct inode *inode, int mode, u64 start, u64 num_bytes, u64 min_size, loff_t actual_len, u64 *alloc_hint, @@ -9645,11 +9710,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, btrfs_dec_block_group_reservations(fs_info, ins.objectid); last_alloc = ins.offset; - ret = insert_reserved_file_extent(trans, inode, - cur_offset, ins.objectid, - ins.offset, ins.offset, - ins.offset, 0, 0, 0, - BTRFS_FILE_EXTENT_PREALLOC); + ret = insert_prealloc_file_extent(trans, inode, &ins, cur_offset); if (ret) { btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 0); @@ -9722,7 +9783,7 @@ next: btrfs_end_transaction(trans); } if (clear_offset < end) - btrfs_free_reserved_data_space(inode, NULL, clear_offset, + btrfs_free_reserved_data_space(BTRFS_I(inode), NULL, clear_offset, end - clear_offset + 1); return ret; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index e8f7c5f00894..bd3511c5ca81 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -164,8 +164,11 @@ static int btrfs_ioctl_getflags(struct file *file, void __user *arg) return 0; } -/* Check if @flags are a supported and valid set of FS_*_FL flags */ -static int check_fsflags(unsigned int flags) +/* + * Check if @flags are a supported and valid set of FS_*_FL flags and that + * the old and new flags are not conflicting + */ +static int check_fsflags(unsigned int old_flags, unsigned int flags) { if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \ FS_NOATIME_FL | FS_NODUMP_FL | \ @@ -174,9 +177,19 @@ static int check_fsflags(unsigned int flags) FS_NOCOW_FL)) return -EOPNOTSUPP; + /* COMPR and NOCOMP on new/old are valid */ if ((flags & FS_NOCOMP_FL) && (flags & FS_COMPR_FL)) return -EINVAL; + if ((flags & FS_COMPR_FL) && (flags & FS_NOCOW_FL)) + return -EINVAL; + + /* NOCOW and compression options are mutually exclusive */ + if ((old_flags & FS_NOCOW_FL) && (flags & (FS_COMPR_FL | FS_NOCOMP_FL))) + return -EINVAL; + if ((flags & FS_NOCOW_FL) && (old_flags & (FS_COMPR_FL | FS_NOCOMP_FL))) + return -EINVAL; + return 0; } @@ -190,7 +203,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) unsigned int fsflags, old_fsflags; int ret; const char *comp = NULL; - u32 binode_flags = binode->flags; + u32 binode_flags; if (!inode_owner_or_capable(inode)) return -EPERM; @@ -201,22 +214,23 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) if (copy_from_user(&fsflags, arg, sizeof(fsflags))) return -EFAULT; - ret = check_fsflags(fsflags); - if (ret) - return ret; - ret = mnt_want_write_file(file); if (ret) return ret; inode_lock(inode); - fsflags = btrfs_mask_fsflags_for_type(inode, fsflags); old_fsflags = btrfs_inode_flags_to_fsflags(binode->flags); + ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags); if (ret) goto out_unlock; + ret = check_fsflags(old_fsflags, fsflags); + if (ret) + goto out_unlock; + + binode_flags = binode->flags; if (fsflags & FS_SYNC_FL) binode_flags |= BTRFS_INODE_SYNC; else @@ -566,6 +580,7 @@ static noinline int create_subvol(struct inode *dir, struct inode *inode; int ret; int err; + dev_t anon_dev = 0; u64 objectid; u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID; u64 index = 0; @@ -578,6 +593,10 @@ static noinline int create_subvol(struct inode *dir, if (ret) goto fail_free; + ret = get_anon_bdev(&anon_dev); + if (ret < 0) + goto fail_free; + /* * Don't create subvolume whose level is not zero. Or qgroup will be * screwed up since it assumes subvolume qgroup's level to be 0. @@ -660,12 +679,15 @@ static noinline int create_subvol(struct inode *dir, goto fail; key.offset = (u64)-1; - new_root = btrfs_get_fs_root(fs_info, objectid, true); + new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev); if (IS_ERR(new_root)) { + free_anon_bdev(anon_dev); ret = PTR_ERR(new_root); btrfs_abort_transaction(trans, ret); goto fail; } + /* Freeing will be done in btrfs_put_root() of new_root */ + anon_dev = 0; btrfs_record_root_in_trans(trans, new_root); @@ -735,6 +757,8 @@ fail: return ret; fail_free: + if (anon_dev) + free_anon_bdev(anon_dev); kfree(root_item); return ret; } @@ -762,6 +786,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (!pending_snapshot) return -ENOMEM; + ret = get_anon_bdev(&pending_snapshot->anon_dev); + if (ret < 0) + goto free_pending; pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item), GFP_KERNEL); pending_snapshot->path = btrfs_alloc_path(); @@ -823,10 +850,16 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, d_instantiate(dentry, inode); ret = 0; + pending_snapshot->anon_dev = 0; fail: + /* Prevent double freeing of anon_dev */ + if (ret && pending_snapshot->snap) + pending_snapshot->snap->anon_dev = 0; btrfs_put_root(pending_snapshot->snap); btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv); free_pending: + if (pending_snapshot->anon_dev) + free_anon_bdev(pending_snapshot->anon_dev); kfree(pending_snapshot->root_item); btrfs_free_path(pending_snapshot->path); kfree(pending_snapshot); @@ -1243,7 +1276,7 @@ static int cluster_pages_for_defrag(struct inode *inode, page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1); - ret = btrfs_delalloc_reserve_space(inode, &data_reserved, + ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved, start_index << PAGE_SHIFT, page_cnt << PAGE_SHIFT); if (ret) @@ -1265,7 +1298,7 @@ again: while (1) { lock_extent_bits(tree, page_start, page_end, &cached_state); - ordered = btrfs_lookup_ordered_extent(inode, + ordered = btrfs_lookup_ordered_extent(BTRFS_I(inode), page_start); unlock_extent_cached(tree, page_start, page_end, &cached_state); @@ -1333,7 +1366,7 @@ again: spin_lock(&BTRFS_I(inode)->lock); btrfs_mod_outstanding_extents(BTRFS_I(inode), 1); spin_unlock(&BTRFS_I(inode)->lock); - btrfs_delalloc_release_space(inode, data_reserved, + btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, start_index << PAGE_SHIFT, (page_cnt - i_done) << PAGE_SHIFT, true); } @@ -1361,7 +1394,7 @@ out: unlock_page(pages[i]); put_page(pages[i]); } - btrfs_delalloc_release_space(inode, data_reserved, + btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, start_index << PAGE_SHIFT, page_cnt << PAGE_SHIFT, true); btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT); @@ -3198,11 +3231,15 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_fs_info_args *fi_args; struct btrfs_device *device; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + u64 flags_in; int ret = 0; - fi_args = kzalloc(sizeof(*fi_args), GFP_KERNEL); - if (!fi_args) - return -ENOMEM; + fi_args = memdup_user(arg, sizeof(*fi_args)); + if (IS_ERR(fi_args)) + return PTR_ERR(fi_args); + + flags_in = fi_args->flags; + memset(fi_args, 0, sizeof(*fi_args)); rcu_read_lock(); fi_args->num_devices = fs_devices->num_devices; @@ -3218,6 +3255,23 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info, fi_args->sectorsize = fs_info->sectorsize; fi_args->clone_alignment = fs_info->sectorsize; + if (flags_in & BTRFS_FS_INFO_FLAG_CSUM_INFO) { + fi_args->csum_type = btrfs_super_csum_type(fs_info->super_copy); + fi_args->csum_size = btrfs_super_csum_size(fs_info->super_copy); + fi_args->flags |= BTRFS_FS_INFO_FLAG_CSUM_INFO; + } + + if (flags_in & BTRFS_FS_INFO_FLAG_GENERATION) { + fi_args->generation = fs_info->generation; + fi_args->flags |= BTRFS_FS_INFO_FLAG_GENERATION; + } + + if (flags_in & BTRFS_FS_INFO_FLAG_METADATA_UUID) { + memcpy(&fi_args->metadata_uuid, fs_devices->metadata_uuid, + sizeof(fi_args->metadata_uuid)); + fi_args->flags |= BTRFS_FS_INFO_FLAG_METADATA_UUID; + } + if (copy_to_user(arg, fi_args, sizeof(*fi_args))) ret = -EFAULT; diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index e13b3d28c063..ebac13389e7e 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -15,6 +15,7 @@ #include "disk-io.h" #include "compression.h" #include "delalloc-space.h" +#include "qgroup.h" static struct kmem_cache *btrfs_ordered_extent_cache; @@ -152,23 +153,39 @@ static inline struct rb_node *tree_search(struct btrfs_ordered_inode_tree *tree, return ret; } -/* allocate and add a new ordered_extent into the per-inode tree. +/* + * Allocate and add a new ordered_extent into the per-inode tree. * * The tree is given a single reference on the ordered extent that was * inserted. */ -static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, +static int __btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes, int type, int dio, int compress_type) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_ordered_inode_tree *tree; + struct btrfs_root *root = inode->root; + struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree; struct rb_node *node; struct btrfs_ordered_extent *entry; + int ret; - tree = &BTRFS_I(inode)->ordered_tree; + if (type == BTRFS_ORDERED_NOCOW || type == BTRFS_ORDERED_PREALLOC) { + /* For nocow write, we can release the qgroup rsv right now */ + ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes); + if (ret < 0) + return ret; + ret = 0; + } else { + /* + * The ordered extent has reserved qgroup space, release now + * and pass the reserved number for qgroup_record to free. + */ + ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes); + if (ret < 0) + return ret; + } entry = kmem_cache_zalloc(btrfs_ordered_extent_cache, GFP_NOFS); if (!entry) return -ENOMEM; @@ -178,9 +195,10 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, entry->num_bytes = num_bytes; entry->disk_num_bytes = disk_num_bytes; entry->bytes_left = num_bytes; - entry->inode = igrab(inode); + entry->inode = igrab(&inode->vfs_inode); entry->compress_type = compress_type; entry->truncated_len = (u64)-1; + entry->qgroup_rsv = ret; if (type != BTRFS_ORDERED_IO_DONE && type != BTRFS_ORDERED_COMPLETE) set_bit(type, &entry->flags); @@ -197,10 +215,8 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, INIT_LIST_HEAD(&entry->root_extent_list); INIT_LIST_HEAD(&entry->work_list); init_completion(&entry->completion); - INIT_LIST_HEAD(&entry->log_list); - INIT_LIST_HEAD(&entry->trans_list); - trace_btrfs_ordered_extent_add(inode, entry); + trace_btrfs_ordered_extent_add(&inode->vfs_inode, entry); spin_lock_irq(&tree->lock); node = tree_insert(&tree->tree, file_offset, @@ -228,14 +244,14 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, * that work has been done at higher layers, so this is truly the * smallest the extent is going to get. */ - spin_lock(&BTRFS_I(inode)->lock); - btrfs_mod_outstanding_extents(BTRFS_I(inode), 1); - spin_unlock(&BTRFS_I(inode)->lock); + spin_lock(&inode->lock); + btrfs_mod_outstanding_extents(inode, 1); + spin_unlock(&inode->lock); return 0; } -int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, +int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes, int type) { @@ -244,7 +260,7 @@ int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, BTRFS_COMPRESS_NONE); } -int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset, +int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes, int type) { @@ -253,7 +269,7 @@ int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset, BTRFS_COMPRESS_NONE); } -int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset, +int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes, int type, int compress_type) @@ -291,12 +307,12 @@ void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry, * file_offset is updated to one byte past the range that is recorded as * complete. This allows you to walk forward in the file. */ -int btrfs_dec_test_first_ordered_pending(struct inode *inode, +int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, struct btrfs_ordered_extent **cached, u64 *file_offset, u64 io_size, int uptodate) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_ordered_inode_tree *tree; + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; int ret; @@ -305,7 +321,6 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode, u64 dec_start; u64 to_dec; - tree = &BTRFS_I(inode)->ordered_tree; spin_lock_irqsave(&tree->lock, flags); node = tree_search(tree, *file_offset); if (!node) { @@ -429,8 +444,6 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry) trace_btrfs_ordered_extent_put(entry->inode, entry); if (refcount_dec_and_test(&entry->refs)) { - ASSERT(list_empty(&entry->log_list)); - ASSERT(list_empty(&entry->trans_list)); ASSERT(list_empty(&entry->root_extent_list)); ASSERT(RB_EMPTY_NODE(&entry->rb_node)); if (entry->inode) @@ -698,14 +711,14 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len) * find an ordered extent corresponding to file_offset. return NULL if * nothing is found, otherwise take a reference on the extent and return it */ -struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode, +struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *inode, u64 file_offset) { struct btrfs_ordered_inode_tree *tree; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; - tree = &BTRFS_I(inode)->ordered_tree; + tree = &inode->ordered_tree; spin_lock_irq(&tree->lock); node = tree_search(tree, file_offset); if (!node) @@ -803,7 +816,7 @@ int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); int index = 0; - ordered = btrfs_lookup_ordered_extent(inode, offset); + ordered = btrfs_lookup_ordered_extent(BTRFS_I(inode), offset); if (!ordered) return 0; diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index c01c9698250b..d61ea9c880a3 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -92,6 +92,9 @@ struct btrfs_ordered_extent { /* compression algorithm */ int compress_type; + /* Qgroup reserved space */ + int qgroup_rsv; + /* reference count */ refcount_t refs; @@ -101,12 +104,6 @@ struct btrfs_ordered_extent { /* list of checksums for insertion when the extent io is done */ struct list_head list; - /* If we need to wait on this to be done */ - struct list_head log_list; - - /* If the transaction needs to wait on this ordered extent */ - struct list_head trans_list; - /* used to wait for the BTRFS_ORDERED_COMPLETE bit */ wait_queue_head_t wait; @@ -150,23 +147,23 @@ void btrfs_remove_ordered_extent(struct inode *inode, int btrfs_dec_test_ordered_pending(struct inode *inode, struct btrfs_ordered_extent **cached, u64 file_offset, u64 io_size, int uptodate); -int btrfs_dec_test_first_ordered_pending(struct inode *inode, +int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, struct btrfs_ordered_extent **cached, u64 *file_offset, u64 io_size, int uptodate); -int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, +int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes, int type); -int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset, +int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes, int type); -int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset, +int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes, int type, int compress_type); void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry, struct btrfs_ordered_sum *sum); -struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode, +struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *inode, u64 file_offset); void btrfs_start_ordered_extent(struct inode *inode, struct btrfs_ordered_extent *entry, int wait); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 5bd4089ad0e1..c0f350c3a0cf 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -11,7 +11,6 @@ #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/btrfs.h> -#include <linux/sizes.h> #include "ctree.h" #include "transaction.h" @@ -22,6 +21,7 @@ #include "extent_io.h" #include "qgroup.h" #include "block-group.h" +#include "sysfs.h" /* TODO XXX FIXME * - subvol delete -> delete when ref goes to 0? delete limits also? @@ -220,10 +220,12 @@ static struct btrfs_qgroup *add_qgroup_rb(struct btrfs_fs_info *fs_info, return qgroup; } -static void __del_qgroup_rb(struct btrfs_qgroup *qgroup) +static void __del_qgroup_rb(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup *qgroup) { struct btrfs_qgroup_list *list; + btrfs_sysfs_del_one_qgroup(fs_info, qgroup); list_del(&qgroup->dirty); while (!list_empty(&qgroup->groups)) { list = list_first_entry(&qgroup->groups, @@ -252,7 +254,7 @@ static int del_qgroup_rb(struct btrfs_fs_info *fs_info, u64 qgroupid) return -ENOENT; rb_erase(&qgroup->node, &fs_info->qgroup_tree); - __del_qgroup_rb(qgroup); + __del_qgroup_rb(fs_info, qgroup); return 0; } @@ -351,6 +353,9 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) goto out; } + ret = btrfs_sysfs_add_qgroups(fs_info); + if (ret < 0) + goto out; /* default this to quota off, in case no status key is found */ fs_info->qgroup_flags = 0; @@ -412,6 +417,10 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) goto out; } } + ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup); + if (ret < 0) + goto out; + switch (found_key.type) { case BTRFS_QGROUP_INFO_KEY: { struct btrfs_qgroup_info_item *ptr; @@ -500,12 +509,51 @@ out: ulist_free(fs_info->qgroup_ulist); fs_info->qgroup_ulist = NULL; fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; + btrfs_sysfs_del_qgroups(fs_info); } return ret < 0 ? ret : 0; } /* + * Called in close_ctree() when quota is still enabled. This verifies we don't + * leak some reserved space. + * + * Return false if no reserved space is left. + * Return true if some reserved space is leaked. + */ +bool btrfs_check_quota_leak(struct btrfs_fs_info *fs_info) +{ + struct rb_node *node; + bool ret = false; + + if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) + return ret; + /* + * Since we're unmounting, there is no race and no need to grab qgroup + * lock. And here we don't go post-order to provide a more user + * friendly sorted result. + */ + for (node = rb_first(&fs_info->qgroup_tree); node; node = rb_next(node)) { + struct btrfs_qgroup *qgroup; + int i; + + qgroup = rb_entry(node, struct btrfs_qgroup, node); + for (i = 0; i < BTRFS_QGROUP_RSV_LAST; i++) { + if (qgroup->rsv.values[i]) { + ret = true; + btrfs_warn(fs_info, + "qgroup %hu/%llu has unreleased space, type %d rsv %llu", + btrfs_qgroup_level(qgroup->qgroupid), + btrfs_qgroup_subvolid(qgroup->qgroupid), + i, qgroup->rsv.values[i]); + } + } + } + return ret; +} + +/* * This is called from close_ctree() or open_ctree() or btrfs_quota_disable(), * first two are in single-threaded paths.And for the third one, we have set * quota_root to be null with qgroup_lock held before, so it is safe to clean @@ -519,7 +567,7 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info) while ((n = rb_first(&fs_info->qgroup_tree))) { qgroup = rb_entry(n, struct btrfs_qgroup, node); rb_erase(n, &fs_info->qgroup_tree); - __del_qgroup_rb(qgroup); + __del_qgroup_rb(fs_info, qgroup); } /* * We call btrfs_free_qgroup_config() when unmounting @@ -528,6 +576,7 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info) */ ulist_free(fs_info->qgroup_ulist); fs_info->qgroup_ulist = NULL; + btrfs_sysfs_del_qgroups(fs_info); } static int add_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src, @@ -900,6 +949,9 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) goto out; } + ret = btrfs_sysfs_add_qgroups(fs_info); + if (ret < 0) + goto out; /* * 1 for quota root item * 1 for BTRFS_QGROUP_STATUS item @@ -987,6 +1039,11 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) btrfs_abort_transaction(trans, ret); goto out_free_path; } + ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup); + if (ret < 0) { + btrfs_abort_transaction(trans, ret); + goto out_free_path; + } } ret = btrfs_next_item(tree_root, path); if (ret < 0) { @@ -1011,6 +1068,11 @@ out_add_root: btrfs_abort_transaction(trans, ret); goto out_free_path; } + ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup); + if (ret < 0) { + btrfs_abort_transaction(trans, ret); + goto out_free_path; + } ret = btrfs_commit_transaction(trans); trans = NULL; @@ -1046,6 +1108,7 @@ out: fs_info->qgroup_ulist = NULL; if (trans) btrfs_end_transaction(trans); + btrfs_sysfs_del_qgroups(fs_info); } mutex_unlock(&fs_info->qgroup_ioctl_lock); return ret; @@ -1398,8 +1461,11 @@ int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) qgroup = add_qgroup_rb(fs_info, qgroupid); spin_unlock(&fs_info->qgroup_lock); - if (IS_ERR(qgroup)) + if (IS_ERR(qgroup)) { ret = PTR_ERR(qgroup); + goto out; + } + ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup); out: mutex_unlock(&fs_info->qgroup_ioctl_lock); return ret; @@ -2818,6 +2884,8 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, unlock: spin_unlock(&fs_info->qgroup_lock); + if (!ret) + ret = btrfs_sysfs_add_one_qgroup(fs_info, dstgroup); out: if (!committing) mutex_unlock(&fs_info->qgroup_ioctl_lock); @@ -2826,20 +2894,8 @@ out: return ret; } -/* - * Two limits to commit transaction in advance. - * - * For RATIO, it will be 1/RATIO of the remaining limit as threshold. - * For SIZE, it will be in byte unit as threshold. - */ -#define QGROUP_FREE_RATIO 32 -#define QGROUP_FREE_SIZE SZ_32M -static bool qgroup_check_limits(struct btrfs_fs_info *fs_info, - const struct btrfs_qgroup *qg, u64 num_bytes) +static bool qgroup_check_limits(const struct btrfs_qgroup *qg, u64 num_bytes) { - u64 free; - u64 threshold; - if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) && qgroup_rsv_total(qg) + (s64)qg->rfer + num_bytes > qg->max_rfer) return false; @@ -2848,32 +2904,6 @@ static bool qgroup_check_limits(struct btrfs_fs_info *fs_info, qgroup_rsv_total(qg) + (s64)qg->excl + num_bytes > qg->max_excl) return false; - /* - * Even if we passed the check, it's better to check if reservation - * for meta_pertrans is pushing us near limit. - * If there is too much pertrans reservation or it's near the limit, - * let's try commit transaction to free some, using transaction_kthread - */ - if ((qg->lim_flags & (BTRFS_QGROUP_LIMIT_MAX_RFER | - BTRFS_QGROUP_LIMIT_MAX_EXCL))) { - if (qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) { - free = qg->max_excl - qgroup_rsv_total(qg) - qg->excl; - threshold = min_t(u64, qg->max_excl / QGROUP_FREE_RATIO, - QGROUP_FREE_SIZE); - } else { - free = qg->max_rfer - qgroup_rsv_total(qg) - qg->rfer; - threshold = min_t(u64, qg->max_rfer / QGROUP_FREE_RATIO, - QGROUP_FREE_SIZE); - } - - /* - * Use transaction_kthread to commit transaction, so we no - * longer need to bother nested transaction nor lock context. - */ - if (free < threshold) - btrfs_commit_transaction_locksafe(fs_info); - } - return true; } @@ -2921,7 +2951,7 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce, qg = unode_aux_to_qgroup(unode); - if (enforce && !qgroup_check_limits(fs_info, qg, num_bytes)) { + if (enforce && !qgroup_check_limits(qg, num_bytes)) { ret = -EDQUOT; goto out; } @@ -3378,28 +3408,132 @@ btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info) } } +#define rbtree_iterate_from_safe(node, next, start) \ + for (node = start; node && ({ next = rb_next(node); 1;}); node = next) + +static int qgroup_unreserve_range(struct btrfs_inode *inode, + struct extent_changeset *reserved, u64 start, + u64 len) +{ + struct rb_node *node; + struct rb_node *next; + struct ulist_node *entry = NULL; + int ret = 0; + + node = reserved->range_changed.root.rb_node; + while (node) { + entry = rb_entry(node, struct ulist_node, rb_node); + if (entry->val < start) + node = node->rb_right; + else if (entry) + node = node->rb_left; + else + break; + } + + /* Empty changeset */ + if (!entry) + return 0; + + if (entry->val > start && rb_prev(&entry->rb_node)) + entry = rb_entry(rb_prev(&entry->rb_node), struct ulist_node, + rb_node); + + rbtree_iterate_from_safe(node, next, &entry->rb_node) { + u64 entry_start; + u64 entry_end; + u64 entry_len; + int clear_ret; + + entry = rb_entry(node, struct ulist_node, rb_node); + entry_start = entry->val; + entry_end = entry->aux; + entry_len = entry_end - entry_start + 1; + + if (entry_start >= start + len) + break; + if (entry_start + entry_len <= start) + continue; + /* + * Now the entry is in [start, start + len), revert the + * EXTENT_QGROUP_RESERVED bit. + */ + clear_ret = clear_extent_bits(&inode->io_tree, entry_start, + entry_end, EXTENT_QGROUP_RESERVED); + if (!ret && clear_ret < 0) + ret = clear_ret; + + ulist_del(&reserved->range_changed, entry->val, entry->aux); + if (likely(reserved->bytes_changed >= entry_len)) { + reserved->bytes_changed -= entry_len; + } else { + WARN_ON(1); + reserved->bytes_changed = 0; + } + } + + return ret; +} + /* - * Reserve qgroup space for range [start, start + len). + * Try to free some space for qgroup. * - * This function will either reserve space from related qgroups or doing - * nothing if the range is already reserved. + * For qgroup, there are only 3 ways to free qgroup space: + * - Flush nodatacow write + * Any nodatacow write will free its reserved data space at run_delalloc_range(). + * In theory, we should only flush nodatacow inodes, but it's not yet + * possible, so we need to flush the whole root. * - * Return 0 for successful reserve - * Return <0 for error (including -EQUOT) + * - Wait for ordered extents + * When ordered extents are finished, their reserved metadata is finally + * converted to per_trans status, which can be freed by later commit + * transaction. * - * NOTE: this function may sleep for memory allocation. - * if btrfs_qgroup_reserve_data() is called multiple times with - * same @reserved, caller must ensure when error happens it's OK - * to free *ALL* reserved space. + * - Commit transaction + * This would free the meta_per_trans space. + * In theory this shouldn't provide much space, but any more qgroup space + * is needed. */ -int btrfs_qgroup_reserve_data(struct inode *inode, +static int try_flush_qgroup(struct btrfs_root *root) +{ + struct btrfs_trans_handle *trans; + int ret; + + /* + * We don't want to run flush again and again, so if there is a running + * one, we won't try to start a new flush, but exit directly. + */ + if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) { + wait_event(root->qgroup_flush_wait, + !test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)); + return 0; + } + + ret = btrfs_start_delalloc_snapshot(root); + if (ret < 0) + goto out; + btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1); + + trans = btrfs_join_transaction(root); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto out; + } + + ret = btrfs_commit_transaction(trans); +out: + clear_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state); + wake_up(&root->qgroup_flush_wait); + return ret; +} + +static int qgroup_reserve_data(struct btrfs_inode *inode, struct extent_changeset **reserved_ret, u64 start, u64 len) { - struct btrfs_root *root = BTRFS_I(inode)->root; - struct ulist_node *unode; - struct ulist_iterator uiter; + struct btrfs_root *root = inode->root; struct extent_changeset *reserved; + bool new_reserved = false; u64 orig_reserved; u64 to_reserve; int ret; @@ -3412,6 +3546,7 @@ int btrfs_qgroup_reserve_data(struct inode *inode, if (WARN_ON(!reserved_ret)) return -EINVAL; if (!*reserved_ret) { + new_reserved = true; *reserved_ret = extent_changeset_alloc(); if (!*reserved_ret) return -ENOMEM; @@ -3419,15 +3554,15 @@ int btrfs_qgroup_reserve_data(struct inode *inode, reserved = *reserved_ret; /* Record already reserved space */ orig_reserved = reserved->bytes_changed; - ret = set_record_extent_bits(&BTRFS_I(inode)->io_tree, start, + ret = set_record_extent_bits(&inode->io_tree, start, start + len -1, EXTENT_QGROUP_RESERVED, reserved); /* Newly reserved space */ to_reserve = reserved->bytes_changed - orig_reserved; - trace_btrfs_qgroup_reserve_data(inode, start, len, + trace_btrfs_qgroup_reserve_data(&inode->vfs_inode, start, len, to_reserve, QGROUP_RESERVE); if (ret < 0) - goto cleanup; + goto out; ret = qgroup_reserve(root, to_reserve, true, BTRFS_QGROUP_RSV_DATA); if (ret < 0) goto cleanup; @@ -3435,23 +3570,49 @@ int btrfs_qgroup_reserve_data(struct inode *inode, return ret; cleanup: - /* cleanup *ALL* already reserved ranges */ - ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(&reserved->range_changed, &uiter))) - clear_extent_bit(&BTRFS_I(inode)->io_tree, unode->val, - unode->aux, EXTENT_QGROUP_RESERVED, 0, 0, NULL); - /* Also free data bytes of already reserved one */ - btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, - orig_reserved, BTRFS_QGROUP_RSV_DATA); - extent_changeset_release(reserved); + qgroup_unreserve_range(inode, reserved, start, len); +out: + if (new_reserved) { + extent_changeset_release(reserved); + kfree(reserved); + *reserved_ret = NULL; + } return ret; } +/* + * Reserve qgroup space for range [start, start + len). + * + * This function will either reserve space from related qgroups or do nothing + * if the range is already reserved. + * + * Return 0 for successful reservation + * Return <0 for error (including -EQUOT) + * + * NOTE: This function may sleep for memory allocation, dirty page flushing and + * commit transaction. So caller should not hold any dirty page locked. + */ +int btrfs_qgroup_reserve_data(struct btrfs_inode *inode, + struct extent_changeset **reserved_ret, u64 start, + u64 len) +{ + int ret; + + ret = qgroup_reserve_data(inode, reserved_ret, start, len); + if (ret <= 0 && ret != -EDQUOT) + return ret; + + ret = try_flush_qgroup(inode->root); + if (ret < 0) + return ret; + return qgroup_reserve_data(inode, reserved_ret, start, len); +} + /* Free ranges specified by @reserved, normally in error path */ -static int qgroup_free_reserved_data(struct inode *inode, +static int qgroup_free_reserved_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len) { - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_root *root = inode->root; struct ulist_node *unode; struct ulist_iterator uiter; struct extent_changeset changeset; @@ -3487,8 +3648,8 @@ static int qgroup_free_reserved_data(struct inode *inode, * EXTENT_QGROUP_RESERVED, we won't double free. * So not need to rush. */ - ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, - free_start, free_start + free_len - 1, + ret = clear_record_extent_bits(&inode->io_tree, free_start, + free_start + free_len - 1, EXTENT_QGROUP_RESERVED, &changeset); if (ret < 0) goto out; @@ -3502,7 +3663,7 @@ out: return ret; } -static int __btrfs_qgroup_release_data(struct inode *inode, +static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len, int free) { @@ -3510,8 +3671,7 @@ static int __btrfs_qgroup_release_data(struct inode *inode, int trace_op = QGROUP_RELEASE; int ret; - if (!test_bit(BTRFS_FS_QUOTA_ENABLED, - &BTRFS_I(inode)->root->fs_info->flags)) + if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &inode->root->fs_info->flags)) return 0; /* In release case, we shouldn't have @reserved */ @@ -3519,18 +3679,18 @@ static int __btrfs_qgroup_release_data(struct inode *inode, if (free && reserved) return qgroup_free_reserved_data(inode, reserved, start, len); extent_changeset_init(&changeset); - ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, start, - start + len -1, EXTENT_QGROUP_RESERVED, &changeset); + ret = clear_record_extent_bits(&inode->io_tree, start, start + len -1, + EXTENT_QGROUP_RESERVED, &changeset); if (ret < 0) goto out; if (free) trace_op = QGROUP_FREE; - trace_btrfs_qgroup_release_data(inode, start, len, + trace_btrfs_qgroup_release_data(&inode->vfs_inode, start, len, changeset.bytes_changed, trace_op); if (free) - btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info, - BTRFS_I(inode)->root->root_key.objectid, + btrfs_qgroup_free_refroot(inode->root->fs_info, + inode->root->root_key.objectid, changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA); ret = changeset.bytes_changed; out: @@ -3550,7 +3710,7 @@ out: * * NOTE: This function may sleep for memory allocation. */ -int btrfs_qgroup_free_data(struct inode *inode, +int btrfs_qgroup_free_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len) { return __btrfs_qgroup_release_data(inode, reserved, start, len, 1); @@ -3571,7 +3731,7 @@ int btrfs_qgroup_free_data(struct inode *inode, * * NOTE: This function may sleep for memory allocation. */ -int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len) +int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len) { return __btrfs_qgroup_release_data(inode, NULL, start, len, 0); } @@ -3616,7 +3776,7 @@ static int sub_root_meta_rsv(struct btrfs_root *root, int num_bytes, return num_bytes; } -int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, +static int qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type, bool enforce) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -3643,6 +3803,21 @@ int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, return ret; } +int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, + enum btrfs_qgroup_rsv_type type, bool enforce) +{ + int ret; + + ret = qgroup_reserve_meta(root, num_bytes, type, enforce); + if (ret <= 0 && ret != -EDQUOT) + return ret; + + ret = try_flush_qgroup(root); + if (ret < 0) + return ret; + return qgroup_reserve_meta(root, num_bytes, type, enforce); +} + void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -3742,7 +3917,7 @@ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes) * Check qgroup reserved space leaking, normally at destroy inode * time */ -void btrfs_qgroup_check_reserved_leak(struct inode *inode) +void btrfs_qgroup_check_reserved_leak(struct btrfs_inode *inode) { struct extent_changeset changeset; struct ulist_node *unode; @@ -3750,19 +3925,19 @@ void btrfs_qgroup_check_reserved_leak(struct inode *inode) int ret; extent_changeset_init(&changeset); - ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, 0, (u64)-1, + ret = clear_record_extent_bits(&inode->io_tree, 0, (u64)-1, EXTENT_QGROUP_RESERVED, &changeset); WARN_ON(ret < 0); if (WARN_ON(changeset.bytes_changed)) { ULIST_ITER_INIT(&iter); while ((unode = ulist_next(&changeset.range_changed, &iter))) { - btrfs_warn(BTRFS_I(inode)->root->fs_info, - "leaking qgroup reserved space, ino: %lu, start: %llu, end: %llu", - inode->i_ino, unode->val, unode->aux); + btrfs_warn(inode->root->fs_info, + "leaking qgroup reserved space, ino: %llu, start: %llu, end: %llu", + btrfs_ino(inode), unode->val, unode->aux); } - btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info, - BTRFS_I(inode)->root->root_key.objectid, + btrfs_qgroup_free_refroot(inode->root->fs_info, + inode->root->root_key.objectid, changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA); } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 1bc654459469..50dea9a2d8fb 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -8,6 +8,7 @@ #include <linux/spinlock.h> #include <linux/rbtree.h> +#include <linux/kobject.h> #include "ulist.h" #include "delayed-ref.h" @@ -223,8 +224,18 @@ struct btrfs_qgroup { */ u64 old_refcnt; u64 new_refcnt; + + /* + * Sysfs kobjectid + */ + struct kobject kobj; }; +static inline u64 btrfs_qgroup_subvolid(u64 qgroupid) +{ + return (qgroupid & ((1ULL << BTRFS_QGROUP_LEVEL_SHIFT) - 1)); +} + /* * For qgroup event trace points only */ @@ -344,12 +355,12 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid, #endif /* New io_tree based accurate qgroup reserve API */ -int btrfs_qgroup_reserve_data(struct inode *inode, +int btrfs_qgroup_reserve_data(struct btrfs_inode *inode, struct extent_changeset **reserved, u64 start, u64 len); -int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len); -int btrfs_qgroup_free_data(struct inode *inode, - struct extent_changeset *reserved, u64 start, u64 len); - +int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len); +int btrfs_qgroup_free_data(struct btrfs_inode *inode, + struct extent_changeset *reserved, u64 start, + u64 len); int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type, bool enforce); /* Reserve metadata space for pertrans and prealloc type */ @@ -399,7 +410,7 @@ void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root); */ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes); -void btrfs_qgroup_check_reserved_leak(struct inode *inode); +void btrfs_qgroup_check_reserved_leak(struct btrfs_inode *inode); /* btrfs_qgroup_swapped_blocks related functions */ void btrfs_qgroup_init_swapped_blocks( @@ -415,5 +426,6 @@ int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans, int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *eb); void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans); +bool btrfs_check_quota_leak(struct btrfs_fs_info *fs_info); #endif diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index c870ef70f817..255490f42b5d 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1083,7 +1083,6 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, unsigned long bio_max_len) { struct bio *last = bio_list->tail; - u64 last_end = 0; int ret; struct bio *bio; struct btrfs_bio_stripe *stripe; @@ -1098,15 +1097,14 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, /* see if we can add this page onto our existing bio */ if (last) { - last_end = (u64)last->bi_iter.bi_sector << 9; + u64 last_end = (u64)last->bi_iter.bi_sector << 9; last_end += last->bi_iter.bi_size; /* * we can't merge these if they are from different * devices or if they are not contiguous */ - if (last_end == disk_start && stripe->dev->bdev && - !last->bi_status && + if (last_end == disk_start && !last->bi_status && last->bi_disk == stripe->dev->bdev->bd_disk && last->bi_partno == stripe->dev->bdev->bd_partno) { ret = bio_add_page(last, page, PAGE_SIZE, 0); @@ -1117,6 +1115,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, /* put a new bio on the list */ bio = btrfs_io_bio_alloc(bio_max_len >> PAGE_SHIFT ?: 1); + btrfs_io_bio(bio)->device = stripe->dev; bio->bi_iter.bi_size = 0; bio_set_dev(bio, stripe->dev->bdev); bio->bi_iter.bi_sector = disk_start >> 9; @@ -1325,11 +1324,7 @@ write_data: atomic_set(&rbio->stripes_pending, bio_list_size(&bio_list)); BUG_ON(atomic_read(&rbio->stripes_pending) == 0); - while (1) { - bio = bio_list_pop(&bio_list); - if (!bio) - break; - + while ((bio = bio_list_pop(&bio_list))) { bio->bi_private = rbio; bio->bi_end_io = raid_write_end_io; bio->bi_opf = REQ_OP_WRITE; @@ -1354,7 +1349,6 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio, struct bio *bio) { u64 physical = bio->bi_iter.bi_sector; - u64 stripe_start; int i; struct btrfs_bio_stripe *stripe; @@ -1362,9 +1356,7 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio, for (i = 0; i < rbio->bbio->num_stripes; i++) { stripe = &rbio->bbio->stripes[i]; - stripe_start = stripe->physical; - if (physical >= stripe_start && - physical < stripe_start + rbio->stripe_len && + if (in_range(physical, stripe->physical, rbio->stripe_len) && stripe->dev->bdev && bio->bi_disk == stripe->dev->bdev->bd_disk && bio->bi_partno == stripe->dev->bdev->bd_partno) { @@ -1382,18 +1374,14 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio, static int find_logical_bio_stripe(struct btrfs_raid_bio *rbio, struct bio *bio) { - u64 logical = bio->bi_iter.bi_sector; - u64 stripe_start; + u64 logical = (u64)bio->bi_iter.bi_sector << 9; int i; - logical <<= 9; - for (i = 0; i < rbio->nr_data; i++) { - stripe_start = rbio->bbio->raid_map[i]; - if (logical >= stripe_start && - logical < stripe_start + rbio->stripe_len) { + u64 stripe_start = rbio->bbio->raid_map[i]; + + if (in_range(logical, stripe_start, rbio->stripe_len)) return i; - } } return -1; } @@ -1567,11 +1555,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio) * not to touch it after that */ atomic_set(&rbio->stripes_pending, bios_to_read); - while (1) { - bio = bio_list_pop(&bio_list); - if (!bio) - break; - + while ((bio = bio_list_pop(&bio_list))) { bio->bi_private = rbio; bio->bi_end_io = raid_rmw_end_io; bio->bi_opf = REQ_OP_READ; @@ -1878,11 +1862,8 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) } /* make sure our ps and qs are in order */ - if (faila > failb) { - int tmp = failb; - failb = faila; - faila = tmp; - } + if (faila > failb) + swap(faila, failb); /* if the q stripe is failed, do a pstripe reconstruction * from the xors. @@ -2102,7 +2083,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) */ if (atomic_read(&rbio->error) <= rbio->bbio->max_errors) { __raid_recover_end_io(rbio); - goto out; + return 0; } else { goto cleanup; } @@ -2113,11 +2094,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) * not to touch it after that */ atomic_set(&rbio->stripes_pending, bios_to_read); - while (1) { - bio = bio_list_pop(&bio_list); - if (!bio) - break; - + while ((bio = bio_list_pop(&bio_list))) { bio->bi_private = rbio; bio->bi_end_io = raid_recover_end_io; bio->bi_opf = REQ_OP_READ; @@ -2126,7 +2103,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) submit_bio(bio); } -out: + return 0; cleanup: @@ -2482,11 +2459,7 @@ submit_write: atomic_set(&rbio->stripes_pending, nr_data); - while (1) { - bio = bio_list_pop(&bio_list); - if (!bio) - break; - + while ((bio = bio_list_pop(&bio_list))) { bio->bi_private = rbio; bio->bi_end_io = raid_write_end_io; bio->bi_opf = REQ_OP_WRITE; @@ -2664,11 +2637,7 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio) * not to touch it after that */ atomic_set(&rbio->stripes_pending, bios_to_read); - while (1) { - bio = bio_list_pop(&bio_list); - if (!bio) - break; - + while ((bio = bio_list_pop(&bio_list))) { bio->bi_private = rbio; bio->bi_end_io = raid56_parity_scrub_end_io; bio->bi_opf = REQ_OP_READ; diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index af92525dbb16..7f03dbe5b609 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -286,6 +286,8 @@ static struct block_entry *add_block_entry(struct btrfs_fs_info *fs_info, exist_re = insert_root_entry(&exist->roots, re); if (exist_re) kfree(re); + } else { + kfree(re); } kfree(be); return exist; diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index 040009d1cc31..5cd02514cf4d 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -68,8 +68,8 @@ static int copy_inline_to_page(struct inode *inode, * reservation here. Also we must not do the reservation while holding * a transaction open, otherwise we would deadlock. */ - ret = btrfs_delalloc_reserve_space(inode, &data_reserved, file_offset, - block_size); + ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved, + file_offset, block_size); if (ret) goto out; @@ -84,7 +84,8 @@ static int copy_inline_to_page(struct inode *inode, clear_extent_bit(&BTRFS_I(inode)->io_tree, file_offset, range_end, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, NULL); - ret = btrfs_set_extent_delalloc(inode, file_offset, range_end, 0, NULL); + ret = btrfs_set_extent_delalloc(BTRFS_I(inode), file_offset, range_end, + 0, NULL); if (ret) goto out_unlock; @@ -133,8 +134,8 @@ out_unlock: put_page(page); } if (ret) - btrfs_delalloc_release_space(inode, data_reserved, file_offset, - block_size, true); + btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, + file_offset, block_size, true); btrfs_delalloc_release_extents(BTRFS_I(inode), block_size); out: extent_changeset_free(data_reserved); @@ -336,6 +337,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode, while (1) { u64 next_key_min_offset = key.offset + 1; struct btrfs_file_extent_item *extent; + u64 extent_gen; int type; u32 size; struct btrfs_key new_key; @@ -384,6 +386,7 @@ process_slot: extent = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); + extent_gen = btrfs_file_extent_generation(leaf, extent); comp = btrfs_file_extent_compression(leaf, extent); type = btrfs_file_extent_type(leaf, extent); if (type == BTRFS_FILE_EXTENT_REG || @@ -488,6 +491,19 @@ process_slot: btrfs_release_path(path); + /* + * If this is a new extent update the last_reflink_trans of both + * inodes. This is used by fsync to make sure it does not log + * multiple checksum items with overlapping ranges. For older + * extents we don't need to do it since inode logging skips the + * checksums for older extents. Also ignore holes and inline + * extents because they don't have checksums in the csum tree. + */ + if (extent_gen == trans->transid && disko > 0) { + BTRFS_I(src)->last_reflink_trans = trans->transid; + BTRFS_I(inode)->last_reflink_trans = trans->transid; + } + last_dest_end = ALIGN(new_key.offset + datal, fs_info->sectorsize); ret = clone_finish_inode_update(trans, inode, last_dest_end, diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 3bbae80c752f..4ba1ab9cc76d 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1686,12 +1686,20 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, btrfs_unlock_up_safe(path, 0); } - min_reserved = fs_info->nodesize * (BTRFS_MAX_LEVEL - 1) * 2; + /* + * In merge_reloc_root(), we modify the upper level pointer to swap the + * tree blocks between reloc tree and subvolume tree. Thus for tree + * block COW, we COW at most from level 1 to root level for each tree. + * + * Thus the needed metadata size is at most root_level * nodesize, + * and * 2 since we have two trees to COW. + */ + min_reserved = fs_info->nodesize * btrfs_root_level(root_item) * 2; memset(&next_key, 0, sizeof(next_key)); while (1) { ret = btrfs_block_rsv_refill(root, rc->block_rsv, min_reserved, - BTRFS_RESERVE_FLUSH_ALL); + BTRFS_RESERVE_FLUSH_LIMIT); if (ret) { err = ret; goto out; @@ -2571,58 +2579,50 @@ out_free_blocks: return err; } -static noinline_for_stack -int prealloc_file_extent_cluster(struct inode *inode, - struct file_extent_cluster *cluster) +static noinline_for_stack int prealloc_file_extent_cluster( + struct btrfs_inode *inode, + struct file_extent_cluster *cluster) { u64 alloc_hint = 0; u64 start; u64 end; - u64 offset = BTRFS_I(inode)->index_cnt; + u64 offset = inode->index_cnt; u64 num_bytes; - int nr = 0; + int nr; int ret = 0; u64 prealloc_start = cluster->start - offset; u64 prealloc_end = cluster->end - offset; - u64 cur_offset; - struct extent_changeset *data_reserved = NULL; + u64 cur_offset = prealloc_start; BUG_ON(cluster->start != cluster->boundary[0]); - inode_lock(inode); - - ret = btrfs_check_data_free_space(inode, &data_reserved, prealloc_start, - prealloc_end + 1 - prealloc_start); + ret = btrfs_alloc_data_chunk_ondemand(inode, + prealloc_end + 1 - prealloc_start); if (ret) - goto out; + return ret; - cur_offset = prealloc_start; - while (nr < cluster->nr) { + inode_lock(&inode->vfs_inode); + for (nr = 0; nr < cluster->nr; nr++) { start = cluster->boundary[nr] - offset; if (nr + 1 < cluster->nr) end = cluster->boundary[nr + 1] - 1 - offset; else end = cluster->end - offset; - lock_extent(&BTRFS_I(inode)->io_tree, start, end); + lock_extent(&inode->io_tree, start, end); num_bytes = end + 1 - start; - if (cur_offset < start) - btrfs_free_reserved_data_space(inode, data_reserved, - cur_offset, start - cur_offset); - ret = btrfs_prealloc_file_range(inode, 0, start, + ret = btrfs_prealloc_file_range(&inode->vfs_inode, 0, start, num_bytes, num_bytes, end + 1, &alloc_hint); cur_offset = end + 1; - unlock_extent(&BTRFS_I(inode)->io_tree, start, end); + unlock_extent(&inode->io_tree, start, end); if (ret) break; - nr++; } + inode_unlock(&inode->vfs_inode); + if (cur_offset < prealloc_end) - btrfs_free_reserved_data_space(inode, data_reserved, - cur_offset, prealloc_end + 1 - cur_offset); -out: - inode_unlock(inode); - extent_changeset_free(data_reserved); + btrfs_free_reserved_data_space_noquota(inode->root->fs_info, + prealloc_end + 1 - cur_offset); return ret; } @@ -2664,7 +2664,8 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end, */ int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info) { - return atomic_read(&fs_info->balance_cancel_req); + return atomic_read(&fs_info->balance_cancel_req) || + fatal_signal_pending(current); } ALLOW_ERROR_INJECTION(btrfs_should_cancel_balance, TRUE); @@ -2690,7 +2691,7 @@ static int relocate_file_extent_cluster(struct inode *inode, if (!ra) return -ENOMEM; - ret = prealloc_file_extent_cluster(inode, cluster); + ret = prealloc_file_extent_cluster(BTRFS_I(inode), cluster); if (ret) goto out; @@ -2762,8 +2763,8 @@ static int relocate_file_extent_cluster(struct inode *inode, nr++; } - ret = btrfs_set_extent_delalloc(inode, page_start, page_end, 0, - NULL); + ret = btrfs_set_extent_delalloc(BTRFS_I(inode), page_start, + page_end, 0, NULL); if (ret) { unlock_page(page); put_page(page); @@ -3872,9 +3873,9 @@ out: * cloning checksum properly handles the nodatasum extents. * it also saves CPU time to re-calculate the checksum. */ -int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len) +int btrfs_reloc_clone_csums(struct btrfs_inode *inode, u64 file_pos, u64 len) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_ordered_sum *sums; struct btrfs_ordered_extent *ordered; int ret; @@ -3885,7 +3886,7 @@ int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len) ordered = btrfs_lookup_ordered_extent(inode, file_pos); BUG_ON(ordered->file_offset != file_pos || ordered->num_bytes != len); - disk_bytenr = file_pos + BTRFS_I(inode)->index_cnt; + disk_bytenr = file_pos + inode->index_cnt; ret = btrfs_lookup_csums_range(fs_info->csum_root, disk_bytenr, disk_bytenr + len - 1, &list, 0); if (ret) diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 016a025e36c7..5a6cb9db512e 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1616,13 +1616,9 @@ static int scrub_write_page_to_dev_replace(struct scrub_block *sblock, struct scrub_page *spage = sblock->pagev[page_num]; BUG_ON(spage->page == NULL); - if (spage->io_error) { - void *mapped_buffer = kmap_atomic(spage->page); + if (spage->io_error) + clear_page(page_address(spage->page)); - clear_page(mapped_buffer); - flush_dcache_page(spage->page); - kunmap_atomic(mapped_buffer); - } return scrub_add_page_to_wr_bio(sblock->sctx, spage); } @@ -1790,42 +1786,21 @@ static int scrub_checksum_data(struct scrub_block *sblock) struct btrfs_fs_info *fs_info = sctx->fs_info; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); u8 csum[BTRFS_CSUM_SIZE]; - u8 *on_disk_csum; - struct page *page; - void *buffer; - u64 len; - int index; + struct scrub_page *spage; + char *kaddr; BUG_ON(sblock->page_count < 1); - if (!sblock->pagev[0]->have_csum) + spage = sblock->pagev[0]; + if (!spage->have_csum) return 0; + kaddr = page_address(spage->page); + shash->tfm = fs_info->csum_shash; crypto_shash_init(shash); + crypto_shash_digest(shash, kaddr, PAGE_SIZE, csum); - on_disk_csum = sblock->pagev[0]->csum; - page = sblock->pagev[0]->page; - buffer = kmap_atomic(page); - - len = sctx->fs_info->sectorsize; - index = 0; - for (;;) { - u64 l = min_t(u64, len, PAGE_SIZE); - - crypto_shash_update(shash, buffer, l); - kunmap_atomic(buffer); - len -= l; - if (len == 0) - break; - index++; - BUG_ON(index >= sblock->page_count); - BUG_ON(!sblock->pagev[index]->page); - page = sblock->pagev[index]->page; - buffer = kmap_atomic(page); - } - - crypto_shash_final(shash, csum); - if (memcmp(csum, on_disk_csum, sctx->csum_size)) + if (memcmp(csum, spage->csum, sctx->csum_size)) sblock->checksum_error = 1; return sblock->checksum_error; @@ -1839,20 +1814,15 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); u8 calculated_csum[BTRFS_CSUM_SIZE]; u8 on_disk_csum[BTRFS_CSUM_SIZE]; - struct page *page; - void *mapped_buffer; - u64 mapped_size; - void *p; - u64 len; - int index; - - shash->tfm = fs_info->csum_shash; - crypto_shash_init(shash); + const int num_pages = sctx->fs_info->nodesize >> PAGE_SHIFT; + int i; + struct scrub_page *spage; + char *kaddr; BUG_ON(sblock->page_count < 1); - page = sblock->pagev[0]->page; - mapped_buffer = kmap_atomic(page); - h = (struct btrfs_header *)mapped_buffer; + spage = sblock->pagev[0]; + kaddr = page_address(spage->page); + h = (struct btrfs_header *)kaddr; memcpy(on_disk_csum, h->csum, sctx->csum_size); /* @@ -1860,40 +1830,29 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) * a) don't have an extent buffer and * b) the page is already kmapped */ - if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h)) + if (spage->logical != btrfs_stack_header_bytenr(h)) sblock->header_error = 1; - if (sblock->pagev[0]->generation != btrfs_stack_header_generation(h)) { + if (spage->generation != btrfs_stack_header_generation(h)) { sblock->header_error = 1; sblock->generation_error = 1; } - if (!scrub_check_fsid(h->fsid, sblock->pagev[0])) + if (!scrub_check_fsid(h->fsid, spage)) sblock->header_error = 1; if (memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid, BTRFS_UUID_SIZE)) sblock->header_error = 1; - len = sctx->fs_info->nodesize - BTRFS_CSUM_SIZE; - mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE; - p = ((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE; - index = 0; - for (;;) { - u64 l = min_t(u64, len, mapped_size); + shash->tfm = fs_info->csum_shash; + crypto_shash_init(shash); + crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE, + PAGE_SIZE - BTRFS_CSUM_SIZE); - crypto_shash_update(shash, p, l); - kunmap_atomic(mapped_buffer); - len -= l; - if (len == 0) - break; - index++; - BUG_ON(index >= sblock->page_count); - BUG_ON(!sblock->pagev[index]->page); - page = sblock->pagev[index]->page; - mapped_buffer = kmap_atomic(page); - mapped_size = PAGE_SIZE; - p = mapped_buffer; + for (i = 1; i < num_pages; i++) { + kaddr = page_address(sblock->pagev[i]->page); + crypto_shash_update(shash, kaddr, PAGE_SIZE); } crypto_shash_final(shash, calculated_csum); @@ -1910,57 +1869,31 @@ static int scrub_checksum_super(struct scrub_block *sblock) struct btrfs_fs_info *fs_info = sctx->fs_info; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); u8 calculated_csum[BTRFS_CSUM_SIZE]; - u8 on_disk_csum[BTRFS_CSUM_SIZE]; - struct page *page; - void *mapped_buffer; - u64 mapped_size; - void *p; + struct scrub_page *spage; + char *kaddr; int fail_gen = 0; int fail_cor = 0; - u64 len; - int index; - - shash->tfm = fs_info->csum_shash; - crypto_shash_init(shash); BUG_ON(sblock->page_count < 1); - page = sblock->pagev[0]->page; - mapped_buffer = kmap_atomic(page); - s = (struct btrfs_super_block *)mapped_buffer; - memcpy(on_disk_csum, s->csum, sctx->csum_size); + spage = sblock->pagev[0]; + kaddr = page_address(spage->page); + s = (struct btrfs_super_block *)kaddr; - if (sblock->pagev[0]->logical != btrfs_super_bytenr(s)) + if (spage->logical != btrfs_super_bytenr(s)) ++fail_cor; - if (sblock->pagev[0]->generation != btrfs_super_generation(s)) + if (spage->generation != btrfs_super_generation(s)) ++fail_gen; - if (!scrub_check_fsid(s->fsid, sblock->pagev[0])) + if (!scrub_check_fsid(s->fsid, spage)) ++fail_cor; - len = BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE; - mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE; - p = ((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE; - index = 0; - for (;;) { - u64 l = min_t(u64, len, mapped_size); - - crypto_shash_update(shash, p, l); - kunmap_atomic(mapped_buffer); - len -= l; - if (len == 0) - break; - index++; - BUG_ON(index >= sblock->page_count); - BUG_ON(!sblock->pagev[index]->page); - page = sblock->pagev[index]->page; - mapped_buffer = kmap_atomic(page); - mapped_size = PAGE_SIZE; - p = mapped_buffer; - } + shash->tfm = fs_info->csum_shash; + crypto_shash_init(shash); + crypto_shash_digest(shash, kaddr + BTRFS_CSUM_SIZE, + BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, calculated_csum); - crypto_shash_final(shash, calculated_csum); - if (memcmp(calculated_csum, on_disk_csum, sctx->csum_size)) + if (memcmp(calculated_csum, s->csum, sctx->csum_size)) ++fail_cor; if (fail_cor + fail_gen) { @@ -1973,10 +1906,10 @@ static int scrub_checksum_super(struct scrub_block *sblock) ++sctx->stat.super_errors; spin_unlock(&sctx->stat_lock); if (fail_cor) - btrfs_dev_stat_inc_and_print(sblock->pagev[0]->dev, + btrfs_dev_stat_inc_and_print(spage->dev, BTRFS_DEV_STAT_CORRUPTION_ERRS); else - btrfs_dev_stat_inc_and_print(sblock->pagev[0]->dev, + btrfs_dev_stat_inc_and_print(spage->dev, BTRFS_DEV_STAT_GENERATION_ERRS); } @@ -3758,7 +3691,7 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx, struct btrfs_fs_info *fs_info = sctx->fs_info; if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) - return -EIO; + return -EROFS; /* Seed devices of a new filesystem has their own generation. */ if (scrub_dev->fs_devices != fs_info->fs_devices) diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index c7bd3fdd7792..475968ccbd1d 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -468,8 +468,8 @@ again: "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s", cache->start, cache->length, cache->used, cache->pinned, cache->reserved, cache->ro ? "[readonly]" : ""); - btrfs_dump_free_space(cache, bytes); spin_unlock(&cache->lock); + btrfs_dump_free_space(cache, bytes); } if (++index < BTRFS_NR_RAID_TYPES) goto again; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index c3826ae883f0..5a9dc31d95c9 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -67,6 +67,21 @@ static struct file_system_type btrfs_root_fs_type; static int btrfs_remount(struct super_block *sb, int *flags, char *data); +/* + * Generally the error codes correspond to their respective errors, but there + * are a few special cases. + * + * EUCLEAN: Any sort of corruption that we encounter. The tree-checker for + * instance will return EUCLEAN if any of the blocks are corrupted in + * a way that is problematic. We want to reserve EUCLEAN for these + * sort of corruptions. + * + * EROFS: If we check BTRFS_FS_STATE_ERROR and fail out with a return error, we + * need to use EROFS for this case. We will have no idea of the + * original failure, that will have been reported at the time we tripped + * over the error. Each subsequent error that doesn't have any context + * of the original error should use EROFS when handling BTRFS_FS_STATE_ERROR. + */ const char * __attribute_const__ btrfs_decode_error(int errno) { char *errstr = "unknown"; @@ -326,7 +341,6 @@ enum { Opt_defrag, Opt_nodefrag, Opt_discard, Opt_nodiscard, Opt_discard_mode, - Opt_nologreplay, Opt_norecovery, Opt_ratio, Opt_rescan_uuid_tree, @@ -340,13 +354,15 @@ enum { Opt_subvolid, Opt_thread_pool, Opt_treelog, Opt_notreelog, - Opt_usebackuproot, Opt_user_subvol_rm_allowed, + /* Rescue options */ + Opt_rescue, + Opt_usebackuproot, + Opt_nologreplay, + /* Deprecated options */ - Opt_alloc_start, Opt_recovery, - Opt_subvolrootid, /* Debugging options */ Opt_check_integrity, @@ -390,7 +406,6 @@ static const match_table_t tokens = { {Opt_discard, "discard"}, {Opt_discard_mode, "discard=%s"}, {Opt_nodiscard, "nodiscard"}, - {Opt_nologreplay, "nologreplay"}, {Opt_norecovery, "norecovery"}, {Opt_ratio, "metadata_ratio=%u"}, {Opt_rescan_uuid_tree, "rescan_uuid_tree"}, @@ -408,13 +423,17 @@ static const match_table_t tokens = { {Opt_thread_pool, "thread_pool=%u"}, {Opt_treelog, "treelog"}, {Opt_notreelog, "notreelog"}, - {Opt_usebackuproot, "usebackuproot"}, {Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"}, + /* Rescue options */ + {Opt_rescue, "rescue=%s"}, + /* Deprecated, with alias rescue=nologreplay */ + {Opt_nologreplay, "nologreplay"}, + /* Deprecated, with alias rescue=usebackuproot */ + {Opt_usebackuproot, "usebackuproot"}, + /* Deprecated options */ - {Opt_alloc_start, "alloc_start=%s"}, {Opt_recovery, "recovery"}, - {Opt_subvolrootid, "subvolrootid=%d"}, /* Debugging options */ {Opt_check_integrity, "check_int"}, @@ -433,6 +452,55 @@ static const match_table_t tokens = { {Opt_err, NULL}, }; +static const match_table_t rescue_tokens = { + {Opt_usebackuproot, "usebackuproot"}, + {Opt_nologreplay, "nologreplay"}, + {Opt_err, NULL}, +}; + +static int parse_rescue_options(struct btrfs_fs_info *info, const char *options) +{ + char *opts; + char *orig; + char *p; + substring_t args[MAX_OPT_ARGS]; + int ret = 0; + + opts = kstrdup(options, GFP_KERNEL); + if (!opts) + return -ENOMEM; + orig = opts; + + while ((p = strsep(&opts, ":")) != NULL) { + int token; + + if (!*p) + continue; + token = match_token(p, rescue_tokens, args); + switch (token){ + case Opt_usebackuproot: + btrfs_info(info, + "trying to use backup root at mount time"); + btrfs_set_opt(info->mount_opt, USEBACKUPROOT); + break; + case Opt_nologreplay: + btrfs_set_and_info(info, NOLOGREPLAY, + "disabling log replay at mount time"); + break; + case Opt_err: + btrfs_info(info, "unrecognized rescue option '%s'", p); + ret = -EINVAL; + goto out; + default: + break; + } + + } +out: + kfree(orig); + return ret; +} + /* * Regular mount options parser. Everything that is needed only when * reading in a new superblock is parsed here. @@ -479,7 +547,6 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, case Opt_subvol: case Opt_subvol_empty: case Opt_subvolid: - case Opt_subvolrootid: case Opt_device: /* * These are parsed by btrfs_parse_subvol_options or @@ -663,10 +730,6 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, goto out; } break; - case Opt_alloc_start: - btrfs_info(info, - "option alloc_start is obsolete, ignored"); - break; case Opt_acl: #ifdef CONFIG_BTRFS_FS_POSIX_ACL info->sb->s_flags |= SB_POSIXACL; @@ -689,6 +752,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, break; case Opt_norecovery: case Opt_nologreplay: + btrfs_warn(info, + "'nologreplay' is deprecated, use 'rescue=nologreplay' instead"); btrfs_set_and_info(info, NOLOGREPLAY, "disabling log replay at mount time"); break; @@ -762,6 +827,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, } break; case Opt_inode_cache: + btrfs_warn(info, + "the 'inode_cache' option is deprecated and will have no effect from 5.11"); btrfs_set_pending_and_info(info, INODE_MAP_CACHE, "enabling inode map caching"); break; @@ -791,10 +858,11 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, "disabling auto defrag"); break; case Opt_recovery: - btrfs_warn(info, - "'recovery' is deprecated, use 'usebackuproot' instead"); - fallthrough; case Opt_usebackuproot: + btrfs_warn(info, + "'%s' is deprecated, use 'rescue=usebackuproot' instead", + token == Opt_recovery ? "recovery" : + "usebackuproot"); btrfs_info(info, "trying to use backup root at mount time"); btrfs_set_opt(info->mount_opt, USEBACKUPROOT); @@ -859,6 +927,11 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, } info->commit_interval = intarg; break; + case Opt_rescue: + ret = parse_rescue_options(info, args[0].from); + if (ret < 0) + goto out; + break; #ifdef CONFIG_BTRFS_DEBUG case Opt_fragment_all: btrfs_info(info, "fragmenting all space"); @@ -1020,9 +1093,6 @@ static int btrfs_parse_subvol_options(const char *options, char **subvol_name, *subvol_objectid = subvolid; break; - case Opt_subvolrootid: - pr_warn("BTRFS: 'subvolrootid' mount option is deprecated and has no effect\n"); - break; default: break; } @@ -1344,7 +1414,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) if (btrfs_test_opt(info, NOTREELOG)) seq_puts(seq, ",notreelog"); if (btrfs_test_opt(info, NOLOGREPLAY)) - seq_puts(seq, ",nologreplay"); + seq_puts(seq, ",rescue=nologreplay"); if (btrfs_test_opt(info, FLUSHONCOMMIT)) seq_puts(seq, ",flushoncommit"); if (btrfs_test_opt(info, DISCARD_SYNC)) @@ -1712,11 +1782,6 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info, new_pool_size); } -static inline void btrfs_remount_prepare(struct btrfs_fs_info *fs_info) -{ - set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state); -} - static inline void btrfs_remount_begin(struct btrfs_fs_info *fs_info, unsigned long old_opts, int flags) { @@ -1750,8 +1815,6 @@ static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info, else if (btrfs_raw_test_opt(old_opts, DISCARD_ASYNC) && !btrfs_test_opt(fs_info, DISCARD_ASYNC)) btrfs_discard_cleanup(fs_info); - - clear_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state); } static int btrfs_remount(struct super_block *sb, int *flags, char *data) @@ -1767,7 +1830,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) int ret; sync_filesystem(sb); - btrfs_remount_prepare(fs_info); + set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state); if (data) { void *new_sec_opts = NULL; @@ -1889,6 +1952,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) out: wake_up_process(fs_info->transaction_kthread); btrfs_remount_cleanup(fs_info, old_opts); + clear_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state); + return 0; restore: @@ -1903,6 +1968,8 @@ restore: old_thread_pool_size, fs_info->thread_pool_size); fs_info->metadata_ratio = old_metadata_ratio; btrfs_remount_cleanup(fs_info, old_opts); + clear_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state); + return ret; } @@ -2296,9 +2363,7 @@ static int btrfs_unfreeze(struct super_block *sb) static int btrfs_show_devname(struct seq_file *m, struct dentry *root) { struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb); - struct btrfs_fs_devices *cur_devices; struct btrfs_device *dev, *first_dev = NULL; - struct list_head *head; /* * Lightweight locking of the devices. We should not need @@ -2308,18 +2373,13 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root) * least until the rcu_read_unlock. */ rcu_read_lock(); - cur_devices = fs_info->fs_devices; - while (cur_devices) { - head = &cur_devices->devices; - list_for_each_entry_rcu(dev, head, dev_list) { - if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) - continue; - if (!dev->name) - continue; - if (!first_dev || dev->devid < first_dev->devid) - first_dev = dev; - } - cur_devices = cur_devices->seed; + list_for_each_entry_rcu(dev, &fs_info->fs_devices->devices, dev_list) { + if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) + continue; + if (!dev->name) + continue; + if (!first_dev || dev->devid < first_dev->devid) + first_dev = dev; } if (first_dev) diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index a39bff64ff24..104c80caaa74 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -19,6 +19,7 @@ #include "volumes.h" #include "space-info.h" #include "block-group.h" +#include "qgroup.h" struct btrfs_feature_attr { struct kobj_attribute kobj_attr; @@ -936,8 +937,12 @@ void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs) void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info) { + struct kobject *fsid_kobj = &fs_info->fs_devices->fsid_kobj; + btrfs_reset_fs_info_ptr(fs_info); + sysfs_remove_link(fsid_kobj, "bdi"); + if (fs_info->space_info_kobj) { sysfs_remove_files(fs_info->space_info_kobj, allocation_attrs); kobject_del(fs_info->space_info_kobj); @@ -957,8 +962,8 @@ void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info) } #endif addrm_unknown_feature_attrs(fs_info, false); - sysfs_remove_group(&fs_info->fs_devices->fsid_kobj, &btrfs_feature_attr_group); - sysfs_remove_files(&fs_info->fs_devices->fsid_kobj, btrfs_attrs); + sysfs_remove_group(fsid_kobj, &btrfs_feature_attr_group); + sysfs_remove_files(fsid_kobj, btrfs_attrs); btrfs_sysfs_remove_devices_dir(fs_info->fs_devices, NULL); } @@ -1273,7 +1278,9 @@ int btrfs_sysfs_add_devices_dir(struct btrfs_fs_devices *fs_devices, { int error = 0; struct btrfs_device *dev; + unsigned int nofs_flag; + nofs_flag = memalloc_nofs_save(); list_for_each_entry(dev, &fs_devices->devices, dev_list) { if (one_device && one_device != dev) @@ -1301,6 +1308,7 @@ int btrfs_sysfs_add_devices_dir(struct btrfs_fs_devices *fs_devices, break; } } + memalloc_nofs_restore(nofs_flag); return error; } @@ -1438,6 +1446,10 @@ int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info) if (error) goto failure; + error = sysfs_create_link(fsid_kobj, &fs_info->sb->s_bdi->dev->kobj, "bdi"); + if (error) + goto failure; + fs_info->space_info_kobj = kobject_create_and_add("allocation", fsid_kobj); if (!fs_info->space_info_kobj) { @@ -1455,6 +1467,153 @@ failure: return error; } +static inline struct btrfs_fs_info *qgroup_kobj_to_fs_info(struct kobject *kobj) +{ + return to_fs_info(kobj->parent->parent); +} + +#define QGROUP_ATTR(_member, _show_name) \ +static ssize_t btrfs_qgroup_show_##_member(struct kobject *qgroup_kobj, \ + struct kobj_attribute *a, \ + char *buf) \ +{ \ + struct btrfs_fs_info *fs_info = qgroup_kobj_to_fs_info(qgroup_kobj); \ + struct btrfs_qgroup *qgroup = container_of(qgroup_kobj, \ + struct btrfs_qgroup, kobj); \ + return btrfs_show_u64(&qgroup->_member, &fs_info->qgroup_lock, buf); \ +} \ +BTRFS_ATTR(qgroup, _show_name, btrfs_qgroup_show_##_member) + +#define QGROUP_RSV_ATTR(_name, _type) \ +static ssize_t btrfs_qgroup_rsv_show_##_name(struct kobject *qgroup_kobj, \ + struct kobj_attribute *a, \ + char *buf) \ +{ \ + struct btrfs_fs_info *fs_info = qgroup_kobj_to_fs_info(qgroup_kobj); \ + struct btrfs_qgroup *qgroup = container_of(qgroup_kobj, \ + struct btrfs_qgroup, kobj); \ + return btrfs_show_u64(&qgroup->rsv.values[_type], \ + &fs_info->qgroup_lock, buf); \ +} \ +BTRFS_ATTR(qgroup, rsv_##_name, btrfs_qgroup_rsv_show_##_name) + +QGROUP_ATTR(rfer, referenced); +QGROUP_ATTR(excl, exclusive); +QGROUP_ATTR(max_rfer, max_referenced); +QGROUP_ATTR(max_excl, max_exclusive); +QGROUP_ATTR(lim_flags, limit_flags); +QGROUP_RSV_ATTR(data, BTRFS_QGROUP_RSV_DATA); +QGROUP_RSV_ATTR(meta_pertrans, BTRFS_QGROUP_RSV_META_PERTRANS); +QGROUP_RSV_ATTR(meta_prealloc, BTRFS_QGROUP_RSV_META_PREALLOC); + +static struct attribute *qgroup_attrs[] = { + BTRFS_ATTR_PTR(qgroup, referenced), + BTRFS_ATTR_PTR(qgroup, exclusive), + BTRFS_ATTR_PTR(qgroup, max_referenced), + BTRFS_ATTR_PTR(qgroup, max_exclusive), + BTRFS_ATTR_PTR(qgroup, limit_flags), + BTRFS_ATTR_PTR(qgroup, rsv_data), + BTRFS_ATTR_PTR(qgroup, rsv_meta_pertrans), + BTRFS_ATTR_PTR(qgroup, rsv_meta_prealloc), + NULL +}; +ATTRIBUTE_GROUPS(qgroup); + +static void qgroup_release(struct kobject *kobj) +{ + struct btrfs_qgroup *qgroup = container_of(kobj, struct btrfs_qgroup, kobj); + + memset(&qgroup->kobj, 0, sizeof(*kobj)); +} + +static struct kobj_type qgroup_ktype = { + .sysfs_ops = &kobj_sysfs_ops, + .release = qgroup_release, + .default_groups = qgroup_groups, +}; + +int btrfs_sysfs_add_one_qgroup(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup *qgroup) +{ + struct kobject *qgroups_kobj = fs_info->qgroups_kobj; + int ret; + + if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state)) + return 0; + if (qgroup->kobj.state_initialized) + return 0; + if (!qgroups_kobj) + return -EINVAL; + + ret = kobject_init_and_add(&qgroup->kobj, &qgroup_ktype, qgroups_kobj, + "%hu_%llu", btrfs_qgroup_level(qgroup->qgroupid), + btrfs_qgroup_subvolid(qgroup->qgroupid)); + if (ret < 0) + kobject_put(&qgroup->kobj); + + return ret; +} + +void btrfs_sysfs_del_qgroups(struct btrfs_fs_info *fs_info) +{ + struct btrfs_qgroup *qgroup; + struct btrfs_qgroup *next; + + if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state)) + return; + + rbtree_postorder_for_each_entry_safe(qgroup, next, + &fs_info->qgroup_tree, node) + btrfs_sysfs_del_one_qgroup(fs_info, qgroup); + kobject_del(fs_info->qgroups_kobj); + kobject_put(fs_info->qgroups_kobj); + fs_info->qgroups_kobj = NULL; +} + +/* Called when qgroups get initialized, thus there is no need for locking */ +int btrfs_sysfs_add_qgroups(struct btrfs_fs_info *fs_info) +{ + struct kobject *fsid_kobj = &fs_info->fs_devices->fsid_kobj; + struct btrfs_qgroup *qgroup; + struct btrfs_qgroup *next; + int ret = 0; + + if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state)) + return 0; + + ASSERT(fsid_kobj); + if (fs_info->qgroups_kobj) + return 0; + + fs_info->qgroups_kobj = kobject_create_and_add("qgroups", fsid_kobj); + if (!fs_info->qgroups_kobj) { + ret = -ENOMEM; + goto out; + } + rbtree_postorder_for_each_entry_safe(qgroup, next, + &fs_info->qgroup_tree, node) { + ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup); + if (ret < 0) + goto out; + } + +out: + if (ret < 0) + btrfs_sysfs_del_qgroups(fs_info); + return ret; +} + +void btrfs_sysfs_del_one_qgroup(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup *qgroup) +{ + if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state)) + return; + + if (qgroup->kobj.state_initialized) { + kobject_del(&qgroup->kobj); + kobject_put(&qgroup->kobj); + } +} /* * Change per-fs features in /sys/fs/btrfs/UUID/features to match current diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h index 718a26c97833..cf839c46a131 100644 --- a/fs/btrfs/sysfs.h +++ b/fs/btrfs/sysfs.h @@ -36,4 +36,11 @@ int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info, void btrfs_sysfs_remove_space_info(struct btrfs_space_info *space_info); void btrfs_sysfs_update_devid(struct btrfs_device *device); +int btrfs_sysfs_add_one_qgroup(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup *qgroup); +void btrfs_sysfs_del_qgroups(struct btrfs_fs_info *fs_info); +int btrfs_sysfs_add_qgroups(struct btrfs_fs_info *fs_info); +void btrfs_sysfs_del_one_qgroup(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup *qgroup); + #endif diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c index 914eea5ba6a7..2c783d2f5228 100644 --- a/fs/btrfs/tests/free-space-tree-tests.c +++ b/fs/btrfs/tests/free-space-tree-tests.c @@ -60,8 +60,6 @@ static int __check_free_space_extents(struct btrfs_trans_handle *trans, if (prev_bit == 0 && bit == 1) { extent_start = offset; } else if (prev_bit == 1 && bit == 0) { - if (i >= num_extents) - goto invalid; if (i >= num_extents || extent_start != extents[i].start || offset - extent_start != extents[i].length) diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index 24a8c714f56c..894a63a92236 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -954,8 +954,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) btrfs_test_inode_set_ops(inode); /* [BTRFS_MAX_EXTENT_SIZE] */ - ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1, 0, - NULL); + ret = btrfs_set_extent_delalloc(BTRFS_I(inode), 0, + BTRFS_MAX_EXTENT_SIZE - 1, 0, NULL); if (ret) { test_err("btrfs_set_extent_delalloc returned %d", ret); goto out; @@ -968,7 +968,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) } /* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */ - ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE, + ret = btrfs_set_extent_delalloc(BTRFS_I(inode), BTRFS_MAX_EXTENT_SIZE, BTRFS_MAX_EXTENT_SIZE + sectorsize - 1, 0, NULL); if (ret) { @@ -999,7 +999,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) } /* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */ - ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE >> 1, + ret = btrfs_set_extent_delalloc(BTRFS_I(inode), BTRFS_MAX_EXTENT_SIZE >> 1, (BTRFS_MAX_EXTENT_SIZE >> 1) + sectorsize - 1, 0, NULL); @@ -1017,7 +1017,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) /* * [BTRFS_MAX_EXTENT_SIZE+sectorsize][sectorsize HOLE][BTRFS_MAX_EXTENT_SIZE+sectorsize] */ - ret = btrfs_set_extent_delalloc(inode, + ret = btrfs_set_extent_delalloc(BTRFS_I(inode), BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize, (BTRFS_MAX_EXTENT_SIZE << 1) + 3 * sectorsize - 1, 0, NULL); @@ -1035,7 +1035,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) /* * [BTRFS_MAX_EXTENT_SIZE+sectorsize][sectorsize][BTRFS_MAX_EXTENT_SIZE+sectorsize] */ - ret = btrfs_set_extent_delalloc(inode, + ret = btrfs_set_extent_delalloc(BTRFS_I(inode), BTRFS_MAX_EXTENT_SIZE + sectorsize, BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, 0, NULL); if (ret) { @@ -1069,7 +1069,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) * Refill the hole again just for good measure, because I thought it * might fail and I'd rather satisfy my paranoia at this point. */ - ret = btrfs_set_extent_delalloc(inode, + ret = btrfs_set_extent_delalloc(BTRFS_I(inode), BTRFS_MAX_EXTENT_SIZE + sectorsize, BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, 0, NULL); if (ret) { diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index b359d4b17658..20c6ac1a5de7 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -937,7 +937,10 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, if (TRANS_ABORTED(trans) || test_bit(BTRFS_FS_STATE_ERROR, &info->fs_state)) { wake_up_process(info->transaction_kthread); - err = -EIO; + if (TRANS_ABORTED(trans)) + err = trans->aborted; + else + err = -EROFS; } kmem_cache_free(btrfs_trans_handle_cachep, trans); @@ -1630,7 +1633,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } key.offset = (u64)-1; - pending->snap = btrfs_get_fs_root(fs_info, objectid, true); + pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev); if (IS_ERR(pending->snap)) { ret = PTR_ERR(pending->snap); btrfs_abort_transaction(trans, ret); @@ -2351,7 +2354,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) */ cur_trans->state = TRANS_STATE_COMPLETED; wake_up(&cur_trans->commit_wait); - clear_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags); spin_lock(&fs_info->trans_lock); list_del_init(&cur_trans->list); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index bf102e64bfb2..d60b055b8695 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -151,18 +151,20 @@ struct btrfs_pending_snapshot { struct btrfs_block_rsv block_rsv; /* extra metadata reservation for relocation */ int error; + /* Preallocated anonymous block device number */ + dev_t anon_dev; bool readonly; struct list_head list; }; static inline void btrfs_set_inode_last_trans(struct btrfs_trans_handle *trans, - struct inode *inode) + struct btrfs_inode *inode) { - spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->last_trans = trans->transaction->transid; - BTRFS_I(inode)->last_sub_trans = BTRFS_I(inode)->root->log_transid; - BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->root->last_log_commit; - spin_unlock(&BTRFS_I(inode)->lock); + spin_lock(&inode->lock); + inode->last_trans = trans->transaction->transid; + inode->last_sub_trans = inode->root->log_transid; + inode->last_log_commit = inode->root->last_log_commit; + spin_unlock(&inode->lock); } /* @@ -208,20 +210,6 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root); int btrfs_commit_transaction(struct btrfs_trans_handle *trans); int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans, int wait_for_unblock); - -/* - * Try to commit transaction asynchronously, so this is safe to call - * even holding a spinlock. - * - * It's done by informing transaction_kthread to commit transaction without - * waiting for commit interval. - */ -static inline void btrfs_commit_transaction_locksafe( - struct btrfs_fs_info *fs_info) -{ - set_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags); - wake_up_process(fs_info->transaction_kthread); -} int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans); int btrfs_should_end_transaction(struct btrfs_trans_handle *trans); void btrfs_throttle(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/tree-defrag.c b/fs/btrfs/tree-defrag.c index 16c3a6d2586d..d3f28b8f4ff9 100644 --- a/fs/btrfs/tree-defrag.c +++ b/fs/btrfs/tree-defrag.c @@ -133,10 +133,9 @@ out: ret = 0; } done: - if (ret != -EAGAIN) { + if (ret != -EAGAIN) memset(&root->defrag_progress, 0, sizeof(root->defrag_progress)); - root->defrag_trans_start = trans->transid; - } + return ret; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index cd5348f352dd..ea8136dcf71f 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3116,29 +3116,17 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, btrfs_init_log_ctx(&root_log_ctx, NULL); mutex_lock(&log_root_tree->log_mutex); - atomic_inc(&log_root_tree->log_batch); - atomic_inc(&log_root_tree->log_writers); index2 = log_root_tree->log_transid % 2; list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]); root_log_ctx.log_transid = log_root_tree->log_transid; - mutex_unlock(&log_root_tree->log_mutex); - - mutex_lock(&log_root_tree->log_mutex); - /* * Now we are safe to update the log_root_tree because we're under the * log_mutex, and we're a current writer so we're holding the commit * open until we drop the log_mutex. */ ret = update_log_root(trans, log, &new_root_item); - - if (atomic_dec_and_test(&log_root_tree->log_writers)) { - /* atomic_dec_and_test implies a barrier */ - cond_wake_up_nomb(&log_root_tree->log_writer_wait); - } - if (ret) { if (!list_empty(&root_log_ctx.list)) list_del_init(&root_log_ctx.list); @@ -3184,8 +3172,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, root_log_ctx.log_transid - 1); } - wait_for_writer(log_root_tree); - /* * now that we've moved on to the tree of log tree roots, * check the full commit flag again @@ -3906,6 +3892,7 @@ static int log_inode_item(struct btrfs_trans_handle *trans, } static int log_csums(struct btrfs_trans_handle *trans, + struct btrfs_inode *inode, struct btrfs_root *log_root, struct btrfs_ordered_sum *sums) { @@ -3914,6 +3901,14 @@ static int log_csums(struct btrfs_trans_handle *trans, int ret; /* + * If this inode was not used for reflink operations in the current + * transaction with new extents, then do the fast path, no need to + * worry about logging checksum items with overlapping ranges. + */ + if (inode->last_reflink_trans < trans->transid) + return btrfs_csum_file_blocks(trans, log_root, sums); + + /* * Serialize logging for checksums. This is to avoid racing with the * same checksum being logged by another task that is logging another * file which happens to refer to the same extent as well. Such races @@ -4064,7 +4059,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = log_csums(trans, log, sums); + ret = log_csums(trans, inode, log, sums); list_del(&sums->list); kfree(sums); } @@ -4123,7 +4118,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = log_csums(trans, log_root, sums); + ret = log_csums(trans, inode, log_root, sums); list_del(&sums->list); kfree(sums); } @@ -4151,7 +4146,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans, if (ret) return ret; - ret = __btrfs_drop_extents(trans, log, &inode->vfs_inode, path, em->start, + ret = __btrfs_drop_extents(trans, log, inode, path, em->start, em->start + em->len, NULL, 0, 1, sizeof(*fi), &extent_inserted); if (ret) @@ -5123,14 +5118,13 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, const loff_t end, struct btrfs_log_ctx *ctx) { - struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_path *path; struct btrfs_path *dst_path; struct btrfs_key min_key; struct btrfs_key max_key; struct btrfs_root *log = root->log_root; int err = 0; - int ret; + int ret = 0; bool fast_search = false; u64 ino = btrfs_ino(inode); struct extent_map_tree *em_tree = &inode->extent_tree; @@ -5166,15 +5160,19 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, max_key.offset = (u64)-1; /* - * Only run delayed items if we are a dir or a new file. - * Otherwise commit the delayed inode only, which is needed in - * order for the log replay code to mark inodes for link count - * fixup (create temporary BTRFS_TREE_LOG_FIXUP_OBJECTID items). + * Only run delayed items if we are a directory. We want to make sure + * all directory indexes hit the fs/subvolume tree so we can find them + * and figure out which index ranges have to be logged. + * + * Otherwise commit the delayed inode only if the full sync flag is set, + * as we want to make sure an up to date version is in the subvolume + * tree so copy_inode_items_to_log() / copy_items() can find it and copy + * it to the log tree. For a non full sync, we always log the inode item + * based on the in-memory struct btrfs_inode which is always up to date. */ - if (S_ISDIR(inode->vfs_inode.i_mode) || - inode->generation > fs_info->last_trans_committed) + if (S_ISDIR(inode->vfs_inode.i_mode)) ret = btrfs_commit_inode_delayed_items(trans, inode); - else + else if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags)) ret = btrfs_commit_inode_delayed_inode(inode); if (ret) { diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 0d6e785bcb98..d7670e2a9f39 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -245,7 +245,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, * * global::fs_devs - add, remove, updates to the global list * - * does not protect: manipulation of the fs_devices::devices list! + * does not protect: manipulation of the fs_devices::devices list in general + * but in mount context it could be used to exclude list modifications by eg. + * scan ioctl * * btrfs_device::name - renames (write side), read is RCU * @@ -258,6 +260,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, * may be used to exclude some operations from running concurrently without any * modifications to the list (see write_all_supers) * + * Is not required at mount and close times, because our device list is + * protected by the uuid_mutex at that point. + * * balance_mutex * ------------- * protects balance structures (status, state) and context accessed from @@ -602,6 +607,11 @@ static int btrfs_free_stale_devices(const char *path, return ret; } +/* + * This is only used on mount, and we are protected from competing things + * messing with our fs_devices by the uuid_mutex, thus we do not need the + * fs_devices->device_list_mutex here. + */ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, struct btrfs_device *device, fmode_t flags, void *holder) @@ -1229,8 +1239,14 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, int ret; lockdep_assert_held(&uuid_mutex); + /* + * The device_list_mutex cannot be taken here in case opening the + * underlying device takes further locks like bd_mutex. + * + * We also don't need the lock here as this is called during mount and + * exclusion is provided by uuid_mutex + */ - mutex_lock(&fs_devices->device_list_mutex); if (fs_devices->opened) { fs_devices->opened++; ret = 0; @@ -1238,7 +1254,6 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, list_sort(NULL, &fs_devices->devices, devid_cmp); ret = open_fs_devices(fs_devices, flags, holder); } - mutex_unlock(&fs_devices->device_list_mutex); return ret; } @@ -3231,7 +3246,7 @@ static int del_balance_item(struct btrfs_fs_info *fs_info) if (!path) return -ENOMEM; - trans = btrfs_start_transaction(root, 0); + trans = btrfs_start_transaction_fallback_global_rsv(root, 0); if (IS_ERR(trans)) { btrfs_free_path(path); return PTR_ERR(trans); @@ -4135,7 +4150,22 @@ int btrfs_balance(struct btrfs_fs_info *fs_info, mutex_lock(&fs_info->balance_mutex); if (ret == -ECANCELED && atomic_read(&fs_info->balance_pause_req)) btrfs_info(fs_info, "balance: paused"); - else if (ret == -ECANCELED && atomic_read(&fs_info->balance_cancel_req)) + /* + * Balance can be canceled by: + * + * - Regular cancel request + * Then ret == -ECANCELED and balance_cancel_req > 0 + * + * - Fatal signal to "btrfs" process + * Either the signal caught by wait_reserve_ticket() and callers + * got -EINTR, or caught by btrfs_should_cancel_balance() and + * got -ECANCELED. + * Either way, in this case balance_cancel_req = 0, and + * ret == -EINTR or ret == -ECANCELED. + * + * So here we only check the return value to catch canceled balance. + */ + else if (ret == -ECANCELED || ret == -EINTR) btrfs_info(fs_info, "balance: canceled"); else btrfs_info(fs_info, "balance: ended with status: %d", ret); @@ -5522,6 +5552,9 @@ static struct btrfs_bio *alloc_btrfs_bio(int total_stripes, int real_stripes) atomic_set(&bbio->error, 0); refcount_set(&bbio->refs, 1); + bbio->tgtdev_map = (int *)(bbio->stripes + total_stripes); + bbio->raid_map = (u64 *)(bbio->tgtdev_map + real_stripes); + return bbio; } @@ -6144,8 +6177,13 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, ret = -ENOMEM; goto out; } - if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL) - bbio->tgtdev_map = (int *)(bbio->stripes + num_alloc_stripes); + + for (i = 0; i < num_stripes; i++) { + bbio->stripes[i].physical = map->stripes[stripe_index].physical + + stripe_offset + stripe_nr * map->stripe_len; + bbio->stripes[i].dev = map->stripes[stripe_index].dev; + stripe_index++; + } /* build raid_map */ if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK && need_raid_map && @@ -6153,11 +6191,6 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, u64 tmp; unsigned rot; - bbio->raid_map = (u64 *)((void *)bbio->stripes + - sizeof(struct btrfs_bio_stripe) * - num_alloc_stripes + - sizeof(int) * tgtdev_indexes); - /* Work out the disk rotation on this stripe-set */ div_u64_rem(stripe_nr, num_stripes, &rot); @@ -6171,25 +6204,13 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, if (map->type & BTRFS_BLOCK_GROUP_RAID6) bbio->raid_map[(i+rot+1) % num_stripes] = RAID6_Q_STRIPE; - } - - for (i = 0; i < num_stripes; i++) { - bbio->stripes[i].physical = - map->stripes[stripe_index].physical + - stripe_offset + - stripe_nr * map->stripe_len; - bbio->stripes[i].dev = - map->stripes[stripe_index].dev; - stripe_index++; + sort_parity_stripes(bbio, num_stripes); } if (need_full_stripe(op)) max_errors = btrfs_chunk_max_errors(map); - if (bbio->raid_map) - sort_parity_stripes(bbio, num_stripes); - if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL && need_full_stripe(op)) { handle_ops_on_dev_replace(op, &bbio, dev_replace, &num_stripes, @@ -6261,23 +6282,18 @@ static void btrfs_end_bio(struct bio *bio) atomic_inc(&bbio->error); if (bio->bi_status == BLK_STS_IOERR || bio->bi_status == BLK_STS_TARGET) { - unsigned int stripe_index = - btrfs_io_bio(bio)->stripe_index; - struct btrfs_device *dev; - - BUG_ON(stripe_index >= bbio->num_stripes); - dev = bbio->stripes[stripe_index].dev; - if (dev->bdev) { - if (bio_op(bio) == REQ_OP_WRITE) - btrfs_dev_stat_inc_and_print(dev, + struct btrfs_device *dev = btrfs_io_bio(bio)->device; + + ASSERT(dev->bdev); + if (bio_op(bio) == REQ_OP_WRITE) + btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS); - else if (!