diff options
1106 files changed, 21327 insertions, 12220 deletions
@@ -73,6 +73,7 @@ Juha Yrjola <juha.yrjola@nokia.com> Juha Yrjola <juha.yrjola@solidboot.com> Kay Sievers <kay.sievers@vrfy.org> Kenneth W Chen <kenneth.w.chen@intel.com> +Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com> Koushik <raghavendra.koushik@neterion.com> Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Leonid I Ananiev <leonid.i.ananiev@intel.com> diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events index 20979f8b3ed..505f080d20a 100644 --- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events +++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events @@ -52,12 +52,18 @@ Description: Per-pmu performance monitoring events specific to the running syste event=0x2abc event=0x423,inv,cmask=0x3 domain=0x1,offset=0x8,starting_index=0xffff + domain=0x1,offset=0x8,core=? Each of the assignments indicates a value to be assigned to a particular set of bits (as defined by the format file corresponding to the <term>) in the perf_event structure passed to the perf_open syscall. + In the case of the last example, a value replacing "?" would + need to be provided by the user selecting the particular event. + This is referred to as "event parameterization". Event + parameters have the format 'param=?'. + What: /sys/bus/event_source/devices/<pmu>/events/<event>.unit Date: 2014/02/24 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> diff --git a/Documentation/ABI/testing/sysfs-kernel-livepatch b/Documentation/ABI/testing/sysfs-kernel-livepatch new file mode 100644 index 00000000000..5bf42a840b2 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-livepatch @@ -0,0 +1,44 @@ +What: /sys/kernel/livepatch +Date: Nov 2014 +KernelVersion: 3.19.0 +Contact: live-patching@vger.kernel.org +Description: + Interface for kernel live patching + + The /sys/kernel/livepatch directory contains subdirectories for + each loaded live patch module. + +What: /sys/kernel/livepatch/<patch> +Date: Nov 2014 +KernelVersion: 3.19.0 +Contact: live-patching@vger.kernel.org +Description: + The patch directory contains subdirectories for each kernel + object (vmlinux or a module) in which it patched functions. + +What: /sys/kernel/livepatch/<patch>/enabled +Date: Nov 2014 +KernelVersion: 3.19.0 +Contact: live-patching@vger.kernel.org +Description: + A writable attribute that indicates whether the patched + code is currently applied. Writing 0 will disable the patch + while writing 1 will re-enable the patch. + +What: /sys/kernel/livepatch/<patch>/<object> +Date: Nov 2014 +KernelVersion: 3.19.0 +Contact: live-patching@vger.kernel.org +Description: + The object directory contains subdirectories for each function + that is patched within the object. + +What: /sys/kernel/livepatch/<patch>/<object>/<function> +Date: Nov 2014 +KernelVersion: 3.19.0 +Contact: live-patching@vger.kernel.org +Description: + The function directory contains attributes regarding the + properties and state of the patched function. + + There are currently no such attributes. diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt index ed186a902d3..b57c0c1cdac 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.txt @@ -15,7 +15,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT 21 seconds. This configuration parameter may be changed at runtime via the - /sys/module/rcutree/parameters/rcu_cpu_stall_timeout, however + /sys/module/rcupdate/parameters/rcu_cpu_stall_timeout, however this parameter is checked only at the beginning of a cycle. So if you are 10 seconds into a 40-second stall, setting this sysfs parameter to (say) five will shorten the timeout for the @@ -152,6 +152,15 @@ no non-lazy callbacks ("." is printed otherwise, as shown above) and "D" indicates that dyntick-idle processing is enabled ("." is printed otherwise, for example, if disabled via the "nohz=" kernel boot parameter). +If the relevant grace-period kthread has been unable to run prior to +the stall warning, the following additional line is printed: + + rcu_preempt kthread starved for 2023 jiffies! + +Starving the grace-period kthreads of CPU time can of course result in +RCU CPU stall warnings even when all CPUs and tasks have passed through +the required quiescent states. + Multiple Warnings From One Stall @@ -187,6 +196,11 @@ o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the behavior, you might need to replace some of the cond_resched() calls with calls to cond_resched_rcu_qs(). +o Anything that prevents RCU's grace-period kthreads from running. + This can result in the "All QSes seen" console-log message. + This message will include information on when the kthread last + ran and how often it should be expected to run. + o A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might happen to preempt a low-priority task in the middle of an RCU read-side critical section. This is especially damaging if diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt index b63b9bb3bc0..08651da1544 100644 --- a/Documentation/RCU/trace.txt +++ b/Documentation/RCU/trace.txt @@ -56,14 +56,14 @@ rcuboost: The output of "cat rcu/rcu_preempt/rcudata" looks as follows: - 0!c=30455 g=30456 pq=1 qp=1 dt=126535/140000000000000/0 df=2002 of=4 ql=0/0 qs=N... b=10 ci=74572 nci=0 co=1131 ca=716 - 1!c=30719 g=30720 pq=1 qp=0 dt=132007/140000000000000/0 df=1874 of=10 ql=0/0 qs=N... b=10 ci=123209 nci=0 co=685 ca=982 - 2!c=30150 g=30151 pq=1 qp=1 dt=138537/140000000000000/0 df=1707 of=8 ql=0/0 qs=N... b=10 ci=80132 nci=0 co=1328 ca=1458 - 3 c=31249 g=31250 pq=1 qp=0 dt=107255/140000000000000/0 df=1749 of=6 ql=0/450 qs=NRW. b=10 ci=151700 nci=0 co=509 ca=622 - 4!c=29502 g=29503 pq=1 qp=1 dt=83647/140000000000000/0 df=965 of=5 ql=0/0 qs=N... b=10 ci=65643 nci=0 co=1373 ca=1521 - 5 c=31201 g=31202 pq=1 qp=1 dt=70422/0/0 df=535 of=7 ql=0/0 qs=.... b=10 ci=58500 nci=0 co=764 ca=698 - 6!c=30253 g=30254 pq=1 qp=1 dt=95363/140000000000000/0 df=780 of=5 ql=0/0 qs=N... b=10 ci=100607 nci=0 co=1414 ca=1353 - 7 c=31178 g=31178 pq=1 qp=0 dt=91536/0/0 df=547 of=4 ql=0/0 qs=.... b=10 ci=109819 nci=0 co=1115 ca=969 + 0!c=30455 g=30456 pq=1/0 qp=1 dt=126535/140000000000000/0 df=2002 of=4 ql=0/0 qs=N... b=10 ci=74572 nci=0 co=1131 ca=716 + 1!c=30719 g=30720 pq=1/0 qp=0 dt=132007/140000000000000/0 df=1874 of=10 ql=0/0 qs=N... b=10 ci=123209 nci=0 co=685 ca=982 + 2!c=30150 g=30151 pq=1/1 qp=1 dt=138537/140000000000000/0 df=1707 of=8 ql=0/0 qs=N... b=10 ci=80132 nci=0 co=1328 ca=1458 + 3 c=31249 g=31250 pq=1/1 qp=0 dt=107255/140000000000000/0 df=1749 of=6 ql=0/450 qs=NRW. b=10 ci=151700 nci=0 co=509 ca=622 + 4!c=29502 g=29503 pq=1/0 qp=1 dt=83647/140000000000000/0 df=965 of=5 ql=0/0 qs=N... b=10 ci=65643 nci=0 co=1373 ca=1521 + 5 c=31201 g=31202 pq=1/0 qp=1 dt=70422/0/0 df=535 of=7 ql=0/0 qs=.... b=10 ci=58500 nci=0 co=764 ca=698 + 6!c=30253 g=30254 pq=1/0 qp=1 dt=95363/140000000000000/0 df=780 of=5 ql=0/0 qs=N... b=10 ci=100607 nci=0 co=1414 ca=1353 + 7 c=31178 g=31178 pq=1/0 qp=0 dt=91536/0/0 df=547 of=4 ql=0/0 qs=.... b=10 ci=109819 nci=0 co=1115 ca=969 This file has one line per CPU, or eight for this 8-CPU system. The fields are as follows: @@ -188,14 +188,14 @@ o "ca" is the number of RCU callbacks that have been adopted by this Kernels compiled with CONFIG_RCU_BOOST=y display the following from /debug/rcu/rcu_preempt/rcudata: - 0!c=12865 g=12866 pq=1 qp=1 dt=83113/140000000000000/0 df=288 of=11 ql=0/0 qs=N... kt=0/O ktl=944 b=10 ci=60709 nci=0 co=748 ca=871 - 1 c=14407 g=14408 pq=1 qp=0 dt=100679/140000000000000/0 df=378 of=7 ql=0/119 qs=NRW. kt=0/W ktl=9b6 b=10 ci=109740 nci=0 co=589 ca=485 - 2 c=14407 g=14408 pq=1 qp=0 dt=105486/0/0 df=90 of=9 ql=0/89 qs=NRW. kt=0/W ktl=c0c b=10 ci=83113 nci=0 co=533 ca=490 - 3 c=14407 g=14408 pq=1 qp=0 dt=107138/0/0 df=142 of=8 ql=0/188 qs=NRW. kt=0/W ktl=b96 b=10 ci=121114 nci=0 co=426 ca=290 - 4 c=14405 g=14406 pq=1 qp=1 dt=50238/0/0 df=706 of=7 ql=0/0 qs=.... kt=0/W ktl=812 b=10 ci=34929 nci=0 co=643 ca=114 - 5!c=14168 g=14169 pq=1 qp=0 dt=45465/140000000000000/0 df=161 of=11 ql=0/0 qs=N... kt=0/O ktl=b4d b=10 ci=47712 nci=0 co=677 ca=722 - 6 c=14404 g=14405 pq=1 qp=0 dt=59454/0/0 df=94 of=6 ql=0/0 qs=.... kt=0/W ktl=e57 b=10 ci=55597 nci=0 co=701 ca=811 - 7 c=14407 g=14408 pq=1 qp=1 dt=68850/0/0 df=31 of=8 ql=0/0 qs=.... kt=0/W ktl=14bd b=10 ci=77475 nci=0 co=508 ca=1042 + 0!c=12865 g=12866 pq=1/0 qp=1 dt=83113/140000000000000/0 df=288 of=11 ql=0/0 qs=N... kt=0/O ktl=944 b=10 ci=60709 nci=0 co=748 ca=871 + 1 c=14407 g=14408 pq=1/0 qp=0 dt=100679/140000000000000/0 df=378 of=7 ql=0/119 qs=NRW. kt=0/W ktl=9b6 b=10 ci=109740 nci=0 co=589 ca=485 + 2 c=14407 g=14408 pq=1/0 qp=0 dt=105486/0/0 df=90 of=9 ql=0/89 qs=NRW. kt=0/W ktl=c0c b=10 ci=83113 nci=0 co=533 ca=490 + 3 c=14407 g=14408 pq=1/0 qp=0 dt=107138/0/0 df=142 of=8 ql=0/188 qs=NRW. kt=0/W ktl=b96 b=10 ci=121114 nci=0 co=426 ca=290 + 4 c=14405 g=14406 pq=1/0 qp=1 dt=50238/0/0 df=706 of=7 ql=0/0 qs=.... kt=0/W ktl=812 b=10 ci=34929 nci=0 co=643 ca=114 + 5!c=14168 g=14169 pq=1/0 qp=0 dt=45465/140000000000000/0 df=161 of=11 ql=0/0 qs=N... kt=0/O ktl=b4d b=10 ci=47712 nci=0 co=677 ca=722 + 6 c=14404 g=14405 pq=1/0 qp=0 dt=59454/0/0 df=94 of=6 ql=0/0 qs=.... kt=0/W ktl=e57 b=10 ci=55597 nci=0 co=701 ca=811 + 7 c=14407 g=14408 pq=1/0 qp=1 dt=68850/0/0 df=31 of=8 ql=0/0 qs=.... kt=0/W ktl=14bd b=10 ci=77475 nci=0 co=508 ca=1042 This is similar to the output discussed above, but contains the following additional fields: diff --git a/Documentation/acpi/enumeration.txt b/Documentation/acpi/enumeration.txt index b60d2ab6949..9b121a569ab 100644 --- a/Documentation/acpi/enumeration.txt +++ b/Documentation/acpi/enumeration.txt @@ -243,7 +243,7 @@ input driver: .owner = THIS_MODULE, .pm = &mpu3050_pm, .of_match_table = mpu3050_of_match, - .acpi_match_table ACPI_PTR(mpu3050_acpi_match), + .acpi_match_table = ACPI_PTR(mpu3050_acpi_match), }, .probe = mpu3050_probe, .remove = mpu3050_remove, diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt index d79b008e4a3..3f9f808b511 100644 --- a/Documentation/cachetlb.txt +++ b/Documentation/cachetlb.txt @@ -317,10 +317,10 @@ maps this page at its virtual address. about doing this. The idea is, first at flush_dcache_page() time, if - page->mapping->i_mmap is an empty tree and ->i_mmap_nonlinear - an empty list, just mark the architecture private page flag bit. - Later, in