diff options
321 files changed, 5806 insertions, 1778 deletions
@@ -9,7 +9,7 @@ Linus ---------- -M: Matt Mackal +N: Matt Mackal D: SLOB slab allocator @@ -1910,7 +1910,7 @@ S: Ra'annana, Israel N: Andi Kleen -U: http://www.halobates.de +W: http://www.halobates.de D: network, x86, NUMA, various hacks S: Schwalbenstr. 96 S: 85551 Ottobrunn @@ -2089,8 +2089,8 @@ D: ST Microelectronics SPEAr13xx PCI host bridge driver D: Synopsys Designware PCI host bridge driver N: Gabor Kuti D: Original author of software suspend N: Jaroslav Kysela diff --git a/Documentation/cpu-freq/cpufreq-stats.txt b/Documentation/cpu-freq/cpufreq-stats.txt index 8d9773f23550..3c355f6ad834 100644 --- a/Documentation/cpu-freq/cpufreq-stats.txt +++ b/Documentation/cpu-freq/cpufreq-stats.txt @@ -44,11 +44,17 @@ the stats driver insertion. total 0 drwxr-xr-x 2 root root 0 May 14 16:06 . drwxr-xr-x 3 root root 0 May 14 15:58 .. +--w------- 1 root root 4096 May 14 16:06 reset -r--r--r-- 1 root root 4096 May 14 16:06 time_in_state -r--r--r-- 1 root root 4096 May 14 16:06 total_trans -r--r--r-- 1 root root 4096 May 14 16:06 trans_table -------------------------------------------------------------------------------- +- reset +Write-only attribute that can be used to reset the stat counters. This can be +useful for evaluating system behaviour under different governors without the +need for a reboot. + - time_in_state This gives the amount of time spent in each of the frequencies supported by this CPU. The cat output will have "<frequency> <time>" pair in each line, which diff --git a/Documentation/cpu-freq/intel-pstate.txt b/Documentation/cpu-freq/intel-pstate.txt index e6bd1e6512a5..1953994ef5e6 100644 --- a/Documentation/cpu-freq/intel-pstate.txt +++ b/Documentation/cpu-freq/intel-pstate.txt @@ -48,7 +48,7 @@ In addition to the frequency-controlling interfaces provided by the cpufreq core, the driver provides its own sysfs files to control the P-State selection. These files have been added to /sys/devices/system/cpu/intel_pstate/. Any changes made to these files are applicable to all CPUs (even in a -multi-package system). +multi-package system, Refer to later section on placing "Per-CPU limits"). max_perf_pct: Limits the maximum P-State that will be requested by the driver. It states it as a percentage of the available performance. The @@ -120,13 +120,57 @@ frequency is fictional for Intel Core processors. Even if the scaling driver selects a single P-State, the actual frequency the processor will run at is selected by the processor itself. +Per-CPU limits + +The kernel command line option "intel_pstate=per_cpu_perf_limits" forces +the intel_pstate driver to use per-CPU performance limits. When it is set, +the sysfs control interface described above is subject to limitations. +- The following controls are not available for both read and write + /sys/devices/system/cpu/intel_pstate/max_perf_pct + /sys/devices/system/cpu/intel_pstate/min_perf_pct +- The following controls can be used to set performance limits, as far as the +architecture of the processor permits: + /sys/devices/system/cpu/cpu*/cpufreq/scaling_max_freq + /sys/devices/system/cpu/cpu*/cpufreq/scaling_min_freq + /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor +- User can still observe turbo percent and number of P-States from + /sys/devices/system/cpu/intel_pstate/turbo_pct + /sys/devices/system/cpu/intel_pstate/num_pstates +- User can read write system wide turbo status + /sys/devices/system/cpu/no_turbo + +Support of energy performance hints +It is possible to provide hints to the HWP algorithms in the processor +to be more performance centric to more energy centric. When the driver +is using HWP, two additional cpufreq sysfs attributes are presented for +each logical CPU. +These attributes are: + - energy_performance_available_preferences + - energy_performance_preference + +To get list of supported hints: +$ cat energy_performance_available_preferences + default performance balance_performance balance_power power + +The current preference can be read or changed via cpufreq sysfs +attribute "energy_performance_preference". Reading from this attribute +will display current effective setting. User can write any of the valid +preference string to this attribute. User can always restore to power-on +default by writing "default". + +Since threads can migrate to different CPUs, this is possible that the +new CPU may have different energy performance preference than the previous +one. To avoid such issues, either threads can be pinned to specific CPUs +or set the same energy performance preference value to all CPUs. + Tuning Intel P-State driver -When HWP mode is not used, debugfs files have also been added to allow the -tuning of the internal governor algorithm. These files are located at -/sys/kernel/debug/pstate_snb/. The algorithm uses a PID (Proportional -Integral Derivative) controller. The PID tunable parameters are: +When the performance can be tuned using PID (Proportional Integral +Derivative) controller, debugfs files are provided for adjusting performance. +They are presented under: +/sys/kernel/debug/pstate_snb/ +The PID tunable parameters are: deadband d_gain_pct i_gain_pct diff --git a/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt b/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt new file mode 100644 index 000000000000..af2385795d78 --- /dev/null +++ b/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt @@ -0,0 +1,78 @@ +Broadcom AVS mail box and interrupt register bindings +===================================================== + +A total of three DT nodes are required. One node (brcm,avs-cpu-data-mem) +references the mailbox register used to communicate with the AVS CPU[1]. The +second node (brcm,avs-cpu-l2-intr) is required to trigger an interrupt on +the AVS CPU. The interrupt tells the AVS CPU that it needs to process a +command sent to it by a driver. Interrupting the AVS CPU is mandatory for +commands to be processed. + +The interface also requires a reference to the AVS host interrupt controller, +so a driver can react to interrupts generated by the AVS CPU whenever a command +has been processed. See [2] for more information on the brcm,l2-intc node. + +[1] The AVS CPU is an independent co-processor that runs proprietary +firmware. On some SoCs, this firmware supports DFS and DVFS in addition to +Adaptive Voltage Scaling. + +[2] Documentation/devicetree/bindings/interrupt-controller/brcm,l2-intc.txt + + +Node brcm,avs-cpu-data-mem +-------------------------- + +Required properties: +- compatible: must include: brcm,avs-cpu-data-mem and + should include: one of brcm,bcm7271-avs-cpu-data-mem or + brcm,bcm7268-avs-cpu-data-mem +- reg: Specifies base physical address and size of the registers. +- interrupts: The interrupt that the AVS CPU will use to interrupt the host + when a command completed. +- interrupt-parent: The interrupt controller the above interrupt is routed + through. +- interrupt-names: The name of the interrupt used to interrupt the host. + +Optional properties: +- None + +Node brcm,avs-cpu-l2-intr +------------------------- + +Required properties: +- compatible: must include: brcm,avs-cpu-l2-intr and + should include: one of brcm,bcm7271-avs-cpu-l2-intr or + brcm,bcm7268-avs-cpu-l2-intr +- reg: Specifies base physical address and size of the registers. + +Optional properties: +- None + + +Example +======= + + avs_host_l2_intc: interrupt-controller@f04d1200 { + #interrupt-cells = <1>; + compatible = "brcm,l2-intc"; + interrupt-parent = <&intc>; + reg = <0xf04d1200 0x48>; + interrupt-controller; + interrupts = <0x0 0x19 0x0>; + interrupt-names = "avs"; + }; + + avs-cpu-data-mem@f04c4000 { + compatible = "brcm,bcm7271-avs-cpu-data-mem", + "brcm,avs-cpu-data-mem"; + reg = <0xf04c4000 0x60>; + interrupts = <0x1a>; + interrupt-parent = <&avs_host_l2_intc>; + interrupt-names = "sw_intr"; + }; + + avs-cpu-l2-intr@f04d1100 { + compatible = "brcm,bcm7271-avs-cpu-l2-intr", + "brcm,avs-cpu-l2-intr"; + reg = <0xf04d1100 0x10>; + }; diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt index e1d76812419c..05150957ecfd 100644 --- a/Documentation/devicetree/bindings/net/ethernet.txt +++ b/Documentation/devicetree/bindings/net/ethernet.txt @@ -9,10 +9,26 @@ The following properties are common to the Ethernet controllers: - max-speed: number, specifies maximum speed in Mbit/s supported by the device; - max-frame-size: number, maximum transfer unit (IEEE defined MTU), rather than the maximum frame size (there's contradiction in ePAPR). -- phy-mode: string, operation mode of the PHY interface; supported values are - "mii", "gmii", "sgmii", "qsgmii", "tbi", "rev-mii", "rmii", "rgmii", "rgmii-id", - "rgmii-rxid", "rgmii-txid", "rtbi", "smii", "xgmii", "trgmii"; this is now a - de-facto standard property; +- phy-mode: string, operation mode of the PHY interface. This is now a de-facto + standard property; supported values are: + * "mii" + * "gmii" + * "sgmii" + * "qsgmii" + * "tbi" + * "rev-mii" + * "rmii" + * "rgmii" (RX and TX delays are added by the MAC when required) + * "rgmii-id" (RGMII with internal RX and TX delays provided by the PHY, the + MAC should not add the RX or TX delays in this case) + * "rgmii-rxid" (RGMII with internal RX delay provided by the PHY, the MAC + should not add an RX delay in this case) + * "rgmii-txid" (RGMII with internal TX delay provided by the PHY, the MAC + should not add an TX delay in this case) + * "rtbi" + * "smii" + * "xgmii" + * "trgmii" - phy-connection-type: the same as "phy-mode" property but described in ePAPR; - phy-handle: phandle, specifies a reference to a node representing a PHY device; this property is described in ePAPR and so preferred; diff --git a/Documentation/devicetree/bindings/opp/opp.txt b/Documentation/devicetree/bindings/opp/opp.txt index ee91cbdd95ee..9f5ca4457b5f 100644 --- a/Documentation/devicetree/bindings/opp/opp.txt +++ b/Documentation/devicetree/bindings/opp/opp.txt @@ -86,8 +86,14 @@ Optional properties: Single entry is for target voltage and three entries are for <target min max> voltages. - Entries for multiple regulators must be present in the same order as - regulators are specified in device's DT node. + Entries for multiple regulators shall be provided in the same field separated + by angular brackets <>. The OPP binding doesn't provide any provisions to + relate the values to their power supplies or the order in which the supplies + need to be configured and that is left for the implementation specific + binding. + + Entries for all regulators shall be of the same size, i.e. either all use a + single value or triplets. - opp-microvolt-<name>: Named opp-microvolt property. This is exactly similar to the above opp-microvolt property, but allows multiple voltage ranges to be @@ -104,10 +110,13 @@ Optional properties: Should only be set if opp-microvolt is set for the OPP. - Entries for multiple regulators must be present in the same order as - regulators are specified in device's DT node. If this property isn't required - for few regulators, then this should be marked as zero for them. If it isn't - required for any regulator, then this property need not be present. + Entries for multiple regulators shall be provided in the same field separated + by angular brackets <>. If current values aren't required for a regulator, + then it shall be filled with 0. If current values aren't required for any of + the regulators, then this field is not required. The OPP binding doesn't + provide any provisions to relate the values to their power supplies or the + order in which the supplies need to be configured and that is left for the + implementation specific binding. - opp-microamp-<name>: Named opp-microamp property. Similar to opp-microvolt-<name> property, but for microamp instead. @@ -386,10 +395,12 @@ Example 4: Handling multiple regulators / { cpus { cpu@0 { - compatible = "arm,cortex-a7"; + compatible = "vendor,cpu-type"; ... - cpu-supply = <&cpu_supply0>, <&cpu_supply1>, <&cpu_supply2>; + vcc0-supply = <&cpu_supply0>; + vcc1-supply = <&cpu_supply1>; + vcc2-supply = <&cpu_supply2>; operating-points-v2 = <&cpu0_opp_table>; }; }; diff --git a/Documentation/devicetree/bindings/power/domain-idle-state.txt b/Documentation/devicetree/bindings/power/domain-idle-state.txt new file mode 100644 index 000000000000..eefc7ed22ca2 --- /dev/null +++ b/Documentation/devicetree/bindings/power/domain-idle-state.txt @@ -0,0 +1,33 @@ +PM Domain Idle State Node: + +A domain idle state node represents the state parameters that will be used to +select the state when there are no active components in the domain. + +The state node has the following parameters - + +- compatible: + Usage: Required + Value type: <string> + Definition: Must be "domain-idle-state". + +- entry-latency-us + Usage: Required + Value type: <prop-encoded-array> + Definition: u32 value representing worst case latency in + microseconds required to enter the idle state. + The exit-latency-us duration may be guaranteed + only after entry-latency-us has passed. + +- exit-latency-us + Usage: Required + Value type: <prop-encoded-array> + Definition: u32 value representing worst case latency + in microseconds required to exit the idle state. + +- min-residency-us + Usage: Required + Value type: <prop-encoded-array> + Definition: u32 value representing minimum residency duration + in microseconds after which the idle state will yield + power benefits after overcoming the overhead in entering +i the idle state. diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt index 025b5e7df61c..723e1ad937da 100644 --- a/Documentation/devicetree/bindings/power/power_domain.txt +++ b/Documentation/devicetree/bindings/power/power_domain.txt @@ -29,6 +29,15 @@ Optional properties: specified by this binding. More details about power domain specifier are available in the next section. +- domain-idle-states : A phandle of an idle-state that shall be soaked into a + generic domain power state. The idle state definitions are + compatible with domain-idle-state specified in [1]. + The domain-idle-state property reflects the idle state of this PM domain and + not the idle states of the devices or sub-domains in the PM domain. Devices + and sub-domains have their own idle-states independent of the parent + domain's idle states. In the absence of this property, the domain would be + considered as capable of being powered-on or powered-off. + Example: power: power-controller@12340000 { @@ -59,6 +68,38 @@ The nodes above define two power controllers: 'parent' and 'child'. Domains created by the 'child' power controller are subdomains of '0' power domain provided by the 'parent' power controller. +Example 3: + parent: power-controller@12340000 { + compatible = "foo,power-controller"; + reg = <0x12340000 0x1000>; + #power-domain-cells = <0>; + domain-idle-states = <&DOMAIN_RET>, <&DOMAIN_PWR_DN>; + }; + + child: power-controller@12341000 { + compatible = "foo,power-controller"; + reg = <0x12341000 0x1000>; + power-domains = <&parent 0>; + #power-domain-cells = <0>; + domain-idle-states = <&DOMAIN_PWR_DN>; + }; + + DOMAIN_RET: state@0 { + compatible = "domain-idle-state"; + reg = <0x0>; + entry-latency-us = <1000>; + exit-latency-us = <2000>; + min-residency-us = <10000>; + }; + + DOMAIN_PWR_DN: state@1 { + compatible = "domain-idle-state"; + reg = <0x1>; + entry-latency-us = <5000>; + exit-latency-us = <8000>; + min-residency-us = <7000>; + }; + ==PM domain consumers== Required properties: @@ -76,3 +117,5 @@ Example: The node above defines a typical PM domain consumer device, which is located inside a PM domain with index 0 of a power controller represented by a node with the label "power". + +[1]. Documentation/devicetree/bindings/power/domain-idle-state.txt diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 37babf91f2cb..dfdd38ec149b 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1760,6 +1760,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted. disable Do not enable intel_pstate as the default scaling driver for the supported processors + passive + Use intel_pstate as a scaling driver, but configure it + to work with generic cpufreq governors (instead of + enabling its internal governor). This mode cannot be + used along with the hardware-managed P-states (HWP) + feature. force Enable intel_pstate on systems that prohibit it by default in favor of acpi-cpufreq. Forcing the intel_pstate driver @@ -1780,6 +1786,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Description Table, specifies preferred power management profile as "Enterprise Server" or "Performance Server", then this feature is turned on by default. + per_cpu_perf_limits + Allow per-logical-CPU P-State performance control limits using + cpufreq sysfs interface intremap= [X86-64, Intel-IOMMU] on enable Interrupt Remapping (default) diff --git a/Documentation/networking/nf_conntrack-sysctl.txt b/Documentation/networking/nf_conntrack-sysctl.txt index 399e4e866a9c..433b6724797a 100644 --- a/Documentation/networking/nf_conntrack-sysctl.txt +++ b/Documentation/networking/nf_conntrack-sysctl.txt @@ -62,10 +62,13 @@ nf_conntrack_generic_timeout - INTEGER (seconds) protocols. nf_conntrack_helper - BOOLEAN - 0 - disabled - not 0 - enabled (default) + 0 - disabled (default) + not 0 - enabled Enable automatic conntrack helper assignment. + If disabled it is required to set up iptables rules to assign + helpers to connections. See the CT target description in the + iptables-extensions(8) man page for further information. nf_conntrack_icmp_timeout - INTEGER (seconds) default 30 diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt index 8ba6625fdd63..73ddea39a9ce 100644 --- a/Documentation/power/devices.txt +++ b/Documentation/power/devices.txt @@ -607,7 +607,9 @@ individually. Instead, a set of devices sharing a power resource can be put into a low-power state together at the same time by turning off the shared power resource. Of course, they also need to be put into the full-power state together, by turning the shared power resource on. A set of devices with this -property is often referred to as a power domain. +property is often referred to as a power domain. A power domain may also be +nested inside another power domain. The nested domain is referred to as the +sub-domain of the parent domain. Support for power domains is provided through the pm_domain field of struct device. This field is a pointer to an object of type struct dev_pm_domain, @@ -629,6 +631,16 @@ support for power domains into subsystem-level callbacks, for example by modifying the platform bus type. Other platforms need not implement it or take it into account in any way. +Devices may be defined as IRQ-safe which indicates to the PM core that their +runtime PM callbacks may be invoked with disabled interrupts (see +Documentation/power/runtime_pm.txt for more information). If an IRQ-safe +device belongs to a PM domain, the runtime PM of the domain will be +disallowed, unless the domain itself is defined as IRQ-safe. However, it +makes sense to define a PM domain as IRQ-safe only if all the devices in it +are IRQ-safe. Moreover, if an IRQ-safe domain has a parent domain, the runtime +PM of the parent is only allowed if the parent itself is IRQ-safe too with the +additional restriction that all child domains of an IRQ-safe parent must also +be IRQ-safe. Device Low Power (suspend) States --------------------------------- diff --git a/MAINTAINERS b/MAINTAINERS index 3c7348536c56..e89a18805bae 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2749,6 +2749,14 @@ L: [email protected] S: Maintained F: drivers/mtd/nand/brcmnand/ +BROADCOM STB AVS CPUFREQ DRIVER +M: Markus Mayer <[email protected]> +S: Maintained +F: Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt +F: drivers/cpufreq/brcmstb* + BROADCOM SPECIFIC AMBA DRIVER (BCMA) M: Rafał Miłecki <[email protected]> @@ -3341,6 +3349,7 @@ L: [email protected] S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git T: git git://git.linaro.org/people/vireshk/linux.git (For ARM Updates) +B: https://bugzilla.kernel.org F: Documentation/cpu-freq/ F: drivers/cpufreq/ F: include/linux/cpufreq.h @@ -9260,11 +9269,12 @@ S: Maintained F: drivers/pci/host/*layerscape* PCI DRIVER FOR IMX6 -M: Richard Zhu <[email protected]> +M: Richard Zhu <[email protected]> M: Lucas Stach <[email protected]> L: [email protected] (moderated for non-subscribers) S: Maintained +F: Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt F: drivers/pci/host/*imx6* PCI DRIVER FOR TI KEYSTONE @@ -9323,17 +9333,11 @@ F: drivers/pci/host/pci-exynos.c PCI DRIVER FOR SYNOPSIS DESIGNWARE M: Jingoo Han <[email protected]> -M: Pratyush Anand <[email protected]> -S: Maintained -F: drivers/pci/host/*designware* - -PCI DRIVER FOR SYNOPSYS PROTOTYPING DEVICE -M: Jose Abreu <[email protected]> +M: Joao Pinto <[email protected]> S: Maintained F: Documentation/devicetree/bindings/pci/designware-pcie.txt -F: drivers/pci/host/pcie-designware-plat.c +F: drivers/pci/host/*designware* PCI DRIVER FOR GENERIC OF HOSTS M: Will Deacon <[email protected]> @@ -1,8 +1,8 @@ VERSION = 4 PATCHLEVEL = 9 SUBLEVEL = 0 -EXTRAVERSION = -rc7 -NAME = Psychotic Stoned Sheep +EXTRAVERSION = +NAME = Roaring Lionus # *DOCUMENTATION* # To see a list of typical targets execute "make help" @@ -607,6 +607,13 @@ else include/config/auto.conf: ; endif # $(dot-config) +# For the kernel to actually contain only the needed exported symbols, +# we have to build modules as well to determine what those symbols are. +# (this can be evaluated only once include/config/auto.conf has been included) +ifdef CONFIG_TRIM_UNUSED_KSYMS + KBUILD_MODULES := 1 +endif + # The all: target is the default when no target is given on the # command line. # This allow a user to issue only 'make' to build a kernel including modules @@ -944,7 +951,7 @@ ifdef CONFIG_GDB_SCRIPTS endif ifdef CONFIG_TRIM_UNUSED_KSYMS $(Q)$(CONFIG_SHELL) $(srctree)/scripts/adjust_autoksyms.sh \ - "$(MAKE) KBUILD_MODULES=1 -f $(srctree)/Makefile vmlinux_prereq" + "$(MAKE) -f $(srctree)/Makefile vmlinux" endif # standalone target for easier testing @@ -1019,8 +1026,6 @@ prepare2: prepare3 prepare-compiler-check outputmakefile asm-generic prepare1: prepare2 $(version_h) include/generated/utsrelease.h \ include/config/auto.conf $(cmd_crmodverdir) - $(Q)test -e include/generated/autoksyms.h || \ - touch include/generated/autoksyms.h archprepare: archheaders archscripts prepare1 scripts_basic diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index befcd2619902..c558ba75cbcc 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -745,7 +745,6 @@ dtb-$(CONFIG_MACH_SUN4I) += \ sun4i-a10-pcduino2.dtb \ sun4i-a10-pov-protab2-ips9.dtb dtb-$(CONFIG_MACH_SUN5I) += \ - ntc-gr8-evb.dtb \ sun5i-a10s-auxtek-t003.dtb \ sun5i-a10s-auxtek-t004.dtb \ sun5i-a10s-mk802.dtb \ @@ -761,6 +760,7 @@ dtb-$(CONFIG_MACH_SUN5I) += \ sun5i-a13-olinuxino-micro.dtb \ sun5i-a13-q8-tablet.dtb \ sun5i-a13-utoo-p66.dtb \ + sun5i-gr8-evb.dtb \ sun5i-r8-chip.dtb dtb-$(CONFIG_MACH_SUN6I) += \ sun6i-a31-app4-evb1.dtb \ diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 0d7d5ac6257b..2b6cb05bc01a 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -643,9 +643,8 @@ reg = <0x30730000 0x10000>; interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>, - <&clks IMX7D_CLK_DUMMY>, - <&clks IMX7D_CLK_DUMMY>; - clock-names = "pix", "axi", "disp_axi"; + <&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>; + clock-names = "pix", "axi"; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/orion5x-linkstation-lsgl.dts b/arch/arm/boot/dts/orion5x-linkstation-lsgl.dts index 1cf644bfd7ea..51dc734cd5b9 100644 --- a/arch/arm/boot/dts/orion5x-linkstation-lsgl.dts +++ b/arch/arm/boot/dts/orion5x-linkstation-lsgl.dts @@ -82,6 +82,10 @@ gpios = <&gpio0 9 GPIO_ACTIVE_HIGH>; }; +&sata { + nr-ports = <2>; +}; + &ehci1 { status = "okay"; }; diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi index 91096a49efa9..8f79b4147bba 100644 --- a/arch/arm/boot/dts/stih407-family.dtsi +++ b/arch/arm/boot/dts/stih407-family.dtsi @@ -283,6 +283,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c0_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -296,6 +298,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c1_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -309,6 +313,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -322,6 +328,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c3_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -335,6 +343,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c4_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -348,6 +358,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c5_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -363,6 +375,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c10_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -376,6 +390,8 @@ clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c11_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/ntc-gr8-evb.dts b/arch/arm/boot/dts/sun5i-gr8-evb.dts index 4b622f3b5220..714381fd64d7 100644 --- a/arch/arm/boot/dts/ntc-gr8-evb.dts +++ b/arch/arm/boot/dts/sun5i-gr8-evb.dts @@ -44,7 +44,7 @@ */ /dts-v1/; -#include "ntc-gr8.dtsi" +#include "sun5i-gr8.dtsi" #include "sunxi-common-regulators.dtsi" #include <dt-bindings/gpio/gpio.h> diff --git a/arch/arm/boot/dts/ntc-gr8.dtsi b/arch/arm/boot/dts/sun5i-gr8.dtsi index ca54e03ef366..ca54e03ef366 100644 --- a/arch/arm/boot/dts/ntc-gr8.dtsi +++ b/arch/arm/boot/dts/sun5i-gr8.dtsi diff --git a/arch/arm/boot/dts/sun8i-h3.dtsi b/arch/arm/boot/dts/sun8i-h3.dtsi index 75a865406d3e..f4ba088b225e 100644 --- a/arch/arm/boot/dts/sun8i-h3.dtsi +++ b/arch/arm/boot/dts/sun8i-h3.dtsi @@ -410,7 +410,7 @@ }; uart3_pins: uart3 { - allwinner,pins = "PG13", "PG14"; + allwinner,pins = "PA13", "PA14"; allwinner,function = "uart3"; allwinner,drive = <SUN4I_PINCTRL_10_MA>; allwinner,pull = <SUN4I_PINCTRL_NO_PULL>; diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c index b54db47f6f32..1dc2a34b9dbd 100644 --- a/arch/arm/mach-imx/gpc.c +++ b/arch/arm/mach-imx/gpc.c @@ -380,13 +380,6 @@ static struct pu_domain imx6q_pu_domain = { .name = "PU", .power_off = imx6q_pm_pu_power_off, .power_on = imx6q_pm_pu_power_on, - .states = { - [0] = { - .power_off_latency_ns = 25000, - .power_on_latency_ns = 2000000, - }, - }, - .state_count = 1, }, }; @@ -430,6 +423,16 @@ static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg) if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS)) return 0; + imx6q_pu_domain.base.states = devm_kzalloc(dev, + sizeof(*imx6q_pu_domain.base.states), + GFP_KERNEL); + if (!imx6q_pu_domain.base.states) + return -ENOMEM; + + imx6q_pu_domain.base.states[0].power_off_latency_ns = 25000; + imx6q_pu_domain.base.states[0].power_on_latency_ns = 2000000; + imx6q_pu_domain.base.state_count = 1; + for (i = 0; i < ARRAY_SIZE(imx_gpc_domains); i++) pm_genpd_init(imx_gpc_domains[i], NULL, false); diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi index 334271a25f70..7d3a2acc6a55 100644 --- a/arch/arm64/boot/dts/arm/juno-base.dtsi +++ b/arch/arm64/boot/dts/arm/juno-base.dtsi @@ -393,7 +393,7 @@ #address-cells = <3>; #size-cells = <2>; dma-coherent; - ranges = <0x01000000 0x00 0x5f800000 0x00 0x5f800000 0x0 0x00800000>, + ranges = <0x01000000 0x00 0x00000000 0x00 0x5f800000 0x0 0x00800000>, <0x02000000 0x00 0x50000000 0x00 0x50000000 0x0 0x08000000>, <0x42000000 0x40 0x00000000 0x40 0x00000000 0x1 0x00000000>; #interrupt-cells = <1>; diff --git a/arch/arm64/boot/dts/arm/juno-r1.dts b/arch/arm64/boot/dts/arm/juno-r1.dts index 123a58b29cbd..f0b857d6d73c 100644 --- a/arch/arm64/boot/dts/arm/juno-r1.dts +++ b/arch/arm64/boot/dts/arm/juno-r1.dts @@ -76,7 +76,7 @@ compatible = "arm,idle-state"; arm,psci-suspend-param = <0x1010000>; local-timer-stop; - entry-latency-us = <300>; + entry-latency-us = <400>; exit-latency-us = <1200>; min-residency-us = <2500>; }; diff --git a/arch/arm64/boot/dts/arm/juno-r2.dts b/arch/arm64/boot/dts/arm/juno-r2.dts index 007be826efce..26aaa6a7670f 100644 --- a/arch/arm64/boot/dts/arm/juno-r2.dts +++ b/arch/arm64/boot/dts/arm/juno-r2.dts @@ -76,7 +76,7 @@ compatible = "arm,idle-state"; arm,psci-suspend-param = <0x1010000>; local-timer-stop; - entry-latency-us = <300>; + entry-latency-us = <400>; exit-latency-us = <1200>; min-residency-us = <2500>; }; diff --git a/arch/arm64/boot/dts/arm/juno.dts b/arch/arm64/boot/dts/arm/juno.dts index a7270eff6939..6e154d948a80 100644 --- a/arch/arm64/boot/dts/arm/juno.dts +++ b/arch/arm64/boot/dts/arm/juno.dts @@ -76,7 +76,7 @@ compatible = "arm,idle-state"; arm,psci-suspend-param = <0x1010000>; local-timer-stop; - entry-latency-us = <300>; + entry-latency-us = <400>; exit-latency-us = <1200>; min-residency-us = <2500>; }; diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 55be7e3ff109..b98acd15ca22 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -95,9 +95,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -105,8 +106,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -366,6 +369,7 @@ CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m # CONFIG_NET_VENDOR_3COM is not set +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_A2065=y CONFIG_ARIADNE=y # CONFIG_NET_VENDOR_ARC is not set diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 365dda66b0e6..f80dc57e6374 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -93,9 +93,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -103,8 +104,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -347,6 +350,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index ce3cbfd16fcd..4e16b1821fbb 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -93,9 +93,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -103,8 +104,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -356,6 +359,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_ATARILANCE=y # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 8db496a9797d..2767bbf5ad61 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -91,9 +91,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -101,8 +102,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -346,6 +349,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index 8314156f7149..d13ba309265e 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -93,9 +93,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -103,8 +104,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -347,6 +350,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_HPLANCE=y # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 6600270b9622..78b5101c1aa6 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -92,9 +92,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -102,8 +103,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -363,6 +366,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_MACMACE=y # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 90abfe9eabba..38e5bcbd0d62 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -102,9 +102,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -112,8 +113,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -397,6 +400,7 @@ CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m # CONFIG_NET_VENDOR_3COM is not set +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_A2065=y CONFIG_ARIADNE=y CONFIG_ATARILANCE=y diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 0d502c2f73d5..28687192b68e 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -90,9 +90,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -100,8 +101,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -345,6 +348,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_MVME147_NET=y # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 5930e91fc710..5a5f109ab3cd 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -91,9 +91,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -101,8 +102,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -346,6 +349,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 74e3ad82eca9..e557c9de3fbc 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -91,9 +91,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -101,8 +102,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -353,6 +356,7 @@ CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m # CONFIG_NET_VENDOR_3COM is not set +# CONFIG_NET_VENDOR_AMAZON is not set # CONFIG_NET_VENDOR_AMD is not set # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 4ba8606a4e69..c6a748a36daf 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -88,9 +88,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -98,8 +99,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -343,6 +346,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_SUN3LANCE=y # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index c6f49726a6c9..10d60857b9a6 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -88,9 +88,10 @@ CONFIG_NF_TABLES_INET=m CONFIG_NF_TABLES_NETDEV=m CONFIG_NFT_EXTHDR=m CONFIG_NFT_META=m +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m -CONFIG_NFT_RBTREE=m -CONFIG_NFT_HASH=m +CONFIG_NFT_SET_RBTREE=m +CONFIG_NFT_SET_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m @@ -98,8 +99,10 @@ CONFIG_NFT_MASQ=m CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m +CONFIG_NFT_HASH=m CONFIG_NFT_DUP_NETDEV=m CONFIG_NFT_FWD_NETDEV=m CONFIG_NETFILTER_XT_SET=m @@ -343,6 +346,7 @@ CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_VETH=m +# CONFIG_NET_VENDOR_AMAZON is not set CONFIG_SUN3LANCE=y # CONFIG_NET_VENDOR_ARC is not set # CONFIG_NET_CADENCE is not set diff --git a/arch/m68k/include/asm/delay.h b/arch/m68k/include/asm/delay.h index d28fa8fe26fe..c598d847d56b 100644 --- a/arch/m68k/include/asm/delay.h +++ b/arch/m68k/include/asm/delay.h @@ -114,6 +114,6 @@ static inline void __udelay(unsigned long usecs) */ #define HZSCALE (268435456 / (1000000 / HZ)) -#define ndelay(n) __delay(DIV_ROUND_UP((n) * ((((HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6), 1000)); +#define ndelay(n) __delay(DIV_ROUND_UP((n) * ((((HZSCALE) >> 11) * (loops_per_jiffy >> 11)) >> 6), 1000)) #endif /* defined(_M68K_DELAY_H) */ diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c index 8d0170969e22..a7f81261c781 100644 --- a/arch/mips/kernel/time.c +++ b/arch/mips/kernel/time.c @@ -36,7 +36,7 @@ EXPORT_SYMBOL(rtc_lock); int __weak rtc_mips_set_time(unsigned long sec) { - return 0; + return -ENODEV; } int __weak rtc_mips_set_mmss(unsigned long nowtime) diff --git a/arch/mips/lantiq/falcon/sysctrl.c b/arch/mips/lantiq/falcon/sysctrl.c index 2a1b3021589c..82bbd0e2e298 100644 --- a/arch/mips/lantiq/falcon/sysctrl.c +++ b/arch/mips/lantiq/falcon/sysctrl.c @@ -24,7 +24,7 @@ /* GPE frequency selection */ #define GPPC_OFFSET 24 -#define GPEFREQ_MASK 0x00000C0 +#define GPEFREQ_MASK 0x0000C00 #define GPEFREQ_OFFSET 10 /* Clock status register */ #define SYSCTL_CLKS 0x0000 diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index c2c43f714684..3a4ed9f91d57 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -65,9 +65,9 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) unsigned long flags; \ spin_lock_irqsave(&pa_tlb_lock, flags); \ old_pte = *ptep; \ - set_pte(ptep, pteval); \ if (pte_inserted(old_pte)) \ purge_tlb_entries(mm, addr); \ + set_pte(ptep, pteval); \ spin_unlock_irqrestore(&pa_tlb_lock, flags); \ } while (0) @@ -478,8 +478,8 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned spin_unlock_irqrestore(&pa_tlb_lock, flags); return 0; } - set_pte(ptep, pte_mkold(pte)); purge_tlb_entries(vma->vm_mm, addr); + set_pte(ptep, pte_mkold(pte)); spin_unlock_irqrestore(&pa_tlb_lock, flags); return 1; } @@ -492,9 +492,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, spin_lock_irqsave(&pa_tlb_lock, flags); old_pte = *ptep; - set_pte(ptep, __pte(0)); if (pte_inserted(old_pte)) purge_tlb_entries(mm, addr); + set_pte(ptep, __pte(0)); spin_unlock_irqrestore(&pa_tlb_lock, flags); return old_pte; @@ -504,8 +504,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, { unsigned long flags; spin_lock_irqsave(&pa_tlb_lock, flags); - set_pte(ptep, pte_wrprotect(*ptep)); purge_tlb_entries(mm, addr); + set_pte(ptep, pte_wrprotect(*ptep)); spin_unlock_irqrestore(&pa_tlb_lock, flags); } diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index c263301648f3..977f0a4f5ecf 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -393,6 +393,15 @@ void __init parisc_setup_cache_timing(void) /* calculate TLB flush threshold */ + /* On SMP machines, skip the TLB measure of kernel text which + * has been mapped as huge pages. */ + if (num_online_cpus() > 1 && !parisc_requires_coherency()) { + threshold = max(cache_info.it_size, cache_info.dt_size); + threshold *= PAGE_SIZE; + threshold /= num_online_cpus(); + goto set_tlb_threshold; + } + alltime = mfctl(16); flush_tlb_all(); alltime = mfctl(16) - alltime; @@ -411,6 +420,8 @@ void __init parisc_setup_cache_timing(void) alltime, size, rangetime); threshold = PAGE_ALIGN(num_online_cpus() * size * alltime / rangetime); + +set_tlb_threshold: if (threshold) parisc_tlb_flush_threshold = threshold; printk(KERN_INFO "TLB flush threshold set to %lu KiB\n", diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index 1b39a2acaadf..adf7187f8951 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -892,19 +892,10 @@ ENTRY_CFI(flush_dcache_page_asm) fdc,m r31(%r28) fdc,m r31(%r28) fdc,m r31(%r28) - cmpb,COND(<<) %r28, %r25,1b + cmpb,COND(<<) %r28, %r25,1b fdc,m r31(%r28) sync - -#ifdef CONFIG_PA20 - pdtlb,l %r0(%r25) -#else - tlb_lock %r20,%r21,%r22 - pdtlb %r0(%r25) - tlb_unlock %r20,%r21,%r22 -#endif - bv %r0(%r2) nop .exit @@ -979,17 +970,6 @@ ENTRY_CFI(flush_icache_page_asm) fic,m %r31(%sr4,%r28) sync - -#ifdef CONFIG_PA20 - pdtlb,l %r0(%r28) - pitlb,l %r0(%sr4,%r25) -#else - tlb_lock %r20,%r21,%r22 - pdtlb %r0(%r28) - pitlb %r0(%sr4,%r25) - tlb_unlock %r20,%r21,%r22 -#endif - bv %r0(%r2) nop .exit diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index eae2dc8bc218..9d47f2efa830 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -100,7 +100,8 @@ src-wlib-y := string.S crt0.S crtsavres.S stdio.c decompress.c main.c \ ns16550.c serial.c simple_alloc.c div64.S util.S \ elf_util.c $(zlib-y) devtree.c stdlib.c \ oflib.c ofconsole.c cuboot.c mpsc.c cpm-serial.c \ - uartlite.c mpc52xx-psc.c opal.c opal-calls.S + uartlite.c mpc52xx-psc.c opal.c +src-wlib-$(CONFIG_PPC64_BOOT_WRAPPER) += opal-calls.S src-wlib-$(CONFIG_40x) += 4xx.c planetcore.c src-wlib-$(CONFIG_44x) += 4xx.c ebony.c bamboo.c src-wlib-$(CONFIG_8xx) += mpc8xx.c planetcore.c fsl-soc.c diff --git a/arch/powerpc/boot/opal.c b/arch/powerpc/boot/opal.c index d7b4fd47eb44..0272570d02de 100644 --- a/arch/powerpc/boot/opal.c +++ b/arch/powerpc/boot/opal.c @@ -13,7 +13,7 @@ #include <libfdt.h> #include "../include/asm/opal-api.h" -#ifdef __powerpc64__ +#ifdef CONFIG_PPC64_BOOT_WRAPPER /* Global OPAL struct used by opal-call.S */ struct opal { diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index a62be72da274..5c31369435f2 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -671,8 +671,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, /* Clear frozen state */ rc = eeh_clear_pe_frozen_state(pe, false); - if (rc) + if (rc) { + pci_unlock_rescan_remove(); return rc; + } /* Give the system 5 seconds to finish running the user-space * hotplug shutdown scripts, e.g. ifdown for ethernet. Yes, diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 8295f51c1a5f..7394b770ae1f 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -94,8 +94,17 @@ SECTIONS * detected, and will result in a crash at boot due to offsets being * wrong. */ +#ifdef CONFIG_PPC64 + /* + * BLOCK(0) overrides the default output section alignment because + * this needs to start right after .head.text in order for fixed + * section placement to work. + */ + .text BLOCK(0) : AT(ADDR(.text) - LOAD_OFFSET) { +#else .text : AT(ADDR(.text) - LOAD_OFFSET) { ALIGN_FUNCTION(); +#endif /* careful! __ftr_alt_* sections need to be close to .text */ *(.text .fixup __ftr_alt_* .ref.text) SCHED_TEXT diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c index 42c702b3be1f..6fa450c12d6d 100644 --- a/arch/powerpc/mm/hash64_4k.c +++ b/arch/powerpc/mm/hash64_4k.c @@ -55,7 +55,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, */ rflags = htab_convert_pte_flags(new_pte); - if (!cpu_has_feature(CPU_FTR_NOEXECUTE) && + if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap); diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c index 3bbbea07378c..1a68cb19b0e3 100644 --- a/arch/powerpc/mm/hash64_64k.c +++ b/arch/powerpc/mm/hash64_64k.c @@ -87,7 +87,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, subpg_pte = new_pte & ~subpg_prot; rflags = htab_convert_pte_flags(subpg_pte); - if (!cpu_has_feature(CPU_FTR_NOEXECUTE) && + if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) { /* @@ -258,7 +258,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access, rflags = htab_convert_pte_flags(new_pte); - if (!cpu_has_feature(CPU_FTR_NOEXECUTE) && + if (cpu_has_feature(CPU_FTR_NOEXECUTE) && !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 9d4bf3ab049e..6e395c996900 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -69,7 +69,7 @@ u64 x86_perf_event_update(struct perf_event *event) int shift = 64 - x86_pmu.cntval_bits; u64 prev_raw_count, new_raw_count; int idx = hwc->idx; - s64 delta; + u64 delta; if (idx == INTEL_PMC_IDX_FIXED_BTS) return 0; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index a74a2dbc0180..cb8522290e6a 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4034,7 +4034,7 @@ __init int intel_pmu_init(void) /* Support full width counters using alternative MSR range */ if (x86_pmu.intel_cap.full_width_write) { - x86_pmu.max_period = x86_pmu.cntval_mask; + x86_pmu.max_period = x86_pmu.cntval_mask >> 1; x86_pmu.perfctr = MSR_IA32_PMC0; pr_cont("full-width counters, "); } diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 4f5ac726335f..da51e5a3e2ff 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -540,6 +540,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 03d269bed941..24118c0b4640 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -272,7 +272,6 @@ struct compat_shmid64_ds { /* * The type of struct elf_prstatus.pr_reg in compatible core dumps. */ -#ifdef CONFIG_X86_X32_ABI typedef struct user_regs_struct compat_elf_gregset_t; /* Full regset -- prstatus on x32, otherwise on ia32 */ @@ -281,10 +280,9 @@ typedef struct user_regs_struct compat_elf_gregset_t; do { *(int *) (((void *) &((S)->pr_reg)) + R) = (V); } \ while (0) +#ifdef CONFIG_X86_X32_ABI #define COMPAT_USE_64BIT_TIME \ (!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)) -#else -typedef struct user_regs_struct32 compat_elf_gregset_t; #endif /* diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index aeef53ce93e1..35690a168cf7 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -815,9 +815,9 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) l = li; } addr1 = (base << shift) + - f * (unsigned long)(1 << m_io); + f * (1ULL << m_io); addr2 = (base << shift) + - (l + 1) * (unsigned long)(1 << m_io); + (l + 1) * (1ULL << m_io); pr_info("UV: %s[%03d..%03d] NASID 0x%04x ADDR 0x%016lx - 0x%016lx\n", id, fi, li, lnasid, addr1, addr2); if (max_io < l) diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c index b80e8bf43cc6..22881ddcbb9f 100644 --- a/arch/x86/kernel/unwind_guess.c +++ b/arch/x86/kernel/unwind_guess.c @@ -7,11 +7,13 @@ unsigned long unwind_get_return_address(struct unwind_state *state) { - unsigned long addr = READ_ONCE_NOCHECK(*state->sp); + unsigned long addr; if (unwind_done(state)) return 0; + addr = READ_ONCE_NOCHECK(*state->sp); + return ftrace_graph_ret_addr(state->task, &state->graph_idx, addr, state->sp); } @@ -25,11 +27,12 @@ bool unwind_next_frame(struct unwind_state *state) return false; do { - unsigned long addr = READ_ONCE_NOCHECK(*state->sp); + for (state->sp++; state->sp < info->end; state->sp++) { + unsigned long addr = READ_ONCE_NOCHECK(*state->sp); - for (state->sp++; state->sp < info->end; state->sp++) if (__kernel_text_address(addr)) return true; + } state->sp = info->next_sp; diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c index 55130846ac87..c0533fbc39e3 100644 --- a/arch/x86/platform/olpc/olpc-xo15-sci.c +++ b/arch/x86/platform/olpc/olpc-xo15-sci.c @@ -196,6 +196,7 @@ static int xo15_sci_remove(struct acpi_device *device) return 0; } +#ifdef CONFIG_PM_SLEEP static int xo15_sci_resume(struct device *dev) { /* Enable all EC events */ @@ -207,6 +208,7 @@ static int xo15_sci_resume(struct device *dev) return 0; } +#endif static SIMPLE_DEV_PM_OPS(xo15_sci_pm, NULL, xo15_sci_resume); diff --git a/arch/x86/tools/relocs.h b/arch/x86/tools/relocs.h index f59590645b68..1d23bf953a4a 100644 --- a/arch/x86/tools/relocs.h +++ b/arch/x86/tools/relocs.h @@ -16,7 +16,7 @@ #include <regex.h> #include <tools/le_byteshift.h> -void die(char *fmt, ...); +void die(char *fmt, ...) __attribute__((noreturn)); #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) diff --git a/block/blk-map.c b/block/blk-map.c index b8657fa8dc9a..27fd8d92892d 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -118,6 +118,9 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, struct iov_iter i; int ret; + if (!iter_is_iovec(iter)) + goto fail; + if (map_data) copy = true; else if (iov_iter_alignment(iter) & align) @@ -140,6 +143,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, unmap_rq: __blk_rq_unmap_user(bio); +fail: rq->bio = NULL; return -EINVAL; } diff --git a/crypto/Makefile b/crypto/Makefile index 99cc64ac70ef..bd6a029094e6 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -40,6 +40,7 @@ obj-$(CONFIG_CRYPTO_ECDH) += ecdh_generic.o $(obj)/rsapubkey-asn1.o: $(obj)/rsapubkey-asn1.c $(obj)/rsapubkey-asn1.h $(obj)/rsaprivkey-asn1.o: $(obj)/rsaprivkey-asn1.c $(obj)/rsaprivkey-asn1.h +$(obj)/rsa_helper.o: $(obj)/rsapubkey-asn1.h $(obj)/rsaprivkey-asn1.h clean-files += rsapubkey-asn1.c rsapubkey-asn1.h clean-files += rsaprivkey-asn1.c rsaprivkey-asn1.h diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index 80a0f1a78551..e9c0993b131d 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -81,7 +81,11 @@ static inline bool aead_sufficient_data(struct aead_ctx *ctx) { unsigned as = crypto_aead_authsize(crypto_aead_reqtfm(&ctx->aead_req)); - return ctx->used >= ctx->aead_assoclen + as; + /* + * The minimum amount of memory needed for an AEAD cipher is + * the AAD and in case of decryption the tag. + */ + return ctx->used >= ctx->aead_assoclen + (ctx->enc ? 0 : as); } static void aead_reset_ctx(struct aead_ctx *ctx) @@ -416,7 +420,7 @@ static int aead_recvmsg_async(struct socket *sock, struct msghdr *msg, unsigned int i, reqlen = GET_REQ_SIZE(tfm); int err = -ENOMEM; unsigned long used; - size_t outlen; + size_t outlen = 0; size_t usedpages = 0; lock_sock(sk); @@ -426,12 +430,15 @@ static int aead_recvmsg_async(struct socket *sock, struct msghdr *msg, goto unlock; } - used = ctx->used; - outlen = used; - if (!aead_sufficient_data(ctx)) goto unlock; + used = ctx->used; + if (ctx->enc) + outlen = used + as; + else + outlen = used - as; + req = sock_kmalloc(sk, reqlen, GFP_KERNEL); if (unlikely(!req)) goto unlock; @@ -445,7 +452,7 @@ static int aead_recvmsg_async(struct socket *sock, struct msghdr *msg, aead_request_set_ad(req, ctx->aead_assoclen); aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, aead_async_cb, sk); - used -= ctx->aead_assoclen + (ctx->enc ? as : 0); + used -= ctx->aead_assoclen; /* take over all tx sgls from ctx */ areq->tsgl = sock_kmalloc(sk, sizeof(*areq->tsgl) * sgl->cur, @@ -461,7 +468,7 @@ static int aead_recvmsg_async(struct socket *sock, struct msghdr *msg, areq->tsgls = sgl->cur; /* create rx sgls */ - while (iov_iter_count(&msg->msg_iter)) { + while (outlen > usedpages && iov_iter_count(&msg->msg_iter)) { size_t seglen = min_t(size_t, iov_iter_count(&msg->msg_iter), (outlen - usedpages)); @@ -491,16 +498,14 @@ static int aead_recvmsg_async(struct socket *sock, struct msghdr *msg, last_rsgl = rsgl; - /* we do not need more iovecs as we have sufficient memory */ - if (outlen <= usedpages) - break; - iov_iter_advance(&msg->msg_iter, err); } - err = -EINVAL; + /* ensure output buffer is sufficiently large */ - if (usedpages < outlen) - goto free; + if (usedpages < outlen) { + err = -EINVAL; + goto unlock; + } aead_request_set_crypt(req, areq->tsgl, areq->first_rsgl.sgl.sg, used, areq->iv); @@ -571,6 +576,7 @@ static int aead_recvmsg_sync(struct socket *sock, struct msghdr *msg, int flags) goto unlock; } + /* data length provided by caller via sendmsg/sendpage */ used = ctx->used; /* @@ -585,16 +591,27 @@ static int aead_recvmsg_sync(struct socket *sock, struct msghdr *msg, int flags) if (!aead_sufficient_data(ctx)) goto unlock; - outlen = used; + /* + * Calculate the minimum output buffer size holding the result of the + * cipher operation. When encrypting data, the receiving buffer is + * larger by the tag length compared to the input buffer as the + * encryption operation generates the tag. For decryption, the input + * buffer provides the tag which is consumed resulting in only the + * plaintext without a buffer for the tag returned to the caller. + */ + if (ctx->enc) + outlen = used + as; + else + outlen = used - as; /* * The cipher operation input data is reduced by the associated data * length as this data is processed separately later on. */ - used -= ctx->aead_assoclen + (ctx->enc ? as : 0); + used -= ctx->aead_assoclen; /* convert iovecs of output buffers into scatterlists */ - while (iov_iter_count(&msg->msg_iter)) { + while (outlen > usedpages && iov_iter_count(&msg->msg_iter)) { size_t seglen = min_t(size_t, iov_iter_count(&msg->msg_iter), (outlen - usedpages)); @@ -621,16 +638,14 @@ static int aead_recvmsg_sync(struct socket *sock, struct msghdr *msg, int flags) last_rsgl = rsgl; - /* we do not need more iovecs as we have sufficient memory */ - if (outlen <= usedpages) - break; iov_iter_advance(&msg->msg_iter, err); } - err = -EINVAL; /* ensure output buffer is sufficiently large */ - if (usedpages < outlen) + if (usedpages < outlen) { + err = -EINVAL; goto unlock; + } sg_mark_end(sgl->sg + sgl->cur - 1); aead_request_set_crypt(&ctx->aead_req, sgl->sg, ctx->first_rsgl.sgl.sg, diff --git a/crypto/drbg.c b/crypto/drbg.c index fb33f7d3b052..053035b5c8f8 100644 --- a/crypto/drbg.c +++ b/crypto/drbg.c @@ -262,6 +262,7 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg, u8 *inbuf, u32 inbuflen, u8 *outbuf, u32 outlen); #define DRBG_CTR_NULL_LEN 128 +#define DRBG_OUTSCRATCHLEN DRBG_CTR_NULL_LEN /* BCC function for CTR DRBG as defined in 10.4.3 */ static int drbg_ctr_bcc(struct drbg_state *drbg, @@ -1644,6 +1645,9 @@ static int drbg_fini_sym_kernel(struct drbg_state *drbg) kfree(drbg->ctr_null_value_buf); drbg->ctr_null_value = NULL; + kfree(drbg->outscratchpadbuf); + drbg->outscratchpadbuf = NULL; + return 0; } @@ -1708,6 +1712,15 @@ static int drbg_init_sym_kernel(struct drbg_state *drbg) drbg->ctr_null_value = (u8 *)PTR_ALIGN(drbg->ctr_null_value_buf, alignmask + 1); + drbg->outscratchpadbuf = kmalloc(DRBG_OUTSCRATCHLEN + alignmask, + GFP_KERNEL); + if (!drbg->outscratchpadbuf) { + drbg_fini_sym_kernel(drbg); + return -ENOMEM; + } + drbg->outscratchpad = (u8 *)PTR_ALIGN(drbg->outscratchpadbuf, + alignmask + 1); + return alignmask; } @@ -1737,15 +1750,16 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg, u8 *outbuf, u32 outlen) { struct scatterlist sg_in; + int ret; sg_init_one(&sg_in, inbuf, inlen); while (outlen) { - u32 cryptlen = min_t(u32, inlen, outlen); + u32 cryptlen = min3(inlen, outlen, (u32)DRBG_OUTSCRATCHLEN); struct scatterlist sg_out; - int ret; - sg_init_one(&sg_out, outbuf, cryptlen); + /* Output buffer may not be valid for SGL, use scratchpad */ + sg_init_one(&sg_out, drbg->outscratchpad, cryptlen); skcipher_request_set_crypt(drbg->ctr_req, &sg_in, &sg_out, cryptlen, drbg->V); ret = crypto_skcipher_encrypt(drbg->ctr_req); @@ -1761,14 +1775,19 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg, break; } default: - return ret; + goto out; } init_completion(&drbg->ctr_completion); + memcpy(outbuf, drbg->outscratchpad, cryptlen); + outlen -= cryptlen; } + ret = 0; - return 0; +out: + memzero_explicit(drbg->outscratchpad, DRBG_OUTSCRATCHLEN); + return ret; } #endif /* CONFIG_CRYPTO_DRBG_CTR */ diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c index 94ee44acd465..c207458d6299 100644 --- a/crypto/mcryptd.c +++ b/crypto/mcryptd.c @@ -254,18 +254,22 @@ out_free_inst: goto out; } -static inline void mcryptd_check_internal(struct rtattr **tb, u32 *type, +static inline bool mcryptd_check_internal(struct rtattr **tb, u32 *type, u32 *mask) { struct crypto_attr_type *algt; algt = crypto_get_attr_type(tb); if (IS_ERR(algt)) - return; - if ((algt->type & CRYPTO_ALG_INTERNAL)) - *type |= CRYPTO_ALG_INTERNAL; - if ((algt->mask & CRYPTO_ALG_INTERNAL)) - *mask |= CRYPTO_ALG_INTERNAL; + return false; + + *type |= algt->type & CRYPTO_ALG_INTERNAL; + *mask |= algt->mask & CRYPTO_ALG_INTERNAL; + + if (*type & *mask & CRYPTO_ALG_INTERNAL) + return true; + else + return false; } static int mcryptd_hash_init_tfm(struct crypto_tfm *tfm) @@ -492,7 +496,8 @@ static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb, u32 mask = 0; int err; - mcryptd_check_internal(tb, &type, &mask); + if (!mcryptd_check_internal(tb, &type, &mask)) + return -EINVAL; halg = ahash_attr_alg(tb[1], type, mask); if (IS_ERR(halg)) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 71a7d07c28c9..312c4b4dc363 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -94,7 +94,7 @@ static struct acpi_device *to_acpi_dev(struct acpi_nfit_desc *acpi_desc) return to_acpi_device(acpi_desc->dev); } -static int xlat_status(void *buf, unsigned int cmd, u32 status) +static int xlat_bus_status(void *buf, unsigned int cmd, u32 status) { struct nd_cmd_clear_error *clear_err; struct nd_cmd_ars_status *ars_status; @@ -113,7 +113,7 @@ static int xlat_status(void *buf, unsigned int cmd, u32 status) flags = ND_ARS_PERSISTENT | ND_ARS_VOLATILE; if ((status >> 16 & flags) == 0) return -ENOTTY; - break; + return 0; case ND_CMD_ARS_START: /* ARS is in progress */ if ((status & 0xffff) == NFIT_ARS_START_BUSY) @@ -122,7 +122,7 @@ static int xlat_status(void *buf, unsigned int cmd, u32 status) /* Command failed */ if (status & 0xffff) return -EIO; - break; + return 0; case ND_CMD_ARS_STATUS: ars_status = buf; /* Command failed */ @@ -146,7 +146,8 @@ static int xlat_status(void *buf, unsigned int cmd, u32 status) * then just continue with the returned results. */ if (status == NFIT_ARS_STATUS_INTR) { - if (ars_status->flags & NFIT_ARS_F_OVERFLOW) + if (ars_status->out_length >= 40 && (ars_status->flags + & NFIT_ARS_F_OVERFLOW)) return -ENOSPC; return 0; } @@ -154,7 +155,7 @@ static int xlat_status(void *buf, unsigned int cmd, u32 status) /* Unknown status */ if (status >> 16) return -EIO; - break; + return 0; case ND_CMD_CLEAR_ERROR: clear_err = buf; if (status & 0xffff) @@ -163,7 +164,7 @@ static int xlat_status(void *buf, unsigned int cmd, u32 status) return -EIO; if (clear_err->length > clear_err->cleared) return clear_err->cleared; - break; + return 0; default: break; } @@ -174,9 +175,18 @@ static int xlat_status(void *buf, unsigned int cmd, u32 status) return 0; } -static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, - struct nvdimm *nvdimm, unsigned int cmd, void *buf, - unsigned int buf_len, int *cmd_rc) +static int xlat_status(struct nvdimm *nvdimm, void *buf, unsigned int cmd, + u32 status) +{ + if (!nvdimm) + return xlat_bus_status(buf, cmd, status); + if (status) + return -EIO; + return 0; +} + +int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, + unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc) { struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc); union acpi_object in_obj, in_buf, *out_obj; @@ -298,7 +308,8 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, for (i = 0, offset = 0; i < desc->out_num; i++) { u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, buf, - (u32 *) out_obj->buffer.pointer); + (u32 *) out_obj->buffer.pointer, + out_obj->buffer.length - offset); if (offset + out_size > out_obj->buffer.length) { dev_dbg(dev, "%s:%s output object underflow cmd: %s field: %d\n", @@ -333,7 +344,8 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, */ rc = buf_len - offset - in_buf.buffer.length; if (cmd_rc) - *cmd_rc = xlat_status(buf, cmd, fw_status); + *cmd_rc = xlat_status(nvdimm, buf, cmd, + fw_status); } else { dev_err(dev, "%s:%s underrun cmd: %s buf_len: %d out_len: %d\n", __func__, dimm_name, cmd_name, buf_len, @@ -343,7 +355,7 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, } else { rc = 0; if (cmd_rc) - *cmd_rc = xlat_status(buf, cmd, fw_status); + *cmd_rc = xlat_status(nvdimm, buf, cmd, fw_status); } out: @@ -351,6 +363,7 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, return rc; } +EXPORT_SYMBOL_GPL(acpi_nfit_ctl); static const char *spa_type_name(u16 type) { @@ -2001,19 +2014,32 @@ static int ars_get_status(struct acpi_nfit_desc *acpi_desc) return cmd_rc; } -static int ars_status_process_records(struct nvdimm_bus *nvdimm_bus, +static int ars_status_process_records(struct acpi_nfit_desc *acpi_desc, struct nd_cmd_ars_status *ars_status) { + struct nvdimm_bus *nvdimm_bus = acpi_desc->nvdimm_bus; int rc; u32 i; + /* + * First record starts at 44 byte offset from the start of the + * payload. + */ + if (ars_status->out_length < 44) + return 0; for (i = 0; i < ars_status->num_records; i++) { + /* only process full records */ + if (ars_status->out_length + < 44 + sizeof(struct nd_ars_record) * (i + 1)) + break; rc = nvdimm_bus_add_poison(nvdimm_bus, ars_status->records[i].err_address, ars_status->records[i].length); if (rc) return rc; } + if (i < ars_status->num_records) + dev_warn(acpi_desc->dev, "detected truncated ars results\n"); return 0; } @@ -2266,8 +2292,7 @@ static int acpi_nfit_query_poison(struct acpi_nfit_desc *acpi_desc, if (rc < 0 && rc != -ENOSPC) return rc; - if (ars_status_process_records(acpi_desc->nvdimm_bus, - acpi_desc->ars_status)) + if (ars_status_process_records(acpi_desc, acpi_desc->ars_status)) return -ENOMEM; return 0; diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index 14296f5267c8..fc29c2e9832e 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -240,5 +240,7 @@ const u8 *to_nfit_uuid(enum nfit_uuids id); int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *nfit, acpi_size sz); void __acpi_nfit_notify(struct device *dev, acpi_handle handle, u32 event); void __acpi_nvdimm_notify(struct device *dev, u32 event); +int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, + unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc); void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev); #endif /* __NFIT_H__ */ diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index bb01dea39fdc..f0b4a981b8d3 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -157,7 +157,7 @@ static void acpi_processor_ppc_ost(acpi_handle handle, int status) status, NULL); } -int acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag) +void acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag) { int ret; @@ -168,7 +168,7 @@ int acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag) */ if (event_flag) acpi_processor_ppc_ost(pr->handle, 1); - return 0; + return; } ret = acpi_processor_get_platform_limit(pr); @@ -182,10 +182,8 @@ int acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag) else acpi_processor_ppc_ost(pr->handle, 0); } - if (ret < 0) - return (ret); - else - return cpufreq_update_policy(pr->id); + if (ret >= 0) + cpufreq_update_policy(pr->id); } int acpi_processor_get_bios_limit(int cpu, unsigned int *limit) @@ -465,11 +463,33 @@ int acpi_processor_get_performance_info(struct acpi_processor *pr) return result; } EXPORT_SYMBOL_GPL(acpi_processor_get_performance_info); -int acpi_processor_notify_smm(struct module *calling_module) + +int acpi_processor_pstate_control(void) { acpi_status status; - static int is_done = 0; + if (!acpi_gbl_FADT.smi_command || !acpi_gbl_FADT.pstate_control) + return 0; + + ACPI_DEBUG_PRINT((ACPI_DB_INFO, + "Writing pstate_control [0x%x] to smi_command [0x%x]\n", + acpi_gbl_FADT.pstate_control, acpi_gbl_FADT.smi_command)); + + status = acpi_os_write_port(acpi_gbl_FADT.smi_command, + (u32)acpi_gbl_FADT.pstate_control, 8); + if (ACPI_SUCCESS(status)) + return 1; + + ACPI_EXCEPTION((AE_INFO, status, + "Failed to write pstate_control [0x%x] to smi_command [0x%x]", + acpi_gbl_FADT.pstate_control, acpi_gbl_FADT.smi_command)); + return -EIO; +} + +int acpi_processor_notify_smm(struct module *calling_module) +{ + static int is_done = 0; + int result; if (!