(bio->bi_opf & REQ_RAHEAD)) - btrfs_dev_stat_inc_and_print(dev, + else if (!(bio->bi_opf & REQ_RAHEAD)) + btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_READ_ERRS); - if (bio->bi_opf & REQ_PREFLUSH) - btrfs_dev_stat_inc_and_print(dev, + if (bio->bi_opf & REQ_PREFLUSH) + btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_FLUSH_ERRS); - } } } @@ -6313,13 +6329,12 @@ static void btrfs_end_bio(struct bio *bio) } static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio, - u64 physical, int dev_nr) + u64 physical, struct btrfs_device *dev) { - struct btrfs_device *dev = bbio->stripes[dev_nr].dev; struct btrfs_fs_info *fs_info = bbio->fs_info; bio->bi_private = bbio; - btrfs_io_bio(bio)->stripe_index = dev_nr; + btrfs_io_bio(bio)->device = dev; bio->bi_end_io = btrfs_end_bio; bio->bi_iter.bi_sector = physical >> 9; btrfs_debug_in_rcu(fs_info, @@ -6420,8 +6435,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, else bio = first_bio; - submit_stripe_bio(bbio, bio, bbio->stripes[dev_nr].physical, - dev_nr); + submit_stripe_bio(bbio, bio, bbio->stripes[dev_nr].physical, dev); } btrfs_bio_counter_dec(fs_info); return BLK_STS_OK; @@ -7029,6 +7043,19 @@ out: return ret; } +static void readahead_tree_node_children(struct extent_buffer *node) +{ + int i; + const int nr_items = btrfs_header_nritems(node); + + for (i = 0; i < nr_items; i++) { + u64 start; + + start = btrfs_node_blockptr(node, i); + readahead_tree_block(node->fs_info, start); + } +} + int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) { struct btrfs_root *root = fs_info->chunk_root; @@ -7039,6 +7066,7 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) int ret; int slot; u64 total_dev = 0; + u64 last_ra_node = 0; path = btrfs_alloc_path(); if (!path) @@ -7049,7 +7077,14 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) * otherwise we don't need it. */ mutex_lock(&uuid_mutex); - mutex_lock(&fs_info->chunk_mutex); + + /* + * It is possible for mount and umount to race in such a way that + * we execute this code path, but open_fs_devices failed to clear + * total_rw_bytes. We certainly want it cleared before reading the + * device items, so clear it here. + */ + fs_info->fs_devices->total_rw_bytes = 0; /* * Read all device items, and then all the chunk items. All @@ -7064,6 +7099,8 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) if (ret < 0) goto error; while (1) { + struct extent_buffer *node; + leaf = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(leaf)) { @@ -7074,6 +7111,17 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) goto error; break; } + /* + * The nodes on level 1 are not locked but we don't need to do + * that during mount time as nothing else can access the tree + */ + node = path->nodes[1]; + if (node) { + if (last_ra_node != node->start) { + readahead_tree_node_children(node); + last_ra_node = node->start; + } + } btrfs_item_key_to_cpu(leaf, &found_key, slot); if (found_key.type == BTRFS_DEV_ITEM_KEY) { struct btrfs_dev_item *dev_item; @@ -7086,7 +7134,9 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) } else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) { struct btrfs_chunk *chunk; chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); + mutex_lock(&fs_info->chunk_mutex); ret = read_one_chunk(&found_key, leaf, chunk); + mutex_unlock(&fs_info->chunk_mutex); if (ret) goto error; } @@ -7116,7 +7166,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) } ret = 0; error: - mutex_unlock(&fs_info->chunk_mutex); mutex_unlock(&uuid_mutex); btrfs_free_path(path); diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 75af2334b2e3..5eea93916fbf 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -288,7 +288,7 @@ struct btrfs_fs_devices { */ struct btrfs_io_bio { unsigned int mirror_num; - unsigned int stripe_index; + struct btrfs_device *device; u64 logical; u8 *csum; u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE]; diff --git a/fs/buffer.c b/fs/buffer.c index 64fe82ec65ff..dc5e05b47646 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -320,9 +320,8 @@ static void decrypt_bh(struct work_struct *work) static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) { /* Decrypt if needed */ - if (uptodate && IS_ENABLED(CONFIG_FS_ENCRYPTION) && - IS_ENCRYPTED(bh->b_page->mapping->host) && - S_ISREG(bh->b_page->mapping->host->i_mode)) { + if (uptodate && + fscrypt_inode_uses_fs_layer_crypto(bh->b_page->mapping->host)) { struct decrypt_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC); if (ctx) { @@ -3046,6 +3045,8 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, */ bio = bio_alloc(GFP_NOIO, 1); + fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); + bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_write_hint = write_hint; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 49c3ea8aa845..ce95801e9b66 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2044,7 +2044,6 @@ cifs_rename2(struct inode *source_dir, struct dentry *source_dentry, FILE_UNIX_BASIC_INFO *info_buf_target; unsigned int xid; int rc, tmprc; - bool new_target = d_really_is_negative(target_dentry); if (flags & ~RENAME_NOREPLACE) return -EINVAL; @@ -2121,13 +2120,8 @@ cifs_rename2(struct inode *source_dir, struct dentry *source_dentry, */ unlink_target: - /* - * If the target dentry was created during the rename, try - * unlinking it if it's not negative - */ - if (new_target && - d_really_is_positive(target_dentry) && - (rc == -EACCES || rc == -EEXIST)) { + /* Try unlinking the target dentry if it's not negative */ + if (d_really_is_positive(target_dentry) && (rc == -EACCES || rc == -EEXIST)) { if (d_is_dir(target_dentry)) tmprc = cifs_rmdir(target_dir, target_dentry); else diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig index 8046d7c7a3e9..a5f5c30368a2 100644 --- a/fs/crypto/Kconfig +++ b/fs/crypto/Kconfig @@ -4,6 +4,7 @@ config FS_ENCRYPTION select CRYPTO select CRYPTO_HASH select CRYPTO_SKCIPHER + select CRYPTO_LIB_SHA256 select KEYS help Enable encryption of files and directories. This @@ -21,6 +22,11 @@ config FS_ENCRYPTION_ALGS select CRYPTO_CTS select CRYPTO_ECB select CRYPTO_HMAC - select CRYPTO_SHA256 select CRYPTO_SHA512 select CRYPTO_XTS + +config FS_ENCRYPTION_INLINE_CRYPT + bool "Enable fscrypt to use inline crypto" + depends on FS_ENCRYPTION && BLK_INLINE_ENCRYPTION + help + Enable fscrypt to use inline encryption hardware if available. diff --git a/fs/crypto/Makefile b/fs/crypto/Makefile index 232e2bb5a337..652c7180ec6d 100644 --- a/fs/crypto/Makefile +++ b/fs/crypto/Makefile @@ -11,3 +11,4 @@ fscrypto-y := crypto.o \ policy.o fscrypto-$(CONFIG_BLOCK) += bio.o +fscrypto-$(CONFIG_FS_ENCRYPTION_INLINE_CRYPT) += inline_crypt.o diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c index 4fa18fff9c4e..b048a0e38516 100644 --- a/fs/crypto/bio.c +++ b/fs/crypto/bio.c @@ -41,6 +41,53 @@ void fscrypt_decrypt_bio(struct bio *bio) } EXPORT_SYMBOL(fscrypt_decrypt_bio); +static int fscrypt_zeroout_range_inline_crypt(const struct inode *inode, + pgoff_t lblk, sector_t pblk, + unsigned int len) +{ + const unsigned int blockbits = inode->i_blkbits; + const unsigned int blocks_per_page = 1 << (PAGE_SHIFT - blockbits); + struct bio *bio; + int ret, err = 0; + int num_pages = 0; + + /* This always succeeds since __GFP_DIRECT_RECLAIM is set. */ + bio = bio_alloc(GFP_NOFS, BIO_MAX_PAGES); + + while (len) { + unsigned int blocks_this_page = min(len, blocks_per_page); + unsigned int bytes_this_page = blocks_this_page << blockbits; + + if (num_pages == 0) { + fscrypt_set_bio_crypt_ctx(bio, inode, lblk, GFP_NOFS); + bio_set_dev(bio, inode->i_sb->s_bdev); + bio->bi_iter.bi_sector = + pblk << (blockbits - SECTOR_SHIFT); + bio_set_op_attrs(bio, REQ_OP_WRITE, 0); + } + ret = bio_add_page(bio, ZERO_PAGE(0), bytes_this_page, 0); + if (WARN_ON(ret != bytes_this_page)) { + err = -EIO; + goto out; + } + num_pages++; + len -= blocks_this_page; + lblk += blocks_this_page; + pblk += blocks_this_page; + if (num_pages == BIO_MAX_PAGES || !len || + !fscrypt_mergeable_bio(bio, inode, lblk)) { + err = submit_bio_wait(bio); + if (err) + goto out; + bio_reset(bio); + num_pages = 0; + } + } +out: + bio_put(bio); + return err; +} + /** * fscrypt_zeroout_range() - zero out a range of blocks in an encrypted file * @inode: the file's inode @@ -75,6 +122,10 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, if (len == 0) return 0; + if (fscrypt_inode_uses_inline_crypto(inode)) + return fscrypt_zeroout_range_inline_crypt(inode, lblk, pblk, + len); + BUILD_BUG_ON(ARRAY_SIZE(pages) > BIO_MAX_PAGES); nr_pages = min_t(unsigned int, ARRAY_SIZE(pages), (len + blocks_per_page - 1) >> blocks_per_page_bits); diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index ed015cb66c7c..9212325763b0 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -84,7 +84,7 @@ void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, WARN_ON_ONCE(lblk_num > U32_MAX); lblk_num = (u32)(ci->ci_hashed_ino + lblk_num); } else if (flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) { - memcpy(iv->nonce, ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE); + memcpy(iv->nonce, ci->ci_nonce, FSCRYPT_FILE_NONCE_SIZE); } iv->lblk_num = cpu_to_le64(lblk_num); } @@ -100,7 +100,7 @@ int fscrypt_crypt_block(const struct inode *inode, fscrypt_direction_t rw, DECLARE_CRYPTO_WAIT(wait); struct scatterlist dst, src; struct fscrypt_info *ci = inode->i_crypt_info; - struct crypto_skcipher *tfm = ci->ci_ctfm; + struct crypto_skcipher *tfm = ci->ci_enc_key.tfm; int res = 0; if (WARN_ON_ONCE(len <= 0)) diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 83ca5f1e7934..011830f84d8d 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -61,30 +61,13 @@ struct fscrypt_nokey_name { */ #define FSCRYPT_NOKEY_NAME_MAX offsetofend(struct fscrypt_nokey_name, sha256) -static struct crypto_shash *sha256_hash_tfm; - -static int fscrypt_do_sha256(const u8 *data, unsigned int data_len, u8 *result) +static void fscrypt_do_sha256(const u8 *data, unsigned int data_len, u8 *result) { - struct crypto_shash *tfm = READ_ONCE(sha256_hash_tfm); - - if (unlikely(!tfm)) { - struct crypto_shash *prev_tfm; - - tfm = crypto_alloc_shash("sha256", 0, 0); - if (IS_ERR(tfm)) { - fscrypt_err(NULL, - "Error allocating SHA-256 transform: %ld", - PTR_ERR(tfm)); - return PTR_ERR(tfm); - } - prev_tfm = cmpxchg(&sha256_hash_tfm, NULL, tfm); - if (prev_tfm) { - crypto_free_shash(tfm); - tfm = prev_tfm; - } - } + struct sha256_state sctx; - return crypto_shash_tfm_digest(tfm, data, data_len, result); + sha256_init(&sctx); + sha256_update(&sctx, data, data_len); + sha256_final(&sctx, result); } static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) @@ -115,7 +98,7 @@ int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname, struct skcipher_request *req = NULL; DECLARE_CRYPTO_WAIT(wait); const struct fscrypt_info *ci = inode->i_crypt_info; - struct crypto_skcipher *tfm = ci->ci_ctfm; + struct crypto_skcipher *tfm = ci->ci_enc_key.tfm; union fscrypt_iv iv; struct scatterlist sg; int res; @@ -171,7 +154,7 @@ static int fname_decrypt(const struct inode *inode, DECLARE_CRYPTO_WAIT(wait); struct scatterlist src_sg, dst_sg; const struct fscrypt_info *ci = inode->i_crypt_info; - struct crypto_skcipher *tfm = ci->ci_ctfm; + struct crypto_skcipher *tfm = ci->ci_enc_key.tfm; union fscrypt_iv iv; int res; @@ -349,7 +332,6 @@ int fscrypt_fname_disk_to_usr(const struct inode *inode, const struct qstr qname = FSTR_TO_QSTR(iname); struct fscrypt_nokey_name nokey_name; u32 size; /* size of the unencoded no-key name */ - int err; if (fscrypt_is_dot_dotdot(&qname)) { oname->name[0] = '.'; @@ -387,11 +369,9 @@ int fscrypt_fname_disk_to_usr(const struct inode *inode, } else { memcpy(nokey_name.bytes, iname->name, sizeof(nokey_name.bytes)); /* Compute strong hash of remaining part of name. */ - err = fscrypt_do_sha256(&iname->name[sizeof(nokey_name.bytes)], - iname->len - sizeof(nokey_name.bytes), - nokey_name.sha256); - if (err) - return err; + fscrypt_do_sha256(&iname->name[sizeof(nokey_name.bytes)], + iname->len - sizeof(nokey_name.bytes), + nokey_name.sha256); size = FSCRYPT_NOKEY_NAME_MAX; } oname->len = base64_encode((const u8 *)&nokey_name, size, oname->name); @@ -530,9 +510,8 @@ bool fscrypt_match_name(const struct fscrypt_name *fname, return false; if (memcmp(de_name, nokey_name->bytes, sizeof(nokey_name->bytes))) return false; - if (fscrypt_do_sha256(&de_name[sizeof(nokey_name->bytes)], - de_name_len - sizeof(nokey_name->bytes), sha256)) - return false; + fscrypt_do_sha256(&de_name[sizeof(nokey_name->bytes)], + de_name_len - sizeof(nokey_name->bytes), sha256); return !memcmp(sha256, nokey_name->sha256, sizeof(sha256)); } EXPORT_SYMBOL_GPL(fscrypt_match_name); diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index eb7fcd2b7fb8..8117a61b6f55 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -14,12 +14,13 @@ #include <linux/fscrypt.h> #include <linux/siphash.h> #include <crypto/hash.h> +#include <linux/blk-crypto.h> #define CONST_STRLEN(str) (sizeof(str) - 1) -#define FS_KEY_DERIVATION_NONCE_SIZE 16 +#define FSCRYPT_FILE_NONCE_SIZE 16 -#define FSCRYPT_MIN_KEY_SIZE 16 +#define FSCRYPT_MIN_KEY_SIZE 16 #define FSCRYPT_CONTEXT_V1 1 #define FSCRYPT_CONTEXT_V2 2 @@ -30,7 +31,7 @@ struct fscrypt_context_v1 { u8 filenames_encryption_mode; u8 flags; u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE]; - u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE]; + u8 nonce[FSCRYPT_FILE_NONCE_SIZE]; }; struct fscrypt_context_v2 { @@ -40,7 +41,7 @@ struct fscrypt_context_v2 { u8 flags; u8 __reserved[4]; u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]; - u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE]; + u8 nonce[FSCRYPT_FILE_NONCE_SIZE]; }; /* @@ -166,6 +167,20 @@ struct fscrypt_symlink_data { char encrypted_path[1]; } __packed; +/** + * struct fscrypt_prepared_key - a key prepared for actual encryption/decryption + * @tfm: crypto API transform object + * @blk_key: key for blk-crypto + * + * Normally only one of the fields will be non-NULL. + */ +struct fscrypt_prepared_key { + struct crypto_skcipher *tfm; +#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT + struct fscrypt_blk_crypto_key *blk_key; +#endif +}; + /* * fscrypt_info - the "encryption key" for an inode * @@ -175,12 +190,20 @@ struct fscrypt_symlink_data { */ struct fscrypt_info { - /* The actual crypto transform used for encryption and decryption */ - struct crypto_skcipher *ci_ctfm; + /* The key in a form prepared for actual encryption/decryption */ + struct fscrypt_prepared_key ci_enc_key; - /* True if the key should be freed when this fscrypt_info is freed */ + /* True if ci_enc_key should be freed when this fscrypt_info is freed */ bool ci_owns_key; +#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT + /* + * True if this inode will use inline encryption (blk-crypto) instead of + * the traditional filesystem-layer encryption. + */ + bool ci_inlinecrypt; +#endif + /* * Encryption mode used for this inode. It corresponds to either the * contents or filenames encryption mode, depending on the inode type. @@ -205,7 +228,7 @@ struct fscrypt_info { /* * If non-NULL, then encryption is done using the master key directly - * and ci_ctfm will equal ci_direct_key->dk_ctfm. + * and ci_enc_key will equal ci_direct_key->dk_key. */ struct fscrypt_direct_key *ci_direct_key; @@ -221,7 +244,7 @@ struct fscrypt_info { union fscrypt_policy ci_policy; /* This inode's nonce, copied from the fscrypt_context */ - u8 ci_nonce[FS_KEY_DERIVATION_NONCE_SIZE]; + u8 ci_nonce[FSCRYPT_FILE_NONCE_SIZE]; /* Hashed inode number. Only set for IV_INO_LBLK_32 */ u32 ci_hashed_ino; @@ -257,9 +280,10 @@ union fscrypt_iv { __le64 lblk_num; /* per-file nonce; only set in DIRECT_KEY mode */ - u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE]; + u8 nonce[FSCRYPT_FILE_NONCE_SIZE]; }; u8 raw[FSCRYPT_MAX_IV_SIZE]; + __le64 dun[FSCRYPT_MAX_IV_SIZE / sizeof(__le64)]; }; void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, @@ -288,13 +312,13 @@ int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key, * outputs are unique and cryptographically isolated, i.e. knowledge of one * output doesn't reveal another. */ -#define HKDF_CONTEXT_KEY_IDENTIFIER 1 -#define HKDF_CONTEXT_PER_FILE_ENC_KEY 2 -#define HKDF_CONTEXT_DIRECT_KEY 3 -#define HKDF_CONTEXT_IV_INO_LBLK_64_KEY 4 -#define HKDF_CONTEXT_DIRHASH_KEY 5 -#define HKDF_CONTEXT_IV_INO_LBLK_32_KEY 6 -#define HKDF_CONTEXT_INODE_HASH_KEY 7 +#define HKDF_CONTEXT_KEY_IDENTIFIER 1 /* info=<empty> */ +#define HKDF_CONTEXT_PER_FILE_ENC_KEY 2 /* info=file_nonce */ +#define HKDF_CONTEXT_DIRECT_KEY 3 /* info=mode_num */ +#define HKDF_CONTEXT_IV_INO_LBLK_64_KEY 4 /* info=mode_num||fs_uuid */ +#define HKDF_CONTEXT_DIRHASH_KEY 5 /* info=file_nonce */ +#define HKDF_CONTEXT_IV_INO_LBLK_32_KEY 6 /* info=mode_num||fs_uuid */ +#define HKDF_CONTEXT_INODE_HASH_KEY 7 /* info=<empty> */ int fscrypt_hkdf_expand(const struct fscrypt_hkdf *hkdf, u8 context, const u8 *info, unsigned int infolen, @@ -302,6 +326,78 @@ int fscrypt_hkdf_expand(const struct fscrypt_hkdf *hkdf, u8 context, void fscrypt_destroy_hkdf(struct fscrypt_hkdf *hkdf); +/* inline_crypt.c */ +#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT +int fscrypt_select_encryption_impl(struct fscrypt_info *ci); + +static inline bool +fscrypt_using_inline_encryption(const struct fscrypt_info *ci) +{ + return ci->ci_inlinecrypt; +} + +int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key, + const u8 *raw_key, + const struct fscrypt_info *ci); + +void fscrypt_destroy_inline_crypt_key(struct fscrypt_prepared_key *prep_key); + +/* + * Check whether the crypto transform or blk-crypto key has been allocated in + * @prep_key, depending on which encryption implementation the file will use. + */ +static inline bool +fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key, + const struct fscrypt_info *ci) +{ + /* + * The two smp_load_acquire()'s here pair with the smp_store_release()'s + * in fscrypt_prepare_inline_crypt_key() and fscrypt_prepare_key(). + * I.e., in some cases (namely, if this prep_key is a per-mode + * encryption key) another task can publish blk_key or tfm concurrently, + * executing a RELEASE barrier. We need to use smp_load_acquire() here + * to safely ACQUIRE the memory the other task published. + */ + if (fscrypt_using_inline_encryption(ci)) + return smp_load_acquire(&prep_key->blk_key) != NULL; + return smp_load_acquire(&prep_key->tfm) != NULL; +} + +#else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ + +static inline int fscrypt_select_encryption_impl(struct fscrypt_info *ci) +{ + return 0; +} + +static inline bool +fscrypt_using_inline_encryption(const struct fscrypt_info *ci) +{ + return false; +} + +static inline int +fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key, + const u8 *raw_key, + const struct fscrypt_info *ci) +{ + WARN_ON(1); + return -EOPNOTSUPP; +} + +static inline void +fscrypt_destroy_inline_crypt_key(struct fscrypt_prepared_key *prep_key) +{ +} + +static inline bool +fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key, + const struct fscrypt_info *ci) +{ + return smp_load_acquire(&prep_key->tfm) != NULL; +} +#endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ + /* keyring.c */ /* @@ -395,9 +491,9 @@ struct fscrypt_master_key { * Per-mode encryption keys for the various types of encryption policies * that use them. Allocated and derived on-demand. */ - struct crypto_skcipher *mk_direct_keys[__FSCRYPT_MODE_MAX + 1]; - struct crypto_skcipher *mk_iv_ino_lblk_64_keys[__FSCRYPT_MODE_MAX + 1]; - struct crypto_skcipher *mk_iv_ino_lblk_32_keys[__FSCRYPT_MODE_MAX + 1]; + struct fscrypt_prepared_key mk_direct_keys[__FSCRYPT_MODE_MAX + 1]; + struct fscrypt_prepared_key mk_iv_ino_lblk_64_keys[__FSCRYPT_MODE_MAX + 1]; + struct fscrypt_prepared_key mk_iv_ino_lblk_32_keys[__FSCRYPT_MODE_MAX + 1]; /* Hash key for inode numbers. Initialized only when needed. */ siphash_key_t mk_ino_hash_key; @@ -461,13 +557,15 @@ struct fscrypt_mode { int keysize; int ivsize; int logged_impl_name; + enum blk_crypto_mode_num blk_crypto_mode; }; extern struct fscrypt_mode fscrypt_modes[]; -struct crypto_skcipher *fscrypt_allocate_skcipher(struct fscrypt_mode *mode, - const u8 *raw_key, - const struct inode *inode); +int fscrypt_prepare_key(struct fscrypt_prepared_key *prep_key, + const u8 *raw_key, const struct fscrypt_info *ci); + +void fscrypt_destroy_prepared_key(struct fscrypt_prepared_key *prep_key); int fscrypt_set_per_file_enc_key(struct fscrypt_info *ci, const u8 *raw_key); diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c new file mode 100644 index 000000000000..b6b8574caa13 --- /dev/null +++ b/fs/crypto/inline_crypt.c @@ -0,0 +1,367 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Inline encryption support for fscrypt + * + * Copyright 2019 Google LLC + */ + +/* + * With "inline encryption", the block layer handles the decryption/encryption + * as part of the bio, instead of the filesystem doing the crypto itself via + * crypto API. See Documentation/block/inline-encryption.rst. fscrypt still + * provides the key and IV to use. + */ + +#include <linux/blk-crypto.h> +#include <linux/blkdev.h> +#include <linux/buffer_head.h> +#include <linux/sched/mm.h> + +#include "fscrypt_private.h" + +struct fscrypt_blk_crypto_key { + struct blk_crypto_key base; + int num_devs; + struct request_queue *devs[]; +}; + +static int fscrypt_get_num_devices(struct super_block *sb) +{ + if (sb->s_cop->get_num_devices) + return sb->s_cop->get_num_devices(sb); + return 1; +} + +static void fscrypt_get_devices(struct super_block *sb, int num_devs, + struct request_queue **devs) +{ + if (num_devs == 1) + devs[0] = bdev_get_queue(sb->s_bdev); + else + sb->s_cop->get_devices(sb, devs); +} + +static unsigned int fscrypt_get_dun_bytes(const struct fscrypt_info *ci) +{ + struct super_block *sb = ci->ci_inode->i_sb; + unsigned int flags = fscrypt_policy_flags(&ci->ci_policy); + int ino_bits = 64, lblk_bits = 64; + + if (flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) + return offsetofend(union fscrypt_iv, nonce); + + if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) + return sizeof(__le64); + + if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) + return sizeof(__le32); + + /* Default case: IVs are just the file logical block number */ + if (sb->s_cop->get_ino_and_lblk_bits) + sb->s_cop->get_ino_and_lblk_bits(sb, &ino_bits, &lblk_bits); + return DIV_ROUND_UP(lblk_bits, 8); +} + +/* Enable inline encryption for this file if supported. */ +int fscrypt_select_encryption_impl(struct fscrypt_info *ci) +{ + const struct inode *inode = ci->ci_inode; + struct super_block *sb = inode->i_sb; + struct blk_crypto_config crypto_cfg; + int num_devs; + struct request_queue **devs; + int i; + + /* The file must need contents encryption, not filenames encryption */ + if (!fscrypt_needs_contents_encryption(inode)) + return 0; + + /* The crypto mode must have a blk-crypto counterpart */ + if (ci->ci_mode->blk_crypto_mode == BLK_ENCRYPTION_MODE_INVALID) + return 0; + + /* The filesystem must be mounted with -o inlinecrypt */ + if (!(sb->s_flags & SB_INLINECRYPT)) + return 0; + + /* + * When a page contains multiple logically contiguous filesystem blocks, + * some filesystem code only calls fscrypt_mergeable_bio() for the first + * block in the page. This is fine for most of fscrypt's IV generation + * strategies, where contiguous blocks imply contiguous IVs. But it + * doesn't work with IV_INO_LBLK_32. For now, simply exclude + * IV_INO_LBLK_32 with blocksize != PAGE_SIZE from inline encryption. + */ + if ((fscrypt_policy_flags(&ci->ci_policy) & + FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) && + sb->s_blocksize != PAGE_SIZE) + return 0; + + /* + * On all the filesystem's devices, blk-crypto must support the crypto + * configuration that the file would use. + */ + crypto_cfg.crypto_mode = ci->ci_mode->blk_crypto_mode; + crypto_cfg.data_unit_size = sb->s_blocksize; + crypto_cfg.dun_bytes = fscrypt_get_dun_bytes(ci); + num_devs = fscrypt_get_num_devices(sb); + devs = kmalloc_array(num_devs, sizeof(*devs), GFP_NOFS); + if (!devs) + return -ENOMEM; + fscrypt_get_devices(sb, num_devs, devs); + + for (i = 0; i < num_devs; i++) { + if (!blk_crypto_config_supported(devs[i], &crypto_cfg)) + goto out_free_devs; + } + + ci->ci_inlinecrypt = true; +out_free_devs: + kfree(devs); + + return 0; +} + +int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key, + const u8 *raw_key, + const struct fscrypt_info *ci) +{ + const struct inode *inode = ci->ci_inode; + struct super_block *sb = inode->i_sb; + enum blk_crypto_mode_num crypto_mode = ci->ci_mode->blk_crypto_mode; + int num_devs = fscrypt_get_num_devices(sb); + int queue_refs = 0; + struct fscrypt_blk_crypto_key *blk_key; + int err; + int i; + unsigned int flags; + + blk_key = kzalloc(struct_size(blk_key, devs, num_devs), GFP_NOFS); + if (!blk_key) + return -ENOMEM; + + blk_key->num_devs = num_devs; + fscrypt_get_devices(sb, num_devs, blk_key->devs); + + err = blk_crypto_init_key(&blk_key->base, raw_key, crypto_mode, + fscrypt_get_dun_bytes(ci), sb->s_blocksize); + if (err) { + fscrypt_err(inode, "error %d initializing blk-crypto key", err); + goto fail; + } + + /* + * We have to start using blk-crypto on all the filesystem's devices. + * We also have to save all the request_queue's for later so that the + * key can be evicted from them. This is needed because some keys + * aren't destroyed until after the filesystem was already unmounted + * (namely, the per-mode keys in struct fscrypt_master_key). + */ + for (i = 0; i < num_devs; i++) { + if (!blk_get_queue(blk_key->devs[i])) { + fscrypt_err(inode, "couldn't get request_queue"); + err = -EAGAIN; + goto fail; + } + queue_refs++; + + flags = memalloc_nofs_save(); + err = blk_crypto_start_using_key(&blk_key->base, + blk_key->devs[i]); + memalloc_nofs_restore(flags); + if (err) { + fscrypt_err(inode, + "error %d starting to use blk-crypto", err); + goto fail; + } + } + /* + * Pairs with the smp_load_acquire() in fscrypt_is_key_prepared(). + * I.e., here we publish ->blk_key with a RELEASE barrier so that + * concurrent tasks can ACQUIRE it. Note that this concurrency is only + * possible for per-mode keys, not for per-file keys. + */ + smp_store_release(&prep_key->blk_key, blk_key); + return 0; + +fail: + for (i = 0; i < queue_refs; i++) + blk_put_queue(blk_key->devs[i]); + kzfree(blk_key); + return err; +} + +void fscrypt_destroy_inline_crypt_key(struct fscrypt_prepared_key *prep_key) +{ + struct fscrypt_blk_crypto_key *blk_key = prep_key->blk_key; + int i; + + if (blk_key) { + for (i = 0; i < blk_key->num_devs; i++) { + blk_crypto_evict_key(blk_key->devs[i], &blk_key->base); + blk_put_queue(blk_key->devs[i]); + } + kzfree(blk_key); + } +} + +bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode) +{ + return inode->i_crypt_info->ci_inlinecrypt; +} +EXPORT_SYMBOL_GPL(__fscrypt_inode_uses_inline_crypto); + +static void fscrypt_generate_dun(const struct fscrypt_info *ci, u64 lblk_num, + u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE]) +{ + union fscrypt_iv iv; + int i; + + fscrypt_generate_iv(&iv, lblk_num, ci); + + BUILD_BUG_ON(FSCRYPT_MAX_IV_SIZE > BLK_CRYPTO_MAX_IV_SIZE); + memset(dun, 0, BLK_CRYPTO_MAX_IV_SIZE); + for (i = 0; i < ci->ci_mode->ivsize/sizeof(dun[0]); i++) + dun[i] = le64_to_cpu(iv.dun[i]); +} + +/** + * fscrypt_set_bio_crypt_ctx() - prepare a file contents bio for inline crypto + * @bio: a bio which will eventually be submitted to the file + * @inode: the file's inode + * @first_lblk: the first file logical block number in the I/O + * @gfp_mask: memory allocation flags - these must be a waiting mask so that + * bio_crypt_set_ctx can't fail. + * + * If the contents of the file should be encrypted (or decrypted) with inline + * encryption, then assign the appropriate encryption context to the bio. + * + * Normally the bio should be newly allocated (i.e. no pages added yet), as + * otherwise fscrypt_mergeable_bio() won't work as intended. + * + * The encryption context will be freed automatically when the bio is freed. + */ +void fscrypt_set_bio_crypt_ctx(struct bio *bio, const struct inode *inode, + u64 first_lblk, gfp_t gfp_mask) +{ + const struct fscrypt_info *ci; + u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE]; + + if (!fscrypt_inode_uses_inline_crypto(inode)) + return; + ci = inode->i_crypt_info; + + fscrypt_generate_dun(ci, first_lblk, dun); + bio_crypt_set_ctx(bio, &ci->ci_enc_key.blk_key->base, dun, gfp_mask); +} +EXPORT_SYMBOL_GPL(fscrypt_set_bio_crypt_ctx); + +/* Extract the inode and logical block number from a buffer_head. */ +static bool bh_get_inode_and_lblk_num(const struct buffer_head *bh, + const struct inode **inode_ret, + u64 *lblk_num_ret) +{ + struct page *page = bh->b_page; + const struct address_space *mapping; + const struct inode *inode; + + /* + * The ext4 journal (jbd2) can submit a buffer_head it directly created + * for a non-pagecache page. fscrypt doesn't care about these. + */ + mapping = page_mapping(page); + if (!mapping) + return false; + inode = mapping->host; + + *inode_ret = inode; + *lblk_num_ret = ((u64)page->index << (PAGE_SHIFT - inode->i_blkbits)) + + (bh_offset(bh) >> inode->i_blkbits); + return true; +} + +/** + * fscrypt_set_bio_crypt_ctx_bh() - prepare a file contents bio for inline + * crypto + * @bio: a bio which will eventually be submitted to the file + * @first_bh: the first buffer_head for which I/O will be submitted + * @gfp_mask: memory allocation flags + * + * Same as fscrypt_set_bio_crypt_ctx(), except this takes a buffer_head instead + * of an inode and block number directly. + */ +void fscrypt_set_bio_crypt_ctx_bh(struct bio *bio, + const struct buffer_head *first_bh, + gfp_t gfp_mask) +{ + const struct inode *inode; + u64 first_lblk; + + if (bh_get_inode_and_lblk_num(first_bh, &inode, &first_lblk)) + fscrypt_set_bio_crypt_ctx(bio, inode, first_lblk, gfp_mask); +} +EXPORT_SYMBOL_GPL(fscrypt_set_bio_crypt_ctx_bh); + +/** + * fscrypt_mergeable_bio() - test whether data can be added to a bio + * @bio: the bio being built up + * @inode: the inode for the next part of the I/O + * @next_lblk: the next file logical block number in the I/O + * + * When building a bio which may contain data which should undergo inline + * encryption (or decryption) via fscrypt, filesystems should call this function + * to ensure that the resulting bio contains only contiguous data unit numbers. + * This will return false if the next part of the I/O cannot be merged with the + * bio because either the encryption key would be different or the encryption + * data unit numbers would be discontiguous. + * + * fscrypt_set_bio_crypt_ctx() must have already been called on the bio. + * + * Return: true iff the I/O is mergeable + */ +bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode, + u64 next_lblk) +{ + const struct bio_crypt_ctx *bc = bio->bi_crypt_context; + u64 next_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]; + + if (!!bc != fscrypt_inode_uses_inline_crypto(inode)) + return false; + if (!bc) + return true; + + /* + * Comparing the key pointers is good enough, as all I/O for each key + * uses the same pointer. I.e., there's currently no need to support + * merging requests where the keys are the same but the pointers differ. + */ + if (bc->bc_key != &inode->i_crypt_info->ci_enc_key.blk_key->base) + return false; + + fscrypt_generate_dun(inode->i_crypt_info, next_lblk, next_dun); + return bio_crypt_dun_is_contiguous(bc, bio->bi_iter.bi_size, next_dun); +} +EXPORT_SYMBOL_GPL(fscrypt_mergeable_bio); + +/** + * fscrypt_mergeable_bio_bh() - test whether data can be added to a bio + * @bio: the bio being built up + * @next_bh: the next buffer_head for which I/O will be submitted + * + * Same as fscrypt_mergeable_bio(), except this takes a buffer_head instead of + * an inode and block number directly. + * + * Return: true iff the I/O is mergeable + */ +bool fscrypt_mergeable_bio_bh(struct bio *bio, + const struct buffer_head *next_bh) +{ + const struct inode *inode; + u64 next_lblk; + + if (!bh_get_inode_and_lblk_num(next_bh, &inode, &next_lblk)) + return !bio->bi_crypt_context; + + return fscrypt_mergeable_bio(bio, inode, next_lblk); +} +EXPORT_SYMBOL_GPL(fscrypt_mergeable_bio_bh); diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index e24eb48bfbe1..71d56f8e2870 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -45,9 +45,9 @@ static void free_master_key(struct fscrypt_master_key *mk) wipe_master_key_secret(&mk->mk_secret); for (i = 0; i <= __FSCRYPT_MODE_MAX; i++) { - crypto_free_skcipher(mk->mk_direct_keys[i]); - crypto_free_skcipher(mk->mk_iv_ino_lblk_64_keys[i]); - crypto_free_skcipher(mk->mk_iv_ino_lblk_32_keys[i]); + fscrypt_destroy_prepared_key(&mk->mk_direct_keys[i]); + fscrypt_destroy_prepared_key(&mk->mk_iv_ino_lblk_64_keys[i]); + fscrypt_destroy_prepared_key(&mk->mk_iv_ino_lblk_32_keys[i]); } key_put(mk->mk_users); @@ -213,7 +213,11 @@ static int allocate_filesystem_keyring(struct super_block *sb) if (IS_ERR(keyring)) return PTR_ERR(keyring); - /* Pairs with READ_ONCE() in fscrypt_find_master_key() */ + /* + * Pairs with the smp_load_acquire() in fscrypt_find_master_key(). + * I.e., here we publish ->s_master_keys with a RELEASE barrier so that + * concurrent tasks can ACQUIRE it. + */ smp_store_release(&sb->s_master_keys, keyring); return 0; } @@ -234,8 +238,13 @@ struct key *fscrypt_find_master_key(struct super_block *sb, struct key *keyring; char description[FSCRYPT_MK_DESCRIPTION_SIZE]; - /* pairs with smp_store_release() in allocate_filesystem_keyring() */ - keyring = READ_ONCE(sb->s_master_keys); + /* + * Pairs with the smp_store_release() in allocate_filesystem_keyring(). + * I.e., another task can publish ->s_master_keys concurrently, + * executing a RELEASE barrier. We need to use smp_load_acquire() here + * to safely ACQUIRE the memory the other task published. + */ + keyring = smp_load_acquire(&sb->s_master_keys); if (keyring == NULL) return ERR_PTR(-ENOKEY); /* No keyring yet, so no keys yet. */ diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index 1129adfa097d..fea6226afc2b 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -19,6 +19,7 @@ struct fscrypt_mode fscrypt_modes[] = { .cipher_str = "xts(aes)", .keysize = 64, .ivsize = 16, + .blk_crypto_mode = BLK_ENCRYPTION_MODE_AES_256_XTS, }, [FSCRYPT_MODE_AES_256_CTS] = { .friendly_name = "AES-256-CTS-CBC", @@ -31,6 +32,7 @@ struct fscrypt_mode fscrypt_modes[] = { .cipher_str = "essiv(cbc(aes),sha256)", .keysize = 16, .ivsize = 16, + .blk_crypto_mode = BLK_ENCRYPTION_MODE_AES_128_CBC_ESSIV, }, [FSCRYPT_MODE_AES_128_CTS] = { .friendly_name = "AES-128-CTS-CBC", @@ -43,6 +45,7 @@ struct fscrypt_mode fscrypt_modes[] = { .cipher_str = "adiantum(xchacha12,aes)", .keysize = 32, .ivsize = 32, + .blk_crypto_mode = BLK_ENCRYPTION_MODE_ADIANTUM, }, }; @@ -64,9 +67,9 @@ select_encryption_mode(const union fscrypt_policy *policy, } /* Create a symmetric cipher object for the given encryption mode and key */ -struct crypto_skcipher *fscrypt_allocate_skcipher(struct fscrypt_mode *mode, - const u8 *raw_key, - const struct inode *inode) +static struct crypto_skcipher * +fscrypt_allocate_skcipher(struct fscrypt_mode *mode, const u8 *raw_key, + const struct inode *inode) { struct crypto_skcipher *tfm; int err; @@ -109,30 +112,56 @@ err_free_tfm: return ERR_PTR(err); } -/* Given a per-file encryption key, set up the file's crypto transform object */ -int fscrypt_set_per_file_enc_key(struct fscrypt_info *ci, const u8 *raw_key) +/* + * Prepare the crypto transform object or blk-crypto key in @prep_key, given the + * raw key, encryption mode, and flag indicating which encryption implementation + * (fs-layer or blk-crypto) will be used. + */ +int fscrypt_prepare_key(struct fscrypt_prepared_key *prep_key, + const u8 *raw_key, const struct fscrypt_info *ci) { struct crypto_skcipher *tfm; + if (fscrypt_using_inline_encryption(ci)) + return fscrypt_prepare_inline_crypt_key(prep_key, raw_key, ci); + tfm = fscrypt_allocate_skcipher(ci->ci_mode, raw_key, ci->ci_inode); if (IS_ERR(tfm)) return PTR_ERR(tfm); + /* + * Pairs with the smp_load_acquire() in fscrypt_is_key_prepared(). + * I.e., here we publish ->tfm with a RELEASE barrier so that + * concurrent tasks can ACQUIRE it. Note that this concurrency is only + * possible for per-mode keys, not for per-file keys. + */ + smp_store_release(&prep_key->tfm, tfm); + return 0; +} - ci->ci_ctfm = tfm; +/* Destroy a crypto transform object and/or blk-crypto key. */ +void fscrypt_destroy_prepared_key(struct fscrypt_prepared_key *prep_key) +{ + crypto_free_skcipher(prep_key->tfm); + fscrypt_destroy_inline_crypt_key(prep_key); +} + +/* Given a per-file encryption key, set up the file's crypto transform object */ +int fscrypt_set_per_file_enc_key(struct fscrypt_info *ci, const u8 *raw_key) +{ ci->ci_owns_key = true; - return 0; + return fscrypt_prepare_key(&ci->ci_enc_key, raw_key, ci); } static int setup_per_mode_enc_key(struct fscrypt_info *ci, struct fscrypt_master_key *mk, - struct crypto_skcipher **tfms, + struct fscrypt_prepared_key *keys, u8 hkdf_context, bool include_fs_uuid) { const struct inode *inode = ci->ci_inode; const struct super_block *sb = inode->i_sb; struct fscrypt_mode *mode = ci->ci_mode; const u8 mode_num = mode - fscrypt_modes; - struct crypto_skcipher *tfm; + struct fscrypt_prepared_key *prep_key; u8 mode_key[FSCRYPT_MAX_KEY_SIZE]; u8 hkdf_info[sizeof(mode_num) + sizeof(sb->s_uuid)]; unsigned int hkdf_infolen = 0; @@ -141,16 +170,15 @@ static int setup_per_mode_enc_key(struct fscrypt_info *ci, if (WARN_ON(mode_num > __FSCRYPT_MODE_MAX)) return -EINVAL; - /* pairs with smp_store_release() below */ - tfm = READ_ONCE(tfms[mode_num]); - if (likely(tfm != NULL)) { - ci->ci_ctfm = tfm; + prep_key = &keys[mode_num]; + if (fscrypt_is_key_prepared(prep_key, ci)) { + ci->ci_enc_key = *prep_key; return 0; } mutex_lock(&fscrypt_mode_key_setup_mutex); - if (tfms[mode_num]) + if (fscrypt_is_key_prepared(prep_key, ci)) goto done_unlock; BUILD_BUG_ON(sizeof(mode_num) != 1); @@ -167,16 +195,12 @@ static int setup_per_mode_enc_key(struct fscrypt_info *ci, mode_key, mode->keysize); if (err) goto out_unlock; - tfm = fscrypt_allocate_skcipher(mode, mode_key, inode); + err = fscrypt_prepare_key(prep_key, mode_key, ci); memzero_explicit(mode_key, mode->keysize); - if (IS_ERR(tfm)) { - err = PTR_ERR(tfm); + if (err) goto out_unlock; - } - /* pairs with READ_ONCE() above */ - smp_store_release(&tfms[mode_num], tfm); done_unlock: - ci->ci_ctfm = tfm; + ci->ci_enc_key = *prep_key; err = 0; out_unlock: mutex_unlock(&fscrypt_mode_key_setup_mutex); @@ -189,7 +213,7 @@ int fscrypt_derive_dirhash_key(struct fscrypt_info *ci, int err; err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf, HKDF_CONTEXT_DIRHASH_KEY, - ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE, + ci->ci_nonce, FSCRYPT_FILE_NONCE_SIZE, (u8 *)&ci->ci_dirhash_key, sizeof(ci->ci_dirhash_key)); if (err) @@ -270,8 +294,7 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci, err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf, HKDF_CONTEXT_PER_FILE_ENC_KEY, - ci->ci_nonce, - FS_KEY_DERIVATION_NONCE_SIZE, + ci->ci_nonce, FSCRYPT_FILE_NONCE_SIZE, derived_key, ci->ci_mode->keysize); if (err) return err; @@ -310,6 +333,10 @@ static int setup_file_encryption_key(struct fscrypt_info *ci, struct