update_mmu_cache(), a check is made of this flag bit, - and if set the flush is done and the flag bit is cleared. + page->mapping->i_mmap is an empty tree, just mark the architecture + private page flag bit. Later, in update_mmu_cache(), a check is + made of this flag bit, and if set the flush is done and the flag + bit is cleared. IMPORTANT NOTE: It is often important, if you defer the flush, that the actual flush occurs on the same CPU diff --git a/Documentation/cgroups/00-INDEX b/Documentation/cgroups/00-INDEX index bc461b6425a..96ce071a363 100644 --- a/Documentation/cgroups/00-INDEX +++ b/Documentation/cgroups/00-INDEX @@ -24,3 +24,5 @@ net_prio.txt - Network priority cgroups details and usages. resource_counter.txt - Resource Counter API. +unified-hierarchy.txt + - Description the new/next cgroup interface. diff --git a/Documentation/cpu-freq/intel-pstate.txt b/Documentation/cpu-freq/intel-pstate.txt index 765d7fc0e69..655750743fb 100644 --- a/Documentation/cpu-freq/intel-pstate.txt +++ b/Documentation/cpu-freq/intel-pstate.txt @@ -37,6 +37,14 @@ controlling P state selection. These files have been added to no_turbo: limits the driver to selecting P states below the turbo frequency range. + turbo_pct: displays the percentage of the total performance that + is supported by hardware that is in the turbo range. This number + is independent of whether turbo has been disabled or not. + + num_pstates: displays the number of pstates that are supported + by hardware. This number is independent of whether turbo has + been disabled or not. + For contemporary Intel processors, the frequency is controlled by the processor itself and the P-states exposed to software are related to performance levels. The idea that frequency can be set to a single diff --git a/Documentation/devicetree/bindings/ata/ahci-platform.txt b/Documentation/devicetree/bindings/ata/ahci-platform.txt index 4ab09f2202d..c2340eeeb97 100644 --- a/Documentation/devicetree/bindings/ata/ahci-platform.txt +++ b/Documentation/devicetree/bindings/ata/ahci-platform.txt @@ -37,9 +37,10 @@ Required properties when using sub-nodes: Sub-nodes required properties: -- reg : the port number -- phys : reference to the SATA PHY node - +- reg : the port number +And at least one of the following properties: +- phys : reference to the SATA PHY node +- target-supply : regulator for SATA target power Examples: sata@ffe08000 { @@ -68,10 +69,12 @@ With sub-nodes: sata0: sata-port@0 { reg = <0>; phys = <&sata_phy 0>; + target-supply = <®_sata0>; }; sata1: sata-port@1 { reg = <1>; phys = <&sata_phy 1>; + target-supply = <®_sata1>;; }; }; diff --git a/Documentation/devicetree/bindings/devfreq/event/exynos-ppmu.txt b/Documentation/devicetree/bindings/devfreq/event/exynos-ppmu.txt new file mode 100644 index 00000000000..b54bf3a2ff5 --- /dev/null +++ b/Documentation/devicetree/bindings/devfreq/event/exynos-ppmu.txt @@ -0,0 +1,110 @@ + +* Samsung Exynos PPMU (Platform Performance Monitoring Unit) device + +The Samsung Exynos SoC has PPMU (Platform Performance Monitoring Unit) for +each IP. PPMU provides the primitive values to get performance data. These +PPMU events provide information of the SoC's behaviors so that you may +use to analyze system performance, to make behaviors visible and to count +usages of each IP (DMC, CPU, RIGHTBUS, LEFTBUS, CAM interface, LCD, G3D, MFC). +The Exynos PPMU driver uses the devfreq-event class to provide event data +to various devfreq devices. The devfreq devices would use the event data when +derterming the current state of each IP. + +Required properties: +- compatible: Should be "samsung,exynos-ppmu". +- reg: physical base address of each PPMU and length of memory mapped region. + +Optional properties: +- clock-names : the name of clock used by the PPMU, "ppmu" +- clocks : phandles for clock specified in "clock-names" property +- #clock-cells: should be 1. + +Example1 : PPMU nodes in exynos3250.dtsi are listed below. + + ppmu_dmc0: ppmu_dmc0@106a0000 { + compatible = "samsung,exynos-ppmu"; + reg = <0x106a0000 0x2000>; + status = "disabled"; + }; + + ppmu_dmc1: ppmu_dmc1@106b0000 { + compatible = "samsung,exynos-ppmu"; + reg = <0x106b0000 0x2000>; + status = "disabled"; + }; + + ppmu_cpu: ppmu_cpu@106c0000 { + compatible = "samsung,exynos-ppmu"; + reg = <0x106c0000 0x2000>; + status = "disabled"; + }; + + ppmu_rightbus: ppmu_rightbus@112a0000 { + compatible = "samsung,exynos-ppmu"; + reg = <0x112a0000 0x2000>; + clocks = <&cmu CLK_PPMURIGHT>; + clock-names = "ppmu"; + status = "disabled"; + }; + + ppmu_leftbus: ppmu_leftbus0@116a0000 { + compatible = "samsung,exynos-ppmu"; + reg = <0x116a0000 0x2000>; + clocks = <&cmu CLK_PPMULEFT>; + clock-names = "ppmu"; + status = "disabled"; + }; + +Example2 : Events of each PPMU node in exynos3250-rinato.dts are listed below. + + &ppmu_dmc0 { + status = "okay"; + + events { + ppmu_dmc0_3: ppmu-event3-dmc0 { + event-name = "ppmu-event3-dmc0"; + }; + + ppmu_dmc0_2: ppmu-event2-dmc0 { + event-name = "ppmu-event2-dmc0"; + }; + + ppmu_dmc0_1: ppmu-event1-dmc0 { + event-name = "ppmu-event1-dmc0"; + }; + + ppmu_dmc0_0: ppmu-event0-dmc0 { + event-name = "ppmu-event0-dmc0"; + }; + }; + }; + + &ppmu_dmc1 { + status = "okay"; + + events { + ppmu_dmc1_3: ppmu-event3-dmc1 { + event-name = "ppmu-event3-dmc1"; + }; + }; + }; + + &ppmu_leftbus { + status = "okay"; + + events { + ppmu_leftbus_3: ppmu-event3-leftbus { + event-name = "ppmu-event3-leftbus"; + }; + }; + }; + + &ppmu_rightbus { + status = "okay"; + + events { + ppmu_rightbus_3: ppmu-event3-rightbus { + event-name = "ppmu-event3-rightbus"; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/mfd/max77686.txt b/Documentation/devicetree/bindings/mfd/max77686.txt index 75fdfaf4183..e39f0bc1f55 100644 --- a/Documentation/devicetree/bindings/mfd/max77686.txt +++ b/Documentation/devicetree/bindings/mfd/max77686.txt @@ -39,6 +39,12 @@ to get matched with their hardware counterparts as follow: -BUCKn : 1-4. Use standard regulator bindings for it ('regulator-off-in-suspend'). + LDO20, LDO21, LDO22, BUCK8 and BUCK9 can be configured to GPIO enable + control. To turn this feature on this property must be added to the regulator + sub-node: + - maxim,ena-gpios : one GPIO specifier enable control (the gpio + flags are actually ignored and always + ACTIVE_HIGH is used) Example: @@ -65,4 +71,12 @@ Example: regulator-always-on; regulator-boot-on; }; + + buck9_reg { + regulator-compatible = "BUCK9"; + regulator-name = "CAM_ISP_CORE_1.2V"; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1200000>; + maxim,ena-gpios = <&gpm0 3 GPIO_ACTIVE_HIGH>; + }; } diff --git a/Documentation/devicetree/bindings/pci/versatile.txt b/Documentation/devicetree/bindings/pci/versatile.txt new file mode 100644 index 00000000000..ebd1e7d0403 --- /dev/null +++ b/Documentation/devicetree/bindings/pci/versatile.txt @@ -0,0 +1,59 @@ +* ARM Versatile Platform Baseboard PCI interface + +PCI host controller found on the ARM Versatile PB board's FPGA. + +Required properties: +- compatible: should contain "arm,versatile-pci" to identify the Versatile PCI + controller. +- reg: base addresses and lengths of the pci controller. There must be 3 + entries: + - Versatile-specific registers + - Self Config space + - Config space +- #address-cells: set to <3> +- #size-cells: set to <2> +- device_type: set to "pci" +- bus-range: set to <0 0xff> +- ranges: ranges for the PCI memory and I/O regions +- #interrupt-cells: set to <1> +- interrupt-map-mask and interrupt-map: standard PCI properties to define + the mapping of the PCI interface to interrupt numbers. + +Example: + +pci-controller@10001000 { + compatible = "arm,versatile-pci"; + device_type = "pci"; + reg = <0x10001000 0x1000 + 0x41000000 0x10000 + 0x42000000 0x100000>; + bus-range = <0 0xff>; + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + + ranges = <0x01000000 0 0x00000000 0x43000000 0 0x00010000 /* downstream I/O */ + 0x02000000 0 0x50000000 0x50000000 0 0x10000000 /* non-prefetchable memory */ + 0x42000000 0 0x60000000 0x60000000 0 0x10000000>; /* prefetchable memory */ + + interrupt-map-mask = <0x1800 0 0 7>; + interrupt-map = <0x1800 0 0 1 &sic 28 + 0x1800 0 0 2 &sic 29 + 0x1800 0 0 3 &sic 30 + 0x1800 0 0 4 &sic 27 + + 0x1000 0 0 1 &sic 27 + 0x1000 0 0 2 &sic 28 + 0x1000 0 0 3 &sic 29 + 0x1000 0 0 4 &sic 30 + + 0x0800 0 0 1 &sic 30 + 0x0800 0 0 2 &sic 27 + 0x0800 0 0 3 &sic 28 + 0x0800 0 0 4 &sic 29 + + 0x0000 0 0 1 &sic 29 + 0x0000 0 0 2 &sic 30 + 0x0000 0 0 3 &sic 27 + 0x0000 0 0 4 &sic 28>; +}; diff --git a/Documentation/devicetree/bindings/regulator/da9211.txt b/Documentation/devicetree/bindings/regulator/da9211.txt index 240019a82f9..eb618907c7d 100644 --- a/Documentation/devicetree/bindings/regulator/da9211.txt +++ b/Documentation/devicetree/bindings/regulator/da9211.txt @@ -11,6 +11,7 @@ Required properties: BUCKA and BUCKB. Optional properties: +- enable-gpios: platform gpio for control of BUCKA/BUCKB. - Any optional property defined in regulator.txt Example 1) DA9211 @@ -27,6 +28,7 @@ Example 1) DA9211 regulator-max-microvolt = <1570000>; regulator-min-microamp = <2000000>; regulator-max-microamp = <5000000>; + enable-gpios = <&gpio 27 0>; }; BUCKB { regulator-name = "VBUCKB"; @@ -34,11 +36,12 @@ Example 1) DA9211 regulator-max-microvolt = <1570000>; regulator-min-microamp = <2000000>; regulator-max-microamp = <5000000>; + enable-gpios = <&gpio 17 0>; }; }; }; -Example 2) DA92113 +Example 2) DA9213 pmic: da9213@68 { compatible = "dlg,da9213"; reg = <0x68>; @@ -51,6 +54,7 @@ Example 2) DA92113 regulator-max-microvolt = <1570000>; regulator-min-microamp = <3000000>; regulator-max-microamp = <6000000>; + enable-gpios = <&gpio 27 0>; }; BUCKB { regulator-name = "VBUCKB"; @@ -58,6 +62,7 @@ Example 2) DA92113 regulator-max-microvolt = <1570000>; regulator-min-microamp = <3000000>; regulator-max-microamp = <6000000>; + enable-gpios = <&gpio 17 0>; }; }; }; diff --git a/Documentation/devicetree/bindings/regulator/isl9305.txt b/Documentation/devicetree/bindings/regulator/isl9305.txt index a626fc1bbf0..d6e7c9ec941 100644 --- a/Documentation/devicetree/bindings/regulator/isl9305.txt +++ b/Documentation/devicetree/bindings/regulator/isl9305.txt @@ -2,7 +2,7 @@ Intersil ISL9305/ISL9305H voltage regulator Required properties: -- compatible: "isl,isl9305" or "isl,isl9305h" +- compatible: "isil,isl9305" or "isil,isl9305h" - reg: I2C slave address, usually 0x68. - regulators: A node that houses a sub-node for each regulator within the device. Each sub-node is identified using the node's name, with valid @@ -19,7 +19,7 @@ Optional properties: Example pmic: isl9305@68 { - compatible = "isl,isl9305"; + compatible = "isil,isl9305"; reg = <0x68>; VINDCD1-supply = <&system_power>; diff --git a/Documentation/devicetree/bindings/regulator/mt6397-regulator.txt b/Documentation/devicetree/bindings/regulator/mt6397-regulator.txt new file mode 100644 index 00000000000..a42b1d6e986 --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/mt6397-regulator.txt @@ -0,0 +1,217 @@ +Mediatek MT6397 Regulator Driver + +Required properties: +- compatible: "mediatek,mt6397-regulator" +- mt6397regulator: List of regulators provided by this controller. It is named + according to its regulator type, buck_<name> and ldo_<name>. + The definition for each of these nodes is defined using the standard binding + for regulators at Documentation/devicetree/bindings/regulator/regulator.txt. + +The valid names for regulators are:: +BUCK: + buck_vpca15, buck_vpca7, buck_vsramca15, buck_vsramca7, buck_vcore, buck_vgpu, + buck_vdrm, buck_vio18 +LDO: + ldo_vtcxo, ldo_va28, ldo_vcama, ldo_vio28, ldo_vusb, ldo_vmc, ldo_vmch, + ldo_vemc3v3, ldo_vgp1, ldo_vgp2, ldo_vgp3, ldo_vgp4, ldo_vgp5, ldo_vgp6, + ldo_vibr + +Example: + pmic { + compatible = "mediatek,mt6397"; + + mt6397regulator: mt6397regulator { + compatible = "mediatek,mt6397-regulator"; + + mt6397_vpca15_reg: buck_vpca15 { + regulator-compatible = "buck_vpca15"; + regulator-name = "vpca15"; + regulator-min-microvolt = < 850000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <12500>; + regulator-enable-ramp-delay = <200>; + }; + + mt6397_vpca7_reg: buck_vpca7 { + regulator-compatible = "buck_vpca7"; + regulator-name = "vpca7"; + regulator-min-microvolt = < 850000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <12500>; + regulator-enable-ramp-delay = <115>; + }; + + mt6397_vsramca15_reg: buck_vsramca15 { + regulator-compatible = "buck_vsramca15"; + regulator-name = "vsramca15"; + regulator-min-microvolt = < 850000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <12500>; + regulator-enable-ramp-delay = <115>; + + }; + + mt6397_vsramca7_reg: buck_vsramca7 { + regulator-compatible = "buck_vsramca7"; + regulator-name = "vsramca7"; + regulator-min-microvolt = < 850000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <12500>; + regulator-enable-ramp-delay = <115>; + + }; + + mt6397_vcore_reg: buck_vcore { + regulator-compatible = "buck_vcore"; + regulator-name = "vcore"; + regulator-min-microvolt = < 850000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <12500>; + regulator-enable-ramp-delay = <115>; + }; + + mt6397_vgpu_reg: buck_vgpu { + regulator-compatible = "buck_vgpu"; + regulator-name = "vgpu"; + regulator-min-microvolt = < 700000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <12500>; + regulator-enable-ramp-delay = <115>; + }; + + mt6397_vdrm_reg: buck_vdrm { + regulator-compatible = "buck_vdrm"; + regulator-name = "vdrm"; + regulator-min-microvolt = < 800000>; + regulator-max-microvolt = <1400000>; + regulator-ramp-delay = <12500>; + regulator-enable-ramp-delay = <500>; + }; + + mt6397_vio18_reg: buck_vio18 { + regulator-compatible = "buck_vio18"; + regulator-name = "vio18"; + regulator-min-microvolt = <1500000>; + regulator-max-microvolt = <2120000>; + regulator-ramp-delay = <12500>; + regulator-enable-ramp-delay = <500>; + }; + + mt6397_vtcxo_reg: ldo_vtcxo { + regulator-compatible = "ldo_vtcxo"; + regulator-name = "vtcxo"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + regulator-enable-ramp-delay = <90>; + }; + + mt6397_va28_reg: ldo_va28 { + regulator-compatible = "ldo_va28"; + regulator-name = "va28"; + /* fixed output 2.8 V */ + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vcama_reg: ldo_vcama { + regulator-compatible = "ldo_vcama"; + regulator-name = "vcama"; + regulator-min-microvolt = <1500000>; + regulator-max-microvolt = <2800000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vio28_reg: ldo_vio28 { + regulator-compatible = "ldo_vio28"; + regulator-name = "vio28"; + /* fixed output 2.8 V */ + regulator-enable-ramp-delay = <240>; + }; + + mt6397_usb_reg: ldo_vusb { + regulator-compatible = "ldo_vusb"; + regulator-name = "vusb"; + /* fixed output 3.3 V */ + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vmc_reg: ldo_vmc { + regulator-compatible = "ldo_vmc"; + regulator-name = "vmc"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vmch_reg: ldo_vmch { + regulator-compatible = "ldo_vmch"; + regulator-name = "vmch"; + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vemc_3v3_reg: ldo_vemc3v3 { + regulator-compatible = "ldo_vemc3v3"; + regulator-name = "vemc_3v3"; + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vgp1_reg: ldo_vgp1 { + regulator-compatible = "ldo_vgp1"; + regulator-name = "vcamd"; + regulator-min-microvolt = <1220000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <240>; + }; + + mt6397_vgp2_reg: ldo_vgp2 { + egulator-compatible = "ldo_vgp2"; + regulator-name = "vcamio"; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vgp3_reg: ldo_vgp3 { + regulator-compatible = "ldo_vgp3"; + regulator-name = "vcamaf"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vgp4_reg: ldo_vgp4 { + regulator-compatible = "ldo_vgp4"; + regulator-name = "vgp4"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vgp5_reg: ldo_vgp5 { + regulator-compatible = "ldo_vgp5"; + regulator-name = "vgp5"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3000000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vgp6_reg: ldo_vgp6 { + regulator-compatible = "ldo_vgp6"; + regulator-name = "vgp6"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vibr_reg: ldo_vibr { + regulator-compatible = "ldo_vibr"; + regulator-name = "vibr"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/regulator/pfuze100.txt b/Documentation/devicetree/bindings/regulator/pfuze100.txt index 34ef5d16d0f..9b40db88f63 100644 --- a/Documentation/devicetree/bindings/regulator/pfuze100.txt +++ b/Documentation/devicetree/bindings/regulator/pfuze100.txt @@ -1,7 +1,7 @@ PFUZE100 family of regulators Required properties: -- compatible: "fsl,pfuze100" or "fsl,pfuze200" +- compatible: "fsl,pfuze100", "fsl,pfuze200", "fsl,pfuze3000" - reg: I2C slave address Required child node: @@ -14,6 +14,8 @@ Required child node: sw1ab,sw1c,sw2,sw3a,sw3b,sw4,swbst,vsnvs,vrefddr,vgen1~vgen6 --PFUZE200 sw1ab,sw2,sw3a,sw3b,swbst,vsnvs,vrefddr,vgen1~vgen6 + --PFUZE3000 + sw1a,sw1b,sw2,sw3,swbst,vsnvs,vrefddr,vldo1,vldo2,vccsd,v33,vldo3,vldo4 Each regulator is defined using the standard binding for regulators. @@ -205,3 +207,93 @@ Example 2: PFUZE200 }; }; }; + +Example 3: PFUZE3000 + + pmic: pfuze3000@08 { + compatible = "fsl,pfuze3000"; + reg = <0x08>; + + regulators { + sw1a_reg: sw1a { + regulator-min-microvolt = <700000>; + regulator-max-microvolt = <1475000>; + regulator-boot-on; + regulator-always-on; + regulator-ramp-delay = <6250>; + }; + /* use sw1c_reg to align with pfuze100/pfuze200 */ + sw1c_reg: sw1b { + regulator-min-microvolt = <700000>; + regulator-max-microvolt = <1475000>; + regulator-boot-on; + regulator-always-on; + regulator-ramp-delay = <6250>; + }; + + sw2_reg: sw2 { + regulator-min-microvolt = <2500000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + + sw3a_reg: sw3 { + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <1650000>; + regulator-boot-on; + regulator-always-on; + }; + + swbst_reg: swbst { + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5150000>; + }; + + snvs_reg: vsnvs { + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <3000000>; + regulator-boot-on; + regulator-always-on; + }; + + vref_reg: vrefddr { + regulator-boot-on; + regulator-always-on; + }; + + vgen1_reg: vldo1 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vgen2_reg: vldo2 { + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <1550000>; + }; + + vgen3_reg: vccsd { + regulator-min-microvolt = <2850000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vgen4_reg: v33 { + regulator-min-microvolt = <2850000>; + regulator-max-microvolt = <3300000>; + }; + + vgen5_reg: vldo3 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vgen6_reg: vldo4 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/spi/sh-msiof.txt b/Documentation/devicetree/bindings/spi/sh-msiof.txt index d11c3721e7c..4c388bb2f0a 100644 --- a/Documentation/devicetree/bindings/spi/sh-msiof.txt +++ b/Documentation/devicetree/bindings/spi/sh-msiof.txt @@ -30,6 +30,22 @@ Optional properties: specifiers, one for transmission, and one for reception. - dma-names : Must contain a list of two DMA names, "tx" and "rx". +- renesas,dtdl : delay sync signal (setup) in transmit mode. + Must contain one of the following values: + 0 (no bit delay) + 50 (0.5-clock-cycle delay) + 100 (1-clock-cycle delay) + 150 (1.5-clock-cycle delay) + 200 (2-clock-cycle delay) + +- renesas,syncdl : delay sync signal (hold) in transmit mode. + Must contain one of the following values: + 0 (no bit delay) + 50 (0.5-clock-cycle delay) + 100 (1-clock-cycle delay) + 150 (1.5-clock-cycle delay) + 200 (2-clock-cycle delay) + 300 (3-clock-cycle delay) Optional properties, deprecated for soctype-specific bindings: - renesas,tx-fifo-size : Overrides the default tx fifo size given in words diff --git a/Documentation/devicetree/bindings/spi/spi-sirf.txt b/Documentation/devicetree/bindings/spi/spi-sirf.txt new file mode 100644 index 00000000000..4c7adb8f777 --- /dev/null +++ b/Documentation/devicetree/bindings/spi/spi-sirf.txt @@ -0,0 +1,41 @@ +* CSR SiRFprimaII Serial Peripheral Interface + +Required properties: +- compatible : Should be "sirf,prima2-spi" +- reg : Offset and length of the register set for the device +- interrupts : Should contain SPI interrupt +- resets: phandle to the reset controller asserting this device in + reset + See ../reset/reset.txt for details. +- dmas : Must contain an entry for each entry in clock-names. + See ../dma/dma.txt for details. +- dma-names : Must include the following entries: + - rx + - tx +- clocks : Must contain an entry for each entry in clock-names. + See ../clocks/clock-bindings.txt for details. + +- #address-cells: Number of cells required to define a chip select + address on the SPI bus. Should be set to 1. +- #size-cells: Should be zero. + +Optional properties: +- spi-max-frequency: Specifies maximum SPI clock frequency, + Units - Hz. Definition as per + Documentation/devicetree/bindings/spi/spi-bus.txt +- cs-gpios: should specify GPIOs used for chipselects. + +Example: + +spi0: spi@b00d0000 { + compatible = "sirf,prima2-spi"; + reg = <0xb00d0000 0x10000>; + interrupts = <15>; + dmas = <&dmac1 9>, + <&dmac1 4>; + dma-names = "rx", "tx"; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clks 19>; + resets = <&rstc 26>; +}; diff --git a/Documentation/devicetree/bindings/spi/spi-st-ssc.txt b/Documentation/devicetree/bindings/spi/spi-st-ssc.txt new file mode 100644 index 00000000000..fe54959ec95 --- /dev/null +++ b/Documentation/devicetree/bindings/spi/spi-st-ssc.txt @@ -0,0 +1,40 @@ +STMicroelectronics SSC (SPI) Controller +--------------------------------------- + +Required properties: +- compatible : "st,comms-ssc4-spi" +- reg : Offset and length of the device's register set +- interrupts : The interrupt specifier +- clock-names : Must contain "ssc" +- clocks : Must contain an entry for each name in clock-names + See ../clk/* +- pinctrl-names : Uses "default", can use "sleep" if provided + See ../pinctrl/pinctrl-binding.txt + +Optional properties: +- cs-gpios : List of GPIO chip selects + See ../spi/spi-bus.txt + +Child nodes represent devices on the SPI bus + See ../spi/spi-bus.txt + +Example: + spi@9840000 { + compatible = "st,comms-ssc4-spi"; + reg = <0x9840000 0x110>; + interrupts = <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk_s_c0_flexgen CLK_EXT2F_A9>; + clock-names = "ssc"; + pinctrl-0 = <&pinctrl_spi0_default>; + pinctrl-names = "default"; + cs-gpios = <&pio17 5 0>; + #address-cells = <1>; + #size-cells = <0>; + + st95hf@0{ + compatible = "st,st95hf"; + reg = <0>; + spi-max-frequency = <1000000>; + interrupts = <2 IRQ_TYPE_EDGE_FALLING>; + }; + }; diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt index 1b805a0efbb..f6d9c99103a 100644 --- a/Documentation/filesystems/fiemap.txt +++ b/Documentation/filesystems/fiemap.txt @@ -196,7 +196,8 @@ struct fiemap_extent_info { }; It is intended that the file system should not need to access any of this -structure directly. +structure directly. Filesystem handlers should be tolerant to signals and return +EINTR once fatal signal received. Flag checking should be done at the beginning of the ->fiemap callback via the diff --git a/Documentation/filesystems/inotify.txt b/Documentation/filesystems/inotify.txt index cfd02712b83..51f61db787f 100644 --- a/Documentation/filesystems/inotify.txt +++ b/Documentation/filesystems/inotify.txt @@ -4,201 +4,10 @@ Document started 15 Mar 2005 by Robert Love <rml@novell.com> +Document updated 4 Jan 2015 by Zhang Zhen <zhenzhang.zhang@huawei.com> + --Deleted obsoleted interface, just refer to manpages for user interface. - -(i) User Interface - -Inotify is controlled by a set of three system calls and normal file I/O on a -returned file descriptor. - -First step in using inotify is to initialise an inotify instance: - - int fd = inotify_init (); - -Each instance is associated with a unique, ordered queue. - -Change events are managed by "watches". A watch is an (object,mask) pair where -the object is a file or directory and the mask is a bit mask of one or more -inotify events that the application wishes to receive. See <linux/inotify.h> -for valid events. A watch is referenced by a watch descriptor, or wd. - -Watches are added via a path to the file. - -Watches on a directory will return events on any files inside of the directory. - -Adding a watch is simple: - - int wd = inotify_add_watch (fd, path, mask); - -Where "fd" is the return value from inotify_init(), path is the path to the -object to watch, and mask is the watch mask (see <linux/inotify.h>). - -You can update an existing watch in the same manner, by passing in a new mask. - -An existing watch is removed via - - int ret = inotify_rm_watch (fd, wd); - -Events are provided in the form of an inotify_event structure that is read(2) -from a given inotify instance. The filename is of dynamic length and follows -the struct. It is of size len. The filename is padded with null bytes to -ensure proper alignment. This padding is reflected in len. - -You can slurp multiple events by passing a large buffer, for example - - size_t len = read (fd, buf, BUF_LEN); - -Where "buf" is a pointer to an array of "inotify_event" structures at least -BUF_LEN bytes in size. The above example will return as many events as are -available and fit in BUF_LEN. - -Each inotify instance fd is also select()- and poll()-able. - -You can find the size of the current event queue via the standard FIONREAD -ioctl on the fd returned by inotify_init(). - -All watches are destroyed and cleaned up on close. - - -(ii) - -Prototypes: - - int inotify_init (void); - int inotify_add_watch (int fd, const char *path, __u32 mask); - int inotify_rm_watch (int fd, __u32 mask); - - -(iii) Kernel Interface - -Inotify's kernel API consists a set of functions for managing watches and an -event callback. - -To use the kernel API, you must first initialize an inotify instance with a set -of inotify_operations. You are given an opaque inotify_handle, which you use -for any further calls to inotify. - - struct inotify_handle *ih = inotify_init(my_event_handler); - -You must provide a function for processing events and a function for destroying -the inotify watch. - - void handle_event(struct inotify_watch *watch, u32 wd, u32 mask, - u32 cookie, const char *name, struct inode *inode) - - watch - the pointer to the inotify_watch that triggered this call - wd - the watch descriptor - mask - describes the event that occurred - cookie - an identifier for synchronizing events - name - the dentry name for affected files in a directory-based event - inode - the affected inode in a directory-based event - - void destroy_watch(struct inotify_watch *watch) - -You may add watches by providing a pre-allocated and initialized inotify_watch -structure and specifying the inode to watch along with an inotify event mask. -You must pin the inode during the call. You will likely wish to embed the -inotify_watch structure in a structure of your own which contains other -information about the watch. Once you add an inotify watch, it is immediately -subject to removal depending on filesystem events. You must grab a reference if -you depend on the watch hanging around after the call. - - inotify_init_watch(&my_watch->iwatch); - inotify_get_watch(&my_watch->iwatch); // optional - s32 wd = inotify_add_watch(ih, &my_watch->iwatch, inode, mask); - inotify_put_watch(&my_watch->iwatch); // optional - -You may use the watch descriptor (wd) or the address of the inotify_watch for -other inotify operations. You must not directly read or manipulate data in the -inotify_watch. Additionally, you must not call inotify_add_watch() more than -once for a given inotify_watch structure, unless you have first called either -inotify_rm_watch() or inotify_rm_wd(). - -To determine if you have already registered a watch for a given inode, you may -call inotify_find_watch(), which gives you both the wd and the watch pointer for -the inotify_watch, or an error if the watch does not exist. - - wd = inotify_find_watch(ih, inode, &watchp); - -You may use container_of() on the watch pointer to access your own data -associated with a given watch. When an existing watch is found, -inotify_find_watch() bumps the refcount before releasing its locks. You must -put that reference with: - - put_inotify_watch(watchp); - -Call inotify_find_update_watch() to update the event mask for an existing watch. -inotify_find_update_watch() returns the wd of the updated watch, or an error if -the watch does not exist. - - wd = inotify_find_update_watch(ih, inode, mask); - -An existing watch may be removed by calling either inotify_rm_watch() or -inotify_rm_wd(). - - int ret = inotify_rm_watch(ih, &my_watch->iwatch); - int ret = inotify_rm_wd(ih, wd); - -A watch may be removed while executing your event handler with the following: - - inotify_remove_watch_locked(ih, iwatch); - -Call inotify_destroy() to remove all watches from your inotify instance and -release it. If there are no outstanding references, inotify_destroy() will call -your destroy_watch op for each watch. - - inotify_destroy(ih); - -When inotify removes a watch, it sends an IN_IGNORED event to your callback. -You may use this event as an indication to free the watch memory. Note that -inotify may remove a watch due to filesystem events, as well as by your request. -If you use IN_ONESHOT, inotify will remove the watch after the first event, at -which point you may call the final inotify_put_watch. - -(iv) Kernel Interface Prototypes - - struct inotify_handle *inotify_init(struct inotify_operations *ops); - - inotify_init_watch(struct inotify_watch *watch); - - s32 inotify_add_watch(struct inotify_handle *ih, - struct inotify_watch *watch, - struct inode *inode, u32 mask); - - s32 inotify_find_watch(struct inotify_handle *ih, struct inode *inode, - struct inotify_watch **watchp); - - s32 inotify_find_update_watch(struct inotify_handle *ih, - struct inode *inode, u32 mask); - - int inotify_rm_wd(struct inotify_handle *ih, u32 wd); - - int inotify_rm_watch(struct inotify_handle *ih, - struct inotify_watch *watch); - - void inotify_remove_watch_locked(struct inotify_handle *ih, - struct inotify_watch *watch); - - void inotify_destroy(struct inotify_handle *ih); - - void get_inotify_watch(struct inotify_watch *watch); - void put_inotify_watch(struct inotify_watch *watch); - - -(v) Internal Kernel Implementation - -Each inotify instance is represented by an inotify_handle structure. -Inotify's userspace consumers also have an inotify_device which is -associated with the inotify_handle, and on which events are queued. - -Each watch is associated with an inotify_watch structure. Watches are chained -off of each associated inotify_handle and each associated inode. - -See fs/notify/inotify/inotify_fsnotify.c and fs/notify/inotify/inotify_user.c -for the locking and lifetime rules. - - -(vi) Rationale +(i) Rationale Q: What is the design decision behind not tying the watch to the open fd of the watched object? diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt index 7618a287aa4..28f8c08201e 100644 --- a/Documentation/filesystems/ocfs2.txt +++ b/Documentation/filesystems/ocfs2.txt @@ -100,3 +100,7 @@ coherency=full (*) Disallow concurrent O_DIRECT writes, cluster inode coherency=buffered Allow concurrent O_DIRECT writes without EX lock among nodes, which gains high performance at risk of getting stale data on other nodes. +journal_async_commit Commit block can be written to disk without waiting + for descriptor blocks. If enabled older kernels cannot + mount the device. This will enable 'journal_checksum' + internally. diff --git a/Documentation/filesystems/xfs.txt b/Documentation/filesystems/xfs.txt index 5be51fd888b..0bfafe10835 100644 --- a/Documentation/filesystems/xfs.txt +++ b/Documentation/filesystems/xfs.txt @@ -287,9 +287,9 @@ The following sysctls are available for the XFS filesystem: XFS_ERRLEVEL_LOW: 1 XFS_ERRLEVEL_HIGH: 5 - fs.xfs.panic_mask (Min: 0 Default: 0 Max: 127) + fs.xfs.panic_mask (Min: 0 Default: 0 Max: 255) Causes certain error conditions to call BUG(). Value is a bitmask; - AND together the tags which represent errors which should cause panics: + OR together the tags which represent errors which should cause panics: XFS_NO_PTAG 0 XFS_PTAG_IFLUSH 0x00000001 @@ -299,6 +299,7 @@ The following sysctls are available for the XFS filesystem: XFS_PTAG_SHUTDOWN_CORRUPT 0x00000010 XFS_PTAG_SHUTDOWN_IOERROR 0x00000020 XFS_PTAG_SHUTDOWN_LOGERROR 0x00000040 + XFS_PTAG_FSBLOCK_ZERO 0x00000080 This option is intended for debugging only. @@ -348,16 +349,13 @@ The following sysctls are available for the XFS filesystem: Deprecated Sysctls ================== - fs.xfs.xfsbufd_centisecs (Min: 50 Default: 100 Max: 3000) - Dirty metadata is now tracked by the log subsystem and - flushing is driven by log space and idling demands. The - xfsbufd no longer exists, so this syctl does nothing. +None at present. - Due for removal in 3.14. - fs.xfs.age_buffer_centisecs (Min: 100 Default: 1500 Max: 720000) - Dirty metadata is now tracked by the log subsystem and - flushing is driven by log space and idling demands. The - xfsbufd no longer exists, so this syctl does nothing. +Removed Sysctls +=============== - Due for removal in 3.14. + Name Removed + ---- ------- + fs.xfs.xfsbufd_centisec v3.20 + fs.xfs.age_buffer_centisecs v3.20 diff --git a/Documentation/futex-requeue-pi.txt b/Documentation/futex-requeue-pi.txt index 31b16610c41..77b36f59d16 100644 --- a/Documentation/futex-requeue-pi.txt +++ b/Documentation/futex-requeue-pi.txt @@ -98,7 +98,7 @@ rt_mutex_start_proxy_lock() and rt_mutex_finish_proxy_lock(), which allow the requeue code to acquire an uncontended rt_mutex on behalf of the waiter and to enqueue the waiter on a contended rt_mutex. Two new system calls provide the kernel<->user interface to -requeue_pi: FUTEX_WAIT_REQUEUE_PI and FUTEX_REQUEUE_CMP_PI. +requeue_pi: FUTEX_WAIT_REQUEUE_PI and FUTEX_CMP_REQUEUE_PI. FUTEX_WAIT_REQUEUE_PI is called by the waiter (pthread_cond_wait() and pthread_cond_timedwait()) to block on the initial futex and wait @@ -107,7 +107,7 @@ result of a high-speed collision between futex_wait() and futex_lock_pi(), with some extra logic to check for the additional wake-up scenarios. -FUTEX_REQUEUE_CMP_PI is called by the waker +FUTEX_CMP_REQUEUE_PI is called by the waker (pthread_cond_broadcast() and pthread_cond_signal()) to requeue and possibly wake the waiting tasks. Internally, this system call is still handled by futex_requeue (by passing requeue_pi=1). Before @@ -120,12 +120,12 @@ task as a waiter on the underlying rt_mutex. It is possible that the lock can be acquired at this stage as well, if so, the next waiter is woken to finish the acquisition of the lock. -FUTEX_REQUEUE_PI accepts nr_wake and nr_requeue as arguments, but +FUTEX_CMP_REQUEUE_PI accepts nr_wake and nr_requeue as arguments, but their sum is all that really matters. futex_requeue() will wake or requeue up to nr_wake + nr_requeue tasks. It will wake only as many tasks as it can acquire the lock for, which in the majority of cases should be 0 as good programming practice dictates that the caller of either pthread_cond_broadcast() or pthread_cond_signal() acquire the -mutex prior to making the call. FUTEX_REQUEUE_PI requires that +mutex prior to making the call. FUTEX_CMP_REQUEUE_PI requires that nr_wake=1. nr_requeue should be INT_MAX for broadcast and 0 for signal. diff --git a/Documentation/hwmon/ina2xx b/Documentation/hwmon/ina2xx index 4223c2d3b50..cfd31d94c87 100644 --- a/Documentation/hwmon/ina2xx +++ b/Documentation/hwmon/ina2xx @@ -26,6 +26,12 @@ Supported chips: Datasheet: Publicly available at the Texas Instruments website http://www.ti.com/ + * Texas Instruments INA231 + Prefix: 'ina231' + Addresses: I2C 0x40 - 0x4f + Datasheet: Publicly available at the Texas Instruments website + http://www.ti.com/ + Author: Lothar Felten <l-felten@ti.com> Description @@ -41,9 +47,18 @@ interface. The INA220 monitors both shunt drop and supply voltage. The INA226 is a current shunt and power monitor with an I2C interface. The INA226 monitors both a shunt voltage drop and bus supply voltage. -The INA230 is a high or low side current shunt and power monitor with an I2C -interface. The INA230 monitors both a shunt voltage drop and bus supply voltage. +INA230 and INA231 are high or low side current shunt and power monitors +with an I2C interface. The chips monitor both a shunt voltage drop and +bus supply voltage. -The shunt value in micro-ohms can be set via platform data or device tree. -Please refer to the Documentation/devicetree/bindings/i2c/ina2xx.txt for bindings +The shunt value in micro-ohms can be set via platform data or device tree at +compile-time or via the shunt_resistor attribute in sysfs at run-time. Please +refer to the Documentation/devicetree/bindings/i2c/ina2xx.txt for bindings if the device tree is used. + +Additionally ina226 supports update_interval attribute as described in +Documentation/hwmon/sysfs-interface. Internally the interval is the sum of +bus and shunt voltage conversion times multiplied by the averaging rate. We +don't touch the conversion times and only modify the number of averages. The +lower limit of the update_interval is 2 ms, the upper limit is 2253 ms. +The actual programmed interval may vary from the desired value. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 2089c051f23..512a35929f9 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1470,6 +1470,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted. no_hwp Do not enable hardware P state control (HWP) if available. + hwp_only + Only load intel_pstate on systems which support + hardware P state control (HWP) if available. intremap= [X86-64, Intel-IOMMU] on enable Interrupt Remapping (default) diff --git a/Documentation/locking/lockdep-design.txt b/Documentation/locking/lockdep-design.txt index 5dbc99c04f6..5001280e9d8 100644 --- a/Documentation/locking/lockdep-design.txt +++ b/Documentation/locking/lockdep-design.txt @@ -34,7 +34,7 @@ The validator tracks lock-class usage history into 4n + 1 separate state bits: - 'ever held with STATE enabled' - 'ever held as readlock with STATE enabled' -Where STATE can be either one of (kernel/lockdep_states.h) +Where STATE can be either one of (kernel/locking/lockdep_states.h) - hardirq - softirq - reclaim_fs diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 70a09f8a038..ca2387ef27a 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -269,6 +269,50 @@ And there are a number of things that _must_ or _must_not_ be assumed: STORE *(A + 4) = Y; STORE *A = X; STORE {*A, *(A + 4) } = {X, Y}; +And there are anti-guarantees: + + (*) These guarantees do not apply to bitfields, because compilers often + generate code to modify these using non-atomic read-modify-write + sequences. Do not attempt to use bitfields to synchronize parallel + algorithms. + + (*) Even in cases where bitfields are protected by locks, all fields + in a given bitfield must be protected by one lock. If two fields + in a given bitfield are protected by different locks, the compiler's + non-atomic read-modify-write sequences can cause an update to one + field to corrupt the value of an adjacent field. + + (*) These guarantees apply only to properly aligned and sized scalar + variables. "Properly sized" currently means variables that are + the same size as "char", "short", "int" and "long". "Properly + aligned" means the natural alignment, thus no constraints for + "char", two-byte alignment for "short", four-byte alignment for + "int", and either four-byte or eight-byte alignment for "long", + on 32-bit and 64-bit systems, respectively. Note that these + guarantees were introduced into the C11 standard, so beware when + using older pre-C11 compilers (for example, gcc 4.6). The portion + of the standard containing this guarantee is Section 3.14, which + defines "memory location" as follows: + + memory location + either an object of scalar type, or a maximal sequence + of adjacent bit-fields all having nonzero width + + NOTE 1: Two threads of execution can update and access + separate memory locations without interfering with + each other. + + NOTE 2: A bit-field and an adjacent non-bit-field member + are in separate memory locations. The same applies + to two bit-fields, if one is declared inside a nested + structure declaration and the other is not, or if the two + are separated by a zero-length bit-field declaration, + or if they are separated by a non-bit-field member + declaration. It is not safe to concurrently update two + bit-fields in the same structure if all members declared + between them are also bit-fields, no matter what the + sizes of those intervening bit-fields happen to be. + ========================= WHAT ARE MEMORY BARRIERS? @@ -750,7 +794,7 @@ In summary: However, they do -not- guarantee any other sort of ordering: Not prior loads against later loads, nor prior stores against later anything. If you need these other forms of ordering, - use smb_rmb(), smp_wmb(), or, in the case of prior stores and + use smp_rmb(), smp_wmb(), or, in the case of prior stores and later loads, smp_mb(). (*) If both legs of the "if" statement begin with identical stores diff --git a/Documentation/oops-tracing.txt b/Documentation/oops-tracing.txt index beefb9f8290..f3ac05cc23e 100644 --- a/Documentation/oops-tracing.txt +++ b/Documentation/oops-tracing.txt @@ -270,6 +270,8 @@ characters, each representing a particular tainted value. 