(acpi_processor_ppc_status & PPC_REGISTERED)) return -EBUSY; @@ -492,26 +512,15 @@ int acpi_processor_notify_smm(struct module *calling_module) is_done = -EIO; - /* Can't write pstate_control to smi_command if either value is zero */ - if ((!acpi_gbl_FADT.smi_command) || (!acpi_gbl_FADT.pstate_control)) { + result = acpi_processor_pstate_control(); + if (!result) { ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No SMI port or pstate_control\n")); module_put(calling_module); return 0; } - - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Writing pstate_control [0x%x] to smi_command [0x%x]\n", - acpi_gbl_FADT.pstate_control, acpi_gbl_FADT.smi_command)); - - status = acpi_os_write_port(acpi_gbl_FADT.smi_command, - (u32) acpi_gbl_FADT.pstate_control, 8); - if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, - "Failed to write pstate_control [0x%x] to " - "smi_command [0x%x]", acpi_gbl_FADT.pstate_control, - acpi_gbl_FADT.smi_command)); + if (result < 0) { module_put(calling_module); - return status; + return result; } /* Success. If there's no _PPC, we need to fear nothing, so diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index c4eb4ae9c3aa..8e575fbdf31d 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1159,6 +1159,7 @@ static void ata_scsi_sdev_config(struct scsi_device *sdev) { sdev->use_10_for_rw = 1; sdev->use_10_for_ms = 1; + sdev->no_write_same = 1; /* Schedule policy is determined by ->qc_defer() callback and * it needs to see every deferred qc. Set dev_blocked to 1 to diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index efc48bf89d51..823e938c9a78 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -4090,7 +4090,20 @@ static int mv_platform_probe(struct platform_device *pdev) /* allocate host */ if (pdev->dev.of_node) { - of_property_read_u32(pdev->dev.of_node, "nr-ports", &n_ports); + rc = of_property_read_u32(pdev->dev.of_node, "nr-ports", + &n_ports); + if (rc) { + dev_err(&pdev->dev, + "error parsing nr-ports property: %d\n", rc); + return rc; + } + + if (n_ports <= 0) { + dev_err(&pdev->dev, "nr-ports must be positive: %d\n", + n_ports); + return -EINVAL; + } + irq = irq_of_parse_and_map(pdev->dev.of_node, 0); } else { mv_platform_data = dev_get_platdata(&pdev->dev); diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c index f2aaf9e32a36..40c2d561417b 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -1727,7 +1727,7 @@ static int eni_do_init(struct atm_dev *dev) printk("\n"); printk(KERN_ERR DEV_LABEL "(itf %d): can't set up page " "mapping\n",dev->number); - return error; + return -ENOMEM; } eni_dev->ioaddr = base; eni_dev->base_diff = real_base - (unsigned long) base; diff --git a/drivers/atm/lanai.c b/drivers/atm/lanai.c index ce43ae3e87b3..445505d9ea07 100644 --- a/drivers/atm/lanai.c +++ b/drivers/atm/lanai.c @@ -2143,6 +2143,7 @@ static int lanai_dev_open(struct atm_dev *atmdev) lanai->base = (bus_addr_t) ioremap(raw_base, LANAI_MAPPING_SIZE); if (lanai->base == NULL) { printk(KERN_ERR DEV_LABEL ": couldn't remap I/O space\n"); + result = -ENOMEM; goto error_pci; } /* 3.3: Reset lanai and PHY */ diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index e023066e4215..5711708532db 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -39,6 +39,105 @@ static LIST_HEAD(gpd_list); static DEFINE_MUTEX(gpd_list_lock); +struct genpd_lock_ops { + void (*lock)(struct generic_pm_domain *genpd); + void (*lock_nested)(struct generic_pm_domain *genpd, int depth); + int (*lock_interruptible)(struct generic_pm_domain *genpd); + void (*unlock)(struct generic_pm_domain *genpd); +}; + +static void genpd_lock_mtx(struct generic_pm_domain *genpd) +{ + mutex_lock(&genpd->mlock); +} + +static void genpd_lock_nested_mtx(struct generic_pm_domain *genpd, + int depth) +{ + mutex_lock_nested(&genpd->mlock, depth); +} + +static int genpd_lock_interruptible_mtx(struct generic_pm_domain *genpd) +{ + return mutex_lock_interruptible(&genpd->mlock); +} + +static void genpd_unlock_mtx(struct generic_pm_domain *genpd) +{ + return mutex_unlock(&genpd->mlock); +} + +static const struct genpd_lock_ops genpd_mtx_ops = { + .lock = genpd_lock_mtx, + .lock_nested = genpd_lock_nested_mtx, + .lock_interruptible = genpd_lock_interruptible_mtx, + .unlock = genpd_unlock_mtx, +}; + +static void genpd_lock_spin(struct generic_pm_domain *genpd) + __acquires(&genpd->slock) +{ + unsigned long flags; + + spin_lock_irqsave(&genpd->slock, flags); + genpd->lock_flags = flags; +} + +static void genpd_lock_nested_spin(struct generic_pm_domain *genpd, + int depth) + __acquires(&genpd->slock) +{ + unsigned long flags; + + spin_lock_irqsave_nested(&genpd->slock, flags, depth); + genpd->lock_flags = flags; +} + +static int genpd_lock_interruptible_spin(struct generic_pm_domain *genpd) + __acquires(&genpd->slock) +{ + unsigned long flags; + + spin_lock_irqsave(&genpd->slock, flags); + genpd->lock_flags = flags; + return 0; +} + +static void genpd_unlock_spin(struct generic_pm_domain *genpd) + __releases(&genpd->slock) +{ + spin_unlock_irqrestore(&genpd->slock, genpd->lock_flags); +} + +static const struct genpd_lock_ops genpd_spin_ops = { + .lock = genpd_lock_spin, + .lock_nested = genpd_lock_nested_spin, + .lock_interruptible = genpd_lock_interruptible_spin, + .unlock = genpd_unlock_spin, +}; + +#define genpd_lock(p) p->lock_ops->lock(p) +#define genpd_lock_nested(p, d) p->lock_ops->lock_nested(p, d) +#define genpd_lock_interruptible(p) p->lock_ops->lock_interruptible(p) +#define genpd_unlock(p) p->lock_ops->unlock(p) + +#define genpd_is_irq_safe(genpd) (genpd->flags & GENPD_FLAG_IRQ_SAFE) + +static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev, + struct generic_pm_domain *genpd) +{ + bool ret; + + ret = pm_runtime_is_irq_safe(dev) && !genpd_is_irq_safe(genpd); + + /* Warn once for each IRQ safe dev in no sleep domain */ + if (ret) + dev_warn_once(dev, "PM domain %s will not be powered off\n", + genpd->name); + + return ret; +} + /* * Get the generic PM domain for a particular struct device. * This validates the struct device pointer, the PM domain pointer, @@ -200,9 +299,9 @@ static int genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth) genpd_sd_counter_inc(master); - mutex_lock_nested(&master->lock, depth + 1); + genpd_lock_nested(master, depth + 1); ret = genpd_poweron(master, depth + 1); - mutex_unlock(&master->lock); + genpd_unlock(master); if (ret) { genpd_sd_counter_dec(master); @@ -255,9 +354,9 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb, spin_unlock_irq(&dev->power.lock); if (!IS_ERR(genpd)) { - mutex_lock(&genpd->lock); + genpd_lock(genpd); genpd->max_off_time_changed = true; - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); } dev = dev->parent; @@ -303,7 +402,12 @@ static int genpd_poweroff(struct generic_pm_domain *genpd, bool is_async) if (stat > PM_QOS_FLAGS_NONE) return -EBUSY; - if (!pm_runtime_suspended(pdd->dev) || pdd->dev->power.irq_safe) + /* + * Do not allow PM domain to be powered off, when an IRQ safe + * device is part of a non-IRQ safe domain. + */ + if (!pm_runtime_suspended(pdd->dev) || + irq_safe_dev_in_no_sleep_domain(pdd->dev, genpd)) not_suspended++; } @@ -354,9 +458,9 @@ static void genpd_power_off_work_fn(struct work_struct *work) genpd = container_of(work, struct generic_pm_domain, power_off_work); - mutex_lock(&genpd->lock); + genpd_lock(genpd); genpd_poweroff(genpd, true); - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); } /** @@ -466,15 +570,15 @@ static int genpd_runtime_suspend(struct device *dev) } /* - * If power.irq_safe is set, this routine will be run with interrupts - * off, so it can't use mutexes. + * If power.irq_safe is set, this routine may be run with + * IRQs disabled, so suspend only if the PM domain also is irq_safe. */ - if (dev->power.irq_safe) + if (irq_safe_dev_in_no_sleep_domain(dev, genpd)) return 0; - mutex_lock(&genpd->lock); + genpd_lock(genpd); genpd_poweroff(genpd, false); - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); return 0; } @@ -503,15 +607,18 @@ static int genpd_runtime_resume(struct device *dev) if (IS_ERR(genpd)) return -EINVAL; - /* If power.irq_safe, the PM domain is never powered off. */ - if (dev->power.irq_safe) { + /* + * As we don't power off a non IRQ safe domain, which holds + * an IRQ safe device, we don't need to restore power to it. + */ + if (irq_safe_dev_in_no_sleep_domain(dev, genpd)) { timed = false; goto out; } - mutex_lock(&genpd->lock); + genpd_lock(genpd); ret = genpd_poweron(genpd, 0); - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); if (ret) return ret; @@ -546,10 +653,11 @@ static int genpd_runtime_resume(struct device *dev) err_stop: genpd_stop_dev(genpd, dev); err_poweroff: - if (!dev->power.irq_safe) { - mutex_lock(&genpd->lock); + if (!pm_runtime_is_irq_safe(dev) || + (pm_runtime_is_irq_safe(dev) && genpd_is_irq_safe(genpd))) { + genpd_lock(genpd); genpd_poweroff(genpd, 0); - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); } return ret; @@ -732,20 +840,20 @@ static int pm_genpd_prepare(struct device *dev) if (resume_needed(dev, genpd)) pm_runtime_resume(dev); - mutex_lock(&genpd->lock); + genpd_lock(genpd); if (genpd->prepared_count++ == 0) genpd->suspended_count = 0; - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); ret = pm_generic_prepare(dev); if (ret) { - mutex_lock(&genpd->lock); + genpd_lock(genpd); genpd->prepared_count--; - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); } return ret; @@ -936,13 +1044,13 @@ static void pm_genpd_complete(struct device *dev) pm_generic_complete(dev); - mutex_lock(&genpd->lock); + genpd_lock(genpd); genpd->prepared_count--; if (!genpd->prepared_count) genpd_queue_power_off_work(genpd); - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); } /** @@ -1071,7 +1179,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, if (IS_ERR(gpd_data)) return PTR_ERR(gpd_data); - mutex_lock(&genpd->lock); + genpd_lock(genpd); if (genpd->prepared_count > 0) { ret = -EAGAIN; @@ -1088,7 +1196,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, list_add_tail(&gpd_data->base.list_node, &genpd->dev_list); out: - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); if (ret) genpd_free_dev_data(dev, gpd_data); @@ -1130,7 +1238,7 @@ static int genpd_remove_device(struct generic_pm_domain *genpd, gpd_data = to_gpd_data(pdd); dev_pm_qos_remove_notifier(dev, &gpd_data->nb); - mutex_lock(&genpd->lock); + genpd_lock(genpd); if (genpd->prepared_count > 0) { ret = -EAGAIN; @@ -1145,14 +1253,14 @@ static int genpd_remove_device(struct generic_pm_domain *genpd, list_del_init(&pdd->list_node); - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); genpd_free_dev_data(dev, gpd_data); return 0; out: - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); dev_pm_qos_add_notifier(dev, &gpd_data->nb); return ret; @@ -1183,12 +1291,23 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd, || genpd == subdomain) return -EINVAL; + /* + * If the domain can be powered on/off in an IRQ safe + * context, ensure that the subdomain can also be + * powered on/off in that context. + */ + if (!genpd_is_irq_safe(genpd) && genpd_is_irq_safe(subdomain)) { + WARN(1, "Parent %s of subdomain %s must be IRQ safe\n", + genpd->name, subdomain->name); + return -EINVAL; + } + link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) return -ENOMEM; - mutex_lock(&subdomain->lock); - mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING); + genpd_lock(subdomain); + genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING); if (genpd->status == GPD_STATE_POWER_OFF && subdomain->status != GPD_STATE_POWER_OFF) { @@ -1211,8 +1330,8 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd, genpd_sd_counter_inc(genpd); out: - mutex_unlock(&genpd->lock); - mutex_unlock(&subdomain->lock); + genpd_unlock(genpd); + genpd_unlock(subdomain); if (ret) kfree(link); return ret; @@ -1250,8 +1369,8 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain)) return -EINVAL; - mutex_lock(&subdomain->lock); - mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING); + genpd_lock(subdomain); + genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING); if (!list_empty(&subdomain->master_links) || subdomain->device_count) { pr_warn("%s: unable to remove subdomain %s\n", genpd->name, @@ -1275,13 +1394,39 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, } out: - mutex_unlock(&genpd->lock); - mutex_unlock(&subdomain->lock); + genpd_unlock(genpd); + genpd_unlock(subdomain); return ret; } EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain); +static int genpd_set_default_power_state(struct generic_pm_domain *genpd) +{ + struct genpd_power_state *state; + + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (!state) + return -ENOMEM; + + genpd->states = state; + genpd->state_count = 1; + genpd->free = state; + + return 0; +} + +static void genpd_lock_init(struct generic_pm_domain *genpd) +{ + if (genpd->flags & GENPD_FLAG_IRQ_SAFE) { + spin_lock_init(&genpd->slock); + genpd->lock_ops = &genpd_spin_ops; + } else { + mutex_init(&genpd->mlock); + genpd->lock_ops = &genpd_mtx_ops; + } +} + /** * pm_genpd_init - Initialize a generic I/O PM domain object. * @genpd: PM domain object to initialize. @@ -1293,13 +1438,15 @@ EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain); int pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off) { + int ret; + if (IS_ERR_OR_NULL(genpd)) return -EINVAL; INIT_LIST_HEAD(&genpd->master_links); INIT_LIST_HEAD(&genpd->slave_links); INIT_LIST_HEAD(&genpd->dev_list); - mutex_init(&genpd->lock); + genpd_lock_init(genpd); genpd->gov = gov; INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn); atomic_set(&genpd->sd_count, 0); @@ -1325,19 +1472,12 @@ int pm_genpd_init(struct generic_pm_domain *genpd, genpd->dev_ops.start = pm_clk_resume; } - if (genpd->state_idx >= GENPD_MAX_NUM_STATES) { - pr_warn("Initial state index out of bounds.\n"); - genpd->state_idx = GENPD_MAX_NUM_STATES - 1; - } - - if (genpd->state_count > GENPD_MAX_NUM_STATES) { - pr_warn("Limiting states to %d\n", GENPD_MAX_NUM_STATES); - genpd->state_count = GENPD_MAX_NUM_STATES; - } - /* Use only one "off" state if there were no states declared */ - if (genpd->state_count == 0) - genpd->state_count = 1; + if (genpd->state_count == 0) { + ret = genpd_set_default_power_state(genpd); + if (ret) + return ret; + } mutex_lock(&gpd_list_lock); list_add(&genpd->gpd_list_node, &gpd_list); @@ -1354,16 +1494,16 @@ static int genpd_remove(struct generic_pm_domain *genpd) if (IS_ERR_OR_NULL(genpd)) return -EINVAL; - mutex_lock(&genpd->lock); + genpd_lock(genpd); if (genpd->has_provider) { - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); pr_err("Provider present, unable to remove %s\n", genpd->name); return -EBUSY; } if (!list_empty(&genpd->master_links) || genpd->device_count) { - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); pr_err("%s: unable to remove %s\n", __func__, genpd->name); return -EBUSY; } @@ -1375,8 +1515,9 @@ static int genpd_remove(struct generic_pm_domain *genpd) } list_del(&genpd->gpd_list_node); - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); cancel_work_sync(&genpd->power_off_work); + kfree(genpd->free); pr_debug("%s: removed %s\n", __func__, genpd->name); return 0; @@ -1890,21 +2031,117 @@ int genpd_dev_pm_attach(struct device *dev) mutex_unlock(&gpd_list_lock); if (ret < 0) { - dev_err(dev, "failed to add to PM domain %s: %d", - pd->name, ret); + if (ret != -EPROBE_DEFER) + dev_err(dev, "failed to add to PM domain %s: %d", + pd->name, ret); goto out; } dev->pm_domain->detach = genpd_dev_pm_detach; dev->pm_domain->sync = genpd_dev_pm_sync; - mutex_lock(&pd->lock); + genpd_lock(pd); ret = genpd_poweron(pd, 0); - mutex_unlock(&pd->lock); + genpd_unlock(pd); out: return ret ? -EPROBE_DEFER : 0; } EXPORT_SYMBOL_GPL(genpd_dev_pm_attach); + +static const struct of_device_id idle_state_match[] = { + { .compatible = "domain-idle-state", }, + { } +}; + +static int genpd_parse_state(struct genpd_power_state *genpd_state, + struct device_node *state_node) +{ + int err; + u32 residency; + u32 entry_latency, exit_latency; + const struct of_device_id *match_id; + + match_id = of_match_node(idle_state_match, state_node); + if (!match_id) + return -EINVAL; + + err = of_property_read_u32(state_node, "entry-latency-us", + &entry_latency); + if (err) { + pr_debug(" * %s missing entry-latency-us property\n", + state_node->full_name); + return -EINVAL; + } + + err = of_property_read_u32(state_node, "exit-latency-us", + &exit_latency); + if (err) { + pr_debug(" * %s missing exit-latency-us property\n", + state_node->full_name); + return -EINVAL; + } + + err = of_property_read_u32(state_node, "min-residency-us", &residency); + if (!err) + genpd_state->residency_ns = 1000 * residency; + + genpd_state->power_on_latency_ns = 1000 * exit_latency; + genpd_state->power_off_latency_ns = 1000 * entry_latency; + genpd_state->fwnode = &state_node->fwnode; + + return 0; +} + +/** + * of_genpd_parse_idle_states: Return array of idle states for the genpd. + * + * @dn: The genpd device node + * @states: The pointer to which the state array will be saved. + * @n: The count of elements in the array returned from this function. + * + * Returns the device states parsed from the OF node. The memory for the states + * is allocated by this function and is the responsibility of the caller to + * free the memory after use. + */ +int of_genpd_parse_idle_states(struct device_node *dn, + struct genpd_power_state **states, int *n) +{ + struct genpd_power_state *st; + struct device_node *np; + int i = 0; + int err, ret; + int count; + struct of_phandle_iterator it; + + count = of_count_phandle_with_args(dn, "domain-idle-states", NULL); + if (count <= 0) + return -EINVAL; + + st = kcalloc(count, sizeof(*st), GFP_KERNEL); + if (!st) + return -ENOMEM; + + /* Loop over the phandles until all the requested entry is found */ + of_for_each_phandle(&it, err, dn, "domain-idle-states", NULL, 0) { + np = it.node; + ret = genpd_parse_state(&st[i++], np); + if (ret) { + pr_err + ("Parsing idle state node %s failed with err %d\n", + np->full_name, ret); + of_node_put(np); + kfree(st); + return ret; + } + } + + *n = count; + *states = st; + + return 0; +} +EXPORT_SYMBOL_GPL(of_genpd_parse_idle_states); + #endif /* CONFIG_PM_GENERIC_DOMAINS_OF */ @@ -1958,7 +2195,7 @@ static int pm_genpd_summary_one(struct seq_file *s, char state[16]; int ret; - ret = mutex_lock_interruptible(&genpd->lock); + ret = genpd_lock_interruptible(genpd); if (ret) return -ERESTARTSYS; @@ -1984,7 +2221,9 @@ static int pm_genpd_summary_one(struct seq_file *s, } list_for_each_entry(pm_data, &genpd->dev_list, list_node) { - kobj_path = kobject_get_path(&pm_data->dev->kobj, GFP_KERNEL); + kobj_path = kobject_get_path(&pm_data->dev->kobj, + genpd_is_irq_safe(genpd) ? + GFP_ATOMIC : GFP_KERNEL); if (kobj_path == NULL) continue; @@ -1995,7 +2234,7 @@ static int pm_genpd_summary_one(struct seq_file *s, seq_puts(s, "\n"); exit: - mutex_unlock(&genpd->lock); + genpd_unlock(genpd); return 0; } diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 2932a5bd892f..eb474c882ebe 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1460,10 +1460,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) dpm_watchdog_clear(&wd); Complete: - complete_all(&dev->power.completion); if (error) async_error = error; + complete_all(&dev->power.completion); TRACE_SUSPEND(error); return error; } diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index 4c7c6da7a989..35ff06283738 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -93,6 +93,8 @@ struct opp_table *_find_opp_table(struct device *dev) * Return: voltage in micro volt corresponding to the opp, else * return 0 * + * This is useful only for devices with single power supply. + * * Locking: This function must be called under rcu_read_lock(). opp is a rcu * protected pointer. This means that opp which could have been fetched by * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are @@ -112,7 +114,7 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) if (IS_ERR_OR_NULL(tmp_opp)) pr_err("%s: Invalid parameters\n", __func__); else - v = tmp_opp->u_volt; + v = tmp_opp->supplies[0].u_volt; return v; } @@ -210,6 +212,24 @@ unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) } EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency); +static int _get_regulator_count(struct device *dev) +{ + struct opp_table *opp_table; + int count; + + rcu_read_lock(); + + opp_table = _find_opp_table(dev); + if (!IS_ERR(opp_table)) + count = opp_table->regulator_count; + else + count = 0; + + rcu_read_unlock(); + + return count; +} + /** * dev_pm_opp_get_max_volt_latency() - Get max voltage latency in nanoseconds * @dev: device for which we do this operation @@ -222,34 +242,51 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) { struct opp_table *opp_table; struct dev_pm_opp *opp; - struct regulator *reg; + struct regulator *reg, **regulators; unsigned long latency_ns = 0; - unsigned long min_uV = ~0, max_uV = 0; - int ret; + int ret, i, count; + struct { + unsigned long min; + unsigned long max; + } *uV; + + count = _get_regulator_count(dev); + + /* Regulator may not be required for the device */ + if (!count) + return 0; + + regulators = kmalloc_array(count, sizeof(*regulators), GFP_KERNEL); + if (!regulators) + return 0; + + uV = kmalloc_array(count, sizeof(*uV), GFP_KERNEL); + if (!uV) + goto free_regulators; rcu_read_lock(); opp_table = _find_opp_table(dev); if (IS_ERR(opp_table)) { rcu_read_unlock(); - return 0; + goto free_uV; } - reg = opp_table->regulator; - if (IS_ERR(reg)) { - /* Regulator may not be required for device */ - rcu_read_unlock(); - return 0; - } + memcpy(regulators, opp_table->regulators, count * sizeof(*regulators)); - list_for_each_entry_rcu(opp, &opp_table->opp_list, node) { - if (!opp->available) - continue; + for (i = 0; i < count; i++) { + uV[i].min = ~0; + uV[i].max = 0; + + list_for_each_entry_rcu(opp, &opp_table->opp_list, node) { + if (!opp->available) + continue; - if (opp->u_volt_min < min_uV) - min_uV = opp->u_volt_min; - if (opp->u_volt_max > max_uV) - max_uV = opp->u_volt_max; + if (opp->supplies[i].u_volt_min < uV[i].min) + uV[i].min = opp->supplies[i].u_volt_min; + if (opp->supplies[i].u_volt_max > uV[i].max) + uV[i].max = opp->supplies[i].u_volt_max; + } } rcu_read_unlock(); @@ -258,9 +295,16 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) * The caller needs to ensure that opp_table (and hence the regulator) * isn't freed, while we are executing this routine. */ - ret = regulator_set_voltage_time(reg, min_uV, max_uV); - if (ret > 0) - latency_ns = ret * 1000; + for (i = 0; reg = regulators[i], i < count; i++) { + ret = regulator_set_voltage_time(reg, uV[i].min, uV[i].max); + if (ret > 0) + latency_ns += ret * 1000; + } + +free_uV: + kfree(uV); +free_regulators: + kfree(regulators); return latency_ns; } @@ -542,8 +586,7 @@ unlock: } static int _set_opp_voltage(struct device *dev, struct regulator *reg, - unsigned long u_volt, unsigned long u_volt_min, - unsigned long u_volt_max) + struct dev_pm_opp_supply *supply) { int ret; @@ -554,14 +597,78 @@ static int _set_opp_voltage(struct device *dev, struct regulator *reg, return 0; } - dev_dbg(dev, "%s: voltages (mV): %lu %lu %lu\n", __func__, u_volt_min, - u_volt, u_volt_max); + dev_dbg(dev, "%s: voltages (mV): %lu %lu %lu\n", __func__, + supply->u_volt_min, supply->u_volt, supply->u_volt_max); - ret = regulator_set_voltage_triplet(reg, u_volt_min, u_volt, - u_volt_max); + ret = regulator_set_voltage_triplet(reg, supply->u_volt_min, + supply->u_volt, supply->u_volt_max); if (ret) dev_err(dev, "%s: failed to set voltage (%lu %lu %lu mV): %d\n", - __func__, u_volt_min, u_volt, u_volt_max, ret); + __func__, supply->u_volt_min, supply->u_volt, + supply->u_volt_max, ret); + + return ret; +} + +static inline int +_generic_set_opp_clk_only(struct device *dev, struct clk *clk, + unsigned long old_freq, unsigned long freq) +{ + int ret; + + ret = clk_set_rate(clk, freq); + if (ret) { + dev_err(dev, "%s: failed to set clock rate: %d\n", __func__, + ret); + } + + return ret; +} + +static int _generic_set_opp(struct dev_pm_set_opp_data *data) +{ + struct dev_pm_opp_supply *old_supply = data->old_opp.supplies; + struct dev_pm_opp_supply *new_supply = data->new_opp.supplies; + unsigned long old_freq = data->old_opp.rate, freq = data->new_opp.rate; + struct regulator *reg = data->regulators[0]; + struct device *dev= data->dev; + int ret; + + /* This function only supports single regulator per device */ + if (WARN_ON(data->regulator_count > 1)) { + dev_err(dev, "multiple regulators are not supported\n"); + return -EINVAL; + } + + /* Scaling up? Scale voltage before frequency */ + if (freq > old_freq) { + ret = _set_opp_voltage(dev, reg, new_supply); + if (ret) + goto restore_voltage; + } + + /* Change frequency */ + ret = _generic_set_opp_clk_only(dev, data->clk, old_freq, freq); + if (ret) + goto restore_voltage; + + /* Scaling down? Scale voltage after frequency */ + if (freq < old_freq) { + ret = _set_opp_voltage(dev, reg, new_supply); + if (ret) + goto restore_freq; + } + + return 0; + +restore_freq: + if (_generic_set_opp_clk_only(dev, data->clk, freq, old_freq)) + dev_err(dev, "%s: failed to restore old-freq (%lu Hz)\n", + __func__, old_freq); +restore_voltage: + /* This shouldn't harm even if the voltages weren't updated earlier */ + if (old_supply->u_volt) + _set_opp_voltage(dev, reg, old_supply); return ret; } @@ -579,12 +686,13 @@ static int _set_opp_voltage(struct device *dev, struct regulator *reg, int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { struct opp_table *opp_table; + unsigned long freq, old_freq; + int (*set_opp)(struct dev_pm_set_opp_data *data); struct dev_pm_opp *old_opp, *opp; - struct regulator *reg; + struct regulator **regulators; + struct dev_pm_set_opp_data *data; struct clk *clk; - unsigned long freq, old_freq; - unsigned long u_volt, u_volt_min, u_volt_max; - int ret; + int ret, size; if (unlikely(!target_freq)) { dev_err(dev, "%s: Invalid target frequency %lu\n", __func__, @@ -633,55 +741,41 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) return ret; } - u_volt = opp->u_volt; - u_volt_min = opp->u_volt_min; - u_volt_max = opp->u_volt_max; + dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n", __func__, + old_freq, freq); - reg = opp_table->regulator; + regulators = opp_table->regulators; - rcu_read_unlock(); - - /* Scaling up? Scale voltage before frequency */ - if (freq > old_freq) { - ret = _set_opp_voltage(dev, reg, u_volt, u_volt_min, - u_volt_max); - if (ret) - goto restore_voltage; - } - - /* Change frequency */ - - dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n", - __func__, old_freq, freq); - - ret = clk_set_rate(clk, freq); - if (ret) { - dev_err(dev, "%s: failed to set clock rate: %d\n", __func__, - ret); - goto restore_voltage; + /* Only frequency scaling */ + if (!regulators) { + rcu_read_unlock(); + return _generic_set_opp_clk_only(dev, clk, old_freq, freq); } - /* Scaling down? Scale voltage after frequency */ - if (freq < old_freq) { - ret = _set_opp_voltage(dev, reg, u_volt, u_volt_min, - u_volt_max); - if (ret) - goto restore_freq; - } + if (opp_table->set_opp) + set_opp = opp_table->set_opp; + else + set_opp = _generic_set_opp; + + data = opp_table->set_opp_data; + data->regulators = regulators; + data->regulator_count = opp_table->regulator_count; + data->clk = clk; + data->dev = dev; + + data->old_opp.rate = old_freq; + size = sizeof(*opp->supplies) * opp_table->regulator_count; + if (IS_ERR(old_opp)) + memset(data->old_opp.supplies, 0, size); + else + memcpy(data->old_opp.supplies, old_opp->supplies, size); - return 0; + data->new_opp.rate = freq; + memcpy(data->new_opp.supplies, opp->supplies, size); -restore_freq: - if (clk_set_rate(clk, old_freq)) - dev_err(dev, "%s: failed to restore old-freq (%lu Hz)\n", - __func__, old_freq); -restore_voltage: - /* This shouldn't harm even if the voltages weren't updated earlier */ - if (!IS_ERR(old_opp)) - _set_opp_voltage(dev, reg, old_opp->u_volt, - old_opp->u_volt_min, old_opp->u_volt_max); + rcu_read_unlock(); - return ret; + return set_opp(data); } EXPORT_SYMBOL_GPL(dev_pm_opp_set_rate); @@ -764,9 +858,6 @@ static struct opp_table *_add_opp_table(struct device *dev) _of_init_opp_table(opp_table, dev); - /* Set regulator to a non-NULL error value */ - opp_table->regulator = ERR_PTR(-ENXIO); - /* Find clk for the device */ opp_table->clk = clk_get(dev, NULL); if (IS_ERR(opp_table->clk)) { @@ -815,7 +906,10 @@ static void _remove_opp_table(struct opp_table *opp_table) if (opp_table->prop_name) return; - if (!IS_ERR(opp_table->regulator)) + if (opp_table->regulators) + return; + + if (opp_table->set_opp) return; /* Release clk */ @@ -924,34 +1018,50 @@ struct dev_pm_opp *_allocate_opp(struct device *dev, struct opp_table **opp_table) { struct dev_pm_opp *opp; + int count, supply_size; + struct opp_table *table; - /* allocate new OPP node */ - opp = kzalloc(sizeof(*opp), GFP_KERNEL); - if (!opp) + table = _add_opp_table(dev); + if (!table) return NULL; - INIT_LIST_HEAD(&opp->node); + /* Allocate space for at least one supply */ + count = table->regulator_count ? table->regulator_count : 1; + supply_size = sizeof(*opp->supplies) * count; - *opp_table = _add_opp_table(dev); - if (!*opp_table) { - kfree(opp); + /* allocate new OPP node and supplies structures */ + opp = kzalloc(sizeof(*opp) + supply_size, GFP_KERNEL); + if (!opp) { + kfree(table); return NULL; } + /* Put the supplies at the end of the OPP structure as an empty array */ + opp->supplies = (struct dev_pm_opp_supply *)(opp + 1); + INIT_LIST_HEAD(&opp->node); + + *opp_table = table; + return opp; } static bool _opp_supported_by_regulators(struct dev_pm_opp *opp, struct opp_table *opp_table) { - struct regulator *reg = opp_table->regulator; - - if (!IS_ERR(reg) && - !regulator_is_supported_voltage(reg, opp->u_volt_min, - opp->u_volt_max)) { - pr_warn("%s: OPP minuV: %lu maxuV: %lu, not supported by regulator\n", - __func__, opp->u_volt_min, opp->u_volt_max); - return false; + struct regulator *reg; + int i; + + for (i = 0; i < opp_table->regulator_count; i++) { + reg = opp_table->regulators[i]; + + if (!regulator_is_supported_voltage(reg, + opp->supplies[i].u_volt_min, + opp->supplies[i].u_volt_max)) { + pr_warn("%s: OPP minuV: %lu maxuV: %lu, not supported by regulator\n", + __func__, opp->supplies[i].u_volt_min, + opp->supplies[i].u_volt_max); + return false; + } } return true; @@ -983,11 +1093,13 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, /* Duplicate OPPs */ dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n", - __func__, opp->rate, opp->u_volt, opp->available, - new_opp->rate, new_opp->u_volt, new_opp->available); + __func__, opp->rate, opp->supplies[0].u_volt, + opp->available, new_opp->rate, + new_opp->supplies[0].u_volt, new_opp->available); - return opp->available && new_opp->u_volt == opp->u_volt ? - 0 : -EEXIST; + /* Should we compare voltages for all regulators here ? */ + return opp->available && + new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? 0 : -EEXIST; } new_opp->opp_table = opp_table; @@ -1054,9 +1166,9 @@ int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt, /* populate the opp table */ new_opp->rate = freq; tol = u_volt * opp_table->voltage_tolerance_v1 / 100; - new_opp->u_volt = u_volt; - new_opp->u_volt_min = u_volt - tol; - new_opp->u_volt_max = u_volt + tol; + new_opp->supplies[0].u_volt = u_volt; + new_opp->supplies[0].u_volt_min = u_volt - tol; + new_opp->supplies[0].u_volt_max = u_volt + tol; new_opp->available = true; new_opp->dynamic = dynamic; @@ -1300,13 +1412,47 @@ unlock: } EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name); +static int _allocate_set_opp_data(struct opp_table *opp_table) +{ + struct dev_pm_set_opp_data *data; + int len, count = opp_table->regulator_count; + + if (WARN_ON(!count)) + return -EINVAL; + + /* space for set_opp_data */ + len = sizeof(*data); + + /* space for old_opp.supplies and new_opp.supplies */ + len += 2 * sizeof(struct dev_pm_opp_supply) * count; + + data = kzalloc(len, GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->old_opp.supplies = (void *)(data + 1); + data->new_opp.supplies = data->old_opp.supplies + count; + + opp_table->set_opp_data = data; + + return 0; +} + +static void _free_set_opp_data(struct opp_table *opp_table) +{ + kfree(opp_table->set_opp_data); + opp_table->set_opp_data = NULL; +} + /** - * dev_pm_opp_set_regulator() - Set regulator name for the device + * dev_pm_opp_set_regulators() - Set regulator names for the device * @dev: Device for which regulator name is being set. - * @name: Name of the regulator. + * @names: Array of pointers to the names of the regulator. + * @count: Number of regulators. * * In order to support OPP switching, OPP layer needs to know the name of the - * device's regulator, as the core would be required to switch voltages as well. + * device's regulators, as the core would be required to switch voltages as + * well. * * This must be called before any OPPs are initialized for the device. * @@ -1316,11 +1462,13 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name); * that this function is *NOT* called under RCU protection or in contexts where * mutex cannot be locked. */ -int dev_pm_opp_set_regulator(struct device *dev, const char *name) +struct opp_table *dev_pm_opp_set_regulators(struct device *dev, + const char * const names[], + unsigned int count) { struct opp_table *opp_table; struct regulator *reg; - int ret; + int ret, i; mutex_lock(&opp_table_lock); @@ -1336,22 +1484,146 @@ int dev_pm_opp_set_regulator(struct device *dev, const char *name) goto err; } - /* Already have a regulator set */ - if (WARN_ON(!IS_ERR(opp_table->regulator))) { + /* Already have regulators set */ + if (opp_table->regulators) { ret = -EBUSY; goto err; } - /* Allocate the regulator */ - reg = regulator_get_optional(dev, name); - if (IS_ERR(reg)) { - ret = PTR_ERR(reg); - if (ret != -EPROBE_DEFER) - dev_err(dev, "%s: no regulator (%s) found: %d\n", - __func__, name, ret); + + opp_table->regulators = kmalloc_array(count, + sizeof(*opp_table->regulators), + GFP_KERNEL); + if (!opp_table->regulators) { + ret = -ENOMEM; + goto err; + } + + for (i = 0; i < count; i++) { + reg = regulator_get_optional(dev, names[i]); + if (IS_ERR(reg)) { + ret = PTR_ERR(reg); + if (ret != -EPROBE_DEFER) + dev_err(dev, "%s: no regulator (%s) found: %d\n", + __func__, names[i], ret); + goto free_regulators; + } + + opp_table->regulators[i] = reg; + } + + opp_table->regulator_count = count; + + /* Allocate block only once to pass to set_opp() routines */ + ret = _allocate_set_opp_data(opp_table); + if (ret) + goto free_regulators; + + mutex_unlock(&opp_table_lock); + return opp_table; + +free_regulators: + while (i != 0) + regulator_put(opp_table->regulators[--i]); + + kfree(opp_table->regulators); + opp_table->regulators = NULL; + opp_table->regulator_count = 0; +err: + _remove_opp_table(opp_table); +unlock: + mutex_unlock(&opp_table_lock); + + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulators); + +/** + * dev_pm_opp_put_regulators() - Releases resources blocked for regulator + * @opp_table: OPP table returned from dev_pm_opp_set_regulators(). + * + * Locking: The internal opp_table and opp structures are RCU protected. + * Hence this function internally uses RCU updater strategy with mutex locks + * to keep the integrity of the internal data structures. Callers should ensure + * that this function is *NOT* called under RCU protection or in contexts where + * mutex cannot be locked. + */ +void dev_pm_opp_put_regulators(struct opp_table *opp_table) +{ + int i; + + mutex_lock(&opp_table_lock); + + if (!opp_table->regulators) { + pr_err("%s: Doesn't have regulators set\n", __func__); + goto unlock; + } + + /* Make sure there are no concurrent readers while updating opp_table */ + WARN_ON(!list_empty(&opp_table->opp_list)); + + for (i = opp_table->regulator_count - 1; i >= 0; i--) + regulator_put(opp_table->regulators[i]); + + _free_set_opp_data(opp_table); + + kfree(opp_table->regulators); + opp_table->regulators = NULL; + opp_table->regulator_count = 0; + + /* Try freeing opp_table if this was the last blocking resource */ + _remove_opp_table(opp_table); + +unlock: + mutex_unlock(&opp_table_lock); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators); + +/** + * dev_pm_opp_register_set_opp_helper() - Register custom set OPP helper + * @dev: Device for which the helper is getting registered. + * @set_opp: Custom set OPP helper. + * + * This is useful to support complex platforms (like platforms with multiple + * regulators per device), instead of the generic OPP set rate helper. + * + * This must be called before any OPPs are initialized for the device. + * + * Locking: The internal opp_table and opp structures are RCU protected. + * Hence this function internally uses RCU updater strategy with mutex locks + * to keep the integrity of the internal data structures. Callers should ensure + * that this function is *NOT* called under RCU protection or in contexts where + * mutex cannot be locked. + */ +int dev_pm_opp_register_set_opp_helper(struct device *dev, + int (*set_opp)(struct dev_pm_set_opp_data *data)) +{ + struct opp_table *opp_table; + int ret; + + if (!set_opp) + return -EINVAL; + + mutex_lock(&opp_table_lock); + + opp_table = _add_opp_table(dev); + if (!opp_table) { + ret = -ENOMEM; + goto unlock; + } + + /* This should be called before OPPs are initialized */ + if (WARN_ON(!list_empty(&opp_table->opp_list))) { + ret = -EBUSY; goto err; } - opp_table->regulator = reg; + /* Already have custom set_opp helper */ + if (WARN_ON(opp_table->set_opp)) { + ret = -EBUSY; + goto err; + } + + opp_table->set_opp = set_opp; mutex_unlock(&opp_table_lock); return 0; @@ -1363,11 +1635,12 @@ unlock: return ret; } -EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulator); +EXPORT_SYMBOL_GPL(dev_pm_opp_register_set_opp_helper); /** - * dev_pm_opp_put_regulator() - Releases resources blocked for regulator - * @dev: Device for which regulator was set. + * dev_pm_opp_register_put_opp_helper() - Releases resources blocked for + * set_opp helper + * @dev: Device for which custom set_opp helper has to be cleared. * * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks @@ -1375,7 +1648,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulator); * that this function is *NOT* called under RCU protection or in contexts where * mutex cannot be locked. */ -void dev_pm_opp_put_regulator(struct device *dev) +void dev_pm_opp_register_put_opp_helper(struct device *dev) { struct opp_table *opp_table; @@ -1389,16 +1662,16 @@ void dev_pm_opp_put_regulator(struct device *dev) goto unlock; } - if (IS_ERR(opp_table->regulator)) { - dev_err(dev, "%s: Doesn't have regulator set\n", __func__); + if (!opp_table->set_opp) { + dev_err(dev, "%s: Doesn't have custom set_opp helper set\n", + __func__); goto unlock; } /* Make sure there are no concurrent readers while updating opp_table */ WARN_ON(!list_empty(&opp_table->opp_list)); - regulator_put(opp_table->regulator); - opp_table->regulator = ERR_PTR(-ENXIO); + opp_table->set_opp = NULL; /* Try freeing opp_table if this was the last blocking resource */ _remove_opp_table(opp_table); @@ -1406,7 +1679,7 @@ void dev_pm_opp_put_regulator(struct device *dev) unlock: mutex_unlock(&opp_table_lock); } -EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulator); +EXPORT_SYMBOL_GPL(dev_pm_opp_register_put_opp_helper); /** * dev_pm_opp_add() - Add an OPP table from a table definitions diff --git a/drivers/base/power/opp/debugfs.c b/drivers/base/power/opp/debugfs.c index ef1ae6b52042..95f433db4ac7 100644 --- a/drivers/base/power/opp/debugfs.c +++ b/drivers/base/power/opp/debugfs.c @@ -15,6 +15,7 @@ #include <linux/err.h> #include <linux/init.h> #include <linux/limits.h> +#include <linux/slab.h> #include "opp.h" @@ -34,6 +35,46 @@ void opp_debug_remove_one(struct dev_pm_opp *opp) debugfs_remove_recursive(opp->dentry); } +static bool opp_debug_create_supplies(struct dev_pm_opp *opp, + struct opp_table *opp_table, + struct dentry *pdentry) +{ + struct dentry *d; + int i = 0; + char *name; + + /* Always create at least supply-0 directory */ + do { + name = kasprintf(GFP_KERNEL, "supply-%d", i); + + /* Create per-opp directory */ + d = debugfs_create_dir(name, pdentry); + + kfree(name); + + if (!d) + return false; + + if (!debugfs_create_ulong("u_volt_target", S_IRUGO, d, + &opp->supplies[i].u_volt)) + return false; + + if (!debugfs_create_ulong("u_volt_min", S_IRUGO, d, + &opp->supplies[i].u_volt_min)) + return false; + + if (!debugfs_create_ulong("u_volt_max", S_IRUGO, d, + &opp->supplies[i].u_volt_max)) + return false; + + if (!debugfs_create_ulong("u_amp", S_IRUGO, d, + &opp->supplies[i].u_amp)) + return false; + } while (++i < opp_table->regulator_count); + + return true; +} + int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table) { struct dentry *pdentry = opp_table->dentry; @@ -63,16 +104,7 @@ int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table) if (!debugfs_create_ulong("rate_hz", S_IRUGO, d, &opp->rate)) return -ENOMEM; - if (!debugfs_create_ulong("u_volt_target", S_IRUGO, d, &opp->u_volt)) - return -ENOMEM; - - if (!debugfs_create_ulong("u_volt_min", S_IRUGO, d, &opp->u_volt_min)) - return -ENOMEM; - - if (!debugfs_create_ulong("u_volt_max", S_IRUGO, d, &opp->u_volt_max)) - return -ENOMEM; - - if (!debugfs_create_ulong("u_amp", S_IRUGO, d, &opp->u_amp)) + if (!opp_debug_create_supplies(opp, opp_table, d)) return -ENOMEM; if (!debugfs_create_ulong("clock_latency_ns", S_IRUGO, d, diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c index 5552211e6fcd..3f7d2591b173 100644 --- a/drivers/base/power/opp/of.c +++ b/drivers/base/power/opp/of.c @@ -17,6 +17,7 @@ #include <linux/errno.h> #include <linux/device.h> #include <linux/of.h> +#include <linux/slab.h> #include <linux/export.h> #include "opp.h" @@ -101,16 +102,16 @@ static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table, return true; } -/* TODO: Support multiple regulators */ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev, struct opp_table *opp_table) { - u32 microvolt[3] = {0}; - u32 val; - int count, ret; + u32 *microvolt, *microamp = NULL; + int supplies, vcount, icount, ret, i, j; struct property *prop = NULL; char name[NAME_MAX]; + supplies = opp_table->regulator_count ? opp_table->regulator_count : 1; + /* Search for "opp-microvolt-<name>" */ if (opp_table->prop_name) { snprintf(name, sizeof(name), "opp-microvolt-%s", @@ -128,34 +129,29 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev, return 0; } - count = of_property_count_u32_elems(opp->np, name); - if (count < 0) { + vcount = of_property_count_u32_elems(opp->np, name); + if (vcount < 0) { dev_err(dev, "%s: Invalid %s property (%d)\n", - __func__, name, count); - return count; + __func__, name, vcount); + return vcount; } - /* There can be one or three elements here */ - if (count != 1 && count != 3) { - dev_err(dev, "%s: Invalid number of elements in %s property (%d)\n", - __func__, name, count); + /* There can be one or three elements per supply */ + if (vcount != supplies && vcount != supplies * 3) { + dev_err(dev, "%s: Invalid number of elements in %s property (%d) with supplies (%d)\n", + __func__, name, vcount, supplies); return -EINVAL; } - ret = of_property_read_u32_array(opp->np, name, microvolt, count); + microvolt = kmalloc_array(vcount, sizeof(*microvolt), GFP_KERNEL); + if (!microvolt) + return -ENOMEM; + + ret = of_property_read_u32_array(opp->np, name, microvolt, vcount); if (ret) { dev_err(dev, "%s: error parsing %s: %d\n", __func__, name, ret); - return -EINVAL; - } - - opp->u_volt = microvolt[0]; - - if (count == 1) { - opp->u_volt_min = opp->u_volt; - opp->u_volt_max = opp->u_volt; - } else { - opp->u_volt_min = microvolt[1]; - opp->u_volt_max = microvolt[2]; + ret = -EINVAL; + goto free_microvolt; } /* Search for "opp-microamp-<name>" */ @@ -172,10 +168,59 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev, prop = of_find_property(opp->np, name, NULL); } - if (prop && !of_property_read_u32(opp->np, name, &val)) - opp->u_amp = val; + if (prop) { + icount = of_property_count_u32_elems(opp->np, name); + if (icount < 0) { + dev_err(dev, "%s: Invalid %s property (%d)\n", __func__, + name, icount); + ret = icount; + goto free_microvolt; + } - return 0; + if (icount != supplies) { + dev_err(dev, "%s: Invalid number of elements in %s property (%d) with supplies (%d)\n", + __func__, name, icount, supplies); + ret = -EINVAL; + goto free_microvolt; + } + + microamp = kmalloc_array(icount, sizeof(*microamp), GFP_KERNEL); + if (!microamp) { + ret = -EINVAL; + goto free_microvolt; + } + + ret = of_property_read_u32_array(opp->np, name, microamp, + icount); + if (ret) { + dev_err(dev, "%s: error parsing %s: %d\n", __func__, + name, ret); + ret = -EINVAL; + goto free_microamp; + } + } + + for (i = 0, j = 0; i < supplies; i++) { + opp->supplies[i].u_volt = microvolt[j++]; + + if (vcount == supplies) { + opp->supplies[i].u_volt_min = opp->supplies[i].u_volt; + opp->supplies[i].u_volt_max = opp->supplies[i].u_volt; + } else { + opp->supplies[i].u_volt_min = microvolt[j++]; + opp->supplies[i].u_volt_max = microvolt[j++]; + } + + if (microamp) + opp->supplies[i].u_amp = microamp[i]; + } + +free_microamp: + kfree(microamp); +free_microvolt: + kfree(microvolt); + + return ret; } /** @@ -198,7 +243,7 @@ void dev_pm_opp_of_remove_table(struct device *dev) EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table); /* Returns opp descriptor node for a device, caller must do of_node_put() */ -struct device_node *_of_get_opp_desc_node(struct device *dev) +static struct device_node *_of_get_opp_desc_node(struct device *dev) { /* * TODO: Support for multiple OPP tables. @@ -303,9 +348,9 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np) mutex_unlock(&opp_table_lock); pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu\n", - __func__, new_opp->turbo, new_opp->rate, new_opp->u_volt, - new_opp->u_volt_min, new_opp->u_volt_max, - new_opp->clock_latency_ns); + __func__, new_opp->turbo, new_opp->rate, + new_opp->supplies[0].u_volt, new_opp->supplies[0].u_volt_min, + new_opp->supplies[0].u_volt_max, new_opp->clock_latency_ns); /* * Notify the changes in the availability of the operable @@ -562,7 +607,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, /* Get OPP descriptor node */ np = _of_get_opp_desc_node(cpu_dev); if (!np) { - dev_dbg(cpu_dev, "%s: Couldn't find cpu_dev node.\n", __func__); + dev_dbg(cpu_dev, "%s: Couldn't find opp node.\n", __func__); return -ENOENT; } @@ -587,7 +632,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, /* Get OPP descriptor node */ tmp_np = _of_get_opp_desc_node(tcpu_dev); if (!tmp_np) { - dev_err(tcpu_dev, "%s: Couldn't find tcpu_dev node.\n", + dev_err(tcpu_dev, "%s: Couldn't find opp node.