fscrypt_key_specifier mk_spec; int err; + err = fscrypt_select_encryption_impl(ci); + if (err) + return err; + switch (ci->ci_policy.version) { case FSCRYPT_POLICY_V1: mk_spec.type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR; @@ -402,7 +429,7 @@ static void put_crypt_info(struct fscrypt_info *ci) if (ci->ci_direct_key) fscrypt_put_direct_key(ci->ci_direct_key); else if (ci->ci_owns_key) - crypto_free_skcipher(ci->ci_ctfm); + fscrypt_destroy_prepared_key(&ci->ci_enc_key); key = ci->ci_master_key; if (key) { @@ -472,7 +499,7 @@ int fscrypt_get_encryption_info(struct inode *inode) } memcpy(crypt_info->ci_nonce, fscrypt_context_nonce(&ctx), - FS_KEY_DERIVATION_NONCE_SIZE); + FSCRYPT_FILE_NONCE_SIZE); if (!fscrypt_supported_policy(&crypt_info->ci_policy, inode)) { res = -EINVAL; @@ -491,7 +518,17 @@ int fscrypt_get_encryption_info(struct inode *inode) if (res) goto out; + /* + * Multiple tasks may race to set ->i_crypt_info, so use + * cmpxchg_release(). This pairs with the smp_load_acquire() in + * fscrypt_get_info(). I.e., here we publish ->i_crypt_info with a + * RELEASE barrier so that other tasks can ACQUIRE it. + */ if (cmpxchg_release(&inode->i_crypt_info, NULL, crypt_info) == NULL) { + /* + * We won the race and set ->i_crypt_info to our crypt_info. + * Now link it into the master key's inode list. + */ if (master_key) { struct fscrypt_master_key *mk = master_key->payload.data[0]; @@ -562,7 +599,7 @@ EXPORT_SYMBOL(fscrypt_free_inode); */ int fscrypt_drop_inode(struct inode *inode) { - const struct fscrypt_info *ci = READ_ONCE(inode->i_crypt_info); + const struct fscrypt_info *ci = fscrypt_get_info(inode); const struct fscrypt_master_key *mk; /* diff --git a/fs/crypto/keysetup_v1.c b/fs/crypto/keysetup_v1.c index 801b48c0cd7f..e4e707fb1100 100644 --- a/fs/crypto/keysetup_v1.c +++ b/fs/crypto/keysetup_v1.c @@ -45,7 +45,7 @@ static DEFINE_SPINLOCK(fscrypt_direct_keys_lock); * key is longer, then only the first 'derived_keysize' bytes are used. */ static int derive_key_aes(const u8 *master_key, - const u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE], + const u8 nonce[FSCRYPT_FILE_NONCE_SIZE], u8 *derived_key, unsigned int derived_keysize) { int res = 0; @@ -68,7 +68,7 @@ static int derive_key_aes(const u8 *master_key, skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &wait); - res = crypto_skcipher_setkey(tfm, nonce, FS_KEY_DERIVATION_NONCE_SIZE); + res = crypto_skcipher_setkey(tfm, nonce, FSCRYPT_FILE_NONCE_SIZE); if (res < 0) goto out; @@ -146,7 +146,7 @@ struct fscrypt_direct_key { struct hlist_node dk_node; refcount_t dk_refcount; const struct fscrypt_mode *dk_mode; - struct crypto_skcipher *dk_ctfm; + struct fscrypt_prepared_key dk_key; u8 dk_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE]; u8 dk_raw[FSCRYPT_MAX_KEY_SIZE]; }; @@ -154,7 +154,7 @@ struct fscrypt_direct_key { static void free_direct_key(struct fscrypt_direct_key *dk) { if (dk) { - crypto_free_skcipher(dk->dk_ctfm); + fscrypt_destroy_prepared_key(&dk->dk_key); kzfree(dk); } } @@ -199,6 +199,8 @@ find_or_insert_direct_key(struct fscrypt_direct_key *to_insert, continue; if (ci->ci_mode != dk->dk_mode) continue; + if (!fscrypt_is_key_prepared(&dk->dk_key, ci)) + continue; if (crypto_memneq(raw_key, dk->dk_raw, ci->ci_mode->keysize)) continue; /* using existing tfm with same (descriptor, mode, raw_key) */ @@ -231,13 +233,9 @@ fscrypt_get_direct_key(const struct fscrypt_info *ci, const u8 *raw_key) return ERR_PTR(-ENOMEM); refcount_set(&dk->dk_refcount, 1); dk->dk_mode = ci->ci_mode; - dk->dk_ctfm = fscrypt_allocate_skcipher(ci->ci_mode, raw_key, - ci->ci_inode); - if (IS_ERR(dk->dk_ctfm)) { - err = PTR_ERR(dk->dk_ctfm); - dk->dk_ctfm = NULL; + err = fscrypt_prepare_key(&dk->dk_key, raw_key, ci); + if (err) goto err_free_dk; - } memcpy(dk->dk_descriptor, ci->ci_policy.v1.master_key_descriptor, FSCRYPT_KEY_DESCRIPTOR_SIZE); memcpy(dk->dk_raw, raw_key, ci->ci_mode->keysize); @@ -259,7 +257,7 @@ static int setup_v1_file_key_direct(struct fscrypt_info *ci, if (IS_ERR(dk)) return PTR_ERR(dk); ci->ci_direct_key = dk; - ci->ci_ctfm = dk->dk_ctfm; + ci->ci_enc_key = dk->dk_key; return 0; } diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index d23ff162c78b..2d73fd39ad96 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -78,6 +78,20 @@ static bool supported_iv_ino_lblk_policy(const struct fscrypt_policy_v2 *policy, int ino_bits = 64, lblk_bits = 64; /* + * IV_INO_LBLK_* exist only because of hardware limitations, and + * currently the only known use case for them involves AES-256-XTS. + * That's also all we test currently. For these reasons, for now only + * allow AES-256-XTS here. This can be relaxed later if a use case for + * IV_INO_LBLK_* with other encryption modes arises. + */ + if (policy->contents_encryption_mode != FSCRYPT_MODE_AES_256_XTS) { + fscrypt_warn(inode, + "Can't use %s policy with contents mode other than AES-256-XTS", + type); + return false; + } + + /* * It's unsafe to include inode numbers in the IVs if the filesystem can * potentially renumber inodes, e.g. via filesystem shrinking. */ @@ -338,7 +352,7 @@ static int fscrypt_get_policy(struct inode *inode, union fscrypt_policy *policy) union fscrypt_context ctx; int ret; - ci = READ_ONCE(inode->i_crypt_info); + ci = fscrypt_get_info(inode); if (ci) { /* key available, use the cached policy */ *policy = ci->ci_policy; @@ -529,7 +543,7 @@ int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg) if (!fscrypt_context_is_valid(&ctx, ret)) return -EINVAL; if (copy_to_user(arg, fscrypt_context_nonce(&ctx), - FS_KEY_DERIVATION_NONCE_SIZE)) + FSCRYPT_FILE_NONCE_SIZE)) return -EFAULT; return 0; } @@ -627,7 +641,7 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child, if (res < 0) return res; - ci = READ_ONCE(parent->i_crypt_info); + ci = fscrypt_get_info(parent); if (ci == NULL) return -ENOKEY; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 12c66f5d92dd..28bb5689333a 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -201,6 +201,9 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_d_op = &efivarfs_d_ops; sb->s_time_gran = 1; + if (!efivar_supports_writes()) + sb->s_flags |= SB_RDONLY; + inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true); if (!inode) return -ENOMEM; @@ -252,9 +255,6 @@ static struct file_system_type efivarfs_type = { static __init int efivarfs_init(void) { - if (!efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES)) - return -ENODEV; - if (!efivars_kobject()) return -ENODEV; diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index 91ece649285d..119abf0d8dd6 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -1112,7 +1112,7 @@ found: ret = exfat_get_next_cluster(sb, &clu.dir); } - if (ret || clu.dir != EXFAT_EOF_CLUSTER) { + if (ret || clu.dir == EXFAT_EOF_CLUSTER) { /* just initialized hint_stat */ hint_stat->clu = p_dir->dir; hint_stat->eidx = 0; diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index 7579cd3bbadb..75c7bdbeba6d 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -371,7 +371,7 @@ static inline bool exfat_is_last_sector_in_cluster(struct exfat_sb_info *sbi, static inline sector_t exfat_cluster_to_sector(struct exfat_sb_info *sbi, unsigned int clus) { - return ((clus - EXFAT_RESERVED_CLUSTERS) << sbi->sect_per_clus_bits) + + return ((sector_t)(clus - EXFAT_RESERVED_CLUSTERS) << sbi->sect_per_clus_bits) + sbi->data_start_sector; } diff --git a/fs/exfat/file.c b/fs/exfat/file.c index 3b7fea465fd4..a6a063830edc 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -176,7 +176,7 @@ int __exfat_truncate(struct inode *inode, loff_t new_size) ep2->dentry.stream.size = 0; } else { ep2->dentry.stream.valid_size = cpu_to_le64(new_size); - ep2->dentry.stream.size = ep->dentry.stream.valid_size; + ep2->dentry.stream.size = ep2->dentry.stream.valid_size; } if (new_size == 0) { diff --git a/fs/exfat/nls.c b/fs/exfat/nls.c index 57b5a7a4d1f7..a3c927501e67 100644 --- a/fs/exfat/nls.c +++ b/fs/exfat/nls.c @@ -495,7 +495,7 @@ static int exfat_utf8_to_utf16(struct super_block *sb, struct exfat_uni_name *p_uniname, int *p_lossy) { int i, unilen, lossy = NLS_NAME_NO_LOSSY; - unsigned short upname[MAX_NAME_LENGTH + 1]; + __le16 upname[MAX_NAME_LENGTH + 1]; unsigned short *uniname = p_uniname->name; WARN_ON(!len); @@ -519,7 +519,7 @@ static int exfat_utf8_to_utf16(struct super_block *sb, exfat_wstrchr(bad_uni_chars, *uniname)) lossy |= NLS_NAME_LOSSY; - upname[i] = exfat_toupper(sb, *uniname); + upname[i] = cpu_to_le16(exfat_toupper(sb, *uniname)); uniname++; } @@ -597,7 +597,7 @@ static int exfat_nls_to_ucs2(struct super_block *sb, struct exfat_uni_name *p_uniname, int *p_lossy) { int i = 0, unilen = 0, lossy = NLS_NAME_NO_LOSSY; - unsigned short upname[MAX_NAME_LENGTH + 1]; + __le16 upname[MAX_NAME_LENGTH + 1]; unsigned short *uniname = p_uniname->name; struct nls_table *nls = EXFAT_SB(sb)->nls_io; @@ -611,7 +611,7 @@ static int exfat_nls_to_ucs2(struct super_block *sb, exfat_wstrchr(bad_uni_chars, *uniname)) lossy |= NLS_NAME_LOSSY; - upname[unilen] = exfat_toupper(sb, *uniname); + upname[unilen] = cpu_to_le16(exfat_toupper(sb, *uniname)); uniname++; unilen++; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 10dd470876b3..44bad4bb8831 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1096,7 +1096,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, } if (unlikely(err)) { page_zero_new_buffers(page, from, to); - } else if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) { + } else if (fscrypt_inode_uses_fs_layer_crypto(inode)) { for (i = 0; i < nr_wait; i++) { int err2; @@ -3737,7 +3737,7 @@ static int __ext4_block_zero_page_range(handle_t *handle, /* Uhhuh. Read error. Complain and punt. */ if (!buffer_uptodate(bh)) goto unlock; - if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode)) { + if (fscrypt_inode_uses_fs_layer_crypto(inode)) { /* We expect the key to be set. */ BUG_ON(!fscrypt_has_encryption_key(inode)); err = fscrypt_decrypt_pagecache_blocks(page, blocksize, diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index de6fe969f773..defd2e10dfd1 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -402,6 +402,7 @@ static void io_submit_init_bio(struct ext4_io_submit *io, * __GFP_DIRECT_RECLAIM is set, see comments for bio_alloc_bioset(). */ bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); + fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_end_io = ext4_end_bio; @@ -418,7 +419,8 @@ static void io_submit_add_bh(struct ext4_io_submit *io, { int ret; - if (io->io_bio && bh->b_blocknr != io->io_next_block) { + if (io->io_bio && (bh->b_blocknr != io->io_next_block || + !fscrypt_mergeable_bio_bh(io->io_bio, bh))) { submit_and_retry: ext4_io_submit(io); } @@ -506,7 +508,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, * (e.g. holes) to be unnecessarily encrypted, but this is rare and * can't happen in the common case of blocksize == PAGE_SIZE. */ - if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode) && nr_to_submit) { + if (fscrypt_inode_uses_fs_layer_crypto(inode) && nr_to_submit) { gfp_t gfp_flags = GFP_NOFS; unsigned int enc_bytes = round_up(len, i_blocksize(inode)); diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 5761e9961682..f2df2db0786c 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -195,7 +195,7 @@ static void ext4_set_bio_post_read_ctx(struct bio *bio, { unsigned int post_read_steps = 0; - if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) + if (fscrypt_inode_uses_fs_layer_crypto(inode)) post_read_steps |= 1 << STEP_DECRYPT; if (ext4_need_verity(inode, first_idx)) @@ -230,6 +230,7 @@ int ext4_mpage_readpages(struct inode *inode, const unsigned blkbits = inode->i_blkbits; const unsigned blocks_per_page = PAGE_SIZE >> blkbits; const unsigned blocksize = 1 << blkbits; + sector_t next_block; sector_t block_in_file; sector_t last_block; sector_t last_block_in_file; @@ -258,7 +259,8 @@ int ext4_mpage_readpages(struct inode *inode, if (page_has_buffers(page)) goto confused; - block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits); + block_in_file = next_block = + (sector_t)page->index << (PAGE_SHIFT - blkbits); last_block = block_in_file + nr_pages * blocks_per_page; last_block_in_file = (ext4_readpage_limit(inode) + blocksize - 1) >> blkbits; @@ -358,7 +360,8 @@ int ext4_mpage_readpages(struct inode *inode, * This page will go to BIO. Do we need to send this * BIO off first? */ - if (bio && (last_block_in_bio != blocks[0] - 1)) { + if (bio && (last_block_in_bio != blocks[0] - 1 || + !fscrypt_mergeable_bio(bio, inode, next_block))) { submit_and_realloc: submit_bio(bio); bio = NULL; @@ -370,6 +373,8 @@ int ext4_mpage_readpages(struct inode *inode, */ bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES)); + fscrypt_set_bio_crypt_ctx(bio, inode, next_block, + GFP_KERNEL); ext4_set_bio_post_read_ctx(bio, inode, page->index); bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 330957ed1f05..0907f907c47d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1508,6 +1508,7 @@ enum { Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption, + Opt_inlinecrypt, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota, Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, @@ -1610,6 +1611,7 @@ static const match_table_t tokens = { {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, {Opt_test_dummy_encryption, "test_dummy_encryption=%s"}, {Opt_test_dummy_encryption, "test_dummy_encryption"}, + {Opt_inlinecrypt, "inlinecrypt"}, {Opt_nombcache, "nombcache"}, {Opt_nombcache, "no_mbcache"}, /* for backward compatibility */ {Opt_removed, "check=none"}, /* mount option from ext2/3 */ @@ -1946,6 +1948,13 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, case Opt_nolazytime: sb->s_flags &= ~SB_LAZYTIME; return 1; + case Opt_inlinecrypt: +#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT + sb->s_flags |= SB_INLINECRYPT; +#else + ext4_msg(sb, KERN_ERR, "inline encryption not supported"); +#endif + return 1; } for (m = ext4_mount_opts; m->token != Opt_err; m++) @@ -2404,6 +2413,9 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, fscrypt_show_test_dummy_encryption(seq, sep, sb); + if (sb->s_flags & SB_INLINECRYPT) + SEQ_OPTS_PUTS("inlinecrypt"); + if (test_opt(sb, DAX_ALWAYS)) { if (IS_EXT2_SB(sb)) SEQ_OPTS_PUTS("dax"); diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 1e02a8c106b0..29e50fbe7eca 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -1086,7 +1086,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, .submitted = false, .io_type = io_type, .io_wbc = wbc, - .encrypted = f2fs_encrypted_file(cc->inode), + .encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode), }; struct dnode_of_data dn; struct node_info ni; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 326c63879ddc..b9642607c07d 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -14,6 +14,7 @@ #include <linux/pagevec.h> #include <linux/blkdev.h> #include <linux/bio.h> +#include <linux/blk-crypto.h> #include <linux/swap.h> #include <linux/prefetch.h> #include <linux/uio.h> @@ -459,6 +460,33 @@ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages) return bio; } +static void f2fs_set_bio_crypt_ctx(struct bio *bio, const struct inode *inode, + pgoff_t first_idx, + const struct f2fs_io_info *fio, + gfp_t gfp_mask) +{ + /* + * The f2fs garbage collector sets ->encrypted_page when it wants to + * read/write raw data without encryption. + */ + if (!fio || !fio->encrypted_page) + fscrypt_set_bio_crypt_ctx(bio, inode, first_idx, gfp_mask); +} + +static bool f2fs_crypt_mergeable_bio(struct bio *bio, const struct inode *inode, + pgoff_t next_idx, + const struct f2fs_io_info *fio) +{ + /* + * The f2fs garbage collector sets ->encrypted_page when it wants to + * read/write raw data without encryption. + */ + if (fio && fio->encrypted_page) + return !bio_has_crypt_ctx(bio); + + return fscrypt_mergeable_bio(bio, inode, next_idx); +} + static inline void __submit_bio(struct f2fs_sb_info *sbi, struct bio *bio, enum page_type type) { @@ -684,6 +712,9 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) /* Allocate a new bio */ bio = __bio_alloc(fio, 1); + f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host, + fio->page->index, fio, GFP_NOIO); + if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { bio_put(bio); return -EFAULT; @@ -763,9 +794,10 @@ static void del_bio_entry(struct bio_entry *be) kmem_cache_free(bio_entry_slab, be); } -static int add_ipu_page(struct f2fs_sb_info *sbi, struct bio **bio, +static int add_ipu_page(struct f2fs_io_info *fio, struct bio **bio, struct page *page) { + struct f2fs_sb_info *sbi = fio->sbi; enum temp_type temp; bool found = false; int ret = -EAGAIN; @@ -782,13 +814,19 @@ static int add_ipu_page(struct f2fs_sb_info *sbi, struct bio **bio, found = true; - if (bio_add_page(*bio, page, PAGE_SIZE, 0) == - PAGE_SIZE) { + f2fs_bug_on(sbi, !page_is_mergeable(sbi, *bio, + *fio->last_block, + fio->new_blkaddr)); + if (f2fs_crypt_mergeable_bio(*bio, + fio->page->mapping->host, + fio->page->index, fio) && + bio_add_page(*bio, page, PAGE_SIZE, 0) == + PAGE_SIZE) { ret = 0; break; } - /* bio is full */ + /* page can't be merged into bio; submit the bio */ del_bio_entry(be); __submit_bio(sbi, *bio, DATA); break; @@ -880,11 +918,13 @@ alloc_new: if (!bio) { bio = __bio_alloc(fio, BIO_MAX_PAGES); __attach_io_flag(fio); + f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host, + fio->page->index, fio, GFP_NOIO); bio_set_op_attrs(bio, fio->op, fio->op_flags); add_bio_entry(fio->sbi, bio, page, fio->temp); } else { - if (add_ipu_page(fio->sbi, &bio, page)) + if (add_ipu_page(fio, &bio, page)) goto alloc_new; } @@ -936,8 +976,11 @@ next: inc_page_count(sbi, WB_DATA_TYPE(bio_page)); - if (io->bio && !io_is_mergeable(sbi, io->bio, io, fio, - io->last_block_in_bio, fio->new_blkaddr)) + if (io->bio && + (!io_is_mergeable(sbi, io->bio, io, fio, io->last_block_in_bio, + fio->new_blkaddr) || + !f2fs_crypt_mergeable_bio(io->bio, fio->page->mapping->host, + bio_page->index, fio))) __submit_merged_bio(io); alloc_new: if (io->bio == NULL) { @@ -949,6 +992,8 @@ alloc_new: goto skip; } io->bio = __bio_alloc(fio, BIO_MAX_PAGES); + f2fs_set_bio_crypt_ctx(io->bio, fio->page->mapping->host, + bio_page->index, fio, GFP_NOIO); io->fio = *fio; } @@ -993,11 +1038,14 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, for_write); if (!bio) return ERR_PTR(-ENOMEM); + + f2fs_set_bio_crypt_ctx(bio, inode, first_idx, NULL, GFP_NOFS); + f2fs_target_device(sbi, blkaddr, bio); bio->bi_end_io = f2fs_read_end_io; bio_set_op_attrs(bio, REQ_OP_READ, op_flag); - if (f2fs_encrypted_file(inode)) + if (fscrypt_inode_uses_fs_layer_crypto(inode)) post_read_steps |= 1 << STEP_DECRYPT; if (f2fs_compressed_file(inode)) post_read_steps |= 1 << STEP_DECOMPRESS_NOWQ; @@ -2073,8 +2121,9 @@ zero_out: * This page will go to BIO. Do we need to send this * BIO off first? */ - if (bio && !page_is_mergeable(F2FS_I_SB(inode), bio, - *last_block_in_bio, block_nr)) { + if (bio && (!page_is_mergeable(F2FS_I_SB(inode), bio, + *last_block_in_bio, block_nr) || + !f2fs_crypt_mergeable_bio(bio, inode, page->index, NULL))) { submit_and_realloc: __submit_bio(F2FS_I_SB(inode), bio, DATA); bio = NULL; @@ -2204,8 +2253,9 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, blkaddr = data_blkaddr(dn.inode, dn.node_page, dn.ofs_in_node + i + 1); - if (bio && !page_is_mergeable(sbi, bio, - *last_block_in_bio, blkaddr)) { + if (bio && (!page_is_mergeable(sbi, bio, + *last_block_in_bio, blkaddr) || + !f2fs_crypt_mergeable_bio(bio, inode, page->index, NULL))) { submit_and_realloc: __submit_bio(sbi, bio, DATA); bio = NULL; @@ -2421,6 +2471,9 @@ int f2fs_encrypt_one_page(struct f2fs_io_info *fio) /* wait for GCed page writeback via META_MAPPING */ f2fs_wait_on_block_writeback(inode, fio->old_blkaddr); + if (fscrypt_inode_uses_inline_crypto(inode)) + return 0; + retry_encrypt: fio->encrypted_page = fscrypt_encrypt_pagecache_blocks(page, PAGE_SIZE, 0, gfp_flags); @@ -2594,7 +2647,7 @@ got_it: f2fs_unlock_op(fio->sbi); err = f2fs_inplace_write_data(fio); if (err) { - if (f2fs_encrypted_file(inode)) + if (fscrypt_inode_uses_fs_layer_crypto(inode)) fscrypt_finalize_bounce_page(&fio->encrypted_page); if (PageWriteback(page)) end_page_writeback(page); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 20e56b0fa46a..23c49c313fb6 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -138,6 +138,7 @@ enum { Opt_alloc, Opt_fsync, Opt_test_dummy_encryption, + Opt_inlinecrypt, Opt_checkpoint_disable, Opt_checkpoint_disable_cap, Opt_checkpoint_disable_cap_perc, @@ -204,6 +205,7 @@ static match_table_t f2fs_tokens = { {Opt_fsync, "fsync_mode=%s"}, {Opt_test_dummy_encryption, "test_dummy_encryption=%s"}, {Opt_test_dummy_encryption, "test_dummy_encryption"}, + {Opt_inlinecrypt, "inlinecrypt"}, {Opt_checkpoint_disable, "checkpoint=disable"}, {Opt_checkpoint_disable_cap, "checkpoint=disable:%u"}, {Opt_checkpoint_disable_cap_perc, "checkpoint=disable:%u%%"}, @@ -833,6 +835,13 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) if (ret) return ret; break; + case Opt_inlinecrypt: +#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT + sb->s_flags |= SB_INLINECRYPT; +#else + f2fs_info(sbi, "inline encryption not supported"); +#endif + break; case Opt_checkpoint_disable_cap_perc: if (args->from && match_int(args, &arg)) return -EINVAL; @@ -1590,6 +1599,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) fscrypt_show_test_dummy_encryption(seq, ',', sbi->sb); + if (sbi->sb->s_flags & SB_INLINECRYPT) + seq_puts(seq, ",inlinecrypt"); + if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_DEFAULT) seq_printf(seq, ",alloc_mode=%s", "default"); else if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE) @@ -1624,6 +1636,8 @@ static void default_options(struct f2fs_sb_info *sbi) F2FS_OPTION(sbi).compress_ext_cnt = 0; F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON; + sbi->sb->s_flags &= ~SB_INLINECRYPT; + set_opt(sbi, INLINE_XATTR); set_opt(sbi, INLINE_DATA); set_opt(sbi, INLINE_DENTRY); @@ -2470,6 +2484,25 @@ static void f2fs_get_ino_and_lblk_bits(struct super_block *sb, *lblk_bits_ret = 8 * sizeof(block_t); } +static int f2fs_get_num_devices(struct super_block *sb) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); + + if (f2fs_is_multi_device(sbi)) + return sbi->s_ndevs; + return 1; +} + +static void f2fs_get_devices(struct super_block *sb, + struct request_queue **devs) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); + int i; + + for (i = 0; i < sbi->s_ndevs; i++) + devs[i] = bdev_get_queue(FDEV(i).bdev); +} + static const struct fscrypt_operations f2fs_cryptops = { .key_prefix = "f2fs:", .get_context = f2fs_get_context, @@ -2479,6 +2512,8 @@ static const struct fscrypt_operations f2fs_cryptops = { .max_namelen = F2FS_NAME_LEN, .has_stable_inodes = f2fs_has_stable_inodes, .get_ino_and_lblk_bits = f2fs_get_ino_and_lblk_bits, + .get_num_devices = f2fs_get_num_devices, + .get_devices = f2fs_get_devices, }; #endif diff --git a/fs/io_uring.c b/fs/io_uring.c index 74bc4a04befa..493e5047e67c 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -605,6 +605,7 @@ enum { struct async_poll { struct io_poll_iocb poll; + struct io_poll_iocb *double_poll; struct io_wq_work work; }; @@ -4159,9 +4160,9 @@ static bool io_poll_rewait(struct io_kiocb *req, struct io_poll_iocb *poll) return false; } -static void io_poll_remove_double(struct io_kiocb *req) +static void io_poll_remove_double(struct io_kiocb *req, void *data) { - struct io_poll_iocb *poll = (struct io_poll_iocb *) req->io; + struct io_poll_iocb *poll = data; lockdep_assert_held(&req->ctx->completion_lock); @@ -4181,7 +4182,7 @@ static void io_poll_complete(struct io_kiocb *req, __poll_t mask, int error) { struct io_ring_ctx *ctx = req->ctx; - io_poll_remove_double(req); + io_poll_remove_double(req, req->io); req->poll.done = true; io_cqring_fill_event(req, error ? error : mangle_poll(mask)); io_commit_cqring(ctx); @@ -4198,10 +4199,9 @@ static void io_poll_task_handler(struct io_kiocb *req, struct io_kiocb **nxt) hash_del(&req->hash_node); io_poll_complete(req, req->result, 0); - req->flags |= REQ_F_COMP_LOCKED; - io_put_req_find_next(req, nxt); spin_unlock_irq(&ctx->completion_lock); + io_put_req_find_next(req, nxt); io_cqring_ev_posted(ctx); } @@ -4224,21 +4224,21 @@ static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode, int sync, void *key) { struct io_kiocb *req = wait->private; - struct io_poll_iocb *poll = (struct io_poll_iocb *) req->io; + struct io_poll_iocb *poll = req->apoll->double_poll; __poll_t mask = key_to_poll(key); /* for instances that support it check for an event match first: */ if (mask && !(mask & poll->events)) return 0; - if (req->poll.head) { + if (poll && poll->head) { bool done; - spin_lock(&req->poll.head->lock); - done = list_empty(&req->poll.wait.entry); + spin_lock(&poll->head->lock); + done = list_empty(&poll->wait.entry); if (!done) - list_del_init(&req->poll.wait.entry); - spin_unlock(&req->poll.head->lock); + list_del_init(&poll->wait.entry); + spin_unlock(&poll->head->lock); if (!done) __io_async_wake(req, poll, mask, io_poll_task_func); } @@ -4258,7 +4258,8 @@ static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events, } static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, - struct wait_queue_head *head) + struct wait_queue_head *head, + struct io_poll_iocb **poll_ptr) { struct io_kiocb *req = pt->req; @@ -4269,7 +4270,7 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, */ if (unlikely(poll->head)) { /* already have a 2nd entry, fail a third attempt */ - if (req->io) { + if (*poll_ptr) { pt->error = -EINVAL; return; } @@ -4281,7 +4282,7 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, io_init_poll_iocb(poll, req->poll.events, io_poll_double_wake); refcount_inc(&req->refs); poll->wait.private = req; - req->io = (void *) poll; + *poll_ptr = poll; } pt->error = 0; @@ -4293,8 +4294,9 @@ static void io_async_queue_proc(struct file *file, struct wait_queue_head *head, struct poll_table_struct *p) { struct io_poll_table *pt = container_of(p, struct io_poll_table, pt); + struct async_poll *apoll = pt->req->apoll; - __io_queue_proc(&pt->req->apoll->poll, pt, head); + __io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll); } static void io_sq_thread_drop_mm(struct io_ring_ctx *ctx) @@ -4344,11 +4346,13 @@ static void io_async_task_func(struct callback_head *cb) } } + io_poll_remove_double(req, apoll->double_poll); spin_unlock_irq(&ctx->completion_lock); /* restore ->work in case we need to retry again */ if (req->flags & REQ_F_WORK_INITIALIZED) memcpy(&req->work, &apoll->work, sizeof(req->work)); + kfree(apoll->double_poll); kfree(apoll); if (!canceled) { @@ -4436,7 +4440,6 @@ static bool io_arm_poll_handler(struct io_kiocb *req) struct async_poll *apoll; struct io_poll_table ipt; __poll_t mask, ret; - bool had_io; if (!req->file || !file_can_poll(req->file)) return false; @@ -4448,11 +4451,11 @@ static bool io_arm_poll_handler(struct io_kiocb *req) apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); if (unlikely(!apoll)) return false; + apoll->double_poll = NULL; req->flags |= REQ_F_POLLED; if (req->flags & REQ_F_WORK_INITIALIZED) memcpy(&apoll->work, &req->work, sizeof(req->work)); - had_io = req->io != NULL; io_get_req_task(req); req->apoll = apoll; @@ -4470,13 +4473,11 @@ static bool io_arm_poll_handler(struct io_kiocb *req) ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask, io_async_wake); if (ret) { - ipt.error = 0; - /* only remove double add if we did it here */ - if (!had_io) - io_poll_remove_double(req); + io_poll_remove_double(req, apoll->double_poll); spin_unlock_irq(&ctx->completion_lock); if (req->flags & REQ_F_WORK_INITIALIZED) memcpy(&req->work, &apoll->work, sizeof(req->work)); + kfree(apoll->double_poll); kfree(apoll); return false; } @@ -4507,11 +4508,13 @@ static bool io_poll_remove_one(struct io_kiocb *req) bool do_complete; if (req->opcode == IORING_OP_POLL_ADD) { - io_poll_remove_double(req); + io_poll_remove_double(req, req->io); do_complete = __io_poll_remove_one(req, &req->poll); } else { struct async_poll *apoll = req->apoll; + io_poll_remove_double(req, apoll->double_poll); + /* non-poll requests have submit ref still */ do_complete = __io_poll_remove_one(req, &apoll->poll); if (do_complete) { @@ -4524,6 +4527,7 @@ static bool io_poll_remove_one(struct io_kiocb *req) if (req->flags & REQ_F_WORK_INITIALIZED) memcpy(&req->work, &apoll->work, sizeof(req->work)); + kfree(apoll->double_poll); kfree(apoll); } } @@ -4624,7 +4628,7 @@ static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head, { struct io_poll_table *pt = container_of(p, struct io_poll_table, pt); - __io_queue_proc(&pt->req->poll, pt, head); + __io_queue_proc(&pt->req->poll, pt, head, (struct io_poll_iocb **) &pt->req->io); } static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) @@ -4653,6 +4657,10 @@ static int io_poll_add(struct io_kiocb *req) struct io_poll_table ipt; __poll_t mask; + /* ->work is in union with hash_node and others */ + io_req_work_drop_env(req); + req->flags &= ~REQ_F_WORK_INITIALIZED; + INIT_HLIST_NODE(&req->hash_node); INIT_LIST_HEAD(&req->list); ipt.pt._qproc = io_poll_queue_proc; @@ -4732,7 +4740,9 @@ static int io_timeout_remove_prep(struct io_kiocb *req, { if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len) + if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) + return -EINVAL; + if (sqe->ioprio || sqe->buf_index || sqe->len) return -EINVAL; req->timeout.addr = READ_ONCE(sqe->addr); @@ -4910,8 +4920,9 @@ static int io_async_cancel_prep(struct io_kiocb *req, { if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - if (sqe->flags || sqe->ioprio || sqe->off || sqe->len || - sqe->cancel_flags) + if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) + return -EINVAL; + if (sqe->ioprio || sqe->off || sqe->len || sqe->cancel_flags) return -EINVAL; req->cancel.addr = READ_ONCE(sqe->addr); @@ -4929,7 +4940,9 @@ static int io_async_cancel(struct io_kiocb *req) static int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (sqe->flags || sqe->ioprio || sqe->rw_flags) + if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) + return -EINVAL; + if (sqe->ioprio || sqe->rw_flags) return -EINVAL; req->files_update.offset = READ_ONCE(sqe->off); @@ -5720,6 +5733,7 @@ fail_req: * Never try inline submit of IOSQE_ASYNC is set, go straight * to async execution. */ + io_req_init_async(req); req->work.flags |= IO_WQ_WORK_CONCURRENT; io_queue_async_work(req); } else { diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index cce2510b2cca..c9056316a0b3 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -507,6 +507,17 @@ find_any_file(struct nfs4_file *f) return ret; } +static struct nfsd_file *find_deleg_file(struct nfs4_file *f) +{ + struct nfsd_file *ret = NULL; + + spin_lock(&f->fi_lock); + if (f->fi_deleg_file) + ret = nfsd_file_get(f->fi_deleg_file); + spin_unlock(&f->fi_lock); + return ret; +} + static atomic_long_t num_delegations; unsigned long max_delegations; @@ -2444,6 +2455,8 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) oo = ols->st_stateowner; nf = st->sc_file; file = find_any_file(nf); + if (!file) + return 0; seq_printf(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); @@ -2481,6 +2494,8 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st) oo = ols->st_stateowner; nf = st->sc_file; file = find_any_file(nf); + if (!file) + return 0; seq_printf(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); @@ -2513,7 +2528,9 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) ds = delegstateid(st); nf = st->sc_file; - file = nf->fi_deleg_file; + file = find_deleg_file(nf); + if (!file) + return 0; seq_printf(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); @@ -2529,6 +2546,7 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) seq_printf(s, ", "); nfs4_show_fname(s, file); seq_printf(s, " }\n"); + nfsd_file_put(file); return 0; } diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 64f61330564a..76bb1c846845 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -175,7 +175,7 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length, /* Extract the length of the metadata block */ data = page_address(bvec->bv_page) + bvec->bv_offset; length = data[offset]; - if (offset <= bvec->bv_len - 1) { + if (offset < bvec->bv_len - 1) { length |= data[offset + 1] << 8; } else { if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all))) { diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 07bc42d62673..abfb17f88f9a 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -607,14 +607,14 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) int nr_pages; ssize_t ret; - nr_pages = iov_iter_npages(from, BIO_MAX_PAGES); - if (!nr_pages) - return 0; - max = queue_max_zone_append_sectors(bdev_get_queue(bdev)); max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize); iov_iter_truncate(from, max); + nr_pages = iov_iter_npages(from, BIO_MAX_PAGES); + if (!nr_pages) + return 0; + bio = bio_alloc_bioset(GFP_NOFS, nr_pages, &fs_bio_set); if (!bio) return -ENOMEM; @@ -1119,7 +1119,7 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd, char *file_name; struct dentry *dir; unsigned int n = 0; - int ret = -ENOMEM; + int ret; /* If the group is empty, there is nothing to do */ if (!zd->nr_zones[type]) @@ -1135,8 +1135,10 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd, zgroup_name = "seq"; dir = zonefs_create_inode(sb->s_root, zgroup_name, NULL, type); - if (!dir) + if (!dir) { + ret = -ENOMEM; goto free; + } /* * The first zone contains the super block: skip it. @@ -1174,8 +1176,10 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd, * Use the file number within its group as file name. */ snprintf(file_name, ZONEFS_NAME_MAX - 1, "%u", n); - if (!zonefs_create_inode(dir, file_name, zone, type)) + if (!zonefs_create_inode(dir, file_name, zone, type)) { + ret = -ENOMEM; goto free; + } n++; } diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h index b0b163b9efc6..bdcac69fa6bd 100644 --- a/include/acpi/actbl3.h +++ b/include/acpi/actbl3.h @@ -415,6 +415,13 @@ struct acpi_table_tpm2 { /* Platform-specific data follows */ }; +/* Optional trailer for revision 4 holding platform-specific data */ +struct acpi_tpm2_phy { + u8 start_method_specific[12]; + u32 log_area_minimum_length; + u64 log_area_start_address; +}; + /* Values for start_method above */ #define ACPI_TPM2_NOT_ALLOWED 0 diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 8b1e020e9a03..30a3aab312e6 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -456,7 +456,7 @@ static inline void writesq(volatile void __iomem *addr, const void *buffer, #if !defined(inb) && !defined(_inb) #define _inb _inb -static inline u16 _inb(unsigned long addr) +static inline u8 _inb(unsigned long addr) { u8 val; @@ -482,7 +482,7 @@ static inline u16 _inw(unsigned long addr) #if !defined(inl) && !defined(_inl) #define _inl _inl -static inline u16 _inl(unsigned long addr) +static inline u32 _inl(unsigned long addr) { u32 val; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index db600ef218d7..052e0f05a984 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -341,7 +341,8 @@ #define PAGE_ALIGNED_DATA(page_align) \ . = ALIGN(page_align); \ - *(.data..page_aligned) + *(.data..page_aligned) \ + . = ALIGN(page_align); #define READ_MOSTLY_DATA(align) \ . = ALIGN(align); \ @@ -737,7 +738,9 @@ . = ALIGN(bss_align); \ .bss : AT(ADDR(.bss) - LOAD_OFFSET) { \ BSS_FIRST_SECTIONS \ + . = ALIGN(PAGE_SIZE); \ *(.bss..page_aligned) \ + . = ALIGN(PAGE_SIZE); \ *(.dynbss) \ *(BSS_MAIN) \ *(COMMON) \ diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index 6c3ef49b46b3..e73dea5c7333 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -866,6 +866,18 @@ struct drm_mode_config { bool prefer_shadow_fbdev; /** + * @fbdev_use_iomem: + * + * Set to true if framebuffer reside in iomem. + * When set to true memcpy_toio() is used when copying the framebuffer in + * drm_fb_helper.drm_fb_helper_dirty_blit_real(). + * + * FIXME: This should be replaced with a per-mapping is_iomem + * flag (like ttm does), and then used everywhere in fbdev code. + */ + bool fbdev_use_iomem; + + /** * @quirk_addfb_prefer_xbgr_30bpp: * * Special hack for legacy ADDFB to keep nouveau userspace happy. Should diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 8750f2dc5613..73dec4b5d5be 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -426,6 +426,7 @@ const char *dm_device_name(struct mapped_device *md); int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid); struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct dm_target *ti); +int dm_post_suspending(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); union map_info *dm_get_rq_mapinfo(struct request *rq); diff --git a/include/linux/efi.h b/include/linux/efi.h index bb35f3305e55..05c47f857383 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -994,6 +994,7 @@ int efivars_register(struct efivars *efivars, int efivars_unregister(struct efivars *efivars); struct kobject *efivars_kobject(void); +int efivar_supports_writes(void); int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), void *data, bool duplicates, struct list_head *head); diff --git a/include/linux/fs.h b/include/linux/fs.h index f5abba86107d..0a6394178360 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1381,6 +1381,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_NODIRATIME 2048 /* Do not update directory access times */ #define SB_SILENT 32768 #define SB_POSIXACL (1<<16) /* VFS does not apply the umask */ +#define SB_INLINECRYPT (1<<17) /* Use blk-crypto for encrypted files */ #define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */ #define SB_I_VERSION (1<<23) /* Update inode I_version field */ #define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 2862ca5fea33..991ff8575d0e 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -69,12 +69,20 @@ struct fscrypt_operations { bool (*has_stable_inodes)(struct super_block *sb); void (*get_ino_and_lblk_bits)(struct super_block *sb, int *ino_bits_ret, int *lblk_bits_ret); + int (*get_num_devices)(struct super_block *sb); + void (*get_devices)(struct super_block *sb, + struct request_queue **devs); }; -static inline bool fscrypt_has_encryption_key(const struct inode *inode) +static inline struct fscrypt_info *fscrypt_get_info(const struct inode *inode) { - /* pairs with cmpxchg_release() in fscrypt_get_encryption_info() */ - return READ_ONCE(inode->i_crypt_info) != NULL; + /* + * Pairs with the cmpxchg_release() in fscrypt_get_encryption_info(). + * I.e., another task may publish ->i_crypt_info concurrently, executing + * a RELEASE barrier. We need to use smp_load_acquire() here to safely + * ACQUIRE the memory the other task published. + */ + return smp_load_acquire(&inode->i_crypt_info); } /** @@ -231,9 +239,9 @@ static inline void fscrypt_set_ops(struct super_block *sb, } #else /* !CONFIG_FS_ENCRYPTION */ -static inline bool fscrypt_has_encryption_key(const struct inode *inode) +static inline struct fscrypt_info *fscrypt_get_info(const struct inode *inode) { - return false; + return NULL; } static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) @@ -537,6 +545,99 @@ static inline void fscrypt_set_ops(struct super_block *sb, #endif /* !CONFIG_FS_ENCRYPTION */ +/* inline_crypt.c */ +#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT + +bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode); + +void fscrypt_set_bio_crypt_ctx(struct bio *bio, + const struct inode *inode, u64 first_lblk, + gfp_t gfp_mask); + +void fscrypt_set_bio_crypt_ctx_bh(struct bio *bio, + const struct buffer_head *first_bh, + gfp_t gfp_mask); + +bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode, + u64 next_lblk); + +bool fscrypt_mergeable_bio_bh(struct bio *bio, + const struct buffer_head *next_bh); + +#else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ + +static inline bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode) +{ + return false; +} + +static inline void fscrypt_set_bio_crypt_ctx(struct bio *bio, + const struct inode *inode, + u64 first_lblk, gfp_t gfp_mask) { } + +static inline void fscrypt_set_bio_crypt_ctx_bh( + struct bio *bio, + const struct buffer_head *first_bh, + gfp_t gfp_mask) { } + +static inline bool fscrypt_mergeable_bio(struct bio *bio, + const struct inode *inode, + u64 next_lblk) +{ + return true; +} + +static inline bool fscrypt_mergeable_bio_bh(struct bio *bio, + const struct buffer_head *next_bh) +{ + return true; +} +#endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ + +/** + * fscrypt_inode_uses_inline_crypto() - test whether an inode uses inline + * encryption + * @inode: an inode. If encrypted, its key must be set up. + * + * Return: true if the inode requires file contents encryption and if the + * encryption should be done in the block layer via blk-crypto rather + * than in the filesystem layer. + */ +static inline bool fscrypt_inode_uses_inline_crypto(const struct inode *inode) +{ + return fscrypt_needs_contents_encryption(inode) && + __fscrypt_inode_uses_inline_crypto(inode); +} + +/** + * fscrypt_inode_uses_fs_layer_crypto() - test whether an inode uses fs-layer + * encryption + * @inode: an inode. If encrypted, its key must be set up. + * + * Return: true if the inode requires file contents encryption and if the + * encryption should be done in the filesystem layer rather than in the + * block layer via blk-crypto. + */ +static inline bool fscrypt_inode_uses_fs_layer_crypto(const struct inode *inode) +{ + return fscrypt_needs_contents_encryption(inode) && + !