15: 'L' if a soft lockup has previously occurred on the system. + 16: 'K' if the kernel has been live patched. + The primary reason for the 'Tainted: ' string is to tell kernel debuggers if this is a clean kernel or if anything unusual has occurred. Tainting is permanent: even if an offending module is diff --git a/Documentation/power/s2ram.txt b/Documentation/power/s2ram.txt index 1bdfa044377..4685aee197f 100644 --- a/Documentation/power/s2ram.txt +++ b/Documentation/power/s2ram.txt @@ -69,6 +69,10 @@ Reason for this is that the RTC is the only reliably available piece of hardware during resume operations where a value can be set that will survive a reboot. +pm_trace is not compatible with asynchronous suspend, so it turns +asynchronous suspend off (which may work around timing or +ordering-sensitive bugs). + Consequence is that after a resume (even if it is successful) your system clock will have a value corresponding to the magic number instead of the correct date/time! It is therefore advisable to use a program like ntp-date diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 75511efefc6..83ab25660fc 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -843,6 +843,7 @@ can be ORed together: 8192 - An unsigned module has been loaded in a kernel supporting module signature. 16384 - A soft lockup has previously occurred on the system. +32768 - The kernel has been live patched. ============================================================== diff --git a/Documentation/usb/usbmon.txt b/Documentation/usb/usbmon.txt index c42bb9cd3b4..7587d84ebd1 100644 --- a/Documentation/usb/usbmon.txt +++ b/Documentation/usb/usbmon.txt @@ -231,7 +231,7 @@ number. Number zero (/dev/usbmon0) is special and means "all buses". Note that specific naming policy is set by your Linux distribution. If you create /dev/usbmon0 by hand, make sure that it is owned by root -and has mode 0600. Otherwise, unpriviledged users will be able to snoop +and has mode 0600. Otherwise, unprivileged users will be able to snoop keyboard traffic. The following ioctl calls are available, with MON_IOC_MAGIC 0x92: diff --git a/Documentation/vm/cleancache.txt b/Documentation/vm/cleancache.txt index 142fbb0f325..01d76282444 100644 --- a/Documentation/vm/cleancache.txt +++ b/Documentation/vm/cleancache.txt @@ -85,7 +85,7 @@ lock the page to ensure serial behavior. CLEANCACHE PERFORMANCE METRICS If properly configured, monitoring of cleancache is done via debugfs in -the /sys/kernel/debug/mm/cleancache directory. The effectiveness of cleancache +the /sys/kernel/debug/cleancache directory. The effectiveness of cleancache can be measured (across all filesystems) with: succ_gets - number of gets that were successful diff --git a/Documentation/vm/remap_file_pages.txt b/Documentation/vm/remap_file_pages.txt index 560e4363a55..f609142f406 100644 --- a/Documentation/vm/remap_file_pages.txt +++ b/Documentation/vm/remap_file_pages.txt @@ -18,10 +18,9 @@ on 32-bit systems to map files bigger than can linearly fit into 32-bit virtual address space. This use-case is not critical anymore since 64-bit systems are widely available. -The plan is to deprecate the syscall and replace it with an emulation. -The emulation will create new VMAs instead of nonlinear mappings. It's -going to work slower for rare users of remap_file_pages() but ABI is -preserved. +The syscall is deprecated and replaced it with an emulation now. The +emulation creates new VMAs instead of nonlinear mappings. It's going to +work slower for rare users of remap_file_pages() but ABI is preserved. One side effect of emulation (apart from performance) is that user can hit vm.max_map_count limit more easily due to additional VMAs. See comment for diff --git a/Documentation/x86/entry_64.txt b/Documentation/x86/entry_64.txt index 4a1c5c2dc5a..9132b86176a 100644 --- a/Documentation/x86/entry_64.txt +++ b/Documentation/x86/entry_64.txt @@ -78,9 +78,6 @@ The expensive (paranoid) way is to read back the MSR_GS_BASE value xorl %ebx,%ebx 1: ret -and the whole paranoid non-paranoid macro complexity is about whether -to suffer that RDMSR cost. - If we are at an interrupt or user-trap/gate-alike boundary then we can use the faster check: the stack will be a reliable indicator of whether SWAPGS was already done: if we see that we are a secondary @@ -93,6 +90,15 @@ which might have triggered right after a normal entry wrote CS to the stack but before we executed SWAPGS, then the only safe way to check for GS is the slower method: the RDMSR. -So we try only to mark those entry methods 'paranoid' that absolutely -need the more expensive check for the GS base - and we generate all -'normal' entry points with the regular (faster) entry macros. +Therefore, super-atomic entries (except NMI, which is handled separately) +must use idtentry with paranoid=1 to handle gsbase correctly. This +triggers three main behavior changes: + + - Interrupt entry will use the slower gsbase check. + - Interrupt entry from user mode will switch off the IST stack. + - Interrupt exit to kernel mode will not attempt to reschedule. + +We try to only use IST entries and the paranoid entry code for vectors +that absolutely need the more expensive check for the GS base - and we +generate all 'normal' entry points with the regular (faster) paranoid=0 +variant. diff --git a/Documentation/x86/x86_64/kernel-stacks b/Documentation/x86/x86_64/kernel-stacks index a01eec5d1d0..e3c8a49d1a2 100644 --- a/Documentation/x86/x86_64/kernel-stacks +++ b/Documentation/x86/x86_64/kernel-stacks @@ -40,9 +40,11 @@ An IST is selected by a non-zero value in the IST field of an interrupt-gate descriptor. When an interrupt occurs and the hardware loads such a descriptor, the hardware automatically sets the new stack pointer based on the IST value, then invokes the interrupt handler. If -software wants to allow nested IST interrupts then the handler must -adjust the IST values on entry to and exit from the interrupt handler. -(This is occasionally done, e.g. for debug exceptions.) +the interrupt came from user mode, then the interrupt handler prologue +will switch back to the per-thread stack. If software wants to allow +nested IST interrupts then the handler must adjust the IST values on +entry to and exit from the interrupt handler. (This is occasionally +done, e.g. for debug exceptions.) Events with different IST codes (i.e. with different stacks) can be nested. For example, a debug interrupt can safely be interrupted by an diff --git a/MAINTAINERS b/MAINTAINERS index 2b3aca7e40b..249e8dd83d4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -270,12 +270,12 @@ F: drivers/acpi/ F: drivers/pnp/pnpacpi/ F: include/linux/acpi.h F: include/acpi/ -F: Documentation/acpi +F: Documentation/acpi/ F: Documentation/ABI/testing/sysfs-bus-acpi F: drivers/pci/*acpi* F: drivers/pci/*/*acpi* F: drivers/pci/*/*/*acpi* -F: tools/power/acpi +F: tools/power/acpi/ ACPI COMPONENT ARCHITECTURE (ACPICA) M: Robert Moore <robert.moore@intel.com> @@ -1586,6 +1586,7 @@ N: xilinx F: drivers/clocksource/cadence_ttc_timer.c F: drivers/i2c/busses/i2c-cadence.c F: drivers/mmc/host/sdhci-of-arasan.c +F: drivers/edac/synopsys_edac.c ARM SMMU DRIVER M: Will Deacon <will.deacon@arm.com> @@ -3512,6 +3513,8 @@ M: Borislav Petkov <bp@alien8.de> M: Mauro Carvalho Chehab <mchehab@osg.samsung.com> L: linux-edac@vger.kernel.org W: bluesmoke.sourceforge.net +T: git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp.git#for-next +T: git://git.kernel.org/pub/linux/kernel/git/mchehab/linux-edac.git#linux_next S: Supported F: Documentation/edac.txt F: drivers/edac/ @@ -4952,6 +4955,16 @@ F: Documentation/input/multi-touch-protocol.txt F: drivers/input/input-mt.c K: \b(ABS|SYN)_MT_ +INTEL ASoC BDW/HSW DRIVERS +M: Jie Yang <yang.jie@linux.intel.com> +L: alsa-devel@alsa-project.org +S: Supported +F: sound/soc/intel/sst-haswell* +F: sound/soc/intel/sst-dsp* +F: sound/soc/intel/sst-firmware.c +F: sound/soc/intel/broadwell.c +F: sound/soc/intel/haswell.c + INTEL C600 SERIES SAS CONTROLLER DRIVER M: Intel SCU Linux support <intel-linux-scu@intel.com> M: Artur Paszkiewicz <artur.paszkiewicz@intel.com> @@ -5839,6 +5852,21 @@ F: Documentation/misc-devices/lis3lv02d F: drivers/misc/lis3lv02d/ F: drivers/platform/x86/hp_accel.c +LIVE PATCHING +M: Josh Poimboeuf <jpoimboe@redhat.com> +M: Seth Jennings <sjenning@redhat.com> +M: Jiri Kosina <jkosina@suse.cz> +M: Vojtech Pavlik <vojtech@suse.cz> +S: Maintained +F: kernel/livepatch/ +F: include/linux/livepatch.h +F: arch/x86/include/asm/livepatch.h +F: arch/x86/kernel/livepatch.c +F: Documentation/ABI/testing/sysfs-kernel-livepatch +F: samples/livepatch/ +L: live-patching@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/livepatching.git + LLC (802.2) M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> S: Maintained @@ -7265,6 +7293,14 @@ F: include/linux/pci* F: arch/x86/pci/ F: arch/x86/kernel/quirks.c +PCI DRIVER FOR ARM VERSATILE PLATFORM +M: Rob Herring <robh@kernel.org> +L: linux-pci@vger.kernel.org +L: linux-arm-kernel@lists.infradead.org +S: Maintained +F: Documentation/devicetree/bindings/pci/versatile.txt +F: drivers/pci/host/pci-versatile.c + PCI DRIVER FOR APPLIEDMICRO XGENE M: Tanmay Inamdar <tinamdar@apm.com> L: linux-pci@vger.kernel.org @@ -9249,7 +9285,6 @@ F: drivers/net/ethernet/dlink/sundance.c SUPERH L: linux-sh@vger.kernel.org -W: http://www.linux-sh.org Q: http://patchwork.kernel.org/project/linux-sh/list/ S: Orphan F: Documentation/sh/ @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = NAME = Diseased Newt # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h index d8f9b7e8923..fce22cf88ee 100644 --- a/arch/alpha/include/asm/pgtable.h +++ b/arch/alpha/include/asm/pgtable.h @@ -73,7 +73,6 @@ struct vm_area_struct; /* .. and these are ours ... */ #define _PAGE_DIRTY 0x20000 #define _PAGE_ACCESSED 0x40000 -#define _PAGE_FILE 0x80000 /* set:pagecache, unset:swap */ /* * NOTE! The "accessed" bit isn't necessarily exact: it can be kept exactly @@ -268,7 +267,6 @@ extern inline void pgd_clear(pgd_t * pgdp) { pgd_val(*pgdp) = 0; } extern inline int pte_write(pte_t pte) { return !