\n", __func__); ret = -ENOENT; goto put_cpu_node; diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h index fabd5ca1a083..af9f2b849a66 100644 --- a/drivers/base/power/opp/opp.h +++ b/drivers/base/power/opp/opp.h @@ -61,10 +61,7 @@ extern struct list_head opp_tables; * @turbo: true if turbo (boost) OPP * @suspend: true if suspend OPP * @rate: Frequency in hertz - * @u_volt: Target voltage in microvolts corresponding to this OPP - * @u_volt_min: Minimum voltage in microvolts corresponding to this OPP - * @u_volt_max: Maximum voltage in microvolts corresponding to this OPP - * @u_amp: Maximum current drawn by the device in microamperes + * @supplies: Power supplies voltage/current values * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's * frequency from any other OPP's frequency. * @opp_table: points back to the opp_table struct this opp belongs to @@ -83,10 +80,8 @@ struct dev_pm_opp { bool suspend; unsigned long rate; - unsigned long u_volt; - unsigned long u_volt_min; - unsigned long u_volt_max; - unsigned long u_amp; + struct dev_pm_opp_supply *supplies; + unsigned long clock_latency_ns; struct opp_table *opp_table; @@ -144,7 +139,10 @@ enum opp_table_access { * @supported_hw_count: Number of elements in supported_hw array. * @prop_name: A name to postfix to many DT properties, while parsing them. * @clk: Device's clock handle - * @regulator: Supply regulator + * @regulators: Supply regulators + * @regulator_count: Number of power supply regulators + * @set_opp: Platform specific set_opp callback + * @set_opp_data: Data to be passed to set_opp callback * @dentry: debugfs dentry pointer of the real device directory (not links). * @dentry_name: Name of the real dentry. * @@ -179,7 +177,11 @@ struct opp_table { unsigned int supported_hw_count; const char *prop_name; struct clk *clk; - struct regulator *regulator; + struct regulator **regulators; + unsigned int regulator_count; + + int (*set_opp)(struct dev_pm_set_opp_data *data); + struct dev_pm_set_opp_data *set_opp_data; #ifdef CONFIG_DEBUG_FS struct dentry *dentry; @@ -190,7 +192,6 @@ struct opp_table { /* Routines internal to opp core */ struct opp_table *_find_opp_table(struct device *dev); struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table); -struct device_node *_of_get_opp_desc_node(struct device *dev); void _dev_pm_opp_remove_table(struct device *dev, bool remove_all); struct dev_pm_opp *_allocate_opp(struct device *dev, struct opp_table **opp_table); int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table); diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h index 50e30e7b059d..a84332aefc2d 100644 --- a/drivers/base/power/power.h +++ b/drivers/base/power/power.h @@ -21,14 +21,22 @@ extern void pm_runtime_init(struct device *dev); extern void pm_runtime_reinit(struct device *dev); extern void pm_runtime_remove(struct device *dev); +#define WAKE_IRQ_DEDICATED_ALLOCATED BIT(0) +#define WAKE_IRQ_DEDICATED_MANAGED BIT(1) +#define WAKE_IRQ_DEDICATED_MASK (WAKE_IRQ_DEDICATED_ALLOCATED | \ + WAKE_IRQ_DEDICATED_MANAGED) + struct wake_irq { struct device *dev; + unsigned int status; int irq; - bool dedicated_irq:1; }; extern void dev_pm_arm_wake_irq(struct wake_irq *wirq); extern void dev_pm_disarm_wake_irq(struct wake_irq *wirq); +extern void dev_pm_enable_wake_irq_check(struct device *dev, + bool can_change_status); +extern void dev_pm_disable_wake_irq_check(struct device *dev); #ifdef CONFIG_PM_SLEEP @@ -104,6 +112,15 @@ static inline void dev_pm_disarm_wake_irq(struct wake_irq *wirq) { } +static inline void dev_pm_enable_wake_irq_check(struct device *dev, + bool can_change_status) +{ +} + +static inline void dev_pm_disable_wake_irq_check(struct device *dev) +{ +} + #endif #ifdef CONFIG_PM_SLEEP diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c index 7f3646e459cb..58fcc758334e 100644 --- a/drivers/base/power/qos.c +++ b/drivers/base/power/qos.c @@ -856,7 +856,10 @@ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val) struct dev_pm_qos_request *req; if (val < 0) { - ret = -EINVAL; + if (val == PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT) + ret = 0; + else + ret = -EINVAL; goto out; } req = kzalloc(sizeof(*req), GFP_KERNEL); @@ -883,6 +886,7 @@ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val) mutex_unlock(&dev_pm_qos_mtx); return ret; } +EXPORT_SYMBOL_GPL(dev_pm_qos_update_user_latency_tolerance); /** * dev_pm_qos_expose_latency_tolerance - Expose latency tolerance to userspace diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 82a081ea4317..26856d050037 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -241,7 +241,8 @@ static int rpm_check_suspend_allowed(struct device *dev) retval = -EACCES; else if (atomic_read(&dev->power.usage_count) > 0) retval = -EAGAIN; - else if (!pm_children_suspended(dev)) + else if (!dev->power.ignore_children && + atomic_read(&dev->power.child_count)) retval = -EBUSY; /* Pending resume requests take precedence over suspends. */ @@ -515,7 +516,7 @@ static int rpm_suspend(struct device *dev, int rpmflags) callback = RPM_GET_CALLBACK(dev, runtime_suspend); - dev_pm_enable_wake_irq(dev); + dev_pm_enable_wake_irq_check(dev, true); retval = rpm_callback(callback, dev); if (retval) goto fail; @@ -554,7 +555,7 @@ static int rpm_suspend(struct device *dev, int rpmflags) return retval; fail: - dev_pm_disable_wake_irq(dev); + dev_pm_disable_wake_irq_check(dev); __update_runtime_status(dev, RPM_ACTIVE); dev->power.deferred_resume = false; wake_up_all(&dev->power.wait_queue); @@ -712,8 +713,8 @@ static int rpm_resume(struct device *dev, int rpmflags) spin_lock(&parent->power.lock); /* - * We can resume if the parent's runtime PM is disabled or it - * is set to ignore children. + * Resume the parent if it has runtime PM enabled and not been + * set to ignore its children. */ if (!parent->power.disable_depth && !parent->power.ignore_children) { @@ -737,12 +738,12 @@ static int rpm_resume(struct device *dev, int rpmflags) callback = RPM_GET_CALLBACK(dev, runtime_resume); - dev_pm_disable_wake_irq(dev); + dev_pm_disable_wake_irq_check(dev); retval = rpm_callback(callback, dev); if (retval) { __update_runtime_status(dev, RPM_SUSPENDED); pm_runtime_cancel_pending(dev); - dev_pm_enable_wake_irq(dev); + dev_pm_enable_wake_irq_check(dev, false); } else { no_callback: __update_runtime_status(dev, RPM_ACTIVE); @@ -1027,7 +1028,17 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) goto out_set; if (status == RPM_SUSPENDED) { - /* It always is possible to set the status to 'suspended'. */ + /* + * It is invalid to suspend a device with an active child, + * unless it has been set to ignore its children. + */ + if (!dev->power.ignore_children && + atomic_read(&dev->power.child_count)) { + dev_err(dev, "runtime PM trying to suspend device but active child\n"); + error = -EBUSY; + goto out; + } + if (parent) { atomic_add_unless(&parent->power.child_count, -1, 0); notify_parent = !parent->power.ignore_children; @@ -1478,6 +1489,16 @@ int pm_runtime_force_suspend(struct device *dev) if (ret) goto err; + /* + * Increase the runtime PM usage count for the device's parent, in case + * when we find the device being used when system suspend was invoked. + * This informs pm_runtime_force_resume() to resume the parent + * immediately, which is needed to be able to resume its children, + * when not deferring the resume to be managed via runtime PM. + */ + if (dev->parent && atomic_read(&dev->power.usage_count) > 1) + pm_runtime_get_noresume(dev->parent); + pm_runtime_set_suspended(dev); return 0; err: @@ -1487,16 +1508,20 @@ err: EXPORT_SYMBOL_GPL(pm_runtime_force_suspend); /** - * pm_runtime_force_resume - Force a device into resume state. + * pm_runtime_force_resume - Force a device into resume state if needed. * @dev: Device to resume. * * Prior invoking this function we expect the user to have brought the device * into low power state by a call to pm_runtime_force_suspend(). Here we reverse - * those actions and brings the device into full power. We update the runtime PM - * status and re-enables runtime PM. + * those actions and brings the device into full power, if it is expected to be + * used on system resume. To distinguish that, we check whether the runtime PM + * usage count is greater than 1 (the PM core increases the usage count in the + * system PM prepare phase), as that indicates a real user (such as a subsystem, + * driver, userspace, etc.) is using it. If that is the case, the device is + * expected to be used on system resume as well, so then we resume it. In the + * other case, we defer the resume to be managed via runtime PM. * - * Typically this function may be invoked from a system resume callback to make - * sure the device is put into full power state. + * Typically this function may be invoked from a system resume callback. */ int pm_runtime_force_resume(struct device *dev) { @@ -1513,6 +1538,17 @@ int pm_runtime_force_resume(struct device *dev) if (!pm_runtime_status_suspended(dev)) goto out; + /* + * Decrease the parent's runtime PM usage count, if we increased it + * during system suspend in pm_runtime_force_suspend(). + */ + if (atomic_read(&dev->power.usage_count) > 1) { + if (dev->parent) + pm_runtime_put_noidle(dev->parent); + } else { + goto out; + } + ret = pm_runtime_set_active(dev); if (ret) goto out; diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index a7b46798c81d..33b4b902741a 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -263,7 +263,11 @@ static ssize_t pm_qos_latency_tolerance_store(struct device *dev, s32 value; int ret; - if (kstrtos32(buf, 0, &value)) { + if (kstrtos32(buf, 0, &value) == 0) { + /* Users can't write negative values directly */ + if (value < 0) + return -EINVAL; + } else { if (!strcmp(buf, "auto") || !strcmp(buf, "auto\n")) value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; else if (!strcmp(buf, "any") || !strcmp(buf, "any\n")) diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index 0d77cd6fd8d1..404d94c6c8bc 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -110,8 +110,10 @@ void dev_pm_clear_wake_irq(struct device *dev) dev->power.wakeirq = NULL; spin_unlock_irqrestore(&dev->power.lock, flags); - if (wirq->dedicated_irq) + if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED) { free_irq(wirq->irq, wirq); + wirq->status &= ~WAKE_IRQ_DEDICATED_MASK; + } kfree(wirq); } EXPORT_SYMBOL_GPL(dev_pm_clear_wake_irq); @@ -179,7 +181,6 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) wirq->dev = dev; wirq->irq = irq; - wirq->dedicated_irq = true; irq_set_status_flags(irq, IRQ_NOAUTOEN); /* @@ -195,6 +196,8 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) if (err) goto err_free_irq; + wirq->status = WAKE_IRQ_DEDICATED_ALLOCATED; + return err; err_free_irq: @@ -210,9 +213,9 @@ EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq); * dev_pm_enable_wake_irq - Enable device wake-up interrupt * @dev: Device * - * Called from the bus code or the device driver for - * runtime_suspend() to enable the wake-up interrupt while - * the device is running. + * Optionally called from the bus code or the device driver for + * runtime_resume() to override the PM runtime core managed wake-up + * interrupt handling to enable the wake-up interrupt. * * Note that for runtime_suspend()) the wake-up interrupts * should be unconditionally enabled unlike for suspend() @@ -222,7 +225,7 @@ void dev_pm_enable_wake_irq(struct device *dev) { struct wake_irq *wirq = dev->power.wakeirq; - if (wirq && wirq->dedicated_irq) + if (wirq && (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED)) enable_irq(wirq->irq); } EXPORT_SYMBOL_GPL(dev_pm_enable_wake_irq); @@ -231,20 +234,73 @@ EXPORT_SYMBOL_GPL(dev_pm_enable_wake_irq); * dev_pm_disable_wake_irq - Disable device wake-up interrupt * @dev: Device * - * Called from the bus code or the device driver for - * runtime_resume() to disable the wake-up interrupt while - * the device is running. + * Optionally called from the bus code or the device driver for + * runtime_suspend() to override the PM runtime core managed wake-up + * interrupt handling to disable the wake-up interrupt. */ void dev_pm_disable_wake_irq(struct device *dev) { struct wake_irq *wirq = dev->power.wakeirq; - if (wirq && wirq->dedicated_irq) + if (wirq && (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED)) disable_irq_nosync(wirq->irq); } EXPORT_SYMBOL_GPL(dev_pm_disable_wake_irq); /** + * dev_pm_enable_wake_irq_check - Checks and enables wake-up interrupt + * @dev: Device + * @can_change_status: Can change wake-up interrupt status + * + * Enables wakeirq conditionally. We need to enable wake-up interrupt + * lazily on the first rpm_suspend(). This is needed as the consumer device + * starts in RPM_SUSPENDED state, and the the first pm_runtime_get() would + * otherwise try to disable already disabled wakeirq. The wake-up interrupt + * starts disabled with IRQ_NOAUTOEN set. + * + * Should be only called from rpm_suspend() and rpm_resume() path. + * Caller must hold &dev->power.lock to change wirq->status + */ +void dev_pm_enable_wake_irq_check(struct device *dev, + bool can_change_status) +{ + struct wake_irq *wirq = dev->power.wakeirq; + + if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK))) + return; + + if (likely(wirq->status & WAKE_IRQ_DEDICATED_MANAGED)) { + goto enable; + } else if (can_change_status) { + wirq->status |= WAKE_IRQ_DEDICATED_MANAGED; + goto enable; + } + + return; + +enable: + enable_irq(wirq->irq); +} + +/** + * dev_pm_disable_wake_irq_check - Checks and disables wake-up interrupt + * @dev: Device + * + * Disables wake-up interrupt conditionally based on status. + * Should be only called from rpm_suspend() and rpm_resume() path. + */ +void dev_pm_disable_wake_irq_check(struct device *dev) +{ + struct wake_irq *wirq = dev->power.wakeirq; + + if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK))) + return; + + if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED) + disable_irq_nosync(wirq->irq); +} + +/** * dev_pm_arm_wake_irq - Arm device wake-up * @wirq: Device wake-up interrupt * diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 5163c8f918cb..5497f7fc44d0 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1413,8 +1413,14 @@ static ssize_t hot_remove_store(struct class *class, return ret ? ret : count; } +/* + * NOTE: hot_add attribute is not the usual read-only sysfs attribute. In a + * sense that reading from this file does alter the state of your system -- it + * creates a new un-initialized zram device and returns back this device's + * device_id (or an error code if it fails to create a new device). + */ static struct class_attribute zram_control_class_attrs[] = { - __ATTR_RO(hot_add), + __ATTR(hot_add, 0400, hot_add_show, NULL), __ATTR_WO(hot_remove), __ATTR_NULL, }; diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index d89b8afe23b6..920c469f3953 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -12,6 +12,27 @@ config ARM_BIG_LITTLE_CPUFREQ help This enables the Generic CPUfreq driver for ARM big.LITTLE platforms. +config ARM_BRCMSTB_AVS_CPUFREQ + tristate "Broadcom STB AVS CPUfreq driver" + depends on ARCH_BRCMSTB || COMPILE_TEST + default y + help + Some Broadcom STB SoCs use a co-processor running proprietary firmware + ("AVS") to handle voltage and frequency scaling. This driver provides + a standard CPUfreq interface to to the firmware. + + Say Y, if you have a Broadcom SoC with AVS support for DFS or DVFS. + +config ARM_BRCMSTB_AVS_CPUFREQ_DEBUG + bool "Broadcom STB AVS CPUfreq driver sysfs debug capability" + depends on ARM_BRCMSTB_AVS_CPUFREQ + help + Enabling this option turns on debug support via sysfs under + /sys/kernel/debug/brcmstb-avs-cpufreq. It is possible to read all and + write some AVS mailbox registers through sysfs entries. + + If in doubt, say N. + config ARM_DT_BL_CPUFREQ tristate "Generic probing via DT for ARM big LITTLE CPUfreq driver" depends on ARM_BIG_LITTLE_CPUFREQ && OF @@ -60,14 +81,6 @@ config ARM_IMX6Q_CPUFREQ If in doubt, say N. -config ARM_INTEGRATOR - tristate "CPUfreq driver for ARM Integrator CPUs" - depends on ARCH_INTEGRATOR - default y - help - This enables the CPUfreq driver for ARM Integrator CPUs. - If in doubt, say Y. - config ARM_KIRKWOOD_CPUFREQ def_bool MACH_KIRKWOOD help diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index 0a9b6a093646..1e46c3918e7a 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -51,12 +51,12 @@ obj-$(CONFIG_ARM_BIG_LITTLE_CPUFREQ) += arm_big_little.o # LITTLE drivers, so that it is probed last. obj-$(CONFIG_ARM_DT_BL_CPUFREQ) += arm_big_little_dt.o +obj-$(CONFIG_ARM_BRCMSTB_AVS_CPUFREQ) += brcmstb-avs-cpufreq.o obj-$(CONFIG_ARCH_DAVINCI) += davinci-cpufreq.o obj-$(CONFIG_UX500_SOC_DB8500) += dbx500-cpufreq.o obj-$(CONFIG_ARM_EXYNOS5440_CPUFREQ) += exynos5440-cpufreq.o obj-$(CONFIG_ARM_HIGHBANK_CPUFREQ) += highbank-cpufreq.o obj-$(CONFIG_ARM_IMX6Q_CPUFREQ) += imx6q-cpufreq.o -obj-$(CONFIG_ARM_INTEGRATOR) += integrator-cpufreq.o obj-$(CONFIG_ARM_KIRKWOOD_CPUFREQ) += kirkwood-cpufreq.o obj-$(CONFIG_ARM_MT8173_CPUFREQ) += mt8173-cpufreq.o obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ) += omap-cpufreq.o diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 297e9128fe9f..3a98702b7445 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -84,7 +84,6 @@ static inline struct acpi_processor_performance *to_perf_data(struct acpi_cpufre static struct cpufreq_driver acpi_cpufreq_driver; static unsigned int acpi_pstate_strict; -static struct msr __percpu *msrs; static bool boost_state(unsigned int cpu) { @@ -104,11 +103,10 @@ static bool boost_state(unsigned int cpu) return false; } -static void boost_set_msrs(bool enable, const struct cpumask *cpumask) +static int boost_set_msr(bool enable) { - u32 cpu; u32 msr_addr; - u64 msr_mask; + u64 msr_mask, val; switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_INTEL: @@ -120,26 +118,31 @@ static void boost_set_msrs(bool enable, const struct cpumask *cpumask) msr_mask = MSR_K7_HWCR_CPB_DIS; break; default: - return; + return -EINVAL; } - rdmsr_on_cpus(cpumask, msr_addr, msrs); + rdmsrl(msr_addr, val); - for_each_cpu(cpu, cpumask) { - struct msr *reg = per_cpu_ptr(msrs, cpu); - if (enable) - reg->q &= ~msr_mask; - else - reg->q |= msr_mask; - } + if (enable) + val &= ~msr_mask; + else + val |= msr_mask; + + wrmsrl(msr_addr, val); + return 0; +} + +static void boost_set_msr_each(void *p_en) +{ + bool enable = (bool) p_en; - wrmsr_on_cpus(cpumask, msr_addr, msrs); + boost_set_msr(enable); } static int set_boost(int val) { get_online_cpus(); - boost_set_msrs(val, cpu_online_mask); + on_each_cpu(boost_set_msr_each, (void *)(long)val, 1); put_online_cpus(); pr_debug("Core Boosting %sabled.\n", val ? "en" : "dis"); @@ -536,46 +539,24 @@ static void free_acpi_perf_data(void) free_percpu(acpi_perf_data); } -static int boost_notify(struct notifier_block *nb, unsigned long action, - void *hcpu) +static int cpufreq_boost_online(unsigned int cpu) { - unsigned cpu = (long)hcpu; - const struct cpumask *cpumask; - - cpumask = get_cpu_mask(cpu); + /* + * On the CPU_UP path we simply keep the boost-disable flag + * in sync with the current global state. + */ + return boost_set_msr(acpi_cpufreq_driver.boost_enabled); +} +static int cpufreq_boost_down_prep(unsigned int cpu) +{ /* * Clear the boost-disable bit on the CPU_DOWN path so that - * this cpu cannot block the remaining ones from boosting. On - * the CPU_UP path we simply keep the boost-disable flag in - * sync with the current global state. + * this cpu cannot block the remaining ones from boosting. */ - - switch (action) { - case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - boost_set_msrs(acpi_cpufreq_driver.boost_enabled, cpumask); - break; - - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - boost_set_msrs(1, cpumask); - break; - - default: - break; - } - - return NOTIFY_OK; + return boost_set_msr(1); } - -static struct notifier_block boost_nb = { - .notifier_call = boost_notify, -}; - /* * acpi_cpufreq_early_init - initialize ACPI P-States library * @@ -922,37 +903,35 @@ static struct cpufreq_driver acpi_cpufreq_driver = { .attr = acpi_cpufreq_attr, }; +static enum cpuhp_state acpi_cpufreq_online; + static void __init acpi_cpufreq_boost_init(void) { - if (boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)) { - msrs = msrs_alloc(); - - if (!msrs) - return; - - acpi_cpufreq_driver.set_boost = set_boost; - acpi_cpufreq_driver.boost_enabled = boost_state(0); - - cpu_notifier_register_begin(); + int ret; - /* Force all MSRs to the same value */ - boost_set_msrs(acpi_cpufreq_driver.boost_enabled, - cpu_online_mask); + if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA))) + return; - __register_cpu_notifier(&boost_nb); + acpi_cpufreq_driver.set_boost = set_boost; + acpi_cpufreq_driver.boost_enabled = boost_state(0); - cpu_notifier_register_done(); + /* + * This calls the online callback on all online cpu and forces all + * MSRs to the same value. + */ + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "cpufreq/acpi:online", + cpufreq_boost_online, cpufreq_boost_down_prep); + if (ret < 0) { + pr_err("acpi_cpufreq: failed to register hotplug callbacks\n"); + return; } + acpi_cpufreq_online = ret; } static void acpi_cpufreq_boost_exit(void) { - if (msrs) { - unregister_cpu_notifier(&boost_nb); - - msrs_free(msrs); - msrs = NULL; - } + if (acpi_cpufreq_online >= 0) + cpuhp_remove_state_nocalls(acpi_cpufreq_online); } static int __init acpi_cpufreq_init(void) diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c new file mode 100644 index 000000000000..4fda623e55bb --- /dev/null +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -0,0 +1,1057 @@ +/* + * CPU frequency scaling for Broadcom SoCs with AVS firmware that + * supports DVS or DVFS + * + * Copyright (c) 2016 Broadcom + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +/* + * "AVS" is the name of a firmware developed at Broadcom. It derives + * its name from the technique called "Adaptive Voltage Scaling". + * Adaptive voltage scaling was the original purpose of this firmware. + * The AVS firmware still supports "AVS mode", where all it does is + * adaptive voltage scaling. However, on some newer Broadcom SoCs, the + * AVS Firmware, despite its unchanged name, also supports DFS mode and + * DVFS mode. + * + * In the context of this document and the related driver, "AVS" by + * itself always means the Broadcom firmware and never refers to the + * technique called "Adaptive Voltage Scaling". + * + * The Broadcom STB AVS CPUfreq driver provides voltage and frequency + * scaling on Broadcom SoCs using AVS firmware with support for DFS and + * DVFS. The AVS firmware is running on its own co-processor. The + * driver supports both uniprocessor (UP) and symmetric multiprocessor + * (SMP) systems which share clock and voltage across all CPUs. + * + * Actual voltage and frequency scaling is done solely by the AVS + * firmware. This driver does not change frequency or voltage itself. + * It provides a standard CPUfreq interface to the rest of the kernel + * and to userland. It interfaces with the AVS firmware to effect the + * requested changes and to report back the current system status in a + * way that is expected by existing tools. + */ + +#include <linux/cpufreq.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/platform_device.h> +#include <linux/semaphore.h> + +#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG +#include <linux/ctype.h> +#include <linux/debugfs.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#endif + +/* Max number of arguments AVS calls take */ +#define AVS_MAX_CMD_ARGS 4 +/* + * This macro is used to generate AVS parameter register offsets. For + * x >= AVS_MAX_CMD_ARGS, it returns 0 to protect against accidental memory + * access outside of the parameter range. (Offset 0 is the first parameter.) + */ +#define AVS_PARAM_MULT(x) ((x) < AVS_MAX_CMD_ARGS ? (x) : 0) + +/* AVS Mailbox Register offsets */ +#define AVS_MBOX_COMMAND 0x00 +#define AVS_MBOX_STATUS 0x04 +#define AVS_MBOX_VOLTAGE0 0x08 +#define AVS_MBOX_TEMP0 0x0c +#define AVS_MBOX_PV0 0x10 +#define AVS_MBOX_MV0 0x14 +#define AVS_MBOX_PARAM(x) (0x18 + AVS_PARAM_MULT(x) * sizeof(u32)) +#define AVS_MBOX_REVISION 0x28 +#define AVS_MBOX_PSTATE 0x2c +#define AVS_MBOX_HEARTBEAT 0x30 +#define AVS_MBOX_MAGIC 0x34 +#define AVS_MBOX_SIGMA_HVT 0x38 +#define AVS_MBOX_SIGMA_SVT 0x3c +#define AVS_MBOX_VOLTAGE1 0x40 +#define AVS_MBOX_TEMP1 0x44 +#define AVS_MBOX_PV1 0x48 +#define AVS_MBOX_MV1 0x4c +#define AVS_MBOX_FREQUENCY 0x50 + +/* AVS Commands */ +#define AVS_CMD_AVAILABLE 0x00 +#define AVS_CMD_DISABLE 0x10 +#define AVS_CMD_ENABLE 0x11 +#define AVS_CMD_S2_ENTER 0x12 +#define AVS_CMD_S2_EXIT 0x13 +#define AVS_CMD_BBM_ENTER 0x14 +#define AVS_CMD_BBM_EXIT 0x15 +#define AVS_CMD_S3_ENTER 0x16 +#define AVS_CMD_S3_EXIT 0x17 +#define AVS_CMD_BALANCE 0x18 +/* PMAP and P-STATE commands */ +#define AVS_CMD_GET_PMAP 0x30 +#define AVS_CMD_SET_PMAP 0x31 +#define AVS_CMD_GET_PSTATE 0x40 +#define AVS_CMD_SET_PSTATE 0x41 + +/* Different modes AVS supports (for GET_PMAP/SET_PMAP) */ +#define AVS_MODE_AVS 0x0 +#define AVS_MODE_DFS 0x1 +#define AVS_MODE_DVS 0x2 +#define AVS_MODE_DVFS 0x3 + +/* + * PMAP parameter p1 + * unused:31-24, mdiv_p0:23-16, unused:15-14, pdiv:13-10 , ndiv_int:9-0 + */ +#define NDIV_INT_SHIFT 0 +#define NDIV_INT_MASK 0x3ff +#define PDIV_SHIFT 10 +#define PDIV_MASK 0xf +#define MDIV_P0_SHIFT 16 +#define MDIV_P0_MASK 0xff +/* + * PMAP parameter p2 + * mdiv_p4:31-24, mdiv_p3:23-16, mdiv_p2:15:8, mdiv_p1:7:0 + */ +#define MDIV_P1_SHIFT 0 +#define MDIV_P1_MASK 0xff +#define MDIV_P2_SHIFT 8 +#define MDIV_P2_MASK 0xff +#define MDIV_P3_SHIFT 16 +#define MDIV_P3_MASK 0xff +#define MDIV_P4_SHIFT 24 +#define MDIV_P4_MASK 0xff + +/* Different P-STATES AVS supports (for GET_PSTATE/SET_PSTATE) */ +#define AVS_PSTATE_P0 0x0 +#define AVS_PSTATE_P1 0x1 +#define AVS_PSTATE_P2 0x2 +#define AVS_PSTATE_P3 0x3 +#define AVS_PSTATE_P4 0x4 +#define AVS_PSTATE_MAX AVS_PSTATE_P4 + +/* CPU L2 Interrupt Controller Registers */ +#define AVS_CPU_L2_SET0 0x04 +#define AVS_CPU_L2_INT_MASK BIT(31) + +/* AVS Command Status Values */ +#define AVS_STATUS_CLEAR 0x00 +/* Command/notification accepted */ +#define AVS_STATUS_SUCCESS 0xf0 +/* Command/notification rejected */ +#define AVS_STATUS_FAILURE 0xff +/* Invalid command/notification (unknown) */ +#define AVS_STATUS_INVALID 0xf1 +/* Non-AVS modes are not supported */ +#define AVS_STATUS_NO_SUPP 0xf2 +/* Cannot set P-State until P-Map supplied */ +#define AVS_STATUS_NO_MAP 0xf3 +/* Cannot change P-Map after initial P-Map set */ +#define AVS_STATUS_MAP_SET 0xf4 +/* Max AVS status; higher numbers are used for debugging */ +#define AVS_STATUS_MAX 0xff + +/* Other AVS related constants */ +#define AVS_LOOP_LIMIT 10000 +#define AVS_TIMEOUT 300 /* in ms; expected completion is < 10ms */ +#define AVS_FIRMWARE_MAGIC 0xa11600d1 + +#define BRCM_AVS_CPUFREQ_PREFIX "brcmstb-avs" +#define BRCM_AVS_CPUFREQ_NAME BRCM_AVS_CPUFREQ_PREFIX "-cpufreq" +#define BRCM_AVS_CPU_DATA "brcm,avs-cpu-data-mem" +#define BRCM_AVS_CPU_INTR "brcm,avs-cpu-l2-intr" +#define BRCM_AVS_HOST_INTR "sw_intr" + +struct pmap { + unsigned int mode; + unsigned int p1; + unsigned int p2; + unsigned int state; +}; + +struct private_data { + void __iomem *base; + void __iomem *avs_intr_base; + struct device *dev; +#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG + struct dentry *debugfs; +#endif + struct completion done; + struct semaphore sem; + struct pmap pmap; +}; + +#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG + +enum debugfs_format { + DEBUGFS_NORMAL, + DEBUGFS_FLOAT, + DEBUGFS_REV, +}; + +struct debugfs_data { + struct debugfs_entry *entry; + struct private_data *priv; +}; + +struct debugfs_entry { + char *name; + u32 offset; + fmode_t mode; + enum debugfs_format format; +}; + +#define DEBUGFS_ENTRY(name, mode, format) { \ + #name, AVS_MBOX_##name, mode, format \ +} + +/* + * These are used for debugfs only. Otherwise we use AVS_MBOX_PARAM() directly. + */ +#define AVS_MBOX_PARAM1 AVS_MBOX_PARAM(0) +#define AVS_MBOX_PARAM2 AVS_MBOX_PARAM(1) +#define AVS_MBOX_PARAM3 AVS_MBOX_PARAM(2) +#define AVS_MBOX_PARAM4 AVS_MBOX_PARAM(3) + +/* + * This table stores the name, access permissions and offset for each hardware + * register and is used to generate debugfs entries. + */ +static struct debugfs_entry debugfs_entries[] = { + DEBUGFS_ENTRY(COMMAND, S_IWUSR, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(STATUS, S_IWUSR, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(VOLTAGE0, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(TEMP0, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(PV0, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(MV0, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(PARAM1, S_IWUSR, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(PARAM2, S_IWUSR, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(PARAM3, S_IWUSR, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(PARAM4, S_IWUSR, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(REVISION, 0, DEBUGFS_REV), + DEBUGFS_ENTRY(PSTATE, 0, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(HEARTBEAT, 0, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(MAGIC, S_IWUSR, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(SIGMA_HVT, 0, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(SIGMA_SVT, 0, DEBUGFS_NORMAL), + DEBUGFS_ENTRY(VOLTAGE1, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(TEMP1, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(PV1, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(MV1, 0, DEBUGFS_FLOAT), + DEBUGFS_ENTRY(FREQUENCY, 0, DEBUGFS_NORMAL), +}; + +static int brcm_avs_target_index(struct cpufreq_policy *, unsigned int); + +static char *__strtolower(char *s) +{ + char *p; + + for (p = s; *p; p++) + *p = tolower(*p); + + return s; +} + +#endif /* CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG */ + +static void __iomem *__map_region(const char *name) +{ + struct device_node *np; + void __iomem *ptr; + + np = of_find_compatible_node(NULL, NULL, name); + if (!np) + return NULL; + + ptr = of_iomap(np, 0); + of_node_put(np); + + return ptr; +} + +static int __issue_avs_command(struct private_data *priv, int cmd, bool is_send, + u32 args[]) +{ + unsigned long time_left = msecs_to_jiffies(AVS_TIMEOUT); + void __iomem *base = priv->base; + unsigned int i; + int ret; + u32 val; + + ret = down_interruptible(&priv->sem); + if (ret) + return ret; + + /* + * Make sure no other command is currently running: cmd is 0 if AVS + * co-processor is idle. Due to the guard above, we should almost never + * have to wait here. + */ + for (i = 0, val = 1; val != 0 && i < AVS_LOOP_LIMIT; i++) + val = readl(base + AVS_MBOX_COMMAND); + + /* Give the caller a chance to retry if AVS is busy. */ + if (i == AVS_LOOP_LIMIT) { + ret = -EAGAIN; + goto out; + } + + /* Clear status before we begin. */ + writel(AVS_STATUS_CLEAR, base + AVS_MBOX_STATUS); + + /* We need to send arguments for this command. */ + if (args && is_send) { + for (i = 0; i < AVS_MAX_CMD_ARGS; i++) + writel(args[i], base + AVS_MBOX_PARAM(i)); + } + + /* Protect from spurious interrupts. */ + reinit_completion(&priv->done); + + /* Now issue the command & tell firmware to wake up to process it. */ + writel(cmd, base + AVS_MBOX_COMMAND); + writel(AVS_CPU_L2_INT_MASK, priv->avs_intr_base + AVS_CPU_L2_SET0); + + /* Wait for AVS co-processor to finish processing the command. */ + time_left = wait_for_completion_timeout(&priv->done, time_left); + + /* + * If the AVS status is not in the expected range, it means AVS didn't + * complete our command in time, and we return an error. Also, if there + * is no "time left", we timed out waiting for the interrupt. + */ + val = readl(base + AVS_MBOX_STATUS); + if (time_left == 0 || val == 0 || val > AVS_STATUS_MAX) { + dev_err(priv->dev, "AVS command %#x didn't complete in time\n", + cmd); + dev_err(priv->dev, " Time left: %u ms, AVS status: %#x\n", + jiffies_to_msecs(time_left), val); + ret = -ETIMEDOUT; + goto out; + } + + /* This command returned arguments, so we read them back. */ + if (args && !is_send) { + for (i = 0; i < AVS_MAX_CMD_ARGS; i++) + args[i] = readl(base + AVS_MBOX_PARAM(i)); + } + + /* Clear status to tell AVS co-processor we are done. */ + writel(AVS_STATUS_CLEAR, base + AVS_MBOX_STATUS); + + /* Convert firmware errors to errno's as much as possible. */ + switch (val) { + case AVS_STATUS_INVALID: + ret = -EINVAL; + break; + case AVS_STATUS_NO_SUPP: + ret = -ENOTSUPP; + break; + case AVS_STATUS_NO_MAP: + ret = -ENOENT; + break; + case AVS_STATUS_MAP_SET: + ret = -EEXIST; + break; + case AVS_STATUS_FAILURE: + ret = -EIO; + break; + } + +out: + up(&priv->sem); + + return ret; +} + +static irqreturn_t irq_handler(int irq, void *data) +{ + struct private_data *priv = data; + + /* AVS command completed execution. Wake up __issue_avs_command(). */ + complete(&priv->done); + + return IRQ_HANDLED; +} + +static char *brcm_avs_mode_to_string(unsigned int mode) +{ + switch (mode) { + case AVS_MODE_AVS: + return "AVS"; + case AVS_MODE_DFS: + return "DFS"; + case AVS_MODE_DVS: + return "DVS"; + case AVS_MODE_DVFS: + return "DVFS"; + } + return NULL; +} + +static void brcm_avs_parse_p1(u32 p1, unsigned int *mdiv_p0, unsigned int *pdiv, + unsigned int *ndiv) +{ + *mdiv_p0 = (p1 >> MDIV_P0_SHIFT) & MDIV_P0_MASK; + *pdiv = (p1 >> PDIV_SHIFT) & PDIV_MASK; + *ndiv = (p1 >> NDIV_INT_SHIFT) & NDIV_INT_MASK; +} + +static void brcm_avs_parse_p2(u32 p2, unsigned int *mdiv_p1, + unsigned int *mdiv_p2, unsigned int *mdiv_p3, + unsigned int *mdiv_p4) +{ + *mdiv_p4 = (p2 >> MDIV_P4_SHIFT) & MDIV_P4_MASK; + *mdiv_p3 = (p2 >> MDIV_P3_SHIFT) & MDIV_P3_MASK; + *mdiv_p2 = (p2 >> MDIV_P2_SHIFT) & MDIV_P2_MASK; + *mdiv_p1 = (p2 >> MDIV_P1_SHIFT) & MDIV_P1_MASK; +} + +static int brcm_avs_get_pmap(struct private_data *priv, struct pmap *pmap) +{ + u32 args[AVS_MAX_CMD_ARGS]; + int ret; + + ret = __issue_avs_command(priv, AVS_CMD_GET_PMAP, false, args); + if (ret || !pmap) + return ret; + + pmap->mode = args[0]; + pmap->p1 = args[1]; + pmap->p2 = args[2]; + pmap->state = args[3]; + + return 0; +} + +static int brcm_avs_set_pmap(struct private_data *priv, struct pmap *pmap) +{ + u32 args[AVS_MAX_CMD_ARGS]; + + args[0] = pmap->mode; + args[1] = pmap->p1; + args[2] = pmap->p2; + args[3] = pmap->state; + + return __issue_avs_command(priv, AVS_CMD_SET_PMAP, true, args); +} + +static int brcm_avs_get_pstate(struct private_data *priv, unsigned int *pstate) +{ + u32 args[AVS_MAX_CMD_ARGS]; + int ret; + + ret = __issue_avs_command(priv, AVS_CMD_GET_PSTATE, false, args); + if (ret) + return ret; + *pstate = args[0]; + + return 0; +} + +static int brcm_avs_set_pstate(struct private_data *priv, unsigned int pstate) +{ + u32 args[AVS_MAX_CMD_ARGS]; + + args[0] = pstate; + + return __issue_avs_command(priv, AVS_CMD_SET_PSTATE, true, args); +} + +static unsigned long brcm_avs_get_voltage(void __iomem *base) +{ + return readl(base + AVS_MBOX_VOLTAGE1); +} + +static unsigned long brcm_avs_get_frequency(void __iomem *base) +{ + return readl(base + AVS_MBOX_FREQUENCY) * 1000; /* in kHz */ +} + +/* + * We determine which frequencies are supported by cycling through all P-states + * and reading back what frequency we are running at for each P-state. + */ +static struct cpufreq_frequency_table * +brcm_avs_get_freq_table(struct device *dev, struct private_data *priv) +{ + struct cpufreq_frequency_table *table; + unsigned int pstate; + int i, ret; + + /* Remember P-state for later */ + ret = brcm_avs_get_pstate(priv, &pstate); + if (ret) + return ERR_PTR(ret); + + table = devm_kzalloc(dev, (AVS_PSTATE_MAX + 1) * sizeof(*table), + GFP_KERNEL); + if (!table) + return ERR_PTR(-ENOMEM); + + for (i = AVS_PSTATE_P0; i <= AVS_PSTATE_MAX; i++) { + ret = brcm_avs_set_pstate(priv, i); + if (ret) + return ERR_PTR(ret); + table[i].frequency = brcm_avs_get_frequency(priv->base); + table[i].driver_data = i; + } + table[i].frequency = CPUFREQ_TABLE_END; + + /* Restore P-state */ + ret = brcm_avs_set_pstate(priv, pstate); + if (ret) + return ERR_PTR(ret); + + return table; +} + +#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG + +#define MANT(x) (unsigned int)(abs((x)) / 1000) +#define FRAC(x) (unsigned int)(abs((x)) - abs((x)) / 1000 * 1000) + +static int brcm_avs_debug_show(struct seq_file *s, void *data) +{ + struct debugfs_data *dbgfs = s->private; + void __iomem *base; + u32 val, offset; + + if (!dbgfs) { + seq_puts(s, "No device pointer\n"); + return 0; + } + + base = dbgfs->priv->base; + offset = dbgfs->entry->offset; + val = readl(base + offset); + switch (dbgfs->entry->format) { + case DEBUGFS_NORMAL: + seq_printf(s, "%u\n", val); + break; + case DEBUGFS_FLOAT: + seq_printf(s, "%d.%03d\n", MANT(val), FRAC(val)); + break; + case DEBUGFS_REV: + seq_printf(s, "%c.%c.%c.%c\n", (val >> 24 & 0xff), + (val >> 16 & 0xff), (val >> 8 & 0xff), + val & 0xff); + break; + } + seq_printf(s, "0x%08x\n", val); + + return 0; +} + +#undef MANT +#undef FRAC + +static ssize_t brcm_avs_seq_write(struct file *file, const char __user *buf, + size_t size, loff_t *ppos) +{ + struct seq_file *s = file->private_data; + struct debugfs_data *dbgfs = s->private; + struct private_data *priv = dbgfs->priv; + void __iomem *base, *avs_intr_base; + bool use_issue_command = false; + unsigned long val, offset; + char str[128]; + int ret; + char *str_ptr = str; + + if (size >= sizeof(str)) + return -E2BIG; + + memset(str, 0, sizeof(str)); + ret = copy_from_user(str, buf, size); + if (ret) + return ret; + + base = priv->base; + avs_intr_base = priv->avs_intr_base; + offset = dbgfs->entry->offset; + /* + * Special case writing to "command" entry only: if the string starts + * with a 'c', we use the driver's __issue_avs_command() function. + * Otherwise, we perform a raw write. This should allow testing of raw + * access as well as using the higher level function. (Raw access + * doesn't clear the firmware return status after issuing the command.) + */ + if (str_ptr[0] == 'c' && offset == AVS_MBOX_COMMAND) { + use_issue_command = true; + str_ptr++; + } + if (kstrtoul(str_ptr, 0, &val) != 0) + return -EINVAL; + + /* + * Setting the P-state is a special case. We need to update the CPU + * frequency we report. + */ + if (val == AVS_CMD_SET_PSTATE) { + struct cpufreq_policy *policy; + unsigned int pstate; + + policy = cpufreq_cpu_get(smp_processor_id()); + /* Read back the P-state we are about to set */ + pstate = readl(base + AVS_MBOX_PARAM(0)); + if (use_issue_command) { + ret = brcm_avs_target_index(policy, pstate); + return ret ? ret : size; + } + policy->cur = policy->freq_table[pstate].frequency; + } + + if (use_issue_command) { + ret = __issue_avs_command(priv, val, false, NULL); + } else { + /* Locking here is not perfect, but is only for debug. */ + ret = down_interruptible(&priv->sem); + if (ret) + return ret; + + writel(val, base + offset); + /* We have to wake up the firmware to process a command. */ + if (offset == AVS_MBOX_COMMAND) + writel(AVS_CPU_L2_INT_MASK, + avs_intr_base + AVS_CPU_L2_SET0); + up(&priv->sem); + } + + return ret ? ret : size; +} + +static struct debugfs_entry *__find_debugfs_entry(const char *name) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(debugfs_entries); i++) + if (strcasecmp(debugfs_entries[i].name, name) == 0) + return &debugfs_entries[i]; + + return NULL; +} + +static int brcm_avs_debug_open(struct inode *inode, struct file *file) +{ + struct debugfs_data *data; + fmode_t fmode; + int ret; + + /* + * seq_open(), which is called by single_open(), clears "write" access. + * We need write access to some files, so we preserve our access mode + * and restore it. + */ + fmode = file->f_mode; + /* + * Check access permissions even for root. We don't want to be writing + * to read-only registers. Access for regular users has already been + * checked by the VFS layer. + */ + if ((fmode & FMODE_WRITER) && !(inode->i_mode & S_IWUSR)) + return -EACCES; + + data = kmalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + /* + * We use the same file system operations for all our debug files. To + * produce specific output, we look up the file name upon opening a + * debugfs entry and map it to a memory offset. This offset is then used + * in the generic "show" function to read a specific register. + */ + data->entry = __find_debugfs_entry(file->f_path.dentry->d_iname); + data->priv = inode->i_private; + + ret = single_open(file, brcm_avs_debug_show, data); + if (ret) + kfree(data); + file->f_mode = fmode; + + return ret; +} + +static int brcm_avs_debug_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq_priv = file->private_data; + struct debugfs_data *data = seq_priv->private; + + kfree(data); + return single_release(inode, file); +} + +static const struct file_operations brcm_avs_debug_ops = { + .open = brcm_avs_debug_open, + .read = seq_read, + .write = brcm_avs_seq_write, + .llseek = seq_lseek, + .release = brcm_avs_debug_release, +}; + +static void brcm_avs_cpufreq_debug_init(struct platform_device *pdev) +{ + struct private_data *priv = platform_get_drvdata(pdev); + struct dentry *dir; + int i; + + if (!priv) + return; + + dir = debugfs_create_dir(BRCM_AVS_CPUFREQ_NAME, NULL); + if (IS_ERR_OR_NULL(dir)) + return; + priv->debugfs = dir; + + for (i = 0; i < ARRAY_SIZE(debugfs_entries); i++) { + /* + * The DEBUGFS_ENTRY macro generates uppercase strings. We + * convert them to lowercase before creating the debugfs + * entries. + */ + char *entry = __strtolower(debugfs_entries[i].name); + fmode_t mode = debugfs_entries[i].mode; + + if (!debugfs_create_file(entry, S_IFREG | S_IRUGO | mode, + dir, priv, &brcm_avs_debug_ops)) { + priv->debugfs = NULL; + debugfs_remove_recursive(dir); + break; + } + } +} + +static void brcm_avs_cpufreq_debug_exit(struct platform_device *pdev) +{ + struct private_data *priv = platform_get_drvdata(pdev); + + if (priv && priv->debugfs) { + debugfs_remove_recursive(priv->debugfs); + priv->debugfs = NULL; + } +} + +#else + +static void brcm_avs_cpufreq_debug_init(struct platform_device *pdev) {} +static void brcm_avs_cpufreq_debug_exit(struct platform_device *pdev) {} + +#endif /* CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG */ + +/* + * To ensure the right firmware is running we need to + * - check the MAGIC matches what we expect + * - brcm_avs_get_pmap() doesn't return -ENOTSUPP or -EINVAL + * We need to set up our interrupt handling before calling brcm_avs_get_pmap()! + */ +static bool brcm_avs_is_firmware_loaded(struct private_data *priv) +{ + u32 magic; + int rc; + + rc = brcm_avs_get_pmap(priv, NULL); + magic = readl(priv->base + AVS_MBOX_MAGIC); + + return (magic == AVS_FIRMWARE_MAGIC) && (rc != -ENOTSUPP) && + (rc != -EINVAL); +} + +static unsigned int brcm_avs_cpufreq_get(unsigned int cpu) +{ + struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); + struct private_data *priv = policy->driver_data; + + return brcm_avs_get_frequency(priv->base); +} + +static int brcm_avs_target_index(struct cpufreq_policy *policy, + unsigned int index) +{ + return brcm_avs_set_pstate(policy->driver_data, + policy->freq_table[index].driver_data); +} + +static int brcm_avs_suspend(struct cpufreq_policy *policy) +{ + struct private_data *priv = policy->driver_data; + + return brcm_avs_get_pmap(priv, &priv->pmap); +} + +static int brcm_avs_resume(struct cpufreq_policy *policy) +{ + struct private_data *priv = policy->driver_data; + int ret; + + ret = brcm_avs_set_pmap(priv, &priv->pmap); + if (ret == -EEXIST) { + struct platform_device *pdev = cpufreq_get_driver_data(); + struct device *dev = &pdev->dev; + + dev_warn(dev, "PMAP was already set\n"); + ret = 0; + } + + return ret; +} + +/* + * All initialization code that we only want to execute once goes here. Setup + * code that can be re-tried on every core (if it failed before) can go into + * brcm_avs_cpufreq_init(). + */ +static int brcm_avs_prepare_init(struct platform_device *pdev) +{ + struct private_data *priv; + struct device *dev; + int host_irq, ret; + + dev = &pdev->dev; + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->dev = dev; + sema_init(&priv->sem, 1); + init_completion(&priv->done); + platform_set_drvdata(pdev, priv); + + priv->base = __map_region(BRCM_AVS_CPU_DATA); + if (!priv->base) { + dev_err(dev, "Couldn't find property %s in device tree.\n", + BRCM_AVS_CPU_DATA); + return -ENOENT; + } + + priv->avs_intr_base = __map_region(BRCM_AVS_CPU_INTR); + if (!priv->avs_intr_base) { + dev_err(dev, "Couldn't find property %s in device tree.\n", + BRCM_AVS_CPU_INTR); + ret = -ENOENT; + goto unmap_base; + } + + host_irq = platform_get_irq_byname(pdev, BRCM_AVS_HOST_INTR); + if (host_irq < 0) { + dev_err(dev, "Couldn't find interrupt %s -- %d\n", + BRCM_AVS_HOST_INTR, host_irq); + ret = host_irq; + goto unmap_intr_base; + } + + ret = devm_request_irq(dev, host_irq, irq_handler, IRQF_TRIGGER_RISING, + BRCM_AVS_HOST_INTR, priv); + if (ret) { + dev_err(dev, "IRQ request failed: %s (%d) -- %d\n", + BRCM_AVS_HOST_INTR, host_irq, ret); + goto unmap_intr_base; + } + + if (brcm_avs_is_firmware_loaded(priv)) + return 0; + + dev_err(dev, "AVS firmware is not loaded or doesn't support DVFS\n"); + ret = -ENODEV; + +unmap_intr_base: + iounmap(priv->avs_intr_base); +unmap_base: + iounmap(priv->base); + platform_set_drvdata(pdev, NULL); + + return ret; +} + +static int brcm_avs_cpufreq_init(struct cpufreq_policy *policy) +{ + struct cpufreq_frequency_table *freq_table; + struct platform_device *pdev; + struct private_data *priv; + struct device *dev; + int ret; + + pdev = cpufreq_get_driver_data(); + priv = platform_get_drvdata(pdev); + policy->driver_data = priv; + dev = &pdev->dev; + + freq_table = brcm_avs_get_freq_table(dev, priv); + if (IS_ERR(freq_table)) { + ret = PTR_ERR(freq_table); + dev_err(dev, "Couldn't determine frequency table (%d).\n", ret); + return ret; + } + + ret = cpufreq_table_validate_and_show(policy, freq_table); + if (ret) { + dev_err(dev, "invalid frequency table: %d\n", ret); + return ret; + } + + /* All cores share the same clock and thus the same policy. */ + cpumask_setall(policy->cpus); + + ret = __issue_avs_command(priv, AVS_CMD_ENABLE, false, NULL); + if (!ret) { + unsigned int pstate; + + ret = brcm_avs_get_pstate(priv, &pstate); + if (!ret) { + policy->cur = freq_table[pstate].frequency; + dev_info(dev, "registered\n"); + return 0; + } + } + + dev_err(dev, "couldn't initialize driver (%d)\n", ret); + + return ret; +} + +static ssize_t show_brcm_avs_pstate(struct cpufreq_policy *policy, char *buf) +{ + struct private_data *priv = policy->driver_data; + unsigned int pstate; + + if (brcm_avs_get_pstate(priv, &pstate)) + return sprintf(buf, "<unknown>\n"); + + return sprintf(buf, "%u\n", pstate); +} + +static ssize_t show_brcm_avs_mode(struct cpufreq_policy *policy, char *buf) +{ + struct private_data *priv = policy->driver_data; + struct pmap pmap; + + if (brcm_avs_get_pmap(priv, &pmap)) + return sprintf(buf, "<unknown>\n"); + + return sprintf(buf, "%s %u\n", brcm_avs_mode_to_string(pmap.mode), + pmap.mode); +} + +static ssize_t show_brcm_avs_pmap(struct cpufreq_policy *policy, char *buf) +{ + unsigned int mdiv_p0, mdiv_p1, mdiv_p2, mdiv_p3, mdiv_p4; + struct private_data *priv = policy->driver_data; + unsigned int ndiv, pdiv; + struct pmap pmap; + + if (brcm_avs_get_pmap(priv, &pmap)) + return sprintf(buf, "<unknown>\n"); + + brcm_avs_parse_p1(pmap.p1, &mdiv_p0, &pdiv, &ndiv); + brcm_avs_parse_p2(pmap.p2, &mdiv_p1, &mdiv_p2, &mdiv_p3, &mdiv_p4); + + return sprintf(buf, "0x%08x 0x%08x %u %u %u %u %u %u %u\n", + pmap.p1, pmap.p2, ndiv, pdiv, mdiv_p0, mdiv_p1, mdiv_p2, + mdiv_p3, mdiv_p4); +} + +static ssize_t show_brcm_avs_voltage(struct cpufreq_policy *policy, char *buf) +{ + struct private_data *priv = policy->driver_data; + + return sprintf(buf, "0x%08lx\n", brcm_avs_get_voltage(priv->base)); +} + +static ssize_t show_brcm_avs_frequency(struct cpufreq_policy *policy, char *buf) +{ + struct private_data *priv = policy->driver_data; + + return sprintf(buf, "0x%08lx\n", brcm_avs_get_frequency(priv->base)); +} + +cpufreq_freq_attr_ro(brcm_avs_pstate); +cpufreq_freq_attr_ro(brcm_avs_mode); +cpufreq_freq_attr_ro(brcm_avs_pmap); +cpufreq_freq_attr_ro(brcm_avs_voltage); +cpufreq_freq_attr_ro(brcm_avs_frequency); + +static struct freq_attr *brcm_avs_cpufreq_attr[] = { + &cpufreq_freq_attr_scaling_available_freqs, + &brcm_avs_pstate, + &brcm_avs_mode, + &brcm_avs_pmap, + &brcm_avs_voltage, + &brcm_avs_frequency, + NULL +}; + +static struct cpufreq_driver brcm_avs_driver = { + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .verify = cpufreq_generic_frequency_table_verify, + .target_index = brcm_avs_target_index, + .get = brcm_avs_cpufreq_get, + .suspend = brcm_avs_suspend, + .resume = brcm_avs_resume, + .init = brcm_avs_cpufreq_init, + .attr = brcm_avs_cpufreq_attr, + .name = BRCM_AVS_CPUFREQ_PREFIX, +}; + +static int brcm_avs_cpufreq_probe(struct platform_device *pdev) +{ + int ret; + + ret = brcm_avs_prepare_init(pdev); + if (ret) + return ret; + + brcm_avs_driver.driver_data = pdev; + ret = cpufreq_register_driver(&brcm_avs_driver); + if (!ret) + brcm_avs_cpufreq_debug_init(pdev); + + return ret; +} + +static int brcm_avs_cpufreq_remove(struct platform_device *pdev) +{ + struct private_data *priv; + int ret; + + ret = cpufreq_unregister_driver(&brcm_avs_driver); + if (ret) + return ret; + + brcm_avs_cpufreq_debug_exit(pdev); + + priv = platform_get_drvdata(pdev); + iounmap(priv->base); + iounmap(priv->avs_intr_base); + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static const struct of_device_id brcm_avs_cpufreq_match[] = { + { .compatible = BRCM_AVS_CPU_DATA }, + { } +}; +MODULE_DEVICE_TABLE(of, brcm_avs_cpufreq_match); + +static struct platform_driver brcm_avs_cpufreq_platdrv = { + .driver = { + .name = BRCM_AVS_CPUFREQ_NAME, + .of_match_table = brcm_avs_cpufreq_match, + }, + .probe = brcm_avs_cpufreq_probe, + .remove = brcm_avs_cpufreq_remove, +}; +module_platform_driver(brcm_avs_cpufreq_platdrv); + +MODULE_AUTHOR("Markus Mayer <[email protected]>"); +MODULE_DESCRIPTION("CPUfreq driver for Broadcom STB AVS"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 4852d9efe74e..e82bb3c30b92 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -247,3 +247,10 @@ MODULE_DESCRIPTION("CPUFreq driver based on the ACPI CPPC v5.0+ spec"); MODULE_LICENSE("GPL"); late_initcall(cppc_cpufreq_init); + +static const struct acpi_device_id cppc_acpi_ids[] = { + {ACPI_PROCESSOR_DEVICE_HID, }, + {} +}; + +MODULE_DEVICE_TABLE(acpi, cppc_acpi_ids); diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 71267626456b..bc97b6a4b1cf 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -26,6 +26,9 @@ static const struct of_device_id machines[] __initconst = { { .compatible = "allwinner,sun8i-a83t", }, { .compatible = "allwinner,sun8i-h3", }, + { .compatible = "arm,integrator-ap", }, + { .compatible = "arm,integrator-cp", }, + { .compatible = "hisilicon,hi6220", }, { .compatible = "fsl,imx27", }, @@ -34,6 +37,8 @@ static const struct of_device_id machines[] __initconst = { { .compatible = "fsl,imx7d", }, { .compatible = "marvell,berlin", }, + { .compatible = "marvell,pxa250", }, + { .compatible = "marvell,pxa270", }, { .compatible = "samsung,exynos3250", }, { .compatible = "samsung,exynos4210", }, @@ -50,6 +55,8 @@ static const struct of_device_id machines[] __initconst = { { .compatible = "renesas,r7s72100", }, { .compatible = "renesas,r8a73a4", }, { .compatible = "renesas,r8a7740", }, + { .compatible = "renesas,r8a7743", }, + { .compatible = "renesas,r8a7745", }, { .compatible = "renesas,r8a7778", }, { .compatible = "renesas,r8a7779", }, { .compatible = "renesas,r8a7790", }, @@ -72,6 +79,12 @@ static const struct of_device_id machines[] __initconst = { { .compatible = "sigma,tango4" }, + { .compatible = "socionext,uniphier-pro5", }, + { .compatible = "socionext,uniphier-pxs2", }, + { .compatible = "socionext,uniphier-ld6b", }, + { .compatible = "socionext,uniphier-ld11", }, + { .compatible = "socionext,uniphier-ld20", }, + { .compatible = "ti,am33xx", }, { .compatible = "ti,dra7", }, { .compatible = "ti,omap2", }, @@ -81,6 +94,8 @@ static const struct of_device_id machines[] __initconst = { { .compatible = "xlnx,zynq-7000", }, + { .compatible = "zte,zx296718", }, + { } }; diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index 5c07ae05d69a..269013311e79 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -28,6 +28,7 @@ #include "cpufreq-dt.h" struct private_data { + struct opp_table *opp_table; struct device *cpu_dev; struct thermal_cooling_device *cdev; const char *reg_name; @@ -143,6 +144,7 @@ static int resources_available(void) static int cpufreq_init(struct cpufreq_policy *policy) { struct cpufreq_frequency_table *freq_table; + struct opp_table *opp_table = NULL; struct private_data *priv; struct device *cpu_dev; struct clk *cpu_clk; @@ -186,8 +188,9 @@ static int cpufreq_init(struct cpufreq_policy *policy) */ name = find_supply_name(cpu_dev); if (name) { - ret = dev_pm_opp_set_regulator(cpu_dev, name); - if (ret) { + opp_table = dev_pm_opp_set_regulators(cpu_dev, &name, 1); + if (IS_ERR(opp_table)) { + ret = PTR_ERR(opp_table); dev_err(cpu_dev, "Failed to set regulator for cpu%d: %d\n", policy->cpu, ret); goto out_put_clk; @@ -237,6 +240,7 @@ static int cpufreq_init(struct cpufreq_policy *policy) } priv->reg_name = name; + priv->opp_table = opp_table; ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table); if (ret) { @@ -285,7 +289,7 @@ out_free_priv: out_free_opp: dev_pm_opp_of_cpumask_remove_table(policy->cpus); if (name) - dev_pm_opp_put_regulator(cpu_dev); + dev_pm_opp_put_regulators(opp_table); out_put_clk: clk_put(cpu_clk); @@ -300,7 +304,7 @@ static int cpufreq_exit(struct cpufreq_policy *policy) dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); dev_pm_opp_of_cpumask_remove_table(policy->related_cpus); if (priv->reg_name) - dev_pm_opp_put_regulator(priv->cpu_dev); + dev_pm_opp_put_regulators(priv->opp_table); clk_put(policy->clk); kfree(priv); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 6e6c1fb60fbc..cc475eff90b3 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1526,7 +1526,10 @@ unsigned int cpufreq_get(unsigned int cpu) if (policy) { down_read(&policy->rwsem); - ret_freq = __cpufreq_get(policy); + + if (!policy_is_inactive(policy)) + ret_freq = __cpufreq_get(policy); + up_read(&policy->rwsem); cpufreq_cpu_put(policy); @@ -2254,17 +2257,19 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, * Useful for policy notifiers which have different necessities * at different times. */ -int cpufreq_update_policy(unsigned int cpu) +void cpufreq_update_policy(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); struct cpufreq_policy new_policy; - int ret; if (!policy) - return -ENODEV; + return; down_write(&policy->rwsem); + if (policy_is_inactive(policy)) + goto unlock; + pr_debug("updating policy for CPU %u\n", cpu); memcpy(&new_policy, policy, sizeof(*policy)); new_policy.min = policy->user_policy.min; @@ -2275,24 +2280,20 @@ int cpufreq_update_policy(unsigned int cpu) * -> ask driver for current freq and notify governors about a change */ if (cpufreq_driver->get && !cpufreq_driver->setpolicy) { - if (cpufreq_suspended) { - ret = -EAGAIN; + if (cpufreq_suspended) goto unlock; - } + new_policy.cur = cpufreq_update_current_freq(policy); - if (WARN_ON(!new_policy.cur)) { - ret = -EIO; + if (WARN_ON(!new_policy.cur)) goto unlock; - } } - ret = cpufreq_set_policy(policy, &new_policy); + cpufreq_set_policy(policy, &new_policy); unlock: up_write(&policy->rwsem); cpufreq_cpu_put(policy); - return ret; } EXPORT_SYMBOL(cpufreq_update_policy); diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index 13475890d792..992f7c20760f 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -37,16 +37,16 @@ struct cs_dbs_tuners { #define DEF_SAMPLING_DOWN_FACTOR (1) #define MAX_SAMPLING_DOWN_FACTOR (10) -static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners, - struct cpufreq_policy *policy) +static inline unsigned int get_freq_step(struct cs_dbs_tuners *cs_tuners, + struct cpufreq_policy *policy) { - unsigned int freq_target = (cs_tuners->freq_step * policy->max) / 100; + unsigned int freq_step = (cs_tuners->freq_step * policy->max) / 100; /* max freq cannot be less than 100. But who knows... */ - if (unlikely(freq_target == 0)) - freq_target = DEF_FREQUENCY_STEP; + if (unlikely(freq_step == 0)) + freq_step = DEF_FREQUENCY_STEP; - return freq_target; + return freq_step; } /* @@ -55,10 +55,10 @@ static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners, * sampling_down_factor, we check, if current idle time is more than 80% * (default), then we try to decrease frequency * - * Any frequency increase takes it to the maximum frequency. Frequency reduction - * happens at minimum steps of 5% (default) of maximum frequency + * Frequency updates happen at minimum steps of 5% (default) of maximum + * frequency */ -static unsigned int cs_dbs_timer(struct cpufreq_policy *policy) +static unsigned int cs_dbs_update(struct cpufreq_policy *policy) { struct policy_dbs_info *policy_dbs = policy->governor_data; struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs); @@ -66,6 +66,7 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy) struct dbs_data *dbs_data = policy_dbs->dbs_data; struct cs_dbs_tuners *cs_tuners = dbs_data->tuners; unsigned int load = dbs_update(policy); + unsigned int freq_step; /* * break out if we 'cannot' reduce the speed as the user might @@ -82,6 +83,23 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy) if (requested_freq > policy->max || requested_freq < policy->min) requested_freq = policy->cur; + freq_step = get_freq_step(cs_tuners, policy); + + /* + * Decrease requested_freq one freq_step for each idle period that + * we didn't update the frequency. + */ + if (policy_dbs->idle_periods < UINT_MAX) { + unsigned int freq_steps = policy_dbs->idle_periods * freq_step; + + if (requested_freq > freq_steps) + requested_freq -= freq_steps; + else + requested_freq = policy->min; + + policy_dbs->idle_periods = UINT_MAX; + } + /* Check for frequency increase */ if (load > dbs_data->up_threshold) { dbs_info->down_skip = 0; @@ -90,7 +108,7 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy) if (requested_freq == policy->max) goto out; - requested_freq += get_freq_target(cs_tuners, policy); + requested_freq += freq_step; if (requested_freq > policy->max) requested_freq = policy->max; @@ -106,16 +124,14 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy) /* Check for frequency decrease */ if (load < cs_tuners->down_threshold) { - unsigned int freq_target; /* * if we cannot reduce the frequency anymore, break out early */ if (requested_freq == policy->min) goto out; - freq_target = get_freq_target(cs_tuners, policy); - if (requested_freq > freq_target) - requested_freq -= freq_target; + if (requested_freq > freq_step) + requested_freq -= freq_step; else requested_freq = policy->min; @@ -305,7 +321,7 @@ static void cs_start(struct cpufreq_policy *policy) static struct dbs_governor cs_governor = { .gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("conservative"), .kobj_type = { .default_attrs = cs_attributes }, - .gov_dbs_timer = cs_dbs_timer, + .gov_dbs_update = cs_dbs_update, .alloc = cs_alloc, .free = cs_free, .init = cs_init, diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index 642dd0f183a8..0196467280bd 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -61,7 +61,7 @@ ssize_t store_sampling_rate(struct gov_attr_set *attr_set, const char *buf, * entries can't be freed concurrently. */ list_for_each_entry(policy_dbs, &attr_set->policy_list, list) { - mutex_lock(&policy_dbs->timer_mutex); + mutex_lock(&policy_dbs->update_mutex); /* * On 32-bit architectures this may race with the * sample_delay_ns read in dbs_update_util_handler(), but that @@ -76,7 +76,7 @@ ssize_t store_sampling_rate(struct gov_attr_set *attr_set, const char *buf, * taken, so it shouldn't be significant. */ gov_update_sample_delay(policy_dbs, 0); - mutex_unlock(&policy_dbs->timer_mutex); + mutex_unlock(&policy_dbs->update_mutex); } return count; @@ -117,7 +117,7 @@ unsigned int dbs_update(struct cpufreq_policy *policy) struct policy_dbs_info *policy_dbs = policy->governor_data; struct dbs_data *dbs_data = policy_dbs->dbs_data; unsigned int ignore_nice = dbs_data->ignore_nice_load; - unsigned int max_load = 0; + unsigned int max_load = 0, idle_periods = UINT_MAX; unsigned int sampling_rate, io_busy, j; /* @@ -215,9 +215,19 @@ unsigned int dbs_update(struct cpufreq_policy *policy) j_cdbs->prev_load = load; } + if (time_elapsed > 2 * sampling_rate) { + unsigned int periods = time_elapsed / sampling_rate; + + if (periods < idle_periods) + idle_periods = periods; + } + if (load > max_load) max_load = load; } + + policy_dbs->idle_periods = idle_periods; + return max_load; } EXPORT_SYMBOL_GPL(dbs_update); @@ -236,9 +246,9 @@ static void dbs_work_handler(struct work_struct *work) * Make sure cpufreq_governor_limits() isn't evaluating load or the * ondemand governor isn't updating the sampling rate in parallel. */ - mutex_lock(&policy_dbs->timer_mutex); - gov_update_sample_delay(policy_dbs, gov->gov_dbs_timer(policy)); - mutex_unlock(&policy_dbs->timer_mutex); + mutex_lock(&policy_dbs->update_mutex); + gov_update_sample_delay(policy_dbs, gov->gov_dbs_update(policy)); + mutex_unlock(&policy_dbs->update_mutex); /* Allow the utilization update handler to queue up more work. */ atomic_set(&policy_dbs->work_count, 0); @@ -348,7 +358,7 @@ static struct policy_dbs_info *alloc_policy_dbs_info(struct cpufreq_policy *poli return NULL; policy_dbs->policy = policy; - mutex_init(&policy_dbs->timer_mutex); + mutex_init(&policy_dbs->update_mutex); atomic_set(&policy_dbs->work_count, 0); init_irq_work(&policy_dbs->irq_work, dbs_irq_work); INIT_WORK(&policy_dbs->work, dbs_work_handler); @@ -367,7 +377,7 @@ static void free_policy_dbs_info(struct policy_dbs_info *policy_dbs, { int j; - mutex_destroy(&policy_dbs->timer_mutex); + mutex_destroy(&policy_dbs->update_mutex); for_each_cpu(j, policy_dbs->policy->related_cpus) { struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j); @@ -547,10 +557,10 @@ void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy) { struct policy_dbs_info *policy_dbs = policy->governor_data; - mutex_lock(&policy_dbs->timer_mutex); + mutex_lock(&policy_dbs->update_mutex); cpufreq_policy_apply_limits(policy); gov_update_sample_delay(policy_dbs, 0); - mutex_unlock(&policy_dbs->timer_mutex); + mutex_unlock(&policy_dbs->update_mutex); } EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_limits); diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h index ef1037e9c92b..f5717ca070cc 100644 --- a/drivers/cpufreq/cpufreq_governor.h +++ b/drivers/cpufreq/cpufreq_governor.h @@ -85,7 +85,7 @@ struct policy_dbs_info { * Per policy mutex that serializes load evaluation from limit-change * and work-handler. */ - struct mutex timer_mutex; + struct mutex update_mutex; u64 last_sample_time; s64 sample_delay_ns; @@ -97,6 +97,7 @@ struct policy_dbs_info { struct list_head