__fscrypt_inode_uses_inline_crypto(inode); +} + +/** + * fscrypt_has_encryption_key() - check whether an inode has had its key set up + * @inode: the inode to check + * + * Return: %true if the inode has had its encryption key set up, else %false. + * + * Usually this should be preceded by fscrypt_get_encryption_info() to try to + * set up the key first. + */ +static inline bool fscrypt_has_encryption_key(const struct inode *inode) +{ + return fscrypt_get_info(inode) != NULL; +} + /** * fscrypt_require_key() - require an inode's encryption key * @inode: the inode we need the key for diff --git a/include/linux/i2c.h b/include/linux/i2c.h index b8b8963f8bb9..4e7714c88f95 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -56,7 +56,7 @@ struct property_entry; * on a bus (or read from them). Apart from two basic transfer functions to * transmit one message at a time, a more complex version can be used to * transmit an arbitrary number of messages without interruption. - * @count must be be less than 64k since msg.len is u16. + * @count must be less than 64k since msg.len is u16. */ int i2c_transfer_buffer_flags(const struct i2c_client *client, char *buf, int count, u16 flags); @@ -1001,7 +1001,7 @@ static inline u32 i2c_acpi_find_bus_speed(struct device *dev) static inline struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, struct i2c_board_info *info) { - return NULL; + return ERR_PTR(-ENODEV); } static inline struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle) { diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 0beaa3eba155..c75e4d3d8833 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -107,9 +107,12 @@ io_mapping_init_wc(struct io_mapping *iomap, resource_size_t base, unsigned long size) { + iomap->iomem = ioremap_wc(base, size); + if (!iomap->iomem) + return NULL; + iomap->base = base; iomap->size = size; - iomap->iomem = ioremap_wc(base, size); #if defined(pgprot_noncached_wc) /* archs can't agree on a name ... */ iomap->prot = pgprot_noncached_wc(PAGE_KERNEL); #elif defined(pgprot_writecombine) diff --git a/include/linux/list.h b/include/linux/list.h index aff44d34f4e4..0d0d17a10d25 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -283,6 +283,24 @@ static inline int list_empty(const struct list_head *head) } /** + * list_del_init_careful - deletes entry from list and reinitialize it. + * @entry: the element to delete from the list. + * + * This is the same as list_del_init(), except designed to be used + * together with list_empty_careful() in a way to guarantee ordering + * of other memory operations. + * + * Any memory operations done before a list_del_init_careful() are + * guaranteed to be visible after a list_empty_careful() test. + */ +static inline void list_del_init_careful(struct list_head *entry) +{ + __list_del_entry(entry); + entry->prev = entry; + smp_store_release(&entry->next, entry); +} + +/** * list_empty_careful - tests whether a list is empty and not being modified * @head: the list to test * @@ -297,7 +315,7 @@ static inline int list_empty(const struct list_head *head) */ static inline int list_empty_careful(const struct list_head *head) { - struct list_head *next = head->next; + struct list_head *next = smp_load_acquire(&head->next); return (next == head) && (next == head->prev); } diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 073b79eacc99..1340e02b14ef 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4381,6 +4381,7 @@ struct mlx5_ifc_query_vport_state_out_bits { enum { MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT = 0x0, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT = 0x1, + MLX5_VPORT_STATE_OP_MOD_UPLINK = 0x2, }; struct mlx5_ifc_arm_monitor_counter_in_bits { diff --git a/include/linux/random.h b/include/linux/random.h index 45e1f8fa742b..9ab7443bd91b 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/list.h> #include <linux/once.h> +#include <asm/percpu.h> #include <uapi/linux/random.h> @@ -119,6 +120,8 @@ struct rnd_state { __u32 s1, s2, s3, s4; }; +DECLARE_PER_CPU(struct rnd_state, net_rand_state); + u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 70ebef866cc8..68dab3e08aad 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -33,7 +33,7 @@ * of two or more hash tables when the rhashtable is being resized. * The end of the chain is marked with a special nulls marks which has * the least significant bit set but otherwise stores the address of - * the hash bucket. This allows us to be be sure we've found the end + * the hash bucket. This allows us to be sure we've found the end * of the right list. * The value stored in the hash bucket has BIT(0) used as a lock bit. * This bit must be atomically set before any changes are made to @@ -84,7 +84,7 @@ struct bucket_table { struct lockdep_map dep_map; - struct rhash_lock_head *buckets[] ____cacheline_aligned_in_smp; + struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; /* @@ -261,13 +261,12 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, void *arg); void rhashtable_destroy(struct rhashtable *ht); -struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash); -struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash); -struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht, - struct bucket_table *tbl, - unsigned int hash); +struct rhash_lock_head __rcu **rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash); +struct rhash_lock_head __rcu **__rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash); +struct rhash_lock_head __rcu **rht_bucket_nested_insert( + struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash); #define rht_dereference(p, ht) \ rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht)) @@ -284,21 +283,21 @@ struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht, #define rht_entry(tpos, pos, member) \ ({ tpos = container_of(pos, typeof(*tpos), member); 1; }) -static inline struct rhash_lock_head *const *rht_bucket( +static inline struct rhash_lock_head __rcu *const *rht_bucket( const struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } -static inline struct rhash_lock_head **rht_bucket_var( +static inline struct rhash_lock_head __rcu **rht_bucket_var( struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) : &tbl->buckets[hash]; } -static inline struct rhash_lock_head **rht_bucket_insert( +static inline struct rhash_lock_head __rcu **rht_bucket_insert( struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) { return unlikely(tbl->nest) ? rht_bucket_nested_insert(ht, tbl, hash) : @@ -325,7 +324,7 @@ static inline struct rhash_lock_head **rht_bucket_insert( */ static inline void rht_lock(struct bucket_table *tbl, - struct rhash_lock_head **bkt) + struct rhash_lock_head __rcu **bkt) { local_bh_disable(); bit_spin_lock(0, (unsigned long *)bkt); @@ -333,7 +332,7 @@ static inline void rht_lock(struct bucket_table *tbl, } static inline void rht_lock_nested(struct bucket_table *tbl, - struct rhash_lock_head **bucket, + struct rhash_lock_head __rcu **bucket, unsigned int subclass) { local_bh_disable(); @@ -342,18 +341,18 @@ static inline void rht_lock_nested(struct bucket_table *tbl, } static inline void rht_unlock(struct bucket_table *tbl, - struct rhash_lock_head **bkt) + struct rhash_lock_head __rcu **bkt) { lock_map_release(&tbl->dep_map); bit_spin_unlock(0, (unsigned long *)bkt); local_bh_enable(); } -static inline struct rhash_head __rcu *__rht_ptr( - struct rhash_lock_head *const *bkt) +static inline struct rhash_head *__rht_ptr( + struct rhash_lock_head *p, struct rhash_lock_head __rcu *const *bkt) { - return (struct rhash_head __rcu *) - ((unsigned long)*bkt & ~BIT(0) ?: + return (struct rhash_head *) + ((unsigned long)p & ~BIT(0) ?: (unsigned long)RHT_NULLS_MARKER(bkt)); } @@ -365,47 +364,41 @@ static inline struct rhash_head __rcu *__rht_ptr( * access is guaranteed, such as when destroying the table. */ static inline struct rhash_head *rht_ptr_rcu( - struct rhash_lock_head *const *bkt) + struct rhash_lock_head __rcu *const *bkt) { - struct rhash_head __rcu *p = __rht_ptr(bkt); - - return rcu_dereference(p); + return __rht_ptr(rcu_dereference(*bkt), bkt); } static inline struct rhash_head *rht_ptr( - struct rhash_lock_head *const *bkt, + struct rhash_lock_head __rcu *const *bkt, struct bucket_table *tbl, unsigned int hash) { - return rht_dereference_bucket(__rht_ptr(bkt), tbl, hash); + return __rht_ptr(rht_dereference_bucket(*bkt, tbl, hash), bkt); } static inline struct rhash_head *rht_ptr_exclusive( - struct rhash_lock_head *const *bkt) + struct rhash_lock_head __rcu *const *bkt) { - return rcu_dereference_protected(__rht_ptr(bkt), 1); + return __rht_ptr(rcu_dereference_protected(*bkt, 1), bkt); } -static inline void rht_assign_locked(struct rhash_lock_head **bkt, +static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt, struct rhash_head *obj) { - struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; - if (rht_is_a_nulls(obj)) obj = NULL; - rcu_assign_pointer(*p, (void *)((unsigned long)obj | BIT(0))); + rcu_assign_pointer(*bkt, (void *)((unsigned long)obj | BIT(0))); } static inline void rht_assign_unlock(struct bucket_table *tbl, - struct rhash_lock_head **bkt, + struct rhash_lock_head __rcu **bkt, struct rhash_head *obj) { - struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt; - if (rht_is_a_nulls(obj)) obj = NULL; lock_map_release(&tbl->dep_map); - rcu_assign_pointer(*p, obj); + rcu_assign_pointer(*bkt, (void *)obj); preempt_enable(); __release(bitlock); local_bh_enable(); @@ -593,7 +586,7 @@ static inline struct rhash_head *__rhashtable_lookup( .ht = ht, .key = key, }; - struct rhash_lock_head *const *bkt; + struct rhash_lock_head __rcu *const *bkt; struct bucket_table *tbl; struct rhash_head *he; unsigned int hash; @@ -709,7 +702,7 @@ static inline void *__rhashtable_insert_fast( .ht = ht, .key = key, }; - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct bucket_table *tbl; struct rhash_head *head; @@ -995,7 +988,7 @@ static inline int __rhashtable_remove_fast_one( struct rhash_head *obj, const struct rhashtable_params params, bool rhlist) { - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; unsigned int hash; @@ -1147,7 +1140,7 @@ static inline int __rhashtable_replace_fast( struct rhash_head *obj_old, struct rhash_head *obj_new, const struct rhashtable_params params) { - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; unsigned int hash; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 9aac824c523c..a1bbaa1c1a3a 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -220,7 +220,9 @@ struct tcp_sock { } rack; u16 advmss; /* Advertised MSS */ u8 compressed_ack; - u8 dup_ack_counter; + u8 dup_ack_counter:2, + tlp_retrans:1, /* TLP is a retransmission */ + unused:5; u32 chrono_start; /* Start time in jiffies of a TCP chrono */ u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u8 chrono_type:2, /* current chronograph type */ @@ -243,7 +245,7 @@ struct tcp_sock { save_syn:1, /* Save headers of SYN packet */ is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ syn_smc:1; /* SYN includes SMC */ - u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ + u32 tlp_high_seq; /* snd_nxt at the time of TLP */ u32 tcp_tx_delay; /* delay (in usec) added to TX packets */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 03e9b184411b..8f4ff39f51e7 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -96,6 +96,7 @@ struct tpm_space { u8 *context_buf; u32 session_tbl[3]; u8 *session_buf; + u32 buf_size; }; struct tpm_bios_log { diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index 64356b199e94..739ba9a03ec1 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -211,9 +211,16 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, efispecid = (struct tcg_efi_specid_event_head *)event_header->event; - /* Check if event is malformed. */ + /* + * Perform validation of the event in order to identify malformed + * events. This function may be asked to parse arbitrary byte sequences + * immediately following a valid event log. The caller expects this + * function to recognize that the byte sequence is not a valid event + * and to return an event size of 0. + */ if (memcmp(efispecid->signature, TCG_SPECID_SIG, - sizeof(TCG_SPECID_SIG)) || count > efispecid->num_algs) { + sizeof(TCG_SPECID_SIG)) || + !efispecid->num_algs || count != efispecid->num_algs) { size = 0; goto out; } diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 47eaa34f8761..c5afaf8ca7a2 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -15,6 +15,7 @@ #include <linux/slab.h> #include <linux/types.h> #include <linux/spinlock.h> +#include <linux/mm.h> #include <uapi/linux/xattr.h> struct inode; @@ -94,7 +95,7 @@ static inline void simple_xattrs_free(struct simple_xattrs *xattrs) list_for_each_entry_safe(xattr, node, &xattrs->head, list) { kfree(xattr->name); - kfree(xattr); + kvfree(xattr); } } diff --git a/include/net/addrconf.h b/include/net/addrconf.h index fdb07105384c..8418b7d38468 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -274,6 +274,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); +void __ipv6_sock_ac_close(struct sock *sk); void ipv6_sock_ac_close(struct sock *sk); int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr); diff --git a/include/net/devlink.h b/include/net/devlink.h index 1df6dfec26c2..95b0322a2a82 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -718,6 +718,7 @@ enum devlink_trap_group_generic_id { DEVLINK_TRAP_GROUP_GENERIC_ID_PIM, DEVLINK_TRAP_GROUP_GENERIC_ID_UC_LB, DEVLINK_TRAP_GROUP_GENERIC_ID_LOCAL_DELIVERY, + DEVLINK_TRAP_GROUP_GENERIC_ID_EXTERNAL_DELIVERY, DEVLINK_TRAP_GROUP_GENERIC_ID_IPV6, DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_EVENT, DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_GENERAL, @@ -915,6 +916,8 @@ enum devlink_trap_group_generic_id { "uc_loopback" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_LOCAL_DELIVERY \ "local_delivery" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_EXTERNAL_DELIVERY \ + "external_delivery" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_IPV6 \ "ipv6" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_PTP_EVENT \ diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 6315324b9dc2..3eaf25f68b79 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -5,7 +5,6 @@ #include <linux/list.h> #include <linux/netlink.h> #include <net/flow_dissector.h> -#include <linux/rhashtable.h> struct flow_match { struct flow_dissector *dissector; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c7d213c9f9d8..51f65d23ebaf 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -941,7 +941,7 @@ struct xfrm_dst { static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst) { #ifdef CONFIG_XFRM - if (dst->xfrm) { + if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { const struct xfrm_dst *xdst = (const struct xfrm_dst *) dst; return xdst->path; @@ -953,7 +953,7 @@ static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst) static inline struct dst_entry *xfrm_dst_child(const struct dst_entry *dst) { #ifdef CONFIG_XFRM - if (dst->xfrm) { + if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { struct xfrm_dst *xdst = (struct xfrm_dst *) dst; return xdst->child; } @@ -1630,13 +1630,16 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, void *); void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net); int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl); -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, - u8 type, int dir, +struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, + const struct xfrm_mark *mark, + u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, u8, - int dir, u32 id, int delete, int *err); +struct xfrm_policy *xfrm_policy_byid(struct net *net, + const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, u32 id, int delete, + int *err); int xfrm_policy_flush(struct net *net, u8 type, bool task_valid); void xfrm_policy_hash_rebuild(struct net *net); u32 xfrm_get_acqseq(void); diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index c4369a6c2951..2f1fc23602cb 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -305,6 +305,25 @@ struct rvt_rq { spinlock_t lock ____cacheline_aligned_in_smp; }; +/** + * rvt_get_rq_count - count numbers of request work queue entries + * in circular buffer + * @rq: data structure for request queue entry + * @head: head indices of the circular buffer + * @tail: tail indices of the circular buffer + * + * Return - total number of entries in the Receive Queue + */ + +static inline u32 rvt_get_rq_count(struct rvt_rq *rq, u32 head, u32 tail) +{ + u32 count = head - tail; + + if ((s32)count < 0) + count += rq->size; + return count; +} + /* * This structure holds the information that the send tasklet needs * to send a RDMA read response or atomic operation. diff --git a/include/sound/rt5670.h b/include/sound/rt5670.h index f9024c7a1600..02e1d7778354 100644 --- a/include/sound/rt5670.h +++ b/include/sound/rt5670.h @@ -12,6 +12,7 @@ struct rt5670_platform_data { int jd_mode; bool in2_diff; bool dev_gpio; + bool gpio1_is_ext_spk_en; bool dmic_en; unsigned int dmic1_data_pin; diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h index 212257e84fac..71e178c89793 100644 --- a/include/sound/soc-dai.h +++ b/include/sound/soc-dai.h @@ -161,6 +161,7 @@ void snd_soc_dai_resume(struct snd_soc_dai *dai); int snd_soc_dai_compress_new(struct snd_soc_dai *dai, struct snd_soc_pcm_runtime *rtd, int num); bool snd_soc_dai_stream_valid(struct snd_soc_dai *dai, int stream); +void snd_soc_dai_link_set_capabilities(struct snd_soc_dai_link *dai_link); void snd_soc_dai_action(struct snd_soc_dai *dai, int stream, int action); static inline void snd_soc_dai_activate(struct snd_soc_dai *dai, diff --git a/include/sound/soc.h b/include/sound/soc.h index 2756f9bcac3e..3ce7f0f5aa92 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -444,6 +444,8 @@ int devm_snd_soc_register_component(struct device *dev, const struct snd_soc_component_driver *component_driver, struct snd_soc_dai_driver *dai_drv, int num_dai); void snd_soc_unregister_component(struct device *dev); +void snd_soc_unregister_component_by_driver(struct device *dev, + const struct snd_soc_component_driver *component_driver); struct snd_soc_component *snd_soc_lookup_component_nolocked(struct device *dev, const char *driver_name); struct snd_soc_component *snd_soc_lookup_component(struct device *dev, diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 360b0f9d2220..863335ecb7e8 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -31,13 +31,6 @@ struct extent_io_tree; struct prelim_ref; struct btrfs_space_info; -TRACE_DEFINE_ENUM(FLUSH_DELAYED_ITEMS_NR); -TRACE_DEFINE_ENUM(FLUSH_DELAYED_ITEMS); -TRACE_DEFINE_ENUM(FLUSH_DELALLOC); -TRACE_DEFINE_ENUM(FLUSH_DELALLOC_WAIT); -TRACE_DEFINE_ENUM(ALLOC_CHUNK); -TRACE_DEFINE_ENUM(COMMIT_TRANS); - #define show_ref_type(type) \ __print_symbolic(type, \ { BTRFS_TREE_BLOCK_REF_KEY, "TREE_BLOCK_REF" }, \ @@ -67,30 +60,72 @@ TRACE_DEFINE_ENUM(COMMIT_TRANS); (obj >= BTRFS_ROOT_TREE_OBJECTID && \ obj <= BTRFS_QUOTA_TREE_OBJECTID)) ? __show_root_type(obj) : "-" -#define show_fi_type(type) \ - __print_symbolic(type, \ - { BTRFS_FILE_EXTENT_INLINE, "INLINE" }, \ - { BTRFS_FILE_EXTENT_REG, "REG" }, \ - { BTRFS_FILE_EXTENT_PREALLOC, "PREALLOC"}) +#define FLUSH_ACTIONS \ + EM( BTRFS_RESERVE_NO_FLUSH, "BTRFS_RESERVE_NO_FLUSH") \ + EM( BTRFS_RESERVE_FLUSH_LIMIT, "BTRFS_RESERVE_FLUSH_LIMIT") \ + EM( BTRFS_RESERVE_FLUSH_ALL, "BTRFS_RESERVE_FLUSH_ALL") \ + EMe(BTRFS_RESERVE_FLUSH_ALL_STEAL, "BTRFS_RESERVE_FLUSH_ALL_STEAL") + +#define FI_TYPES \ + EM( BTRFS_FILE_EXTENT_INLINE, "INLINE") \ + EM( BTRFS_FILE_EXTENT_REG, "REG") \ + EMe(BTRFS_FILE_EXTENT_PREALLOC, "PREALLOC") + +#define QGROUP_RSV_TYPES \ + EM( BTRFS_QGROUP_RSV_DATA, "DATA") \ + EM( BTRFS_QGROUP_RSV_META_PERTRANS, "META_PERTRANS") \ + EMe(BTRFS_QGROUP_RSV_META_PREALLOC, "META_PREALLOC") + +#define IO_TREE_OWNER \ + EM( IO_TREE_FS_PINNED_EXTENTS, "PINNED_EXTENTS") \ + EM( IO_TREE_FS_EXCLUDED_EXTENTS, "EXCLUDED_EXTENTS") \ + EM( IO_TREE_INODE_IO, "INODE_IO") \ + EM( IO_TREE_INODE_IO_FAILURE, "INODE_IO_FAILURE") \ + EM( IO_TREE_RELOC_BLOCKS, "RELOC_BLOCKS") \ + EM( IO_TREE_TRANS_DIRTY_PAGES, "TRANS_DIRTY_PAGES") \ + EM( IO_TREE_ROOT_DIRTY_LOG_PAGES, "ROOT_DIRTY_LOG_PAGES") \ + EM( IO_TREE_INODE_FILE_EXTENT, "INODE_FILE_EXTENT") \ + EM( IO_TREE_LOG_CSUM_RANGE, "LOG_CSUM_RANGE") \ + EMe(IO_TREE_SELFTEST, "SELFTEST") + +#define FLUSH_STATES \ + EM( FLUSH_DELAYED_ITEMS_NR, "FLUSH_DELAYED_ITEMS_NR") \ + EM( FLUSH_DELAYED_ITEMS, "FLUSH_DELAYED_ITEMS") \ + EM( FLUSH_DELALLOC, "FLUSH_DELALLOC") \ + EM( FLUSH_DELALLOC_WAIT, "FLUSH_DELALLOC_WAIT") \ + EM( FLUSH_DELAYED_REFS_NR, "FLUSH_DELAYED_REFS_NR") \ + EM( FLUSH_DELAYED_REFS, "FLUSH_ELAYED_REFS") \ + EM( ALLOC_CHUNK, "ALLOC_CHUNK") \ + EM( ALLOC_CHUNK_FORCE, "ALLOC_CHUNK_FORCE") \ + EM( RUN_DELAYED_IPUTS, "RUN_DELAYED_IPUTS") \ + EMe(COMMIT_TRANS, "COMMIT_TRANS") + +/* + * First define the enums in the above macros to be exported to userspace via + * TRACE_DEFINE_ENUM(). + */ + +#undef EM +#undef EMe +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define EMe(a, b) TRACE_DEFINE_ENUM(a); + +FLUSH_ACTIONS +FI_TYPES +QGROUP_RSV_TYPES +IO_TREE_OWNER +FLUSH_STATES + +/* + * Now redefine the EM and EMe macros to map the enums to the strings that will + * be printed in the output + */ + +#undef EM +#undef EMe +#define EM(a, b) {a, b}, +#define EMe(a, b) {a, b} -#define show_qgroup_rsv_type(type) \ - __print_symbolic(type, \ - { BTRFS_QGROUP_RSV_DATA, "DATA" }, \ - { BTRFS_QGROUP_RSV_META_PERTRANS, "META_PERTRANS" }, \ - { BTRFS_QGROUP_RSV_META_PREALLOC, "META_PREALLOC" }) - -#define show_extent_io_tree_owner(owner) \ - __print_symbolic(owner, \ - { IO_TREE_FS_PINNED_EXTENTS, "PINNED_EXTENTS" }, \ - { IO_TREE_FS_EXCLUDED_EXTENTS, "EXCLUDED_EXTENTS" }, \ - { IO_TREE_INODE_IO, "INODE_IO" }, \ - { IO_TREE_INODE_IO_FAILURE, "INODE_IO_FAILURE" }, \ - { IO_TREE_RELOC_BLOCKS, "RELOC_BLOCKS" }, \ - { IO_TREE_TRANS_DIRTY_PAGES, "TRANS_DIRTY_PAGES" }, \ - { IO_TREE_ROOT_DIRTY_LOG_PAGES, "ROOT_DIRTY_LOG_PAGES" }, \ - { IO_TREE_INODE_FILE_EXTENT, "INODE_FILE_EXTENT" }, \ - { IO_TREE_LOG_CSUM_RANGE, "LOG_CSUM_RANGE" }, \ - { IO_TREE_SELFTEST, "SELFTEST" }) #define BTRFS_GROUP_FLAGS \ { BTRFS_BLOCK_GROUP_DATA, "DATA"}, \ @@ -380,7 +415,7 @@ DECLARE_EVENT_CLASS(btrfs__file_extent_item_regular, __entry->disk_isize, __entry->extent_start, __entry->extent_end, __entry->num_bytes, __entry->ram_bytes, __entry->disk_bytenr, __entry->disk_num_bytes, - __entry->extent_offset, show_fi_type(__entry->extent_type), + __entry->extent_offset, __print_symbolic(__entry->extent_type, FI_TYPES), __entry->compression) ); @@ -421,7 +456,7 @@ DECLARE_EVENT_CLASS( "extent_type=%s compression=%u", show_root_type(__entry->root_obj), __entry->ino, __entry->isize, __entry->disk_isize, __entry->extent_start, - __entry->extent_end, show_fi_type(__entry->extent_type), + __entry->extent_end, __print_symbolic(__entry->extent_type, FI_TYPES), __entry->compression) ); @@ -1042,12 +1077,6 @@ TRACE_EVENT(btrfs_space_reservation, __entry->bytes) ); -#define show_flush_action(action) \ - __print_symbolic(action, \ - { BTRFS_RESERVE_NO_FLUSH, "BTRFS_RESERVE_NO_FLUSH"}, \ - { BTRFS_RESERVE_FLUSH_LIMIT, "BTRFS_RESERVE_FLUSH_LIMIT"}, \ - { BTRFS_RESERVE_FLUSH_ALL, "BTRFS_RESERVE_FLUSH_ALL"}) - TRACE_EVENT(btrfs_trigger_flush, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 flags, u64 bytes, @@ -1071,25 +1100,13 @@ TRACE_EVENT(btrfs_trigger_flush, TP_printk_btrfs("%s: flush=%d(%s) flags=%llu(%s) bytes=%llu", __get_str(reason), __entry->flush, - show_flush_action(__entry->flush), + __print_symbolic(__entry->flush, FLUSH_ACTIONS), __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), __entry->bytes) ); -#define show_flush_state(state) \ - __print_symbolic(state, \ - { FLUSH_DELAYED_ITEMS_NR, "FLUSH_DELAYED_ITEMS_NR"}, \ - { FLUSH_DELAYED_ITEMS, "FLUSH_DELAYED_ITEMS"}, \ - { FLUSH_DELALLOC, "FLUSH_DELALLOC"}, \ - { FLUSH_DELALLOC_WAIT, "FLUSH_DELALLOC_WAIT"}, \ - { FLUSH_DELAYED_REFS_NR, "FLUSH_DELAYED_REFS_NR"}, \ - { FLUSH_DELAYED_REFS, "FLUSH_ELAYED_REFS"}, \ - { ALLOC_CHUNK, "ALLOC_CHUNK"}, \ - { ALLOC_CHUNK_FORCE, "ALLOC_CHUNK_FORCE"}, \ - { RUN_DELAYED_IPUTS, "RUN_DELAYED_IPUTS"}, \ - { COMMIT_TRANS, "COMMIT_TRANS"}) TRACE_EVENT(btrfs_flush_space, @@ -1114,7 +1131,7 @@ TRACE_EVENT(btrfs_flush_space, TP_printk_btrfs("state=%d(%s) flags=%llu(%s) num_bytes=%llu ret=%d", __entry->state, - show_flush_state(__entry->state), + __print_symbolic(__entry->state, FLUSH_STATES), __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), @@ -1690,7 +1707,7 @@ TRACE_EVENT(qgroup_update_reserve, ), TP_printk_btrfs("qgid=%llu type=%s cur_reserved=%llu diff=%lld", - __entry->qgid, show_qgroup_rsv_type(__entry->type), + __entry->qgid, __print_symbolic(__entry->type, QGROUP_RSV_TYPES), __entry->cur_reserved, __entry->diff) ); @@ -1714,7 +1731,7 @@ TRACE_EVENT(qgroup_meta_reserve, TP_printk_btrfs("refroot=%llu(%s) type=%s diff=%lld", show_root_type(__entry->refroot), - show_qgroup_rsv_type(__entry->type), __entry->diff) + __print_symbolic(__entry->type, QGROUP_RSV_TYPES), __entry->diff) ); TRACE_EVENT(qgroup_meta_convert, @@ -1735,8 +1752,8 @@ TRACE_EVENT(qgroup_meta_convert, TP_printk_btrfs("refroot=%llu(%s) type=%s->%s diff=%lld", show_root_type(__entry->refroot), - show_qgroup_rsv_type(BTRFS_QGROUP_RSV_META_PREALLOC), - show_qgroup_rsv_type(BTRFS_QGROUP_RSV_META_PERTRANS), + __print_symbolic(BTRFS_QGROUP_RSV_META_PREALLOC, QGROUP_RSV_TYPES), + __print_symbolic(BTRFS_QGROUP_RSV_META_PERTRANS, QGROUP_RSV_TYPES), __entry->diff) ); @@ -1762,7 +1779,7 @@ TRACE_EVENT(qgroup_meta_free_all_pertrans, TP_printk_btrfs("refroot=%llu(%s) type=%s diff=%lld", show_root_type(__entry->refroot), - show_qgroup_rsv_type(__entry->type), __entry->diff) + __print_symbolic(__entry->type, QGROUP_RSV_TYPES), __entry->diff) ); DECLARE_EVENT_CLASS(btrfs__prelim_ref, @@ -1920,7 +1937,7 @@ TRACE_EVENT(btrfs_set_extent_bit, TP_printk_btrfs( "io_tree=%s ino=%llu root=%llu start=%llu len=%llu set_bits=%s", - show_extent_io_tree_owner(__entry->owner), __entry->ino, + __print_symbolic(__entry->owner, IO_TREE_OWNER), __entry->ino, __entry->rootid, __entry->start, __entry->len, __print_flags(__entry->set_bits, "|", EXTENT_FLAGS)) ); @@ -1959,7 +1976,7 @@ TRACE_EVENT(btrfs_clear_extent_bit, TP_printk_btrfs( "io_tree=%s ino=%llu root=%llu start=%llu len=%llu clear_bits=%s", - show_extent_io_tree_owner(__entry->owner), __entry->ino, + __print_symbolic(__entry->owner, IO_TREE_OWNER), __entry->ino, __entry->rootid, __entry->start, __entry->len, __print_flags(__entry->clear_bits, "|", EXTENT_FLAGS)) ); @@ -2000,7 +2017,7 @@ TRACE_EVENT(btrfs_convert_extent_bit, TP_printk_btrfs( "io_tree=%s ino=%llu root=%llu start=%llu len=%llu set_bits=%s clear_bits=%s", - show_extent_io_tree_owner(__entry->owner), __entry->ino, + __print_symbolic(__entry->owner, IO_TREE_OWNER), __entry->ino, __entry->rootid, __entry->start, __entry->len, __print_flags(__entry->set_bits , "|", EXTENT_FLAGS), __print_flags(__entry->clear_bits, "|", EXTENT_FLAGS)) diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index e6b6cb0f8bc6..2c39d15a2beb 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -243,6 +243,18 @@ struct btrfs_ioctl_dev_info_args { __u8 path[BTRFS_DEVICE_PATH_NAME_MAX]; /* out */ }; +/* + * Retrieve information about the filesystem + */ + +/* Request information about checksum type and size */ +#define BTRFS_FS_INFO_FLAG_CSUM_INFO (1 << 0) + +/* Request information about filesystem generation */ +#define BTRFS_FS_INFO_FLAG_GENERATION (1 << 1) +/* Request information about filesystem metadata UUID */ +#define BTRFS_FS_INFO_FLAG_METADATA_UUID (1 << 2) + struct btrfs_ioctl_fs_info_args { __u64 max_id; /* out */ __u64 num_devices; /* out */ @@ -250,8 +262,13 @@ struct btrfs_ioctl_fs_info_args { __u32 nodesize; /* out */ __u32 sectorsize; /* out */ __u32 clone_alignment; /* out */ - __u32 reserved32; - __u64 reserved[122]; /* pad to 1k */ + /* See BTRFS_FS_INFO_FLAG_* */ + __u16 csum_type; /* out */ + __u16 csum_size; /* out */ + __u64 flags; /* in/out */ + __u64 generation; /* out */ + __u8 metadata_uuid[BTRFS_FSID_SIZE]; /* out */ + __u8 reserved[944]; /* pad to 1k */ }; /* diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index a3f3975df0de..9ba64ca6b4ac 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -913,9 +913,9 @@ struct btrfs_free_space_info { #define BTRFS_FREE_SPACE_USING_BITMAPS (1ULL << 0) #define BTRFS_QGROUP_LEVEL_SHIFT 48 -static inline __u64 btrfs_qgroup_level(__u64 qgroupid) +static inline __u16 btrfs_qgroup_level(__u64 qgroupid) { - return qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT; + return (__u16)(qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT); } /* diff --git a/kernel/audit.c b/kernel/audit.c index 8c201f414226..b2301bdc9773 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1851,7 +1851,6 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, } audit_get_stamp(ab->ctx, &t, &serial); - audit_clear_dummy(ab->ctx); audit_log_format(ab, "audit(%llu.%03lu:%u): ", (unsigned long long)t.tv_sec, t.tv_nsec/1000000, serial); diff --git a/kernel/audit.h b/kernel/audit.h index f0233dc40b17..ddc22878433d 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -290,13 +290,6 @@ extern int audit_signal_info_syscall(struct task_struct *t); extern void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx); extern struct list_head *audit_killed_trees(void); - -static inline void audit_clear_dummy(struct audit_context *ctx) -{ - if (ctx) - ctx->dummy = 0; -} - #else /* CONFIG_AUDITSYSCALL */ #define auditsc_get_stamp(c, t, s) 0 #define audit_put_watch(w) {} @@ -330,7 +323,6 @@ static inline int audit_signal_info_syscall(struct task_struct *t) } #define audit_filter_inodes(t, c) AUDIT_DISABLED -#define audit_clear_dummy(c) {} #endif /* CONFIG_AUDITSYSCALL */ extern char *audit_unpack_string(void **bufp, size_t *remain, size_t len); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 468a23390457..fd840c40abf7 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1417,6 +1417,9 @@ static void audit_log_proctitle(void) struct audit_context *context = audit_context(); struct audit_buffer *ab; + if (!context || context->dummy) + return; + ab = audit_log_start(context, GFP_KERNEL, AUDIT_PROCTITLE); if (!ab) return; /* audit_panic or being filtered */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 9a1a98dd9e97..0443600146dc 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4058,6 +4058,11 @@ static int __btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, const char *tname, *sym; u32 btf_id, i; + if (!btf_vmlinux) { + bpf_log(log, "btf_vmlinux doesn't exist\n"); + return -EINVAL; + } + if (IS_ERR(btf_vmlinux)) { bpf_log(log, "btf_vmlinux is malformed\n"); return -EINVAL; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index b4b288a3c3c9..b32cc8ce8ff6 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -779,15 +779,20 @@ static void htab_elem_free_rcu(struct rcu_head *head) htab_elem_free(htab, l); } -static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) { struct bpf_map *map = &htab->map; + void *ptr; if (map->ops->map_fd_put_ptr) { - void *ptr = fd_htab_map_get_ptr(map, l); - + ptr = fd_htab_map_get_ptr(map, l); map->ops->map_fd_put_ptr(ptr); } +} + +static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) +{ + htab_put_fd_value(htab, l); if (htab_is_prealloc(htab)) { __pcpu_freelist_push(&htab->freelist, &l->fnode); @@ -839,6 +844,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, */ pl_new = this_cpu_ptr(htab->extra_elems); l_new = *pl_new; + htab_put_fd_value(htab, old_elem); *pl_new = old_elem; } else { struct pcpu_freelist_node *l; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index bb0862873dba..5f8b0c52fd2e 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -2199,7 +2199,7 @@ static void handle_swbp(struct pt_regs *regs) if (!uprobe) { if (is_swbp > 0) { /* No matching uprobe; signal SIGTRAP. */ - send_sig(SIGTRAP, current, 0); + force_sig(SIGTRAP); } else { /* * Either we raced with uprobe_unregister() or we can't diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e15543cb8481..2142c6767682 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4119,9 +4119,6 @@ static void __sched notrace __schedule(bool preempt) local_irq_disable(); rcu_note_context_switch(preempt); - /* See deactivate_task() below. */ - prev_state = prev->state; - /* * Make sure that signal_pending_state()->signal_pending() below * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) @@ -4145,11 +4142,16 @@ static void __sched notrace __schedule(bool preempt) update_rq_clock(rq); switch_count = &prev->nivcsw; + /* - * We must re-load prev->state in case ttwu_remote() changed it - * before we acquired rq->lock. + * We must load prev->state once (task_struct::state is volatile), such + * that: + * + * - we form a control dependency vs deactivate_task() below. + * - ptrace_{,un}freeze_traced() can change ->state underneath us. */ - if (!preempt && prev_state && prev_state == prev->state) { + prev_state = prev->state; + if (!preempt && prev_state) { if (signal_pending_state(prev_state, prev)) { prev->state = TASK_RUNNING; } else { @@ -4163,10 +4165,12 @@ static void __sched notrace __schedule(bool preempt) /* * __schedule() ttwu() - * prev_state = prev->state; if (READ_ONCE(p->on_rq) && ...) - * LOCK rq->lock goto out; - * smp_mb__after_spinlock(); smp_acquire__after_ctrl_dep(); - * p->on_rq = 0; p->state = TASK_WAKING; + * prev_state = prev->state; if (p->on_rq && ...) + * if (prev_state) goto out; + * p->on_rq = 0; smp_acquire__after_ctrl_dep(); + * p->state = TASK_WAKING + * + * Where __schedule() and ttwu() have matching control dependencies. * * After this, schedule() must not care about p->state any more. */ @@ -4481,6 +4485,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void) int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags, void *key) { + WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~WF_SYNC); return try_to_wake_up(curr->private, mode, wake_flags); } EXPORT_SYMBOL(default_wake_function); diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index ba059fbfc53a..01f5d3020589 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -389,7 +389,7 @@ int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, i int ret = default_wake_function(wq_entry, mode, sync, key); if (ret) - list_del_init(&wq_entry->entry); + list_del_init_careful(&wq_entry->entry); return ret; } diff --git a/kernel/signal.c b/kernel/signal.c index ee22ec78fd6d..6f16f7c5d375 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -719,7 +719,7 @@ static int dequeue_synchronous_signal(kernel_siginfo_t *info) * Return the first synchronous signal in the queue. */ list_for_each_entry(q, &pending->list, list) { - /* Synchronous signals have a postive si_code */ + /* Synchronous signals have a positive si_code */ if ((q->info.si_code > SI_USER) && (sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) { sync = q; diff --git a/kernel/time/timer.c b/kernel/time/timer.c index df1ff803acc4..026ac01af9da 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -43,6 +43,7 @@ #include <linux/sched/debug.h> #include <linux/slab.h> #include <linux/compat.h> +#include <linux/random.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -1742,6 +1743,13 @@ void update_process_times(int user_tick) scheduler_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); + + /* The current CPU might make use of net randoms without receiving IRQs + * to renew them often enough. Let's update the net_rand_state from a + * non-constant value that's not affine to the number of calls to make + * sure it's updated when there's some activity (we don't care in idle). + */ + this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick); } /** diff --git a/lib/random32.c b/lib/random32.c index 763b920a6206..3d749abb9e80 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -48,7 +48,7 @@ static inline void prandom_state_selftest(void) } #endif -static DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; +DEFINE_PER_CPU(struct rnd_state, net_rand_state); /** * prandom_u32_state - seeded pseudo-random number generator. diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 9f6890aedd1a..c949c1e3b87c 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -31,7 +31,7 @@ union nested_table { union nested_table __rcu *table; - struct rhash_lock_head *bucket; + struct rhash_lock_head __rcu *bucket; }; static u32 head_hashfn(struct rhashtable *ht, @@ -222,7 +222,7 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht, } static int rhashtable_rehash_one(struct rhashtable *ht, - struct rhash_lock_head **bkt, + struct rhash_lock_head __rcu **bkt, unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); @@ -275,7 +275,7 @@ static int rhashtable_rehash_chain(struct rhashtable *ht, unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); - struct rhash_lock_head **bkt = rht_bucket_var(old_tbl, old_hash); + struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash); int err; if (!bkt) @@ -485,7 +485,7 @@ fail: } static void *rhashtable_lookup_one(struct rhashtable *ht, - struct rhash_lock_head **bkt, + struct rhash_lock_head __rcu **bkt, struct bucket_table *tbl, unsigned int hash, const void *key, struct rhash_head *obj) { @@ -535,12 +535,10 @@ static void *rhashtable_lookup_one(struct rhashtable *ht, return ERR_PTR(-ENOENT); } -static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht, - struct rhash_lock_head **bkt, - struct bucket_table *tbl, - unsigned int hash, - struct rhash_head *obj, - void *data) +static struct bucket_table *rhashtable_insert_one( + struct rhashtable *ht, struct rhash_lock_head __rcu **bkt, + struct bucket_table *tbl, unsigned int hash, struct rhash_head *obj, + void *data) { struct bucket_table *new_tbl; struct rhash_head *head; @@ -591,7 +589,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, { struct bucket_table *new_tbl; struct bucket_table *tbl; - struct rhash_lock_head **bkt; + struct rhash_lock_head __rcu **bkt; unsigned int hash; void *data; @@ -1173,8 +1171,8 @@ void rhashtable_destroy(struct rhashtable *ht) } EXPORT_SYMBOL_GPL(rhashtable_destroy); -struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash) +struct rhash_lock_head __rcu **__rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); unsigned int index = hash & ((1 << tbl->nest) - 1); @@ -1202,10 +1200,10 @@ struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl, } EXPORT_SYMBOL_GPL(__rht_bucket_nested); -struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl, - unsigned int hash) +struct rhash_lock_head __rcu **rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash) { - static struct rhash_lock_head *rhnull; + static struct rhash_lock_head __rcu *rhnull; if (!rhnull) INIT_RHT_NULLS_HEAD(rhnull); @@ -1213,9 +1211,8 @@ struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl, } EXPORT_SYMBOL_GPL(rht_bucket_nested); -struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht, - struct bucket_table *tbl, - unsigned int hash) +struct rhash_lock_head __rcu **rht_bucket_nested_insert( + struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); unsigned int index = hash & ((1 << tbl->nest) - 1); diff --git a/mm/filemap.c b/mm/filemap.c index 385759c4ce4b..991503bbf922 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1002,6 +1002,7 @@ struct wait_page_queue { static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { + int ret; struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); @@ -1014,17 +1015,35 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, return 0; /* - * Stop walking if it's locked. - * Is this safe if put_and_wait_on_page_locked() is in use? - * Yes: the waker must hold a reference to this page, and if PG_locked - * has now already been set by another task, that task must also hold - * a reference to the *same usage* of this page; so there is no need - * to walk on to wake even the put_and_wait_on_page_locked() callers. + * If it's an exclusive wait, we get the bit for it, and + * stop walking if we can't. + * + * If it's a non-exclusive wait, then the fact that this + * wake function was called means that the bit already + * was cleared, and we don't care if somebody then + * re-took it. */ - if (test_bit(key->bit_nr, &key->page->flags)) - return -1; + ret = 0; + if (wait->flags & WQ_FLAG_EXCLUSIVE) { + if (test_and_set_bit(key->bit_nr, &key->page->flags)) + return -1; + ret = 1; + } + wait->flags |= WQ_FLAG_WOKEN; - return autoremove_wake_function(wait, mode, sync, key); + wake_up_state(wait->private, mode); + + /* + * Ok, we have successfully done what we're waiting for, + * and we can unconditionally remove the wait entry. + * + * Note that this has to be the absolute last thing we do, + * since after list_del_init(&wait->entry) the wait entry + * might be de-allocated and the process might even have + * exited. + */ + list_del_init_careful(&wait->entry); + return ret; } static void wake_up_page_bit(struct page *page, int bit_nr) @@ -1103,16 +1122,31 @@ enum behavior { */ }; +/* + * Attempt to check (or get) the page bit, and mark the + * waiter woken if successful. + */ +static inline bool trylock_page_bit_common(struct page *page, int bit_nr, + struct wait_queue_entry *wait) +{ + if (wait->flags & WQ_FLAG_EXCLUSIVE) { + if (test_and_set_bit(bit_nr, &page->flags)) + return false; + } else if (test_bit(bit_nr, &page->flags)) + return false; + + wait->flags |= WQ_FLAG_WOKEN; + return true; +} + static inline int wait_on_page_bit_common(wait_queue_head_t *q, struct page *page, int bit_nr, int state, enum behavior behavior) { struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; - bool bit_is_set; bool thrashing = false; bool delayacct = false; unsigned long pflags; - int ret = 0; if (bit_nr == PG_locked && !PageUptodate(page) && PageWorkingset(page)) { @@ -1130,48 +1164,47 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, wait_page.page = page; wait_page.bit_nr = bit_nr; - for (;;) { - spin_lock_irq(&q->lock); + /* + * Do one last check whether we can get the + * page bit synchronously. + * + * Do the SetPageWaiters() marking before that + * to let any waker we _just_ missed know they + * need to wake us up (otherwise they'll never + * even go to the slow case that looks at the + * page queue), and add ourselves to the wait + * queue if we need to sleep. + * + * This part needs to be done under the queue + * lock to avoid races. + */ + spin_lock_irq(&q->lock); + SetPageWaiters(page); + if (!trylock_page_bit_common(page, bit_nr, wait)) + __add_wait_queue_entry_tail(q, wait); + spin_unlock_irq(&q->lock); - if (likely(list_empty(&wait->entry))) { - __add_wait_queue_entry_tail(q, wait); - SetPageWaiters(page); - } + /* + * From now on, all the logic will be based on + * the WQ_FLAG_WOKEN flag, and the and the page + * bit testing (and setting) will be - or has + * already been - done by the wake function. + * + * We can drop our reference to the page. + */ + if (behavior == DROP) + put_page(page); + for (;;) { set_current_state(state); - spin_unlock_irq(&q->lock); - - bit_is_set = test_bit(bit_nr, &page->flags); - if (behavior == DROP) - put_page(page); - - if (likely(bit_is_set)) - io_schedule(); - - if (behavior == EXCLUSIVE) { - if (!test_and_set_bit_lock(bit_nr, &page->flags)) - break; - } else if (behavior == SHARED) { - if (!test_bit(bit_nr, &page->flags)) - break; - } - - if (signal_pending_state(state, current)) { - ret = -EINTR; + if (signal_pending_state(state, current)) break; - } - if (behavior == DROP) { - /* - * We can no longer safely access page->flags: - * even if CONFIG_MEMORY_HOTREMOVE is not enabled, - * there is a risk of waiting forever on a page reused - * for something that keeps it locked indefinitely. - * But best check for -EINTR above before breaking. - */ + if (wait->flags & WQ_FLAG_WOKEN) break; - } + + io_schedule(); } finish_wait(q, wait); @@ -1190,7 +1223,7 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, * bother with signals either. */ - return ret; + return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } void wait_on_page_bit(struct page *page, int bit_nr) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index fab4485b9e52..590111ea6975 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -45,7 +45,10 @@ int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; +#ifdef CONFIG_CMA static struct cma *hugetlb_cma[MAX_NUMNODES]; +#endif +static unsigned long hugetlb_cma_size __initdata; /* * Minimum page order among possible hugepage sizes, set to a proper value @@ -1235,9 +1238,10 @@ static void free_gigantic_page(struct page *page, unsigned int order) * If the page isn't allocated using the cma allocator, * cma_release() returns false. */ - if (IS_ENABLED(CONFIG_CMA) && - cma_release(hugetlb_cma[page_to_nid(page)], page, 1 << order)) +#ifdef CONFIG_CMA + if (cma_release(hugetlb_cma[page_to_nid(page)], page, 1 << order)) return; +#endif free_contig_range(page_to_pfn(page), 1 << order); } @@ -1248,7 +1252,8 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, { unsigned long nr_pages = 1UL << huge_page_order(h); - if (IS_ENABLED(CONFIG_CMA)) { +#ifdef CONFIG_CMA + { struct page *page; int node; @@ -1262,6 +1267,7 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, return page; } } +#endif return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); } @@ -2571,7 +2577,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) for (i = 0; i < h->max_huge_pages; ++i) { if (hstate_is_gigantic(h)) { - if (IS_ENABLED(CONFIG_CMA) && hugetlb_cma[0]) { + if (hugetlb_cma_size) { pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); break; } @@ -5654,7 +5660,6 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason) } #ifdef CONFIG_CMA -static unsigned long hugetlb_cma_size __initdata; static bool cma_reserve_called __initdata; static int __init cmdline_parse_hugetlb_cma(char *p) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index b043c40a21d4..700f5160f3e4 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -958,6 +958,9 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, return SCAN_ADDRESS_RANGE; if (!hugepage_vma_check(vma, vma->vm_flags)) return SCAN_VMA_CHECK; + /* Anon VMA expected */ + if (!vma->anon_vma || vma->vm_ops) + return SCAN_VMA_CHECK; return 0; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 19622328e4b5..13f559af1ab6 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5669,7 +5669,6 @@ static void __mem_cgroup_clear_mc(void) if (!mem_cgroup_is_root(mc.to)) page_counter_uncharge(&mc.to->memory, mc.moved_swap); - mem_cgroup_id_get_many(mc.to, mc.moved_swap); css_put_many(&mc.to->css, mc.moved_swap); mc.moved_swap = 0; @@ -5860,7 +5859,8 @@ put: /* get_mctgt_type() gets the page */ ent = target.ent; if (!mem_cgroup_move_swap_account(ent, mc.from, mc.to)) { mc.precharge--; - /* we fixup refcnts and charges later. */ + mem_cgroup_id_get_many(mc.to, 1); + /* we fixup other refcnts and charges later. */ mc.moved_swap++; } break; @@ -7186,6 +7186,13 @@ static struct cftype memsw_files[] = { { }, /* terminate */ }; +/* + * If mem_cgroup_swap_init() is implemented as a subsys_initcall() + * instead of a core_initcall(), this could mean cgroup_memory_noswap still + * remains set to false even when memcg is disabled via "cgroup_disable=memory" + * boot parameter. This may result in premature OOPS inside + * mem_cgroup_get_nr_swap_pages() function in corner cases. + */ static int __init mem_cgroup_swap_init(void) { /* No memory control -> no swap control */ @@ -7200,6 +7207,6 @@ static int __init mem_cgroup_swap_init(void) return 0; } -subsys_initcall(mem_cgroup_swap_init); +core_initcall(mem_cgroup_swap_init); #endif /* CONFIG_MEMCG_SWAP */ diff --git a/mm/memory.c b/mm/memory.c index 87ec87cdc1ff..3ecad55103ad 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1601,7 +1601,7 @@ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, return insert_pages(vma, addr, pages, num, vma->vm_page_prot); #else unsigned long idx = 0, pgcount = *num; - int err; + int err = -EINVAL; for (; idx < pgcount; ++idx) { err = vm_insert_page(vma, addr + (PAGE_SIZE * idx), pages[idx]); diff --git a/mm/mmap.c b/mm/mmap.c index 59a4682ebf3f..8c7ca737a19b 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2620,7 +2620,7 @@ static void unmap_region(struct mm_struct *mm, * Create a list of vma's touched by the unmap, removing them from the mm's * vma list as we go.. */ -static void +static bool detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long end) { @@ -2645,6 +2645,17 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, /* Kill the cache */ vmacache_invalidate(mm); + + /* + * Do not downgrade mmap_lock if we are next to VM_GROWSDOWN or + * VM_GROWSUP VMA. Such VMAs can change their size under + * down_read(mmap_lock) and collide with the VMA we are about to unmap. + */ + if (vma && (vma->vm_flags & VM_GROWSDOWN)) + return false; + if (prev && (prev->vm_flags & VM_GROWSUP)) + return false; + return true; } /* @@ -2825,7 +2836,8 @@ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, } /* Detach vmas from rbtree */ - detach_vmas_to_be_unmapped(mm, vma, prev, end); + if (!detach_vmas_to_be_unmapped(mm, vma, prev, end)) + downgrade = false; if (downgrade) mmap_write_downgrade(mm); diff --git a/mm/shmem.c b/mm/shmem.c index a0dbe62f8042..b2abca3f7f33 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3178,7 +3178,7 @@ static int shmem_initxattrs(struct inode *inode, new_xattr->name = kmalloc(XATTR_SECURITY_PREFIX_LEN + len, GFP_KERNEL); if (!new_xattr->name) { - kfree(new_xattr); + kvfree(new_xattr); return -ENOMEM; } diff --git a/mm/slab_common.c b/mm/slab_common.c index 37d48a56431d..fe8b68482670 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -326,6 +326,14 @@ int slab_unmergeable(struct kmem_cache *s) if (s->refcount < 0) return 1; +#ifdef CONFIG_MEMCG_KMEM + /* + * Skip the dying kmem_cache. + */ + if (s->memcg_params.dying) + return 1; +#endif + return 0; } @@ -886,12 +894,15 @@ static int shutdown_memcg_caches(struct kmem_cache *s) return 0; } -static void flush_memcg_workqueue(struct kmem_cache *s) +static void memcg_set_kmem_cache_dying(struct kmem_cache *s) { spin_lock_irq(&memcg_kmem_wq_lock); s->memcg_params.dying = true; spin_unlock_irq(&memcg_kmem_wq_lock); +} +static void flush_memcg_workqueue(struct kmem_cache *s) +{ /* * SLAB and SLUB deactivate the kmem_caches through call_rcu. Make * sure all registered rcu callbacks have been invoked. @@ -923,10 +934,6 @@ static inline int shutdown_memcg_caches(struct kmem_cache *s) { return 0; } - -static inline void flush_memcg_workqueue(struct kmem_cache *s) -{ -} #endif /* CONFIG_MEMCG_KMEM */ void slab_kmem_cache_release(struct kmem_cache *s) @@ -944,8 +951,6 @@ void kmem_cache_destroy(struct kmem_cache *s) if (unlikely(!s)) return; - flush_memcg_workqueue(s); - get_online_cpus(); get_online_mems(); @@ -955,6 +960,22 @@ void kmem_cache_destroy(struct kmem_cache *s) if (s->refcount) goto out_unlock; +#ifdef CONFIG_MEMCG_KMEM + memcg_set_kmem_cache_dying(s); + + mutex_unlock(&slab_mutex); + + put_online_mems(); + put_online_cpus(); + + flush_memcg_workqueue(s); + + get_online_cpus(); + get_online_mems(); + + mutex_lock(&slab_mutex); +#endif + err = shutdown_memcg_caches(s); if (!err) err = shutdown_cache(s); diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 13cd683a658a..12ecacf0c55f 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -362,6 +362,10 @@ static void p9_read_work(struct work_struct *work) if (m->rreq->status == REQ_STATUS_SENT) { list_del(&m->rreq->req_list); p9_client_cb(m->client, m->rreq, REQ_STATUS_RCVD); + } else if (m->rreq->status == REQ_STATUS_FLSHD) { + /* Ignore replies associated with a cancelled request. */ + p9_debug(P9_DEBUG_TRANS, + "Ignore replies associated with a cancelled request\n"); } else { spin_unlock(&m->client->lock); p9_debug(P9_DEBUG_ERROR, @@ -703,11 +707,20 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req) { p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req); + spin_lock(&client->lock); + /* Ignore cancelled request if message has been received + * before lock. + */ + if (req->status == REQ_STATUS_RCVD) { + spin_unlock(&client->lock); + return 0; + } + /* we haven't received a response for oldreq, * remove it from the list. */ - spin_lock(&client->lock); list_del(&req->req_list); + req->status = REQ_STATUS_FLSHD; spin_unlock(&client->lock); p9_req_put(req); @@ -803,20 +816,28 @@ static int p9_fd_open(struct p9_client *client, int rfd, int wfd) return -ENOMEM; ts->rd = fget(rfd); + if (!ts->rd) + goto out_free_ts; + if (!(ts->rd->f_mode & FMODE_READ)) + goto out_put_rd; ts->wr = fget(wfd); - if (!ts->rd || !ts->wr) { - if (ts->rd) - fput(ts->rd); - if (ts->wr) - fput(ts->wr); - kfree(ts); - return -EIO; - } + if (!ts->wr) + goto out_put_rd; + if (!(ts->wr->f_mode & FMODE_WRITE)) + goto out_put_wr; client->trans = ts; client->status = Connected; return 0; + +out_put_wr: + fput(ts->wr); +out_put_rd: + fput(ts->rd); +out_free_ts: + kfree(ts); + return -EIO; } static int p9_socket_open(struct p9_client *client, struct socket *csocket) diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index fd91cd34f25e..dec3f35467c9 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1187,7 +1187,10 @@ static int __must_check ax25_connect(struct socket *sock, if (addr_len > sizeof(struct sockaddr_ax25) && fsa->fsa_ax25.sax25_ndigis != 0) { /* Valid number of digipeaters ? */ - if (fsa->fsa_ax25.sax25_ndigis < 1 || fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS) { + if (fsa->fsa_ax25.sax25_ndigis < 1 || + fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS || + addr_len < sizeof(struct sockaddr_ax25) + + sizeof(ax25_address) * fsa->fsa_ax25.sax25_ndigis) { err = -EINVAL; goto out_release; } @@ -1507,7 +1510,10 @@ static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)usax; /* Valid number of digipeaters ? */ - if (usax->sax25_ndigis < 1 || usax->sax25_ndigis > AX25_MAX_DIGIS) { + if (usax->sax25_ndigis < 1 || + usax->sax25_ndigis > AX25_MAX_DIGIS || + addr_len < sizeof(struct sockaddr_ax25) + + sizeof(ax25_address) * usax->sax25_ndigis) { err = -EINVAL; goto out; } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index cfeaee347db3..af9d7f2ff8ba 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1338,6 +1338,9 @@ static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr, { struct discovery_state *d = &hdev->discovery; + if (len > HCI_MAX_AD_LENGTH) + return; + bacpy(&d->last_adv_addr, bdaddr); d->last_adv_addr_type = bdaddr_type; d->last_adv_rssi = rssi; @@ -5355,7 +5358,8 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *direct_addr, - u8 direct_addr_type, s8 rssi, u8 *data, u8 len) + u8 direct_addr_type, s8 rssi, u8 *data, u8 len, + bool ext_adv) { struct discovery_state *d = &hdev->discovery; struct smp_irk *irk; @@ -5377,6 +5381,11 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, return; } + if (!ext_adv && len > HCI_MAX_AD_LENGTH) { + bt_dev_err_ratelimited(hdev, "legacy adv larger than 31 bytes"); + return; + } + /* Find the end of the data in case the report contains padded zero * bytes at the end causing an invalid length value. * @@ -5437,7 +5446,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, */ conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, type, direct_addr); - if (conn && type == LE_ADV_IND) { + if (!ext_adv && conn && type == LE_ADV_IND && len <= HCI_MAX_AD_LENGTH) { /* Store report for later inclusion by * mgmt_device_connected */ @@ -5491,7 +5500,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, * event or send an immediate device found event if the data * should not be stored for later. */ - if (!has_pending_adv_report(hdev)) { + if (!ext_adv && !has_pending_adv_report(hdev)) { /* If the report will trigger a SCAN_REQ store it for * later merging. */ @@ -5526,7 +5535,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, /* If the new report will trigger a SCAN_REQ store it for * later merging. */ - if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) { + if (!ext_adv && (type == LE_ADV_IND || + type == LE_ADV_SCAN_IND)) { store_pending_adv_report(hdev, bdaddr, bdaddr_type, rssi, flags, data, len); return; @@ -5566,7 +5576,7 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) rssi = ev->data[ev->length]; process_adv_report(hdev, ev->evt_type, &ev->bdaddr, ev->bdaddr_type, NULL, 0, rssi, - ev->data, ev->length); + ev->data, ev->length, false); } else { bt_dev_err(hdev, "Dropping invalid advertising data"); } @@ -5638,7 +5648,8 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) if (legacy_evt_type != LE_ADV_INVALID) { process_adv_report(hdev, legacy_evt_type, &ev->bdaddr, ev->bdaddr_type, NULL, 0, ev->rssi, - ev->data, ev->length); + ev->data, ev->length, + !(evt_type & LE_EXT_ADV_LEGACY_PDU)); } ptr += sizeof(*ev) + ev->length; @@ -5836,7 +5847,8 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, process_adv_report(hdev, ev->evt_type, &ev->bdaddr, ev->bdaddr_type, &ev->direct_addr, - ev->direct_addr_type, ev->rssi, NULL, 0); + ev->direct_addr_type, ev->rssi, NULL, 0, + false); ptr += sizeof(*ev); } diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c index 1905e01c3aa9..4494ea6056cd 100644 --- a/net/bpfilter/bpfilter_kern.c +++ b/net/bpfilter/bpfilter_kern.c @@ -39,7 +39,7 @@ static int __bpfilter_process_sockopt(struct sock *sk, int optname, { struct mbox_request req; struct mbox_reply reply; - loff_t pos; + loff_t pos = 0; ssize_t n; int ret = -EFAULT; diff --git a/net/compat.c b/net/compat.c index 5e3041a2c37d..434838bef5f8 100644 --- a/net/compat.c +++ b/net/compat.c @@ -202,7 +202,7 @@ int cmsghdr_from_user_compat_to_kern(struct msghdr *kmsg, struct sock *sk, /* Advance. */ kcmsg = (struct cmsghdr *)((char *)kcmsg + tmp); - ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, ucmlen); + ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, cmsg.cmsg_len); } /* diff --git a/net/core/dev.c b/net/core/dev.c index 90b59fc50dc9..7a774ebf64e2 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5601,7 +5601,7 @@ static void flush_backlog(struct work_struct *work) skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); - kfree_skb(skb); + dev_kfree_skb_irq(skb); input_queue_head_incr(sd); } } diff --git a/net/core/devlink.c b/net/core/devlink.c index 2cafbc808b09..47f14a2f25fb 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1065,7 +1065,9 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -1266,7 +1268,9 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg, devlink, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -1498,7 +1502,9 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -3299,7 +3305,9 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -3569,7 +3577,9 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err && err != -EOPNOTSUPP) { + if (err == -EOPNOTSUPP) { + err = 0; + } else if (err) { mutex_unlock(&devlink->lock); goto out; } @@ -4518,7 +4528,9 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); mutex_unlock(&devlink->lock); - if (err && err != -EOPNOTSUPP) + if (err == -EOPNOTSUPP) + err = 0; + else if (err) break; idx++; } @@ -8567,6 +8579,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(PIM), DEVLINK_TRAP_GROUP(UC_LB), DEVLINK_TRAP_GROUP(LOCAL_DELIVERY), + DEVLINK_TRAP_GROUP(EXTERNAL_DELIVERY), DEVLINK_TRAP_GROUP(IPV6), DEVLINK_TRAP_GROUP(PTP_EVENT), DEVLINK_TRAP_GROUP(PTP_GENERAL), diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index b739cfab796e..2076219b8ba5 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -4,6 +4,7 @@ #include <net/flow_offload.h> #include <linux/rtnetlink.h> #include <linux/mutex.h> +#include <linux/rhashtable.h> struct flow_rule *flow_rule_alloc(unsigned int num_actions) { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index e353b822bb15..7bd6440c63bf 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1108,7 +1108,7 @@ static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf) trans_timeout = queue->trans_timeout; spin_unlock_irq(&queue->_xmit_lock); - return sprintf(buf, "%lu", trans_timeout); + return sprintf(buf, fmt_ulong, trans_timeout); } static unsigned int get_netdev_queue_index(struct netdev_queue *queue) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9aedc15736ad..85a4b0101f76 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3343,7 +3343,8 @@ replay: */ if (err < 0) { /* If device is not registered at all, free it now */ - if (dev->reg_state == NETREG_UNINITIALIZED) + if (dev->reg_state == NETREG_UNINITIALIZED || + dev->reg_state == NETREG_UNREGISTERED) free_netdev(dev); goto out; } diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index adcb3aea576d..bbdd3c7b6cb5 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -101,6 +101,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) more_reuse->prog = reuse->prog; more_reuse->reuseport_id = reuse->reuseport_id; more_reuse->bind_inany = reuse->bind_inany; + more_reuse->has_conns = reuse->has_conns; memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index ed13760463de..1ea17752fffc 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -120,13 +120,18 @@ static struct sk_buff *frame_get_stripped_skb(struct hsr_frame_info *frame, return skb_clone(frame->skb_std, GFP_ATOMIC); } -static void hsr_fill_tag(struct sk_buff *skb, struct hsr_frame_info *frame, - struct hsr_port *port, u8 proto_version) +static struct sk_buff *hsr_fill_tag(struct sk_buff *skb, + struct hsr_frame_info *frame, + struct hsr_port *port, u8 proto_version) { struct hsr_ethhdr *hsr_ethhdr; int lane_id; int lsdu_size; + /* pad to minimum packet size which is 60 + 6 (HSR tag) */ + if (skb_put_padto(skb, ETH_ZLEN + HSR_HLEN)) + return NULL; + if (port->type == HSR_PT_SLAVE_A) lane_id = 0; else @@ -144,6 +149,8 @@ static void hsr_fill_tag(struct sk_buff *skb, struct hsr_frame_info *frame, hsr_ethhdr->hsr_tag.encap_proto = hsr_ethhdr->ethhdr.h_proto; hsr_ethhdr->ethhdr.h_proto = htons(proto_version ? ETH_P_HSR : ETH_P_PRP); + + return skb; } static struct sk_buff *create_tagged_skb(struct sk_buff *skb_o, @@ -172,9 +179,10 @@ static struct sk_buff *create_tagged_skb(struct sk_buff *skb_o, memmove(dst, src, movelen); skb_reset_mac_header(skb); - hsr_fill_tag(skb, frame, port, port->hsr->prot_version); - - return skb; + /* skb_put_padto free skb on error and hsr_fill_tag returns NULL in + * that case + */ + return hsr_fill_tag(skb, frame, port, port->hsr->prot_version); } /* If the original frame was an HSR tagged frame, just clone it to be sent diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 03b891904314..530de24b1fb5 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -325,7 +325,8 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, if (port->type != node_dst->addr_B_port) return; - ether_addr_copy(eth_hdr(skb)->h_dest, node_dst->macaddress_B); + if (is_valid_ether_addr(node_dst->macaddress_B)) + ether_addr_copy(eth_hdr(skb)->h_dest, node_dst->macaddress_B); } void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port, diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 248f1c1959a6..3c65f71d0e82 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1864,7 +1864,7 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) while ((l = leaf_walk_rcu(&tp, key)) != NULL) { struct key_vector *local_l = NULL, *local_tp; - hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { + hlist_for_each_entry(fa, &l->leaf, fa_list) { struct fib_alias *new_fa; if (local_tb->tb_id != fa->tb_id) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9615e72656d1..518f04355fbf 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3488,10 +3488,8 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) } } -/* This routine deals with acks during a TLP episode. - * We mark the end of a TLP episode on receiving TLP dupack or when - * ack is after tlp_high_seq. - * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe. +/* This routine deals with acks during a TLP episode and ends an episode by + * resetting tlp_high_seq. Ref: TLP algorithm in draft-ietf-tcpm-rack */ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) { @@ -3500,7 +3498,10 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) if (before(ack, tp->tlp_high_seq)) return; - if (flag & FLAG_DSACKING_ACK) { + if (!tp->tlp_retrans) { + /* TLP of new data has been acknowledged */ + tp->tlp_high_seq = 0; + } else if (flag & FLAG_DSACKING_ACK) { /* This DSACK means original and TLP probe arrived; no loss */ tp->tlp_high_seq = 0; } else if (after(ack, tp->tlp_high_seq)) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5f5b2f0b0e60..0bc05d68cd74 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2624,6 +2624,11 @@ void tcp_send_loss_probe(struct sock *sk) int pcount; int mss = tcp_current_mss(sk); + /* At most one outstanding TLP */ + if (tp->tlp_high_seq) + goto rearm_timer; + + tp->tlp_retrans = 0; skb = tcp_send_head(sk); if (skb && tcp_snd_wnd_test(tp, skb, mss)) { pcount = tp->packets_out; @@ -2641,10 +2646,6 @@ void tcp_send_loss_probe(struct sock *sk) return; } - /* At most one outstanding TLP retransmission. */ - if (tp->tlp_high_seq) - goto rearm_timer; - if (skb_still_in_host_queue(sk, skb)) goto rearm_timer; @@ -2666,10 +2667,12 @@ void tcp_send_loss_probe(struct sock *sk) if (__tcp_retransmit_skb(sk, skb, 1)) goto rearm_timer; + tp->tlp_retrans = 1; + +probe_sent: /* Record snd_nxt for loss detection. */ tp->tlp_high_seq = tp->snd_nxt; -probe_sent: NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); /* Reset s.t. tcp_rearm_rto will restart timer from now */ inet_csk(sk)->icsk_pending = 0; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1b7ebbcae497..4077d589b72e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -416,7 +416,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, struct udp_hslot *hslot2, struct sk_buff *skb) { - struct sock *sk, *result; + struct sock *sk, *result, *reuseport_result; int score, badness; u32 hash = 0; @@ -426,17 +426,20 @@ static struct sock *udp4_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { + reuseport_result = NULL; + if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) { hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - result = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (result && !reuseport_has_conns(sk, false)) - return result; + reuseport_result = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (reuseport_result && !reuseport_has_conns(sk, false)) + return reuseport_result; } + + result = reuseport_result ? : sk; badness = score; - result = sk; } } return result; @@ -2051,7 +2054,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) /* * UDP-Lite specific tests, ignored on UDP sockets */ - if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { /* * MIB statistics other than incrementing the error count are diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 893261230ffc..dacdea7fcb62 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -183,7 +183,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) return 0; } -void ipv6_sock_ac_close(struct sock *sk) +void __ipv6_sock_ac_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev = NULL; @@ -191,10 +191,7 @@ void ipv6_sock_ac_close(struct sock *sk) struct net *net = sock_net(sk); int prev_index; - if (!np->ipv6_ac_list) - return; - - rtnl_lock(); + ASSERT_RTNL(); pac = np->ipv6_ac_list; np->ipv6_ac_list = NULL; @@ -211,6 +208,16 @@ void ipv6_sock_ac_close(struct sock *sk) sock_kfree_s(sk, pac, sizeof(*pac)); pac = next; } +} + +void ipv6_sock_ac_close(struct sock *sk) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + + if (!np->ipv6_ac_list) + return; + rtnl_lock(); + __ipv6_sock_ac_close(sk); rtnl_unlock(); } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index c43592771126..52c2f063529f 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -805,10 +805,17 @@ int esp6_input_done2(struct sk_buff *skb, int err) if (x->encap) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); + int offset = skb_network_offset(skb) + sizeof(*ip6h); struct xfrm_encap_tmpl *encap = x->encap; - struct udphdr *uh = (void *)(skb_network_header(skb) + hdr_len); - struct tcphdr *th = (void *)(skb_network_header(skb) + hdr_len); - __be16 source; + u8 nexthdr = ip6h->nexthdr; + __be16 frag_off, source; + struct udphdr *uh; + struct tcphdr *th; + + offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); + uh = (void *)(skb->data + offset); + th = (void *)(skb->data + offset); + hdr_len += offset; switch (x->encap->encap_type) { case TCP_ENCAP_ESPINTCP: diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 6532bde82b40..3a57fb9ce049 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1562,17 +1562,18 @@ static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head) static int __net_init ip6gre_init_net(struct net *net) { struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + struct net_device *ndev; int err; if (!net_has_fallback_tunnels(net)) return 0; - ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", - NET_NAME_UNKNOWN, - ip6gre_tunnel_setup); - if (!ign->fb_tunnel_dev) { + ndev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", + NET_NAME_UNKNOWN, ip6gre_tunnel_setup); + if (!ndev) { err = -ENOMEM; goto err_alloc_dev; } + ign->fb_tunnel_dev = ndev; dev_net_set(ign->fb_tunnel_dev, net); /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. @@ -1592,7 +1593,7 @@ static int __net_init ip6gre_init_net(struct net *net) return 0; err_reg_dev: - free_netdev(ign->fb_tunnel_dev); + free_netdev(ndev); err_alloc_dev: return err; } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 20576e87a5f7..76f9e41859a2 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -240,6 +240,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, fl6_free_socklist(sk); __ipv6_sock_mc_close(sk); + __ipv6_sock_ac_close(sk); /* * Sock is moving from IPv6 to IPv4 (sk_prot), so diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f3279810d765..4c36bd0c7930 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3685,14 +3685,14 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, rt->fib6_src.plen = cfg->fc_src_len; #endif if (nh) { - if (!nexthop_get(nh)) { - NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); - goto out; - } if (rt->fib6_src.plen) { NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); goto out; } + if (!nexthop_get(nh)) { + NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); + goto out; + } rt->nh = nh; fib6_nh = nexthop_fib6_nh(rt->nh); } else { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 7d4151747340..a8d74f44056a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -148,7 +148,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, int dif, int sdif, struct udp_hslot *hslot2, struct sk_buff *skb) { - struct sock *sk, *result; + struct sock *sk, *result, *reuseport_result; int score, badness; u32 hash = 0; @@ -158,17 +158,20 @@ static struct sock *udp6_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { + reuseport_result = NULL; + if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) { hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - result = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (result && !reuseport_has_conns(sk, false)) - return result; + reuseport_result = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (reuseport_result && !reuseport_has_conns(sk, false)) + return reuseport_result; } - result = sk; + + result = reuseport_result ? : sk; badness = score; } } @@ -643,7 +646,7 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) /* * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c). */ - if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { if (up->pcrlen == 0) { /* full coverage was set */ net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n", diff --git a/net/key/af_key.c b/net/key/af_key.c index b67ed3a8486c..a915bc86620a 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1849,6 +1849,13 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; + if ((xfilter->sadb_x_filter_splen >= + (sizeof(xfrm_address_t) << 3)) || + (xfilter->sadb_x_filter_dplen >= + (sizeof(xfrm_address_t) << 3))) { + mutex_unlock(&pfk->dump_lock); + return -EINVAL; + } filter = kmalloc(sizeof(*filter), GFP_KERNEL); if (filter == NULL) { mutex_unlock(&pfk->dump_lock); @@ -2400,7 +2407,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa return err; } - xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_bysel_ctx(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, pol->sadb_x_policy_dir - 1, &sel, pol_ctx, 1, &err); security_xfrm_policy_free(pol_ctx); @@ -2651,7 +2658,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_ return -EINVAL; delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2); - xp = xfrm_policy_byid(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_byid(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, dir, pol->sadb_x_policy_id, delete, &err); if (xp == NULL) return -ENOENT; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 9b360544ad6f..1079a07e43e4 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2166,6 +2166,7 @@ static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev) ieee80211_stop_mesh(sdata); mutex_lock(&sdata->local->mtx); ieee80211_vif_release_channel(sdata); + kfree(sdata->u.mesh.ie); mutex_unlock(&sdata->local->mtx); return 0; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 5f1ca25b6c97..e88beb3ff6db 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -617,6 +617,19 @@ int mesh_add_he_oper_ie(struct ieee80211_sub_if_data *sdata, int mesh_add_he_6ghz_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { + struct ieee80211_supported_band *sband; + const struct ieee80211_sband_iftype_data *iftd; + + sband = ieee80211_get_sband(sdata); + if (!sband) + return -EINVAL; + + iftd = ieee80211_get_sband_iftype_data(sband, + NL80211_IFTYPE_MESH_POINT); + /* The device doesn't support HE in mesh mode or at all */ + if (!iftd) + return 0; + ieee80211_ie_build_he_6ghz_cap(sdata, skb); return 0; } diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 117519bf33d6..aca608ae313f 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -521,6 +521,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, del_timer_sync(&mpath->timer); atomic_dec(&sdata->u.mesh.mpaths); atomic_dec(&tbl->entries); + mesh_path_flush_pending(mpath); kfree_rcu(mpath, rcu); } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index cd8487bc6fc2..af4cc5fb678e 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1923,9 +1923,7 @@ void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local, if (sta) { tx_pending = atomic_sub_return(tx_airtime, &sta->airtime[ac].aql_tx_pending); - if (WARN_ONCE(tx_pending < 0, - "STA %pM AC %d txq pending airtime underflow: %u, %u", - sta->addr, ac, tx_pending, tx_airtime)) + if (tx_pending < 0) atomic_cmpxchg(&sta->airtime[ac].aql_tx_pending, tx_pending, 0); } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1a2941e5244f..3529d1368068 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -4230,11 +4230,12 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state)) goto out_free; + memset(info, 0, sizeof(*info)); + if (unlikely(!multicast && skb->sk && skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)) - ieee80211_store_ack_skb(local, skb, &info->flags, NULL); - - memset(info, 0, sizeof(*info)); + info->ack_frame_id = ieee80211_store_ack_skb(local, skb, + &info->flags, NULL); if (unlikely(sdata->control_port_protocol == ehdr->h_proto)) { if (sdata->control_port_no_encrypt) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 21c94094a699..dd9f5c7a1ade 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2878,6 +2878,10 @@ void ieee80211_ie_build_he_6ghz_cap(struct ieee80211_sub_if_data *sdata, if (WARN_ON(!iftd)) return; + /* Check for device HE 6 GHz capability before adding element */ + if (!iftd->he_6ghz_capa.capa) + return; + cap = le16_to_cpu(iftd->he_6ghz_capa.capa); cap &= ~IEEE80211_HE_6GHZ_CAP_SM_PS; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3980fbb6f31e..c0abe738e7d3 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1833,7 +1833,7 @@ do_connect: /* on successful connect, the msk state will be moved to established by * subflow_finish_connect() */ - if (!err || err == EINPROGRESS) + if (!err || err == -EINPROGRESS) mptcp_copy_inaddrs(sock->sk, ssock->sk); else inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk)); diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 605e0f68f8bd..2b8abbfe018c 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1717,6 +1717,8 @@ static int sync_thread_backup(void *data) { struct ip_vs_sync_thread_data *tinfo = data; struct netns_ipvs *ipvs = tinfo->ipvs; + struct sock *sk = tinfo->sock->sk; + struct udp_sock *up = udp_sk(sk); int len; pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, " @@ -1724,12 +1726,14 @@ static int sync_thread_backup(void *data) ipvs->bcfg.mcast_ifn, ipvs->bcfg.syncid, tinfo->id); while (!kthread_should_stop()) { - wait_event_interruptible(*sk_sleep(tinfo->sock->sk), - !skb_queue_empty(&tinfo->sock->sk->sk_receive_queue) - || kthread_should_stop()); + wait_event_interruptible(*sk_sleep(sk), + !skb_queue_empty_lockless(&sk->sk_receive_queue) || + !skb_queue_empty_lockless(&up->reader_queue) || + kthread_should_stop()); /* do we have data now? */ - while (!skb_queue_empty(&(tinfo->sock->sk->sk_receive_queue))) { + while (!skb_queue_empty_lockless(&sk->sk_receive_queue) || + !skb_queue_empty_lockless(&up->reader_queue)) { len = ip_vs_receive(tinfo->sock, tinfo->buf, ipvs->bcfg.sync_maxlen); if (len <= 0) { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7647ecfa0d40..88325b264737 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -188,24 +188,6 @@ static void nft_netdev_unregister_hooks(struct net *net, nf_unregister_net_hook(net, &hook->ops); } -static int nft_register_basechain_hooks(struct net *net, int family, - struct nft_base_chain *basechain) -{ - if (family == NFPROTO_NETDEV) - return nft_netdev_register_hooks(net, &basechain->hook_list); - - return nf_register_net_hook(net, &basechain->ops); -} - -static void nft_unregister_basechain_hooks(struct net *net, int family, - struct nft_base_chain *basechain) -{ - if (family == NFPROTO_NETDEV) - nft_netdev_unregister_hooks(net, &basechain->hook_list); - else - nf_unregister_net_hook(net, &basechain->ops); -} - static int nf_tables_register_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) @@ -223,7 +205,10 @@ static int nf_tables_register_hook(struct net *net, if (basechain->type->ops_register) return basechain->type->ops_register(net, ops); - return nft_register_basechain_hooks(net, table->family, basechain); + if (table->family == NFPROTO_NETDEV) + return nft_netdev_register_hooks(net, &basechain->hook_list); + + return nf_register_net_hook(net, &basechain->ops); } static void nf_tables_unregister_hook(struct net *net, @@ -242,7 +227,10 @@ static void nf_tables_unregister_hook(struct net *net, if (basechain->type->ops_unregister) return basechain->type->ops_unregister(net, ops); - nft_unregister_basechain_hooks(net, table->family, basechain); + if (table->family == NFPROTO_NETDEV) + nft_netdev_unregister_hooks(net, &basechain->hook_list); + else + nf_unregister_net_hook(net, &basechain->ops); } static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) @@ -832,8 +820,7 @@ static void nft_table_disable(struct net *net, struct nft_table *table, u32 cnt) if (cnt && i++ == cnt) break; - nft_unregister_basechain_hooks(net, table->family, - nft_base_chain(chain)); + nf_tables_unregister_hook(net, table, chain); } } @@ -848,8 +835,7 @@ static int nf_tables_table_enable(struct net *net, struct nft_table *table) if (!nft_is_base_chain(chain)) continue; - err = nft_register_basechain_hooks(net, table->family, - nft_base_chain(chain)); + err = nf_tables_register_hook(net, table, chain); if (err < 0) goto err_register_hooks; @@ -894,11 +880,12 @@ static int nf_tables_updtable(struct nft_ctx *ctx) nft_trans_table_enable(trans) = false; } else if (!(flags & NFT_TABLE_F_DORMANT) && ctx->table->flags & NFT_TABLE_F_DORMANT) { + ctx->table->flags &= ~NFT_TABLE_F_DORMANT; ret = nf_tables_table_enable(ctx->net, ctx->table); - if (ret >= 0) { - ctx->table->flags &= ~NFT_TABLE_F_DORMANT; + if (ret >= 0) nft_trans_table_enable(trans) = true; - } + else + ctx->table->flags |= NFT_TABLE_F_DORMANT; } if (ret < 0) goto err; diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 7cd524884304..78ea8c94dcba 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1228,10 +1228,13 @@ int nci_register_device(struct nci_dev *ndev) rc = nfc_register_device(ndev->nfc_dev); if (rc) - goto destroy_rx_wq_exit; + goto destroy_tx_wq_exit; goto exit; +destroy_tx_wq_exit: + destroy_workqueue(ndev->tx_wq); + destroy_rx_wq_exit: destroy_workqueue(ndev->rx_wq); diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 24a8c3c6da0d..300a104b9a0f 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -1180,6 +1180,7 @@ static int qrtr_release(struct socket *sock) sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); + sock_orphan(sk); sock->sk = NULL; if (!sock_flag(sk, SOCK_ZAPPED)) diff --git a/net/rds/recv.c b/net/rds/recv.c index c8404971d5ab..aba4afe4dfed 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -450,12 +450,13 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc, int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msghdr) { struct rds_notifier *notifier; - struct rds_rdma_notify cmsg = { 0 }; /* fill holes with zero */ + struct rds_rdma_notify cmsg; unsigned int count = 0, max_messages = ~0U; unsigned long flags; LIST_HEAD(copy); int err = 0; + memset(&cmsg, 0, sizeof(cmsg)); /* fill holes with zero */ /* put_cmsg copies to user space and thus may sleep. We can't do this * with rs_lock held, so first grab as many notifications as we can stuff diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f07970207b54..38a46167523f 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -288,7 +288,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, */ ret = rxrpc_connect_call(rx, call, cp, srx, gfp); if (ret < 0) - goto error; + goto error_attached_to_socket; trace_rxrpc_call(call->debug_id, rxrpc_call_connected, atomic_read(&call->usage), here, NULL); @@ -308,18 +308,29 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, error_dup_user_ID: write_unlock(&rx->call_lock); release_sock(&rx->sk); - ret = -EEXIST; - -error: __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - RX_CALL_DEAD, ret); + RX_CALL_DEAD, -EEXIST); trace_rxrpc_call(call->debug_id, rxrpc_call_error, - atomic_read(&call->usage), here, ERR_PTR(ret)); + atomic_read(&call->usage), here, ERR_PTR(-EEXIST)); rxrpc_release_call(rx, call); mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); - _leave(" = %d", ret); - return ERR_PTR(ret); + _leave(" = -EEXIST"); + return ERR_PTR(-EEXIST); + + /* We got an error, but the call is attached to the socket and is in + * need of release. However, we might now race with recvmsg() when + * completing the call queues it. Return 0 from sys_sendmsg() and + * leave the error to recvmsg() to deal with. + */ +error_attached_to_socket: + trace_rxrpc_call(call->debug_id, rxrpc_call_error, + atomic_read(&call->usage), here, ERR_PTR(ret)); + set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); + __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, + RX_CALL_DEAD, ret); + _leave(" = c=%08x [err]", call->debug_id); + return call; } /* diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 19e141eeed17..8cbe0bf20ed5 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -212,9 +212,11 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) call->peer->cong_cwnd = call->cong_cwnd; - spin_lock_bh(&conn->params.peer->lock); - hlist_del_rcu(&call->error_link); - spin_unlock_bh(&conn->params.peer->lock); + if (!hlist_unhashed(&call->error_link)) { + spin_lock_bh(&call->peer->lock); + hlist_del_rcu(&call->error_link); + spin_unlock_bh(&call->peer->lock); + } if (rxrpc_is_client_call(call)) return rxrpc_disconnect_client_call(call); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 2989742a4aa1..efecc5a8f67d 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -543,7 +543,7 @@ try_again: list_empty(&rx->recvmsg_q) && rx->sk.sk_state != RXRPC_SERVER_LISTENING) { release_sock(&rx->sk); - return -ENODATA; + return -EAGAIN; } if (list_empty(&rx->recvmsg_q)) { @@ -620,7 +620,7 @@ try_again: goto error_unlock_call; } - if (msg->msg_name) { + if (msg->msg_name && call->peer) { struct sockaddr_rxrpc *srx = msg->msg_name; size_t len = sizeof(call->peer->srx); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 1304b8608f56..f3f6da6e4ad2 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -304,7 +304,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, /* this should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) + if (sk->sk_shutdown & SEND_SHUTDOWN) return -EPIPE; more = msg->msg_flags & MSG_MORE; @@ -681,6 +681,9 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (IS_ERR(call)) return PTR_ERR(call); /* ... and we have the call lock. */ + ret = 0; + if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) + goto out_put_unlock; } else { switch (READ_ONCE(call->state)) { case RXRPC_CALL_UNINITIALISED: diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 67504aece9ae..6ed1652d1e26 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -673,9 +673,10 @@ static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag) } static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, - u8 family, u16 zone) + u8 family, u16 zone, bool *defrag) { enum ip_conntrack_info ctinfo; + struct qdisc_skb_cb cb; struct nf_conn *ct; int err = 0; bool frag; @@ -693,6 +694,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, return err; skb_get(skb); + cb = *qdisc_skb_cb(skb); if (family == NFPROTO_IPV4) { enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone; @@ -703,6 +705,9 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, local_bh_enable(); if (err && err != -EINPROGRESS) goto out_free; + + if (!err) + *defrag = true; } else { /* NFPROTO_IPV6 */ #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; @@ -711,12 +716,16 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, err = nf_ct_frag6_gather(net, skb, user); if (err && err != -EINPROGRESS) goto out_free; + + if (!err) + *defrag = true; #else err = -EOPNOTSUPP; goto out_free; #endif } + *qdisc_skb_cb(skb) = cb; skb_clear_hash(skb); skb->ignore_df = 1; return err; @@ -914,6 +923,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, int nh_ofs, err, retval; struct tcf_ct_params *p; bool skip_add = false; + bool defrag = false; struct nf_conn *ct; u8 family; @@ -946,7 +956,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, */ nh_ofs = skb_network_offset(skb); skb_pull_rcsum(skb, nh_ofs); - err = tcf_ct_handle_fragments(net, skb, family, p->zone); + err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag); if (err == -EINPROGRESS) { retval = TC_ACT_STOLEN; goto out; @@ -1014,6 +1024,8 @@ out_push: out: tcf_action_update_bstats(&c->common, skb); + if (defrag) + qdisc_skb_cb(skb)->pkt_len = skb->len; return retval; drop: @@ -1531,10 +1543,10 @@ static int __init ct_init_module(void) return 0; -err_tbl_init: - destroy_workqueue(act_ct_wq); err_register: tcf_ct_flow_tables_uninit(); +err_tbl_init: + destroy_workqueue(act_ct_wq); return err; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index e62beec0d844..4619cb3cb0a8 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -20,7 +20,6 @@ #include <linux/kmod.h> #include <linux/slab.h> #include <linux/idr.h> -#include <linux/rhashtable.h> #include <linux/jhash.h> #include <linux/rculist.h> #include <net/net_namespace.h> diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 67f7e71f9129..bda2536dd740 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -22,17 +22,11 @@ #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> -/* Migrates chunks from stream queues to new stream queues if needed, - * but not across associations. Also, removes those chunks to streams - * higher than the new max. - */ -static void sctp_stream_outq_migrate(struct sctp_stream *stream, - struct sctp_stream *new, __u16 outcnt) +static void sctp_stream_shrink_out(struct sctp_stream *stream, __u16 outcnt) { struct sctp_association *asoc; struct sctp_chunk *ch, *temp; struct sctp_outq *outq; - int i; asoc = container_of(stream, struct sctp_association, stream); outq = &asoc->outqueue; @@ -56,6 +50,19 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream, sctp_chunk_free(ch); } +} + +/* Migrates chunks from stream queues to new stream queues if needed, + * but not across associations. Also, removes those chunks to streams + * higher than the new max. + */ +static void sctp_stream_outq_migrate(struct sctp_stream *stream, + struct sctp_stream *new, __u16 outcnt) +{ + int i; + + if (stream->outcnt > outcnt) + sctp_stream_shrink_out(stream, outcnt); if (new) { /* Here we actually move the old ext stuff into the new @@ -1037,11 +1044,13 @@ struct sctp_chunk *sctp_process_strreset_resp( nums = ntohs(addstrm->number_of_streams); number = stream->outcnt - nums; - if (result == SCTP_STRRESET_PERFORMED) + if (result == SCTP_STRRESET_PERFORMED) { for (i = number; i < stream->outcnt; i++) SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; - else + } else { + sctp_stream_shrink_out(stream, number); stream->outcnt = number; + } *evp = sctp_ulpevent_make_stream_change_event(asoc, flags, 0, nums, GFP_ATOMIC); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 903321543838..1163d51196da 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -126,8 +126,10 @@ EXPORT_SYMBOL_GPL(smc_proto6); static void smc_restore_fallback_changes(struct smc_sock *smc) { - smc->clcsock->file->private_data = smc->sk.sk_socket; - smc->clcsock->file = NULL; + if (smc->clcsock->file) { /* non-accepted sockets have no file yet */ + smc->clcsock->file->private_data = smc->sk.sk_socket; + smc->clcsock->file = NULL; + } } static int __smc_release(struct smc_sock *smc) @@ -352,7 +354,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link, */ mutex_lock(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (lgr->lnk[i].state != SMC_LNK_ACTIVE) + if (!smc_link_active(&lgr->lnk[i])) continue; rc = smcr_link_reg_rmb(&lgr->lnk[i], rmb_desc); if (rc) @@ -632,7 +634,9 @@ static int smc_connect_rdma(struct smc_sock *smc, for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *l = &smc->conn.lgr->lnk[i]; - if (l->peer_qpn == ntoh24(aclc->qpn)) { + if (l->peer_qpn == ntoh24(aclc->qpn) && + !memcmp(l->peer_gid, &aclc->lcl.gid, SMC_GID_SIZE) && + !memcmp(l->peer_mac, &aclc->lcl.mac, sizeof(l->peer_mac))) { link = l; break; } diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index a47e8855e045..ce468ff62a19 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -66,9 +66,13 @@ int smc_cdc_get_free_slot(struct smc_connection *conn, rc = smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf, wr_rdma_buf, (struct smc_wr_tx_pend_priv **)pend); - if (conn->killed) + if (conn->killed) { /* abnormal termination */ + if (!rc) + smc_wr_tx_put_slot(link, + (struct smc_wr_tx_pend_priv *)pend); rc = -EPIPE; + } return rc; } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index f69d205b3e11..f82a2e599917 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -45,18 +45,10 @@ static struct smc_lgr_list smc_lgr_list = { /* established link groups */ static atomic_t lgr_cnt = ATOMIC_INIT(0); /* number of existing link groups */ static DECLARE_WAIT_QUEUE_HEAD(lgrs_deleted); -struct smc_ib_up_work { - struct work_struct work; - struct smc_link_group *lgr; - struct smc_ib_device *smcibdev; - u8 ibport; -}; - static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc); static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft); -static void smc_link_up_work(struct work_struct *work); static void smc_link_down_work(struct work_struct *work); /* return head of link group list and its lock for a given link group */ @@ -326,7 +318,6 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, get_device(&ini->ib_dev->ibdev->dev); atomic_inc(&ini->ib_dev->lnk_cnt); - lnk->state = SMC_LNK_ACTIVATING; lnk->link_id = smcr_next_link_id(lgr); lnk->lgr = lgr; lnk->link_idx = link_idx; @@ -362,6 +353,7 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, rc = smc_wr_create_link(lnk); if (rc) goto destroy_qp; + lnk->state = SMC_LNK_ACTIVATING; return 0; destroy_qp: @@ -452,7 +444,7 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) } smc->conn.lgr = lgr; spin_lock_bh(lgr_lock); - list_add(&lgr->list, lgr_list); + list_add_tail(&lgr->list, lgr_list); spin_unlock_bh(lgr_lock); return 0; @@ -550,8 +542,7 @@ struct smc_link *smc_switch_conns(struct smc_link_group *lgr, smc_wr_wakeup_tx_wait(from_lnk); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (lgr->lnk[i].state != SMC_LNK_ACTIVE || - i == from_lnk->link_idx) + if (!smc_link_active(&lgr->lnk[i]) || i == from_lnk->link_idx) continue; if (is_dev_err && from_lnk->smcibdev == lgr->lnk[i].smcibdev && from_lnk->ibport == lgr->lnk[i].ibport) { @@ -1106,67 +1097,23 @@ static void smc_conn_abort_work(struct work_struct *work) sock_put(&smc->sk); /* sock_hold done by schedulers of abort_work */ } -/* link is up - establish alternate link if applicable */ -static void smcr_link_up(struct smc_link_group *lgr, - struct smc_ib_device *smcibdev, u8 ibport) -{ - struct smc_link *link = NULL; - - if (list_empty(&lgr->list) || - lgr->type == SMC_LGR_SYMMETRIC || - lgr->type == SMC_LGR_ASYMMETRIC_PEER) - return; - - if (lgr->role == SMC_SERV) { - /* trigger local add link processing */ - link = smc_llc_usable_link(lgr); - if (!link) - return; - smc_llc_srv_add_link_local(link); - } else { - /* invite server to start add link processing */ - u8 gid[SMC_GID_SIZE]; - - if (smc_ib_determine_gid(smcibdev, ibport, lgr->vlan_id, gid, - NULL)) - return; - if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { - /* some other llc task is ongoing */ - wait_event_timeout(lgr->llc_flow_waiter, - (list_empty(&lgr->list) || - lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE), - SMC_LLC_WAIT_TIME); - } - /* lgr or device no longer active? */ - if (!list_empty(&lgr->list) && - smc_ib_port_active(smcibdev, ibport)) - link = smc_llc_usable_link(lgr); - if (link) - smc_llc_send_add_link(link, smcibdev->mac[ibport - 1], - gid, NULL, SMC_LLC_REQ); - wake_up(&lgr->llc_flow_waiter); /* wake up next waiter */ - } -} - void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport) { - struct smc_ib_up_work *ib_work; struct smc_link_group *lgr, *n; list_for_each_entry_safe(lgr, n, &smc_lgr_list.list, list) { + struct smc_link *link; + if (strncmp(smcibdev->pnetid[ibport - 1], lgr->pnet_id, SMC_MAX_PNETID_LEN) || lgr->type == SMC_LGR_SYMMETRIC || lgr->type == SMC_LGR_ASYMMETRIC_PEER) continue; - ib_work = kmalloc(sizeof(*ib_work), GFP_KERNEL); - if (!ib_work) - continue; - INIT_WORK(&ib_work->work, smc_link_up_work); - ib_work->lgr = lgr; - ib_work->smcibdev = smcibdev; - ib_work->ibport = ibport; - schedule_work(&ib_work->work); + + /* trigger local add link processing */ + link = smc_llc_usable_link(lgr); + if (link) + smc_llc_add_link_local(link); } } @@ -1204,10 +1151,12 @@ static void smcr_link_down(struct smc_link *lnk) SMC_LLC_WAIT_TIME); mutex_lock(&lgr->llc_conf_mutex); } - if (!list_empty(&lgr->list)) + if (!list_empty(&lgr->list)) { smc_llc_send_delete_link(to_lnk, del_link_id, SMC_LLC_REQ, true, SMC_LLC_DEL_LOST_PATH); + smcr_link_clear(lnk, true); + } wake_up(&lgr->llc_flow_waiter); /* wake up next waiter */ } } @@ -1247,20 +1196,6 @@ void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport) } } -static void smc_link_up_work(struct work_struct *work) -{ - struct smc_ib_up_work *ib_work = container_of(work, - struct smc_ib_up_work, - work); - struct smc_link_group *lgr = ib_work->lgr; - - if (list_empty(&lgr->list)) - goto out; - smcr_link_up(lgr, ib_work->smcibdev, ib_work->ibport); -out: - kfree(ib_work); -} - static void smc_link_down_work(struct work_struct *work) { struct smc_link *link = container_of(work, struct smc_link, @@ -1333,7 +1268,7 @@ static bool smcr_lgr_match(struct smc_link_group *lgr, return false; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (lgr->lnk[i].state != SMC_LNK_ACTIVE) + if (!smc_link_active(&lgr->lnk[i])) continue; if ((lgr->role == SMC_SERV || lgr->lnk[i].peer_qpn == clcqpn) && !memcmp(lgr->lnk[i].peer_gid, &lcl->gid, SMC_GID_SIZE) && @@ -1376,7 +1311,7 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) && !lgr->sync_err && lgr->vlan_id == ini->vlan_id && - (role == SMC_CLNT || + (role == SMC_CLNT || ini->is_smcd || lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) { /* link group found */ ini->cln_first_contact = SMC_REUSE_CONTACT; @@ -1781,14 +1716,14 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn) { - if (!conn->lgr || conn->lgr->is_smcd || !smc_link_usable(conn->lnk)) + if (!conn->lgr || conn->lgr->is_smcd || !smc_link_active(conn->lnk)) return; smc_ib_sync_sg_for_cpu(conn->lnk, conn->sndbuf_desc, DMA_TO_DEVICE); } void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn) { - if (!conn->lgr || conn->lgr->is_smcd || !smc_link_usable(conn->lnk)) + if (!conn->lgr || conn->lgr->is_smcd || !smc_link_active(conn->lnk)) return; smc_ib_sync_sg_for_device(conn->lnk, conn->sndbuf_desc, DMA_TO_DEVICE); } @@ -1800,7 +1735,7 @@ void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn) if (!conn->lgr || conn->lgr->is_smcd) return; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (!smc_link_usable(&conn->lgr->lnk[i])) + if (!smc_link_active(&conn->lgr->lnk[i])) continue; smc_ib_sync_sg_for_cpu(&conn->lgr->lnk[i], conn->rmb_desc, DMA_FROM_DEVICE); @@ -1814,7 +1749,7 @@ void smc_rmb_sync_sg_for_device(struct smc_connection *conn) if (!conn->lgr || conn->lgr->is_smcd) return; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (!smc_link_usable(&conn->lgr->lnk[i])) + if (!smc_link_active(&conn->lgr->lnk[i])) continue; smc_ib_sync_sg_for_device(&conn->lgr->lnk[i], conn->rmb_desc, DMA_FROM_DEVICE); @@ -1837,8 +1772,12 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd) return rc; /* create rmb */ rc = __smc_buf_create(smc, is_smcd, true); - if (rc) + if (rc) { + mutex_lock(&smc->conn.lgr->sndbufs_lock); + list_del(&smc->conn.sndbuf_desc->list); + mutex_unlock(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); + } return rc; } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index c3ff512fd891..1c4d5439d0ff 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -349,6 +349,11 @@ static inline bool smc_link_usable(struct smc_link *lnk) return true; } +static inline bool smc_link_active(struct smc_link *lnk) +{ + return lnk->state == SMC_LNK_ACTIVE; +} + struct smc_sock; struct smc_clc_msg_accept_confirm; struct smc_clc_msg_local; diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 7637fdebbb78..1c314dbdc7fa 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -506,6 +506,10 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev) int cqe_size_order, smc_order; long rc; + mutex_lock(&smcibdev->mutex); + rc = 0; + if (smcibdev->initialized) + goto out; /* the calculated number of cq entries fits to mlx5 cq allocation */ cqe_size_order = cache_line_size() == 128 ? 7 : 6; smc_order = MAX_ORDER - cqe_size_order - 1; @@ -517,7 +521,7 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev) rc = PTR_ERR_OR_ZERO(smcibdev->roce_cq_send); if (IS_ERR(smcibdev->roce_cq_send)) { smcibdev->roce_cq_send = NULL; - return rc; + goto out; } smcibdev->roce_cq_recv = ib_create_cq(smcibdev->ibdev, smc_wr_rx_cq_handler, NULL, @@ -529,21 +533,26 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev) } smc_wr_add_dev(smcibdev); smcibdev->initialized = 1; - return rc; + goto out; err: ib_destroy_cq(smcibdev->roce_cq_send); +out: + mutex_unlock(&smcibdev->mutex); return rc; } static void smc_ib_cleanup_per_ibdev(struct smc_ib_device *smcibdev) { + mutex_lock(&smcibdev->mutex); if (!smcibdev->initialized) - return; + goto out; smcibdev->initialized = 0; ib_destroy_cq(smcibdev->roce_cq_recv); ib_destroy_cq(smcibdev->roce_cq_send); smc_wr_remove_dev(smcibdev); +out: + mutex_unlock(&smcibdev->mutex); } static struct ib_client smc_ib_client; @@ -566,6 +575,7 @@ static int smc_ib_add_dev(struct ib_device *ibdev) INIT_WORK(&smcibdev->port_event_work, smc_ib_port_event_work); atomic_set(&smcibdev->lnk_cnt, 0); init_waitqueue_head(&smcibdev->lnks_deleted); + mutex_init(&smcibdev->mutex); mutex_lock(&smc_ib_devices.mutex); list_add_tail(&smcibdev->list, &smc_ib_devices.list); mutex_unlock(&smc_ib_devices.mutex); diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index ae6776e1e726..2ce481187dd0 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -52,6 +52,7 @@ struct smc_ib_device { /* ib-device infos for smc */ DECLARE_BITMAP(ports_going_away, SMC_MAX_PORTS); atomic_t lnk_cnt; /* number of links on ibdev */ wait_queue_head_t lnks_deleted; /* wait 4 removal of all links*/ + struct mutex mutex; /* protect dev setup+cleanup */ }; struct smc_buf_desc; diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index c1a038689c63..df5b0a6ea848 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -428,7 +428,7 @@ static int smc_llc_send_confirm_rkey(struct smc_link *send_link, rtok_ix = 1; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { link = &send_link->lgr->lnk[i]; - if (link->state == SMC_LNK_ACTIVE && link != send_link) { + if (smc_link_active(link) && link != send_link) { rkeyllc->rtoken[rtok_ix].link_id = link->link_id; rkeyllc->rtoken[rtok_ix].rmb_key = htonl(rmb_desc->mr_rx[link->link_idx]->rkey); @@ -895,6 +895,36 @@ out: return rc; } +/* as an SMC client, invite server to start the add_link processing */ +static void smc_llc_cli_add_link_invite(struct smc_link *link, + struct smc_llc_qentry *qentry) +{ + struct smc_link_group *lgr = smc_get_lgr(link); + struct smc_init_info ini; + + if (lgr->type == SMC_LGR_SYMMETRIC || + lgr->type == SMC_LGR_ASYMMETRIC_PEER) + goto out; + + ini.vlan_id = lgr->vlan_id; + smc_pnet_find_alt_roce(lgr, &ini, link->smcibdev); + if (!ini.ib_dev) + goto out; + + smc_llc_send_add_link(link, ini.ib_dev->mac[ini.ib_port - 1], + ini.ib_gid, NULL, SMC_LLC_REQ); +out: + kfree(qentry); +} + +static bool smc_llc_is_local_add_link(union smc_llc_msg *llc) +{ + if (llc->raw.hdr.common.type == SMC_LLC_ADD_LINK && + !llc->add_link.qp_mtu && !llc->add_link.link_num) + return true; + return false; +} + static void smc_llc_process_cli_add_link(struct smc_link_group *lgr) { struct smc_llc_qentry *qentry; @@ -902,7 +932,10 @@ static void smc_llc_process_cli_add_link(struct smc_link_group *lgr) qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); mutex_lock(&lgr->llc_conf_mutex); - smc_llc_cli_add_link(qentry->link, qentry); + if (smc_llc_is_local_add_link(&qentry->msg)) + smc_llc_cli_add_link_invite(qentry->link, qentry); + else + smc_llc_cli_add_link(qentry->link, qentry); mutex_unlock(&lgr->llc_conf_mutex); } @@ -911,7 +944,7 @@ static int smc_llc_active_link_count(struct smc_link_group *lgr) int i, link_count = 0; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (!smc_link_usable(&lgr->lnk[i])) + if (!smc_link_active(&lgr->lnk[i])) continue; link_count++; } @@ -1051,12 +1084,14 @@ static int smc_llc_srv_conf_link(struct smc_link *link, if (rc) return -ENOLINK; /* receive CONFIRM LINK response over the RoCE fabric */ - qentry = smc_llc_wait(lgr, link, SMC_LLC_WAIT_FIRST_TIME, - SMC_LLC_CONFIRM_LINK); - if (!qentry) { + qentry = smc_llc_wait(lgr, link, SMC_LLC_WAIT_FIRST_TIME, 0); + if (!qentry || + qentry->msg.raw.hdr.common.type != SMC_LLC_CONFIRM_LINK) { /* send DELETE LINK */ smc_llc_send_delete_link(link, link_new->link_id, SMC_LLC_REQ, false, SMC_LLC_DEL_LOST_PATH); + if (qentry) + smc_llc_flow_qentry_del(&lgr->llc_flow_lcl); return -ENOLINK; } smc_llc_save_peer_uid(qentry); @@ -1158,14 +1193,14 @@ static void smc_llc_process_srv_add_link(struct smc_link_group *lgr) mutex_unlock(&lgr->llc_conf_mutex); } -/* enqueue a local add_link req to trigger a new add_link flow, only as SERV */ -void smc_llc_srv_add_link_local(struct smc_link *link) +/* enqueue a local add_link req to trigger a new add_link flow */ +void smc_llc_add_link_local(struct smc_link *link) { struct smc_llc_msg_add_link add_llc = {0}; add_llc.hd.length = sizeof(add_llc); add_llc.hd.common.type = SMC_LLC_ADD_LINK; - /* no dev and port needed, we as server ignore client data anyway */ + /* no dev and port needed */ smc_llc_enqueue(link, (union smc_llc_msg *)&add_llc); } @@ -1345,7 +1380,7 @@ static void smc_llc_process_srv_delete_link(struct smc_link_group *lgr) if (lgr->type == SMC_LGR_SINGLE && !list_empty(&lgr->list)) { /* trigger setup of asymm alt link */ - smc_llc_srv_add_link_local(lnk); + smc_llc_add_link_local(lnk); } out: mutex_unlock(&lgr->llc_conf_mutex); @@ -1474,7 +1509,18 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) if (list_empty(&lgr->list)) goto out; /* lgr is terminating */ if (lgr->role == SMC_CLNT) { - if (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_ADD_LINK) { + if (smc_llc_is_local_add_link(llc)) { + if (lgr->llc_flow_lcl.type == + SMC_LLC_FLOW_ADD_LINK) + break; /* add_link in progress */ + if (smc_llc_flow_start(&lgr->llc_flow_lcl, + qentry)) { + schedule_work(&lgr->llc_add_link_work); + } + return; + } + if (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_ADD_LINK && + !lgr->llc_flow_lcl.qentry) { /* a flow is waiting for this message */ smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry); @@ -1498,28 +1544,13 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) } break; case SMC_LLC_DELETE_LINK: - if (lgr->role == SMC_CLNT) { - /* server requests to delete this link, send response */ - if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { - /* DEL LINK REQ during ADD LINK SEQ */ - smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, - qentry); - wake_up(&lgr->llc_msg_waiter); - } else if (smc_llc_flow_start(&lgr->llc_flow_lcl, - qentry)) { - schedule_work(&lgr->llc_del_link_work); - } - } else { - if (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_ADD_LINK && - !lgr->llc_flow_lcl.qentry) { - /* DEL LINK REQ during ADD LINK SEQ */ - smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, - qentry); - wake_up(&lgr->llc_msg_waiter); - } else if (smc_llc_flow_start(&lgr->llc_flow_lcl, - qentry)) { - schedule_work(&lgr->llc_del_link_work); - } + if (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_ADD_LINK && + !lgr->llc_flow_lcl.qentry) { + /* DEL LINK REQ during ADD LINK SEQ */ + smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry); + wake_up(&lgr->llc_msg_waiter); + } else if (smc_llc_flow_start(&lgr->llc_flow_lcl, qentry)) { + schedule_work(&lgr->llc_del_link_work); } return; case SMC_LLC_CONFIRM_RKEY: @@ -1585,23 +1616,30 @@ again: static void smc_llc_rx_response(struct smc_link *link, struct smc_llc_qentry *qentry) { + enum smc_llc_flowtype flowtype = link->lgr->llc_flow_lcl.type; + struct smc_llc_flow *flow = &link->lgr->llc_flow_lcl; u8 llc_type = qentry->msg.raw.hdr.common.type; switch (llc_type) { case SMC_LLC_TEST_LINK: - if (link->state == SMC_LNK_ACTIVE) + if (smc_link_active(link)) complete(&link->llc_testlink_resp); break; case SMC_LLC_ADD_LINK: - case SMC_LLC_DELETE_LINK: - case SMC_LLC_CONFIRM_LINK: case SMC_LLC_ADD_LINK_CONT: + case SMC_LLC_CONFIRM_LINK: + if (flowtype != SMC_LLC_FLOW_ADD_LINK || flow->qentry) + break; /* drop out-of-flow response */ + goto assign; + case SMC_LLC_DELETE_LINK: + if (flowtype != SMC_LLC_FLOW_DEL_LINK || flow->qentry) + break; /* drop out-of-flow response */ + goto assign; case SMC_LLC_CONFIRM_RKEY: case SMC_LLC_DELETE_RKEY: - /* assign responses to the local flow, we requested them */ - smc_llc_flow_qentry_set(&link->lgr->llc_flow_lcl, qentry); - wake_up(&link->lgr->llc_msg_waiter); - return; + if (flowtype != SMC_LLC_FLOW_RKEY || flow->qentry) + break; /* drop out-of-flow response */ + goto assign; case SMC_LLC_CONFIRM_RKEY_CONT: /* not used because max links is 3 */ break; @@ -1610,6 +1648,11 @@ static void smc_llc_rx_response(struct smc_link *link, break; } kfree(qentry); + return; +assign: + /* assign responses to the local flow, we requested them */ + smc_llc_flow_qentry_set(&link->lgr->llc_flow_lcl, qentry); + wake_up(&link->lgr->llc_msg_waiter); } static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc) @@ -1663,7 +1706,7 @@ static void smc_llc_testlink_work(struct work_struct *work) u8 user_data[16] = { 0 }; int rc; - if (link->state != SMC_LNK_ACTIVE) + if (!smc_link_active(link)) return; /* don't reschedule worker */ expire_time = link->wr_rx_tstamp + link->llc_testlink_time; if (time_is_after_jiffies(expire_time)) { @@ -1675,7 +1718,7 @@ static void smc_llc_testlink_work(struct work_struct *work) /* receive TEST LINK response over RoCE fabric */ rc = wait_for_completion_interruptible_timeout(&link->llc_testlink_resp, SMC_LLC_WAIT_TIME); - if (link->state != SMC_LNK_ACTIVE) + if (!smc_link_active(link)) return; /* link state changed */ if (rc <= 0) { smcr_link_down_cond_sched(link); diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h index a5d2fe3eea61..cc00a2ec4e92 100644 --- a/net/smc/smc_llc.h +++ b/net/smc/smc_llc.h @@ -103,7 +103,7 @@ void smc_llc_send_link_delete_all(struct smc_link_group *lgr, bool ord, u32 rsn); int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry); int smc_llc_srv_add_link(struct smc_link *link); -void smc_llc_srv_add_link_local(struct smc_link *link); +void smc_llc_add_link_local(struct smc_link *link); int smc_llc_init(void) __init; #endif /* SMC_LLC_H */ diff --git a/net/tipc/link.c b/net/tipc/link.c index 263d950e70e9..d40f8e5b7683 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -827,11 +827,11 @@ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq) state |= l->bc_rcvlink->rcv_unacked; state |= l->rcv_unacked; state |= !skb_queue_empty(&l->transmq); - state |= !skb_queue_empty(&l->deferdq); probe = mstate->probing; probe |= l->silent_intv_cnt; if (probe || mstate->monitoring) l->silent_intv_cnt++; + probe |= !skb_queue_empty(&l->deferdq); if (l->snd_nxt == l->checkpoint) { tipc_link_update_cwin(l, 0, 0); probe = true; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index dfbaf6bd8b1c..2700a63ab095 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -22,7 +22,7 @@ #include <net/af_vsock.h> static struct workqueue_struct *virtio_vsock_workqueue; -static struct virtio_vsock *the_virtio_vsock; +static struct virtio_vsock __rcu *the_virtio_vsock; static DEFINE_MUTEX(the_virtio_vsock_mutex); /* protects the_virtio_vsock */ struct virtio_vsock { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0e07fb8585fb..7fbca0854265 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -13266,13 +13266,13 @@ static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info) if (!wdev_running(wdev)) return -ENETDOWN; } - - if (!vcmd->doit) - return -EOPNOTSUPP; } else { wdev = NULL; } + if (!vcmd->doit) + return -EOPNOTSUPP; + if (info->attrs[NL80211_ATTR_VENDOR_DATA]) { data = nla_data(info->attrs[NL80211_ATTR_VENDOR_DATA]); len = nla_len(info->attrs[NL80211_ATTR_VENDOR_DATA]); diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index 100e29682b48..827ccdf2db57 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -15,6 +15,7 @@ static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb, { if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf || !sk_rmem_schedule(sk, skb, skb->truesize)) { + XFRM_INC_STATS(sock_net(sk), LINUX_MIB_XFRMINERROR); kfree_skb(skb); return; } @@ -49,23 +50,51 @@ static void espintcp_rcv(struct strparser *strp, struct sk_buff *skb) struct espintcp_ctx *ctx = container_of(strp, struct espintcp_ctx, strp); struct strp_msg *rxm = strp_msg(skb); + int len = rxm->full_len - 2; u32 nonesp_marker; int err; + /* keepalive packet? */ + if (unlikely(len == 1)) { + u8 data; + + err = skb_copy_bits(skb, rxm->offset + 2, &data, 1); + if (err < 0) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR); + kfree_skb(skb); + return; + } + + if (data == 0xff) { + kfree_skb(skb); + return; + } + } + + /* drop other short messages */ + if (unlikely(len <= sizeof(nonesp_marker))) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR); + kfree_skb(skb); + return; + } + err = skb_copy_bits(skb, rxm->offset + 2, &nonesp_marker, sizeof(nonesp_marker)); if (err < 0) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINHDRERROR); kfree_skb(skb); return; } /* remove header, leave non-ESP marker/SPI */ if (!__pskb_pull(skb, rxm->offset + 2)) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINERROR); kfree_skb(skb); return; } if (pskb_trim(skb, rxm->full_len - 2) != 0) { + XFRM_INC_STATS(sock_net(strp->sk), LINUX_MIB_XFRMINERROR); kfree_skb(skb); return; } @@ -91,7 +120,7 @@ static int espintcp_parse(struct strparser *strp, struct sk_buff *skb) return err; len = be16_to_cpu(blen); - if (len < 6) + if (len < 2) return -EINVAL; return len; @@ -109,8 +138,11 @@ static int espintcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, flags |= nonblock ? MSG_DONTWAIT : 0; skb = __skb_recv_datagram(sk, &ctx->ike_queue, flags, &off, &err); - if (!skb) + if (!skb) { + if (err == -EAGAIN && sk->sk_shutdown & RCV_SHUTDOWN) + return 0; return err; + } copied = len; if (copied > skb->len) @@ -213,7 +245,7 @@ retry: return 0; } -static int espintcp_push_msgs(struct sock *sk) +static int espintcp_push_msgs(struct sock *sk, int flags) { struct espintcp_ctx *ctx = espintcp_getctx(sk); struct espintcp_msg *emsg = &ctx->partial; @@ -227,12 +259,12 @@ static int espintcp_push_msgs(struct sock *sk) ctx->tx_running = 1; if (emsg->skb) - err = espintcp_sendskb_locked(sk, emsg, 0); + err = espintcp_sendskb_locked(sk, emsg, flags); else - err = espintcp_sendskmsg_locked(sk, emsg, 0); + err = espintcp_sendskmsg_locked(sk, emsg, flags); if (err == -EAGAIN) { ctx->tx_running = 0; - return 0; + return flags & MSG_DONTWAIT ? -EAGAIN : 0; } if (!err) memset(emsg, 0, sizeof(*emsg)); @@ -257,7 +289,7 @@ int espintcp_push_skb(struct sock *sk, struct sk_buff *skb) offset = skb_transport_offset(skb); len = skb->len - offset; - espintcp_push_msgs(sk); + espintcp_push_msgs(sk, 0); if (emsg->len) { kfree_skb(skb); @@ -270,7 +302,7 @@ int espintcp_push_skb(struct sock *sk, struct sk_buff *skb) emsg->len = len; emsg->skb = skb; - espintcp_push_msgs(sk); + espintcp_push_msgs(sk, 0); return 0; } @@ -287,7 +319,7 @@ static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) char buf[2] = {0}; int err, end; - if (msg->msg_flags) + if (msg->msg_flags & ~MSG_DONTWAIT) return -EOPNOTSUPP; if (size > MAX_ESPINTCP_MSG) @@ -298,9 +330,10 @@ static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) lock_sock(sk); - err = espintcp_push_msgs(sk); + err = espintcp_push_msgs(sk, msg->msg_flags & MSG_DONTWAIT); if (err < 0) { - err = -ENOBUFS; + if (err != -EAGAIN || !(msg->msg_flags & MSG_DONTWAIT)) + err = -ENOBUFS; goto unlock; } @@ -337,10 +370,9 @@ static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) tcp_rate_check_app_limited(sk); - err = espintcp_push_msgs(sk); + err = espintcp_push_msgs(sk, msg->msg_flags & MSG_DONTWAIT); /* this message could be partially sent, keep it */ - if (err < 0) - goto unlock; + release_sock(sk); return size; @@ -374,7 +406,7 @@ static void espintcp_tx_work(struct work_struct *work) lock_sock(sk); if (!ctx->tx_running) - espintcp_push_msgs(sk); + espintcp_push_msgs(sk, 0); release_sock(sk); } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 564aa6492e7c..19c5e0fa3f44 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -39,7 +39,7 @@ #ifdef CONFIG_XFRM_STATISTICS #include <net/snmp.h> #endif -#ifdef CONFIG_INET_ESPINTCP +#ifdef CONFIG_XFRM_ESPINTCP #include <net/espintcp.h> #endif @@ -1433,14 +1433,10 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, spin_unlock_bh(&pq->hold_queue.lock); } -static bool xfrm_policy_mark_match(struct xfrm_policy *policy, - struct xfrm_policy *pol) +static inline bool xfrm_policy_mark_match(const struct xfrm_mark *mark, + struct xfrm_policy *pol) { - if (policy->mark.v == pol->mark.v && - policy->priority == pol->priority) - return true; - - return false; + return mark->v == pol->mark.v && mark->m == pol->mark.m; } static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed) @@ -1503,7 +1499,7 @@ static void xfrm_policy_insert_inexact_list(struct hlist_head *chain, if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && - xfrm_policy_mark_match(policy, pol) && + xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { delpol = pol; @@ -1538,7 +1534,7 @@ static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain, if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && - xfrm_policy_mark_match(policy, pol) && + xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { if (excl) @@ -1610,9 +1606,8 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) EXPORT_SYMBOL(xfrm_policy_insert); static struct xfrm_policy * -__xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, - u8 type, int dir, - struct xfrm_selector *sel, +__xfrm_policy_bysel_ctx(struct hlist_head *chain, const struct xfrm_mark *mark, + u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx) { struct xfrm_policy *pol; @@ -1623,7 +1618,7 @@ __xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && pol->if_id == if_id && - (mark & pol->mark.m) == pol->mark.v && + xfrm_policy_mark_match(mark, pol) && !selector_cmp(sel, &pol->selector) && xfrm_sec_ctx_match(ctx, pol->security)) return pol; @@ -1632,11 +1627,10 @@ __xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, return NULL; } -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, - u8 type, int dir, - struct xfrm_selector *sel, - struct xfrm_sec_ctx *ctx, int delete, - int *err) +struct xfrm_policy * +xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, struct xfrm_selector *sel, + struct xfrm_sec_ctx *ctx, int delete, int *err) { struct xfrm_pol_inexact_bin *bin = NULL; struct xfrm_policy *pol, *ret = NULL; @@ -1703,9 +1697,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, - u8 type, int dir, u32 id, int delete, - int *err) +struct xfrm_policy * +xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, u32 id, int delete, int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; @@ -1720,8 +1714,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, ret = NULL; hlist_for_each_entry(pol, chain, byidx) { if (pol->type == type && pol->index == id && - pol->if_id == if_id && - (mark & pol->mark.m) == pol->mark.v) { + pol->if_id == if_id && xfrm_policy_mark_match(mark, pol)) { xfrm_pol_hold(pol); if (delete) { *err = security_xfrm_policy_delete( @@ -4156,7 +4149,7 @@ void __init xfrm_init(void) seqcount_init(&xfrm_policy_hash_generation); xfrm_input_init(); -#ifdef CONFIG_INET_ESPINTCP +#ifdef CONFIG_XFRM_ESPINTCP espintcp_init(); #endif diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index e6cfaa680ef3..fbb7d9d06478 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1863,7 +1863,6 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct km_event c; int delete; struct xfrm_mark m; - u32 mark = xfrm_mark_get(attrs, &m); u32 if_id = 0; p = nlmsg_data(nlh); @@ -1880,8 +1879,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + xfrm_mark_get(attrs, &m); + if (p->index) - xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, delete, &err); + xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, + p->index, delete, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -1898,8 +1900,8 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel, - ctx, delete, &err); + xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir, + &p->sel, ctx, delete, &err); security_xfrm_policy_free(ctx); } if (xp == NULL) @@ -2166,7 +2168,6 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, u8 type = XFRM_POLICY_TYPE_MAIN; int err = -ENOENT; struct xfrm_mark m; - u32 mark = xfrm_mark_get(attrs, &m); u32 if_id = 0; err = copy_from_user_policy_type(&type, attrs); @@ -2180,8 +2181,11 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + xfrm_mark_get(attrs, &m); + if (p->index) - xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, 0, &err); + xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, p->index, + 0, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -2198,7 +2202,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, + xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir, &p->sel, ctx, 0, &err); security_xfrm_policy_free(ctx); } diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index 3651cbf6ad49..f54b6ac37ac2 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -124,9 +124,6 @@ existing-targets := $(wildcard $(sort $(targets))) -include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd) -PHONY += FORCE -FORCE: - endif .PHONY: $(PHONY) diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh index 66a6d511b524..0869def435ee 100755 --- a/scripts/decode_stacktrace.sh +++ b/scripts/decode_stacktrace.sh @@ -87,8 +87,8 @@ parse_symbol() { return fi - # Strip out the base of the path - code=${code#$basepath/} + # Strip out the base of the path on each line + code=$(while read -r line; do echo "${line#$basepath/}"; done <<< "$code") # In the case of inlines, move everything to same line code=${code//$'\n'/' '} diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py index be984aa29b75..1be9763cf8bb 100644 --- a/scripts/gdb/linux/symbols.py +++ b/scripts/gdb/linux/symbols.py @@ -96,7 +96,7 @@ lx-symbols command.""" return "" attrs = sect_attrs['attrs'] section_name_to_address = { - attrs[n]['name'].string(): attrs[n]['address'] + attrs[n]['battr']['attr']['name'].string(): attrs[n]['address'] for n in range(int(sect_attrs['nsections']))} args = [] for section_name in [".data", ".data..read_mostly", ".rodata", ".bss", diff --git a/scripts/kconfig/.gitignore b/scripts/kconfig/.gitignore index 12a67fdab541..c3d537cd0275 100644 --- a/scripts/kconfig/.gitignore +++ b/scripts/kconfig/.gitignore @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -*.moc +/qconf-moc.cc *conf-cfg # diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index 426881ea954f..52b59bf9efe4 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -181,19 +181,22 @@ $(addprefix $(obj)/, mconf.o $(lxdialog)): $(obj)/mconf-cfg # qconf: Used for the xconfig target based on Qt hostprogs += qconf -qconf-cxxobjs := qconf.o +qconf-cxxobjs := qconf.o qconf-moc.o qconf-objs := images.o $(common-objs) HOSTLDLIBS_qconf = $(shell . $(obj)/qconf-cfg && echo $$libs) HOSTCXXFLAGS_qconf.o = $(shell . $(obj)/qconf-cfg && echo $$cflags) +HOSTCXXFLAGS_qconf-moc.o = $(shell . $(obj)/qconf-cfg && echo $$cflags) -$(obj)/qconf.o: $(obj)/qconf-cfg $(obj)/qconf.moc +$(obj)/qconf.o: $(obj)/qconf-cfg quiet_cmd_moc = MOC $@ - cmd_moc = $(shell . $(obj)/qconf-cfg && echo $$moc) -i $< -o $@ + cmd_moc = $(shell . $(obj)/qconf-cfg && echo $$moc) $< -o $@ -$(obj)/%.moc: $(src)/%.h $(obj)/qconf-cfg - $(call cmd,moc) +$(obj)/qconf-moc.cc: $(src)/qconf.h $(obj)/qconf-cfg FORCE + $(call if_changed,moc) + +targets += qconf-moc.cc # gconf: Used for the gconfig target based on GTK+ hostprogs += gconf diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc index 4a616128a154..23d1cb01a41a 100644 --- a/scripts/kconfig/qconf.cc +++ b/scripts/kconfig/qconf.cc @@ -23,7 +23,6 @@ #include "lkc.h" #include "qconf.h" -#include "qconf.moc" #include "images.h" @@ -308,10 +307,7 @@ ConfigList::ConfigList(ConfigView* p, const char *name) setVerticalScrollMode(ScrollPerPixel); setHorizontalScrollMode(ScrollPerPixel); - if (mode == symbolMode) - setHeaderLabels(QStringList() << "Item" << "Name" << "N" << "M" << "Y" << "Value"); - else - setHeaderLabels(QStringList() << "Option" << "Name" << "N" << "M" << "Y" << "Value"); + setHeaderLabels(QStringList() << "Option" << "Name" << "N" << "M" << "Y" << "Value"); connect(this, SIGNAL(itemSelectionChanged(void)), SLOT(updateSelection(void))); @@ -392,11 +388,6 @@ void ConfigList::updateSelection(void) struct menu *menu; enum prop_type type; - if (mode == symbolMode) - setHeaderLabels(QStringList() << "Item" << "Name" << "N" << "M" << "Y" << "Value"); - else - setHeaderLabels(QStringList() << "Option" << "Name" << "N" << "M" << "Y" << "Value"); - if (selectedItems().count() == 0) return; @@ -437,14 +428,13 @@ void ConfigList::updateList(ConfigItem* item) if (rootEntry != &rootmenu && (mode == singleMode || (mode == symbolMode && rootEntry->parent != &rootmenu))) { item = (ConfigItem *)topLevelItem(0); - if (!item && mode != symbolMode) { + if (!item) item = new ConfigItem(this, 0, true); - last = item; - } + last = item; } if ((mode == singleMode || (mode == symbolMode && !