list; /* Multiplier for increasing sample delay temporarily. */ unsigned int rate_mult; + unsigned int idle_periods; /* For conservative */ /* Status indicators */ bool is_shared; /* This object is used by multiple CPUs */ bool work_in_progress; /* Work is being queued up or in progress */ @@ -135,7 +136,7 @@ struct dbs_governor { */ struct dbs_data *gdbs_data; - unsigned int (*gov_dbs_timer)(struct cpufreq_policy *policy); + unsigned int (*gov_dbs_update)(struct cpufreq_policy *policy); struct policy_dbs_info *(*alloc)(void); void (*free)(struct policy_dbs_info *policy_dbs); int (*init)(struct dbs_data *dbs_data); diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index 3a1f49f5f4c6..4a017e895296 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -25,7 +25,7 @@ #define MAX_SAMPLING_DOWN_FACTOR (100000) #define MICRO_FREQUENCY_UP_THRESHOLD (95) #define MICRO_FREQUENCY_MIN_SAMPLE_RATE (10000) -#define MIN_FREQUENCY_UP_THRESHOLD (11) +#define MIN_FREQUENCY_UP_THRESHOLD (1) #define MAX_FREQUENCY_UP_THRESHOLD (100) static struct od_ops od_ops; @@ -169,7 +169,7 @@ static void od_update(struct cpufreq_policy *policy) } } -static unsigned int od_dbs_timer(struct cpufreq_policy *policy) +static unsigned int od_dbs_update(struct cpufreq_policy *policy) { struct policy_dbs_info *policy_dbs = policy->governor_data; struct dbs_data *dbs_data = policy_dbs->dbs_data; @@ -191,7 +191,7 @@ static unsigned int od_dbs_timer(struct cpufreq_policy *policy) od_update(policy); if (dbs_info->freq_lo) { - /* Setup timer for SUB_SAMPLE */ + /* Setup SUB_SAMPLE */ dbs_info->sample_type = OD_SUB_SAMPLE; return dbs_info->freq_hi_delay_us; } @@ -255,11 +255,11 @@ static ssize_t store_sampling_down_factor(struct gov_attr_set *attr_set, list_for_each_entry(policy_dbs, &attr_set->policy_list, list) { /* * Doing this without locking might lead to using different - * rate_mult values in od_update() and od_dbs_timer(). + * rate_mult values in od_update() and od_dbs_update(). */ - mutex_lock(&policy_dbs->timer_mutex); + mutex_lock(&policy_dbs->update_mutex); policy_dbs->rate_mult = 1; - mutex_unlock(&policy_dbs->timer_mutex); + mutex_unlock(&policy_dbs->update_mutex); } return count; @@ -374,8 +374,7 @@ static int od_init(struct dbs_data *dbs_data) dbs_data->up_threshold = MICRO_FREQUENCY_UP_THRESHOLD; /* * In nohz/micro accounting case we set the minimum frequency - * not depending on HZ, but fixed (very low). The deferred - * timer might skip some samples if idle/sleeping as needed. + * not depending on HZ, but fixed (very low). */ dbs_data->min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE; } else { @@ -415,7 +414,7 @@ static struct od_ops od_ops = { static struct dbs_governor od_dbs_gov = { .gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("ondemand"), .kobj_type = { .default_attrs = od_attributes }, - .gov_dbs_timer = od_dbs_timer, + .gov_dbs_update = od_dbs_update, .alloc = od_alloc, .free = od_free, .init = od_init, diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index 06d3abdffd3a..ac284e66839c 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -41,6 +41,18 @@ static int cpufreq_stats_update(struct cpufreq_stats *stats) return 0; } +static void cpufreq_stats_clear_table(struct cpufreq_stats *stats) +{ + unsigned int count = stats->max_state; + + memset(stats->time_in_state, 0, count * sizeof(u64)); +#ifdef CONFIG_CPU_FREQ_STAT_DETAILS + memset(stats->trans_table, 0, count * count * sizeof(int)); +#endif + stats->last_time = get_jiffies_64(); + stats->total_trans = 0; +} + static ssize_t show_total_trans(struct cpufreq_policy *policy, char *buf) { return sprintf(buf, "%d\n", policy->stats->total_trans); @@ -64,6 +76,14 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf) return len; } +static ssize_t store_reset(struct cpufreq_policy *policy, const char *buf, + size_t count) +{ + /* We don't care what is written to the attribute. */ + cpufreq_stats_clear_table(policy->stats); + return count; +} + #ifdef CONFIG_CPU_FREQ_STAT_DETAILS static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf) { @@ -113,10 +133,12 @@ cpufreq_freq_attr_ro(trans_table); cpufreq_freq_attr_ro(total_trans); cpufreq_freq_attr_ro(time_in_state); +cpufreq_freq_attr_wo(reset); static struct attribute *default_attrs[] = { &total_trans.attr, &time_in_state.attr, + &reset.attr, #ifdef CONFIG_CPU_FREQ_STAT_DETAILS &trans_table.attr, #endif diff --git a/drivers/cpufreq/integrator-cpufreq.c b/drivers/cpufreq/integrator-cpufreq.c deleted file mode 100644 index 79e3ff2771a6..000000000000 --- a/drivers/cpufreq/integrator-cpufreq.c +++ /dev/null @@ -1,239 +0,0 @@ -/* - * Copyright (C) 2001-2002 Deep Blue Solutions Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * CPU support functions - */ -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/cpufreq.h> -#include <linux/sched.h> -#include <linux/smp.h> -#include <linux/init.h> -#include <linux/io.h> -#include <linux/platform_device.h> -#include <linux/of.h> -#include <linux/of_address.h> - -#include <asm/mach-types.h> -#include <asm/hardware/icst.h> - -static void __iomem *cm_base; -/* The cpufreq driver only use the OSC register */ -#define INTEGRATOR_HDR_OSC_OFFSET 0x08 -#define INTEGRATOR_HDR_LOCK_OFFSET 0x14 - -static struct cpufreq_driver integrator_driver; - -static const struct icst_params lclk_params = { - .ref = 24000000, - .vco_max = ICST525_VCO_MAX_5V, - .vco_min = ICST525_VCO_MIN, - .vd_min = 8, - .vd_max = 132, - .rd_min = 24, - .rd_max = 24, - .s2div = icst525_s2div, - .idx2s = icst525_idx2s, -}; - -static const struct icst_params cclk_params = { - .ref = 24000000, - .vco_max = ICST525_VCO_MAX_5V, - .vco_min = ICST525_VCO_MIN, - .vd_min = 12, - .vd_max = 160, - .rd_min = 24, - .rd_max = 24, - .s2div = icst525_s2div, - .idx2s = icst525_idx2s, -}; - -/* - * Validate the speed policy. - */ -static int integrator_verify_policy(struct cpufreq_policy *policy) -{ - struct icst_vco vco; - - cpufreq_verify_within_cpu_limits(policy); - - vco = icst_hz_to_vco(&cclk_params, policy->max * 1000); - policy->max = icst_hz(&cclk_params, vco) / 1000; - - vco = icst_hz_to_vco(&cclk_params, policy->min * 1000); - policy->min = icst_hz(&cclk_params, vco) / 1000; - - cpufreq_verify_within_cpu_limits(policy); - return 0; -} - - -static int integrator_set_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) -{ - cpumask_t cpus_allowed; - int cpu = policy->cpu; - struct icst_vco vco; - struct cpufreq_freqs freqs; - u_int cm_osc; - - /* - * Save this threads cpus_allowed mask. - */ - cpus_allowed = current->cpus_allowed; - - /* - * Bind to the specified CPU. When this call returns, - * we should be running on the right CPU. - */ - set_cpus_allowed_ptr(current, cpumask_of(cpu)); - BUG_ON(cpu != smp_processor_id()); - - /* get current setting */ - cm_osc = __raw_readl(cm_base + INTEGRATOR_HDR_OSC_OFFSET); - - if (machine_is_integrator()) - vco.s = (cm_osc >> 8) & 7; - else if (machine_is_cintegrator()) - vco.s = 1; - vco.v = cm_osc & 255; - vco.r = 22; - freqs.old = icst_hz(&cclk_params, vco) / 1000; - - /* icst_hz_to_vco rounds down -- so we need the next - * larger freq in case of CPUFREQ_RELATION_L. - */ - if (relation == CPUFREQ_RELATION_L) - target_freq += 999; - if (target_freq > policy->max) - target_freq = policy->max; - vco = icst_hz_to_vco(&cclk_params, target_freq * 1000); - freqs.new = icst_hz(&cclk_params, vco) / 1000; - - if (freqs.old == freqs.new) { - set_cpus_allowed_ptr(current, &cpus_allowed); - return 0; - } - - cpufreq_freq_transition_begin(policy, &freqs); - - cm_osc = __raw_readl(cm_base + INTEGRATOR_HDR_OSC_OFFSET); - - if (machine_is_integrator()) { - cm_osc &= 0xfffff800; - cm_osc |= vco.s << 8; - } else if (machine_is_cintegrator()) { - cm_osc &= 0xffffff00; - } - cm_osc |= vco.v; - - __raw_writel(0xa05f, cm_base + INTEGRATOR_HDR_LOCK_OFFSET); - __raw_writel(cm_osc, cm_base + INTEGRATOR_HDR_OSC_OFFSET); - __raw_writel(0, cm_base + INTEGRATOR_HDR_LOCK_OFFSET); - - /* - * Restore the CPUs allowed mask. - */ - set_cpus_allowed_ptr(current, &cpus_allowed); - - cpufreq_freq_transition_end(policy, &freqs, 0); - - return 0; -} - -static unsigned int integrator_get(unsigned int cpu) -{ - cpumask_t cpus_allowed; - unsigned int current_freq; - u_int cm_osc; - struct icst_vco vco; - - cpus_allowed = current->cpus_allowed; - - set_cpus_allowed_ptr(current, cpumask_of(cpu)); - BUG_ON(cpu != smp_processor_id()); - - /* detect memory etc. */ - cm_osc = __raw_readl(cm_base + INTEGRATOR_HDR_OSC_OFFSET); - - if (machine_is_integrator()) - vco.s = (cm_osc >> 8) & 7; - else - vco.s = 1; - vco.v = cm_osc & 255; - vco.r = 22; - - current_freq = icst_hz(&cclk_params, vco) / 1000; /* current freq */ - - set_cpus_allowed_ptr(current, &cpus_allowed); - - return current_freq; -} - -static int integrator_cpufreq_init(struct cpufreq_policy *policy) -{ - - /* set default policy and cpuinfo */ - policy->max = policy->cpuinfo.max_freq = 160000; - policy->min = policy->cpuinfo.min_freq = 12000; - policy->cpuinfo.transition_latency = 1000000; /* 1 ms, assumed */ - - return 0; -} - -static struct cpufreq_driver integrator_driver = { - .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, - .verify = integrator_verify_policy, - .target = integrator_set_target, - .get = integrator_get, - .init = integrator_cpufreq_init, - .name = "integrator", -}; - -static int __init integrator_cpufreq_probe(struct platform_device *pdev) -{ - struct resource *res; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENODEV; - - cm_base = devm_ioremap(&pdev->dev, res->start, resource_size(res)); - if (!cm_base) - return -ENODEV; - - return cpufreq_register_driver(&integrator_driver); -} - -static int __exit integrator_cpufreq_remove(struct platform_device *pdev) -{ - return cpufreq_unregister_driver(&integrator_driver); -} - -static const struct of_device_id integrator_cpufreq_match[] = { - { .compatible = "arm,core-module-integrator"}, - { }, -}; - -MODULE_DEVICE_TABLE(of, integrator_cpufreq_match); - -static struct platform_driver integrator_cpufreq_driver = { - .driver = { - .name = "integrator-cpufreq", - .of_match_table = integrator_cpufreq_match, - }, - .remove = __exit_p(integrator_cpufreq_remove), -}; - -module_platform_driver_probe(integrator_cpufreq_driver, - integrator_cpufreq_probe); - -MODULE_AUTHOR("Russell M. King"); -MODULE_DESCRIPTION("cpufreq driver for ARM Integrator CPUs"); -MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 4737520ec823..7cd0177ddeaf 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -37,6 +37,8 @@ #include <asm/cpufeature.h> #include <asm/intel-family.h> +#define INTEL_CPUFREQ_TRANSITION_LATENCY 20000 + #define ATOM_RATIOS 0x66a #define ATOM_VIDS 0x66b #define ATOM_TURBO_RATIOS 0x66c @@ -52,6 +54,8 @@ #define EXT_BITS 6 #define EXT_FRAC_BITS (EXT_BITS + FRAC_BITS) +#define fp_ext_toint(X) ((X) >> EXT_FRAC_BITS) +#define int_ext_tofp(X) ((int64_t)(X) << EXT_FRAC_BITS) static inline int32_t mul_fp(int32_t x, int32_t y) { @@ -122,6 +126,8 @@ struct sample { * @scaling: Scaling factor to convert frequency to cpufreq * frequency units * @turbo_pstate: Max Turbo P state possible for this platform + * @max_freq: @max_pstate frequency in cpufreq units + * @turbo_freq: @turbo_pstate frequency in cpufreq units * * Stores the per cpu model P state limits and current P state. */ @@ -132,6 +138,8 @@ struct pstate_data { int max_pstate_physical; int scaling; int turbo_pstate; + unsigned int max_freq; + unsigned int turbo_freq; }; /** @@ -177,6 +185,48 @@ struct _pid { }; /** + * struct perf_limits - Store user and policy limits + * @no_turbo: User requested turbo state from intel_pstate sysfs + * @turbo_disabled: Platform turbo status either from msr + * MSR_IA32_MISC_ENABLE or when maximum available pstate + * matches the maximum turbo pstate + * @max_perf_pct: Effective maximum performance limit in percentage, this + * is minimum of either limits enforced by cpufreq policy + * or limits from user set limits via intel_pstate sysfs + * @min_perf_pct: Effective minimum performance limit in percentage, this + * is maximum of either limits enforced by cpufreq policy + * or limits from user set limits via intel_pstate sysfs + * @max_perf: This is a scaled value between 0 to 255 for max_perf_pct + * This value is used to limit max pstate + * @min_perf: This is a scaled value between 0 to 255 for min_perf_pct + * This value is used to limit min pstate + * @max_policy_pct: The maximum performance in percentage enforced by + * cpufreq setpolicy interface + * @max_sysfs_pct: The maximum performance in percentage enforced by + * intel pstate sysfs interface, unused when per cpu + * controls are enforced + * @min_policy_pct: The minimum performance in percentage enforced by + * cpufreq setpolicy interface + * @min_sysfs_pct: The minimum performance in percentage enforced by + * intel pstate sysfs interface, unused when per cpu + * controls are enforced + * + * Storage for user and policy defined limits. + */ +struct perf_limits { + int no_turbo; + int turbo_disabled; + int max_perf_pct; + int min_perf_pct; + int32_t max_perf; + int32_t min_perf; + int max_policy_pct; + int max_sysfs_pct; + int min_policy_pct; + int min_sysfs_pct; +}; + +/** * struct cpudata - Per CPU instance data storage * @cpu: CPU number for this instance data * @policy: CPUFreq policy value @@ -194,8 +244,19 @@ struct _pid { * @prev_cummulative_iowait: IO Wait time difference from last and * current sample * @sample: Storage for storing last Sample data + * @perf_limits: Pointer to perf_limit unique to this CPU + * Not all field in the structure are applicable + * when per cpu controls are enforced * @acpi_perf_data: Stores ACPI perf information read from _PSS * @valid_pss_table: Set to true for valid ACPI _PSS entries found + * @epp_powersave: Last saved HWP energy performance preference + * (EPP) or energy performance bias (EPB), + * when policy switched to performance + * @epp_policy: Last saved policy used to set EPP/EPB + * @epp_default: Power on default HWP energy performance + * preference/bias + * @epp_saved: Saved EPP/EPB during system suspend or CPU offline + * operation * * This structure stores per CPU instance data for all CPUs. */ @@ -217,11 +278,16 @@ struct cpudata { u64 prev_tsc; u64 prev_cummulative_iowait; struct sample sample; + struct perf_limits *perf_limits; #ifdef CONFIG_ACPI struct acpi_processor_performance acpi_perf_data; bool valid_pss_table; #endif unsigned int iowait_boost; + s16 epp_powersave; + s16 epp_policy; + s16 epp_default; + s16 epp_saved; }; static struct cpudata **all_cpu_data; @@ -235,7 +301,6 @@ static struct cpudata **all_cpu_data; * @p_gain_pct: PID proportional gain * @i_gain_pct: PID integral gain * @d_gain_pct: PID derivative gain - * @boost_iowait: Whether or not to use iowait boosting. * * Stores per CPU model static PID configuration data. */ @@ -247,7 +312,6 @@ struct pstate_adjust_policy { int p_gain_pct; int d_gain_pct; int i_gain_pct; - bool boost_iowait; }; /** @@ -291,58 +355,19 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu); static struct pstate_adjust_policy pid_params __read_mostly; static struct pstate_funcs pstate_funcs __read_mostly; static int hwp_active __read_mostly; +static bool per_cpu_limits __read_mostly; #ifdef CONFIG_ACPI static bool acpi_ppc; #endif -/** - * struct perf_limits - Store user and policy limits - * @no_turbo: User requested turbo state from intel_pstate sysfs - * @turbo_disabled: Platform turbo status either from msr - * MSR_IA32_MISC_ENABLE or when maximum available pstate - * matches the maximum turbo pstate - * @max_perf_pct: Effective maximum performance limit in percentage, this - * is minimum of either limits enforced by cpufreq policy - * or limits from user set limits via intel_pstate sysfs - * @min_perf_pct: Effective minimum performance limit in percentage, this - * is maximum of either limits enforced by cpufreq policy - * or limits from user set limits via intel_pstate sysfs - * @max_perf: This is a scaled value between 0 to 255 for max_perf_pct - * This value is used to limit max pstate - * @min_perf: This is a scaled value between 0 to 255 for min_perf_pct - * This value is used to limit min pstate - * @max_policy_pct: The maximum performance in percentage enforced by - * cpufreq setpolicy interface - * @max_sysfs_pct: The maximum performance in percentage enforced by - * intel pstate sysfs interface - * @min_policy_pct: The minimum performance in percentage enforced by - * cpufreq setpolicy interface - * @min_sysfs_pct: The minimum performance in percentage enforced by - * intel pstate sysfs interface - * - * Storage for user and policy defined limits. - */ -struct perf_limits { - int no_turbo; - int turbo_disabled; - int max_perf_pct; - int min_perf_pct; - int32_t max_perf; - int32_t min_perf; - int max_policy_pct; - int max_sysfs_pct; - int min_policy_pct; - int min_sysfs_pct; -}; - static struct perf_limits performance_limits = { .no_turbo = 0, .turbo_disabled = 0, .max_perf_pct = 100, - .max_perf = int_tofp(1), + .max_perf = int_ext_tofp(1), .min_perf_pct = 100, - .min_perf = int_tofp(1), + .min_perf = int_ext_tofp(1), .max_policy_pct = 100, .max_sysfs_pct = 100, .min_policy_pct = 0, @@ -353,7 +378,7 @@ static struct perf_limits powersave_limits = { .no_turbo = 0, .turbo_disabled = 0, .max_perf_pct = 100, - .max_perf = int_tofp(1), + .max_perf = int_ext_tofp(1), .min_perf_pct = 0, .min_perf = 0, .max_policy_pct = 100, @@ -368,6 +393,8 @@ static struct perf_limits *limits = &performance_limits; static struct perf_limits *limits = &powersave_limits; #endif +static DEFINE_MUTEX(intel_pstate_limits_lock); + #ifdef CONFIG_ACPI static bool intel_pstate_get_ppc_enable_status(void) @@ -459,11 +486,11 @@ static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) } #else -static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) +static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) { } -static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) +static inline void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) { } #endif @@ -559,24 +586,252 @@ static inline void update_turbo_state(void) cpu->pstate.max_pstate == cpu->pstate.turbo_pstate); } +static s16 intel_pstate_get_epb(struct cpudata *cpu_data) +{ + u64 epb; + int ret; + + if (!static_cpu_has(X86_FEATURE_EPB)) + return -ENXIO; + + ret = rdmsrl_on_cpu(cpu_data->cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb); + if (ret) + return (s16)ret; + + return (s16)(epb & 0x0f); +} + +static s16 intel_pstate_get_epp(struct cpudata *cpu_data, u64 hwp_req_data) +{ + s16 epp; + + if (static_cpu_has(X86_FEATURE_HWP_EPP)) { + /* + * When hwp_req_data is 0, means that caller didn't read + * MSR_HWP_REQUEST, so need to read and get EPP. + */ + if (!hwp_req_data) { + epp = rdmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, + &hwp_req_data); + if (epp) + return epp; + } + epp = (hwp_req_data >> 24) & 0xff; + } else { + /* When there is no EPP present, HWP uses EPB settings */ + epp = intel_pstate_get_epb(cpu_data); + } + + return epp; +} + +static int intel_pstate_set_epb(int cpu, s16 pref) +{ + u64 epb; + int ret; + + if (!static_cpu_has(X86_FEATURE_EPB)) + return -ENXIO; + + ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb); + if (ret) + return ret; + + epb = (epb & ~0x0f) | pref; + wrmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, epb); + + return 0; +} + +/* + * EPP/EPB display strings corresponding to EPP index in the + * energy_perf_strings[] + * index String + *------------------------------------- + * 0 default + * 1 performance + * 2 balance_performance + * 3 balance_power + * 4 power + */ +static const char * const energy_perf_strings[] = { + "default", + "performance", + "balance_performance", + "balance_power", + "power", + NULL +}; + +static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data) +{ + s16 epp; + int index = -EINVAL; + + epp = intel_pstate_get_epp(cpu_data, 0); + if (epp < 0) + return epp; + + if (static_cpu_has(X86_FEATURE_HWP_EPP)) { + /* + * Range: + * 0x00-0x3F : Performance + * 0x40-0x7F : Balance performance + * 0x80-0xBF : Balance power + * 0xC0-0xFF : Power + * The EPP is a 8 bit value, but our ranges restrict the + * value which can be set. Here only using top two bits + * effectively. + */ + index = (epp >> 6) + 1; + } else if (static_cpu_has(X86_FEATURE_EPB)) { + /* + * Range: + * 0x00-0x03 : Performance + * 0x04-0x07 : Balance performance + * 0x08-0x0B : Balance power + * 0x0C-0x0F : Power + * The EPB is a 4 bit value, but our ranges restrict the + * value which can be set. Here only using top two bits + * effectively. + */ + index = (epp >> 2) + 1; + } + + return index; +} + +static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data, + int pref_index) +{ + int epp = -EINVAL; + int ret; + + if (!pref_index) + epp = cpu_data->epp_default; + + mutex_lock(&intel_pstate_limits_lock); + + if (static_cpu_has(X86_FEATURE_HWP_EPP)) { + u64 value; + + ret = rdmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, &value); + if (ret) + goto return_pref; + + value &= ~GENMASK_ULL(31, 24); + + /* + * If epp is not default, convert from index into + * energy_perf_strings to epp value, by shifting 6 + * bits left to use only top two bits in epp. + * The resultant epp need to shifted by 24 bits to + * epp position in MSR_HWP_REQUEST. + */ + if (epp == -EINVAL) + epp = (pref_index - 1) << 6; + + value |= (u64)epp << 24; + ret = wrmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, value); + } else { + if (epp == -EINVAL) + epp = (pref_index - 1) << 2; + ret = intel_pstate_set_epb(cpu_data->cpu, epp); + } +return_pref: + mutex_unlock(&intel_pstate_limits_lock); + + return ret; +} + +static ssize_t show_energy_performance_available_preferences( + struct cpufreq_policy *policy, char *buf) +{ + int i = 0; + int ret = 0; + + while (energy_perf_strings[i] != NULL) + ret += sprintf(&buf[ret], "%s ", energy_perf_strings[i++]); + + ret += sprintf(&buf[ret], "\n"); + + return ret; +} + +cpufreq_freq_attr_ro(energy_performance_available_preferences); + +static ssize_t store_energy_performance_preference( + struct cpufreq_policy *policy, const char *buf, size_t count) +{ + struct cpudata *cpu_data = all_cpu_data[policy->cpu]; + char str_preference[21]; + int ret, i = 0; + + ret = sscanf(buf, "%20s", str_preference); + if (ret != 1) + return -EINVAL; + + while (energy_perf_strings[i] != NULL) { + if (!strcmp(str_preference, energy_perf_strings[i])) { + intel_pstate_set_energy_pref_index(cpu_data, i); + return count; + } + ++i; + } + + return -EINVAL; +} + +static ssize_t show_energy_performance_preference( + struct cpufreq_policy *policy, char *buf) +{ + struct cpudata *cpu_data = all_cpu_data[policy->cpu]; + int preference; + + preference = intel_pstate_get_energy_pref_index(cpu_data); + if (preference < 0) + return preference; + + return sprintf(buf, "%s\n", energy_perf_strings[preference]); +} + +cpufreq_freq_attr_rw(energy_performance_preference); + +static struct freq_attr *hwp_cpufreq_attrs[] = { + &energy_performance_preference, + &energy_performance_available_preferences, + NULL, +}; + static void intel_pstate_hwp_set(const struct cpumask *cpumask) { int min, hw_min, max, hw_max, cpu, range, adj_range; + struct perf_limits *perf_limits = limits; u64 value, cap; for_each_cpu(cpu, cpumask) { + int max_perf_pct, min_perf_pct; + struct cpudata *cpu_data = all_cpu_data[cpu]; + s16 epp; + + if (per_cpu_limits) + perf_limits = all_cpu_data[cpu]->perf_limits; + rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap); hw_min = HWP_LOWEST_PERF(cap); hw_max = HWP_HIGHEST_PERF(cap); range = hw_max - hw_min; + max_perf_pct = perf_limits->max_perf_pct; + min_perf_pct = perf_limits->min_perf_pct; + rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value); - adj_range = limits->min_perf_pct * range / 100; + adj_range = min_perf_pct * range / 100; min = hw_min + adj_range; value &= ~HWP_MIN_PERF(~0L); value |= HWP_MIN_PERF(min); - adj_range = limits->max_perf_pct * range / 100; + adj_range = max_perf_pct * range / 100; max = hw_min + adj_range; if (limits->no_turbo) { hw_max = HWP_GUARANTEED_PERF(cap); @@ -586,6 +841,53 @@ static void intel_pstate_hwp_set(const struct cpumask *cpumask) value &= ~HWP_MAX_PERF(~0L); value |= HWP_MAX_PERF(max); + + if (cpu_data->epp_policy == cpu_data->policy) + goto skip_epp; + + cpu_data->epp_policy = cpu_data->policy; + + if (cpu_data->epp_saved >= 0) { + epp = cpu_data->epp_saved; + cpu_data->epp_saved = -EINVAL; + goto update_epp; + } + + if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) { + epp = intel_pstate_get_epp(cpu_data, value); + cpu_data->epp_powersave = epp; + /* If EPP read was failed, then don't try to write */ + if (epp < 0) + goto skip_epp; + + + epp = 0; + } else { + /* skip setting EPP, when saved value is invalid */ + if (cpu_data->epp_powersave < 0) + goto skip_epp; + + /* + * No need to restore EPP when it is not zero. This + * means: + * - Policy is not changed + * - user has manually changed + * - Error reading EPB + */ + epp = intel_pstate_get_epp(cpu_data, value); + if (epp) + goto skip_epp; + + epp = cpu_data->epp_powersave; + } +update_epp: + if (static_cpu_has(X86_FEATURE_HWP_EPP)) { + value &= ~GENMASK_ULL(31, 24); + value |= (u64)epp << 24; + } else { + intel_pstate_set_epb(cpu, epp); + } +skip_epp: wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value); } } @@ -598,6 +900,28 @@ static int intel_pstate_hwp_set_policy(struct cpufreq_policy *policy) return 0; } +static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy) +{ + struct cpudata *cpu_data = all_cpu_data[policy->cpu]; + + if (!hwp_active) + return 0; + + cpu_data->epp_saved = intel_pstate_get_epp(cpu_data, 0); + + return 0; +} + +static int intel_pstate_resume(struct cpufreq_policy *policy) +{ + if (!hwp_active) + return 0; + + all_cpu_data[policy->cpu]->epp_policy = 0; + + return intel_pstate_hwp_set_policy(policy); +} + static void intel_pstate_hwp_set_online_cpus(void) { get_online_cpus(); @@ -640,8 +964,10 @@ static void __init intel_pstate_debug_expose_params(void) struct dentry *debugfs_parent; int i = 0; - if (hwp_active) + if (hwp_active || + pstate_funcs.get_target_pstate == get_target_pstate_use_cpu_load) return; + debugfs_parent = debugfs_create_dir("pstate_snb", NULL); if (IS_ERR_OR_NULL(debugfs_parent)) return; @@ -714,9 +1040,12 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, if (ret != 1) return -EINVAL; + mutex_lock(&intel_pstate_limits_lock); + update_turbo_state(); if (limits->turbo_disabled) { pr_warn("Turbo disabled by BIOS or unavailable on processor\n"); + mutex_unlock(&intel_pstate_limits_lock); return -EPERM; } @@ -725,6 +1054,8 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b, if (hwp_active) intel_pstate_hwp_set_online_cpus(); + mutex_unlock(&intel_pstate_limits_lock); + return count; } @@ -738,6 +1069,8 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, if (ret != 1) return -EINVAL; + mutex_lock(&intel_pstate_limits_lock); + limits->max_sysfs_pct = clamp_t(int, input, 0 , 100); limits->max_perf_pct = min(limits->max_policy_pct, limits->max_sysfs_pct); @@ -745,10 +1078,13 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b, limits->max_perf_pct); limits->max_perf_pct = max(limits->min_perf_pct, limits->max_perf_pct); - limits->max_perf = div_fp(limits->max_perf_pct, 100); + limits->max_perf = div_ext_fp(limits->max_perf_pct, 100); if (hwp_active) intel_pstate_hwp_set_online_cpus(); + + mutex_unlock(&intel_pstate_limits_lock); + return count; } @@ -762,6 +1098,8 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, if (ret != 1) return -EINVAL; + mutex_lock(&intel_pstate_limits_lock); + limits->min_sysfs_pct = clamp_t(int, input, 0 , 100); limits->min_perf_pct = max(limits->min_policy_pct, limits->min_sysfs_pct); @@ -769,10 +1107,13 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, limits->min_perf_pct); limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct); - limits->min_perf = div_fp(limits->min_perf_pct, 100); + limits->min_perf = div_ext_fp(limits->min_perf_pct, 100); if (hwp_active) intel_pstate_hwp_set_online_cpus(); + + mutex_unlock(&intel_pstate_limits_lock); + return count; } @@ -787,8 +1128,6 @@ define_one_global_ro(num_pstates); static struct attribute *intel_pstate_attributes[] = { &no_turbo.attr, - &max_perf_pct.attr, - &min_perf_pct.attr, &turbo_pct.attr, &num_pstates.attr, NULL @@ -805,9 +1144,26 @@ static void __init intel_pstate_sysfs_expose_params(void) intel_pstate_kobject = kobject_create_and_add("intel_pstate", &cpu_subsys.dev_root->kobj); - BUG_ON(!intel_pstate_kobject); + if (WARN_ON(!intel_pstate_kobject)) + return; + rc = sysfs_create_group(intel_pstate_kobject, &intel_pstate_attr_group); - BUG_ON(rc); + if (WARN_ON(rc)) + return; + + /* + * If per cpu limits are enforced there are no global limits, so + * return without creating max/min_perf_pct attributes + */ + if (per_cpu_limits) + return; + + rc = sysfs_create_file(intel_pstate_kobject, &max_perf_pct.attr); + WARN_ON(rc); + + rc = sysfs_create_file(intel_pstate_kobject, &min_perf_pct.attr); + WARN_ON(rc); + } /************************** sysfs end ************************/ @@ -818,6 +1174,9 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata) wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00); wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1); + cpudata->epp_policy = 0; + if (cpudata->epp_default == -EINVAL) + cpudata->epp_default = intel_pstate_get_epp(cpudata, 0); } static int atom_get_min_pstate(void) @@ -1045,7 +1404,6 @@ static const struct cpu_defaults silvermont_params = { .p_gain_pct = 14, .d_gain_pct = 0, .i_gain_pct = 4, - .boost_iowait = true, }, .funcs = { .get_max = atom_get_max_pstate, @@ -1067,7 +1425,6 @@ static const struct cpu_defaults airmont_params = { .p_gain_pct = 14, .d_gain_pct = 0, .i_gain_pct = 4, - .boost_iowait = true, }, .funcs = { .get_max = atom_get_max_pstate, @@ -1109,7 +1466,6 @@ static const struct cpu_defaults bxt_params = { .p_gain_pct = 14, .d_gain_pct = 0, .i_gain_pct = 4, - .boost_iowait = true, }, .funcs = { .get_max = core_get_max_pstate, @@ -1127,20 +1483,24 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max) int max_perf = cpu->pstate.turbo_pstate; int max_perf_adj; int min_perf; + struct perf_limits *perf_limits = limits; if (limits->no_turbo || limits->turbo_disabled) max_perf = cpu->pstate.max_pstate; + if (per_cpu_limits) + perf_limits = cpu->perf_limits; + /* * performance can be limited by user through sysfs, by cpufreq * policy, or by cpu specific default values determined through * experimentation. */ - max_perf_adj = fp_toint(max_perf * limits->max_perf); + max_perf_adj = fp_ext_toint(max_perf * perf_limits->max_perf); *max = clamp_t(int, max_perf_adj, cpu->pstate.min_pstate, cpu->pstate.turbo_pstate); - min_perf = fp_toint(max_perf * limits->min_perf); + min_perf = fp_ext_toint(max_perf * perf_limits->min_perf); *min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf); } @@ -1178,6 +1538,8 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) cpu->pstate.max_pstate_physical = pstate_funcs.get_max_physical(); cpu->pstate.turbo_pstate = pstate_funcs.get_turbo(); cpu->pstate.scaling = pstate_funcs.get_scaling(); + cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling; + cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling; if (pstate_funcs.get_vid) pstate_funcs.get_vid(cpu); @@ -1316,15 +1678,19 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu) return cpu->pstate.current_pstate - pid_calc(&cpu->pid, perf_scaled); } -static inline void intel_pstate_update_pstate(struct cpudata *cpu, int pstate) +static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate) { int max_perf, min_perf; - update_turbo_state(); - intel_pstate_get_min_max(cpu, &min_perf, &max_perf); pstate = clamp_t(int, pstate, min_perf, max_perf); trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu); + return pstate; +} + +static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate) +{ + pstate = intel_pstate_prepare_request(cpu, pstate); if (pstate == cpu->pstate.current_pstate) return; @@ -1342,6 +1708,8 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) target_pstate = cpu->policy == CPUFREQ_POLICY_PERFORMANCE ? cpu->pstate.turbo_pstate : pstate_funcs.get_target_pstate(cpu); + update_turbo_state(); + intel_pstate_update_pstate(cpu, target_pstate); sample = &cpu->sample; @@ -1362,7 +1730,7 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time, struct cpudata *cpu = container_of(data, struct cpudata, update_util); u64 delta_ns; - if (pid_params.boost_iowait) { + if (pstate_funcs.get_target_pstate == get_target_pstate_use_cpu_load) { if (flags & SCHED_CPUFREQ_IOWAIT) { cpu->iowait_boost = int_tofp(1); } else if (cpu->iowait_boost) { @@ -1408,6 +1776,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = { ICPU(INTEL_FAM6_SKYLAKE_DESKTOP, core_params), ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_params), ICPU(INTEL_FAM6_XEON_PHI_KNL, knl_params), + ICPU(INTEL_FAM6_XEON_PHI_KNM, knl_params), ICPU(INTEL_FAM6_ATOM_GOLDMONT, bxt_params), {} }; @@ -1424,11 +1793,26 @@ static int intel_pstate_init_cpu(unsigned int cpunum) { struct cpudata *cpu; - if (!all_cpu_data[cpunum]) - all_cpu_data[cpunum] = kzalloc(sizeof(struct cpudata), - GFP_KERNEL); - if (!all_cpu_data[cpunum]) - return -ENOMEM; + cpu = all_cpu_data[cpunum]; + + if (!cpu) { + unsigned int size = sizeof(struct cpudata); + + if (per_cpu_limits) + size += sizeof(struct perf_limits); + + cpu = kzalloc(size, GFP_KERNEL); + if (!cpu) + return -ENOMEM; + + all_cpu_data[cpunum] = cpu; + if (per_cpu_limits) + cpu->perf_limits = (struct perf_limits *)(cpu + 1); + + cpu->epp_default = -EINVAL; + cpu->epp_powersave = -EINVAL; + cpu->epp_saved = -EINVAL; + } cpu = all_cpu_data[cpunum]; @@ -1487,18 +1871,57 @@ static void intel_pstate_set_performance_limits(struct perf_limits *limits) limits->no_turbo = 0; limits->turbo_disabled = 0; limits->max_perf_pct = 100; - limits->max_perf = int_tofp(1); + limits->max_perf = int_ext_tofp(1); limits->min_perf_pct = 100; - limits->min_perf = int_tofp(1); + limits->min_perf = int_ext_tofp(1); limits->max_policy_pct = 100; limits->max_sysfs_pct = 100; limits->min_policy_pct = 0; limits->min_sysfs_pct = 0; } +static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy, + struct perf_limits *limits) +{ + + limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100, + policy->cpuinfo.max_freq); + limits->max_policy_pct = clamp_t(int, limits->max_policy_pct, 0, 100); + if (policy->max == policy->min) { + limits->min_policy_pct = limits->max_policy_pct; + } else { + limits->min_policy_pct = DIV_ROUND_UP(policy->min * 100, + policy->cpuinfo.max_freq); + limits->min_policy_pct = clamp_t(int, limits->min_policy_pct, + 0, 100); + } + + /* Normalize user input to [min_policy_pct, max_policy_pct] */ + limits->min_perf_pct = max(limits->min_policy_pct, + limits->min_sysfs_pct); + limits->min_perf_pct = min(limits->max_policy_pct, + limits->min_perf_pct); + limits->max_perf_pct = min(limits->max_policy_pct, + limits->max_sysfs_pct); + limits->max_perf_pct = max(limits->min_policy_pct, + limits->max_perf_pct); + + /* Make sure min_perf_pct <= max_perf_pct */ + limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct); + + limits->min_perf = div_ext_fp(limits->min_perf_pct, 100); + limits->max_perf = div_ext_fp(limits->max_perf_pct, 100); + limits->max_perf = round_up(limits->max_perf, EXT_FRAC_BITS); + limits->min_perf = round_up(limits->min_perf, EXT_FRAC_BITS); + + pr_debug("cpu:%d max_perf_pct:%d min_perf_pct:%d\n", policy->cpu, + limits->max_perf_pct, limits->min_perf_pct); +} + static int intel_pstate_set_policy(struct cpufreq_policy *policy) { struct cpudata *cpu; + struct perf_limits *perf_limits = NULL; if (!policy->cpuinfo.max_freq) return -ENODEV; @@ -1516,41 +1939,31 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) policy->max = policy->cpuinfo.max_freq; } - if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) { - limits = &performance_limits; + if (per_cpu_limits) + perf_limits = cpu->perf_limits; + + mutex_lock(&intel_pstate_limits_lock); + + if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) { + if (!perf_limits) { + limits = &performance_limits; + perf_limits = limits; + } if (policy->max >= policy->cpuinfo.max_freq) { pr_debug("set performance\n"); - intel_pstate_set_performance_limits(limits); + intel_pstate_set_performance_limits(perf_limits); goto out; } } else { pr_debug("set powersave\n"); - limits = &powersave_limits; - } - - limits->min_policy_pct = (policy->min * 100) / policy->cpuinfo.max_freq; - limits->min_policy_pct = clamp_t(int, limits->min_policy_pct, 0 , 100); - limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100, - policy->cpuinfo.max_freq); - limits->max_policy_pct = clamp_t(int, limits->max_policy_pct, 0 , 100); - - /* Normalize user input to [min_policy_pct, max_policy_pct] */ - limits->min_perf_pct = max(limits->min_policy_pct, - limits->min_sysfs_pct); - limits->min_perf_pct = min(limits->max_policy_pct, - limits->min_perf_pct); - limits->max_perf_pct = min(limits->max_policy_pct, - limits->max_sysfs_pct); - limits->max_perf_pct = max(limits->min_policy_pct, - limits->max_perf_pct); - - /* Make sure min_perf_pct <= max_perf_pct */ - limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct); + if (!perf_limits) { + limits = &powersave_limits; + perf_limits = limits; + } - limits->min_perf = div_fp(limits->min_perf_pct, 100); - limits->max_perf = div_fp(limits->max_perf_pct, 100); - limits->max_perf = round_up(limits->max_perf, FRAC_BITS); + } + intel_pstate_update_perf_limits(policy, perf_limits); out: if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) { /* @@ -1565,6 +1978,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) intel_pstate_hwp_set_policy(policy); + mutex_unlock(&intel_pstate_limits_lock); + return 0; } @@ -1579,22 +1994,32 @@ static int intel_pstate_verify_policy(struct cpufreq_policy *policy) return 0; } +static void intel_cpufreq_stop_cpu(struct cpufreq_policy *policy) +{ + intel_pstate_set_min_pstate(all_cpu_data[policy->cpu]); +} + static void intel_pstate_stop_cpu(struct cpufreq_policy *policy) { - int cpu_num = policy->cpu; - struct cpudata *cpu = all_cpu_data[cpu_num]; + pr_debug("CPU %d exiting\n", policy->cpu); - pr_debug("CPU %d exiting\n", cpu_num); + intel_pstate_clear_update_util_hook(policy->cpu); + if (hwp_active) + intel_pstate_hwp_save_state(policy); + else + intel_cpufreq_stop_cpu(policy); +} - intel_pstate_clear_update_util_hook(cpu_num); +static int intel_pstate_cpu_exit(struct cpufreq_policy *policy) +{ + intel_pstate_exit_perf_limits(policy); - if (hwp_active) - return; + policy->fast_switch_possible = false; - intel_pstate_set_min_pstate(cpu); + return 0; } -static int intel_pstate_cpu_init(struct cpufreq_policy *policy) +static int __intel_pstate_cpu_init(struct cpufreq_policy *policy) { struct cpudata *cpu; int rc; @@ -1605,10 +2030,13 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) cpu = all_cpu_data[policy->cpu]; - if (limits->min_perf_pct == 100 && limits->max_perf_pct == 100) - policy->policy = CPUFREQ_POLICY_PERFORMANCE; - else - policy->policy = CPUFREQ_POLICY_POWERSAVE; + /* + * We need sane value in the cpu->perf_limits, so inherit from global + * perf_limits limits, which are seeded with values based on the + * CONFIG_CPU_FREQ_DEFAULT_GOV_*, during boot up. + */ + if (per_cpu_limits) + memcpy(cpu->perf_limits, limits, sizeof(struct perf_limits)); policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling; policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling; @@ -1621,24 +2049,35 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) policy->cpuinfo.max_freq *= cpu->pstate.scaling; intel_pstate_init_acpi_perf_limits(policy); - policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL; cpumask_set_cpu(policy->cpu, policy->cpus); + policy->fast_switch_possible = true; + return 0; } -static int intel_pstate_cpu_exit(struct cpufreq_policy *policy) +static int intel_pstate_cpu_init(struct cpufreq_policy *policy) { - intel_pstate_exit_perf_limits(policy); + int ret = __intel_pstate_cpu_init(policy); + + if (ret) + return ret; + + policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL; + if (limits->min_perf_pct == 100 && limits->max_perf_pct == 100) + policy->policy = CPUFREQ_POLICY_PERFORMANCE; + else + policy->policy = CPUFREQ_POLICY_POWERSAVE; return 0; } -static struct cpufreq_driver intel_pstate_driver = { +static struct cpufreq_driver intel_pstate = { .flags = CPUFREQ_CONST_LOOPS, .verify = intel_pstate_verify_policy, .setpolicy = intel_pstate_set_policy, - .resume = intel_pstate_hwp_set_policy, + .suspend = intel_pstate_hwp_save_state, + .resume = intel_pstate_resume, .get = intel_pstate_get, .init = intel_pstate_cpu_init, .exit = intel_pstate_cpu_exit, @@ -1646,6 +2085,118 @@ static struct cpufreq_driver intel_pstate_driver = { .name = "intel_pstate", }; +static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy) +{ + struct cpudata *cpu = all_cpu_data[policy->cpu]; + struct perf_limits *perf_limits = limits; + + update_turbo_state(); + policy->cpuinfo.max_freq = limits->turbo_disabled ? + cpu->pstate.max_freq : cpu->pstate.turbo_freq; + + cpufreq_verify_within_cpu_limits(policy); + + if (per_cpu_limits) + perf_limits = cpu->perf_limits; + + intel_pstate_update_perf_limits(policy, perf_limits); + + return 0; +} + +static unsigned int intel_cpufreq_turbo_update(struct cpudata *cpu, + struct cpufreq_policy *policy, + unsigned int target_freq) +{ + unsigned int max_freq; + + update_turbo_state(); + + max_freq = limits->no_turbo || limits->turbo_disabled ? + cpu->pstate.max_freq : cpu->pstate.turbo_freq; + policy->cpuinfo.max_freq = max_freq; + if (policy->max > max_freq) + policy->max = max_freq; + + if (target_freq > max_freq) + target_freq = max_freq; + + return target_freq; +} + +static int intel_cpufreq_target(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation) +{ + struct cpudata *cpu = all_cpu_data[policy->cpu]; + struct cpufreq_freqs freqs; + int target_pstate; + + freqs.old = policy->cur; + freqs.new = intel_cpufreq_turbo_update(cpu, policy, target_freq); + + cpufreq_freq_transition_begin(policy, &freqs); + switch (relation) { + case CPUFREQ_RELATION_L: + target_pstate = DIV_ROUND_UP(freqs.new, cpu->pstate.scaling); + break; + case CPUFREQ_RELATION_H: + target_pstate = freqs.new / cpu->pstate.scaling; + break; + default: + target_pstate = DIV_ROUND_CLOSEST(freqs.new, cpu->pstate.scaling); + break; + } + target_pstate = intel_pstate_prepare_request(cpu, target_pstate); + if (target_pstate != cpu->pstate.current_pstate) { + cpu->pstate.current_pstate = target_pstate; + wrmsrl_on_cpu(policy->cpu, MSR_IA32_PERF_CTL, + pstate_funcs.get_val(cpu, target_pstate)); + } + cpufreq_freq_transition_end(policy, &freqs, false); + + return 0; +} + +static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + struct cpudata *cpu = all_cpu_data[policy->cpu]; + int target_pstate; + + target_freq = intel_cpufreq_turbo_update(cpu, policy, target_freq); + target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling); + intel_pstate_update_pstate(cpu, target_pstate); + return target_freq; +} + +static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy) +{ + int ret = __intel_pstate_cpu_init(policy); + + if (ret) + return ret; + + policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY; + /* This reflects the intel_pstate_get_cpu_pstates() setting. */ + policy->cur = policy->cpuinfo.min_freq; + + return 0; +} + +static struct cpufreq_driver intel_cpufreq = { + .flags = CPUFREQ_CONST_LOOPS, + .verify = intel_cpufreq_verify_policy, + .target = intel_cpufreq_target, + .fast_switch = intel_cpufreq_fast_switch, + .init = intel_cpufreq_cpu_init, + .exit = intel_pstate_cpu_exit, + .stop_cpu = intel_cpufreq_stop_cpu, + .name = "intel_cpufreq", +}; + +static struct cpufreq_driver *intel_pstate_driver = &intel_pstate; + static int no_load __initdata; static int no_hwp __initdata; static int hwp_only __initdata; @@ -1672,6 +2223,19 @@ static void __init copy_pid_params(struct pstate_adjust_policy *policy) pid_params.setpoint = policy->setpoint; } +#ifdef CONFIG_ACPI +static void intel_pstate_use_acpi_profile(void) +{ + if (acpi_gbl_FADT.preferred_profile == PM_MOBILE) + pstate_funcs.get_target_pstate = + get_target_pstate_use_cpu_load; +} +#else +static void intel_pstate_use_acpi_profile(void) +{ +} +#endif + static void __init copy_cpu_funcs(struct pstate_funcs *funcs) { pstate_funcs.get_max = funcs->get_max; @@ -1683,6 +2247,7 @@ static void __init copy_cpu_funcs(struct pstate_funcs *funcs) pstate_funcs.get_vid = funcs->get_vid; pstate_funcs.get_target_pstate = funcs->get_target_pstate; + intel_pstate_use_acpi_profile(); } #ifdef CONFIG_ACPI @@ -1796,9 +2361,20 @@ static bool __init intel_pstate_platform_pwr_mgmt_exists(void) return false; } + +static void intel_pstate_request_control_from_smm(void) +{ + /* + * It may be unsafe to request P-states control from SMM if _PPC support + * has not been enabled. + */ + if (acpi_ppc) + acpi_processor_pstate_control(); +} #else /* CONFIG_ACPI not enabled */ static inline bool intel_pstate_platform_pwr_mgmt_exists(void) { return false; } static inline bool intel_pstate_has_acpi_ppc(void) { return false; } +static inline void intel_pstate_request_control_from_smm(void) {} #endif /* CONFIG_ACPI */ static const struct x86_cpu_id hwp_support_ids[] __initconst = { @@ -1818,6 +2394,7 @@ static int __init intel_pstate_init(void) if (x86_match_cpu(hwp_support_ids) && !no_hwp) { copy_cpu_funcs(&core_params.funcs); hwp_active++; + intel_pstate.attr = hwp_cpufreq_attrs; goto hwp_cpu_matched; } @@ -1850,7 +2427,9 @@ hwp_cpu_matched: if (!hwp_active && hwp_only) goto out; - rc = cpufreq_register_driver(&intel_pstate_driver); + intel_pstate_request_control_from_smm(); + + rc = cpufreq_register_driver(intel_pstate_driver); if (rc) goto out; @@ -1865,7 +2444,9 @@ out: get_online_cpus(); for_each_online_cpu(cpu) { if (all_cpu_data[cpu]) { - intel_pstate_clear_update_util_hook(cpu); + if (intel_pstate_driver == &intel_pstate) + intel_pstate_clear_update_util_hook(cpu); + kfree(all_cpu_data[cpu]); } } @@ -1881,8 +2462,13 @@ static int __init intel_pstate_setup(char *str) if (!str) return -EINVAL; - if (!strcmp(str, "disable")) + if (!strcmp(str, "disable")) { no_load = 1; + } else if (!strcmp(str, "passive")) { + pr_info("Passive mode enabled\n"); + intel_pstate_driver = &intel_cpufreq; + no_hwp = 1; + } if (!strcmp(str, "no_hwp")) { pr_info("HWP disabled\n"); no_hwp = 1; @@ -1891,6 +2477,8 @@ static int __init intel_pstate_setup(char *str) force_load = 1; if (!strcmp(str, "hwp_only")) hwp_only = 1; + if (!strcmp(str, "per_cpu_perf_limits")) + per_cpu_limits = true; #ifdef CONFIG_ACPI if (!strcmp(str, "support_acpi_ppc")) diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index d3ffde806629..37671b545880 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -42,6 +42,10 @@ #define PMSR_PSAFE_ENABLE (1UL << 30) #define PMSR_SPR_EM_DISABLE (1UL << 31) #define PMSR_MAX(x) ((x >> 32) & 0xFF) +#define LPSTATE_SHIFT 48 +#define GPSTATE_SHIFT 56 +#define GET_LPSTATE(x) (((x) >> LPSTATE_SHIFT) & 0xFF) +#define GET_GPSTATE(x) (((x) >> GPSTATE_SHIFT) & 0xFF) #define MAX_RAMP_DOWN_TIME 5120 /* @@ -592,7 +596,8 @@ void gpstate_timer_handler(unsigned long data) { struct cpufreq_policy *policy = (struct cpufreq_policy *)data; struct global_pstate_info *gpstates = policy->driver_data; - int gpstate_idx; + int gpstate_idx, lpstate_idx; + unsigned long val; unsigned int time_diff = jiffies_to_msecs(jiffies) - gpstates->last_sampled_time; struct powernv_smp_call_data freq_data; @@ -600,21 +605,37 @@ void gpstate_timer_handler(unsigned long data) if (!spin_trylock(&gpstates->gpstate_lock)) return; + /* + * If PMCR was last updated was using fast_swtich then + * We may have wrong in gpstate->last_lpstate_idx + * value. Hence, read from PMCR to get correct data. + */ + val = get_pmspr(SPRN_PMCR); + freq_data.gpstate_id = (s8)GET_GPSTATE(val); + freq_data.pstate_id = (s8)GET_LPSTATE(val); + if (freq_data.gpstate_id == freq_data.pstate_id) { + reset_gpstates(policy); + spin_unlock(&gpstates->gpstate_lock); + return; + } + gpstates->last_sampled_time += time_diff; gpstates->elapsed_time += time_diff; - freq_data.pstate_id = idx_to_pstate(gpstates->last_lpstate_idx); - if ((gpstates->last_gpstate_idx == gpstates->last_lpstate_idx) || - (gpstates->elapsed_time > MAX_RAMP_DOWN_TIME)) { + if (gpstates->elapsed_time > MAX_RAMP_DOWN_TIME) { gpstate_idx = pstate_to_idx(freq_data.pstate_id); + lpstate_idx = gpstate_idx; reset_gpstates(policy); gpstates->highest_lpstate_idx = gpstate_idx; } else { + lpstate_idx = pstate_to_idx(freq_data.pstate_id); gpstate_idx = calc_global_pstate(gpstates->elapsed_time, gpstates->highest_lpstate_idx, - gpstates->last_lpstate_idx); + lpstate_idx); } - + freq_data.gpstate_id = idx_to_pstate(gpstate_idx); + gpstates->last_gpstate_idx = gpstate_idx; + gpstates->last_lpstate_idx = lpstate_idx; /* * If local pstate is equal to global pstate, rampdown is over * So timer is not required to be queued. @@ -622,10 +643,6 @@ void gpstate_timer_handler(unsigned long data) if (gpstate_idx != gpstates->last_lpstate_idx) queue_gpstate_timer(gpstates); - freq_data.gpstate_id = idx_to_pstate(gpstate_idx); - gpstates->last_gpstate_idx = pstate_to_idx(freq_data.gpstate_id); - gpstates->last_lpstate_idx = pstate_to_idx(freq_data.pstate_id); - spin_unlock(&gpstates->gpstate_lock); /* Timer may get migrated to a different cpu on cpu hot unplug */ @@ -647,8 +664,14 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy, if (unlikely(rebooting) && new_index != get_nominal_index()) return 0; - if (!throttled) + if (!throttled) { + /* we don't want to be preempted while + * checking if the CPU frequency has been throttled + */ + preempt_disable(); powernv_cpufreq_throttle_check(NULL); + preempt_enable(); + } cur_msec = jiffies_to_msecs(get_jiffies_64()); @@ -752,9 +775,12 @@ static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy) spin_lock_init(&gpstates->gpstate_lock); ret = cpufreq_table_validate_and_show(policy, powernv_freqs); - if (ret < 0) + if (ret < 0) { kfree(policy->driver_data); + return ret; + } + policy->fast_switch_possible = true; return ret; } @@ -897,6 +923,20 @@ static void powernv_cpufreq_stop_cpu(struct cpufreq_policy *policy) del_timer_sync(&gpstates->timer); } +static unsigned int powernv_fast_switch(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + int index; + struct powernv_smp_call_data freq_data; + + index = cpufreq_table_find_index_dl(policy, target_freq); + freq_data.pstate_id = powernv_freqs[index].driver_data; + freq_data.gpstate_id = powernv_freqs[index].driver_data; + set_pstate(&freq_data); + + return powernv_freqs[index].frequency; +} + static struct cpufreq_driver powernv_cpufreq_driver = { .name = "powernv-cpufreq", .flags = CPUFREQ_CONST_LOOPS, @@ -904,6 +944,7 @@ static struct cpufreq_driver powernv_cpufreq_driver = { .exit = powernv_cpufreq_cpu_exit, .verify = cpufreq_generic_frequency_table_verify, .target_index = powernv_cpufreq_target_index, + .fast_switch = powernv_fast_switch, .get = powernv_cpufreq_get, .stop_cpu = powernv_cpufreq_stop_cpu, .attr = powernv_cpu_freq_attr, diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index 72ff19658985..e483b78c6343 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -558,8 +558,9 @@ static int caam_probe(struct platform_device *pdev) * Enable DECO watchdogs and, if this is a PHYS_ADDR_T_64BIT kernel, * long pointers in master configuration register */ - clrsetbits_32(&ctrl->mcr, MCFGR_AWCACHE_MASK, MCFGR_AWCACHE_CACH | - MCFGR_AWCACHE_BUFF | MCFGR_WDENABLE | MCFGR_LARGE_BURST | + clrsetbits_32(&ctrl->mcr, MCFGR_AWCACHE_MASK | MCFGR_LONG_PTR, + MCFGR_AWCACHE_CACH | MCFGR_AWCACHE_BUFF | + MCFGR_WDENABLE | MCFGR_LARGE_BURST | (sizeof(dma_addr_t) == sizeof(u64) ? MCFGR_LONG_PTR : 0)); /* diff --git a/drivers/crypto/chelsio/chcr_algo.h b/drivers/crypto/chelsio/chcr_algo.h index ec64fbcdeb49..199b0bb69b89 100644 --- a/drivers/crypto/chelsio/chcr_algo.h +++ b/drivers/crypto/chelsio/chcr_algo.h @@ -422,7 +422,7 @@ static inline void get_aes_decrypt_key(unsigned char *dec_key, { u32 temp; u32 w_ring[MAX_NK]; - int i, j, k = 0; + int i, j, k; u8 nr, nk; switch (keylength) { @@ -460,6 +460,7 @@ static inline void get_aes_decrypt_key(unsigned char *dec_key, temp = w_ring[i % nk]; i++; } + i--; for (k = 0, j = i % nk; k < nk; k++) { *((u32 *)dec_key + k) = htonl(w_ring[j]); j--; diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c index 9f284682c091..77712b375b84 100644 --- a/drivers/crypto/marvell/hash.c +++ b/drivers/crypto/marvell/hash.c @@ -168,12 +168,11 @@ static void mv_cesa_ahash_std_step(struct ahash_request *req) mv_cesa_adjust_op(engine, &creq->op_tmpl); memcpy_toio(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl)); - digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(req)); - for (i = 0; i < digsize / 4; i++) - writel_relaxed(creq->state[i], engine->regs + CESA_IVDIG(i)); - - mv_cesa_adjust_op(engine, &creq->op_tmpl); - memcpy_toio(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl)); + if (!sreq->offset) { + digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(req)); + for (i = 0; i < digsize / 4; i++) + writel_relaxed(creq->state[i], engine->regs + CESA_IVDIG(i)); + } if (creq->cache_ptr) memcpy_toio(engine->sram + CESA_SA_DATA_SRAM_OFFSET, diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c index 3d94ff20fdca..286447a83dab 100644 --- a/drivers/dax/dax.c +++ b/drivers/dax/dax.c @@ -271,7 +271,7 @@ static int check_vma(struct dax_dev *dax_dev, struct vm_area_struct *vma, return -ENXIO; /* prevent private mappings from being established */ - if ((vma->vm_flags & VM_SHARED) != VM_SHARED) { + if ((vma->vm_flags & VM_MAYSHARE) != VM_MAYSHARE) { dev_info(dev, "%s: %s: fail, attempted private mapping\n", current->comm, func); return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 496f72b134eb..05c2850c04b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -2472,6 +2472,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev, struct drm_file *file_priv); void amdgpu_driver_preclose_kms(struct drm_device *dev, struct drm_file *file_priv); +int amdgpu_suspend(struct amdgpu_device *adev); int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon); int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon); u32 amdgpu_get_vblank_counter_kms(struct drm_device *dev, unsigned int pipe); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index 02ca5dd978f6..6c343a933182 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -485,7 +485,6 @@ static int amdgpu_atpx_power_state(enum vga_switcheroo_client_id id, */ static bool amdgpu_atpx_pci_probe_handle(struct pci_dev *pdev) { - struct pci_dev *parent_pdev = pci_upstream_bridge(pdev); acpi_handle dhandle, atpx_handle; acpi_status status; @@ -500,7 +499,6 @@ static bool amdgpu_atpx_pci_probe_handle(struct pci_dev *pdev) } amdgpu_atpx_priv.dhandle = dhandle; amdgpu_atpx_priv.atpx.handle = atpx_handle; - amdgpu_atpx_priv.bridge_pm_usable = parent_pdev && parent_pdev->bridge_d3; return true; } @@ -562,17 +560,25 @@ static bool amdgpu_atpx_detect(void) struct pci_dev *pdev = NULL; bool has_atpx = false; int vga_count = 0; + bool d3_supported = false; + struct pci_dev *parent_pdev; while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) { vga_count++; has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true); + + parent_pdev = pci_upstream_bridge(pdev); + d3_supported |= parent_pdev && parent_pdev->bridge_d3; } while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) { vga_count++; has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true); + + parent_pdev = pci_upstream_bridge(pdev); + d3_supported |= parent_pdev && parent_pdev->bridge_d3; } if (has_atpx && vga_count == 2) { @@ -580,6 +586,7 @@ static bool amdgpu_atpx_detect(void) printk(KERN_INFO "vga_switcheroo: detected switching method %s handle\n", acpi_method_name); amdgpu_atpx_priv.atpx_detected = true; + amdgpu_atpx_priv.bridge_pm_usable = d3_supported; amdgpu_atpx_init(); return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3161d77bf299..e41d4baebf86 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1493,7 +1493,7 @@ static int amdgpu_fini(struct amdgpu_device *adev) return 0; } -static int amdgpu_suspend(struct amdgpu_device *adev) +int amdgpu_suspend(struct amdgpu_device *adev) { int i, r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 02ff0747197c..e0890deccb2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -479,12 +479,15 @@ amdgpu_pci_remove(struct pci_dev *pdev) static void amdgpu_pci_shutdown(struct pci_dev *pdev) { + struct drm_device *dev = pci_get_drvdata(pdev); + struct amdgpu_device *adev = dev->dev_private; + /* if we are running in a VM, make sure the device * torn down properly on reboot/shutdown. * unfortunately we can't detect certain * hypervisors so just do this all the time. */ - amdgpu_pci_remove(pdev); + amdgpu_suspend(adev); } static int amdgpu_pmops_suspend(struct device *dev) diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c index 4ccc0b72324d..71bb2f8dc157 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c @@ -2214,6 +2214,7 @@ uint32_t polaris10_get_mac_definition(uint32_t value) int polaris10_process_firmware_header(struct pp_hwmgr *hwmgr) { struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(hwmgr->smumgr->backend); + struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend); uint32_t tmp; int result; bool error = false; @@ -2233,8 +2234,10 @@ int polaris10_process_firmware_header(struct pp_hwmgr *hwmgr) offsetof(SMU74_Firmware_Header, SoftRegisters), &tmp, SMC_RAM_END); - if (!result) + if (!result) { + data->soft_regs_start = tmp; smu_data->smu7_data.soft_regs_start = tmp; + } error |= (0 != result); diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c index fb6a418ce6be..e138fb51e8ce 100644 --- a/drivers/gpu/drm/arm/hdlcd_drv.c +++ b/drivers/gpu/drm/arm/hdlcd_drv.c @@ -375,7 +375,6 @@ static int hdlcd_drm_bind(struct device *dev) err_fbdev: drm_kms_helper_poll_fini(drm); - drm_mode_config_cleanup(drm); drm_vblank_cleanup(drm); err_vblank: pm_runtime_disable(drm->dev); @@ -387,6 +386,7 @@ err_unload: drm_irq_uninstall(drm); of_reserved_mem_device_release(drm->dev); err_free: + drm_mode_config_cleanup(drm); dev_set_drvdata(dev, NULL); drm_dev_unref(drm); diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index 0ad2c47f808f..71c3473476c7 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -254,10 +254,12 @@ static int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_ req->value = dev->mode_config.async_page_flip; break; case DRM_CAP_PAGE_FLIP_TARGET: - req->value = 1; - drm_for_each_crtc(crtc, dev) { - if (!crtc->funcs->page_flip_target) - req->value = 0; + if (drm_core_check_feature(dev, DRIVER_MODESET)) { + req->value = 1; + drm_for_each_crtc(crtc, dev) { + if (!crtc->funcs->page_flip_target) + req->value = 0; + } } break; case DRM_CAP_CURSOR_WIDTH: diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 91ab7e9d6d2e..00eb4814b913 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2268,7 +2268,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) page = shmem_read_mapping_page(mapping, i); if (IS_ERR(page)) { ret = PTR_ERR(page); - goto err_pages; + goto err_sg; } } #ifdef CONFIG_SWIOTLB @@ -2311,8 +2311,9 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) return 0; -err_pages: +err_sg: sg_mark_end(sg); +err_pages: for_each_sgt_page(page, sgt_iter, st) put_page(page); sg_free_table(st); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 81c11499bcf0..3cb70d73239b 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -12260,7 +12260,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, intel_crtc->reset_count = i915_reset_count(&dev_priv->gpu_error); if (i915_reset_in_progress_or_wedged(&dev_priv->gpu_error)) { ret = -EIO; - goto cleanup; + goto unlock; } atomic_inc(&intel_crtc->unpin_work_count); @@ -12352,6 +12352,7 @@ cleanup_unpin: intel_unpin_fb_obj(fb, crtc->primary->state->rotation); cleanup_pending: atomic_dec(&intel_crtc->unpin_work_count); +unlock: mutex_unlock(&dev->struct_mutex); cleanup: crtc->primary->fb = old_fb; diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c index 4129b12521a6..0ae13cd2adda 100644 --- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c +++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c @@ -479,7 +479,6 @@ static int radeon_atpx_power_state(enum vga_switcheroo_client_id id, */ static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev) { - struct pci_dev *parent_pdev = pci_upstream_bridge(pdev); acpi_handle dhandle, atpx_handle; acpi_status status; @@ -493,7 +492,6 @@ static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev) radeon_atpx_priv.dhandle = dhandle; radeon_atpx_priv.atpx.handle = atpx_handle; - radeon_atpx_priv.bridge_pm_usable = parent_pdev && parent_pdev->bridge_d3; return true; } @@ -555,11 +553,16 @@ static bool radeon_atpx_detect(void) struct pci_dev *pdev = NULL; bool has_atpx = false; int vga_count = 0; + bool d3_supported = false; + struct pci_dev *parent_pdev; while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) { vga_count++; has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true); + + parent_pdev = pci_upstream_bridge(pdev); + d3_supported |= parent_pdev && parent_pdev->bridge_d3; } /* some newer PX laptops mark the dGPU as a non-VGA display device */ @@ -567,6 +570,9 @@ static bool radeon_atpx_detect(void) vga_count++; has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true); + + parent_pdev = pci_upstream_bridge(pdev); + d3_supported |= parent_pdev && parent_pdev->bridge_d3; } if (has_atpx && vga_count == 2) { @@ -574,6 +580,7 @@ static bool radeon_atpx_detect(void) printk(KERN_INFO "vga_switcheroo: detected switching method %s handle\n", acpi_method_name); radeon_atpx_priv.atpx_detected = true; + radeon_atpx_priv.bridge_pm_usable = d3_supported; radeon_atpx_init(); return true; } diff --git a/drivers/i2c/busses/i2c-octeon-core.c b/drivers/i2c/busses/i2c-octeon-core.c index 419b54bfc7c7..5e63b17f935d 100644 --- a/drivers/i2c/busses/i2c-octeon-core.c +++ b/drivers/i2c/busses/i2c-octeon-core.c @@ -381,9 +381,7 @@ static int octeon_i2c_read(struct octeon_i2c *i2c, int target, if (result) return result; - data[i] = octeon_i2c_data_read(i2c, &result); - if (result) - return result; + data[i] = octeon_i2c_data_read(i2c); if (recv_len && i == 0) { if (data[i] > I2C_SMBUS_BLOCK_MAX + 1) return -EPROTO; diff --git a/drivers/i2c/busses/i2c-octeon-core.h b/drivers/i2c/busses/i2c-octeon-core.h index 1db7c835a454..87151ea74acd 100644 --- a/drivers/i2c/busses/i2c-octeon-core.h +++ b/drivers/i2c/busses/i2c-octeon-core.h @@ -5,7 +5,6 @@ #include <linux/i2c.h> #include <linux/i2c-smbus.h> #include <linux/io.h> -#include <linux/iopoll.h> #include <linux/kernel.h> #include <linux/pci.h> @@ -145,9 +144,9 @@ static inline void octeon_i2c_reg_write(struct octeon_i2c *i2c, u64 eop_reg, u8 u64 tmp; __raw_writeq(SW_TWSI_V | eop_reg | data, i2c->twsi_base + SW_TWSI(i2c)); - - readq_poll_timeout(i2c->twsi_base + SW_TWSI(i2c), tmp, tmp & SW_TWSI_V, - I2C_OCTEON_EVENT_WAIT, i2c->adap.timeout); + do { + tmp = __raw_readq(i2c->twsi_base + SW_TWSI(i2c)); + } while ((tmp & SW_TWSI_V) != 0); } #define octeon_i2c_ctl_write(i2c, val) \ @@ -164,28 +163,24 @@ static inline void octeon_i2c_reg_write(struct octeon_i2c *i2c, u64 eop_reg, u8 * * The I2C core registers are accessed indirectly via the SW_TWSI CSR. */ -static inline int octeon_i2c_reg_read(struct octeon_i2c *i2c, u64 eop_reg, - int *error) +static inline u8 octeon_i2c_reg_read(struct octeon_i2c *i2c, u64 eop_reg) { u64 tmp; - int ret; __raw_writeq(SW_TWSI_V | eop_reg | SW_TWSI_R, i2c->twsi_base + SW_TWSI(i2c)); + do { + tmp = __raw_readq(i2c->twsi_base + SW_TWSI(i2c)); + } while ((tmp & SW_TWSI_V) != 0); - ret = readq_poll_timeout(i2c->twsi_base + SW_TWSI(i2c), tmp, - tmp & SW_TWSI_V, I2C_OCTEON_EVENT_WAIT, - i2c->adap.timeout); - if (error) - *error = ret; return tmp & 0xFF; } #define octeon_i2c_ctl_read(i2c) \ - octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_CTL, NULL) -#define octeon_i2c_data_read(i2c, error) \ - octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_DATA, error) + octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_CTL) +#define octeon_i2c_data_read(i2c) \ + octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_DATA) #define octeon_i2c_stat_read(i2c) \ - octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_STAT, NULL) + octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_STAT) /** * octeon_i2c_read_int - read the TWSI_INT register diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c index fb4b185dea96..bee267424972 100644 --- a/drivers/input/mouse/psmouse-base.c +++ b/drivers/input/mouse/psmouse-base.c @@ -1115,10 +1115,6 @@ static int psmouse_extensions(struct psmouse *psmouse, if (psmouse_try_protocol(psmouse, PSMOUSE_TOUCHKIT_PS2, &max_proto, set_properties, true)) return PSMOUSE_TOUCHKIT_PS2; - - if (psmouse_try_protocol(psmouse, PSMOUSE_BYD, - &max_proto, set_properties, true)) - return PSMOUSE_BYD; } /* diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c index d1f8ab915b15..b90776ef56ec 100644 --- a/drivers/isdn/gigaset/ser-gigaset.c +++ b/drivers/isdn/gigaset/ser-gigaset.c @@ -755,8 +755,10 @@ static int __init ser_gigaset_init(void) driver = gigaset_initdriver(GIGASET_MINOR, GIGASET_MINORS, GIGASET_MODULENAME, GIGASET_DEVNAME, &ops, THIS_MODULE); - if (!driver) + if (!driver) { + rc = -ENOMEM; goto error; + } rc = tty_register_ldisc(N_GIGASET_M101, &gigaset_ldisc); if (rc != 0) { diff --git a/drivers/isdn/hisax/hfc4s8s_l1.c b/drivers/isdn/hisax/hfc4s8s_l1.c index 9600cd771f1a..e034ed847ff3 100644 --- a/drivers/isdn/hisax/hfc4s8s_l1.c +++ b/drivers/isdn/hisax/hfc4s8s_l1.c @@ -1499,6 +1499,7 @@ hfc4s8s_probe(struct pci_dev *pdev, const struct pci_device_id *ent) printk(KERN_INFO "HFC-4S/8S: failed to request address space at 0x%04x\n", hw->iobase); + err = -EBUSY; goto out; } diff --git a/drivers/net/can/usb/peak_usb/pcan_ucan.h b/drivers/net/can/usb/peak_usb/pcan_ucan.h index e8fc4952c6b0..2147678f0225 100644 --- a/drivers/net/can/usb/peak_usb/pcan_ucan.h +++ b/drivers/net/can/usb/peak_usb/pcan_ucan.h @@ -43,11 +43,22 @@ struct __packed pucan_command { u16 args[3]; }; +#define PUCAN_TSLOW_BRP_BITS 10 +#define PUCAN_TSLOW_TSGEG1_BITS 8 +#define PUCAN_TSLOW_TSGEG2_BITS 7 +#define PUCAN_TSLOW_SJW_BITS 7 + +#define PUCAN_TSLOW_BRP_MASK ((1 << PUCAN_TSLOW_BRP_BITS) - 1) +#define PUCAN_TSLOW_TSEG1_MASK ((1 << PUCAN_TSLOW_TSGEG1_BITS) - 1) +#define PUCAN_TSLOW_TSEG2_MASK ((1 << PUCAN_TSLOW_TSGEG2_BITS) - 1) +#define PUCAN_TSLOW_SJW_MASK ((1 << PUCAN_TSLOW_SJW_BITS) - 1) + /* uCAN TIMING_SLOW command fields */ -#define PUCAN_TSLOW_SJW_T(s, t) (((s) & 0xf) | ((!!(t)) << 7)) -#define PUCAN_TSLOW_TSEG2(t) ((t) & 0xf) -#define PUCAN_TSLOW_TSEG1(t) ((t) & 0x3f) -#define PUCAN_TSLOW_BRP(b) ((b) & 0x3ff) +#define PUCAN_TSLOW_SJW_T(s, t) (((s) & PUCAN_TSLOW_SJW_MASK) | \ + ((!!(t)) << 7)) +#define PUCAN_TSLOW_TSEG2(t) ((t) & PUCAN_TSLOW_TSEG2_MASK) +#define PUCAN_TSLOW_TSEG1(t) ((t) & PUCAN_TSLOW_TSEG1_MASK) +#define PUCAN_TSLOW_BRP(b) ((b) & PUCAN_TSLOW_BRP_MASK) struct __packed pucan_timing_slow { __le16 opcode_channel; @@ -60,11 +71,21 @@ struct __packed pucan_timing_slow { __le16 brp; /* BaudRate Prescaler */ }; +#define PUCAN_TFAST_BRP_BITS 10 +#define PUCAN_TFAST_TSGEG1_BITS 5 +#define PUCAN_TFAST_TSGEG2_BITS 4 +#define PUCAN_TFAST_SJW_BITS 4 + +#define PUCAN_TFAST_BRP_MASK ((1 << PUCAN_TFAST_BRP_BITS) - 1) +#define PUCAN_TFAST_TSEG1_MASK ((1 << PUCAN_TFAST_TSGEG1_BITS) - 1) +#define PUCAN_TFAST_TSEG2_MASK ((1 << PUCAN_TFAST_TSGEG2_BITS) - 1) +#define PUCAN_TFAST_SJW_MASK ((1 << PUCAN_TFAST_SJW_BITS) - 1) + /* uCAN TIMING_FAST command fields */ -#define PUCAN_TFAST_SJW(s) ((s) & 0x3) -#define PUCAN_TFAST_TSEG2(t) ((t) & 0x7) -#define PUCAN_TFAST_TSEG1(t) ((t) & 0xf) -#define PUCAN_TFAST_BRP(b) ((b) & 0x3ff) +#define PUCAN_TFAST_SJW(s) ((s) & PUCAN_TFAST_SJW_MASK) +#define PUCAN_TFAST_TSEG2(t) ((t) & PUCAN_TFAST_TSEG2_MASK) +#define PUCAN_TFAST_TSEG1(t) ((t) & PUCAN_TFAST_TSEG1_MASK) +#define PUCAN_TFAST_BRP(b) ((b) & PUCAN_TFAST_BRP_MASK) struct __packed pucan_timing_fast { __le16 opcode_channel; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index c06382cdfdfe..0b0302af3bd2 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -39,6 +39,7 @@ static struct usb_device_id peak_usb_table[] = { {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBPRO_PRODUCT_ID)}, {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBFD_PRODUCT_ID)}, {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBPROFD_PRODUCT_ID)}, + {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBX6_PRODUCT_ID)}, {} /* Terminating entry */ }; @@ -50,6 +51,7 @@ static const struct peak_usb_adapter *const peak_usb_adapters_list[] = { &pcan_usb_pro, &pcan_usb_fd, &pcan_usb_pro_fd, + &pcan_usb_x6, }; /* @@ -868,23 +870,25 @@ lbl_free_candev: static void peak_usb_disconnect(struct usb_interface *intf) { struct peak_usb_device *dev; + struct peak_usb_device *dev_prev_siblings; /* unregister as many netdev devices as siblings */ - for (dev = usb_get_intfdata(intf); dev; dev = dev->prev_siblings) { + for (dev = usb_get_intfdata(intf); dev; dev = dev_prev_siblings) { struct net_device *netdev = dev->netdev; char name[IFNAMSIZ]; + dev_prev_siblings = dev->prev_siblings; dev->state &= ~PCAN_USB_STATE_CONNECTED; strncpy(name, netdev->name, IFNAMSIZ); unregister_netdev(netdev); - free_candev(netdev); kfree(dev->cmd_buf); dev->next_siblings = NULL; if (dev->adapter->dev_free) dev->adapter->dev_free(dev); + free_candev(netdev); dev_info(&intf->dev, "%s removed\n", name); } diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.h b/drivers/net/can/usb/peak_usb/pcan_usb_core.h index 506fe506c9d3..3cbfb069893d 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.h +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.h @@ -27,6 +27,7 @@ #define PCAN_USBPRO_PRODUCT_ID 0x000d #define PCAN_USBPROFD_PRODUCT_ID 0x0011 #define PCAN_USBFD_PRODUCT_ID 0x0012 +#define PCAN_USBX6_PRODUCT_ID 0x0014 #define PCAN_USB_DRIVER_NAME "peak_usb" @@ -90,6 +91,7 @@ extern const struct peak_usb_adapter pcan_usb; extern const struct peak_usb_adapter pcan_usb_pro; extern const struct peak_usb_adapter pcan_usb_fd; extern const struct peak_usb_adapter pcan_usb_pro_fd; +extern const struct peak_usb_adapter pcan_usb_x6; struct peak_time_ref { struct timeval tv_host_0, tv_host; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index ce44a033f63b..304732550f0a 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -993,24 +993,24 @@ static void pcan_usb_fd_free(struct peak_usb_device *dev) static const struct can_bittiming_const pcan_usb_fd_const = { .name = "pcan_usb_fd", .tseg1_min = 1, - .tseg1_max = 64, + .tseg1_max = (1 << PUCAN_TSLOW_TSGEG1_BITS), .tseg2_min = 1, - .tseg2_max = 16, - .sjw_max = 16, + .tseg2_max = (1 << PUCAN_TSLOW_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TSLOW_SJW_BITS), .brp_min = 1, - .brp_max = 1024, + .brp_max = (1 << PUCAN_TSLOW_BRP_BITS), .brp_inc = 1, }; static const struct can_bittiming_const pcan_usb_fd_data_const = { .name = "pcan_usb_fd", .tseg1_min = 1, - .tseg1_max = 16, + .tseg1_max = (1 << PUCAN_TFAST_TSGEG1_BITS), .tseg2_min = 1, - .tseg2_max = 8, - .sjw_max = 4, + .tseg2_max = (1 << PUCAN_TFAST_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TFAST_SJW_BITS), .brp_min = 1, - .brp_max = 1024, + .brp_max = (1 << PUCAN_TFAST_BRP_BITS), .brp_inc = 1, }; @@ -1065,24 +1065,24 @@ const struct peak_usb_adapter pcan_usb_fd = { static const struct can_bittiming_const pcan_usb_pro_fd_const = { .name = "pcan_usb_pro_fd", .tseg1_min = 1, - .tseg1_max = 64, + .tseg1_max = (1 << PUCAN_TSLOW_TSGEG1_BITS), .tseg2_min = 1, - .tseg2_max = 16, - .sjw_max = 16, + .tseg2_max = (1 << PUCAN_TSLOW_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TSLOW_SJW_BITS), .brp_min = 1, - .brp_max = 1024, + .brp_max = (1 << PUCAN_TSLOW_BRP_BITS), .brp_inc = 1, }; static const struct can_bittiming_const pcan_usb_pro_fd_data_const = { .name = "pcan_usb_pro_fd", .tseg1_min = 1, - .tseg1_max = 16, + .tseg1_max = (1 << PUCAN_TFAST_TSGEG1_BITS), .tseg2_min = 1, - .tseg2_max = 8, - .sjw_max = 4, + .tseg2_max = (1 << PUCAN_TFAST_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TFAST_SJW_BITS), .brp_min = 1, - .brp_max = 1024, + .brp_max = (1 << PUCAN_TFAST_BRP_BITS), .brp_inc = 1, }; @@ -1132,3 +1132,75 @@ const struct peak_usb_adapter pcan_usb_pro_fd = { .do_get_berr_counter = pcan_usb_fd_get_berr_counter, }; + +/* describes the PCAN-USB X6 adapter */ +static const struct can_bittiming_const pcan_usb_x6_const = { + .name = "pcan_usb_x6", + .tseg1_min = 1, + .tseg1_max = (1 << PUCAN_TSLOW_TSGEG1_BITS), + .tseg2_min = 1, + .tseg2_max = (1 << PUCAN_TSLOW_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TSLOW_SJW_BITS), + .brp_min = 1, + .brp_max = (1 << PUCAN_TSLOW_BRP_BITS), + .brp_inc = 1, +}; + +static const struct can_bittiming_const pcan_usb_x6_data_const = { + .name = "pcan_usb_x6", + .tseg1_min = 1, + .tseg1_max = (1 << PUCAN_TFAST_TSGEG1_BITS), + .tseg2_min = 1, + .tseg2_max = (1 << PUCAN_TFAST_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TFAST_SJW_BITS), + .brp_min = 1, + .brp_max = (1 << PUCAN_TFAST_BRP_BITS), + .brp_inc = 1, +}; + +const struct peak_usb_adapter pcan_usb_x6 = { + .name = "PCAN-USB X6", + .device_id = PCAN_USBX6_PRODUCT_ID, + .ctrl_count = PCAN_USBPROFD_CHANNEL_COUNT, + .ctrlmode_supported = CAN_CTRLMODE_FD | + CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY, + .clock = { + .freq = PCAN_UFD_CRYSTAL_HZ, + }, + .bittiming_const = &pcan_usb_x6_const, + .data_bittiming_const = &pcan_usb_x6_data_const, + + /* size of device private data */ + .sizeof_dev_private = sizeof(struct pcan_usb_fd_device), + + /* timestamps usage */ + .ts_used_bits = 32, + .ts_period = 1000000, /* calibration period in ts. */ + .us_per_ts_scale = 1, /* us = (ts * scale) >> shift */ + .us_per_ts_shift = 0, + + /* give here messages in/out endpoints */ + .ep_msg_in = PCAN_USBPRO_EP_MSGIN, + .ep_msg_out = {PCAN_USBPRO_EP_MSGOUT_0, PCAN_USBPRO_EP_MSGOUT_1}, + + /* size of rx/tx usb buffers */ + .rx_buffer_size = PCAN_UFD_RX_BUFFER_SIZE, + .tx_buffer_size = PCAN_UFD_TX_BUFFER_SIZE, + + /* device callbacks */ + .intf_probe = pcan_usb_pro_probe, /* same as PCAN-USB Pro */ + .dev_init = pcan_usb_fd_init, + + .dev_exit = pcan_usb_fd_exit, + .dev_free = pcan_usb_fd_free, + .dev_set_bus = pcan_usb_fd_set_bus, + .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow, + .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast, + .dev_decode_buf = pcan_usb_fd_decode_buf, + .dev_start = pcan_usb_fd_start, + .dev_stop = pcan_usb_fd_stop, + .dev_restart_async = pcan_usb_fd_restart_async, + .dev_encode_msg = pcan_usb_fd_encode_msg, + + .do_get_berr_counter = pcan_usb_fd_get_berr_counter, +}; diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index bda31f308cc2..a0eee7218695 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -400,12 +400,6 @@ static int tse_rx(struct altera_tse_private *priv, int limit) skb_put(skb, pktlength); - /* make cache consistent with receive packet buffer */ - dma_sync_single_for_cpu(priv->device, - priv->rx_ring[entry].dma_addr, - priv->rx_ring[entry].len, - DMA_FROM_DEVICE); - dma_unmap_single(priv->device, priv->rx_ring[entry].dma_addr, priv->rx_ring[entry].len, DMA_FROM_DEVICE); @@ -469,7 +463,6 @@ static int tse_tx_complete(struct altera_tse_private *priv) if (unlikely(netif_queue_stopped(priv->dev) && tse_tx_avail(priv) > TSE_TX_THRESH(priv))) { - netif_tx_lock(priv->dev); if (netif_queue_stopped(priv->dev) && tse_tx_avail(priv) > TSE_TX_THRESH(priv)) { if (netif_msg_tx_done(priv)) @@ -477,7 +470,6 @@ static int tse_tx_complete(struct altera_tse_private *priv) __func__); netif_wake_queue(priv->dev); } - netif_tx_unlock(priv->dev); } spin_unlock(&priv->tx_lock); @@ -592,10 +584,6 @@ static int tse_start_xmit(struct sk_buff *skb, struct net_device *dev) buffer->dma_addr = dma_addr; buffer->len = nopaged_len; - /* Push data out of the cache hierarchy into main memory */ - dma_sync_single_for_device(priv->device, buffer->dma_addr, - buffer->len, DMA_TO_DEVICE); - priv->dmaops->tx_buffer(priv, buffer); skb_tx_timestamp(skb); @@ -819,6 +807,8 @@ static int init_phy(struct net_device *dev) if (!phydev) { netdev_err(dev, "Could not find the PHY\n"); + if (fixed_link) + of_phy_deregister_fixed_link(priv->device->of_node); return -ENODEV; } @@ -1545,10 +1535,15 @@ err_free_netdev: static int altera_tse_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); + struct altera_tse_private *priv = netdev_priv(ndev); - if (ndev->phydev) + if (ndev->phydev) { phy_disconnect(ndev->phydev); + if (of_phy_is_fixed_link(priv->device->of_node)) + of_phy_deregister_fixed_link(priv->device->of_node); + } + platform_set_drvdata(pdev, NULL); altera_tse_mdio_destroy(ndev); unregister_netdev(ndev); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index 9de078819aa6..4f7635178200 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -829,7 +829,7 @@ static int xgbe_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static int xgbe_suspend(struct device *dev) { struct net_device *netdev = dev_get_drvdata(dev); @@ -874,7 +874,7 @@ static int xgbe_resume(struct device *dev) return ret; } -#endif /* CONFIG_PM */ +#endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_ACPI static const struct acpi_device_id xgbe_acpi_match[] = { diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index 00c38bf151e6..e078d8da978c 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -1466,12 +1466,12 @@ static int nb8800_probe(struct platform_device *pdev) ret = nb8800_hw_init(dev); if (ret) - goto err_free_bus; + goto err_deregister_fixed_link; if (ops && ops->init) { ret = ops->init(dev); if (ret) - goto err_free_bus; + goto err_deregister_fixed_link; } dev->netdev_ops = &nb8800_netdev_ops; @@ -1504,6 +1504,9 @@ static int nb8800_probe(struct platform_device *pdev) err_free_dma: nb8800_dma_free(dev); +err_deregister_fixed_link: + if (of_phy_is_fixed_link(pdev->dev.of_node)) + of_phy_deregister_fixed_link(pdev->dev.of_node); err_free_bus: of_node_put(priv->phy_node); mdiobus_unregister(bus); @@ -1521,6 +1524,8 @@ static int nb8800_remove(struct platform_device *pdev) struct nb8800_priv *priv = netdev_priv(ndev); unregister_netdev(ndev); + if (of_phy_is_fixed_link(pdev->dev.of_node)) + of_phy_deregister_fixed_link(pdev->dev.of_node); of_node_put(priv->phy_node); mdiobus_unregister(priv->mii_bus); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index c3354b9941d1..25d1eb4933d0 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1755,13 +1755,13 @@ static int bcm_sysport_probe(struct platform_device *pdev) if (priv->irq0 <= 0 || priv->irq1 <= 0) { dev_err(&pdev->dev, "invalid interrupts\n"); ret = -EINVAL; - goto err; + goto err_free_netdev; } priv->base = devm_ioremap_resource(&pdev->dev, r); if (IS_ERR(priv->base)) { ret = PTR_ERR(priv->base); - goto err; + goto err_free_netdev; } priv->netdev = dev; @@ -1779,7 +1779,7 @@ static int bcm_sysport_probe(struct platform_device *pdev) ret = of_phy_register_fixed_link(dn); if (ret) { dev_err(&pdev->dev, "failed to register fixed PHY\n"); - goto err; + goto err_free_netdev; } priv->phy_dn = dn; @@ -1821,7 +1821,7 @@ static int bcm_sysport_probe(struct platform_device *pdev) ret = register_netdev(dev); if (ret) { dev_err(&pdev->dev, "failed to register net_device\n"); - goto err; + goto err_deregister_fixed_link; } priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK; @@ -1832,7 +1832,11 @@ static int bcm_sysport_probe(struct platform_device *pdev) priv->base, priv->irq0, priv->irq1, txq, rxq); return 0; -err: + +err_deregister_fixed_link: + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); +err_free_netdev: free_netdev(dev); return ret; } @@ -1840,11 +1844,14 @@ err: static int bcm_sysport_remove(struct platform_device *pdev) { struct net_device *dev = dev_get_drvdata(&pdev->dev); + struct device_node *dn = pdev->dev.of_node; /* Not much to do, ndo_close has been called * and we use managed allocations */ unregister_netdev(dev); + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); free_netdev(dev); dev_set_drvdata(&pdev->dev, NULL); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 85a7800bfc12..5f19427c7b27 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -1872,8 +1872,16 @@ static void bnx2x_get_ringparam(struct net_device *dev, ering->rx_max_pending = MAX_RX_AVAIL; + /* If size isn't already set, we give an estimation of the number + * of buffers we'll have. We're neglecting some possible conditions + * [we couldn't know for certain at this point if number of queues + * might shrink] but the number would be correct for the likely + * scenario. + */ if (bp->rx_ring_size) ering->rx_pending = bp->rx_ring_size; + else if (BNX2X_NUM_RX_QUEUES(bp)) + ering->rx_pending = MAX_RX_AVAIL / BNX2X_NUM_RX_QUEUES(bp); else ering->rx_pending = MAX_RX_AVAIL; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 0cee4c0283f9..4febe60eadc2 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -10138,7 +10138,7 @@ static void __bnx2x_add_udp_port(struct bnx2x *bp, u16 port, { struct bnx2x_udp_tunnel *udp_port = &bp->udp_tunnel_ports[type]; - if (!netif_running(bp->dev) || !IS_PF(bp)) + if (!netif_running(bp->dev) || !IS_PF(bp) || CHIP_IS_E1x(bp)) return; if (udp_port->count && udp_port->dst_port == port) { @@ -10163,7 +10163,7 @@ static void __bnx2x_del_udp_port(struct bnx2x *bp, u16 port, { struct bnx2x_udp_tunnel *udp_port = &bp->udp_tunnel_ports[type]; - if (!IS_PF(bp)) + if (!IS_PF(bp) || CHIP_IS_E1x(bp)) return; if (!udp_port->count || udp_port->dst_port != port) { @@ -13505,6 +13505,7 @@ static int bnx2x_init_firmware(struct bnx2x *bp) /* Initialize the pointers to the init arrays */ /* Blob */ + rc = -ENOMEM; BNX2X_ALLOC_AND_SET(init_data, request_firmware_exit, be32_to_cpu_n); /* Opcodes */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index ee1a803aa11a..f08a20b921e7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4120,7 +4120,7 @@ static int bnxt_hwrm_stat_ctx_alloc(struct bnxt *bp) bp->grp_info[i].fw_stats_ctx = cpr->hw_stats_ctx_id; } mutex_unlock(&bp->hwrm_cmd_lock); - return 0; + return rc; } static int bnxt_hwrm_func_qcfg(struct bnxt *bp) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 4464bc5db934..a4e60e56c14f 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1172,6 +1172,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, struct bcmgenet_tx_ring *ring) { struct bcmgenet_priv *priv = netdev_priv(dev); + struct device *kdev = &priv->pdev->dev; struct enet_cb *tx_cb_ptr; struct netdev_queue *txq; unsigned int pkts_compl = 0; @@ -1199,13 +1200,13 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, if (tx_cb_ptr->skb) { pkts_compl++; bytes_compl += GENET_CB(tx_cb_ptr->skb)->bytes_sent; - dma_unmap_single(&dev->dev, + dma_unmap_single(kdev, dma_unmap_addr(tx_cb_ptr, dma_addr), dma_unmap_len(tx_cb_ptr, dma_len), DMA_TO_DEVICE); bcmgenet_free_cb(tx_cb_ptr); } else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) { - dma_unmap_page(&dev->dev, + dma_unmap_page(kdev, dma_unmap_addr(tx_cb_ptr, dma_addr), dma_unmap_len(tx_cb_ptr, dma_len), DMA_TO_DEVICE); @@ -1775,6 +1776,7 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv, static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv) { + struct device *kdev = &priv->pdev->dev; struct enet_cb *cb; int i; @@ -1782,7 +1784,7 @@ static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv) cb = &priv->rx_cbs[i]; if (dma_unmap_addr(cb, dma_addr)) { - dma_unmap_single(&priv->dev->dev, + dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr), priv->rx_buf_len, DMA_FROM_DEVICE); dma_unmap_addr_set(cb, dma_addr, 0); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 457c3bc8cfff..e87607621e62 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -542,8 +542,10 @@ static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv) /* Make sure we initialize MoCA PHYs with a link down */ if (phy_mode == PHY_INTERFACE_MODE_MOCA) { phydev = of_phy_find_device(dn); - if (phydev) + if (phydev) { phydev->link = 0; + put_device(&phydev->mdio.dev); + } } return 0; @@ -625,6 +627,7 @@ static int bcmgenet_mii_bus_init(struct bcmgenet_priv *priv) int bcmgenet_mii_init(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); + struct device_node *dn = priv->pdev->dev.of_node; int ret; ret = bcmgenet_mii_alloc(priv); @@ -638,6 +641,8 @@ int bcmgenet_mii_init(struct net_device *dev) return 0; out: + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); of_node_put(priv->phy_dn); mdiobus_unregister(priv->mii_bus); mdiobus_free(priv->mii_bus); @@ -647,7 +652,10 @@ out: void bcmgenet_mii_exit(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); + struct device_node *dn = priv->pdev->dev.of_node; + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); of_node_put(priv->phy_dn); mdiobus_unregister(priv->mii_bus); mdiobus_free(priv->mii_bus); diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 533653bd7aec..ec09fcece711 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -975,6 +975,7 @@ static inline void macb_init_rx_ring(struct macb *bp) addr += bp->rx_buffer_size; } bp->rx_ring[RX_RING_SIZE - 1].addr |= MACB_BIT(RX_WRAP); + bp->rx_tail = 0; } static int macb_rx(struct macb *bp, int budget) @@ -1156,6 +1157,7 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) if (status & MACB_BIT(RXUBR)) { ctrl = macb_readl(bp, NCR); macb_writel(bp, NCR, ctrl & ~MACB_BIT(RE)); + wmb(); macb_writel(bp, NCR, ctrl | MACB_BIT(RE)); if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) @@ -1616,8 +1618,6 @@ static void macb_init_rings(struct macb *bp) bp->queues[0].tx_head = 0; bp->queues[0].tx_tail = 0; bp->queues[0].tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP); - - bp->rx_tail = 0; } static void macb_reset_hw(struct macb *bp) @@ -2770,6 +2770,7 @@ static irqreturn_t at91ether_interrupt(int irq, void *dev_id) if (intstatus & MACB_BIT(RXUBR)) { ctl = macb_readl(lp, NCR); macb_writel(lp, NCR, ctl & ~MACB_BIT(RE)); + wmb(); macb_writel(lp, NCR, ctl | MACB_BIT(RE)); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 57eb4e1345cb..19dc9e25aa72 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -4931,6 +4931,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) */ for_each_port(adapter, i) { pi = adap2pinfo(adapter, i); + adapter->port[i]->dev_port = pi->lport; netif_set_real_num_tx_queues(adapter->port[i], pi->nqsets); netif_set_real_num_rx_queues(adapter->port[i], pi->nqsets); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 20dec85da63d..e8139514d32c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -7851,7 +7851,6 @@ int t4_port_init(struct adapter *adap, int mbox, int pf, int vf) return ret; memcpy(adap->port[i]->dev_addr, addr, ETH_ALEN); - adap->port[i]->dev_port = j; j++; } return 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index df1573c4a659..ecf3ccc257bc 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -168,6 +168,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x509a), /* Custom T520-CR */ CH_PCI_ID_TABLE_FENTRY(0x509b), /* Custom T540-CR LOM */ CH_PCI_ID_TABLE_FENTRY(0x509c), /* Custom T520-CR*/ + CH_PCI_ID_TABLE_FENTRY(0x509d), /* Custom T540-CR*/ /* T6 adapters: */ diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 100b2cc064a3..a37481c04a87 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -2969,6 +2969,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, netdev->netdev_ops = &cxgb4vf_netdev_ops; netdev->ethtool_ops = &cxgb4vf_ethtool_ops; + netdev->dev_port = pi->port_id; /* * Initialize the hardware/software state for the port. diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c index de9f7c97d916..9a161e981529 100644 --- a/drivers/net/ethernet/cirrus/ep93xx_eth.c +++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c @@ -468,6 +468,9 @@ static void ep93xx_free_buffers(struct ep93xx_priv *ep) struct device *dev = ep->dev->dev.parent; int i; + if (!ep->descs) + return; + for (i = 0; i < RX_QUEUE_ENTRIES; i++) { dma_addr_t d; @@ -490,6 +493,7 @@ static void ep93xx_free_buffers(struct ep93xx_priv *ep) dma_free_coherent(dev, sizeof(struct ep93xx_descs), ep->descs, ep->descs_dma_addr); + ep->descs = NULL; } static int ep93xx_alloc_buffers(struct ep93xx_priv *ep) diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 1fb5d7239254..0e74529a4209 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -90,7 +90,8 @@ static struct be_cmd_priv_map cmd_priv_map[] = { { OPCODE_COMMON_SET_HSW_CONFIG, CMD_SUBSYSTEM_COMMON, - BE_PRIV_DEVCFG | BE_PRIV_VHADM + BE_PRIV_DEVCFG | BE_PRIV_VHADM | + BE_PRIV_DEVSEC }, { OPCODE_COMMON_GET_EXT_FAT_CAPABILITIES, diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index c865135f3cb9..5ea740b4cf14 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -574,6 +574,8 @@ struct fec_enet_private { unsigned int reload_period; int pps_enable; unsigned int next_counter; + + u64 ethtool_stats[0]; }; void fec_ptp_init(struct platform_device *pdev); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 5aa9d4ded214..12aef1b15356 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2313,14 +2313,26 @@ static const struct fec_stat { { "IEEE_rx_octets_ok", IEEE_R_OCTETS_OK }, }; -static void fec_enet_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, u64 *data) +#define FEC_STATS_SIZE (ARRAY_SIZE(fec_stats) * sizeof(u64)) + +static void fec_enet_update_ethtool_stats(struct net_device *dev) { struct fec_enet_private *fep = netdev_priv(dev); int i; for (i = 0; i < ARRAY_SIZE(fec_stats); i++) - data[i] = readl(fep->hwp + fec_stats[i].offset); + fep->ethtool_stats[i] = readl(fep->hwp + fec_stats[i].offset); +} + +static void fec_enet_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct fec_enet_private *fep = netdev_priv(dev); + + if (netif_running(dev)) + fec_enet_update_ethtool_stats(dev); + + memcpy(data, fep->ethtool_stats, FEC_STATS_SIZE); } static void fec_enet_get_strings(struct net_device *netdev, @@ -2345,6 +2357,12 @@ static int fec_enet_get_sset_count(struct net_device *dev, int sset) return -EOPNOTSUPP; } } + +#else /* !defined(CONFIG_M5272) */ +#define FEC_STATS_SIZE 0 +static inline void fec_enet_update_ethtool_stats(struct net_device *dev) +{ +} #endif /* !defined(CONFIG_M5272) */ static int fec_enet_nway_reset(struct net_device *dev) @@ -2874,6 +2892,8 @@ fec_enet_close(struct net_device *ndev) if (fep->quirks & FEC_QUIRK_ERR006687) imx6q_cpuidle_fec_irqs_unused(); + fec_enet_update_ethtool_stats(ndev); + fec_enet_clk_enable(ndev, false); pinctrl_pm_select_sleep_state(&fep->pdev->dev); pm_runtime_mark_last_busy(&fep->pdev->dev); @@ -3180,6 +3200,8 @@ static int fec_enet_init(struct net_device *ndev) fec_restart(ndev); + fec_enet_update_ethtool_stats(ndev); + return 0; } @@ -3278,8 +3300,8 @@ fec_probe(struct platform_device *pdev) fec_enet_get_queue_num(pdev, &num_tx_qs, &num_rx_qs); /* Init network device */ - ndev = alloc_etherdev_mqs(sizeof(struct fec_enet_private), - num_tx_qs, num_rx_qs); + ndev = alloc_etherdev_mqs(sizeof(struct fec_enet_private) + + FEC_STATS_SIZE, num_tx_qs, num_rx_qs); if (!ndev) return -ENOMEM; @@ -3475,6 +3497,8 @@ failed_regulator: failed_clk_ipg: fec_enet_clk_enable(ndev, false); failed_clk: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); failed_phy: of_node_put(phy_node); failed_ioremap: @@ -3488,6 +3512,7 @@ fec_drv_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); + struct device_node *np = pdev->dev.of_node; cancel_work_sync(&fep->tx_timeout_work); fec_ptp_stop(pdev); @@ -3495,6 +3520,8 @@ fec_drv_remove(struct platform_device *pdev) fec_enet_mii_remove(fep); if (fep->reg_phy) regulator_disable(fep->reg_phy); + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); of_node_put(fep->phy_node); free_netdev(ndev); diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 53ef51e3bd9e..71a5ded9d1de 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -1107,6 +1107,9 @@ int memac_free(struct fman_mac *memac) { free_init_resources(memac); + if (memac->pcsphy) + put_device(&memac->pcsphy->mdio.dev); + kfree(memac->memac_drv_param); kfree(memac); diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 8fe6b3e253fa..736db9d9b0ad 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -892,6 +892,8 @@ static int mac_probe(struct platform_device *_of_dev) priv->fixed_link->duplex = phy->duplex; priv->fixed_link->pause = phy->pause; priv->fixed_link->asym_pause = phy->asym_pause; + + put_device(&phy->mdio.dev); } err = mac_dev->init(mac_dev); diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index dc120c148d97..4b86260584a0 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -980,7 +980,7 @@ static int fs_enet_probe(struct platform_device *ofdev) err = clk_prepare_enable(clk); if (err) { ret = err; - goto out_free_fpi; + goto out_deregister_fixed_link; } fpi->clk_per = clk; } @@ -1061,6 +1061,9 @@ out_put: of_node_put(fpi->phy_node); if (fpi->clk_per) clk_disable_unprepare(fpi->clk_per); +out_deregister_fixed_link: + if (of_phy_is_fixed_link(ofdev->dev.of_node)) + of_phy_deregister_fixed_link(ofdev->dev.of_node); out_free_fpi: kfree(fpi); return ret; @@ -1079,6 +1082,8 @@ static int fs_enet_remove(struct platform_device *ofdev) of_node_put(fep->fpi->phy_node); if (fep->fpi->clk_per) clk_disable_unprepare(fep->fpi->clk_per); + if (of_phy_is_fixed_link(ofdev->dev.of_node)) + of_phy_deregister_fixed_link(ofdev->dev.of_node); free_netdev(ndev); return 0; } diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 4b4f5bc0e279..9061c2f82b9c 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1312,6 +1312,7 @@ static void gfar_init_addr_hash_table(struct gfar_private *priv) */ static int gfar_probe(struct platform_device *ofdev) { + struct device_node *np = ofdev->dev.of_node; struct net_device *dev = NULL; struct gfar_private *priv = NULL; int err = 0, i; @@ -1462,6 +1463,8 @@ static int gfar_probe(struct platform_device *ofdev) return 0; register_fail: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); unmap_group_regs(priv); gfar_free_rx_queues(priv); gfar_free_tx_queues(priv); @@ -1474,11 +1477,16 @@ register_fail: static int gfar_remove(struct platform_device *ofdev) { struct gfar_private *priv = platform_get_drvdata(ofdev); + struct device_node *np = ofdev->dev.of_node; of_node_put(priv->phy_node); of_node_put(priv->tbi_node); unregister_netdev(priv->ndev); + + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + unmap_group_regs(priv); gfar_free_rx_queues(priv); gfar_free_tx_queues(priv); diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 186ef8f16c80..f76d33279454 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -3868,9 +3868,8 @@ static int ucc_geth_probe(struct platform_device* ofdev) dev = alloc_etherdev(sizeof(*ugeth)); if (dev == NULL) { - of_node_put(ug_info->tbi_node); - of_node_put(ug_info->phy_node); - return -ENOMEM; + err = -ENOMEM; + goto err_deregister_fixed_link; } ugeth = netdev_priv(dev); @@ -3907,10 +3906,7 @@ static int ucc_geth_probe(struct platform_device* ofdev) if (netif_msg_probe(ugeth)) pr_err("%s: Cannot register net device, aborting\n", dev->name); - free_netdev(dev); - of_node_put(ug_info->tbi_node); - of_node_put(ug_info->phy_node); - return err; + goto err_free_netdev; } mac_addr = of_get_mac_address(np); @@ -3923,16 +3919,29 @@ static int ucc_geth_probe(struct platform_device* ofdev) ugeth->node = np; return 0; + +err_free_netdev: + free_netdev(dev); +err_deregister_fixed_link: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + of_node_put(ug_info->tbi_node); + of_node_put(ug_info->phy_node); + + return err; } static int ucc_geth_remove(struct platform_device* ofdev) { struct net_device *dev = platform_get_drvdata(ofdev); struct ucc_geth_private *ugeth = netdev_priv(dev); + struct device_node *np = ofdev->dev.of_node; unregister_netdev(dev); free_netdev(dev); ucc_geth_memclean(ugeth); + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); of_node_put(ugeth->ug_info->tbi_node); of_node_put(ugeth->ug_info->phy_node); diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index ebe60719e489..a36022ba4e42 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -58,7 +58,7 @@ static struct kobj_type ktype_veth_pool; static const char ibmveth_driver_name[] = "ibmveth"; static const char ibmveth_driver_string[] = "IBM Power Virtual Ethernet Driver"; -#define ibmveth_driver_version "1.05" +#define ibmveth_driver_version "1.06" MODULE_AUTHOR("Santiago Leon <[email protected]>"); MODULE_DESCRIPTION("IBM Power Virtual Ethernet Driver"); @@ -137,6 +137,11 @@ static inline int ibmveth_rxq_frame_offset(struct ibmveth_adapter *adapter) return ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_OFF_MASK; } +static inline int ibmveth_rxq_large_packet(struct ibmveth_adapter *adapter) +{ + return ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_LRG_PKT; +} + static inline int ibmveth_rxq_frame_length(struct ibmveth_adapter *adapter) { return be32_to_cpu(adapter->rx_queue.queue_addr[adapter->rx_queue.index].length); @@ -1174,6 +1179,45 @@ map_failed: goto retry_bounce; } +static void ibmveth_rx_mss_helper(struct sk_buff *skb, u16 mss, int lrg_pkt) +{ + int offset = 0; + + /* only TCP packets will be aggregated */ + if (skb->protocol == htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)skb->data; + + if (iph->protocol == IPPROTO_TCP) { + offset = iph->ihl * 4; + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + } else { + return; + } + } else if (skb->protocol == htons(ETH_P_IPV6)) { + struct ipv6hdr *iph6 = (struct ipv6hdr *)skb->data; + + if (iph6->nexthdr == IPPROTO_TCP) { + offset = sizeof(struct ipv6hdr); + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + } else { + return; + } + } else { + return; + } + /* if mss is not set through Large Packet bit/mss in rx buffer, + * expect that the mss will be written to the tcp header checksum. + */ + if (lrg_pkt) { + skb_shinfo(skb)->gso_size = mss; + } else if (offset) { + struct tcphdr *tcph = (struct tcphdr *)(skb->data + offset); + + skb_shinfo(skb)->gso_size = ntohs(tcph->check); + tcph->check = 0; + } +} + static int ibmveth_poll(struct napi_struct *napi, int budget) { struct ibmveth_adapter *adapter = @@ -1182,6 +1226,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) int frames_processed = 0; unsigned long lpar_rc; struct iphdr *iph; + u16 mss = 0; restart_poll: while (frames_processed < budget) { @@ -1199,9 +1244,21 @@ restart_poll: int length = ibmveth_rxq_frame_length(adapter); int offset = ibmveth_rxq_frame_offset(adapter); int csum_good = ibmveth_rxq_csum_good(adapter); + int lrg_pkt = ibmveth_rxq_large_packet(adapter); skb = ibmveth_rxq_get_buffer(adapter); + /* if the large packet bit is set in the rx queue + * descriptor, the mss will be written by PHYP eight + * bytes from the start of the rx buffer, which is + * skb->data at this stage + */ + if (lrg_pkt) { + __be64 *rxmss = (__be64 *)(skb->data + 8); + + mss = (u16)be64_to_cpu(*rxmss); + } + new_skb = NULL; if (length < rx_copybreak) new_skb = netdev_alloc_skb(netdev, length); @@ -1235,11 +1292,15 @@ restart_poll: if (iph->check == 0xffff) { iph->check = 0; iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); - adapter->rx_large_packets++; } } } + if (length > netdev->mtu + ETH_HLEN) { + ibmveth_rx_mss_helper(skb, mss, lrg_pkt); + adapter->rx_large_packets++; + } + napi_gro_receive(napi, skb); /* send it up */ netdev->stats.rx_packets++; diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h index 4eade67fe30c..7acda04d034e 100644 --- a/drivers/net/ethernet/ibm/ibmveth.h +++ b/drivers/net/ethernet/ibm/ibmveth.h @@ -209,6 +209,7 @@ struct ibmveth_rx_q_entry { #define IBMVETH_RXQ_TOGGLE 0x80000000 #define IBMVETH_RXQ_TOGGLE_SHIFT 31 #define IBMVETH_RXQ_VALID 0x40000000 +#define IBMVETH_RXQ_LRG_PKT 0x04000000 #define IBMVETH_RXQ_NO_CSUM 0x02000000 #define IBMVETH_RXQ_CSUM_GOOD 0x01000000 #define IBMVETH_RXQ_OFF_MASK 0x0000FFFF diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index edc9a6ac5169..9affd7c198bd 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4931,11 +4931,15 @@ static int igb_tso(struct igb_ring *tx_ring, /* initialize outer IP header fields */ if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + /* IP header will have to cancel out any data that * is not a part of the outer IP header */ - ip.v4->check = csum_fold(csum_add(lco_csum(skb), - csum_unfold(l4.tcp->check))); + ip.v4->check = csum_fold(csum_partial(trans_start, + csum_start - trans_start, + 0)); type_tucmd |= E1000_ADVTXD_TUCMD_IPV4; ip.v4->tot_len = 0; diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 12bb877df860..7dff7f6239cd 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1965,11 +1965,15 @@ static int igbvf_tso(struct igbvf_ring *tx_ring, /* initialize outer IP header fields */ if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + /* IP header will have to cancel out any data that * is not a part of the outer IP header */ - ip.v4->check = csum_fold(csum_add(lco_csum(skb), - csum_unfold(l4.tcp->check))); + ip.v4->check = csum_fold(csum_partial(trans_start, + csum_start - trans_start, + 0)); type_tucmd |= E1000_ADVTXD_TUCMD_IPV4; ip.v4->tot_len = 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index bd93d823cc25..fee1f2918ead 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7277,11 +7277,15 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring, /* initialize outer IP header fields */ if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + /* IP header will have to cancel out any data that * is not a part of the outer IP header */ - ip.v4->check = csum_fold(csum_add(lco_csum(skb), - csum_unfold(l4.tcp->check))); + ip.v4->check = csum_fold(csum_partial(trans_start, + csum_start - trans_start, + 0)); type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; ip.v4->tot_len = 0; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 7eaac3234049..cbf70fe4028a 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -3329,11 +3329,15 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, /* initialize outer IP header fields */ if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + /* IP header will have to cancel out any data that * is not a part of the outer IP header */ - ip.v4->check = csum_fold(csum_add(lco_csum(skb), - csum_unfold(l4.tcp->check))); + ip.v4->check = csum_fold(csum_partial(trans_start, + csum_start - trans_start, + 0)); type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; ip.v4->tot_len = 0; diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 91e09d68b7e2..a167fd7ee13e 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -704,6 +704,7 @@ ltq_etop_probe(struct platform_device *pdev) priv->pldata = dev_get_platdata(&pdev->dev); priv->netdev = dev; spin_lock_init(&priv->lock); + SET_NETDEV_DEV(dev, &pdev->dev); for (i = 0; i < MAX_DMA_CHAN; i++) { if (IS_TX(i)) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 0c0a45af950f..707bc4680b9b 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4191,6 +4191,8 @@ err_clk: clk_disable_unprepare(pp->clk); err_put_phy_node: of_node_put(phy_node); + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); err_free_irq: irq_dispose_mapping(dev->irq); err_free_netdev: @@ -4202,6 +4204,7 @@ err_free_netdev: static int mvneta_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); + struct device_node *dn = pdev->dev.of_node; struct mvneta_port *pp = netdev_priv(dev); unregister_netdev(dev); @@ -4209,6 +4212,8 @@ static int mvneta_remove(struct platform_device *pdev) clk_disable_unprepare(pp->clk); free_percpu(pp->ports); free_percpu(pp->stats); + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); irq_dispose_mapping(dev->irq); of_node_put(pp->phy_node); free_netdev(dev); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 4a62ffd7729d..86a89cbd3ec9 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -318,6 +318,8 @@ static int mtk_phy_connect(struct net_device *dev) return 0; err_phy: + if (of_phy_is_fixed_link(mac->of_node)) + of_phy_deregister_fixed_link(mac->of_node); of_node_put(np); dev_err(eth->dev, "%s: invalid phy\n", __func__); return -EINVAL; @@ -1923,6 +1925,8 @@ static void mtk_uninit(struct net_device *dev) struct mtk_eth *eth = mac->hw; phy_disconnect(dev->phydev); + if (of_phy_is_fixed_link(mac->of_node)) + of_phy_deregister_fixed_link(mac->of_node); mtk_irq_disable(eth, MTK_QDMA_INT_MASK, ~0); mtk_irq_disable(eth, MTK_PDMA_INT_MASK, ~0); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index a60f635da78b..fb8bb027b69c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2079,13 +2079,6 @@ err: return -ENOMEM; } -static void mlx4_en_shutdown(struct net_device *dev) -{ - rtnl_lock(); - netif_device_detach(dev); - mlx4_en_close(dev); - rtnl_unlock(); -} static int mlx4_en_copy_priv(struct mlx4_en_priv *dst, struct mlx4_en_priv *src, @@ -2162,8 +2155,6 @@ void mlx4_en_destroy_netdev(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; - bool shutdown = mdev->dev->persist->interface_state & - MLX4_INTERFACE_STATE_SHUTDOWN; en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port); @@ -2171,10 +2162,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev) if (priv->registered) { devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev, priv->port)); - if (shutdown) - mlx4_en_shutdown(dev); - else - unregister_netdev(dev); + unregister_netdev(dev); } if (priv->allocated) @@ -2203,8 +2191,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev) kfree(priv->tx_ring); kfree(priv->tx_cq); - if (!shutdown) - free_netdev(dev); + free_netdev(dev); } static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 6f4e67bc3538..75d07fa9d0b1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4147,11 +4147,8 @@ static void mlx4_shutdown(struct pci_dev *pdev) mlx4_info(persist->dev, "mlx4_shutdown was called\n"); mutex_lock(&persist->interface_state_mutex); - if (persist->interface_state & MLX4_INTERFACE_STATE_UP) { - /* Notify mlx4 clients that the kernel is being shut down */ - persist->interface_state |= MLX4_INTERFACE_STATE_SHUTDOWN; + if (persist->interface_state & MLX4_INTERFACE_STATE_UP) mlx4_unload_one(pdev); - } mutex_unlock(&persist->interface_state_mutex); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 94b891c118c1..1a670b681555 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -1457,7 +1457,12 @@ EXPORT_SYMBOL_GPL(mlx4_multicast_detach); int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn, enum mlx4_net_trans_promisc_mode mode) { - struct mlx4_net_trans_rule rule; + struct mlx4_net_trans_rule rule = { + .queue_mode = MLX4_NET_TRANS_Q_FIFO, + .exclusive = 0, + .allow_loopback = 1, + }; + u64 *regid_p; switch (mode) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index aae46884bf93..521cfdb7d11e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -18,8 +18,6 @@ config MLX5_CORE_EN default n ---help--- Ethernet support in Mellanox Technologies ConnectX-4 NIC. - Ethernet and Infiniband support in ConnectX-4 are currently mutually - exclusive. config MLX5_CORE_EN_DCB bool "Data Center Bridging (DCB) Support" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 1e639f886021..bfe410e8a469 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -268,11 +268,6 @@ static void dump_buf(void *buf, int size, int data_only, int offset) pr_debug("\n"); } -enum { - MLX5_DRIVER_STATUS_ABORTED = 0xfe, - MLX5_DRIVER_SYND = 0xbadd00de, -}; - static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, u32 *synd, u8 *status) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 7a43502a89cc..71382df59fc0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -241,7 +241,7 @@ struct mlx5e_tstamp { }; enum { - MLX5E_RQ_STATE_FLUSH, + MLX5E_RQ_STATE_ENABLED, MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, MLX5E_RQ_STATE_AM, }; @@ -394,7 +394,7 @@ struct mlx5e_sq_dma { }; enum { - MLX5E_SQ_STATE_FLUSH, + MLX5E_SQ_STATE_ENABLED, MLX5E_SQ_STATE_BF_ENABLE, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 84e8b250e2af..246d98ebb588 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -759,6 +759,7 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, if (err) goto err_destroy_rq; + set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY); if (err) goto err_disable_rq; @@ -773,6 +774,7 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, return 0; err_disable_rq: + clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); mlx5e_disable_rq(rq); err_destroy_rq: mlx5e_destroy_rq(rq); @@ -782,7 +784,7 @@ err_destroy_rq: static void mlx5e_close_rq(struct mlx5e_rq *rq) { - set_bit(MLX5E_RQ_STATE_FLUSH, &rq->state); + clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */ cancel_work_sync(&rq->am.work); @@ -1006,7 +1008,6 @@ static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param) MLX5_SET(sqc, sqc, min_wqe_inline_mode, sq->min_inline_mode); MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST); MLX5_SET(sqc, sqc, tis_lst_sz, param->type == MLX5E_SQ_ICO ? 0 : 1); - MLX5_SET(sqc, sqc, flush_in_error_en, 1); MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC); MLX5_SET(wq, wq, uar_page, sq->uar.index); @@ -1083,6 +1084,7 @@ static int mlx5e_open_sq(struct mlx5e_channel *c, if (err) goto err_destroy_sq; + set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RST, MLX5_SQC_STATE_RDY, false, 0); if (err) @@ -1096,6 +1098,7 @@ static int mlx5e_open_sq(struct mlx5e_channel *c, return 0; err_disable_sq: + clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); mlx5e_disable_sq(sq); err_destroy_sq: mlx5e_destroy_sq(sq); @@ -1112,7 +1115,7 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq) static void mlx5e_close_sq(struct mlx5e_sq *sq) { - set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state); + clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); /* prevent netif_tx_wake_queue */ napi_synchronize(&sq->channel->napi); @@ -3092,7 +3095,7 @@ static void mlx5e_tx_timeout(struct net_device *dev) if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i))) continue; sched_work = true; - set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state); + clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x\n", i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc); } @@ -3147,13 +3150,13 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) for (i = 0; i < priv->params.num_channels; i++) { struct mlx5e_channel *c = priv->channel[i]; - set_bit(MLX5E_RQ_STATE_FLUSH, &c->rq.state); + clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); napi_synchronize(&c->napi); /* prevent mlx5e_poll_rx_cq from accessing rq->xdp_prog */ old_prog = xchg(&c->rq.xdp_prog, prog); - clear_bit(MLX5E_RQ_STATE_FLUSH, &c->rq.state); + set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); /* napi_schedule in case we have missed anything */ set_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags); napi_schedule(&c->napi); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index c6de6fba5843..33495d88aeb2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -340,7 +340,7 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix) while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) { sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP; sq->db.ico_wqe[pi].num_wqebbs = 1; - mlx5e_send_nop(sq, true); + mlx5e_send_nop(sq, false); } wqe = mlx5_wq_cyc_get_wqe(wq, pi); @@ -412,7 +412,7 @@ void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq) clear_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state); - if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state))) { + if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) { mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]); return; } @@ -445,7 +445,7 @@ void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) } #define RQ_CANNOT_POST(rq) \ - (test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state) || \ + (!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state) || \ test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state)) bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) @@ -924,7 +924,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) struct mlx5e_sq *xdp_sq = &rq->channel->xdp_sq; int work_done = 0; - if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state))) + if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) return 0; if (cq->decmprs_left) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 70a717382357..cfb68371c397 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -409,7 +409,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) sq = container_of(cq, struct mlx5e_sq, cq); - if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state))) + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) return false; npkts = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 5703f19a6a24..e5c12a732aa1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -56,7 +56,7 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) struct mlx5_cqe64 *cqe; u16 sqcc; - if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state))) + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) return; cqe = mlx5e_get_cqe(cq); @@ -113,7 +113,7 @@ static inline bool mlx5e_poll_xdp_tx_cq(struct mlx5e_cq *cq) sq = container_of(cq, struct mlx5e_sq, cq); - if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state))) + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) return false; /* sq->cc must be updated only after mlx5_cqwq_update_db_record(), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 3b7c6a9f2b5f..ada24e103b02 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -62,13 +62,13 @@ MODULE_DESCRIPTION("Mellanox Connect-IB, ConnectX-4 core driver"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_VERSION(DRIVER_VERSION); -int mlx5_core_debug_mask; -module_param_named(debug_mask, mlx5_core_debug_mask, int, 0644); +unsigned int mlx5_core_debug_mask; +module_param_named(debug_mask, mlx5_core_debug_mask, uint, 0644); MODULE_PARM_DESC(debug_mask, "debug mask: 1 = dump cmd data, 2 = dump cmd exec time, 3 = both. Default=0"); #define MLX5_DEFAULT_PROF 2 -static int prof_sel = MLX5_DEFAULT_PROF; -module_param_named(prof_sel, prof_sel, int, 0444); +static unsigned int prof_sel = MLX5_DEFAULT_PROF; +module_param_named(prof_sel, prof_sel, uint, 0444); MODULE_PARM_DESC(prof_sel, "profile selector. Valid range 0 - 2"); enum { @@ -732,13 +732,15 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev) u8 status; mlx5_cmd_mbox_status(query_out, &status, &syndrome); - if (status == MLX5_CMD_STAT_BAD_OP_ERR) { - pr_debug("Only ISSI 0 is supported\n"); - return 0; + if (!status || syndrome == MLX5_DRIVER_SYND) { + mlx5_core_err(dev, "Failed to query ISSI err(%d) status(%d) synd(%d)\n", + err, status, syndrome); + return err; } - pr_err("failed to query ISSI err(%d)\n", err); - return err; + mlx5_core_warn(dev, "Query ISSI is not supported by FW, ISSI is 0\n"); + dev->issi = 0; + return 0; } sup_issi = MLX5_GET(query_issi_out, query_out, supported_issi_dw0); @@ -752,7 +754,8 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev) err = mlx5_cmd_exec(dev, set_in, sizeof(set_in), set_out, sizeof(set_out)); if (err) { - pr_err("failed to set ISSI=1 err(%d)\n", err); + mlx5_core_err(dev, "Failed to set ISSI to 1 err(%d)\n", + err); return err; } @@ -1227,13 +1230,6 @@ static int init_one(struct pci_dev *pdev, dev->pdev = pdev; dev->event = mlx5_core_event; - - if (prof_sel < 0 || prof_sel >= ARRAY_SIZE(profile)) { - mlx5_core_warn(dev, - "selected profile out of range, selecting default (%d)\n", - MLX5_DEFAULT_PROF); - prof_sel = MLX5_DEFAULT_PROF; - } dev->profile = &profile[prof_sel]; INIT_LIST_HEAD(&priv->ctx_list); @@ -1450,10 +1446,22 @@ static struct pci_driver mlx5_core_driver = { .sriov_configure = mlx5_core_sriov_configure, }; +static void mlx5_core_verify_params(void) +{ + if (prof_sel >= ARRAY_SIZE(profile)) { + pr_warn("mlx5_core: WARNING: Invalid module parameter prof_sel %d, valid range 0-%zu, changing back to default(%d)\n", + prof_sel, + ARRAY_SIZE(profile) - 1, + MLX5_DEFAULT_PROF); + prof_sel = MLX5_DEFAULT_PROF; + } +} + static int __init init(void) { int err; + mlx5_core_verify_params(); mlx5_register_debugfs(); err = pci_register_driver(&mlx5_core_driver); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 187662c8ea96..63b9a0dba885 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -44,11 +44,11 @@ #define MLX5_TOTAL_VPORTS(mdev) (1 + pci_sriov_get_totalvfs(mdev->pdev)) -extern int mlx5_core_debug_mask; +extern uint mlx5_core_debug_mask; #define mlx5_core_dbg(__dev, format, ...) \ - dev_dbg(&(__dev)->pdev->dev, "%s:%s:%d:(pid %d): " format, \ - (__dev)->priv.name, __func__, __LINE__, current->pid, \ + dev_dbg(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format, \ + __func__, __LINE__, current->pid, \ ##__VA_ARGS__) #define mlx5_core_dbg_mask(__dev, mask, format, ...) \ @@ -63,8 +63,8 @@ do { \ ##__VA_ARGS__) #define mlx5_core_warn(__dev, format, ...) \ - dev_warn(&(__dev)->pdev->dev, "%s:%s:%d:(pid %d): " format, \ - (__dev)->priv.name, __func__, __LINE__, current->pid, \ + dev_warn(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format, \ + __func__, __LINE__, current->pid, \ ##__VA_ARGS__) #define mlx5_core_info(__dev, format, ...) \ @@ -75,6 +75,11 @@ enum { MLX5_CMD_TIME, /* print command execution time */ }; +enum { + MLX5_DRIVER_STATUS_ABORTED = 0xfe, + MLX5_DRIVER_SYND = 0xbadd00de, +}; + int mlx5_query_hca_caps(struct mlx5_core_dev *dev); int mlx5_query_board_id(struct mlx5_core_dev *dev); int mlx5_cmd_init_hca(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index f95385cbbd40..62ae55bd81b8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -1730,6 +1730,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb) mapping))) { DP_NOTICE(cdev, "Unable to map frag - dropping packet\n"); + rc = -ENOMEM; goto err; } } else { diff --git a/drivers/net/ethernet/qualcomm/emac/emac-phy.c b/drivers/net/ethernet/qualcomm/emac/emac-phy.c index da4e90db4d98..99a14df28b96 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-phy.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-phy.c @@ -212,6 +212,7 @@ int emac_phy_config(struct platform_device *pdev, struct emac_adapter *adpt) phy_np = of_parse_phandle(np, "phy-handle", 0); adpt->phydev = of_phy_find_device(phy_np); + of_node_put(phy_np); } if (!adpt->phydev) { diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 4fede4b86538..57b35aeac51a 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -711,6 +711,8 @@ static int emac_probe(struct platform_device *pdev) err_undo_napi: netif_napi_del(&adpt->rx_q.napi); err_undo_mdiobus: + if (!has_acpi_companion(&pdev->dev)) + put_device(&adpt->phydev->mdio.dev); mdiobus_unregister(adpt->mii_bus); err_undo_clocks: emac_clks_teardown(adpt); @@ -730,6 +732,8 @@ static int emac_remove(struct platform_device *pdev) emac_clks_teardown(adpt); + if (!has_acpi_companion(&pdev->dev)) + put_device(&adpt->phydev->mdio.dev); mdiobus_unregister(adpt->mii_bus); free_netdev(netdev); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 630536bc72f9..d6a217874a8b 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1008,20 +1008,18 @@ static int ravb_phy_init(struct net_device *ndev) of_node_put(pn); if (!phydev) { netdev_err(ndev, "failed to connect PHY\n"); - return -ENOENT; + err = -ENOENT; + goto err_deregister_fixed_link; } /* This driver only support 10/100Mbit speeds on Gen3 * at this time. */ if (priv->chip_id == RCAR_GEN3) { - int err; - err = phy_set_max_speed(phydev, SPEED_100); if (err) { netdev_err(ndev, "failed to limit PHY to 100Mbit/s\n"); - phy_disconnect(phydev); - return err; + goto err_phy_disconnect; } netdev_info(ndev, "limited PHY to 100Mbit/s\n"); @@ -1033,6 +1031,14 @@ static int ravb_phy_init(struct net_device *ndev) phy_attached_info(phydev); return 0; + +err_phy_disconnect: + phy_disconnect(phydev); +err_deregister_fixed_link: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + + return err; } /* PHY control start function */ @@ -1634,6 +1640,7 @@ static void ravb_set_rx_mode(struct net_device *ndev) /* Device close function for Ethernet AVB */ static int ravb_close(struct net_device *ndev) { + struct device_node *np = ndev->dev.parent->of_node; struct ravb_private *priv = netdev_priv(ndev); struct ravb_tstamp_skb *ts_skb, *ts_skb2; @@ -1663,6 +1670,8 @@ static int ravb_close(struct net_device *ndev) if (ndev->phydev) { phy_stop(ndev->phydev); phy_disconnect(ndev->phydev); + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); } if (priv->chip_id != RCAR_GEN2) { diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 05b0dc55de77..1a92de705199 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -518,7 +518,7 @@ static struct sh_eth_cpu_data r7s72100_data = { .ecsr_value = ECSR_ICD, .ecsipr_value = ECSIPR_ICDIP, - .eesipr_value = 0xff7f009f, + .eesipr_value = 0xe77f009f, .tx_check = EESR_TC1 | EESR_FTC, .eesr_err_check = EESR_TWB1 | EESR_TWB | EESR_TABT | EESR_RABT | diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index e9b8579e6241..6fb2d15b5351 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -438,9 +438,16 @@ static int smsc911x_request_resources(struct platform_device *pdev) ret = regulator_bulk_get(&pdev->dev, ARRAY_SIZE(pdata->supplies), pdata->supplies); - if (ret) + if (ret) { + /* + * Retry on deferrals, else just report the error + * and try to continue. + */ + if (ret == -EPROBE_DEFER) + return ret; netdev_err(ndev, "couldn't get regulators %d\n", ret); + } /* Request optional RESET GPIO */ pdata->reset_gpiod = devm_gpiod_get_optional(&pdev->dev, @@ -2584,6 +2591,9 @@ static int smsc911x_suspend(struct device *dev) PMT_CTRL_PM_MODE_D1_ | PMT_CTRL_WOL_EN_ | PMT_CTRL_ED_EN_ | PMT_CTRL_PME_EN_); + pm_runtime_disable(dev); + pm_runtime_set_suspended(dev); + return 0; } @@ -2593,6 +2603,9 @@ static int smsc911x_resume(struct device *dev) struct smsc911x_data *pdata = netdev_priv(ndev); unsigned int to = 100; + pm_runtime_enable(dev); + pm_runtime_resume(dev); + /* Note 3.11 from the datasheet: * "When the LAN9220 is in a power saving state, a write of any * data to the BYTE_TEST register will wake-up the device." diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c index b1e5f24708c9..e6e6c2fcc4b7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c @@ -50,10 +50,23 @@ static int dwmac_generic_probe(struct platform_device *pdev) if (plat_dat->init) { ret = plat_dat->init(pdev, plat_dat->bsp_priv); if (ret) - return ret; + goto err_remove_config_dt; } - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_exit; + + return 0; + +err_exit: + if (plat_dat->exit) + plat_dat->exit(pdev, plat_dat->bsp_priv); +err_remove_config_dt: + if (pdev->dev.of_node) + stmmac_remove_config_dt(pdev, plat_dat); + + return ret; } static const struct of_device_id dwmac_generic_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index 36d3355f2fb0..866444b6c82f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -271,15 +271,17 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); gmac = devm_kzalloc(dev, sizeof(*gmac), GFP_KERNEL); - if (!gmac) - return -ENOMEM; + if (!gmac) { + err = -ENOMEM; + goto err_remove_config_dt; + } gmac->pdev = pdev; err = ipq806x_gmac_of_parse(gmac); if (err) { dev_err(dev, "device tree parsing error\n"); - return err; + goto err_remove_config_dt; } regmap_write(gmac->qsgmii_csr, QSGMII_PCS_CAL_LCKDT_CTL, @@ -300,7 +302,8 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) default: dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n", phy_modes(gmac->phy_mode)); - return -EINVAL; + err = -EINVAL; + goto err_remove_config_dt; } regmap_write(gmac->nss_common, NSS_COMMON_GMAC_CTL(gmac->id), val); @@ -319,7 +322,8 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) default: dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n", phy_modes(gmac->phy_mode)); - return -EINVAL; + err = -EINVAL; + goto err_remove_config_dt; } regmap_write(gmac->nss_common, NSS_COMMON_CLK_SRC_CTRL, val); @@ -346,7 +350,16 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) plat_dat->bsp_priv = gmac; plat_dat->fix_mac_speed = ipq806x_gmac_fix_mac_speed; - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + err = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (err) + goto err_remove_config_dt; + + return 0; + +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); + + return err; } static const struct of_device_id ipq806x_gmac_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c index 78e9d1861896..3d3f43d91b98 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c @@ -46,7 +46,8 @@ static int lpc18xx_dwmac_probe(struct platform_device *pdev) reg = syscon_regmap_lookup_by_compatible("nxp,lpc1850-creg"); if (IS_ERR(reg)) { dev_err(&pdev->dev, "syscon lookup failed\n"); - return PTR_ERR(reg); + ret = PTR_ERR(reg); + goto err_remove_config_dt; } if (plat_dat->interface == PHY_INTERFACE_MODE_MII) { @@ -55,13 +56,23 @@ static int lpc18xx_dwmac_probe(struct platform_device *pdev) ethmode = LPC18XX_CREG_CREG6_ETHMODE_RMII; } else { dev_err(&pdev->dev, "Only MII and RMII mode supported\n"); - return -EINVAL; + ret = -EINVAL; + goto err_remove_config_dt; } regmap_update_bits(reg, LPC18XX_CREG_CREG6, LPC18XX_CREG_CREG6_ETHMODE_MASK, ethmode); - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_remove_config_dt; + + return 0; + +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); + + return ret; } static const struct of_device_id lpc18xx_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c index 309d99536a2c..7fdd1760a74c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c @@ -64,18 +64,31 @@ static int meson6_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } res = platform_get_resource(pdev, IORESOURCE_MEM, 1); dwmac->reg = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(dwmac->reg)) - return PTR_ERR(dwmac->reg); + if (IS_ERR(dwmac->reg)) { + ret = PTR_ERR(dwmac->reg); + goto err_remove_config_dt; + } plat_dat->bsp_priv = dwmac; plat_dat->fix_mac_speed = meson6_dwmac_fix_mac_speed; - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_remove_config_dt; + + return 0; + +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); + + return ret; } static const struct of_device_id meson6_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 250e4ceafc8d..ffaed1f35efe 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -264,32 +264,48 @@ static int meson8b_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } res = platform_get_resource(pdev, IORESOURCE_MEM, 1); dwmac->regs = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(dwmac->regs)) - return PTR_ERR(dwmac->regs); + if (IS_ERR(dwmac->regs)) { + ret = PTR_ERR(dwmac->regs); + goto err_remove_config_dt; + } dwmac->pdev = pdev; dwmac->phy_mode = of_get_phy_mode(pdev->dev.of_node); if (dwmac->phy_mode < 0) { dev_err(&pdev->dev, "missing phy-mode property\n"); - return -EINVAL; + ret = -EINVAL; + goto err_remove_config_dt; } ret = meson8b_init_clk(dwmac); if (ret) - return ret; + goto err_remove_config_dt; ret = meson8b_init_prg_eth(dwmac); if (ret) - return ret; + goto err_remove_config_dt; plat_dat->bsp_priv = dwmac; - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_clk_disable; + + return 0; + +err_clk_disable: + clk_disable_unprepare(dwmac->m25_div_clk); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); + + return ret; } static int meson8b_dwmac_remove(struct platform_device *pdev) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 3740a4417fa0..d80c88bd2bba 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -981,14 +981,27 @@ static int rk_gmac_probe(struct platform_device *pdev) plat_dat->resume = rk_gmac_resume; plat_dat->bsp_priv = rk_gmac_setup(pdev, data); - if (IS_ERR(plat_dat->bsp_priv)) - return PTR_ERR(plat_dat->bsp_priv); + if (IS_ERR(plat_dat->bsp_priv)) { + ret = PTR_ERR(plat_dat->bsp_priv); + goto err_remove_config_dt; + } ret = rk_gmac_init(pdev, plat_dat->bsp_priv); if (ret) - return ret; + goto err_remove_config_dt; + + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_gmac_exit; + + return 0; + +err_gmac_exit: + rk_gmac_exit(pdev, plat_dat->bsp_priv); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + return ret; } static const struct of_device_id rk_gmac_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index bec6963ac71e..0c420e97de1e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -304,6 +304,8 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; int ret; struct socfpga_dwmac *dwmac; + struct net_device *ndev; + struct stmmac_priv *stpriv; ret = stmmac_get_platform_resources(pdev, &stmmac_res); if (ret) @@ -314,32 +316,43 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } ret = socfpga_dwmac_parse_data(dwmac, dev); if (ret) { dev_err(dev, "Unable to parse OF data\n"); - return ret; + goto err_remove_config_dt; } plat_dat->bsp_priv = dwmac; plat_dat->fix_mac_speed = socfpga_dwmac_fix_mac_speed; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_remove_config_dt; - if (!ret) { - struct net_device *ndev = platform_get_drvdata(pdev); - struct stmmac_priv *stpriv = netdev_priv(ndev); + ndev = platform_get_drvdata(pdev); + stpriv = netdev_priv(ndev); - /* The socfpga driver needs to control the stmmac reset to - * set the phy mode. Create a copy of the core reset handel - * so it can be used by the driver later. - */ - dwmac->stmmac_rst = stpriv->stmmac_rst; + /* The socfpga driver needs to control the stmmac reset to set the phy + * mode. Create a copy of the core reset handle so it can be used by + * the driver later. + */ + dwmac->stmmac_rst = stpriv->stmmac_rst; - ret = socfpga_dwmac_set_phy_mode(dwmac); - } + ret = socfpga_dwmac_set_phy_mode(dwmac); + if (ret) + goto err_dvr_remove; + + return 0; + +err_dvr_remove: + stmmac_dvr_remove(&pdev->dev); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c index 58c05acc2aab..060b98c37a85 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c @@ -345,13 +345,15 @@ static int sti_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } ret = sti_dwmac_parse_data(dwmac, pdev); if (ret) { dev_err(&pdev->dev, "Unable to parse OF data\n"); - return ret; + goto err_remove_config_dt; } dwmac->fix_retime_src = data->fix_retime_src; @@ -363,9 +365,20 @@ static int sti_dwmac_probe(struct platform_device *pdev) ret = sti_dwmac_init(pdev, plat_dat->bsp_priv); if (ret) - return ret; + goto err_remove_config_dt; + + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_dwmac_exit; + + return 0; + +err_dwmac_exit: + sti_dwmac_exit(pdev, plat_dat->bsp_priv); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + return ret; } static const struct sti_dwmac_of_data stih4xx_dwmac_data = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c index e5a926b8bee7..61cb24810d10 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -107,24 +107,33 @@ static int stm32_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } ret = stm32_dwmac_parse_data(dwmac, &pdev->dev); if (ret) { dev_err(&pdev->dev, "Unable to parse OF data\n"); - return ret; + goto err_remove_config_dt; } plat_dat->bsp_priv = dwmac; ret = stm32_dwmac_init(plat_dat); if (ret) - return ret; + goto err_remove_config_dt; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) - stm32_dwmac_clk_disable(dwmac); + goto err_clk_disable; + + return 0; + +err_clk_disable: + stm32_dwmac_clk_disable(dwmac); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c index adff46375a32..d07520fb969e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c @@ -120,22 +120,27 @@ static int sun7i_gmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); gmac = devm_kzalloc(dev, sizeof(*gmac), GFP_KERNEL); - if (!gmac) - return -ENOMEM; + if (!gmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } gmac->interface = of_get_phy_mode(dev->of_node); gmac->tx_clk = devm_clk_get(dev, "allwinner_gmac_tx"); if (IS_ERR(gmac->tx_clk)) { dev_err(dev, "could not get tx clock\n"); - return PTR_ERR(gmac->tx_clk); + ret = PTR_ERR(gmac->tx_clk); + goto err_remove_config_dt; } /* Optional regulator for PHY */ gmac->regulator = devm_regulator_get_optional(dev, "phy"); if (IS_ERR(gmac->regulator)) { - if (PTR_ERR(gmac->regulator) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (PTR_ERR(gmac->regulator) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto err_remove_config_dt; + } dev_info(dev, "no regulator found\n"); gmac->regulator = NULL; } @@ -151,11 +156,18 @@ static int sun7i_gmac_probe(struct platform_device *pdev) ret = sun7i_gmac_init(pdev, plat_dat->bsp_priv); if (ret) - return ret; + goto err_remove_config_dt; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) - sun7i_gmac_exit(pdev, plat_dat->bsp_priv); + goto err_gmac_exit; + + return 0; + +err_gmac_exit: + sun7i_gmac_exit(pdev, plat_dat->bsp_priv); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c index 990746955216..f35385266fbf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c @@ -43,9 +43,11 @@ static void dwmac1000_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) if (axi->axi_xit_frm) value |= DMA_AXI_LPI_XIT_FRM; + value &= ~DMA_AXI_WR_OSR_LMT; value |= (axi->axi_wr_osr_lmt & DMA_AXI_WR_OSR_LMT_MASK) << DMA_AXI_WR_OSR_LMT_SHIFT; + value &= ~DMA_AXI_RD_OSR_LMT; value |= (axi->axi_rd_osr_lmt & DMA_AXI_RD_OSR_LMT_MASK) << DMA_AXI_RD_OSR_LMT_SHIFT; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 116151cd6a95..32bc2fc73cdc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -30,9 +30,11 @@ static void dwmac4_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) if (axi->axi_xit_frm) value |= DMA_AXI_LPI_XIT_FRM; + value &= ~DMA_AXI_WR_OSR_LMT; value |= (axi->axi_wr_osr_lmt & DMA_AXI_OSR_MAX) << DMA_AXI_WR_OSR_LMT_SHIFT; + value &= ~DMA_AXI_RD_OSR_LMT; value |= (axi->axi_rd_osr_lmt & DMA_AXI_OSR_MAX) << DMA_AXI_RD_OSR_LMT_SHIFT; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 1f9ec02fa7f8..caf069a465f2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3416,7 +3416,6 @@ int stmmac_dvr_remove(struct device *dev) stmmac_set_mac(priv->ioaddr, false); netif_carrier_off(ndev); unregister_netdev(ndev); - of_node_put(priv->plat->phy_node); if (priv->stmmac_rst) reset_control_assert(priv->stmmac_rst); clk_disable_unprepare(priv->pclk); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 0a0d6a86f397..ac3d39c69509 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -126,8 +126,10 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) axi->axi_mb = of_property_read_bool(np, "snps,axi_mb"); axi->axi_rb = of_property_read_bool(np, "snps,axi_rb"); - of_property_read_u32(np, "snps,wr_osr_lmt", &axi->axi_wr_osr_lmt); - of_property_read_u32(np, "snps,rd_osr_lmt", &axi->axi_rd_osr_lmt); + if (of_property_read_u32(np, "snps,wr_osr_lmt", &axi->axi_wr_osr_lmt)) + axi->axi_wr_osr_lmt = 1; + if (of_property_read_u32(np, "snps,rd_osr_lmt", &axi->axi_rd_osr_lmt)) + axi->axi_rd_osr_lmt = 1; of_property_read_u32_array(np, "snps,blen", axi->axi_blen, AXI_BLEN); of_node_put(np); @@ -200,7 +202,6 @@ static int stmmac_dt_phy(struct plat_stmmacenet_data *plat, /** * stmmac_probe_config_dt - parse device-tree driver parameters * @pdev: platform_device structure - * @plat: driver data platform structure * @mac: MAC address to use * Description: * this function is to read the driver parameters from device-tree and @@ -306,7 +307,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg), GFP_KERNEL); if (!dma_cfg) { - of_node_put(plat->phy_node); + stmmac_remove_config_dt(pdev, plat); return ERR_PTR(-ENOMEM); } plat->dma_cfg = dma_cfg; @@ -329,14 +330,37 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) return plat; } + +/** + * stmmac_remove_config_dt - undo the effects of stmmac_probe_config_dt() + * @pdev: platform_device structure + * @plat: driver data platform structure + * + * Release resources claimed by stmmac_probe_config_dt(). + */ +void stmmac_remove_config_dt(struct platform_device *pdev, + struct plat_stmmacenet_data *plat) +{ + struct device_node *np = pdev->dev.of_node; + + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + of_node_put(plat->phy_node); +} #else struct plat_stmmacenet_data * stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) { return ERR_PTR(-ENOSYS); } + +void stmmac_remove_config_dt(struct platform_device *pdev, + struct plat_stmmacenet_data *plat) +{ +} #endif /* CONFIG_OF */ EXPORT_SYMBOL_GPL(stmmac_probe_config_dt); +EXPORT_SYMBOL_GPL(stmmac_remove_config_dt); int stmmac_get_platform_resources(struct platform_device *pdev, struct stmmac_resources *stmmac_res) @@ -392,10 +416,13 @@ int stmmac_pltfr_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct stmmac_priv *priv = netdev_priv(ndev); + struct plat_stmmacenet_data *plat = priv->plat; int ret = stmmac_dvr_remove(&pdev->dev); - if (priv->plat->exit) - priv->plat->exit(pdev, priv->plat->bsp_priv); + if (plat->exit) + plat->exit(pdev, plat->bsp_priv); + + stmmac_remove_config_dt(pdev, plat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h index 64e147f53a9c..b72eb0de57b7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h @@ -23,6 +23,8 @@ struct plat_stmmacenet_data * stmmac_probe_config_dt(struct platform_device *pdev, const char **mac); +void stmmac_remove_config_dt(struct platform_device *pdev, + struct plat_stmmacenet_data *plat); int stmmac_get_platform_resources(struct platform_device *pdev, struct stmmac_resources *stmmac_res); diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index 4ba2421e625d..97d64bfed465 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -2881,7 +2881,7 @@ static int dwceqos_probe(struct platform_device *pdev) ret = of_get_phy_mode(lp->pdev->dev.of_node); if (ret < 0) { dev_err(&lp->pdev->dev, "error in getting phy i/f\n"); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } lp->phy_interface = ret; @@ -2889,14 +2889,14 @@ static int dwceqos_probe(struct platform_device *pdev) ret = dwceqos_mii_init(lp); if (ret) { dev_err(&lp->pdev->dev, "error in dwceqos_mii_init\n"); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } ret = dwceqos_mii_probe(ndev); if (ret != 0) { netdev_err(ndev, "mii_probe fail.\n"); ret = -ENXIO; - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } dwceqos_set_umac_addr(lp, lp->ndev->dev_addr, 0); @@ -2914,7 +2914,7 @@ static int dwceqos_probe(struct platform_device *pdev) if (ret) { dev_err(&lp->pdev->dev, "Unable to retrieve DT, error %d\n", ret); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } dev_info(&lp->pdev->dev, "pdev->id %d, baseaddr 0x%08lx, irq %d\n", pdev->id, ndev->base_addr, ndev->irq); @@ -2924,7 +2924,7 @@ static int dwceqos_probe(struct platform_device *pdev) if (ret) { dev_err(&lp->pdev->dev, "Unable to request IRQ %d, error %d\n", ndev->irq, ret); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } if (netif_msg_probe(lp)) @@ -2935,11 +2935,14 @@ static int dwceqos_probe(struct platform_device *pdev) ret = register_netdev(ndev); if (ret) { dev_err(&pdev->dev, "Cannot register net device, aborting.\n"); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } return 0; +err_out_deregister_fixed_link: + if (of_phy_is_fixed_link(pdev->dev.of_node)) + of_phy_deregister_fixed_link(pdev->dev.of_node); err_out_clk_dis_phy: clk_disable_unprepare(lp->phy_ref_clk); err_out_clk_dis_aper: @@ -2959,8 +2962,11 @@ static int dwceqos_remove(struct platform_device *pdev) if (ndev) { lp = netdev_priv(ndev); - if (ndev->phydev) + if (ndev->phydev) { phy_disconnect(ndev->phydev); + if (of_phy_is_fixed_link(pdev->dev.of_node)) + of_phy_deregister_fixed_link(pdev->dev.of_node); + } mdiobus_unregister(lp->mii_bus); mdiobus_free(lp->mii_bus); diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c index fa0cfda24fd9..28097be2ff28 100644 --- a/drivers/net/ethernet/ti/cpmac.c +++ b/drivers/net/ethernet/ti/cpmac.c @@ -1113,6 +1113,7 @@ static int cpmac_probe(struct platform_device *pdev) if (!dev) return -ENOMEM; + SET_NETDEV_DEV(dev, &pdev->dev); platform_set_drvdata(pdev, dev); priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c index ba1e45ff6aae..18013645e76c 100644 --- a/drivers/net/ethernet/ti/cpsw-phy-sel.c +++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c @@ -81,6 +81,7 @@ static void cpsw_gmii_sel_am3352(struct cpsw_phy_sel_priv *priv, }; mask = GMII_SEL_MODE_MASK << (slave * 2) | BIT(slave + 6); + mask |= BIT(slave + 4); mode <<= slave * 2; if (priv->rmii_clock_external) { diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 58947aae31c7..b9087b828eff 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2459,20 +2459,8 @@ static void cpsw_remove_dt(struct platform_device *pdev) if (strcmp(slave_node->name, "slave")) continue; - if (of_phy_is_fixed_link(slave_node)) { - struct phy_device *phydev; - - phydev = of_phy_find_device(slave_node); - if (phydev) { - fixed_phy_unregister(phydev); - /* Put references taken by - * of_phy_find_device() and - * of_phy_register_fixed_link(). - */ - phy_device_free(phydev); - phy_device_free(phydev); - } - } + if (of_phy_is_fixed_link(slave_node)) + of_phy_deregister_fixed_link(slave_node); of_node_put(slave_data->phy_node); @@ -2942,6 +2930,8 @@ static int cpsw_resume(struct device *dev) /* Select default pin state */ pinctrl_pm_select_default_state(dev); + /* shut up ASSERT_RTNL() warning in netif_set_real_num_tx/rx_queues */ + rtnl_lock(); if (cpsw->data.dual_emac) { int i; @@ -2953,6 +2943,8 @@ static int cpsw_resume(struct device *dev) if (netif_running(ndev)) cpsw_ndo_open(ndev); } + rtnl_unlock(); + return 0; } #endif diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 84fbe5714f8b..481c7bf0395b 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1767,6 +1767,7 @@ static int davinci_emac_try_get_mac(struct platform_device *pdev, */ static int davinci_emac_probe(struct platform_device *pdev) { + struct device_node *np = pdev->dev.of_node; int rc = 0; struct resource *res, *res_ctrl; struct net_device *ndev; @@ -1805,7 +1806,7 @@ static int davinci_emac_probe(struct platform_device *pdev) if (!pdata) { dev_err(&pdev->dev, "no platform data\n"); rc = -ENODEV; - goto no_pdata; + goto err_free_netdev; } /* MAC addr and PHY mask , RMII enable info from platform_data */ @@ -1941,6 +1942,10 @@ no_cpdma_chan: cpdma_chan_destroy(priv->rxchan); cpdma_ctlr_destroy(priv->dma); no_pdata: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + of_node_put(priv->phy_node); +err_free_netdev: free_netdev(ndev); return rc; } @@ -1956,6 +1961,7 @@ static int davinci_emac_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct emac_priv *priv = netdev_priv(ndev); + struct device_node *np = pdev->dev.of_node; dev_notice(&ndev->dev, "DaVinci EMAC: davinci_emac_remove()\n"); @@ -1968,6 +1974,8 @@ static int davinci_emac_remove(struct platform_device *pdev) unregister_netdev(ndev); of_node_put(priv->phy_node); pm_runtime_disable(&pdev->dev); + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); free_netdev(ndev); return 0; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 42edd7b7902f..8b4822ad27cb 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -859,7 +859,6 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve = netdev_priv(dev); struct geneve_sock *gs4; struct rtable *rt = NULL; - const struct iphdr *iip; /* interior IP header */ int err = -EINVAL; struct flowi4 fl4; __u8 tos, ttl; @@ -890,8 +889,6 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); skb_reset_mac_header(skb); - iip = ip_hdr(skb); - if (info) { const struct ip_tunnel_key *key = &info->key; u8 *opts = NULL; @@ -911,7 +908,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (unlikely(err)) goto tx_error; - tos = ip_tunnel_ecn_encap(key->tos, iip, skb); + tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; } else { @@ -920,7 +917,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (unlikely(err)) goto tx_error; - tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, iip, skb); + tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, ip_hdr(skb), skb); ttl = geneve->ttl; if (!ttl && IN_MULTICAST(ntohl(fl4.daddr))) ttl = 1; @@ -952,7 +949,6 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, { struct geneve_dev *geneve = netdev_priv(dev); struct dst_entry *dst = NULL; - const struct iphdr *iip; /* interior IP header */ struct geneve_sock *gs6; int err = -EINVAL; struct flowi6 fl6; @@ -982,8 +978,6 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); skb_reset_mac_header(skb); - iip = ip_hdr(skb); - if (info) { const struct ip_tunnel_key *key = &info->key; u8 *opts = NULL; @@ -1004,7 +998,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (unlikely(err)) goto tx_error; - prio = ip_tunnel_ecn_encap(key->tos, iip, skb); + prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; label = info->key.label; } else { @@ -1014,7 +1008,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, goto tx_error; prio = ip_tunnel_ecn_encap(ip6_tclass(fl6.flowlabel), - iip, skb); + ip_hdr(skb), skb); ttl = geneve->ttl; if (!ttl && ipv6_addr_is_multicast(&fl6.daddr)) ttl = 1; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index f6382150b16a..c9140c3aeb67 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -47,6 +47,10 @@ NETIF_F_TSO | \ NETIF_F_TSO6 | \ NETIF_F_HW_CSUM) + +/* Restrict GSO size to account for NVGRE */ +#define NETVSC_GSO_MAX_SIZE 62768 + static int ring_size = 128; module_param(ring_size, int, S_IRUGO); MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)"); @@ -1400,6 +1404,7 @@ static int netvsc_probe(struct hv_device *dev, nvdev = net_device_ctx->nvdev; netif_set_real_num_tx_queues(net, nvdev->num_chn); netif_set_real_num_rx_queues(net, nvdev->num_chn); + netif_set_gso_max_size(net, NETVSC_GSO_MAX_SIZE); ret = register_netdev(net); if (ret != 0) { diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index f442eb366863..dfbc4ef6d507 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -497,6 +497,7 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev, struct net_device *phy_dev; int err; u16 mode = IPVLAN_MODE_L3; + bool create = false; if (!tb[IFLA_LINK]) return -EINVAL; @@ -513,6 +514,7 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev, err = ipvlan_port_create(phy_dev); if (err < 0) return err; + create = true; } if (data && data[IFLA_IPVLAN_MODE]) @@ -536,22 +538,29 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev, err = register_netdevice(dev); if (err < 0) - return err; + goto destroy_ipvlan_port; err = netdev_upper_dev_link(phy_dev, dev); if (err) { - unregister_netdevice(dev); - return err; + goto unregister_netdev; } err = ipvlan_set_port_mode(port, mode); if (err) { - unregister_netdevice(dev); - return err; + goto unlink_netdev; } list_add_tail_rcu(&ipvlan->pnode, &port->ipvlans); netif_stacked_transfer_operstate(phy_dev, dev); return 0; + +unlink_netdev: + netdev_upper_dev_unlink(phy_dev, dev); +unregister_netdev: + unregister_netdevice(dev); +destroy_ipvlan_port: + if (create) + ipvlan_port_destroy(phy_dev); + return err; } static void ipvlan_link_delete(struct net_device *dev, struct list_head *head) diff --git a/drivers/net/irda/irda-usb.c b/drivers/net/irda/irda-usb.c index a198946bc54f..8716b8c07feb 100644 --- a/drivers/net/irda/irda-usb.c +++ b/drivers/net/irda/irda-usb.c @@ -1723,6 +1723,7 @@ static int irda_usb_probe(struct usb_interface *intf, /* Don't change this buffer size and allocation without doing * some heavy and complete testing. Don't ask why :-( * Jean II */ + ret = -ENOMEM; self->speed_buff = kzalloc(IRDA_USB_SPEED_MTU, GFP_KERNEL); if (!self->speed_buff) goto err_out_3; diff --git a/drivers/net/irda/w83977af_ir.c b/drivers/net/irda/w83977af_ir.c index 4e3d2e7c697c..e8c3a8c32534 100644 --- a/drivers/net/irda/w83977af_ir.c +++ b/drivers/net/irda/w83977af_ir.c @@ -518,7 +518,9 @@ static netdev_tx_t w83977af_hard_xmit(struct sk_buff *skb, mtt = irda_get_mtt(skb); pr_debug("%s(%ld), mtt=%d\n", __func__ , jiffies, mtt); - if (mtt) + if (mtt > 1000) + mdelay(mtt/1000); + else if (mtt) udelay(mtt); /* Enable DMA interrupt */ diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 070e3290aa6e..7869b0651576 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -491,7 +491,13 @@ static int macvtap_newlink(struct net *src_net, /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ - return macvlan_common_newlink(src_net, dev, tb, data); + err = macvlan_common_newlink(src_net, dev, tb, data); + if (err) { + netdev_rx_handler_unregister(dev); + return err; + } + + return 0; } static void macvtap_dellink(struct net_device *dev, @@ -736,13 +742,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, if (zerocopy) err = zerocopy_sg_from_iter(skb, from); - else { + else err = skb_copy_datagram_from_iter(skb, 0, from, len); - if (!err && m && m->msg_control) { - struct ubuf_info *uarg = m->msg_control; - uarg->callback(uarg, false); - } - } if (err) goto err_kfree; @@ -773,7 +774,11 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, skb_shinfo(skb)->destructor_arg = m->msg_control; skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + } else if (m && m->msg_control) { + struct ubuf_info *uarg = m->msg_control; + uarg->callback(uarg, false); } + if (vlan) { skb->dev = vlan->dev; dev_queue_xmit(skb); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 1a4bf8acad78..c4ceb082e970 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -857,11 +857,17 @@ EXPORT_SYMBOL(phy_attached_print); int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, u32 flags, phy_interface_t interface) { + struct module *ndev_owner = dev->dev.parent->driver->owner; struct mii_bus *bus = phydev->mdio.bus; struct device *d = &phydev->mdio.dev; int err; - if (!try_module_get(bus->owner)) { + /* For Ethernet device drivers that register their own MDIO bus, we + * will have bus->owner match ndev_mod, so we do not want to increment + * our own module->refcnt here, otherwise we would not be able to + * unload later on. + */ + if (ndev_owner != bus->owner && !try_module_get(bus->owner)) { dev_err(&dev->dev, "failed to get the bus module\n"); return -EIO; } @@ -921,7 +927,8 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, error: put_device(d); - module_put(bus->owner); + if (ndev_owner != bus->owner) + module_put(bus->owner); return err; } EXPORT_SYMBOL(phy_attach_direct); @@ -971,6 +978,8 @@ EXPORT_SYMBOL(phy_attach); */ void phy_detach(struct phy_device *phydev) { + struct net_device *dev = phydev->attached_dev; + struct module *ndev_owner = dev->dev.parent->driver->owner; struct mii_bus *bus; int i; @@ -998,7 +1007,8 @@ void phy_detach(struct phy_device *phydev) bus = phydev->mdio.bus; put_device(&phydev->mdio.dev); - module_put(bus->owner); + if (ndev_owner != bus->owner) + module_put(bus->owner); } EXPORT_SYMBOL(phy_detach); diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index aadd6e9f54ad..9cbe645e3d89 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -102,15 +102,19 @@ static int rtl8211f_config_init(struct phy_device *phydev) if (ret < 0) return ret; - if (phydev->interface == PHY_INTERFACE_MODE_RGMII) { - /* enable TXDLY */ - phy_write(phydev, RTL8211F_PAGE_SELECT, 0xd08); - reg = phy_read(phydev, 0x11); + phy_write(phydev, RTL8211F_PAGE_SELECT, 0xd08); + reg = phy_read(phydev, 0x11); + + /* enable TX-delay for rgmii-id and rgmii-txid, otherwise disable it */ + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID || + phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) reg |= RTL8211F_TX_DELAY; - phy_write(phydev, 0x11, reg); - /* restore to default page 0 */ - phy_write(phydev, RTL8211F_PAGE_SELECT, 0x0); - } + else + reg &= ~RTL8211F_TX_DELAY; + + phy_write(phydev, 0x11, reg); + /* restore to default page 0 */ + phy_write(phydev, RTL8211F_PAGE_SELECT, 0x0); return 0; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 8093e39ae263..db6acecabeaa 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1246,13 +1246,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, if (zerocopy) err = zerocopy_sg_from_iter(skb, from); - else { + else err = skb_copy_datagram_from_iter(skb, 0, from, len); - if (!err && msg_control) { - struct ubuf_info *uarg = msg_control; - uarg->callback(uarg, false); - } - } if (err) { this_cpu_inc(tun->pcpu_stats->rx_dropped); @@ -1298,6 +1293,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_shinfo(skb)->destructor_arg = msg_control; skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + } else if (msg_control) { + struct ubuf_info *uarg = msg_control; + uarg->callback(uarg, false); } skb_reset_network_header(skb); diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index cce24950a0ab..dc7b6392e75a 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -603,12 +603,12 @@ static void ax88772_suspend(struct usbnet *dev) u16 medium; /* Stop MAC operation */ - medium = asix_read_medium_status(dev, 0); + medium = asix_read_medium_status(dev, 1); medium &= ~AX_MEDIUM_RE; - asix_write_medium_mode(dev, medium, 0); + asix_write_medium_mode(dev, medium, 1); netdev_dbg(dev->net, "ax88772_suspend: medium=0x%04x\n", - asix_read_medium_status(dev, 0)); + asix_read_medium_status(dev, 1)); /* Preserve BMCR for restoring */ priv->presvd_phy_bmcr = diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index c47ec0a04c8e..dd623f674487 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -388,12 +388,6 @@ void usbnet_cdc_status(struct usbnet *dev, struct urb *urb) case USB_CDC_NOTIFY_NETWORK_CONNECTION: netif_dbg(dev, timer, dev->net, "CDC: carrier %s\n", event->wValue ? "on" : "off"); - - /* Work-around for devices with broken off-notifications */ - if (event->wValue && - !test_bit(__LINK_STATE_NOCARRIER, &dev->net->state)) - usbnet_link_change(dev, 0, 0); - usbnet_link_change(dev, !!event->wValue, 0); break; case USB_CDC_NOTIFY_SPEED_CHANGE: /* tx/rx rates */ @@ -466,6 +460,36 @@ static int usbnet_cdc_zte_rx_fixup(struct usbnet *dev, struct sk_buff *skb) return 1; } +/* Ensure correct link state + * + * Some devices (ZTE MF823/831/910) export two carrier on notifications when + * connected. This causes the link state to be incorrect. Work around this by + * always setting the state to off, then on. + */ +void usbnet_cdc_zte_status(struct usbnet *dev, struct urb *urb) +{ + struct usb_cdc_notification *event; + + if (urb->actual_length < sizeof(*event)) + return; + + event = urb->transfer_buffer; + + if (event->bNotificationType != USB_CDC_NOTIFY_NETWORK_CONNECTION) { + usbnet_cdc_status(dev, urb); + return; + } + + netif_dbg(dev, timer, dev->net, "CDC: carrier %s\n", + event->wValue ? "on" : "off"); + + if (event->wValue && + netif_carrier_ok(dev->net)) + netif_carrier_off(dev->net); + + usbnet_link_change(dev, !!event->wValue, 0); +} + static const struct driver_info cdc_info = { .description = "CDC Ethernet Device", .flags = FLAG_ETHER | FLAG_POINTTOPOINT, @@ -481,7 +505,7 @@ static const struct driver_info zte_cdc_info = { .flags = FLAG_ETHER | FLAG_POINTTOPOINT, .bind = usbnet_cdc_zte_bind, .unbind = usbnet_cdc_unbind, - .status = usbnet_cdc_status, + .status = usbnet_cdc_zte_status, .set_rx_mode = usbnet_cdc_update_filter, .manage_power = usbnet_manage_power, .rx_fixup = usbnet_cdc_zte_rx_fixup, diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index 96a5028621c8..3a98f3762a4c 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -602,6 +602,21 @@ static const struct driver_info cdc_mbim_info_ndp_to_end = { .data = CDC_NCM_FLAG_NDP_TO_END, }; +/* Some modems (e.g. Telit LE922A6) do not work properly with altsetting + * toggle done in cdc_ncm_bind_common. CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE + * flag is used to avoid this procedure. + */ +static const struct driver_info cdc_mbim_info_avoid_altsetting_toggle = { + .description = "CDC MBIM", + .flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN, + .bind = cdc_mbim_bind, + .unbind = cdc_mbim_unbind, + .manage_power = cdc_mbim_manage_power, + .rx_fixup = cdc_mbim_rx_fixup, + .tx_fixup = cdc_mbim_tx_fixup, + .data = CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE, +}; + static const struct usb_device_id mbim_devs[] = { /* This duplicate NCM entry is intentional. MBIM devices can * be disguised as NCM by default, and this is necessary to @@ -626,6 +641,12 @@ static const struct usb_device_id mbim_devs[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x12d1, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&cdc_mbim_info_ndp_to_end, }, + + /* Telit LE922A6 in MBIM composition */ + { USB_DEVICE_AND_INTERFACE_INFO(0x1bc7, 0x1041, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&cdc_mbim_info_avoid_altsetting_toggle, + }, + /* default entry */ { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&cdc_mbim_info_zlp, diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 877c9516e781..afbfc0f656f3 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -839,11 +839,18 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber; + /* Device-specific flags */ + ctx->drvflags = drvflags; + /* Reset data interface. Some devices will not reset properly * unless they are configured first. Toggle the altsetting to - * force a reset + * force a reset. + * Some other devices do not work properly with this procedure + * that can be avoided using quirk CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE */ - usb_set_interface(dev->udev, iface_no, data_altsetting); + if (!(ctx->drvflags & CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE)) + usb_set_interface(dev->udev, iface_no, data_altsetting); + temp = usb_set_interface(dev->udev, iface_no, 0); if (temp) { dev_dbg(&intf->dev, "set interface failed\n"); @@ -890,9 +897,6 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ /* finish setting up the device specific data */ cdc_ncm_setup(dev); - /* Device-specific flags */ - ctx->drvflags = drvflags; - /* Allocate the delayed NDP if needed. */ if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) { ctx->delayed_ndp16 = kzalloc(ctx->max_ndp_size, GFP_KERNEL); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index db558b8b32fe..f33460cec79f 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3395,6 +3395,7 @@ static int lan78xx_probe(struct usb_interface *intf, if (buf) { dev->urb_intr = usb_alloc_urb(0, GFP_KERNEL); if (!dev->urb_intr) { + ret = -ENOMEM; kfree(buf); goto out3; } else { diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 3ff76c6db4f6..6fe1cdb0174f 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -894,6 +894,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */ {QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)}, /* XS Stick W100-2 from 4G Systems */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 7276d5a95bd0..cbf1c613c67a 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -969,12 +969,17 @@ static int virtnet_set_mac_address(struct net_device *dev, void *p) struct virtnet_info *vi = netdev_priv(dev); struct virtio_device *vdev = vi->vdev; int ret; - struct sockaddr *addr = p; + struct sockaddr *addr; struct scatterlist sg; - ret = eth_prepare_mac_addr_change(dev, p); + addr = kmalloc(sizeof(*addr), GFP_KERNEL); + if (!addr) + return -ENOMEM; + memcpy(addr, p, sizeof(*addr)); + + ret = eth_prepare_mac_addr_change(dev, addr); if (ret) - return ret; + goto out; if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) { sg_init_one(&sg, addr->sa_data, dev->addr_len); @@ -982,7 +987,8 @@ static int virtnet_set_mac_address(struct net_device *dev, void *p) VIRTIO_NET_CTRL_MAC_ADDR_SET, &sg)) { dev_warn(&vdev->dev, "Failed to set mac address by vq command.\n"); - return -EINVAL; + ret = -EINVAL; + goto out; } } else if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC) && !virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) { @@ -996,8 +1002,11 @@ static int virtnet_set_mac_address(struct net_device *dev, void *p) } eth_commit_mac_addr_change(dev, p); + ret = 0; - return 0; +out: + kfree(addr); + return ret; } static struct rtnl_link_stats64 *virtnet_stats(struct net_device *dev, diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 24532cdebb00..2ba01ca02c9c 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -611,6 +611,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int notify = 0; + int rc; f = __vxlan_find_mac(vxlan, mac); if (f) { @@ -641,8 +642,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, if ((flags & NLM_F_APPEND) && (is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { - int rc = vxlan_fdb_append(f, ip, port, vni, ifindex, - &rd); + rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); if (rc < 0) return rc; @@ -673,7 +673,11 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, INIT_LIST_HEAD(&f->remotes); memcpy(f->eth_addr, mac, ETH_ALEN); - vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); + rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); + if (rc < 0) { + kfree(f); + return rc; + } ++vxlan->addrcnt; hlist_add_head_rcu(&f->hlist, diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c index 39ce76ad00bc..16241d21727b 100644 --- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c +++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c @@ -2222,8 +2222,9 @@ done: is_scanning_required = 1; } else { mwifiex_dbg(priv->adapter, MSG, - "info: trying to associate to '%s' bssid %pM\n", - (char *)req_ssid.ssid, bss->bssid); + "info: trying to associate to '%.*s' bssid %pM\n", + req_ssid.ssid_len, (char *)req_ssid.ssid, + bss->bssid); memcpy(&priv->cfg_bssid, bss->bssid, ETH_ALEN); break; } @@ -2283,8 +2284,8 @@ mwifiex_cfg80211_connect(struct wiphy *wiphy, struct net_device *dev, } mwifiex_dbg(adapter, INFO, - "info: Trying to associate to %s and bssid %pM\n", - (char *)sme->ssid, sme->bssid); + "info: Trying to associate to %.*s and bssid %pM\n", + (int)sme->ssid_len, (char *)sme->ssid, sme->bssid); if (!mwifiex_stop_bg_scan(priv)) cfg80211_sched_scan_stopped_rtnl(priv->wdev.wiphy); @@ -2417,8 +2418,8 @@ mwifiex_cfg80211_join_ibss(struct wiphy *wiphy, struct net_device *dev, } mwifiex_dbg(priv->adapter, MSG, - "info: trying to join to %s and bssid %pM\n", - (char *)params->ssid, params->bssid); + "info: trying to join to %.*s and bssid %pM\n", + params->ssid_len, (char *)params->ssid, params->bssid); mwifiex_set_ibss_params(priv, params); diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index a8b6949a8778..23d4a1728cdf 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -715,7 +715,7 @@ EXPORT_SYMBOL_GPL(nd_cmd_in_size); u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, const struct nd_cmd_desc *desc, int idx, const u32 *in_field, - const u32 *out_field) + const u32 *out_field, unsigned long remainder) { if (idx >= desc->out_num) return UINT_MAX; @@ -727,9 +727,24 @@ u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, return in_field[1]; else if (nvdimm && cmd == ND_CMD_VENDOR && idx == 2) return out_field[1]; - else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 2) - return out_field[1] - 8; - else if (cmd == ND_CMD_CALL) { + else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 2) { + /* + * Per table 9-276 ARS Data in ACPI 6.1, out_field[1] is + * "Size of Output Buffer in bytes, including this + * field." + */ + if (out_field[1] < 4) + return 0; + /* + * ACPI 6.1 is ambiguous if 'status' is included in the + * output size. If we encounter an output size that + * overshoots the remainder by 4 bytes, assume it was + * including 'status'. + */ + if (out_field[1] - 8 == remainder) + return remainder; + return out_field[1] - 4; + } else if (cmd == ND_CMD_CALL) { struct nd_cmd_pkg *pkg = (struct nd_cmd_pkg *) in_field; return pkg->nd_size_out; @@ -876,7 +891,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, /* process an output envelope */ for (i = 0; i < desc->out_num; i++) { u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, - (u32 *) in_env, (u32 *) out_env); + (u32 *) in_env, (u32 *) out_env, 0); u32 copy; if (out_size == UINT_MAX) { diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 5a3145a02547..262281bd68fa 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -490,3 +490,18 @@ int of_phy_register_fixed_link(struct device_node *np) return -ENODEV; } EXPORT_SYMBOL(of_phy_register_fixed_link); + +void of_phy_deregister_fixed_link(struct device_node *np) +{ + struct phy_device *phydev; + + phydev = of_phy_find_device(np); + if (!phydev) + return; + + fixed_phy_unregister(phydev); + + put_device(&phydev->mdio.dev); /* of_phy_find_device() */ + phy_device_free(phydev); /* fixed_phy_register() */ +} +EXPORT_SYMBOL(of_phy_deregister_fixed_link); diff --git a/drivers/pci/host/pcie-designware-plat.c b/drivers/pci/host/pcie-designware-plat.c index 8df6312ed300..1a02038c4640 100644 --- a/drivers/pci/host/pcie-designware-plat.c +++ b/drivers/pci/host/pcie-designware-plat.c @@ -3,7 +3,7 @@ * * Copyright (C) 2015-2016 Synopsys, Inc. (www.synopsys.com) * - * Authors: Joao Pinto <[email protected]> + * Authors: Joao Pinto <[email protected]> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c index db553dc22c8e..2b6a59266689 100644 --- a/drivers/pci/pcie/aer/aer_inject.c +++ b/drivers/pci/pcie/aer/aer_inject.c @@ -307,20 +307,6 @@ out: return 0; } -static struct pci_dev *pcie_find_root_port(struct pci_dev *dev) -{ - while (1) { - if (!pci_is_pcie(dev)) - break; - if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) - return dev; - if (!dev->bus->self) - break; - dev = dev->bus->self; - } - return NULL; -} - static int find_aer_device_iter(struct device *device, void *data) { struct pcie_device **result = data; diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ab002671fa60..104c46d53121 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1439,6 +1439,21 @@ static void program_hpp_type1(struct pci_dev *dev, struct hpp_type1 *hpp) dev_warn(&dev->dev, "PCI-X settings not supported\n"); } +static bool pcie_root_rcb_set(struct pci_dev *dev) +{ + struct pci_dev *rp = pcie_find_root_port(dev); + u16 lnkctl; + + if (!rp) + return false; + + pcie_capability_read_word(rp, PCI_EXP_LNKCTL, &lnkctl); + if (lnkctl & PCI_EXP_LNKCTL_RCB) + return true; + + return false; +} + static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp) { int pos; @@ -1468,9 +1483,20 @@ static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp) ~hpp->pci_exp_devctl_and, hpp->pci_exp_devctl_or); /* Initialize Link Control Register */ - if (pcie_cap_has_lnkctl(dev)) + if (pcie_cap_has_lnkctl(dev)) { + + /* + * If the Root Port supports Read Completion Boundary of + * 128, set RCB to 128. Otherwise, clear it. + */ + hpp->pci_exp_lnkctl_and |= PCI_EXP_LNKCTL_RCB; + hpp->pci_exp_lnkctl_or &= ~PCI_EXP_LNKCTL_RCB; + if (pcie_root_rcb_set(dev)) + hpp->pci_exp_lnkctl_or |= PCI_EXP_LNKCTL_RCB; + pcie_capability_clear_and_set_word(dev, PCI_EXP_LNKCTL, ~hpp->pci_exp_lnkctl_and, hpp->pci_exp_lnkctl_or); + } /* Find Advanced Error Reporting Enhanced Capability */ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); diff --git a/drivers/power/avs/rockchip-io-domain.c b/drivers/power/avs/rockchip-io-domain.c index 01b6d3f9b8fb..56bce1908be2 100644 --- a/drivers/power/avs/rockchip-io-domain.c +++ b/drivers/power/avs/rockchip-io-domain.c @@ -143,7 +143,7 @@ static int rockchip_iodomain_notify(struct notifier_block *nb, if (ret && event == REGULATOR_EVENT_PRE_VOLTAGE_CHANGE) return NOTIFY_BAD; - dev_info(supply->iod->dev, "Setting to %d done\n", uV); + dev_dbg(supply->iod->dev, "Setting to %d done\n", uV); return NOTIFY_OK; } diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index c5326055beee..f4f77c5b0c83 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -1323,18 +1323,20 @@ lpfc_sli_ringtxcmpl_put(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, { lockdep_assert_held(&phba->hbalock); - BUG_ON(!piocb || !piocb->vport); + BUG_ON(!piocb); list_add_tail(&piocb->list, &pring->txcmplq); piocb->iocb_flag |= LPFC_IO_ON_TXCMPLQ; if ((unlikely(pring->ringno == LPFC_ELS_RING)) && (piocb->iocb.ulpCommand != CMD_ABORT_XRI_CN) && - (piocb->iocb.ulpCommand != CMD_CLOSE_XRI_CN) && - (!(piocb->vport->load_flag & FC_UNLOADING))) - mod_timer(&piocb->vport->els_tmofunc, - jiffies + - msecs_to_jiffies(1000 * (phba->fc_ratov << 1))); + (piocb->iocb.ulpCommand != CMD_CLOSE_XRI_CN)) { + BUG_ON(!piocb->vport); + if (!(piocb->vport->load_flag & FC_UNLOADING)) + mod_timer(&piocb->vport->els_tmofunc, + jiffies + + msecs_to_jiffies(1000 * (phba->fc_ratov << 1))); + } return 0; } diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index e3b30ea9ece5..a504e2e003da 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -506,7 +506,7 @@ static void vhost_vsock_reset_orphans(struct sock *sk) * executing. */ - if (!vhost_vsock_get(vsk->local_addr.svm_cid)) { + if (!vhost_vsock_get(vsk->remote_addr.svm_cid)) { sock_set_flag(sk, SOCK_DONE); vsk->peer_shutdown = SHUTDOWN_MASK; sk->sk_state = SS_UNCONNECTED; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 78180d151730..a594c7879cc2 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1261,26 +1261,30 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) return -ECHILD; op = ceph_snap(dir) == CEPH_SNAPDIR ? - CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_LOOKUP; + CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_GETATTR; req = ceph_mdsc_create_request(mdsc, op, USE_ANY_MDS); if (!IS_ERR(req)) { req->r_dentry = dget(dentry); - req->r_num_caps = 2; + req->r_num_caps = op == CEPH_MDS_OP_GETATTR ? 