(rootEntry->flags & MENU_ROOT))) && rootEntry->sym && rootEntry->prompt) { - item = last ? last->nextSibling() : firstChild(); + item = last ? last->nextSibling() : nullptr; if (!item) item = new ConfigItem(this, last, rootEntry, true); else @@ -1239,7 +1229,7 @@ void ConfigInfoView::clicked(const QUrl &url) if (count < 1) { qInfo() << "Clicked link is empty"; - delete data; + delete[] data; return; } @@ -1252,7 +1242,7 @@ void ConfigInfoView::clicked(const QUrl &url) result = sym_re_search(data); if (!result) { qInfo() << "Clicked symbol is invalid:" << data; - delete data; + delete[] data; return; } @@ -1735,7 +1725,6 @@ void ConfigMainWindow::listFocusChanged(void) void ConfigMainWindow::goBack(void) { -qInfo() << __FUNCTION__; if (configList->rootEntry == &rootmenu) return; diff --git a/scripts/kconfig/qconf.h b/scripts/kconfig/qconf.h index fb9e9729266f..5eeab4a8bb43 100644 --- a/scripts/kconfig/qconf.h +++ b/scripts/kconfig/qconf.h @@ -92,10 +92,6 @@ public: { return this; } - ConfigItem* firstChild() const - { - return (ConfigItem *)children().first(); - } void addColumn(colIdx idx) { showColumn(idx); diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 6aea65c65745..69341b36f271 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -138,11 +138,20 @@ char *read_text_file(const char *filename) char *get_line(char **stringp) { + char *orig = *stringp, *next; + /* do not return the unwanted extra line at EOF */ - if (*stringp && **stringp == '\0') + if (!orig || *orig == '\0') return NULL; - return strsep(stringp, "\n"); + /* don't use strsep here, it is not available everywhere */ + next = strchr(orig, '\n'); + if (next) + *next++ = '\0'; + + *stringp = next; + + return orig; } /* A list of all modules we processed */ diff --git a/sound/core/info.c b/sound/core/info.c index 8c6bc5241df5..9fec3070f8ba 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -606,7 +606,9 @@ int snd_info_get_line(struct snd_info_buffer *buffer, char *line, int len) { int c; - if (snd_BUG_ON(!buffer || !buffer->buffer)) + if (snd_BUG_ON(!buffer)) + return 1; + if (!buffer->buffer) return 1; if (len <= 0 || buffer->stop || buffer->error) return 1; diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 7e3ae4534df9..803978d69e3c 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -2935,6 +2935,10 @@ static int hda_codec_runtime_suspend(struct device *dev) struct hda_codec *codec = dev_to_hda_codec(dev); unsigned int state; + /* Nothing to do if card registration fails and the component driver never probes */ + if (!codec->card) + return 0; + cancel_delayed_work_sync(&codec->jackpoll_work); state = hda_call_codec_suspend(codec); if (codec->link_down_at_suspend || @@ -2949,6 +2953,10 @@ static int hda_codec_runtime_resume(struct device *dev) { struct hda_codec *codec = dev_to_hda_codec(dev); + /* Nothing to do if card registration fails and the component driver never probes */ + if (!codec->card) + return 0; + codec_display_power(codec, true); snd_hdac_codec_link_up(&codec->core); hda_call_codec_resume(codec); diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h index 82e26442724b..a356fb0e5773 100644 --- a/sound/pci/hda/hda_controller.h +++ b/sound/pci/hda/hda_controller.h @@ -41,7 +41,7 @@ /* 24 unused */ #define AZX_DCAPS_COUNT_LPIB_DELAY (1 << 25) /* Take LPIB as delay */ #define AZX_DCAPS_PM_RUNTIME (1 << 26) /* runtime PM support */ -/* 27 unused */ +#define AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP (1 << 27) /* Workaround for spurious wakeups after suspend */ #define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28) /* CORBRP clears itself after reset */ #define AZX_DCAPS_NO_MSI64 (1 << 29) /* Stick to 32-bit MSIs */ #define AZX_DCAPS_SEPARATE_STREAM_TAG (1 << 30) /* capture and playback use separate stream tag */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 3565e2ab0965..3fbba2e51e36 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -298,7 +298,8 @@ enum { /* PCH for HSW/BDW; with runtime PM */ /* no i915 binding for this as HSW/BDW has another controller for HDMI */ #define AZX_DCAPS_INTEL_PCH \ - (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME) + (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\ + AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP) /* HSW HDMI */ #define AZX_DCAPS_INTEL_HASWELL \ @@ -1028,7 +1029,14 @@ static int azx_suspend(struct device *dev) chip = card->private_data; bus = azx_bus(chip); snd_power_change_state(card, SNDRV_CTL_POWER_D3hot); - pm_runtime_force_suspend(dev); + /* An ugly workaround: direct call of __azx_runtime_suspend() and + * __azx_runtime_resume() for old Intel platforms that suffer from + * spurious wakeups after S3 suspend + */ + if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP) + __azx_runtime_suspend(chip); + else + pm_runtime_force_suspend(dev); if (bus->irq >= 0) { free_irq(bus->irq, chip); bus->irq = -1; @@ -1057,7 +1065,10 @@ static int azx_resume(struct device *dev) if (azx_acquire_irq(chip, 1) < 0) return -EIO; - pm_runtime_force_resume(dev); + if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP) + __azx_runtime_resume(chip, false); + else + pm_runtime_force_resume(dev); snd_power_change_state(card, SNDRV_CTL_POWER_D0); trace_azx_resume(chip); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 41eaa89660c3..cd46247988e4 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2440,6 +2440,7 @@ static void generic_acomp_notifier_set(struct drm_audio_component *acomp, mutex_lock(&spec->bind_lock); spec->use_acomp_notifier = use_acomp; spec->codec->relaxed_resume = use_acomp; + spec->codec->bus->keep_power = 0; /* reprogram each jack detection logic depending on the notifier */ for (i = 0; i < spec->num_pins; i++) reprogram_jack_detect(spec->codec, @@ -2534,7 +2535,6 @@ static void generic_acomp_init(struct hda_codec *codec, if (!snd_hdac_acomp_init(&codec->bus->core, &spec->drm_audio_ops, match_bound_vga, 0)) { spec->acomp_registered = true; - codec->bus->keep_power = 0; } } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 1b06c4261248..29f5878f0c50 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5975,6 +5975,16 @@ static void alc_fixup_disable_mic_vref(struct hda_codec *codec, snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREFHIZ); } +static void alc285_fixup_hp_gpio_amp_init(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action != HDA_FIXUP_ACT_INIT) + return; + + msleep(100); + alc_write_coef_idx(codec, 0x65, 0x0); +} + /* for hda_fixup_thinkpad_acpi() */ #include "thinkpad_helper.c" @@ -6152,8 +6162,10 @@ enum { ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS, ALC269VC_FIXUP_ACER_HEADSET_MIC, ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE, - ALC289_FIXUP_ASUS_G401, + ALC289_FIXUP_ASUS_GA401, + ALC289_FIXUP_ASUS_GA502, ALC256_FIXUP_ACER_MIC_NO_PRESENCE, + ALC285_FIXUP_HP_GPIO_AMP_INIT, }; static const struct hda_fixup alc269_fixups[] = { @@ -7363,7 +7375,14 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MIC }, - [ALC289_FIXUP_ASUS_G401] = { + [ALC289_FIXUP_ASUS_GA401] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11020 }, /* headset mic with jack detect */ + { } + }, + }, + [ALC289_FIXUP_ASUS_GA502] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { { 0x19, 0x03a11020 }, /* headset mic with jack detect */ @@ -7379,6 +7398,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE }, + [ALC285_FIXUP_HP_GPIO_AMP_INIT] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_hp_gpio_amp_init, + .chained = true, + .chain_id = ALC285_FIXUP_HP_GPIO_LED + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7529,7 +7554,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED), - SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), @@ -7561,7 +7586,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC), - SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_G401), + SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502), + SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC), @@ -7581,12 +7607,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10cf, 0x1629, "Lifebook U7x7", ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC), SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), - SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC225_FIXUP_HEADSET_JACK), + SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8), + SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), diff --git a/sound/soc/amd/raven/pci-acp3x.c b/sound/soc/amd/raven/pci-acp3x.c index f25ce50f1a90..ebf4388b6262 100644 --- a/sound/soc/amd/raven/pci-acp3x.c +++ b/sound/soc/amd/raven/pci-acp3x.c @@ -232,9 +232,7 @@ static int snd_acp3x_probe(struct pci_dev *pci, } pm_runtime_set_autosuspend_delay(&pci->dev, 2000); pm_runtime_use_autosuspend(&pci->dev); - pm_runtime_set_active(&pci->dev); pm_runtime_put_noidle(&pci->dev); - pm_runtime_enable(&pci->dev); pm_runtime_allow(&pci->dev); return 0; @@ -303,7 +301,7 @@ static void snd_acp3x_remove(struct pci_dev *pci) ret = acp3x_deinit(adata->acp3x_base); if (ret) dev_err(&pci->dev, "ACP de-init failed\n"); - pm_runtime_disable(&pci->dev); + pm_runtime_forbid(&pci->dev); pm_runtime_get_noresume(&pci->dev); pci_disable_msi(pci); pci_release_regions(pci); diff --git a/sound/soc/codecs/max98373.c b/sound/soc/codecs/max98373.c index 96718e3a1ad0..d87402a86c88 100644 --- a/sound/soc/codecs/max98373.c +++ b/sound/soc/codecs/max98373.c @@ -779,13 +779,6 @@ static int max98373_probe(struct snd_soc_component *component) regmap_write(max98373->regmap, MAX98373_R202A_PCM_TO_SPK_MONO_MIX_2, 0x1); - /* Set inital volume (0dB) */ - regmap_write(max98373->regmap, - MAX98373_R203D_AMP_DIG_VOL_CTRL, - 0x00); - regmap_write(max98373->regmap, - MAX98373_R203E_AMP_PATH_GAIN, - 0x00); /* Enable DC blocker */ regmap_write(max98373->regmap, MAX98373_R203F_AMP_DSP_CFG, @@ -869,7 +862,6 @@ static const struct snd_soc_component_driver soc_codec_dev_max98373 = { .num_dapm_widgets = ARRAY_SIZE(max98373_dapm_widgets), .dapm_routes = max98373_audio_map, .num_dapm_routes = ARRAY_SIZE(max98373_audio_map), - .idle_bias_on = 1, .use_pmdown_time = 1, .endianness = 1, .non_legacy_dai_naming = 1, diff --git a/sound/soc/codecs/rt286.c b/sound/soc/codecs/rt286.c index 9593a9a27bf8..e8d14eefc41b 100644 --- a/sound/soc/codecs/rt286.c +++ b/sound/soc/codecs/rt286.c @@ -272,13 +272,13 @@ static int rt286_jack_detect(struct rt286_priv *rt286, bool *hp, bool *mic) regmap_read(rt286->regmap, RT286_GET_MIC1_SENSE, &buf); *mic = buf & 0x80000000; } - if (!*mic) { + + if (!*hp) { snd_soc_dapm_disable_pin(dapm, "HV"); snd_soc_dapm_disable_pin(dapm, "VREF"); - } - if (!*hp) snd_soc_dapm_disable_pin(dapm, "LDO1"); - snd_soc_dapm_sync(dapm); + snd_soc_dapm_sync(dapm); + } return 0; } diff --git a/sound/soc/codecs/rt5670.c b/sound/soc/codecs/rt5670.c index 70fee6849ab0..dfbc0ca38ff7 100644 --- a/sound/soc/codecs/rt5670.c +++ b/sound/soc/codecs/rt5670.c @@ -31,18 +31,19 @@ #include "rt5670.h" #include "rt5670-dsp.h" -#define RT5670_DEV_GPIO BIT(0) -#define RT5670_IN2_DIFF BIT(1) -#define RT5670_DMIC_EN BIT(2) -#define RT5670_DMIC1_IN2P BIT(3) -#define RT5670_DMIC1_GPIO6 BIT(4) -#define RT5670_DMIC1_GPIO7 BIT(5) -#define RT5670_DMIC2_INR BIT(6) -#define RT5670_DMIC2_GPIO8 BIT(7) -#define RT5670_DMIC3_GPIO5 BIT(8) -#define RT5670_JD_MODE1 BIT(9) -#define RT5670_JD_MODE2 BIT(10) -#define RT5670_JD_MODE3 BIT(11) +#define RT5670_DEV_GPIO BIT(0) +#define RT5670_IN2_DIFF BIT(1) +#define RT5670_DMIC_EN BIT(2) +#define RT5670_DMIC1_IN2P BIT(3) +#define RT5670_DMIC1_GPIO6 BIT(4) +#define RT5670_DMIC1_GPIO7 BIT(5) +#define RT5670_DMIC2_INR BIT(6) +#define RT5670_DMIC2_GPIO8 BIT(7) +#define RT5670_DMIC3_GPIO5 BIT(8) +#define RT5670_JD_MODE1 BIT(9) +#define RT5670_JD_MODE2 BIT(10) +#define RT5670_JD_MODE3 BIT(11) +#define RT5670_GPIO1_IS_EXT_SPK_EN BIT(12) static unsigned long rt5670_quirk; static unsigned int quirk_override; @@ -602,9 +603,9 @@ int rt5670_set_jack_detect(struct snd_soc_component *component, EXPORT_SYMBOL_GPL(rt5670_set_jack_detect); static const DECLARE_TLV_DB_SCALE(out_vol_tlv, -4650, 150, 0); -static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -65625, 375, 0); +static const DECLARE_TLV_DB_MINMAX(dac_vol_tlv, -6562, 0); static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -3450, 150, 0); -static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -17625, 375, 0); +static const DECLARE_TLV_DB_MINMAX(adc_vol_tlv, -1762, 3000); static const DECLARE_TLV_DB_SCALE(adc_bst_tlv, 0, 1200, 0); /* {0, +20, +24, +30, +35, +40, +44, +50, +52} dB */ @@ -1447,6 +1448,33 @@ static int rt5670_hp_event(struct snd_soc_dapm_widget *w, return 0; } +static int rt5670_spk_event(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); + struct rt5670_priv *rt5670 = snd_soc_component_get_drvdata(component); + + if (!rt5670->pdata.gpio1_is_ext_spk_en) + return 0; + + switch (event) { + case SND_SOC_DAPM_POST_PMU: + regmap_update_bits(rt5670->regmap, RT5670_GPIO_CTRL2, + RT5670_GP1_OUT_MASK, RT5670_GP1_OUT_HI); + break; + + case SND_SOC_DAPM_PRE_PMD: + regmap_update_bits(rt5670->regmap, RT5670_GPIO_CTRL2, + RT5670_GP1_OUT_MASK, RT5670_GP1_OUT_LO); + break; + + default: + return 0; + } + + return 0; +} + static int rt5670_bst1_event(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kcontrol, int event) { @@ -1860,7 +1888,9 @@ static const struct snd_soc_dapm_widget rt5670_specific_dapm_widgets[] = { }; static const struct snd_soc_dapm_widget rt5672_specific_dapm_widgets[] = { - SND_SOC_DAPM_PGA("SPO Amp", SND_SOC_NOPM, 0, 0, NULL, 0), + SND_SOC_DAPM_PGA_E("SPO Amp", SND_SOC_NOPM, 0, 0, NULL, 0, + rt5670_spk_event, SND_SOC_DAPM_PRE_PMD | + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_OUTPUT("SPOLP"), SND_SOC_DAPM_OUTPUT("SPOLN"), SND_SOC_DAPM_OUTPUT("SPORP"), @@ -2857,14 +2887,14 @@ static const struct dmi_system_id dmi_platform_intel_quirks[] = { }, { .callback = rt5670_quirk_cb, - .ident = "Lenovo Thinkpad Tablet 10", + .ident = "Lenovo Miix 2 10", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Miix 2 10"), }, .driver_data = (unsigned long *)(RT5670_DMIC_EN | RT5670_DMIC1_IN2P | - RT5670_DEV_GPIO | + RT5670_GPIO1_IS_EXT_SPK_EN | RT5670_JD_MODE2), }, { @@ -2924,6 +2954,10 @@ static int rt5670_i2c_probe(struct i2c_client *i2c, rt5670->pdata.dev_gpio = true; dev_info(&i2c->dev, "quirk dev_gpio\n"); } + if (rt5670_quirk & RT5670_GPIO1_IS_EXT_SPK_EN) { + rt5670->pdata.gpio1_is_ext_spk_en = true; + dev_info(&i2c->dev, "quirk GPIO1 is external speaker enable\n"); + } if (rt5670_quirk & RT5670_IN2_DIFF) { rt5670->pdata.in2_diff = true; dev_info(&i2c->dev, "quirk IN2_DIFF\n"); @@ -3023,6 +3057,13 @@ static int rt5670_i2c_probe(struct i2c_client *i2c, RT5670_GP1_PF_MASK, RT5670_GP1_PF_OUT); } + if (rt5670->pdata.gpio1_is_ext_spk_en) { + regmap_update_bits(rt5670->regmap, RT5670_GPIO_CTRL1, + RT5670_GP1_PIN_MASK, RT5670_GP1_PIN_GPIO1); + regmap_update_bits(rt5670->regmap, RT5670_GPIO_CTRL2, + RT5670_GP1_PF_MASK, RT5670_GP1_PF_OUT); + } + if (rt5670->pdata.jd_mode) { regmap_update_bits(rt5670->regmap, RT5670_GLB_CLK, RT5670_SCLK_SRC_MASK, RT5670_SCLK_SRC_RCCLK); diff --git a/sound/soc/codecs/rt5670.h b/sound/soc/codecs/rt5670.h index a8c3e44770b8..de0203369b7c 100644 --- a/sound/soc/codecs/rt5670.h +++ b/sound/soc/codecs/rt5670.h @@ -757,7 +757,7 @@ #define RT5670_PWR_VREF2_BIT 4 #define RT5670_PWR_FV2 (0x1 << 3) #define RT5670_PWR_FV2_BIT 3 -#define RT5670_LDO_SEL_MASK (0x3) +#define RT5670_LDO_SEL_MASK (0x7) #define RT5670_LDO_SEL_SFT 0 /* Power Management for Analog 2 (0x64) */ diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index 7d6670abdb08..d503b5bef4ba 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -967,13 +967,12 @@ int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert) rt5682_enable_push_button_irq(component, false); snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1, RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_LOW); - if (snd_soc_dapm_get_pin_status(dapm, "MICBIAS")) + if (!snd_soc_dapm_get_pin_status(dapm, "MICBIAS")) snd_soc_component_update_bits(component, - RT5682_PWR_ANLG_1, RT5682_PWR_VREF2, 0); - else + RT5682_PWR_ANLG_1, RT5682_PWR_MB, 0); + if (!snd_soc_dapm_get_pin_status(dapm, "Vref2")) snd_soc_component_update_bits(component, - RT5682_PWR_ANLG_1, - RT5682_PWR_VREF2 | RT5682_PWR_MB, 0); + RT5682_PWR_ANLG_1, RT5682_PWR_VREF2, 0); snd_soc_component_update_bits(component, RT5682_PWR_ANLG_3, RT5682_PWR_CBJ, 0); @@ -992,16 +991,17 @@ static int rt5682_set_jack_detect(struct snd_soc_component *component, rt5682->hs_jack = hs_jack; - if (!rt5682->is_sdw) { - if (!hs_jack) { - regmap_update_bits(rt5682->regmap, RT5682_IRQ_CTRL_2, - RT5682_JD1_EN_MASK, RT5682_JD1_DIS); - regmap_update_bits(rt5682->regmap, RT5682_RC_CLK_CTRL, - RT5682_POW_JDH | RT5682_POW_JDL, 0); - cancel_delayed_work_sync(&rt5682->jack_detect_work); - return 0; - } + if (!hs_jack) { + regmap_update_bits(rt5682->regmap, RT5682_IRQ_CTRL_2, + RT5682_JD1_EN_MASK, RT5682_JD1_DIS); + regmap_update_bits(rt5682->regmap, RT5682_RC_CLK_CTRL, + RT5682_POW_JDH | RT5682_POW_JDL, 0); + cancel_delayed_work_sync(&rt5682->jack_detect_work); + return 0; + } + + if (!rt5682->is_sdw) { switch (rt5682->pdata.jd_src) { case RT5682_JD1: snd_soc_component_update_bits(component, @@ -1082,7 +1082,8 @@ void rt5682_jack_detect_handler(struct work_struct *work) /* jack was out, report jack type */ rt5682->jack_type = rt5682_headset_detect(rt5682->component, 1); - } else { + } else if ((rt5682->jack_type & SND_JACK_HEADSET) == + SND_JACK_HEADSET) { /* jack is already in, report button event */ rt5682->jack_type = SND_JACK_HEADSET; btn_type = rt5682_button_detect(rt5682->component); @@ -1608,8 +1609,7 @@ static const struct snd_soc_dapm_widget rt5682_dapm_widgets[] = { 0, set_filter_clk, SND_SOC_DAPM_PRE_PMU), SND_SOC_DAPM_SUPPLY("Vref1", RT5682_PWR_ANLG_1, RT5682_PWR_VREF1_BIT, 0, rt5682_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU), - SND_SOC_DAPM_SUPPLY("Vref2", RT5682_PWR_ANLG_1, RT5682_PWR_VREF2_BIT, 0, - NULL, 0), + SND_SOC_DAPM_SUPPLY("Vref2", SND_SOC_NOPM, 0, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("MICBIAS", SND_SOC_NOPM, 0, 0, NULL, 0), /* ASRC */ @@ -2492,6 +2492,15 @@ static int rt5682_wclk_prepare(struct clk_hw *hw) snd_soc_dapm_force_enable_pin_unlocked(dapm, "MICBIAS"); snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1, RT5682_PWR_MB, RT5682_PWR_MB); + + snd_soc_dapm_force_enable_pin_unlocked(dapm, "Vref2"); + snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1, + RT5682_PWR_VREF2 | RT5682_PWR_FV2, + RT5682_PWR_VREF2); + usleep_range(55000, 60000); + snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1, + RT5682_PWR_FV2, RT5682_PWR_FV2); + snd_soc_dapm_force_enable_pin_unlocked(dapm, "I2S1"); snd_soc_dapm_force_enable_pin_unlocked(dapm, "PLL2F"); snd_soc_dapm_force_enable_pin_unlocked(dapm, "PLL2B"); @@ -2517,9 +2526,12 @@ static void rt5682_wclk_unprepare(struct clk_hw *hw) snd_soc_dapm_mutex_lock(dapm); snd_soc_dapm_disable_pin_unlocked(dapm, "MICBIAS"); + snd_soc_dapm_disable_pin_unlocked(dapm, "Vref2"); if (!rt5682->jack_type) snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1, + RT5682_PWR_VREF2 | RT5682_PWR_FV2 | RT5682_PWR_MB, 0); + snd_soc_dapm_disable_pin_unlocked(dapm, "I2S1"); snd_soc_dapm_disable_pin_unlocked(dapm, "PLL2F"); snd_soc_dapm_disable_pin_unlocked(dapm, "PLL2B"); diff --git a/sound/soc/codecs/wm8974.c b/sound/soc/codecs/wm8974.c index 06ba36595ddd..7cfc89602fc3 100644 --- a/sound/soc/codecs/wm8974.c +++ b/sound/soc/codecs/wm8974.c @@ -186,7 +186,7 @@ SOC_DAPM_SINGLE("PCM Playback Switch", WM8974_MONOMIX, 0, 1, 0), /* Boost mixer */ static const struct snd_kcontrol_new wm8974_boost_mixer[] = { -SOC_DAPM_SINGLE("Aux Switch", WM8974_INPPGA, 6, 1, 0), +SOC_DAPM_SINGLE("Aux Switch", WM8974_INPPGA, 6, 1, 1), }; /* Input PGA */ @@ -474,6 +474,10 @@ static int wm8974_set_dai_fmt(struct snd_soc_dai *codec_dai, iface |= 0x0008; break; case SND_SOC_DAIFMT_DSP_A: + if ((fmt & SND_SOC_DAIFMT_INV_MASK) == SND_SOC_DAIFMT_IB_IF || + (fmt & SND_SOC_DAIFMT_INV_MASK) == SND_SOC_DAIFMT_NB_IF) { + return -EINVAL; + } iface |= 0x00018; break; default: diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c index 9ad35d9940fe..97b4f5480a31 100644 --- a/sound/soc/generic/audio-graph-card.c +++ b/sound/soc/generic/audio-graph-card.c @@ -317,8 +317,8 @@ static int graph_dai_link_of_dpcm(struct asoc_simple_priv *priv, if (ret < 0) goto out_put_node; - dai_link->dpcm_playback = 1; - dai_link->dpcm_capture = 1; + snd_soc_dai_link_set_capabilities(dai_link); + dai_link->ops = &graph_ops; dai_link->init = asoc_simple_dai_init; diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index 55e9f8800b3e..04d4d28ed511 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -231,8 +231,8 @@ static int simple_dai_link_of_dpcm(struct asoc_simple_priv *priv, if (ret < 0) goto out_put_node; - dai_link->dpcm_playback = 1; - dai_link->dpcm_capture = 1; + snd_soc_dai_link_set_capabilities(dai_link); + dai_link->ops = &simple_ops; dai_link->init = asoc_simple_dai_init; diff --git a/sound/soc/intel/boards/bdw-rt5677.c b/sound/soc/intel/boards/bdw-rt5677.c index 5f96d7ac0a22..bed4d5f73d9c 100644 --- a/sound/soc/intel/boards/bdw-rt5677.c +++ b/sound/soc/intel/boards/bdw-rt5677.c @@ -354,6 +354,7 @@ static struct snd_soc_dai_link bdw_rt5677_dais[] = { { .name = "Codec DSP", .stream_name = "Wake on Voice", + .capture_only = 1, .ops = &bdw_rt5677_dsp_ops, SND_SOC_DAILINK_REG(dsp), }, diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c index 9e5fc9430628..ecbc58e8a37f 100644 --- a/sound/soc/intel/boards/bytcht_es8316.c +++ b/sound/soc/intel/boards/bytcht_es8316.c @@ -543,8 +543,10 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev) if (cnt) { ret = device_add_properties(codec_dev, props); - if (ret) + if (ret) { + put_device(codec_dev); return ret; + } } devm_acpi_dev_add_driver_gpios(codec_dev, byt_cht_es8316_gpios); diff --git a/sound/soc/intel/boards/cht_bsw_rt5672.c b/sound/soc/intel/boards/cht_bsw_rt5672.c index 7a43c70a1378..22e432768edb 100644 --- a/sound/soc/intel/boards/cht_bsw_rt5672.c +++ b/sound/soc/intel/boards/cht_bsw_rt5672.c @@ -253,21 +253,20 @@ static int cht_codec_fixup(struct snd_soc_pcm_runtime *rtd, params_set_format(params, SNDRV_PCM_FORMAT_S24_LE); /* - * Default mode for SSP configuration is TDM 4 slot + * Default mode for SSP configuration is TDM 4 slot. One board/design, + * the Lenovo Miix 2 10 uses not 1 but 2 codecs connected to SSP2. The + * second piggy-backed, output-only codec is inside the keyboard-dock + * (which has extra speakers). Unlike the main rt5672 codec, we cannot + * configure this codec, it is hard coded to use 2 channel 24 bit I2S. + * Since we only support 2 channels anyways, there is no need for TDM + * on any cht-bsw-rt5672 designs. So we simply use I2S 2ch everywhere. */ - ret = snd_soc_dai_set_fmt(asoc_rtd_to_codec(rtd, 0), - SND_SOC_DAIFMT_DSP_B | - SND_SOC_DAIFMT_IB_NF | + ret = snd_soc_dai_set_fmt(asoc_rtd_to_cpu(rtd, 0), + SND_SOC_DAIFMT_I2S | + SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBS_CFS); if (ret < 0) { - dev_err(rtd->dev, "can't set format to TDM %d\n", ret); - return ret; - } - - /* TDM 4 slots 24 bit, set Rx & Tx bitmask to 4 active slots */ - ret = snd_soc_dai_set_tdm_slot(asoc_rtd_to_codec(rtd, 0), 0xF, 0xF, 4, 24); - if (ret < 0) { - dev_err(rtd->dev, "can't set codec TDM slot %d\n", ret); + dev_err(rtd->dev, "can't set format to I2S, err %d\n", ret); return ret; } diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig index f51b28d1b94d..92f51d0e9fe2 100644 --- a/sound/soc/qcom/Kconfig +++ b/sound/soc/qcom/Kconfig @@ -72,7 +72,7 @@ config SND_SOC_QDSP6_ASM_DAI config SND_SOC_QDSP6 tristate "SoC ALSA audio driver for QDSP6" - depends on QCOM_APR && HAS_DMA + depends on QCOM_APR select SND_SOC_QDSP6_COMMON select SND_SOC_QDSP6_CORE select SND_SOC_QDSP6_AFE diff --git a/sound/soc/rockchip/rk3399_gru_sound.c b/sound/soc/rockchip/rk3399_gru_sound.c index f45e5aaa4b30..9539b0d024fe 100644 --- a/sound/soc/rockchip/rk3399_gru_sound.c +++ b/sound/soc/rockchip/rk3399_gru_sound.c @@ -219,19 +219,32 @@ static int rockchip_sound_dmic_hw_params(struct snd_pcm_substream *substream, return 0; } +static int rockchip_sound_startup(struct snd_pcm_substream *substream) +{ + struct snd_pcm_runtime *runtime = substream->runtime; + + runtime->hw.formats = SNDRV_PCM_FMTBIT_S16_LE; + return snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_RATE, + 8000, 96000); +} + static const struct snd_soc_ops rockchip_sound_max98357a_ops = { + .startup = rockchip_sound_startup, .hw_params = rockchip_sound_max98357a_hw_params, }; static const struct snd_soc_ops rockchip_sound_rt5514_ops = { + .startup = rockchip_sound_startup, .hw_params = rockchip_sound_rt5514_hw_params, }; static const struct snd_soc_ops rockchip_sound_da7219_ops = { + .startup = rockchip_sound_startup, .hw_params = rockchip_sound_da7219_hw_params, }; static const struct snd_soc_ops rockchip_sound_dmic_ops = { + .startup = rockchip_sound_startup, .hw_params = rockchip_sound_dmic_hw_params, }; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 0f30f5aabaa8..2b8abf88ec60 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -2573,6 +2573,33 @@ int snd_soc_register_component(struct device *dev, EXPORT_SYMBOL_GPL(snd_soc_register_component); /** + * snd_soc_unregister_component_by_driver - Unregister component using a given driver + * from the ASoC core + * + * @dev: The device to unregister + * @component_driver: The component driver to unregister + */ +void snd_soc_unregister_component_by_driver(struct device *dev, + const struct snd_soc_component_driver *component_driver) +{ + struct snd_soc_component *component; + + if (!component_driver) + return; + + mutex_lock(&client_mutex); + component = snd_soc_lookup_component_nolocked(dev, component_driver->name); + if (!component) + goto out; + + snd_soc_del_component_unlocked(component); + +out: + mutex_unlock(&client_mutex); +} +EXPORT_SYMBOL_GPL(snd_soc_unregister_component_by_driver); + +/** * snd_soc_unregister_component - Unregister all related component * from the ASoC core * diff --git a/sound/soc/soc-dai.c b/sound/soc/soc-dai.c index b05e18b63a1c..457159975b01 100644 --- a/sound/soc/soc-dai.c +++ b/sound/soc/soc-dai.c @@ -391,6 +391,44 @@ bool snd_soc_dai_stream_valid(struct snd_soc_dai *dai, int dir) return stream->channels_min; } +/* + * snd_soc_dai_link_set_capabilities() - set dai_link properties based on its DAIs + */ +void snd_soc_dai_link_set_capabilities(struct snd_soc_dai_link *dai_link) +{ + struct snd_soc_dai_link_component *cpu; + struct snd_soc_dai_link_component *codec; + struct snd_soc_dai *dai; + bool supported[SNDRV_PCM_STREAM_LAST + 1]; + int direction; + int i; + + for_each_pcm_streams(direction) { + supported[direction] = true; + + for_each_link_cpus(dai_link, i, cpu) { + dai = snd_soc_find_dai(cpu); + if (!dai || !snd_soc_dai_stream_valid(dai, direction)) { + supported[direction] = false; + break; + } + } + if (!supported[direction]) + continue; + for_each_link_codecs(dai_link, i, codec) { + dai = snd_soc_find_dai(codec); + if (!dai || !snd_soc_dai_stream_valid(dai, direction)) { + supported[direction] = false; + break; + } + } + } + + dai_link->dpcm_playback = supported[SNDRV_PCM_STREAM_PLAYBACK]; + dai_link->dpcm_capture = supported[SNDRV_PCM_STREAM_CAPTURE]; +} +EXPORT_SYMBOL_GPL(snd_soc_dai_link_set_capabilities); + void snd_soc_dai_action(struct snd_soc_dai *dai, int stream, int action) { diff --git a/sound/soc/soc-devres.c b/sound/soc/soc-devres.c index 11e5d7962370..4534a1c03e8e 100644 --- a/sound/soc/soc-devres.c +++ b/sound/soc/soc-devres.c @@ -48,7 +48,9 @@ EXPORT_SYMBOL_GPL(devm_snd_soc_register_dai); static void devm_component_release(struct device *dev, void *res) { - snd_soc_unregister_component(*(struct device **)res); + const struct snd_soc_component_driver **cmpnt_drv = res; + + snd_soc_unregister_component_by_driver(dev, *cmpnt_drv); } /** @@ -65,7 +67,7 @@ int devm_snd_soc_register_component(struct device *dev, const struct snd_soc_component_driver *cmpnt_drv, struct snd_soc_dai_driver *dai_drv, int num_dai) { - struct device **ptr; + const struct snd_soc_component_driver **ptr; int ret; ptr = devres_alloc(devm_component_release, sizeof(*ptr), GFP_KERNEL); @@ -74,7 +76,7 @@ int devm_snd_soc_register_component(struct device *dev, ret = snd_soc_register_component(dev, cmpnt_drv, dai_drv, num_dai); if (ret == 0) { - *ptr = dev; + *ptr = cmpnt_drv; devres_add(dev, ptr); } else { devres_free(ptr); diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c index 80a4e71f2d95..61844403f181 100644 --- a/sound/soc/soc-generic-dmaengine-pcm.c +++ b/sound/soc/soc-generic-dmaengine-pcm.c @@ -478,7 +478,7 @@ void snd_dmaengine_pcm_unregister(struct device *dev) pcm = soc_component_to_pcm(component); - snd_soc_unregister_component(dev); + snd_soc_unregister_component_by_driver(dev, component->driver); dmaengine_pcm_release_chan(pcm); kfree(pcm); } diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 43e5745b06aa..6eaa00c21011 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1261,17 +1261,29 @@ static int soc_tplg_dapm_graph_elems_load(struct soc_tplg *tplg, list_add(&routes[i]->dobj.list, &tplg->comp->dobj_list); ret = soc_tplg_add_route(tplg, routes[i]); - if (ret < 0) + if (ret < 0) { + /* + * this route was added to the list, it will + * be freed in remove_route() so increment the + * counter to skip it in the error handling + * below. + */ + i++; break; + } /* add route, but keep going if some fail */ snd_soc_dapm_add_routes(dapm, routes[i], 1); } - /* free memory allocated for all dapm routes in case of error */ - if (ret < 0) - for (i = 0; i < count ; i++) - kfree(routes[i]); + /* + * free memory allocated for all dapm routes not added to the + * list in case of error + */ + if (ret < 0) { + while (i < count) + kfree(routes[i++]); + } /* * free pointer to array of dapm routes as this is no longer needed. @@ -1359,7 +1371,6 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_dmixer_create( if (err < 0) { dev_err(tplg->dev, "ASoC: failed to init %s\n", mc->hdr.name); - soc_tplg_free_tlv(tplg, &kc[i]); goto err_sm; } } @@ -1367,6 +1378,7 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_dmixer_create( err_sm: for (; i >= 0; i--) { + soc_tplg_free_tlv(tplg, &kc[i]); sm = (struct soc_mixer_control *)kc[i].private_value; kfree(sm); kfree(kc[i].name); diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c index 339c4930b0c0..adc7c37145d6 100644 --- a/sound/soc/sof/core.c +++ b/sound/soc/sof/core.c @@ -345,15 +345,15 @@ int snd_sof_device_remove(struct device *dev) struct snd_sof_pdata *pdata = sdev->pdata; int ret; - ret = snd_sof_dsp_power_down_notify(sdev); - if (ret < 0) - dev_warn(dev, "error: %d failed to prepare DSP for device removal", - ret); - if (IS_ENABLED(CONFIG_SND_SOC_SOF_PROBE_WORK_QUEUE)) cancel_work_sync(&sdev->probe_work); if (sdev->fw_state > SOF_FW_BOOT_NOT_STARTED) { + ret = snd_sof_dsp_power_down_notify(sdev); + if (ret < 0) + dev_warn(dev, "error: %d failed to prepare DSP for device removal", + ret); + snd_sof_fw_unload(sdev); snd_sof_ipc_free(sdev); snd_sof_free_debug(sdev); diff --git a/sound/soc/sof/imx/imx8.c b/sound/soc/sof/imx/imx8.c index 63f9c20a1bac..a4fa8451d8cb 100644 --- a/sound/soc/sof/imx/imx8.c +++ b/sound/soc/sof/imx/imx8.c @@ -375,6 +375,14 @@ static int imx8_ipc_pcm_params(struct snd_sof_dev *sdev, static struct snd_soc_dai_driver imx8_dai[] = { { .name = "esai-port", + .playback = { + .channels_min = 1, + .channels_max = 8, + }, + .capture = { + .channels_min = 1, + .channels_max = 8, + }, }, }; diff --git a/sound/soc/sof/imx/imx8m.c b/sound/soc/sof/imx/imx8m.c index fa86a9e2990f..287114a37688 100644 --- a/sound/soc/sof/imx/imx8m.c +++ b/sound/soc/sof/imx/imx8m.c @@ -240,6 +240,14 @@ static int imx8m_ipc_pcm_params(struct snd_sof_dev *sdev, static struct snd_soc_dai_driver imx8m_dai[] = { { .name = "sai-port", + .playback = { + .channels_min = 1, + .channels_max = 32, + }, + .capture = { + .channels_min = 1, + .channels_max = 32, + }, }, }; diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 40b7cd13fed9..a69d9e75f66f 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -367,6 +367,7 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, ifnum = 0; goto add_sync_ep_from_ifnum; case USB_ID(0x07fd, 0x0008): /* MOTU M Series */ + case USB_ID(0x31e9, 0x0001): /* Solid State Logic SSL2 */ case USB_ID(0x31e9, 0x0002): /* Solid State Logic SSL2+ */ case USB_ID(0x0d9a, 0x00df): /* RTX6001 */ ep = 0x81; diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 5b36c589a029..ba4f33804af1 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -2861,6 +2861,7 @@ process_dynamic_array_len(struct tep_event *event, struct tep_print_arg *arg, if (read_expected(TEP_EVENT_DELIM, ")") < 0) goto out_err; + free_token(token); type = read_token(&token); *tok = token; diff --git a/tools/lib/traceevent/plugins/Makefile b/tools/lib/traceevent/plugins/Makefile index 349bb81482ab..680d883efe05 100644 --- a/tools/lib/traceevent/plugins/Makefile +++ b/tools/lib/traceevent/plugins/Makefile @@ -197,7 +197,7 @@ define do_generate_dynamic_list_file xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\ if [ "$$symbol_type" = "U W" ];then \ (echo '{'; \ - $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\ + $(NM) -u -D $1 | awk 'NF>1 {sub("@.*", "", $$2); print "\t"$$2";"}' | sort -u;\ echo '};'; \ ) > $2; \ else \ diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 0a6e75b8777a..28a5d0c18b1d 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -56,7 +56,7 @@ struct auxtrace_record struct perf_pmu *cs_etm_pmu; struct evsel *evsel; bool found_etm = false; - bool found_spe = false; + struct perf_pmu *found_spe = NULL; static struct perf_pmu **arm_spe_pmus = NULL; static int nr_spes = 0; int i = 0; @@ -74,12 +74,12 @@ struct auxtrace_record evsel->core.attr.type == cs_etm_pmu->type) found_etm = true; - if (!nr_spes) + if (!nr_spes || found_spe) continue; for (i = 0; i < nr_spes; i++) { if (evsel->core.attr.type == arm_spe_pmus[i]->type) { - found_spe = true; + found_spe = arm_spe_pmus[i]; break; } } @@ -96,7 +96,7 @@ struct auxtrace_record #if defined(__aarch64__) if (found_spe) - return arm_spe_recording_init(err, arm_spe_pmus[i]); + return arm_spe_recording_init(err, found_spe); #endif /* diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json index 2df2e231e9ee..24c4ba2a9ae5 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json @@ -380,7 +380,7 @@ { "Unit": "CPU-M-CF", "EventCode": "265", - "EventName": "DFLT_CCERROR", + "EventName": "DFLT_CCFINISH", "BriefDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed that ended in Condition Codes 0, 1 or 2", "PublicDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed that ended in Condition Codes 0, 1 or 2" }, diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh index 63a91ec473bb..045723b3d992 100755 --- a/tools/perf/tests/shell/record+zstd_comp_decomp.sh +++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh @@ -12,7 +12,8 @@ skip_if_no_z_record() { collect_z_record() { echo "Collecting compressed record file:" - $perf_tool record -o $trace_file -g -z -F 5000 -- \ + [[ "$(uname -m)" != s390x ]] && gflag='-g' + $perf_tool record -o $trace_file $gflag -z -F 5000 -- \ dd count=500 if=/dev/urandom of=/dev/null } diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c index f7ee8fa377ad..6ccecbd39476 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c @@ -5,10 +5,60 @@ #include "test_btf_map_in_map.skel.h" +static int duration; + +static __u32 bpf_map_id(struct bpf_map *map) +{ + struct bpf_map_info info; + __u32 info_len = sizeof(info); + int err; + + memset(&info, 0, info_len); + err = bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, &info_len); + if (err) + return 0; + return info.id; +} + +/* + * Trigger synchronize_rcu() in kernel. + * + * ARRAY_OF_MAPS/HASH_OF_MAPS lookup/update operations trigger synchronize_rcu() + * if looking up an existing non-NULL element or updating the map with a valid + * inner map FD. Use this fact to trigger synchronize_rcu(): create map-in-map, + * create a trivial ARRAY map, update map-in-map with ARRAY inner map. Then + * cleanup. At the end, at least one synchronize_rcu() would be called. + */ +static int kern_sync_rcu(void) +{ + int inner_map_fd, outer_map_fd, err, zero = 0; + + inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0); + if (CHECK(inner_map_fd < 0, "inner_map_create", "failed %d\n", -errno)) + return -1; + + outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL, + sizeof(int), inner_map_fd, 1, 0); + if (CHECK(outer_map_fd < 0, "outer_map_create", "failed %d\n", -errno)) { + close(inner_map_fd); + return -1; + } + + err = bpf_map_update_elem(outer_map_fd, &zero, &inner_map_fd, 0); + if (err) + err = -errno; + CHECK(err, "outer_map_update", "failed %d\n", err); + close(inner_map_fd); + close(outer_map_fd); + return err; +} + void test_btf_map_in_map(void) { - int duration = 0, err, key = 0, val; - struct test_btf_map_in_map* skel; + int err, key = 0, val, i; + struct test_btf_map_in_map *skel; + int outer_arr_fd, outer_hash_fd; + int fd, map1_fd, map2_fd, map1_id, map2_id; skel = test_btf_map_in_map__open_and_load(); if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n")) @@ -18,32 +68,78 @@ void test_btf_map_in_map(void) if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) goto cleanup; + map1_fd = bpf_map__fd(skel->maps.inner_map1); + map2_fd = bpf_map__fd(skel->maps.inner_map2); + outer_arr_fd = bpf_map__fd(skel->maps.outer_arr); + outer_hash_fd = bpf_map__fd(skel->maps.outer_hash); + /* inner1 = input, inner2 = input + 1 */ - val = bpf_map__fd(skel->maps.inner_map1); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); - val = bpf_map__fd(skel->maps.inner_map2); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + map1_fd = bpf_map__fd(skel->maps.inner_map1); + bpf_map_update_elem(outer_arr_fd, &key, &map1_fd, 0); + map2_fd = bpf_map__fd(skel->maps.inner_map2); + bpf_map_update_elem(outer_hash_fd, &key, &map2_fd, 0); skel->bss->input = 1; usleep(1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + bpf_map_lookup_elem(map1_fd, &key, &val); CHECK(val != 1, "inner1", "got %d != exp %d\n", val, 1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + bpf_map_lookup_elem(map2_fd, &key, &val); CHECK(val != 2, "inner2", "got %d != exp %d\n", val, 2); /* inner1 = input + 1, inner2 = input */ - val = bpf_map__fd(skel->maps.inner_map2); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); - val = bpf_map__fd(skel->maps.inner_map1); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + bpf_map_update_elem(outer_arr_fd, &key, &map2_fd, 0); + bpf_map_update_elem(outer_hash_fd, &key, &map1_fd, 0); skel->bss->input = 3; usleep(1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + bpf_map_lookup_elem(map1_fd, &key, &val); CHECK(val != 4, "inner1", "got %d != exp %d\n", val, 4); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + bpf_map_lookup_elem(map2_fd, &key, &val); CHECK(val != 3, "inner2", "got %d != exp %d\n", val, 3); + for (i = 0; i < 5; i++) { + val = i % 2 ? map1_fd : map2_fd; + err = bpf_map_update_elem(outer_hash_fd, &key, &val, 0); + if (CHECK_FAIL(err)) { + printf("failed to update hash_of_maps on iter #%d\n", i); + goto cleanup; + } + err = bpf_map_update_elem(outer_arr_fd, &key, &val, 0); + if (CHECK_FAIL(err)) { + printf("failed to update hash_of_maps on iter #%d\n", i); + goto cleanup; + } + } + + map1_id = bpf_map_id(skel->maps.inner_map1); + map2_id = bpf_map_id(skel->maps.inner_map2); + CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n"); + CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n"); + + test_btf_map_in_map__destroy(skel); + skel = NULL; + + /* we need to either wait for or force synchronize_rcu(), before + * checking for "still exists" condition, otherwise map could still be + * resolvable by ID, causing false positives. + * + * Older kernels (5.8 and earlier) freed map only after two + * synchronize_rcu()s, so trigger two, to be entirely sure. + */ + CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); + CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); + + fd = bpf_map_get_fd_by_id(map1_id); + if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) { + close(fd); + goto cleanup; + } + fd = bpf_map_get_fd_by_id(map2_id); + if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) { + close(fd); + goto cleanup; + } + cleanup: test_btf_map_in_map__destroy(skel); } diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 8294ae3ffb3c..43c9cda199b8 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -318,6 +318,9 @@ class DebugfsDir: continue if os.path.isfile(p): + # We need to init trap_flow_action_cookie before read it + if f == "trap_flow_action_cookie": + cmd('echo deadbeef > %s/%s' % (path, f)) _, out = cmd('cat %s/%s' % (path, f)) dfs[f] = out.strip() elif os.path.isdir(p): diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c index 99f8f582c02b..c5e805980409 100644 --- a/tools/testing/selftests/bpf/verifier/event_output.c +++ b/tools/testing/selftests/bpf/verifier/event_output.c @@ -112,6 +112,7 @@ "perfevent for cgroup sockopt", .insns = { __PERF_EVENT_INSNS__ }, .prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .fixup_map_event_output = { 4 }, .result = ACCEPT, .retval = 1, diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c index 54cdefdfb49d..d59f3eb67c8f 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c @@ -76,10 +76,8 @@ void set_default_state(struct kvm_nested_state *state) void set_default_vmx_state(struct kvm_nested_state *state, int size) { memset(state, 0, size); - state->flags = KVM_STATE_NESTED_GUEST_MODE | - KVM_STATE_NESTED_RUN_PENDING; if (have_evmcs) - state->flags |= KVM_STATE_NESTED_EVMCS; + state->flags = KVM_STATE_NESTED_EVMCS; state->format = 0; state->size = size; state->hdr.vmx.vmxon_pa = 0x1000; @@ -148,6 +146,11 @@ void test_vmx_nested_state(struct kvm_vm *vm) state->hdr.vmx.smm.flags = 1; test_nested_state_expect_einval(vm, state); + /* Invalid flags are rejected. */ + set_default_vmx_state(state, state_sz); + state->hdr.vmx.flags = ~0; + test_nested_state_expect_einval(vm, state); + /* It is invalid to have vmxon_pa == -1ull and vmcs_pa != -1ull. */ set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = -1ull; @@ -185,20 +188,41 @@ void test_vmx_nested_state(struct kvm_vm *vm) state->hdr.vmx.smm.flags = KVM_STATE_NESTED_SMM_GUEST_MODE; test_nested_state_expect_einval(vm, state); - /* Size must be large enough to fit kvm_nested_state and vmcs12. */ + /* + * Size must be large enough to fit kvm_nested_state and vmcs12 + * if VMCS12 physical address is set + */ set_default_vmx_state(state, state_sz); state->size = sizeof(*state); + state->flags = 0; + test_nested_state_expect_einval(vm, state); + + set_default_vmx_state(state, state_sz); + state->size = sizeof(*state); + state->flags = 0; + state->hdr.vmx.vmcs12_pa = -1; test_nested_state(vm, state); - /* vmxon_pa cannot be the same address as vmcs_pa. */ + /* + * KVM_SET_NESTED_STATE succeeds with invalid VMCS + * contents but L2 not running. + */ set_default_vmx_state(state, state_sz); - state->hdr.vmx.vmxon_pa = 0; - state->hdr.vmx.vmcs12_pa = 0; + state->flags = 0; + test_nested_state(vm, state); + + /* Invalid flags are rejected, even if no VMCS loaded. */ + set_default_vmx_state(state, state_sz); + state->size = sizeof(*state); + state->flags = 0; + state->hdr.vmx.vmcs12_pa = -1; + state->hdr.vmx.flags = ~0; test_nested_state_expect_einval(vm, state); - /* The revision id for vmcs12 must be VMCS12_REVISION. */ + /* vmxon_pa cannot be the same address as vmcs_pa. */ set_default_vmx_state(state, state_sz); - set_revision_id_for_vmcs12(state, 0); + state->hdr.vmx.vmxon_pa = 0; + state->hdr.vmx.vmcs12_pa = 0; test_nested_state_expect_einval(vm, state); /* diff --git a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh index 9dc35a16e415..51df5e305855 100755 --- a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh +++ b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh @@ -144,7 +144,7 @@ setup() cleanup() { - for n in h1 r1 h2 h3 h4 + for n in h0 r1 h1 h2 h3 do ip netns del ${n} 2>/dev/null done diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh index eb8e2a23bbb4..43a948feed26 100755 --- a/tools/testing/selftests/net/forwarding/ethtool.sh +++ b/tools/testing/selftests/net/forwarding/ethtool.sh @@ -252,8 +252,6 @@ check_highest_speed_is_chosen() fi local -a speeds_arr=($(common_speeds_get $h1 $h2 0 1)) - # Remove the first speed, h1 does not advertise this speed. - unset speeds_arr[0] max_speed=${speeds_arr[0]} for current in ${speeds_arr[@]}; do diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh index 15d3489ecd9c..ceb7ad4dbd94 100755 --- a/tools/testing/selftests/net/ip_defrag.sh +++ b/tools/testing/selftests/net/ip_defrag.sh @@ -6,6 +6,8 @@ set +x set -e +modprobe -q nf_defrag_ipv6 + readonly NETNS="ns-$(mktemp -u XXXXXX)" setup() { diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 8c8c7d79c38d..2c522f7a0aec 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -350,7 +350,8 @@ static int test_datapath(uint16_t typeflags, int port_off, int fds[2], fds_udp[2][2], ret; fprintf(stderr, "\ntest: datapath 0x%hx ports %hu,%hu\n", - typeflags, PORT_BASE, PORT_BASE + port_off); + typeflags, (uint16_t)PORT_BASE, + (uint16_t)(PORT_BASE + port_off)); fds[0] = sock_fanout_open(typeflags, 0); fds[1] = sock_fanout_open(typeflags, 0); diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c index 422e7761254d..bcb79ba1f214 100644 --- a/tools/testing/selftests/net/rxtimestamp.c +++ b/tools/testing/selftests/net/rxtimestamp.c @@ -329,8 +329,7 @@ int main(int argc, char **argv) bool all_tests = true; int arg_index = 0; int failures = 0; - int s, t; - char opt; + int s, t, opt; while ((opt = getopt_long(argc, argv, "", long_options, &arg_index)) != -1) { diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index ceaad78e9667..3155fbbf644b 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -121,7 +121,7 @@ static bool do_recv_one(int fdr, struct timed_send *ts) if (rbuf[0] != ts->data) error(1, 0, "payload mismatch. expected %c", ts->data); - if (labs(tstop - texpect) > cfg_variance_us) + if (llabs(tstop - texpect) > cfg_variance_us) error(1, 0, "exceeds variance (%d us)", cfg_variance_us); return false; diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 4555f88252ba..a61b7b3da549 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -344,7 +344,7 @@ int main(int argc, char *argv[]) { struct sockaddr_storage listenaddr, addr; unsigned int max_pacing_rate = 0; - size_t total = 0; + uint64_t total = 0; char *host = NULL; int fd, c, on = 1; char *buffer; @@ -473,12 +473,12 @@ int main(int argc, char *argv[]) zflg = 0; } while (total < FILE_SZ) { - ssize_t wr = FILE_SZ - total; + int64_t wr = FILE_SZ - total; if (wr > chunk_size) wr = chunk_size; /* Note : we just want to fill the pipe with 0 bytes */ - wr = send(fd, buffer, wr, zflg ? MSG_ZEROCOPY : 0); + wr = send(fd, buffer, (size_t)wr, zflg ? MSG_ZEROCOPY : 0); if (wr <= 0) break; total += wr; diff --git a/tools/testing/selftests/net/txtimestamp.sh b/tools/testing/selftests/net/txtimestamp.sh index eea6f5193693..31637769f59f 100755 --- a/tools/testing/selftests/net/txtimestamp.sh +++ b/tools/testing/selftests/net/txtimestamp.sh @@ -75,7 +75,7 @@ main() { fi } -if [[ "$(ip netns identify)" == "root" ]]; then +if [[ -z "$(ip netns identify)" ]]; then ./in_netns.sh $0 $@ else main $@ |