1 : 2; mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED; if (ceph_security_xattr_wanted(dir)) mask |= CEPH_CAP_XATTR_SHARED; req->r_args.getattr.mask = mask; - req->r_locked_dir = dir; err = ceph_mdsc_do_request(mdsc, NULL, req); - if (err == 0 || err == -ENOENT) { - if (dentry == req->r_dentry) { - valid = !d_unhashed(dentry); - } else { - d_invalidate(req->r_dentry); - err = -EAGAIN; - } + switch (err) { + case 0: + if (d_really_is_positive(dentry) && + d_inode(dentry) == req->r_target_inode) + valid = 1; + break; + case -ENOENT: + if (d_really_is_negative(dentry)) + valid = 1; + /* Fallthrough */ + default: + break; } ceph_mdsc_put_request(req); dout("d_revalidate %p lookup result=%d\n", diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index b3ebe512d64c..096f79997f75 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1739,8 +1739,6 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) * This should be done on write(), truncate() and chown(). */ if (!fc->handle_killpriv) { - int kill; - /* * ia_mode calculation may have used stale i_mode. * Refresh and recalculate. @@ -1750,12 +1748,11 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) return ret; attr->ia_mode = inode->i_mode; - kill = should_remove_suid(entry); - if (kill & ATTR_KILL_SUID) { + if (inode->i_mode & S_ISUID) { attr->ia_valid |= ATTR_MODE; attr->ia_mode &= ~S_ISUID; } - if (kill & ATTR_KILL_SGID) { + if ((inode->i_mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { attr->ia_valid |= ATTR_MODE; attr->ia_mode &= ~S_ISGID; } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index edd46a0e951d..0e100856c7b8 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -328,11 +328,11 @@ static struct dentry *ovl_d_real(struct dentry *dentry, if (!real) goto bug; + /* Handle recursion */ + real = d_real(real, inode, open_flags); + if (!inode || inode == d_inode(real)) return real; - - /* Handle recursion */ - return d_real(real, inode, open_flags); bug: WARN(1, "ovl_d_real(%pd4, %s:%lu): real dentry not found\n", dentry, inode ? inode->i_sb->s_id : "NULL", inode ? inode->i_ino : 0); diff --git a/include/acpi/processor.h b/include/acpi/processor.h index f3db11c24654..c1ba00fc4888 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -249,6 +249,7 @@ extern int acpi_processor_register_performance(struct acpi_processor_performance *performance, unsigned int cpu); extern void acpi_processor_unregister_performance(unsigned int cpu); +int acpi_processor_pstate_control(void); /* note: this locks both the calling module and the processor module if a _PPC object exists, rmmod is disallowed then */ int acpi_processor_notify_smm(struct module *calling_module); @@ -294,7 +295,7 @@ static inline void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx #ifdef CONFIG_CPU_FREQ void acpi_processor_ppc_init(void); void acpi_processor_ppc_exit(void); -int acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag); +void acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag); extern int acpi_processor_get_bios_limit(int cpu, unsigned int *limit); #else static inline void acpi_processor_ppc_init(void) diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h index 61580b19f9f6..22f884c97387 100644 --- a/include/crypto/drbg.h +++ b/include/crypto/drbg.h @@ -124,6 +124,8 @@ struct drbg_state { struct skcipher_request *ctr_req; /* CTR mode request handle */ __u8 *ctr_null_value_buf; /* CTR mode unaligned buffer */ __u8 *ctr_null_value; /* CTR mode aligned zero buf */ + __u8 *outscratchpadbuf; /* CTR mode output scratchpad */ + __u8 *outscratchpad; /* CTR mode aligned outbuf */ struct completion ctr_completion; /* CTR mode async handler */ int ctr_async_err; /* CTR mode async error */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 32dc0cbd51ca..7e05c5e4e45c 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -175,7 +175,7 @@ void disable_cpufreq(void); u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy); int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); -int cpufreq_update_policy(unsigned int cpu); +void cpufreq_update_policy(unsigned int cpu); bool have_governor_per_policy(void); struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); void cpufreq_enable_fast_switch(struct cpufreq_policy *policy); @@ -234,6 +234,10 @@ __ATTR(_name, _perm, show_##_name, NULL) static struct freq_attr _name = \ __ATTR(_name, 0644, show_##_name, store_##_name) +#define cpufreq_freq_attr_wo(_name) \ +static struct freq_attr _name = \ +__ATTR(_name, 0200, NULL, store_##_name) + struct global_attr { struct attribute attr; ssize_t (*show)(struct kobject *kobj, diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index f4947fda11e7..8458c5351e56 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -143,7 +143,7 @@ u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd, const struct nd_cmd_desc *desc, int idx, void *buf); u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, const struct nd_cmd_desc *desc, int idx, const u32 *in_field, - const u32 *out_field); + const u32 *out_field, unsigned long remainder); int nvdimm_bus_check_dimm_count(struct nvdimm_bus *nvdimm_bus, int dimm_count); struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region_desc *ndr_desc); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 3be7abd6e722..c9f379689dd0 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -476,7 +476,6 @@ enum { enum { MLX4_INTERFACE_STATE_UP = 1 << 0, MLX4_INTERFACE_STATE_DELETION = 1 << 1, - MLX4_INTERFACE_STATE_SHUTDOWN = 1 << 2, }; #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \ diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 2ab233661ae5..a58cca8bcb29 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -29,6 +29,7 @@ struct phy_device *of_phy_attach(struct net_device *dev, extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); extern int of_mdio_parse_addr(struct device *dev, const struct device_node *np); extern int of_phy_register_fixed_link(struct device_node *np); +extern void of_phy_deregister_fixed_link(struct device_node *np); extern bool of_phy_is_fixed_link(struct device_node *np); #else /* CONFIG_OF */ @@ -83,6 +84,9 @@ static inline int of_phy_register_fixed_link(struct device_node *np) { return -ENOSYS; } +static inline void of_phy_deregister_fixed_link(struct device_node *np) +{ +} static inline bool of_phy_is_fixed_link(struct device_node *np) { return false; diff --git a/include/linux/pci.h b/include/linux/pci.h index 0e49f70dbd9b..a38772a85588 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1928,6 +1928,20 @@ static inline int pci_pcie_type(const struct pci_dev *dev) return (pcie_caps_reg(dev) & PCI_EXP_FLAGS_TYPE) >> 4; } +static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev) +{ + while (1) { + if (!pci_is_pcie(dev)) + break; + if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) + return dev; + if (!dev->bus->self) + break; + dev = dev->bus->self; + } + return NULL; +} + void pci_request_acs(void); bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags); bool pci_acs_path_enabled(struct pci_dev *start, diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index a09fe5c009c8..81ece61075df 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -15,11 +15,11 @@ #include <linux/err.h> #include <linux/of.h> #include <linux/notifier.h> +#include <linux/spinlock.h> /* Defines used for the flags field in the struct generic_pm_domain */ #define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ - -#define GENPD_MAX_NUM_STATES 8 /* Number of possible low power states */ +#define GENPD_FLAG_IRQ_SAFE (1U << 1) /* PM domain operates in atomic */ enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ @@ -40,15 +40,18 @@ struct gpd_dev_ops { struct genpd_power_state { s64 power_off_latency_ns; s64 power_on_latency_ns; + s64 residency_ns; + struct fwnode_handle *fwnode; }; +struct genpd_lock_ops; + struct generic_pm_domain { struct dev_pm_domain domain; /* PM domain operations */ struct list_head gpd_list_node; /* Node in the global PM domains list */ struct list_head master_links; /* Links with PM domain as a master */ struct list_head slave_links; /* Links with PM domain as a slave */ struct list_head dev_list; /* List of devices */ - struct mutex lock; struct dev_power_governor *gov; struct work_struct power_off_work; struct fwnode_handle *provider; /* Identity of the domain provider */ @@ -70,9 +73,18 @@ struct generic_pm_domain { void (*detach_dev)(struct generic_pm_domain *domain, struct device *dev); unsigned int flags; /* Bit field of configs for genpd */ - struct genpd_power_state states[GENPD_MAX_NUM_STATES]; + struct genpd_power_state *states; unsigned int state_count; /* number of states */ unsigned int state_idx; /* state that genpd will go to when off */ + void *free; /* Free the state that was allocated for default */ + const struct genpd_lock_ops *lock_ops; + union { + struct mutex mlock; + struct { + spinlock_t slock; + unsigned long lock_flags; + }; + }; }; @@ -205,6 +217,8 @@ extern int of_genpd_add_device(struct of_phandle_args *args, extern int of_genpd_add_subdomain(struct of_phandle_args *parent, struct of_phandle_args *new_subdomain); extern struct generic_pm_domain *of_genpd_remove_last(struct device_node *np); +extern int of_genpd_parse_idle_states(struct device_node *dn, + struct genpd_power_state **states, int *n); int genpd_dev_pm_attach(struct device *dev); #else /* !CONFIG_PM_GENERIC_DOMAINS_OF */ @@ -234,6 +248,12 @@ static inline int of_genpd_add_subdomain(struct of_phandle_args *parent, return -ENODEV; } +static inline int of_genpd_parse_idle_states(struct device_node *dn, + struct genpd_power_state **states, int *n) +{ + return -ENODEV; +} + static inline int genpd_dev_pm_attach(struct device *dev) { return -ENODEV; diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index bca26157f5b6..0edd88f93904 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -17,13 +17,65 @@ #include <linux/err.h> #include <linux/notifier.h> +struct clk; +struct regulator; struct dev_pm_opp; struct device; +struct opp_table; enum dev_pm_opp_event { OPP_EVENT_ADD, OPP_EVENT_REMOVE, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE, }; +/** + * struct dev_pm_opp_supply - Power supply voltage/current values + * @u_volt: Target voltage in microvolts corresponding to this OPP + * @u_volt_min: Minimum voltage in microvolts corresponding to this OPP + * @u_volt_max: Maximum voltage in microvolts corresponding to this OPP + * @u_amp: Maximum current drawn by the device in microamperes + * + * This structure stores the voltage/current values for a single power supply. + */ +struct dev_pm_opp_supply { + unsigned long u_volt; + unsigned long u_volt_min; + unsigned long u_volt_max; + unsigned long u_amp; +}; + +/** + * struct dev_pm_opp_info - OPP freq/voltage/current values + * @rate: Target clk rate in hz + * @supplies: Array of voltage/current values for all power supplies + * + * This structure stores the freq/voltage/current values for a single OPP. + */ +struct dev_pm_opp_info { + unsigned long rate; + struct dev_pm_opp_supply *supplies; +}; + +/** + * struct dev_pm_set_opp_data - Set OPP data + * @old_opp: Old OPP info + * @new_opp: New OPP info + * @regulators: Array of regulator pointers + * @regulator_count: Number of regulators + * @clk: Pointer to clk + * @dev: Pointer to the struct device + * + * This structure contains all information required for setting an OPP. + */ +struct dev_pm_set_opp_data { + struct dev_pm_opp_info old_opp; + struct dev_pm_opp_info new_opp; + + struct regulator **regulators; + unsigned int regulator_count; + struct clk *clk; + struct device *dev; +}; + #if defined(CONFIG_PM_OPP) unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); @@ -62,8 +114,10 @@ int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, void dev_pm_opp_put_supported_hw(struct device *dev); int dev_pm_opp_set_prop_name(struct device *dev, const char *name); void dev_pm_opp_put_prop_name(struct device *dev); -int dev_pm_opp_set_regulator(struct device *dev, const char *name); -void dev_pm_opp_put_regulator(struct device *dev); +struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count); +void dev_pm_opp_put_regulators(struct opp_table *opp_table); +int dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); +void dev_pm_opp_register_put_opp_helper(struct device *dev); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask); int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); @@ -163,6 +217,14 @@ static inline int dev_pm_opp_set_supported_hw(struct device *dev, static inline void dev_pm_opp_put_supported_hw(struct device *dev) {} +static inline int dev_pm_opp_register_set_opp_helper(struct device *dev, + int (*set_opp)(struct dev_pm_set_opp_data *data)) +{ + return -ENOTSUPP; +} + +static inline void dev_pm_opp_register_put_opp_helper(struct device *dev) {} + static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) { return -ENOTSUPP; @@ -170,12 +232,12 @@ static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) static inline void dev_pm_opp_put_prop_name(struct device *dev) {} -static inline int dev_pm_opp_set_regulator(struct device *dev, const char *name) +static inline struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count) { - return -ENOTSUPP; + return ERR_PTR(-ENOTSUPP); } -static inline void dev_pm_opp_put_regulator(struct device *dev) {} +static inline void dev_pm_opp_put_regulators(struct opp_table *opp_table) {} static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 2e14d2667b6c..4957fc185ea9 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -61,12 +61,6 @@ static inline void pm_suspend_ignore_children(struct device *dev, bool enable) dev->power.ignore_children = enable; } -static inline bool pm_children_suspended(struct device *dev) -{ - return dev->power.ignore_children - || !atomic_read(&dev->power.child_count); -} - static inline void pm_runtime_get_noresume(struct device *dev) { atomic_inc(&dev->power.usage_count); @@ -162,7 +156,6 @@ static inline void pm_runtime_allow(struct device *dev) {} static inline void pm_runtime_forbid(struct device *dev) {} static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {} -static inline bool pm_children_suspended(struct device *dev) { return false; } static inline void pm_runtime_get_noresume(struct device *dev) {} static inline void pm_runtime_put_noidle(struct device *dev) {} static inline bool device_run_wake(struct device *dev) { return false; } @@ -265,9 +258,9 @@ static inline int pm_runtime_set_active(struct device *dev) return __pm_runtime_set_status(dev, RPM_ACTIVE); } -static inline void pm_runtime_set_suspended(struct device *dev) +static inline int pm_runtime_set_suspended(struct device *dev) { - __pm_runtime_set_status(dev, RPM_SUSPENDED); + return __pm_runtime_set_status(dev, RPM_SUSPENDED); } static inline void pm_runtime_disable(struct device *dev) diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 3a375d07d0dc..00d232406f18 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -81,7 +81,8 @@ #define CDC_NCM_TIMER_INTERVAL_MAX (U32_MAX / NSEC_PER_USEC) /* Driver flags */ -#define CDC_NCM_FLAG_NDP_TO_END 0x02 /* NDP is placed at end of frame */ +#define CDC_NCM_FLAG_NDP_TO_END 0x02 /* NDP is placed at end of frame */ +#define CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE 0x04 /* Avoid altsetting toggle during init */ #define cdc_ncm_comm_intf_is_mbim(x) ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \ (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 8fed1cd78658..f11ca837361b 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -970,6 +970,8 @@ int compat_ipv6_setsockopt(struct sock *sk, int level, int optname, int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); +int __ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, + int addr_len); int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr, int addr_len); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 50418052a520..d9d52c020a70 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -100,6 +100,9 @@ struct nf_conn { possible_net_t ct_net; +#if IS_ENABLED(CONFIG_NF_NAT) + struct rhlist_head nat_bysource; +#endif /* all members below initialized via memset */ u8 __nfct_init_offset[0]; @@ -117,9 +120,6 @@ struct nf_conn { /* Extensions */ struct nf_ct_ext *ext; -#if IS_ENABLED(CONFIG_NF_NAT) - struct rhash_head nat_bysource; -#endif /* Storage reserved for other modules, must be the last member */ union nf_conntrack_proto proto; }; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index d79d1e9b9546..b02af0bf5777 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -313,7 +313,7 @@ void nft_unregister_set(struct nft_set_ops *ops); * @size: maximum set size * @nelems: number of elements * @ndeact: number of deactivated elements queued for removal - * @timeout: default timeout value in msecs + * @timeout: default timeout value in jiffies * @gc_int: garbage collection interval in msecs * @policy: set parameterization (see enum nft_set_policies) * @udlen: user data length diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index 9692cda5f8fc..c48d93a28d1a 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -196,5 +196,6 @@ struct can_filter { }; #define CAN_INV_FILTER 0x20000000U /* to be set in can_filter.can_id */ +#define CAN_RAW_FILTER_MAX 512 /* maximum number of can_filter set via setsockopt() */ #endif /* !_UAPI_CAN_H */ diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h index e601c8c3bdc7..1158a043342a 100644 --- a/include/uapi/linux/if.h +++ b/include/uapi/linux/if.h @@ -31,7 +31,7 @@ #include <linux/hdlc/ioctl.h> /* For glibc compatibility. An empty enum does not compile. */ -#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 && \ +#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 || \ __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 /** * enum net_device_flags - &struct net_device flags @@ -99,7 +99,7 @@ enum net_device_flags { IFF_ECHO = 1<<18, /* volatile */ #endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */ }; -#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 && __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 */ +#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 || __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 */ /* for compatibility with glibc net/if.h */ #if __UAPI_DEF_IF_NET_DEVICE_FLAGS diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index d6d071fc3c56..3af60ee69053 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -640,7 +640,7 @@ * Control a data application associated with the currently viewed channel, * e.g. teletext or data broadcast application (MHEG, MHP, HbbTV, etc.) */ -#define KEY_DATA 0x275 +#define KEY_DATA 0x277 #define BTN_TRIGGER_HAPPY 0x2c0 #define BTN_TRIGGER_HAPPY1 0x2c0 diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild index cd26d7a0fd07..03f194aeadc5 100644 --- a/include/uapi/linux/netfilter/Kbuild +++ b/include/uapi/linux/netfilter/Kbuild @@ -5,6 +5,7 @@ header-y += nf_conntrack_ftp.h header-y += nf_conntrack_sctp.h header-y += nf_conntrack_tcp.h header-y += nf_conntrack_tuple_common.h +header-y += nf_log.h header-y += nf_tables.h header-y += nf_tables_compat.h header-y += nf_nat.h diff --git a/include/uapi/linux/tc_act/Kbuild b/include/uapi/linux/tc_act/Kbuild index e3969bd939e4..e3db7403296f 100644 --- a/include/uapi/linux/tc_act/Kbuild +++ b/include/uapi/linux/tc_act/Kbuild @@ -11,3 +11,5 @@ header-y += tc_vlan.h header-y += tc_bpf.h header-y += tc_connmark.h header-y += tc_ife.h +header-y += tc_tunnel_key.h +header-y += tc_skbmod.h diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6a936159c6e0..8199821f54cf 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2454,6 +2454,7 @@ static bool states_equal(struct bpf_verifier_env *env, struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { + bool varlen_map_access = env->varlen_map_value_access; struct bpf_reg_state *rold, *rcur; int i; @@ -2467,12 +2468,17 @@ static bool states_equal(struct bpf_verifier_env *env, /* If the ranges were not the same, but everything else was and * we didn't do a variable access into a map then we are a-ok. */ - if (!env->varlen_map_value_access && + if (!varlen_map_access && rold->type == rcur->type && rold->imm == rcur->imm) continue; + /* If we didn't map access then again we don't care about the + * mismatched range values and it's ok if our old type was + * UNKNOWN and we didn't go to a NOT_INIT'ed reg. + */ if (rold->type == NOT_INIT || - (rold->type == UNKNOWN_VALUE && rcur->type != NOT_INIT)) + (!varlen_map_access && rold->type == UNKNOWN_VALUE && + rcur->type != NOT_INIT)) continue; if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET && diff --git a/kernel/events/core.c b/kernel/events/core.c index 6ee1febdf6ff..02c8421f8c01 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -903,17 +903,14 @@ list_update_cgroup_event(struct perf_event *event, */ cpuctx = __get_cpu_context(ctx); - /* Only set/clear cpuctx->cgrp if current task uses event->cgrp. */ - if (perf_cgroup_from_task(current, ctx) != event->cgrp) { - /* - * We are removing the last cpu event in this context. - * If that event is not active in this cpu, cpuctx->cgrp - * should've been cleared by perf_cgroup_switch. - */ - WARN_ON_ONCE(!add && cpuctx->cgrp); - return; - } - cpuctx->cgrp = add ? event->cgrp : NULL; + /* + * cpuctx->cgrp is NULL until a cgroup event is sched in or + * ctx->nr_cgroup == 0 . + */ + if (add && perf_cgroup_from_task(current, ctx) == event->cgrp) + cpuctx->cgrp = event->cgrp; + else if (!add) + cpuctx->cgrp = NULL; } #else /* !CONFIG_CGROUP_PERF */ diff --git a/kernel/kcov.c b/kernel/kcov.c index 30e6d05aa5a9..3cbb0c879705 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -7,6 +7,7 @@ #include <linux/fs.h> #include <linux/mm.h> #include <linux/printk.h> +#include <linux/sched.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 589d763a49b3..4d7ffc0a0d00 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -506,13 +506,13 @@ static void __print_lock_name(struct lock_class *class) name = class->name; if (!name) { name = __get_key_name(class->key, str); - printk("%s", name); + printk(KERN_CONT "%s", name); } else { - printk("%s", name); + printk(KERN_CONT "%s", name); if (class->name_version > 1) - printk("#%d", class->name_version); + printk(KERN_CONT "#%d", class->name_version); if (class->subclass) - printk("/%d", class->subclass); + printk(KERN_CONT "/%d", class->subclass); } } @@ -522,9 +522,9 @@ static void print_lock_name(struct lock_class *class) get_usage_chars(class, usage); - printk(" ("); + printk(KERN_CONT " ("); __print_lock_name(class); - printk("){%s}", usage); + printk(KERN_CONT "){%s}", usage); } static void print_lockdep_cache(struct lockdep_map *lock) @@ -536,7 +536,7 @@ static void print_lockdep_cache(struct lockdep_map *lock) if (!name) name = __get_key_name(lock->key->subkeys, str); - printk("%s", name); + printk(KERN_CONT "%s", name); } static void print_lock(struct held_lock *hlock) @@ -551,13 +551,13 @@ static void print_lock(struct held_lock *hlock) barrier(); if (!class_idx || (class_idx - 1) >= MAX_LOCKDEP_KEYS) { - printk("<RELEASED>\n"); + printk(KERN_CONT "<RELEASED>\n"); return; } print_lock_name(lock_classes + class_idx - 1); - printk(", at: "); - print_ip_sym(hlock->acquire_ip); + printk(KERN_CONT ", at: [<%p>] %pS\n", + (void *)hlock->acquire_ip, (void *)hlock->acquire_ip); } static void lockdep_print_held_locks(struct task_struct *curr) @@ -792,8 +792,8 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) printk("\nnew class %p: %s", class->key, class->name); if (class->name_version > 1) - printk("#%d", class->name_version); - printk("\n"); + printk(KERN_CONT "#%d", class->name_version); + printk(KERN_CONT "\n"); dump_stack(); if (!graph_lock()) { @@ -1071,7 +1071,7 @@ print_circular_bug_entry(struct lock_list *target, int depth) return 0; printk("\n-> #%u", depth); print_lock_name(target->class); - printk(":\n"); + printk(KERN_CONT ":\n"); print_stack_trace(&target->trace, 6); return 0; @@ -1102,11 +1102,11 @@ print_circular_lock_scenario(struct held_lock *src, if (parent != source) { printk("Chain exists of:\n "); __print_lock_name(source); - printk(" --> "); + printk(KERN_CONT " --> "); __print_lock_name(parent); - printk(" --> "); + printk(KERN_CONT " --> "); __print_lock_name(target); - printk("\n\n"); + printk(KERN_CONT "\n\n"); } printk(" Possible unsafe locking scenario:\n\n"); @@ -1114,16 +1114,16 @@ print_circular_lock_scenario(struct held_lock *src, printk(" ---- ----\n"); printk(" lock("); __print_lock_name(target); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(parent); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(target); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(source); - printk(");\n"); + printk(KERN_CONT ");\n"); printk("\n *** DEADLOCK ***\n\n"); } @@ -1359,22 +1359,22 @@ static void print_lock_class_header(struct lock_class *class, int depth) printk("%*s->", depth, ""); print_lock_name(class); - printk(" ops: %lu", class->ops); - printk(" {\n"); + printk(KERN_CONT " ops: %lu", class->ops); + printk(KERN_CONT " {\n"); for (bit = 0; bit < LOCK_USAGE_STATES; bit++) { if (class->usage_mask & (1 << bit)) { int len = depth; len += printk("%*s %s", depth, "", usage_str[bit]); - len += printk(" at:\n"); + len += printk(KERN_CONT " at:\n"); print_stack_trace(class->usage_traces + bit, len); } } printk("%*s }\n", depth, ""); - printk("%*s ... key at: ",depth,""); - print_ip_sym((unsigned long)class->key); + printk("%*s ... key at: [<%p>] %pS\n", + depth, "", class->key, class->key); } /* @@ -1437,11 +1437,11 @@ print_irq_lock_scenario(struct lock_list *safe_entry, if (middle_class != unsafe_class) { printk("Chain exists of:\n "); __print_lock_name(safe_class); - printk(" --> "); + printk(KERN_CONT " --> "); __print_lock_name(middle_class); - printk(" --> "); + printk(KERN_CONT " --> "); __print_lock_name(unsafe_class); - printk("\n\n"); + printk(KERN_CONT "\n\n"); } printk(" Possible interrupt unsafe locking scenario:\n\n"); @@ -1449,18 +1449,18 @@ print_irq_lock_scenario(struct lock_list *safe_entry, printk(" ---- ----\n"); printk(" lock("); __print_lock_name(unsafe_class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" local_irq_disable();\n"); printk(" lock("); __print_lock_name(safe_class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(middle_class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" <Interrupt>\n"); printk(" lock("); __print_lock_name(safe_class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk("\n *** DEADLOCK ***\n\n"); } @@ -1497,9 +1497,9 @@ print_bad_irq_dependency(struct task_struct *curr, print_lock(prev); printk("which would create a new lock dependency:\n"); print_lock_name(hlock_class(prev)); - printk(" ->"); + printk(KERN_CONT " ->"); print_lock_name(hlock_class(next)); - printk("\n"); + printk(KERN_CONT "\n"); printk("\nbut this new dependency connects a %s-irq-safe lock:\n", irqclass); @@ -1521,8 +1521,7 @@ print_bad_irq_dependency(struct task_struct *curr, lockdep_print_held_locks(curr); - printk("\nthe dependencies between %s-irq-safe lock", irqclass); - printk(" and the holding lock:\n"); + printk("\nthe dependencies between %s-irq-safe lock and the holding lock:\n", irqclass); if (!save_trace(&prev_root->trace)) return 0; print_shortest_lock_dependencies(backwards_entry, prev_root); @@ -1694,10 +1693,10 @@ print_deadlock_scenario(struct held_lock *nxt, printk(" ----\n"); printk(" lock("); __print_lock_name(prev); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(next); - printk(");\n"); + printk(KERN_CONT ");\n"); printk("\n *** DEADLOCK ***\n\n"); printk(" May be due to missing lock nesting notation\n\n"); } @@ -1891,9 +1890,9 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, graph_unlock(); printk("\n new dependency: "); print_lock_name(hlock_class(prev)); - printk(" => "); + printk(KERN_CONT " => "); print_lock_name(hlock_class(next)); - printk("\n"); + printk(KERN_CONT "\n"); dump_stack(); return graph_lock(); } @@ -2343,11 +2342,11 @@ print_usage_bug_scenario(struct held_lock *lock) printk(" ----\n"); printk(" lock("); __print_lock_name(class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" <Interrupt>\n"); printk(" lock("); __print_lock_name(class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk("\n *** DEADLOCK ***\n\n"); } @@ -2522,14 +2521,18 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this, void print_irqtrace_events(struct task_struct *curr) { printk("irq event stamp: %u\n", curr->irq_events); - printk("hardirqs last enabled at (%u): ", curr->hardirq_enable_event); - print_ip_sym(curr->hardirq_enable_ip); - printk("hardirqs last disabled at (%u): ", curr->hardirq_disable_event); - print_ip_sym(curr->hardirq_disable_ip); - printk("softirqs last enabled at (%u): ", curr->softirq_enable_event); - print_ip_sym(curr->softirq_enable_ip); - printk("softirqs last disabled at (%u): ", curr->softirq_disable_event); - print_ip_sym(curr->softirq_disable_ip); + printk("hardirqs last enabled at (%u): [<%p>] %pS\n", + curr->hardirq_enable_event, (void *)curr->hardirq_enable_ip, + (void *)curr->hardirq_enable_ip); + printk("hardirqs last disabled at (%u): [<%p>] %pS\n", + curr->hardirq_disable_event, (void *)curr->hardirq_disable_ip, + (void *)curr->hardirq_disable_ip); + printk("softirqs last enabled at (%u): [<%p>] %pS\n", + curr->softirq_enable_event, (void *)curr->softirq_enable_ip, + (void *)curr->softirq_enable_ip); + printk("softirqs last disabled at (%u): [<%p>] %pS\n", + curr->softirq_disable_event, (void *)curr->softirq_disable_ip, + (void *)curr->softirq_disable_ip); } static int HARDIRQ_verbose(struct lock_class *class) @@ -3235,8 +3238,8 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (very_verbose(class)) { printk("\nacquire class [%p] %s", class->key, class->name); if (class->name_version > 1) - printk("#%d", class->name_version); - printk("\n"); + printk(KERN_CONT "#%d", class->name_version); + printk(KERN_CONT "\n"); dump_stack(); } @@ -3378,7 +3381,7 @@ print_unlock_imbalance_bug(struct task_struct *curr, struct lockdep_map *lock, printk("%s/%d is trying to release lock (", curr->comm, task_pid_nr(curr)); print_lockdep_cache(lock); - printk(") at:\n"); + printk(KERN_CONT ") at:\n"); print_ip_sym(ip); printk("but there are no more locks to release!\n"); printk("\nother info that might help us debug this:\n"); @@ -3871,7 +3874,7 @@ print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock, printk("%s/%d is trying to contend lock (", curr->comm, task_pid_nr(curr)); print_lockdep_cache(lock); - printk(") at:\n"); + printk(KERN_CONT ") at:\n"); print_ip_sym(ip); printk("but there are no locks held!\n"); printk("\nother info that might help us debug this:\n"); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 1ec0f48962b3..2c49d76f96c3 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -65,8 +65,72 @@ static inline void clear_rt_mutex_waiters(struct rt_mutex *lock) static void fixup_rt_mutex_waiters(struct rt_mutex *lock) { - if (!rt_mutex_has_waiters(lock)) - clear_rt_mutex_waiters(lock); + unsigned long owner, *p = (unsigned long *) &lock->owner; + + if (rt_mutex_has_waiters(lock)) + return; + + /* + * The rbtree has no waiters enqueued, now make sure that the + * lock->owner still has the waiters bit set, otherwise the + * following can happen: + * + * CPU 0 CPU 1 CPU2 + * l->owner=T1 + * rt_mutex_lock(l) + * lock(l->lock) + * l->owner = T1 | HAS_WAITERS; + * enqueue(T2) + * boost() + * unlock(l->lock) + * block() + * + * rt_mutex_lock(l) + * lock(l->lock) + * l->owner = T1 | HAS_WAITERS; + * enqueue(T3) + * boost() + * unlock(l->lock) + * block() + * signal(->T2) signal(->T3) + * lock(l->lock) + * dequeue(T2) + * deboost() + * unlock(l->lock) + * lock(l->lock) + * dequeue(T3) + * ==> wait list is empty + * deboost() + * unlock(l->lock) + * lock(l->lock) + * fixup_rt_mutex_waiters() + * if (wait_list_empty(l) { + * l->owner = owner + * owner = l->owner & ~HAS_WAITERS; + * ==> l->owner = T1 + * } + * lock(l->lock) + * rt_mutex_unlock(l) fixup_rt_mutex_waiters() + * if (wait_list_empty(l) { + * owner = l->owner & ~HAS_WAITERS; + * cmpxchg(l->owner, T1, NULL) + * ===> Success (l->owner = NULL) + * + * l->owner = owner + * ==> l->owner = T1 + * } + * + * With the check for the waiter bit in place T3 on CPU2 will not + * overwrite. All tasks fiddling with the waiters bit are + * serialized by l->lock, so nothing else can modify the waiters + * bit. If the bit is set then nothing can change l->owner either + * so the simple RMW is safe. The cmpxchg() will simply fail if it + * happens in the middle of the RMW because the waiters bit is + * still set. + */ + owner = READ_ONCE(*p); + if (owner & RT_MUTEX_HAS_WAITERS) + WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); } /* diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index 4f5f83c7d2d3..e317e1cbb3eb 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -75,8 +75,9 @@ task_top_pi_waiter(struct task_struct *p) static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) { - return (struct task_struct *) - ((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL); + unsigned long owner = (unsigned long) READ_ONCE(lock->owner); + + return (struct task_struct *) (owner & ~RT_MUTEX_OWNER_MASKALL); } /* diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c index f1c8fd566246..da39489d2d80 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/auto_group.c @@ -212,6 +212,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) { static unsigned long next = INITIAL_JIFFIES; struct autogroup *ag; + unsigned long shares; int err; if (nice < MIN_NICE || nice > MAX_NICE) @@ -230,9 +231,10 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) next = HZ / 10 + jiffies; ag = autogroup_task_get(p); + shares = scale_load(sched_prio_to_weight[nice + 20]); down_write(&ag->lock); - err = sched_group_set_shares(ag->tg, sched_prio_to_weight[nice + 20]); + err = sched_group_set_shares(ag->tg, shares); if (!err) ag->nice = nice; up_write(&ag->lock); diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 69e06898997d..fd4659313640 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -12,11 +12,14 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/cpufreq.h> +#include <linux/kthread.h> #include <linux/slab.h> #include <trace/events/power.h> #include "sched.h" +#define SUGOV_KTHREAD_PRIORITY 50 + struct sugov_tunables { struct gov_attr_set attr_set; unsigned int rate_limit_us; @@ -35,8 +38,10 @@ struct sugov_policy { /* The next fields are only needed if fast switch cannot be used. */ struct irq_work irq_work; - struct work_struct work; + struct kthread_work work; struct mutex work_lock; + struct kthread_worker worker; + struct task_struct *thread; bool work_in_progress; bool need_freq_update; @@ -291,7 +296,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, raw_spin_unlock(&sg_policy->update_lock); } -static void sugov_work(struct work_struct *work) +static void sugov_work(struct kthread_work *work) { struct sugov_policy *sg_policy = container_of(work, struct sugov_policy, work); @@ -308,7 +313,21 @@ static void sugov_irq_work(struct irq_work *irq_work) struct sugov_policy *sg_policy; sg_policy = container_of(irq_work, struct sugov_policy, irq_work); - schedule_work_on(smp_processor_id(), &sg_policy->work); + + /* + * For RT and deadline tasks, the schedutil governor shoots the + * frequency to maximum. Special care must be taken to ensure that this + * kthread doesn't result in the same behavior. + * + * This is (mostly) guaranteed by the work_in_progress flag. The flag is + * updated only at the end of the sugov_work() function and before that + * the schedutil governor rejects all other frequency scaling requests. + * + * There is a very rare case though, where the RT thread yields right + * after the work_in_progress flag is cleared. The effects of that are + * neglected for now. + */ + kthread_queue_work(&sg_policy->worker, &sg_policy->work); } /************************** sysfs interface ************************/ @@ -371,19 +390,64 @@ static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy) return NULL; sg_policy->policy = policy; - init_irq_work(&sg_policy->irq_work, sugov_irq_work); - INIT_WORK(&sg_policy->work, sugov_work); - mutex_init(&sg_policy->work_lock); raw_spin_lock_init(&sg_policy->update_lock); return sg_policy; } static void sugov_policy_free(struct sugov_policy *sg_policy) { - mutex_destroy(&sg_policy->work_lock); kfree(sg_policy); } +static int sugov_kthread_create(struct sugov_policy *sg_policy) +{ + struct task_struct *thread; + struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 }; + struct cpufreq_policy *policy = sg_policy->policy; + int ret; + + /* kthread only required for slow path */ + if (policy->fast_switch_enabled) + return 0; + + kthread_init_work(&sg_policy->work, sugov_work); + kthread_init_worker(&sg_policy->worker); + thread = kthread_create(kthread_worker_fn, &sg_policy->worker, + "sugov:%d", + cpumask_first(policy->related_cpus)); + if (IS_ERR(thread)) { + pr_err("failed to create sugov thread: %ld\n", PTR_ERR(thread)); + return PTR_ERR(thread); + } + + ret = sched_setscheduler_nocheck(thread, SCHED_FIFO, ¶m); + if (ret) { + kthread_stop(thread); + pr_warn("%s: failed to set SCHED_FIFO\n", __func__); + return ret; + } + + sg_policy->thread = thread; + kthread_bind_mask(thread, policy->related_cpus); + init_irq_work(&sg_policy->irq_work, sugov_irq_work); + mutex_init(&sg_policy->work_lock); + + wake_up_process(thread); + + return 0; +} + +static void sugov_kthread_stop(struct sugov_policy *sg_policy) +{ + /* kthread only required for slow path */ + if (sg_policy->policy->fast_switch_enabled) + return; + + kthread_flush_worker(&sg_policy->worker); + kthread_stop(sg_policy->thread); + mutex_destroy(&sg_policy->work_lock); +} + static struct sugov_tunables *sugov_tunables_alloc(struct sugov_policy *sg_policy) { struct sugov_tunables *tunables; @@ -416,16 +480,24 @@ static int sugov_init(struct cpufreq_policy *policy) if (policy->governor_data) return -EBUSY; + cpufreq_enable_fast_switch(policy); + sg_policy = sugov_policy_alloc(policy); - if (!sg_policy) - return -ENOMEM; + if (!sg_policy) { + ret = -ENOMEM; + goto disable_fast_switch; + } + + ret = sugov_kthread_create(sg_policy); + if (ret) + goto free_sg_policy; mutex_lock(&global_tunables_lock); if (global_tunables) { if (WARN_ON(have_governor_per_policy())) { ret = -EINVAL; - goto free_sg_policy; + goto stop_kthread; } policy->governor_data = sg_policy; sg_policy->tunables = global_tunables; @@ -437,7 +509,7 @@ static int sugov_init(struct cpufreq_policy *policy) tunables = sugov_tunables_alloc(sg_policy); if (!tunables) { ret = -ENOMEM; - goto free_sg_policy; + goto stop_kthread; } tunables->rate_limit_us = LATENCY_MULTIPLIER; @@ -454,20 +526,25 @@ static int sugov_init(struct cpufreq_policy *policy) if (ret) goto fail; - out: +out: mutex_unlock(&global_tunables_lock); - - cpufreq_enable_fast_switch(policy); return 0; - fail: +fail: policy->governor_data = NULL; sugov_tunables_free(tunables); - free_sg_policy: +stop_kthread: + sugov_kthread_stop(sg_policy); + +free_sg_policy: mutex_unlock(&global_tunables_lock); sugov_policy_free(sg_policy); + +disable_fast_switch: + cpufreq_disable_fast_switch(policy); + pr_err("initialization failed (error %d)\n", ret); return ret; } @@ -478,8 +555,6 @@ static void sugov_exit(struct cpufreq_policy *policy) struct sugov_tunables *tunables = sg_policy->tunables; unsigned int count; - cpufreq_disable_fast_switch(policy); - mutex_lock(&global_tunables_lock); count = gov_attr_set_put(&tunables->attr_set, &sg_policy->tunables_hook); @@ -489,7 +564,9 @@ static void sugov_exit(struct cpufreq_policy *policy) mutex_unlock(&global_tunables_lock); + sugov_kthread_stop(sg_policy); sugov_policy_free(sg_policy); + cpufreq_disable_fast_switch(policy); } static int sugov_start(struct cpufreq_policy *policy) @@ -535,8 +612,10 @@ static void sugov_stop(struct cpufreq_policy *policy) synchronize_sched(); - irq_work_sync(&sg_policy->irq_work); - cancel_work_sync(&sg_policy->work); + if (!policy->fast_switch_enabled) { + irq_work_sync(&sg_policy->irq_work); + kthread_cancel_work_sync(&sg_policy->work); + } } static void sugov_limits(struct cpufreq_policy *policy) diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index 872a15a2a637..f3a217ea0388 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -980,23 +980,23 @@ static void dotest(void (*testcase_fn)(void), int expected, int lockclass_mask) #ifndef CONFIG_PROVE_LOCKING if (expected == FAILURE && debug_locks) { expected_testcase_failures++; - printk("failed|"); + pr_cont("failed|"); } else #endif if (debug_locks != expected) { unexpected_testcase_failures++; - printk("FAILED|"); + pr_cont("FAILED|"); dump_stack(); } else { testcase_successes++; - printk(" ok |"); + pr_cont(" ok |"); } testcase_total++; if (debug_locks_verbose) - printk(" lockclass mask: %x, debug_locks: %d, expected: %d\n", + pr_cont(" lockclass mask: %x, debug_locks: %d, expected: %d\n", lockclass_mask, debug_locks, expected); /* * Some tests (e.g. double-unlock) might corrupt the preemption @@ -1021,26 +1021,26 @@ static inline void print_testname(const char *testname) #define DO_TESTCASE_1(desc, name, nr) \ print_testname(desc"/"#nr); \ dotest(name##_##nr, SUCCESS, LOCKTYPE_RWLOCK); \ - printk("\n"); + pr_cont("\n"); #define DO_TESTCASE_1B(desc, name, nr) \ print_testname(desc"/"#nr); \ dotest(name##_##nr, FAILURE, LOCKTYPE_RWLOCK); \ - printk("\n"); + pr_cont("\n"); #define DO_TESTCASE_3(desc, name, nr) \ print_testname(desc"/"#nr); \ dotest(name##_spin_##nr, FAILURE, LOCKTYPE_SPIN); \ dotest(name##_wlock_##nr, FAILURE, LOCKTYPE_RWLOCK); \ dotest(name##_rlock_##nr, SUCCESS, LOCKTYPE_RWLOCK); \ - printk("\n"); + pr_cont("\n"); #define DO_TESTCASE_3RW(desc, name, nr) \ print_testname(desc"/"#nr); \ dotest(name##_spin_##nr, FAILURE, LOCKTYPE_SPIN|LOCKTYPE_RWLOCK);\ dotest(name##_wlock_##nr, FAILURE, LOCKTYPE_RWLOCK); \ dotest(name##_rlock_##nr, SUCCESS, LOCKTYPE_RWLOCK); \ - printk("\n"); + pr_cont("\n"); #define DO_TESTCASE_6(desc, name) \ print_testname(desc); \ @@ -1050,7 +1050,7 @@ static inline void print_testname(const char *testname) dotest(name##_mutex, FAILURE, LOCKTYPE_MUTEX); \ dotest(name##_wsem, FAILURE, LOCKTYPE_RWSEM); \ dotest(name##_rsem, FAILURE, LOCKTYPE_RWSEM); \ - printk("\n"); + pr_cont("\n"); #define DO_TESTCASE_6_SUCCESS(desc, name) \ print_testname(desc); \ @@ -1060,7 +1060,7 @@ static inline void print_testname(const char *testname) dotest(name##_mutex, SUCCESS, LOCKTYPE_MUTEX); \ dotest(name##_wsem, SUCCESS, LOCKTYPE_RWSEM); \ dotest(name##_rsem, SUCCESS, LOCKTYPE_RWSEM); \ - printk("\n"); + pr_cont("\n"); /* * 'read' variant: rlocks must not trigger. @@ -1073,7 +1073,7 @@ static inline void print_testname(const char *testname) dotest(name##_mutex, FAILURE, LOCKTYPE_MUTEX); \ dotest(name##_wsem, FAILURE, LOCKTYPE_RWSEM); \ dotest(name##_rsem, FAILURE, LOCKTYPE_RWSEM); \ - printk("\n"); + pr_cont("\n"); #define DO_TESTCASE_2I(desc, name, nr) \ DO_TESTCASE_1("hard-"desc, name##_hard, nr); \ @@ -1726,25 +1726,25 @@ static void ww_tests(void) dotest(ww_test_fail_acquire, SUCCESS, LOCKTYPE_WW); dotest(ww_test_normal, SUCCESS, LOCKTYPE_WW); dotest(ww_test_unneeded_slow, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("ww contexts mixing"); dotest(ww_test_two_contexts, FAILURE, LOCKTYPE_WW); dotest(ww_test_diff_class, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("finishing ww context"); dotest(ww_test_context_done_twice, FAILURE, LOCKTYPE_WW); dotest(ww_test_context_unlock_twice, FAILURE, LOCKTYPE_WW); dotest(ww_test_context_fini_early, FAILURE, LOCKTYPE_WW); dotest(ww_test_context_lock_after_done, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("locking mismatches"); dotest(ww_test_object_unlock_twice, FAILURE, LOCKTYPE_WW); dotest(ww_test_object_lock_unbalanced, FAILURE, LOCKTYPE_WW); dotest(ww_test_object_lock_stale_context, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("EDEADLK handling"); dotest(ww_test_edeadlk_normal, SUCCESS, LOCKTYPE_WW); @@ -1757,11 +1757,11 @@ static void ww_tests(void) dotest(ww_test_edeadlk_acquire_more_edeadlk_slow, FAILURE, LOCKTYPE_WW); dotest(ww_test_edeadlk_acquire_wrong, FAILURE, LOCKTYPE_WW); dotest(ww_test_edeadlk_acquire_wrong_slow, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("spinlock nest unlocked"); dotest(ww_test_spin_nest_unlocked, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); printk(" -----------------------------------------------------\n"); printk(" |block | try |context|\n"); @@ -1771,25 +1771,25 @@ static void ww_tests(void) dotest(ww_test_context_block, FAILURE, LOCKTYPE_WW); dotest(ww_test_context_try, SUCCESS, LOCKTYPE_WW); dotest(ww_test_context_context, SUCCESS, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("try"); dotest(ww_test_try_block, FAILURE, LOCKTYPE_WW); dotest(ww_test_try_try, SUCCESS, LOCKTYPE_WW); dotest(ww_test_try_context, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("block"); dotest(ww_test_block_block, FAILURE, LOCKTYPE_WW); dotest(ww_test_block_try, SUCCESS, LOCKTYPE_WW); dotest(ww_test_block_context, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); print_testname("spinlock"); dotest(ww_test_spin_block, FAILURE, LOCKTYPE_WW); dotest(ww_test_spin_try, SUCCESS, LOCKTYPE_WW); dotest(ww_test_spin_context, FAILURE, LOCKTYPE_WW); - printk("\n"); + pr_cont("\n"); } void locking_selftest(void) @@ -1829,32 +1829,32 @@ void locking_selftest(void) printk(" --------------------------------------------------------------------------\n"); print_testname("recursive read-lock"); - printk(" |"); + pr_cont(" |"); dotest(rlock_AA1, SUCCESS, LOCKTYPE_RWLOCK); - printk(" |"); + pr_cont(" |"); dotest(rsem_AA1, FAILURE, LOCKTYPE_RWSEM); - printk("\n"); + pr_cont("\n"); print_testname("recursive read-lock #2"); - printk(" |"); + pr_cont(" |"); dotest(rlock_AA1B, SUCCESS, LOCKTYPE_RWLOCK); - printk(" |"); + pr_cont(" |"); dotest(rsem_AA1B, FAILURE, LOCKTYPE_RWSEM); - printk("\n"); + pr_cont("\n"); print_testname("mixed read-write-lock"); - printk(" |"); + pr_cont(" |"); dotest(rlock_AA2, FAILURE, LOCKTYPE_RWLOCK); - printk(" |"); + pr_cont(" |"); dotest(rsem_AA2, FAILURE, LOCKTYPE_RWSEM); - printk("\n"); + pr_cont("\n"); print_testname("mixed write-read-lock"); - printk(" |"); + pr_cont(" |"); dotest(rlock_AA3, FAILURE, LOCKTYPE_RWLOCK); - printk(" |"); + pr_cont(" |"); dotest(rsem_AA3, FAILURE, LOCKTYPE_RWSEM); - printk("\n"); + pr_cont("\n"); printk(" --------------------------------------------------------------------------\n"); diff --git a/mm/shmem.c b/mm/shmem.c index 166ebf5d2bce..9d32e1cb9f38 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1848,6 +1848,18 @@ unlock: return error; } +/* + * This is like autoremove_wake_function, but it removes the wait queue + * entry unconditionally - even if something else had already woken the + * target. + */ +static int synchronous_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) +{ + int ret = default_wake_function(wait, mode, sync, key); + list_del_init(&wait->task_list); + return ret; +} + static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct inode *inode = file_inode(vma->vm_file); @@ -1883,7 +1895,7 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) vmf->pgoff >= shmem_falloc->start && vmf->pgoff < shmem_falloc->next) { wait_queue_head_t *shmem_falloc_waitq; - DEFINE_WAIT(shmem_fault_wait); + DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function); ret = VM_FAULT_NOPAGE; if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) && @@ -2665,6 +2677,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, spin_lock(&inode->i_lock); inode->i_private = NULL; wake_up_all(&shmem_falloc_waitq); + WARN_ON_ONCE(!list_empty(&shmem_falloc_waitq.task_list)); spin_unlock(&inode->i_lock); error = 0; goto out; diff --git a/mm/vmscan.c b/mm/vmscan.c index 76fda2268148..d75cdf360730 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2354,6 +2354,8 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc } } + cond_resched(); + if (nr_reclaimed < nr_to_reclaim || scan_adjusted) continue; diff --git a/mm/workingset.c b/mm/workingset.c index 617475f529f4..fb1f9183d89a 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -348,7 +348,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc); local_irq_enable(); - if (memcg_kmem_enabled()) { + if (sc->memcg) { pages = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid, LRU_ALL_FILE); } else { diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 7f663092f6de..0dc85eb1cb7a 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -3282,7 +3282,7 @@ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv, &tvlv_tt_data, &tt_change, &tt_len); - if (!tt_len) + if (!tt_len || !tvlv_len) goto unlock; /* Copy the last orig_node's OGM buffer */ @@ -3300,7 +3300,7 @@ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv, &tvlv_tt_data, &tt_change, &tt_len); - if (!tt_len) + if (!tt_len || !tvlv_len) goto out; /* fill the rest of the tvlv with the real TT entries */ diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index e120307c6e36..f88c4df3f91e 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -898,6 +898,7 @@ int br_sysfs_addbr(struct net_device *dev) if (!br->ifobj) { pr_info("%s: can't add kobject (directory) %s/%s\n", __func__, dev->name, SYSFS_BRIDGE_PORT_SUBDIR); + err = -ENOMEM; goto out3; } return 0; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index aa209b1066c9..92cbbd2afddb 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -1107,10 +1107,7 @@ static struct net_proto_family caif_family_ops = { static int __init caif_sktinit_module(void) { - int err = sock_register(&caif_family_ops); - if (!err) - return err; - return 0; + return sock_register(&caif_family_ops); } static void __exit caif_sktexit_module(void) diff --git a/net/can/raw.c b/net/can/raw.c index 972c187d40ab..b075f028d7e2 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -499,6 +499,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, if (optlen % sizeof(struct can_filter) != 0) return -EINVAL; + if (optlen > CAN_RAW_FILTER_MAX * sizeof(struct can_filter)) + return -EINVAL; + count = optlen / sizeof(struct can_filter); if (count > 1) { diff --git a/net/core/flow.c b/net/core/flow.c index 3937b1b68d5b..18e8893d4be5 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -95,7 +95,6 @@ static void flow_cache_gc_task(struct work_struct *work) list_for_each_entry_safe(fce, n, &gc_list, u.gc_list) { flow_entry_kill(fce, xfrm); atomic_dec(&xfrm->flow_cache_gc_count); - WARN_ON(atomic_read(&xfrm->flow_cache_gc_count) < 0); } } @@ -236,9 +235,8 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, if (fcp->hash_count > fc->high_watermark) flow_cache_shrink(fc, fcp); - if (fcp->hash_count > 2 * fc->high_watermark || - atomic_read(&net->xfrm.flow_cache_gc_count) > fc->high_watermark) { - atomic_inc(&net->xfrm.flow_cache_genid); + if (atomic_read(&net->xfrm.flow_cache_gc_count) > + 2 * num_online_cpus() * fc->high_watermark) { flo = ERR_PTR(-ENOBUFS); goto ret_object; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index deb35acbefd0..a6196cf844f6 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -931,8 +931,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_PROMISCUITY */ + nla_total_size(4) /* IFLA_NUM_TX_QUEUES */ + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */ - + nla_total_size(4) /* IFLA_MAX_GSO_SEGS */ - + nla_total_size(4) /* IFLA_MAX_GSO_SIZE */ + + nla_total_size(4) /* IFLA_GSO_MAX_SEGS */ + + nla_total_size(4) /* IFLA_GSO_MAX_SIZE */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(4) /* IFLA_CARRIER_CHANGES */ diff --git a/net/core/sock.c b/net/core/sock.c index 5e3ca414357e..00a074dbfe9b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -715,7 +715,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, val = min_t(u32, val, sysctl_wmem_max); set_sndbuf: sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF); + sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; @@ -751,7 +751,7 @@ set_rcvbuf: * returning the value we actually used in getsockopt * is the most desirable behavior. */ - sk->sk_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF); + sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); break; case SO_RCVBUFFORCE: diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 4f6c1862dfd2..3202d75329b5 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1353,6 +1353,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) dcb_unlock: spin_unlock_bh(&dcb_lock); nla_put_failure: + err = -EMSGSIZE; return err; } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b567c8725aea..edbe59d203ef 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -700,6 +700,7 @@ int dccp_invalid_packet(struct sk_buff *skb) { const struct dccp_hdr *dh; unsigned int cscov; + u8 dccph_doff; if (skb->pkt_type != PACKET_HOST) return 1; @@ -721,18 +722,19 @@ int dccp_invalid_packet(struct sk_buff *skb) /* * If P.Data Offset is too small for packet type, drop packet and return */ - if (dh->dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) { - DCCP_WARN("P.Data Offset(%u) too small\n", dh->dccph_doff); + dccph_doff = dh->dccph_doff; + if (dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) { + DCCP_WARN("P.Data Offset(%u) too small\n", dccph_doff); return 1; } /* * If P.Data Offset is too too large for packet, drop packet and return */ - if (!pskb_may_pull(skb, dh->dccph_doff * sizeof(u32))) { - DCCP_WARN("P.Data Offset(%u) too large\n", dh->dccph_doff); + if (!pskb_may_pull(skb, dccph_doff * sizeof(u32))) { + DCCP_WARN("P.Data Offset(%u) too large\n", dccph_doff); return 1; } - + dh = dccp_hdr(skb); /* * If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet * has short sequence numbers), drop packet and return diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index a6902c1e2f28..7899919cd9f0 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -233,6 +233,8 @@ int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev, genphy_read_status(phydev); if (ds->ops->adjust_link) ds->ops->adjust_link(ds, port, phydev); + + put_device(&phydev->mdio.dev); } return 0; @@ -504,15 +506,8 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, void dsa_cpu_dsa_destroy(struct device_node *port_dn) { - struct phy_device *phydev; - - if (of_phy_is_fixed_link(port_dn)) { - phydev = of_phy_find_device(port_dn); - if (phydev) { - phy_device_free(phydev); - fixed_phy_unregister(phydev); - } - } + if (of_phy_is_fixed_link(port_dn)) + of_phy_deregister_fixed_link(port_dn); } static void dsa_switch_destroy(struct dsa_switch *ds) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index f8a7d9aab437..5fff951a0a49 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -28,8 +28,10 @@ static struct dsa_switch_tree *dsa_get_dst(u32 tree) struct dsa_switch_tree *dst; list_for_each_entry(dst, &dsa_switch_trees, list) - if (dst->tree == tree) + if (dst->tree == tree) { + kref_get(&dst->refcount); return dst; + } return NULL; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 6b1282c006b1..30e2e21d7619 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1125,7 +1125,7 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, p->phy_interface = mode; phy_dn = of_parse_phandle(port_dn, "phy-handle", 0); - if (of_phy_is_fixed_link(port_dn)) { + if (!phy_dn && of_phy_is_fixed_link(port_dn)) { /* In the case of a fixed PHY, the DT node associated * to the fixed PHY is the Port DT node */ @@ -1135,7 +1135,7 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, return ret; } phy_is_fixed = true; - phy_dn = port_dn; + phy_dn = of_node_get(port_dn); } if (ds->ops->get_phy_flags) @@ -1154,6 +1154,7 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, ret = dsa_slave_phy_connect(p, slave_dev, phy_id); if (ret) { netdev_err(slave_dev, "failed to connect to phy%d: %d\n", phy_id, ret); + of_node_put(phy_dn); return ret; } } else { @@ -1162,6 +1163,8 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, phy_flags, p->phy_interface); } + + of_node_put(phy_dn); } if (p->phy && phy_is_fixed) @@ -1174,6 +1177,8 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, ret = dsa_slave_phy_connect(p, slave_dev, p->port); if (ret) { netdev_err(slave_dev, "failed to connect to port %d: %d\n", p->port, ret); + if (phy_is_fixed) + of_phy_deregister_fixed_link(port_dn); return ret; } } @@ -1289,10 +1294,18 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, void dsa_slave_destroy(struct net_device *slave_dev) { struct dsa_slave_priv *p = netdev_priv(slave_dev); + struct dsa_switch *ds = p->parent; + struct device_node *port_dn; + + port_dn = ds->ports[p->port].dn; netif_carrier_off(slave_dev); - if (p->phy) + if (p->phy) { phy_disconnect(p->phy); + + if (of_phy_is_fixed_link(port_dn)) + of_phy_deregister_fixed_link(port_dn); + } unregister_netdev(slave_dev); free_netdev(slave_dev); } diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 300b06888fdf..b54b3ca939db 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -715,6 +715,7 @@ config DEFAULT_TCP_CONG default "reno" if DEFAULT_RENO default "dctcp" if DEFAULT_DCTCP default "cdg" if DEFAULT_CDG + default "bbr" if DEFAULT_BBR default "cubic" config TCP_MD5SIG diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5ddf5cda07f4..215143246e4b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1233,7 +1233,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID); /* fixed ID is invalid if DF bit is not set */ - if (fixedid && !(iph->frag_off & htons(IP_DF))) + if (fixedid && !(ip_hdr(skb)->frag_off & htons(IP_DF))) goto out; } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index d95631d09248..20fb25e3027b 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -476,7 +476,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb) esph = (void *)skb_push(skb, 4); *seqhi = esph->spi; esph->spi = esph->seq_no; - esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi); + esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; aead_request_set_callback(req, 0, esp_input_done_esn, skb); } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 026f309c51e9..e3665bf7a7f3 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -719,6 +719,13 @@ static unsigned char update_suffix(struct key_vector *tn) { unsigned char slen = tn->pos; unsigned long stride, i; + unsigned char slen_max; + + /* only vector 0 can have a suffix length greater than or equal to + * tn->pos + tn->bits, the second highest node will have a suffix + * length at most of tn->pos + tn->bits - 1 + */ + slen_max = min_t(unsigned char, tn->pos + tn->bits - 1, tn->slen); /* search though the list of children looking for nodes that might * have a suffix greater than the one we currently have. This is @@ -736,12 +743,8 @@ static unsigned char update_suffix(struct key_vector *tn) slen = n->slen; i &= ~(stride - 1); - /* if slen covers all but the last bit we can stop here - * there will be nothing longer than that since only node - * 0 and 1 << (bits - 1) could have that as their suffix - * length. - */ - if ((slen + 1) >= (tn->pos + tn->bits)) + /* stop searching if we have hit the maximum possible value */ + if (slen >= slen_max) break; } @@ -913,39 +916,27 @@ static struct key_vector *resize(struct trie *t, struct key_vector *tn) return collapse(t, tn); /* update parent in case halve failed */ - tp = node_parent(tn); - - /* Return if at least one deflate was run */ - if (max_work != MAX_WORK) - return tp; - - /* push the suffix length to the parent node */ - if (tn->slen > tn->pos) { - unsigned char slen = update_suffix(tn); - - if (slen > tp->slen) - tp->slen = slen; - } - - return tp; + return node_parent(tn); } -static void leaf_pull_suffix(struct key_vector *tp, struct key_vector *l) +static void node_pull_suffix(struct key_vector *tn, unsigned char slen) { - while ((tp->slen > tp->pos) && (tp->slen > l->slen)) { - if (update_suffix(tp) > l->slen) + unsigned char node_slen = tn->slen; + + while ((node_slen > tn->pos) && (node_slen > slen)) { + slen = update_suffix(tn); + if (node_slen == slen) break; - tp = node_parent(tp); + + tn = node_parent(tn); + node_slen = tn->slen; } } -static void leaf_push_suffix(struct key_vector *tn, struct key_vector *l) +static void node_push_suffix(struct key_vector *tn, unsigned char slen) { - /* if this is a new leaf then tn will be NULL and we can sort - * out parent suffix lengths as a part of trie_rebalance - */ - while (tn->slen < l->slen) { - tn->slen = l->slen; + while (tn->slen < slen) { + tn->slen = slen; tn = node_parent(tn); } } @@ -1066,6 +1057,7 @@ static int fib_insert_node(struct trie *t, struct key_vector *tp, } /* Case 3: n is NULL, and will just insert a new leaf */ + node_push_suffix(tp, new->fa_slen); NODE_INIT_PARENT(l, tp); put_child_root(tp, key, l); trie_rebalance(t, tp); @@ -1107,7 +1099,7 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp, /* if we added to the tail node then we need to update slen */ if (l->slen < new->fa_slen) { l->slen = new->fa_slen; - leaf_push_suffix(tp, l); + node_push_suffix(tp, new->fa_slen); } return 0; @@ -1499,6 +1491,8 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp, * out parent suffix lengths as a part of trie_rebalance */ if (hlist_empty(&l->leaf)) { + if (tp->slen == l->slen) + node_pull_suffix(tp, tp->pos); put_child_root(tp, l->key, NULL); node_free(l); trie_rebalance(t, tp); @@ -1511,7 +1505,7 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp, /* update the trie with the latest suffix length */ l->slen = fa->fa_slen; - leaf_pull_suffix(tp, l); + node_pull_suffix(tp, fa->fa_slen); } /* Caller must hold RTNL. */ @@ -1783,6 +1777,10 @@ void fib_table_flush_external(struct fib_table *tb) if (IS_TRIE(pn)) break; + /* update the suffix to address pulled leaves */ + if (pn->slen > pn->pos) + update_suffix(pn); + /* resize completed node */ pn = resize(t, pn); cindex = get_index(pkey, pn); @@ -1849,6 +1847,10 @@ int fib_table_flush(struct net *net, struct fib_table *tb) if (IS_TRIE(pn)) break; + /* update the suffix to address pulled leaves */ + if (pn->slen > pn->pos) + update_suffix(pn); + /* resize completed node */ pn = resize(t, pn); cindex = get_index(pkey, pn); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 105908d841a3..877bdb02e887 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -107,6 +107,8 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) if (unlikely(!skb)) return 0; + skb->protocol = htons(ETH_P_IP); + return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index c3776ff6749f..b3cc1335adbc 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -24,10 +24,11 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t struct flowi4 fl4 = {}; __be32 saddr = iph->saddr; __u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0; + struct net_device *dev = skb_dst(skb)->dev; unsigned int hh_len; if (addr_type == RTN_UNSPEC) - addr_type = inet_addr_type(net, saddr); + addr_type = inet_addr_type_dev_table(net, dev, saddr); if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) flags |= FLOWI_FLAG_ANYSRC; else @@ -40,6 +41,8 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t fl4.saddr = saddr; fl4.flowi4_tos = RT_TOS(iph->tos); fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; + if (!fl4.flowi4_oif) + fl4.flowi4_oif = l3mdev_master_ifindex(dev); fl4.flowi4_mark = skb->mark; fl4.flowi4_flags = flags; rt = ip_route_output_key(net, &fl4); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index b31df597fd37..697538464e6e 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1201,8 +1201,8 @@ static int translate_compat_table(struct xt_table_info **pinfo, newinfo->number = compatr->num_entries; for (i = 0; i < NF_ARP_NUMHOOKS; i++) { - newinfo->hook_entry[i] = info->hook_entry[i]; - newinfo->underflow[i] = info->underflow[i]; + newinfo->hook_entry[i] = compatr->hook_entry[i]; + newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 205e2000d395..96b8e2b95731 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -657,6 +657,10 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, if (len > 0xFFFF) return -EMSGSIZE; + /* Must have at least a full ICMP header. */ + if (len < icmph_len) + return -EINVAL; + /* * Check the flags. */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a27b9c0e27c0..c71d49ce0c93 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -128,6 +128,23 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define REXMIT_LOST 1 /* retransmit packets marked lost */ #define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */ +static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb) +{ + static bool __once __read_mostly; + + if (!__once) { + struct net_device *dev; + + __once = true; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); + pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n", + dev ? dev->name : "Unknown driver"); + rcu_read_unlock(); + } +} + /* Adapt the MSS value used to make delayed ack decision to the * real world. */ @@ -144,7 +161,10 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) */ len = skb_shinfo(skb)->gso_size ? : skb->len; if (len >= icsk->icsk_ack.rcv_mss) { - icsk->icsk_ack.rcv_mss = len; + icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, + tcp_sk(sk)->advmss); + if (unlikely(icsk->icsk_ack.rcv_mss != len)) + tcp_gro_dev_warn(sk, skb); } else { /* Otherwise, we make more careful check taking into account, * that SACKs block is variable. diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 37874e2f30ed..ccf40550c475 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -139,7 +139,8 @@ void ip6_datagram_release_cb(struct sock *sk) } EXPORT_SYMBOL_GPL(ip6_datagram_release_cb); -static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, + int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); @@ -252,6 +253,7 @@ ipv4_connected: out: return err; } +EXPORT_SYMBOL_GPL(__ip6_datagram_connect); int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 060a60b2f8a6..111ba55fd512 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -418,7 +418,7 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) esph = (void *)skb_push(skb, 4); *seqhi = esph->spi; esph->spi = esph->seq_no; - esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi); + esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; aead_request_set_callback(req, 0, esp_input_done_esn, skb); } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 7370ad2e693a..2772004ba5a1 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -447,8 +447,10 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (__ipv6_addr_needs_scope_id(addr_type)) iif = skb->dev->ifindex; - else - iif = l3mdev_master_ifindex(skb_dst(skb)->dev); + else { + dst = skb_dst(skb); + iif = l3mdev_master_ifindex(dst ? dst->dev : skb->dev); + } /* * Must not send error if the source does not uniquely diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 1fcf61f1cbc3..89c59e656f44 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -99,7 +99,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, segs = ops->callbacks.gso_segment(skb, features); } - if (IS_ERR(segs)) + if (IS_ERR_OR_NULL(segs)) goto out; gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 0a4759b89da2..d76674efe523 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1181,7 +1181,6 @@ route_lookup: if (err) return err; - skb->protocol = htons(ETH_P_IPV6); skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 8a02ca8a11af..c299c1e2bbf0 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -1138,6 +1138,33 @@ static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = { .priority = 100, }; +static bool is_vti6_tunnel(const struct net_device *dev) +{ + return dev->netdev_ops == &vti6_netdev_ops; +} + +static int vti6_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct ip6_tnl *t = netdev_priv(dev); + + if (!is_vti6_tunnel(dev)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_DOWN: + if (!net_eq(t->net, dev_net(dev))) + xfrm_garbage_collect(t->net); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block vti6_notifier_block __read_mostly = { + .notifier_call = vti6_device_event, +}; + /** * vti6_tunnel_init - register protocol and reserve needed resources * @@ -1148,6 +1175,8 @@ static int __init vti6_tunnel_init(void) const char *msg; int err; + register_netdevice_notifier(&vti6_notifier_block); + msg = "tunnel device"; err = register_pernet_device(&vti6_net_ops); if (err < 0) @@ -1180,6 +1209,7 @@ xfrm_proto_ah_failed: xfrm_proto_esp_failed: unregister_pernet_device(&vti6_net_ops); pernet_dev_failed: + unregister_netdevice_notifier(&vti6_notifier_block); pr_err("vti6 init: failed to register %s\n", msg); return err; } @@ -1194,6 +1224,7 @@ static void __exit vti6_tunnel_cleanup(void) xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); unregister_pernet_device(&vti6_net_ops); + unregister_netdevice_notifier(&vti6_notifier_block); } module_init(vti6_tunnel_init); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index e4347aeb2e65..9948b5ce52da 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -576,11 +576,11 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) /* Jumbo payload inhibits frag. header */ if (ipv6_hdr(skb)->payload_len == 0) { pr_debug("payload len = 0\n"); - return -EINVAL; + return 0; } if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0) - return -EINVAL; + return 0; if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr))) return -ENOMEM; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index f7aab5ab93a5..f06b0471f39f 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -69,7 +69,7 @@ static unsigned int ipv6_defrag(void *priv, if (err == -EINPROGRESS) return NF_STOLEN; - return NF_ACCEPT; + return err == 0 ? NF_ACCEPT : NF_DROP; } static struct nf_hook_ops ipv6_defrag_ops[] = { diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index a5400223fd74..10090400c72f 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -156,6 +156,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) fl6.daddr = oip6h->saddr; fl6.fl6_sport = otcph->dest; fl6.fl6_dport = otcph->source; + fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev); security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6)); dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 7cca8ac66fe9..cd4252346a32 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -155,6 +155,8 @@ int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) if (unlikely(!skb)) return 0; + skb->protocol = htons(ETH_P_IPV6); + return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 982f6c44ea01..8938b6ba57a0 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -61,7 +61,8 @@ static struct sock *__l2tp_ip_bind_lookup(struct net *net, __be32 laddr, int dif if ((l2tp->conn_id == tunnel_id) && net_eq(sock_net(sk), net) && !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) && - !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + (!sk->sk_bound_dev_if || !dif || + sk->sk_bound_dev_if == dif)) goto found; } @@ -182,15 +183,17 @@ pass_up: struct iphdr *iph = (struct iphdr *) skb_network_header(skb); read_lock_bh(&l2tp_ip_lock); - sk = __l2tp_ip_bind_lookup(net, iph->daddr, 0, tunnel_id); + sk = __l2tp_ip_bind_lookup(net, iph->daddr, inet_iif(skb), + tunnel_id); + if (!sk) { + read_unlock_bh(&l2tp_ip_lock); + goto discard; + } + + sock_hold(sk); read_unlock_bh(&l2tp_ip_lock); } - if (sk == NULL) - goto discard; - - sock_hold(sk); - if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; @@ -256,15 +259,9 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (addr->l2tp_family != AF_INET) return -EINVAL; - ret = -EADDRINUSE; - read_lock_bh(&l2tp_ip_lock); - if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, - sk->sk_bound_dev_if, addr->l2tp_conn_id)) - goto out_in_use; - - read_unlock_bh(&l2tp_ip_lock); - lock_sock(sk); + + ret = -EINVAL; if (!sock_flag(sk, SOCK_ZAPPED)) goto out; @@ -281,14 +278,22 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_rcv_saddr = inet->inet_saddr = addr->l2tp_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ - sk_dst_reset(sk); + write_lock_bh(&l2tp_ip_lock); + if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, + sk->sk_bound_dev_if, addr->l2tp_conn_id)) { + write_unlock_bh(&l2tp_ip_lock); + ret = -EADDRINUSE; + goto out; + } + + sk_dst_reset(sk); l2tp_ip_sk(sk)->conn_id = addr->l2tp_conn_id; - write_lock_bh(&l2tp_ip_lock); sk_add_bind_node(sk, &l2tp_ip_bind_table); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); + ret = 0; sock_reset_flag(sk, SOCK_ZAPPED); @@ -296,11 +301,6 @@ out: release_sock(sk); return ret; - -out_in_use: - read_unlock_bh(&l2tp_ip_lock); - - return ret; } static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) @@ -308,21 +308,24 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *) uaddr; int rc; - if (sock_flag(sk, SOCK_ZAPPED)) /* Must bind first - autobinding does not work */ - return -EINVAL; - if (addr_len < sizeof(*lsa)) return -EINVAL; if (ipv4_is_multicast(lsa->l2tp_addr.s_addr)) return -EINVAL; - rc = ip4_datagram_connect(sk, uaddr, addr_len); - if (rc < 0) - return rc; - lock_sock(sk); + /* Must bind first - autobinding does not work */ + if (sock_flag(sk, SOCK_ZAPPED)) { + rc = -EINVAL; + goto out_sk; + } + + rc = __ip4_datagram_connect(sk, uaddr, addr_len); + if (rc < 0) + goto out_sk; + l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; write_lock_bh(&l2tp_ip_lock); @@ -330,7 +333,9 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len sk_add_bind_node(sk, &l2tp_ip_bind_table); write_unlock_bh(&l2tp_ip_lock); +out_sk: release_sock(sk); + return rc; } diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 9978d01ba0ba..aa821cb639e5 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -72,8 +72,9 @@ static struct sock *__l2tp_ip6_bind_lookup(struct net *net, if ((l2tp->conn_id == tunnel_id) && net_eq(sock_net(sk), net) && - !(addr && ipv6_addr_equal(addr, laddr)) && - !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + (!addr || ipv6_addr_equal(addr, laddr)) && + (!sk->sk_bound_dev_if || !dif || + sk->sk_bound_dev_if == dif)) goto found; } @@ -196,16 +197,17 @@ pass_up: struct ipv6hdr *iph = ipv6_hdr(skb); read_lock_bh(&l2tp_ip6_lock); - sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, - 0, tunnel_id); + sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, inet6_iif(skb), + tunnel_id); + if (!sk) { + read_unlock_bh(&l2tp_ip6_lock); + goto discard; + } + + sock_hold(sk); read_unlock_bh(&l2tp_ip6_lock); } - if (sk == NULL) - goto discard; - - sock_hold(sk); - if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; @@ -266,6 +268,7 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *) uaddr; struct net *net = sock_net(sk); __be32 v4addr = 0; + int bound_dev_if; int addr_type; int err; @@ -284,13 +287,6 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (addr_type & IPV6_ADDR_MULTICAST) return -EADDRNOTAVAIL; - err = -EADDRINUSE; - read_lock_bh(&l2tp_ip6_lock); - if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, - sk->sk_bound_dev_if, addr->l2tp_conn_id)) - goto out_in_use; - read_unlock_bh(&l2tp_ip6_lock); - lock_sock(sk); err = -EINVAL; @@ -300,28 +296,25 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (sk->sk_state != TCP_CLOSE) goto out_unlock; + bound_dev_if = sk->sk_bound_dev_if; + /* Check if the address belongs to the host. */ rcu_read_lock(); if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; if (addr_type & IPV6_ADDR_LINKLOCAL) { - if (addr_len >= sizeof(struct sockaddr_in6) && - addr->l2tp_scope_id) { - /* Override any existing binding, if another - * one is supplied by user. - */ - sk->sk_bound_dev_if = addr->l2tp_scope_id; - } + if (addr->l2tp_scope_id) + bound_dev_if = addr->l2tp_scope_id; /* Binding to link-local address requires an - interface */ - if (!sk->sk_bound_dev_if) + * interface. + */ + if (!bound_dev_if) goto out_unlock_rcu; err = -ENODEV; - dev = dev_get_by_index_rcu(sock_net(sk), - sk->sk_bound_dev_if); + dev = dev_get_by_index_rcu(sock_net(sk), bound_dev_if); if (!dev) goto out_unlock_rcu; } @@ -336,13 +329,22 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) } rcu_read_unlock(); - inet->inet_rcv_saddr = inet->inet_saddr = v4addr; + write_lock_bh(&l2tp_ip6_lock); + if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, bound_dev_if, + addr->l2tp_conn_id)) { + write_unlock_bh(&l2tp_ip6_lock); + err = -EADDRINUSE; + goto out_unlock; + } + + inet->inet_saddr = v4addr; + inet->inet_rcv_saddr = v4addr; + sk->sk_bound_dev_if = bound_dev_if; sk->sk_v6_rcv_saddr = addr->l2tp_addr; np->saddr = addr->l2tp_addr; l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id; - write_lock_bh(&l2tp_ip6_lock); sk_add_bind_node(sk, &l2tp_ip6_bind_table); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip6_lock); @@ -355,10 +357,7 @@ out_unlock_rcu: rcu_read_unlock(); out_unlock: release_sock(sk); - return err; -out_in_use: - read_unlock_bh(&l2tp_ip6_lock); return err; } @@ -371,9 +370,6 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_type; int rc; - if (sock_flag(sk, SOCK_ZAPPED)) /* Must bind first - autobinding does not work */ - return -EINVAL; - if (addr_len < sizeof(*lsa)) return -EINVAL; @@ -390,10 +386,18 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, return -EINVAL; } - rc = ip6_datagram_connect(sk, uaddr, addr_len); - lock_sock(sk); + /* Must bind first - autobinding does not work */ + if (sock_flag(sk, SOCK_ZAPPED)) { + rc = -EINVAL; + goto out_sk; + } + + rc = __ip6_datagram_connect(sk, uaddr, addr_len); + if (rc < 0) + goto out_sk; + l2tp_ip6_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; write_lock_bh(&l2tp_ip6_lock); @@ -401,6 +405,7 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, sk_add_bind_node(sk, &l2tp_ip6_bind_table); write_unlock_bh(&l2tp_ip6_lock); +out_sk: release_sock(sk); return rc; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 0e4334cbde17..15fe97644ffe 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1252,7 +1252,7 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (!nla) continue; - switch(index) { + switch (index) { case RTA_OIF: cfg->rc_ifindex = nla_get_u32(nla); break; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index bbb8f3df79f7..5b9c884a452e 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -42,7 +42,7 @@ struct nf_nat_conn_key { const struct nf_conntrack_zone *zone; }; -static struct rhashtable nf_nat_bysource_table; +static struct rhltable nf_nat_bysource_table; inline const struct nf_nat_l3proto * __nf_nat_l3proto_find(u8 family) @@ -193,9 +193,12 @@ static int nf_nat_bysource_cmp(struct rhashtable_compare_arg *arg, const struct nf_nat_conn_key *key = arg->key; const struct nf_conn *ct = obj; - return same_src(ct, key->tuple) && - net_eq(nf_ct_net(ct), key->net) && - nf_ct_zone_equal(ct, key->zone, IP_CT_DIR_ORIGINAL); + if (!same_src(ct, key->tuple) || + !net_eq(nf_ct_net(ct), key->net) || + !nf_ct_zone_equal(ct, key->zone, IP_CT_DIR_ORIGINAL)) + return 1; + + return 0; } static struct rhashtable_params nf_nat_bysource_params = { @@ -204,7 +207,6 @@ static struct rhashtable_params nf_nat_bysource_params = { .obj_cmpfn = nf_nat_bysource_cmp, .nelem_hint = 256, .min_size = 1024, - .nulls_base = (1U << RHT_BASE_SHIFT), }; /* Only called for SRC manip */ @@ -223,12 +225,15 @@ find_appropriate_src(struct net *net, .tuple = tuple, .zone = zone }; + struct rhlist_head *hl; - ct = rhashtable_lookup_fast(&nf_nat_bysource_table, &key, - nf_nat_bysource_params); - if (!ct) + hl = rhltable_lookup(&nf_nat_bysource_table, &key, + nf_nat_bysource_params); + if (!hl) return 0; + ct = container_of(hl, typeof(*ct), nat_bysource); + nf_ct_invert_tuplepr(result, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); result->dst = tuple->dst; @@ -446,11 +451,17 @@ nf_nat_setup_info(struct nf_conn *ct, } if (maniptype == NF_NAT_MANIP_SRC) { + struct nf_nat_conn_key key = { + .net = nf_ct_net(ct), + .tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + .zone = nf_ct_zone(ct), + }; int err; - err = rhashtable_insert_fast(&nf_nat_bysource_table, - &ct->nat_bysource, - nf_nat_bysource_params); + err = rhltable_insert_key(&nf_nat_bysource_table, + &key, + &ct->nat_bysource, + nf_nat_bysource_params); if (err) return NF_DROP; } @@ -567,8 +578,8 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) * will delete entry from already-freed table. */ ct->status &= ~IPS_NAT_DONE_MASK; - rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource, - nf_nat_bysource_params); + rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource, + nf_nat_bysource_params); /* don't delete conntrack. Although that would make things a lot * simpler, we'd end up flushing all conntracks on nat rmmod. @@ -698,8 +709,8 @@ static void nf_nat_cleanup_conntrack(struct nf_conn *ct) if (!nat) return; - rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource, - nf_nat_bysource_params); + rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource, + nf_nat_bysource_params); } static struct nf_ct_ext_type nat_extend __read_mostly = { @@ -834,13 +845,13 @@ static int __init nf_nat_init(void) { int ret; - ret = rhashtable_init(&nf_nat_bysource_table, &nf_nat_bysource_params); + ret = rhltable_init(&nf_nat_bysource_table, &nf_nat_bysource_params); if (ret) return ret; ret = nf_ct_extend_register(&nat_extend); if (ret < 0) { - rhashtable_destroy(&nf_nat_bysource_table); + rhltable_destroy(&nf_nat_bysource_table); printk(KERN_ERR "nf_nat_core: Unable to register extension\n"); return ret; } @@ -864,7 +875,7 @@ static int __init nf_nat_init(void) return 0; cleanup_extend: - rhashtable_destroy(&nf_nat_bysource_table); + rhltable_destroy(&nf_nat_bysource_table); nf_ct_extend_unregister(&nat_extend); return ret; } @@ -883,7 +894,7 @@ static void __exit nf_nat_cleanup(void) for (i = 0; i < NFPROTO_NUMPROTO; i++) kfree(nf_nat_l4protos[i]); - rhashtable_destroy(&nf_nat_bysource_table); + rhltable_destroy(&nf_nat_bysource_table); } MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 026581b04ea8..e5194f6f906c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2570,7 +2570,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, } if (set->timeout && - nla_put_be64(skb, NFTA_SET_TIMEOUT, cpu_to_be64(set->timeout), + nla_put_be64(skb, NFTA_SET_TIMEOUT, + cpu_to_be64(jiffies_to_msecs(set->timeout)), NFTA_SET_PAD)) goto nla_put_failure; if (set->gc_int && @@ -2859,7 +2860,8 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_TIMEOUT] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = be64_to_cpu(nla_get_be64(nla[NFTA_SET_TIMEOUT])); + timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( + nla[NFTA_SET_TIMEOUT]))); } gc_int = 0; if (nla[NFTA_SET_GC_INTERVAL] != NULL) { @@ -3178,7 +3180,8 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, - cpu_to_be64(*nft_set_ext_timeout(ext)), + cpu_to_be64(jiffies_to_msecs( + *nft_set_ext_timeout(ext))), NFTA_SET_ELEM_PAD)) goto nla_put_failure; @@ -3447,7 +3450,7 @@ void *nft_set_elem_init(const struct nft_set *set, memcpy(nft_set_ext_data(ext), data, set->dlen); if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) *nft_set_ext_expiration(ext) = - jiffies + msecs_to_jiffies(timeout); + jiffies + timeout; if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) *nft_set_ext_timeout(ext) = timeout; @@ -3535,7 +3538,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = be64_to_cpu(nla_get_be64(nla[NFTA_SET_ELEM_TIMEOUT])); + timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( + nla[NFTA_SET_ELEM_TIMEOUT]))); } else if (set->flags & NFT_SET_TIMEOUT) { timeout = set->timeout; } diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index baf694de3935..d5447a22275c 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -53,6 +53,7 @@ static int nft_hash_init(const struct nft_ctx *ctx, { struct nft_hash *priv = nft_expr_priv(expr); u32 len; + int err; if (!tb[NFTA_HASH_SREG] || !tb[NFTA_HASH_DREG] || @@ -67,8 +68,10 @@ static int nft_hash_init(const struct nft_ctx *ctx, priv->sreg = nft_parse_register(tb[NFTA_HASH_SREG]); priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); - len = ntohl(nla_get_be32(tb[NFTA_HASH_LEN])); - if (len == 0 || len > U8_MAX) + err = nft_parse_u32_check(tb[NFTA_HASH_LEN], U8_MAX, &len); + if (err < 0) + return err; + if (len == 0) return -ERANGE; priv->len = len; diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index fbc88009ca2e..8f0aaaea1376 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -59,6 +59,12 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr int err; u32 op; + if (!tb[NFTA_RANGE_SREG] || + !tb[NFTA_RANGE_OP] || + !tb[NFTA_RANGE_FROM_DATA] || + !tb[NFTA_RANGE_TO_DATA]) + return -EINVAL; + err = nft_data_init(NULL, &priv->data_from, sizeof(priv->data_from), &desc_from, tb[NFTA_RANGE_FROM_DATA]); if (err < 0) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 62bea4591054..246f29d365c0 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -329,7 +329,6 @@ static void netlink_sock_destruct(struct sock *sk) if (nlk->cb_running) { if (nlk->cb.done) nlk->cb.done(&nlk->cb); - module_put(nlk->cb.module); kfree_skb(nlk->cb.skb); } @@ -346,6 +345,14 @@ static void netlink_sock_destruct(struct sock *sk) WARN_ON(nlk_sk(sk)->groups); } +static void netlink_sock_destruct_work(struct work_struct *work) +{ + struct netlink_sock *nlk = container_of(work, struct netlink_sock, + work); + + sk_free(&nlk->sk); +} + /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on * SMP. Look, when several writers sleep and reader wakes them up, all but one * immediately hit write lock and grab all the cpus. Exclusive sleep solves @@ -648,8 +655,18 @@ out_module: static void deferred_put_nlk_sk(struct rcu_head *head) { struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu); + struct sock *sk = &nlk->sk; + + if (!atomic_dec_and_test(&sk->sk_refcnt)) + return; + + if (nlk->cb_running && nlk->cb.done) { + INIT_WORK(&nlk->work, netlink_sock_destruct_work); + schedule_work(&nlk->work); + return; + } - sock_put(&nlk->sk); + sk_free(sk); } static int netlink_release(struct socket *sock) diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 3cfd6cc60504..4fdb38318977 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -3,6 +3,7 @@ #include <linux/rhashtable.h> #include <linux/atomic.h> +#include <linux/workqueue.h> #include <net/sock.h> #define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8) @@ -33,6 +34,7 @@ struct netlink_sock { struct rhash_head node; struct rcu_head rcu; + struct work_struct work; }; static inline struct netlink_sock *nlk_sk(struct sock *sk) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 31045ef44a82..fecefa2dc94e 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -370,8 +370,11 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, skb_orphan(skb); memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); err = nf_ct_frag6_gather(net, skb, user); - if (err) + if (err) { + if (err != -EINPROGRESS) + kfree_skb(skb); return err; + } key->ip.proto = ipv6_hdr(skb)->nexthdr; ovs_cb.mru = IP6CB(skb)->frag_max_size; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d2238b204691..dd2332390c45 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3648,19 +3648,25 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; switch (val) { case TPACKET_V1: case TPACKET_V2: case TPACKET_V3: - po->tp_version = val; - return 0; + break; default: return -EINVAL; } + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_version = val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_RESERVE: { @@ -4164,6 +4170,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; + lock_sock(sk); /* Opening a Tx-ring is NOT supported in TPACKET_V3 */ if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) { net_warn_ratelimited("Tx-ring is not supported.\n"); @@ -4245,7 +4252,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, goto out; } - lock_sock(sk); /* Detach socket from network */ spin_lock(&po->bind_lock); @@ -4294,11 +4300,11 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (!tx_ring) prb_shutdown_retire_blk_timer(po, rb_queue); } - release_sock(sk); if (pg_vec) free_pg_vec(pg_vec, order, req->tp_block_nr); out: + release_sock(sk); return err; } diff --git a/net/rds/tcp.c b/net/rds/tcp.c index fcddacc92e01..20e2923dc827 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -659,6 +659,8 @@ out_recv: out_pernet: unregister_pernet_subsys(&rds_tcp_net_ops); out_slab: + if (unregister_netdevice_notifier(&rds_tcp_dev_notifier)) + pr_warn("could not unregister rds_tcp_dev_notifier\n"); kmem_cache_destroy(rds_tcp_conn_slab); out: return ret; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index b54d56d4959b..cf9b2fe8eac6 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -108,6 +108,17 @@ static void tcf_pedit_cleanup(struct tc_action *a, int bind) kfree(keys); } +static bool offset_valid(struct sk_buff *skb, int offset) +{ + if (offset > 0 && offset > skb->len) + return false; + + if (offset < 0 && -offset > skb_headroom(skb)) + return false; + + return true; +} + static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -134,6 +145,11 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, if (tkey->offmask) { char *d, _d; + if (!offset_valid(skb, off + tkey->at)) { + pr_info("tc filter pedit 'at' offset %d out of bounds\n", + off + tkey->at); + goto bad; + } d = skb_header_pointer(skb, off + tkey->at, 1, &_d); if (!d) @@ -146,10 +162,10 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, " offset must be on 32 bit boundaries\n"); goto bad; } - if (offset > 0 && offset > skb->len) { - pr_info("tc filter pedit" - " offset %d can't exceed pkt length %d\n", - offset, skb->len); + + if (!offset_valid(skb, off + offset)) { + pr_info("tc filter pedit offset %d out of bounds\n", + offset); goto bad; } diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index eb219b78cd49..5877f6061b57 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -62,9 +62,6 @@ static unsigned long basic_get(struct tcf_proto *tp, u32 handle) struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f; - if (head == NULL) - return 0UL; - list_for_each_entry(f, &head->flist, link) { if (f->handle == handle) { l = (unsigned long) f; @@ -109,7 +106,6 @@ static bool basic_destroy(struct tcf_proto *tp, bool force) tcf_unbind_filter(tp, &f->res); call_rcu(&f->rcu, basic_delete_filter); } - RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); return true; } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index bb1d5a487081..0a47ba5e6109 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -292,7 +292,6 @@ static bool cls_bpf_destroy(struct tcf_proto *tp, bool force) call_rcu(&prog->rcu, __cls_bpf_delete_prog); } - RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); return true; } @@ -303,9 +302,6 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle) struct cls_bpf_prog *prog; unsigned long ret = 0UL; - if (head == NULL) - return 0UL; - list_for_each_entry(prog, &head->plist, link) { if (prog->handle == handle) { ret = (unsigned long) prog; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 85233c470035..c1f20077837f 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -137,11 +137,10 @@ static bool cls_cgroup_destroy(struct tcf_proto *tp, bool force) if (!force) return false; - - if (head) { - RCU_INIT_POINTER(tp->root, NULL); + /* Head can still be NULL due to cls_cgroup_init(). */ + if (head) call_rcu(&head->rcu, cls_cgroup_destroy_rcu); - } + return true; } diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index e39672394c7b..6575aba87630 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -596,7 +596,6 @@ static bool flow_destroy(struct tcf_proto *tp, bool force) list_del_rcu(&f->list); call_rcu(&f->rcu, flow_destroy_filter); } - RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); return true; } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f6f40fba599b..904442421db3 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -13,6 +13,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/rhashtable.h> +#include <linux/workqueue.h> #include <linux/if_ether.h> #include <linux/in6.h> @@ -64,7 +65,10 @@ struct cls_fl_head { bool mask_assigned; struct list_head filters; struct rhashtable_params ht_params; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; struct cls_fl_filter { @@ -269,6 +273,24 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc); } +static void fl_destroy_sleepable(struct work_struct *work) +{ + struct cls_fl_head *head = container_of(work, struct cls_fl_head, + work); + if (head->mask_assigned) + rhashtable_destroy(&head->ht); + kfree(head); + module_put(THIS_MODULE); +} + +static void fl_destroy_rcu(struct rcu_head *rcu) +{ + struct cls_fl_head *head = container_of(rcu, struct cls_fl_head, rcu); + + INIT_WORK(&head->work, fl_destroy_sleepable); + schedule_work(&head->work); +} + static bool fl_destroy(struct tcf_proto *tp, bool force) { struct cls_fl_head *head = rtnl_dereference(tp->root); @@ -282,10 +304,9 @@ static bool fl_destroy(struct tcf_proto *tp, bool force) list_del_rcu(&f->list); call_rcu(&f->rcu, fl_destroy_filter); } - RCU_INIT_POINTER(tp->root, NULL); - if (head->mask_assigned) - rhashtable_destroy(&head->ht); - kfree_rcu(head, rcu); + + __module_get(THIS_MODULE); + call_rcu(&head->rcu, fl_destroy_rcu); return true; } @@ -711,8 +732,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, goto errout; if (fold) { - rhashtable_remove_fast(&head->ht, &fold->ht_node, - head->ht_params); + if (!tc_skip_sw(fold->flags)) + rhashtable_remove_fast(&head->ht, &fold->ht_node, + head->ht_params); fl_hw_destroy_filter(tp, (unsigned long)fold); } @@ -739,8 +761,9 @@ static int fl_delete(struct tcf_proto *tp, unsigned long arg) struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f = (struct cls_fl_filter *) arg; - rhashtable_remove_fast(&head->ht, &f->ht_node, - head->ht_params); + if (!tc_skip_sw(f->flags)) + rhashtable_remove_fast(&head->ht, &f->ht_node, + head->ht_params); list_del_rcu(&f->list); fl_hw_destroy_filter(tp, (unsigned long)f); tcf_unbind_filter(tp, &f->res); diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 25927b6c4436..f935429bd5ef 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -114,7 +114,6 @@ static bool mall_destroy(struct tcf_proto *tp, bool force) call_rcu(&f->rcu, mall_destroy_filter); } - RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); return true; } diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 4f05a19fb073..322438fb3ffc 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -152,7 +152,8 @@ static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; nhptr = ip_hdr(skb); #endif - + if (unlikely(!head)) + return -1; restart: #if RSVP_DST_LEN == 4 diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 96144bdf30db..0751245a6ace 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -543,7 +543,6 @@ static bool tcindex_destroy(struct tcf_proto *tp, bool force) walker.fn = tcindex_destroy_element; tcindex_walk(tp, &walker); - RCU_INIT_POINTER(tp->root, NULL); call_rcu(&p->rcu, __tcindex_destroy); return true; } diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 975dbeb60ab0..52d74760fb68 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -421,6 +421,10 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, dev = dev_get_by_name(net, driver_name); if (!dev) return -ENODEV; + if (tipc_mtu_bad(dev, 0)) { + dev_put(dev); + return -EINVAL; + } /* Associate TIPC bearer with L2 bearer */ rcu_assign_pointer(b->media_ptr, dev); @@ -610,8 +614,6 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, if (!b) return NOTIFY_DONE; - b->mtu = dev->mtu; - switch (evt) { case NETDEV_CHANGE: if (netif_carrier_ok(dev)) @@ -624,6 +626,11 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, tipc_reset_bearer(net, b); break; case NETDEV_CHANGEMTU: + if (tipc_mtu_bad(dev, 0)) { + bearer_disable(net, b); + break; + } + b->mtu = dev->mtu; tipc_reset_bearer(net, b); break; case NETDEV_CHANGEADDR: diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 78892e2f53e3..278ff7f616f9 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -39,6 +39,7 @@ #include "netlink.h" #include "core.h" +#include "msg.h" #include <net/genetlink.h> #define MAX_MEDIA 3 @@ -59,6 +60,9 @@ #define TIPC_MEDIA_TYPE_IB 2 #define TIPC_MEDIA_TYPE_UDP 3 +/* minimum bearer MTU */ +#define TIPC_MIN_BEARER_MTU (MAX_H_SIZE + INT_H_SIZE) + /** * struct tipc_media_addr - destination address used by TIPC bearers * @value: address info (format defined by media) @@ -215,4 +219,13 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id, void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq); +/* check if device MTU is too low for tipc headers */ +static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve) +{ + if (dev->mtu >= TIPC_MIN_BEARER_MTU + reserve) + return false; + netdev_warn(dev, "MTU too low for tipc bearer\n"); + return true; +} + #endif /* _TIPC_BEARER_H */ diff --git a/net/tipc/link.c b/net/tipc/link.c index ecc12411155e..bda89bf9f4ff 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -47,8 +47,8 @@ #include <linux/pkt_sched.h> struct tipc_stats { - u32 sent_info; /* used in counting # sent packets */ - u32 recv_info; /* used in counting # recv'd packets */ + u32 sent_pkts; + u32 recv_pkts; u32 sent_states; u32 recv_states; u32 sent_probes; @@ -857,7 +857,6 @@ void tipc_link_reset(struct tipc_link *l) l->acked = 0; l->silent_intv_cnt = 0; l->rst_cnt = 0; - l->stats.recv_info = 0; l->stale_count = 0; l->bc_peer_is_up = false; memset(&l->mon_state, 0, sizeof(l->mon_state)); @@ -888,6 +887,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *transmq = &l->transmq; struct sk_buff_head *backlogq = &l->backlogq; struct sk_buff *skb, *_skb, *bskb; + int pkt_cnt = skb_queue_len(list); /* Match msg importance against this and all higher backlog limits: */ if (!skb_queue_empty(backlogq)) { @@ -901,6 +901,11 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, return -EMSGSIZE; } + if (pkt_cnt > 1) { + l->stats.sent_fragmented++; + l->stats.sent_fragments += pkt_cnt; + } + /* Prepare each packet for sending, and add to relevant queue: */ while (skb_queue_len(list)) { skb = skb_peek(list); @@ -920,6 +925,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; l->rcv_unacked = 0; + l->stats.sent_pkts++; seqno++; continue; } @@ -968,6 +974,7 @@ void tipc_link_advance_backlog(struct tipc_link *l, struct sk_buff_head *xmitq) msg_set_ack(hdr, ack); msg_set_bcast_ack(hdr, bc_ack); l->rcv_unacked = 0; + l->stats.sent_pkts++; seqno++; } l->snd_nxt = seqno; @@ -1260,7 +1267,7 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, /* Deliver packet */ l->rcv_nxt++; - l->stats.recv_info++; + l->stats.recv_pkts++; if (!tipc_data_input(l, skb, l->inputq)) rc |= tipc_link_input(l, skb, l->inputq); if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN)) @@ -1800,10 +1807,6 @@ void tipc_link_set_queue_limits(struct tipc_link *l, u32 win) void tipc_link_reset_stats(struct tipc_link *l) { memset(&l->stats, 0, sizeof(l->stats)); - if (!link_is_bc_sndlink(l)) { - l->stats.sent_info = l->snd_nxt; - l->stats.recv_info = l->rcv_nxt; - } } static void link_print(struct tipc_link *l, const char *str) @@ -1867,12 +1870,12 @@ static int __tipc_nl_add_stats(struct sk_buff *skb, struct tipc_stats *s) }; struct nla_map map[] = { - {TIPC_NLA_STATS_RX_INFO, s->recv_info}, + {TIPC_NLA_STATS_RX_INFO, 0}, {TIPC_NLA_STATS_RX_FRAGMENTS, s->recv_fragments}, {TIPC_NLA_STATS_RX_FRAGMENTED, s->recv_fragmented}, {TIPC_NLA_STATS_RX_BUNDLES, s->recv_bundles}, {TIPC_NLA_STATS_RX_BUNDLED, s->recv_bundled}, - {TIPC_NLA_STATS_TX_INFO, s->sent_info}, + {TIPC_NLA_STATS_TX_INFO, 0}, {TIPC_NLA_STATS_TX_FRAGMENTS, s->sent_fragments}, {TIPC_NLA_STATS_TX_FRAGMENTED, s->sent_fragmented}, {TIPC_NLA_STATS_TX_BUNDLES, s->sent_bundles}, @@ -1947,9 +1950,9 @@ int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_MTU, link->mtu)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, link->rcv_nxt)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, link->stats.recv_pkts)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, link->snd_nxt)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, link->stats.sent_pkts)) goto attr_msg_full; if (tipc_link_is_up(link)) @@ -2004,12 +2007,12 @@ static int __tipc_nl_add_bc_link_stat(struct sk_buff *skb, }; struct nla_map map[] = { - {TIPC_NLA_STATS_RX_INFO, stats->recv_info}, + {TIPC_NLA_STATS_RX_INFO, stats->recv_pkts}, {TIPC_NLA_STATS_RX_FRAGMENTS, stats->recv_fragments}, {TIPC_NLA_STATS_RX_FRAGMENTED, stats->recv_fragmented}, {TIPC_NLA_STATS_RX_BUNDLES, stats->recv_bundles}, {TIPC_NLA_STATS_RX_BUNDLED, stats->recv_bundled}, - {TIPC_NLA_STATS_TX_INFO, stats->sent_info}, + {TIPC_NLA_STATS_TX_INFO, stats->sent_pkts}, {TIPC_NLA_STATS_TX_FRAGMENTS, stats->sent_fragments}, {TIPC_NLA_STATS_TX_FRAGMENTED, stats->sent_fragmented}, {TIPC_NLA_STATS_TX_BUNDLES, stats->sent_bundles}, @@ -2076,9 +2079,9 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) goto attr_msg_full; if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, bcl->name)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, bcl->rcv_nxt)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, 0)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, bcl->snd_nxt)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, 0)) goto attr_msg_full; prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 78cab9c5a445..b58dc95f3d35 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -697,6 +697,11 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, udp_conf.local_ip.s_addr = htonl(INADDR_ANY); udp_conf.use_udp_checksums = false; ub->ifindex = dev->ifindex; + if (tipc_mtu_bad(dev, sizeof(struct iphdr) + + sizeof(struct udphdr))) { + err = -EINVAL; + goto err; + } b->mtu = dev->mtu - sizeof(struct iphdr) - sizeof(struct udphdr); #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index fd6986634e6f..5bf7e1bfeac7 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1268,12 +1268,14 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, err = security_xfrm_policy_lookup(pol->security, fl->flowi_secid, policy_to_flow_dir(dir)); - if (!err && !xfrm_pol_hold_rcu(pol)) - goto again; - else if (err == -ESRCH) + if (!err) { + if (!xfrm_pol_hold_rcu(pol)) + goto again; + } else if (err == -ESRCH) { pol = NULL; - else + } else { pol = ERR_PTR(err); + } } else pol = NULL; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 08892091cfe3..671a1d0333f0 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2450,7 +2450,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) #ifdef CONFIG_COMPAT if (in_compat_syscall()) - return -ENOTSUPP; + return -EOPNOTSUPP; #endif type = nlh->nlmsg_type; diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index 90f44bd2045e..dadd5161bd91 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -113,7 +113,7 @@ static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) = #define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */ #define PT_REGS_RC(x) ((x)->gprs[2]) #define PT_REGS_SP(x) ((x)->gprs[15]) -#define PT_REGS_IP(x) ((x)->ip) +#define PT_REGS_IP(x) ((x)->psw.addr) #elif defined(__aarch64__) diff --git a/samples/bpf/sampleip_kern.c b/samples/bpf/sampleip_kern.c index 774a681f374a..ceabf31079cf 100644 --- a/samples/bpf/sampleip_kern.c +++ b/samples/bpf/sampleip_kern.c @@ -25,7 +25,7 @@ int do_sample(struct bpf_perf_event_data *ctx) u64 ip; u32 *value, init_val = 1; - ip = ctx->regs.ip; + ip = PT_REGS_IP(&ctx->regs); value = bpf_map_lookup_elem(&ip_map, &ip); if (value) *value += 1; diff --git a/samples/bpf/trace_event_kern.c b/samples/bpf/trace_event_kern.c index 71a8ed32823e..41b6115a32eb 100644 --- a/samples/bpf/trace_event_kern.c +++ b/samples/bpf/trace_event_kern.c @@ -50,7 +50,7 @@ int bpf_prog1(struct bpf_perf_event_data *ctx) key.userstack = bpf_get_stackid(ctx, &stackmap, USER_STACKID_FLAGS); if ((int)key.kernstack < 0 && (int)key.userstack < 0) { bpf_trace_printk(fmt, sizeof(fmt), cpu, ctx->sample_period, - ctx->regs.ip); + PT_REGS_IP(&ctx->regs)); return 0; } diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index ebced77deb9c..90a091b6ae4d 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -35,6 +35,8 @@ nconfig: $(obj)/nconf silentoldconfig: $(obj)/conf $(Q)mkdir -p include/config include/generated + $(Q)test -e include/generated/autoksyms.h || \ + touch include/generated/autoksyms.h $< $(silent) --$@ $(Kconfig) localyesconfig localmodconfig: $(obj)/streamline_config.pl $(obj)/conf diff --git a/sound/sparc/dbri.c b/sound/sparc/dbri.c index 3fe4468ea2c5..52063b262667 100644 --- a/sound/sparc/dbri.c +++ b/sound/sparc/dbri.c @@ -1702,7 +1702,7 @@ interrupts are disabled. static void xmit_descs(struct snd_dbri *dbri) { struct dbri_streaminfo *info; - u32 dvma_addr = (u32)dbri->dma_dvma; + u32 dvma_addr; s32 *cmd; unsigned long flags; int first_td; @@ -1710,6 +1710,7 @@ static void xmit_descs(struct snd_dbri *dbri) if (dbri == NULL) return; /* Disabled */ + dvma_addr = (u32)dbri->dma_dvma; info = &dbri->stream_info[DBRI_REC]; spin_lock_irqsave(&dbri->lock, flags); diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index b63a31be1218..5e0dea2cdc01 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -99,7 +99,7 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, break; case 0x8d: - if (insn.rex_prefix.bytes && + if (insn.rex_prefix.nbytes && insn.rex_prefix.bytes[0] == 0x48 && insn.modrm.nbytes && insn.modrm.bytes[0] == 0x2c && insn.sib.nbytes && insn.sib.bytes[0] == 0x24) diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index 582db95127ed..405212be044a 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -14,6 +14,7 @@ ldflags-y += --wrap=devm_memremap_pages ldflags-y += --wrap=insert_resource ldflags-y += --wrap=remove_resource ldflags-y += --wrap=acpi_evaluate_object +ldflags-y += --wrap=acpi_evaluate_dsm DRIVERS := ../../../drivers NVDIMM_SRC := $(DRIVERS)/nvdimm diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 3ccef732fce9..64cae1a5deff 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -26,14 +26,17 @@ static LIST_HEAD(iomap_head); static struct iomap_ops { nfit_test_lookup_fn nfit_test_lookup; + nfit_test_evaluate_dsm_fn evaluate_dsm; struct list_head list; } iomap_ops = { .list = LIST_HEAD_INIT(iomap_ops.list), }; -void nfit_test_setup(nfit_test_lookup_fn lookup) +void nfit_test_setup(nfit_test_lookup_fn lookup, + nfit_test_evaluate_dsm_fn evaluate) { iomap_ops.nfit_test_lookup = lookup; + iomap_ops.evaluate_dsm = evaluate; list_add_rcu(&iomap_ops.list, &iomap_head); } EXPORT_SYMBOL(nfit_test_setup); @@ -367,4 +370,22 @@ acpi_status __wrap_acpi_evaluate_object(acpi_handle handle, acpi_string path, } EXPORT_SYMBOL(__wrap_acpi_evaluate_object); +union acpi_object * __wrap_acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid, + u64 rev, u64 func, union acpi_object *argv4) +{ + union acpi_object *obj = ERR_PTR(-ENXIO); + struct iomap_ops *ops; + + rcu_read_lock(); + ops = list_first_or_null_rcu(&iomap_head, typeof(*ops), list); + if (ops) + obj = ops->evaluate_dsm(handle, uuid, rev, func, argv4); + rcu_read_unlock(); + + if (IS_ERR(obj)) + return acpi_evaluate_dsm(handle, uuid, rev, func, argv4); + return obj; +} +EXPORT_SYMBOL(__wrap_acpi_evaluate_dsm); + MODULE_LICENSE("GPL v2"); diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index c9a6458cb63e..71620fa95953 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -23,6 +23,7 @@ #include <linux/sizes.h> #include <linux/list.h> #include <linux/slab.h> +#include <nd-core.h> #include <nfit.h> #include <nd.h> #include "nfit_test.h" @@ -1506,6 +1507,225 @@ static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa, return 0; } +static unsigned long nfit_ctl_handle; + +union acpi_object *result; + +static union acpi_object *nfit_test_evaluate_dsm(acpi_handle handle, + const u8 *uuid, u64 rev, u64 func, union acpi_object *argv4) +{ + if (handle != &nfit_ctl_handle) + return ERR_PTR(-ENXIO); + + return result; +} + +static int setup_result(void *buf, size_t size) +{ + result = kmalloc(sizeof(union acpi_object) + size, GFP_KERNEL); + if (!result) + return -ENOMEM; + result->package.type = ACPI_TYPE_BUFFER, + result->buffer.pointer = (void *) (result + 1); + result->buffer.length = size; + memcpy(result->buffer.pointer, buf, size); + memset(buf, 0, size); + return 0; +} + +static int nfit_ctl_test(struct device *dev) +{ + int rc, cmd_rc; + struct nvdimm *nvdimm; + struct acpi_device *adev; + struct nfit_mem *nfit_mem; + struct nd_ars_record *record; + struct acpi_nfit_desc *acpi_desc; + const u64 test_val = 0x0123456789abcdefULL; + unsigned long mask, cmd_size, offset; + union { + struct nd_cmd_get_config_size cfg_size; + struct nd_cmd_ars_status ars_stat; + struct nd_cmd_ars_cap ars_cap; + char buf[sizeof(struct nd_cmd_ars_status) + + sizeof(struct nd_ars_record)]; + } cmds; + + adev = devm_kzalloc(dev, sizeof(*adev), GFP_KERNEL); + if (!adev) + return -ENOMEM; + *adev = (struct acpi_device) { + .handle = &nfit_ctl_handle, + .dev = { + .init_name = "test-adev", + }, + }; + + acpi_desc = devm_kzalloc(dev, sizeof(*acpi_desc), GFP_KERNEL); + if (!acpi_desc) + return -ENOMEM; + *acpi_desc = (struct acpi_nfit_desc) { + .nd_desc = { + .cmd_mask = 1UL << ND_CMD_ARS_CAP + | 1UL << ND_CMD_ARS_START + | 1UL << ND_CMD_ARS_STATUS + | 1UL << ND_CMD_CLEAR_ERROR, + .module = THIS_MODULE, + .provider_name = "ACPI.NFIT", + .ndctl = acpi_nfit_ctl, + }, + .dev = &adev->dev, + }; + + nfit_mem = devm_kzalloc(dev, sizeof(*nfit_mem), GFP_KERNEL); + if (!nfit_mem) + return -ENOMEM; + + mask = 1UL << ND_CMD_SMART | 1UL << ND_CMD_SMART_THRESHOLD + | 1UL << ND_CMD_DIMM_FLAGS | 1UL << ND_CMD_GET_CONFIG_SIZE + | 1UL << ND_CMD_GET_CONFIG_DATA | 1UL << ND_CMD_SET_CONFIG_DATA + | 1UL << ND_CMD_VENDOR; + *nfit_mem = (struct nfit_mem) { + .adev = adev, + .family = NVDIMM_FAMILY_INTEL, + .dsm_mask = mask, + }; + + nvdimm = devm_kzalloc(dev, sizeof(*nvdimm), GFP_KERNEL); + if (!nvdimm) + return -ENOMEM; + *nvdimm = (struct nvdimm) { + .provider_data = nfit_mem, + .cmd_mask = mask, + .dev = { + .init_name = "test-dimm", + }, + }; + + + /* basic checkout of a typical 'get config size' command */ + cmd_size = sizeof(cmds.cfg_size); + cmds.cfg_size = (struct nd_cmd_get_config_size) { + .status = 0, + .config_size = SZ_128K, + .max_xfer = SZ_4K, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, nvdimm, ND_CMD_GET_CONFIG_SIZE, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc || cmds.cfg_size.status != 0 + || cmds.cfg_size.config_size != SZ_128K + || cmds.cfg_size.max_xfer != SZ_4K) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test ars_status with zero output */ + cmd_size = offsetof(struct nd_cmd_ars_status, address); + cmds.ars_stat = (struct nd_cmd_ars_status) { + .out_length = 0, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_STATUS, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test ars_cap with benign extended status */ + cmd_size = sizeof(cmds.ars_cap); + cmds.ars_cap = (struct nd_cmd_ars_cap) { + .status = ND_ARS_PERSISTENT << 16, + }; + offset = offsetof(struct nd_cmd_ars_cap, status); + rc = setup_result(cmds.buf + offset, cmd_size - offset); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_CAP, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test ars_status with 'status' trimmed from 'out_length' */ + cmd_size = sizeof(cmds.ars_stat) + sizeof(struct nd_ars_record); + cmds.ars_stat = (struct nd_cmd_ars_status) { + .out_length = cmd_size - 4, + }; + record = &cmds.ars_stat.records[0]; + *record = (struct nd_ars_record) { + .length = test_val, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_STATUS, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc || record->length != test_val) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test ars_status with 'Output (Size)' including 'status' */ + cmd_size = sizeof(cmds.ars_stat) + sizeof(struct nd_ars_record); + cmds.ars_stat = (struct nd_cmd_ars_status) { + .out_length = cmd_size, + }; + record = &cmds.ars_stat.records[0]; + *record = (struct nd_ars_record) { + .length = test_val, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_STATUS, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc || record->length != test_val) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test extended status for get_config_size results in failure */ + cmd_size = sizeof(cmds.cfg_size); + cmds.cfg_size = (struct nd_cmd_get_config_size) { + .status = 1 << 16, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, nvdimm, ND_CMD_GET_CONFIG_SIZE, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc >= 0) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + return 0; +} + static int nfit_test_probe(struct platform_device *pdev) { struct nvdimm_bus_descriptor *nd_desc; @@ -1516,6 +1736,12 @@ static int nfit_test_probe(struct platform_device *pdev) union acpi_object *obj; int rc; + if (strcmp(dev_name(&pdev->dev), "nfit_test.0") == 0) { + rc = nfit_ctl_test(&pdev->dev); + if (rc) + return rc; + } + nfit_test = to_nfit_test(&pdev->dev); /* common alloc */ @@ -1639,11 +1865,13 @@ static __init int nfit_test_init(void) { int rc, i; - nfit_test_dimm = class_create(THIS_MODULE, "nfit_test_dimm"); - if (IS_ERR(nfit_test_dimm)) - return PTR_ERR(nfit_test_dimm); + nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm); - nfit_test_setup(nfit_test_lookup); + nfit_test_dimm = class_create(THIS_MODULE, "nfit_test_dimm"); + if (IS_ERR(nfit_test_dimm)) { + rc = PTR_ERR(nfit_test_dimm); + goto err_register; + } for (i = 0; i < NUM_NFITS; i++) { struct nfit_test *nfit_test; diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h index c281dd2e5e2d..f54c0032c6ff 100644 --- a/tools/testing/nvdimm/test/nfit_test.h +++ b/tools/testing/nvdimm/test/nfit_test.h @@ -31,11 +31,17 @@ struct nfit_test_resource { void *buf; }; +union acpi_object; +typedef void *acpi_handle; + typedef struct nfit_test_resource *(*nfit_test_lookup_fn)(resource_size_t); +typedef union acpi_object *(*nfit_test_evaluate_dsm_fn)(acpi_handle handle, + const u8 *uuid, u64 rev, u64 func, union acpi_object *argv4); void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size); void __wrap_iounmap(volatile void __iomem *addr); -void nfit_test_setup(nfit_test_lookup_fn lookup); +void nfit_test_setup(nfit_test_lookup_fn lookup, + nfit_test_evaluate_dsm_fn evaluate); void nfit_test_teardown(void); struct nfit_test_resource *get_nfit_res(resource_size_t resource); #endif diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c index 0a063af40565..9bab86757fa4 100644 --- a/virt/kvm/arm/vgic/vgic-v2.c +++ b/virt/kvm/arm/vgic/vgic-v2.c @@ -50,8 +50,10 @@ void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu) WARN_ON(cpuif->vgic_lr[lr] & GICH_LR_STATE); - kvm_notify_acked_irq(vcpu->kvm, 0, - intid - VGIC_NR_PRIVATE_IRQS); + /* Only SPIs require notification */ + if (vgic_valid_spi(vcpu->kvm, intid)) + kvm_notify_acked_irq(vcpu->kvm, 0, + intid - VGIC_NR_PRIVATE_IRQS); } } diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 9f0dae397d9c..5c9f9745e6ca 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -41,8 +41,10 @@ void vgic_v3_process_maintenance(struct kvm_vcpu *vcpu) WARN_ON(cpuif->vgic_lr[lr] & ICH_LR_STATE); - kvm_notify_acked_irq(vcpu->kvm, 0, - intid - VGIC_NR_PRIVATE_IRQS); + /* Only SPIs require notification */ + if (vgic_valid_spi(vcpu->kvm, intid)) + kvm_notify_acked_irq(vcpu->kvm, 0, + intid - VGIC_NR_PRIVATE_IRQS); } /* diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 5c360347a1e9..7f9ee2929cfe 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2889,10 +2889,10 @@ static int kvm_ioctl_create_device(struct kvm *kvm, ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { - ops->destroy(dev); mutex_lock(&kvm->lock); list_del(&dev->vm_node); mutex_unlock(&kvm->lock); + ops->destroy(dev); return ret; } |