(pte_val(pte) & _PAGE_FOW); } extern inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } extern inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } -extern inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } extern inline int pte_special(pte_t pte) { return 0; } extern inline pte_t pte_wrprotect(pte_t pte) { pte_val(pte) |= _PAGE_FOW; return pte; } @@ -345,11 +343,6 @@ extern inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define pte_to_pgoff(pte) (pte_val(pte) >> 32) -#define pgoff_to_pte(off) ((pte_t) { ((off) << 32) | _PAGE_FILE }) - -#define PTE_FILE_MAX_BITS 32 - #ifndef CONFIG_DISCONTIGMEM #define kern_addr_valid(addr) (1) #endif diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 6b0b7f7ef78..bdc8ccaf390 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -61,7 +61,6 @@ #define _PAGE_WRITE (1<<4) /* Page has user write perm (H) */ #define _PAGE_READ (1<<5) /* Page has user read perm (H) */ #define _PAGE_MODIFIED (1<<6) /* Page modified (dirty) (S) */ -#define _PAGE_FILE (1<<7) /* page cache/ swap (S) */ #define _PAGE_GLOBAL (1<<8) /* Page is global (H) */ #define _PAGE_PRESENT (1<<10) /* TLB entry is valid (H) */ @@ -73,7 +72,6 @@ #define _PAGE_READ (1<<3) /* Page has user read perm (H) */ #define _PAGE_ACCESSED (1<<4) /* Page is accessed (S) */ #define _PAGE_MODIFIED (1<<5) /* Page modified (dirty) (S) */ -#define _PAGE_FILE (1<<6) /* page cache/ swap (S) */ #define _PAGE_GLOBAL (1<<8) /* Page is global (H) */ #define _PAGE_PRESENT (1<<9) /* TLB entry is valid (H) */ #define _PAGE_SHARED_CODE (1<<11) /* Shared Code page with cmn vaddr @@ -268,15 +266,6 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) pte; \ }) -/* TBD: Non linear mapping stuff */ -static inline int pte_file(pte_t pte) -{ - return pte_val(pte) & _PAGE_FILE; -} - -#define PTE_FILE_MAX_BITS 30 -#define pgoff_to_pte(x) __pte(x) -#define pte_to_pgoff(x) (pte_val(x) >> 2) #define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT) #define pfn_pte(pfn, prot) (__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))) #define __pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) @@ -364,7 +353,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, /* Encode swap {type,off} tuple into PTE * We reserve 13 bits for 5-bit @type, keeping bits 12-5 zero, ensuring that - * both PAGE_FILE and PAGE_PRESENT are zero in a PTE holding swap "identifier" + * PAGE_PRESENT is zero in a PTE holding swap "identifier" */ #define __swp_entry(type, off) ((swp_entry_t) { \ ((type) & 0x1f) | ((off) << 13) }) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 97d07ed60a0..dcb2e0c55be 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1279,6 +1279,9 @@ config PCI_DOMAINS bool depends on PCI +config PCI_DOMAINS_GENERIC + def_bool PCI_DOMAINS + config PCI_NANOENGINE bool "BSE nanoEngine PCI support" depends on SA1100_NANOENGINE diff --git a/arch/arm/boot/dts/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi index b8168f1f813..24ff27049ce 100644 --- a/arch/arm/boot/dts/exynos4.dtsi +++ b/arch/arm/boot/dts/exynos4.dtsi @@ -368,7 +368,7 @@ }; i2s1: i2s@13960000 { - compatible = "samsung,s5pv210-i2s"; + compatible = "samsung,s3c6410-i2s"; reg = <0x13960000 0x100>; clocks = <&clock CLK_I2S1>; clock-names = "iis"; @@ -378,7 +378,7 @@ }; i2s2: i2s@13970000 { - compatible = "samsung,s5pv210-i2s"; + compatible = "samsung,s3c6410-i2s"; reg = <0x13970000 0x100>; clocks = <&clock CLK_I2S2>; clock-names = "iis"; diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts index e36c1e82fea..b83137f6603 100644 --- a/arch/arm/boot/dts/versatile-pb.dts +++ b/arch/arm/boot/dts/versatile-pb.dts @@ -29,6 +29,43 @@ clock-names = "apb_pclk"; }; + pci-controller@10001000 { + compatible = "arm,versatile-pci"; + device_type = "pci"; + reg = <0x10001000 0x1000 + 0x41000000 0x10000 + 0x42000000 0x100000>; + bus-range = <0 0xff>; + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + + ranges = <0x01000000 0 0x00000000 0x43000000 0 0x00010000 /* downstream I/O */ + 0x02000000 0 0x50000000 0x50000000 0 0x10000000 /* non-prefetchable memory */ + 0x42000000 0 0x60000000 0x60000000 0 0x10000000>; /* prefetchable memory */ + + interrupt-map-mask = <0x1800 0 0 7>; + interrupt-map = <0x1800 0 0 1 &sic 28 + 0x1800 0 0 2 &sic 29 + 0x1800 0 0 3 &sic 30 + 0x1800 0 0 4 &sic 27 + + 0x1000 0 0 1 &sic 27 + 0x1000 0 0 2 &sic 28 + 0x1000 0 0 3 &sic 29 + 0x1000 0 0 4 &sic 30 + + 0x0800 0 0 1 &sic 30 + 0x0800 0 0 2 &sic 27 + 0x0800 0 0 3 &sic 28 + 0x0800 0 0 4 &sic 29 + + 0x0000 0 0 1 &sic 29 + 0x0000 0 0 2 &sic 30 + 0x0000 0 0 3 &sic 27 + 0x0000 0 0 4 &sic 28>; + }; + fpga { uart@9000 { compatible = "arm,pl011", "arm,primecell"; diff --git a/arch/arm/include/asm/mach/pci.h b/arch/arm/include/asm/mach/pci.h index 8292b5f81e2..28b9bb35949 100644 --- a/arch/arm/include/asm/mach/pci.h +++ b/arch/arm/include/asm/mach/pci.h @@ -19,9 +19,6 @@ struct pci_bus; struct device; struct hw_pci { -#ifdef CONFIG_PCI_DOMAINS - int domain; -#endif #ifdef CONFIG_PCI_MSI struct msi_controller *msi_ctrl; #endif @@ -45,9 +42,6 @@ struct hw_pci { * Per-controller structure */ struct pci_sys_data { -#ifdef CONFIG_PCI_DOMAINS - int domain; -#endif #ifdef CONFIG_PCI_MSI struct msi_controller *msi_ctrl; #endif diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h index 7e95d8535e2..585dc33a7a2 100644 --- a/arch/arm/include/asm/pci.h +++ b/arch/arm/include/asm/pci.h @@ -18,13 +18,6 @@ static inline int pcibios_assign_all_busses(void) } #ifdef CONFIG_PCI_DOMAINS -static inline int pci_domain_nr(struct pci_bus *bus) -{ - struct pci_sys_data *root = bus->sysdata; - - return root->domain; -} - static inline int pci_proc_domain(struct pci_bus *bus) { return pci_domain_nr(bus); diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index f0279411847..bcc5e300413 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -118,7 +118,6 @@ #define L_PTE_VALID (_AT(pteval_t, 1) << 0) /* Valid */ #define L_PTE_PRESENT (_AT(pteval_t, 1) << 0) #define L_PTE_YOUNG (_AT(pteval_t, 1) << 1) -#define L_PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !PRESENT */ #define L_PTE_DIRTY (_AT(pteval_t, 1) << 6) #define L_PTE_RDONLY (_AT(pteval_t, 1) << 7) #define L_PTE_USER (_AT(pteval_t, 1) << 8) diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index a31ecdad4b5..18dbc82f85e 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -77,7 +77,6 @@ */ #define L_PTE_VALID (_AT(pteval_t, 1) << 0) /* Valid */ #define L_PTE_PRESENT (_AT(pteval_t, 3) << 0) /* Present */ -#define L_PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !PRESENT */ #define L_PTE_USER (_AT(pteval_t, 1) << 6) /* AP[1] */ #define L_PTE_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */ #define L_PTE_YOUNG (_AT(pteval_t, 1) << 10) /* AF */ diff --git a/arch/arm/include/asm/pgtable-nommu.h b/arch/arm/include/asm/pgtable-nommu.h index 0642228ff78..c35e53ee666 100644 --- a/arch/arm/include/asm/pgtable-nommu.h +++ b/arch/arm/include/asm/pgtable-nommu.h @@ -54,8 +54,6 @@ typedef pte_t *pte_addr_t; -static inline int pte_file(pte_t pte) { return 0; } - /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index d5cac545ba3..f40354198ba 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -318,12 +318,12 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) * * 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 - * <--------------- offset ----------------------> < type -> 0 0 0 + * <--------------- offset ------------------------> < type -> 0 0 * - * This gives us up to 31 swap files and 64GB per swap file. Note that + * This gives us up to 31 swap files and 128GB per swap file. Note that * the offset field is always non-zero. */ -#define __SWP_TYPE_SHIFT 3 +#define __SWP_TYPE_SHIFT 2 #define __SWP_TYPE_BITS 5 #define __SWP_TYPE_MASK ((1 << __SWP_TYPE_BITS) - 1) #define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT) @@ -342,20 +342,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) */ #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS) -/* - * Encode and decode a file entry. File entries are stored in the Linux - * page tables as follows: - * - * 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 - * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 - * <----------------------- offset ------------------------> 1 0 0 - */ -#define pte_file(pte) (pte_val(pte) & L_PTE_FILE) -#define pte_to_pgoff(x) (pte_val(x) >> 3) -#define pgoff_to_pte(x) __pte(((x) << 3) | L_PTE_FILE) - -#define PTE_FILE_MAX_BITS 29 - /* Needs to be defined here and not in linux/mm.h, as it is arch dependent */ /* FIXME: this is not correct */ #define kern_addr_valid(addr) (1) diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h index 68c739b3fdf..2f7e6ff67d5 100644 --- a/arch/arm/include/asm/xen/page.h +++ b/arch/arm/include/asm/xen/page.h @@ -92,7 +92,7 @@ extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, struct page **pages, unsigned int count); extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, - struct gnttab_map_grant_ref *kmap_ops, + struct gnttab_unmap_grant_ref *kunmap_ops, struct page **pages, unsigned int count); bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index a4effd6d8f2..ab19b7c0342 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -422,17 +422,16 @@ static int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) static int pcibios_init_resources(int busnr, struct pci_sys_data *sys) { int ret; - struct pci_host_bridge_window *window; + struct resource_entry *window; if (list_empty(&sys->resources)) { pci_add_resource_offset(&sys->resources, &iomem_resource, sys->mem_offset); } - list_for_each_entry(window, &sys->resources, list) { + resource_list_for_each_entry(window, &sys->resources) if (resource_type(window->res) == IORESOURCE_IO) return 0; - } sys->io_res.start = (busnr * SZ_64K) ? : pcibios_min_io; sys->io_res.end = (busnr + 1) * SZ_64K - 1; @@ -463,9 +462,6 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw, if (!sys) panic("PCI: unable to allocate sys data!"); -#ifdef CONFIG_PCI_DOMAINS - sys->domain = hw->domain; -#endif #ifdef CONFIG_PCI_MSI sys->msi_ctrl = hw->msi_ctrl; #endif diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index 466bd299b1a..3afee5f40f4 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -23,6 +23,7 @@ config KVM select HAVE_KVM_CPU_RELAX_INTERCEPT select KVM_MMIO select KVM_ARM_HOST + select SRCU depends on ARM_VIRT_EXT && ARM_LPAE ---help--- Support hosting virtualized guest machines. You will also diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c index 45d6bd09e6e..c622c306c39 100644 --- a/arch/arm/mach-cns3xxx/pcie.c +++ b/arch/arm/mach-cns3xxx/pcie.c @@ -30,18 +30,15 @@ struct cns3xxx_pcie { unsigned int irqs[2]; struct resource res_io; struct resource res_mem; - struct hw_pci hw_pci; - + int port; bool linked; }; -static struct cns3xxx_pcie cns3xxx_pcie[]; /* forward decl. */ - static struct cns3xxx_pcie *sysdata_to_cnspci(void *sysdata) { struct pci_sys_data *root = sysdata; - return &cns3xxx_pcie[root->domain]; + return root->private_data; } static struct cns3xxx_pcie *pdev_to_cnspci(const struct pci_dev *dev) @@ -54,8 +51,8 @@ static struct cns3xxx_pcie *pbus_to_cnspci(struct pci_bus *bus) return sysdata_to_cnspci(bus->sysdata); } -static void __iomem *cns3xxx_pci_cfg_base(struct pci_bus *bus, - unsigned int devfn, int where) +static void __iomem *cns3xxx_pci_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) { struct cns3xxx_pcie *cnspci = pbus_to_cnspci(bus); int busno = bus->number; @@ -91,55 +88,22 @@ static void __iomem *cns3xxx_pci_cfg_base(struct pci_bus *bus, static int cns3xxx_pci_read_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { - u32 v; - void __iomem *base; + int ret; u32 mask = (0x1ull << (size * 8)) - 1; int shift = (where % 4) * 8; - base = cns3xxx_pci_cfg_base(bus, devfn, where); - if (!base) { - *val = 0xffffffff; - return PCIBIOS_SUCCESSFUL; - } - - v = __raw_readl(base); + ret = pci_generic_config_read32(bus, devfn, where, size, val); - if (bus->number == 0 && devfn == 0 && - (where & 0xffc) == PCI_CLASS_REVISION) { + if (ret == PCIBIOS_SUCCESSFUL && !bus->number && !devfn && + (where & 0xffc) == PCI_CLASS_REVISION) /* * RC's class is 0xb, but Linux PCI driver needs 0x604 * for a PCIe bridge. So we must fixup the class code * to 0x604 here. */ - v &= 0xff; - v |= 0x604 << 16; - } + *val = ((((*val << shift) & 0xff) | (0x604 << 16)) >> shift) & mask; - *val = (v >> shift) & mask; - - return PCIBIOS_SUCCESSFUL; -} - -static int cns3xxx_pci_write_config(struct pci_bus *bus, unsigned int devfn, - int where, int size, u32 val) -{ - u32 v; - void __iomem *base; - u32 mask = (0x1ull << (size * 8)) - 1; - int shift = (where % 4) * 8; - - base = cns3xxx_pci_cfg_base(bus, devfn, where); - if (!base) - return PCIBIOS_SUCCESSFUL; - - v = __raw_readl(base); - - v &= ~(mask << shift); - v |= (val & mask) << shift; - - __raw_writel(v, base); - - return PCIBIOS_SUCCESSFUL; + return ret; } static int cns3xxx_pci_setup(int nr, struct pci_sys_data *sys) @@ -158,8 +122,9 @@ static int cns3xxx_pci_setup(int nr, struct pci_sys_data *sys) } static struct pci_ops cns3xxx_pcie_ops = { + .map_bus = cns3xxx_pci_map_bus, .read = cns3xxx_pci_read_config, - .write = cns3xxx_pci_write_config, + .write = pci_generic_config_write, }; static int cns3xxx_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) @@ -192,13 +157,7 @@ static struct cns3xxx_pcie cns3xxx_pcie[] = { .flags = IORESOURCE_MEM, }, .irqs = { IRQ_CNS3XXX_PCIE0_RC, IRQ_CNS3XXX_PCIE0_DEVICE, }, - .hw_pci = { - .domain = 0, - .nr_controllers = 1, - .ops = &cns3xxx_pcie_ops, - .setup = cns3xxx_pci_setup, - .map_irq = cns3xxx_pcie_map_irq, - }, + .port = 0, }, [1] = { .host_regs = (void __iomem *)CNS3XXX_PCIE1_HOST_BASE_VIRT, @@ -217,19 +176,13 @@ static struct cns3xxx_pcie cns3xxx_pcie[] = { .flags = IORESOURCE_MEM, }, .irqs = { IRQ_CNS3XXX_PCIE1_RC, IRQ_CNS3XXX_PCIE1_DEVICE, }, - .hw_pci = { - .domain = 1, - .nr_controllers = 1, - .ops = &cns3xxx_pcie_ops, - .setup = cns3xxx_pci_setup, - .map_irq = cns3xxx_pcie_map_irq, - }, + .port = 1, }, }; static void __init cns3xxx_pcie_check_link(struct cns3xxx_pcie *cnspci) { - int port = cnspci->hw_pci.domain; + int port = cnspci->port; u32 reg; unsigned long time; @@ -260,9 +213,9 @@ static void __init cns3xxx_pcie_check_link(struct cns3xxx_pcie *cnspci) static void __init cns3xxx_pcie_hw_init(struct cns3xxx_pcie *cnspci) { - int port = cnspci->hw_pci.domain; + int port = cnspci->port; struct pci_sys_data sd = { - .domain = port, + .private_data = cnspci, }; struct pci_bus bus = { .number = 0, @@ -323,6 +276,14 @@ static int cns3xxx_pcie_abort_handler(unsigned long addr, unsigned int fsr, void __init cns3xxx_pcie_init_late(void) { int i; + void *private_data; + struct hw_pci hw_pci = { + .nr_controllers = 1, + .ops = &cns3xxx_pcie_ops, + .setup = cns3xxx_pci_setup, + .map_irq = cns3xxx_pcie_map_irq, + .private_data = &private_data, + }; pcibios_min_io = 0; pcibios_min_mem = 0; @@ -335,7 +296,8 @@ void __init cns3xxx_pcie_init_late(void) cns3xxx_pwr_soft_rst(0x1 << PM_SOFT_RST_REG_OFFST_PCIE(i)); cns3xxx_pcie_check_link(&cns3xxx_pcie[i]); cns3xxx_pcie_hw_init(&cns3xxx_pcie[i]); - pci_common_init(&cns3xxx_pcie[i].hw_pci); + private_data = &cns3xxx_pcie[i]; + pci_common_init(&hw_pci); } pci_assign_unassigned_resources(); diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c index c186a17c2cf..2565f0e7b5c 100644 --- a/arch/arm/mach-integrator/pci_v3.c +++ b/arch/arm/mach-integrator/pci_v3.c @@ -356,7 +356,6 @@ static u64 pre_mem_pci_sz; * 7:2 register number * */ -static DEFINE_RAW_SPINLOCK(v3_lock); #undef V3_LB_BASE_PREFETCH #define V3_LB_BASE_PREFETCH 0 @@ -457,67 +456,21 @@ static void v3_close_config_window(void) static int v3_read_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { - void __iomem *addr; - unsigned long flags; - u32 v; - - raw_spin_lock_irqsave(&v3_lock, flags); - addr = v3_open_config_window(bus, devfn, where); - - switch (size) { - case 1: - v = __raw_readb(addr); - break; - - case 2: - v = __raw_readw(addr); - break; - - default: - v = __raw_readl(addr); - break; - } - + int ret = pci_generic_config_read(bus, devfn, where, size, val); v3_close_config_window(); - raw_spin_unlock_irqrestore(&v3_lock, flags); - - *val = v; - return PCIBIOS_SUCCESSFUL; + return ret; } static int v3_write_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val) { - void __iomem *addr; - unsigned long flags; - - raw_spin_lock_irqsave(&v3_lock, flags); - addr = v3_open_config_window(bus, devfn, where); - - switch (size) { - case 1: - __raw_writeb((u8)val, addr); - __raw_readb(addr); - break; - - case 2: - __raw_writew((u16)val, addr); - __raw_readw(addr); - break; - - case 4: - __raw_writel(val, addr); - __raw_readl(addr); - break; - } - + int ret = pci_generic_config_write(bus, devfn, where, size, val); v3_close_config_window(); - raw_spin_unlock_irqrestore(&v3_lock, flags); - - return PCIBIOS_SUCCESSFUL; + return ret; } static struct pci_ops pci_v3_ops = { + .map_bus = v3_open_config_window, .read = v3_read_config, .write = v3_write_config, }; @@ -658,7 +611,6 @@ static int __init pci_v3_setup(int nr, struct pci_sys_data *sys) */ static void __init pci_v3_preinit(void) { - unsigned long flags; unsigned int temp; phys_addr_t io_address = pci_pio_to_address(io_mem.start); @@ -672,8 +624,6 @@ static void __init pci_v3_preinit(void) hook_fault_code(8, v3_pci_fault, SIGBUS, 0, "external abort on non-linefetch"); hook_fault_code(10, v3_pci_fault, SIGBUS, 0, "external abort on non-linefetch"); - raw_spin_lock_irqsave(&v3_lock, flags); - /* * Unlock V3 registers, but only if they were previously locked. */ @@ -736,8 +686,6 @@ static void __init pci_v3_preinit(void) v3_writew(V3_LB_CFG, v3_readw(V3_LB_CFG) | (1 << 10)); v3_writeb(V3_LB_IMASK, 0x28); __raw_writel(3, ap_syscon_base + INTEGRATOR_SC_PCIENABLE_OFFSET); - - raw_spin_unlock_irqrestore(&v3_lock, flags); } static void __init pci_v3_postinit(void) diff --git a/arch/arm/mach-ks8695/pci.c b/arch/arm/mach-ks8695/pci.c index bb18193b4ba..c1bc4c3716e 100644 --- a/arch/arm/mach-ks8695/pci.c +++ b/arch/arm/mach-ks8695/pci.c @@ -38,8 +38,6 @@ static int pci_dbg; -static int pci_cfg_dbg; - static void ks8695_pci_setupconfig(unsigned int bus_nr, unsigned int devfn, unsigned int where) { @@ -59,75 +57,11 @@ static void ks8695_pci_setupconfig(unsigned int bus_nr, unsigned int devfn, unsi } } - -/* - * The KS8695 datasheet prohibits anything other than 32bit accesses - * to the IO registers, so all our configuration must be done with - * 32bit operations, and the correct bit masking and shifting. - */ - -static int ks8695_pci_readconfig(struct pci_bus *bus, - unsigned int devfn, int where, int size, u32 *value) -{ - ks8695_pci_setupconfig(bus->number, devfn, where); - - *value = __raw_readl(KS8695_PCI_VA + KS8695_PBCD); - - switch (size) { - case 4: - break; - case 2: - *value = *value >> ((where & 2) * 8); - *value &= 0xffff; - break; - case 1: - *value = *value >> ((where & 3) * 8); - *value &= 0xff; - break; - } - - if (pci_cfg_dbg) { - printk("read: %d,%08x,%02x,%d: %08x (%08x)\n", - bus->number, devfn, where, size, *value, - __raw_readl(KS8695_PCI_VA + KS8695_PBCD)); - } - - return PCIBIOS_SUCCESSFUL; -} - -static int ks8695_pci_writeconfig(struct pci_bus *bus, - unsigned int devfn, int where, int size, u32 value) +static void __iomem *ks8695_pci_map_bus(struct pci_bus *bus, unsigned int devfn, + int where) { - unsigned long tmp; - - if (pci_cfg_dbg) { - printk("write: %d,%08x,%02x,%d: %08x\n", - bus->number, devfn, where, size, value); - } - ks8695_pci_setupconfig(bus->number, devfn, where); - - switch (size) { - case 4: - __raw_writel(value, KS8695_PCI_VA + KS8695_PBCD); - break; - case 2: - tmp = __raw_readl(KS8695_PCI_VA + KS8695_PBCD); - tmp &= ~(0xffff << ((where & 2) * 8)); - tmp |= value << ((where & 2) * 8); - - __raw_writel(tmp, KS8695_PCI_VA + KS8695_PBCD); - break; - case 1: - tmp = __raw_readl(KS8695_PCI_VA + KS8695_PBCD); - tmp &= ~(0xff << ((where & 3) * 8)); - tmp |= value << ((where & 3) * 8); - - __raw_writel(tmp, KS8695_PCI_VA + KS8695_PBCD); - break; - } - - return PCIBIOS_SUCCESSFUL; + return KS8695_PCI_VA + KS8695_PBCD; } static void ks8695_local_writeconfig(int where, u32 value) @@ -137,8 +71,9 @@ static void ks8695_local_writeconfig(int where, u32 value) } static struct pci_ops ks8695_pci_ops = { - .read = ks8695_pci_readconfig, - .write = ks8695_pci_writeconfig, + .map_bus = ks8695_pci_map_bus, + .read = pci_generic_config_read32, + .write = pci_generic_config_write32, }; static struct resource pci_mem = { diff --git a/arch/arm/mach-sa1100/pci-nanoengine.c b/arch/arm/mach-sa1100/pci-nanoengine.c index b704433c529..d7ae8d50f6d 100644 --- a/arch/arm/mach-sa1100/pci-nanoengine.c +++ b/arch/arm/mach-sa1100/pci-nanoengine.c @@ -22,7 +22,6 @@ #include <linux/kernel.h> #include <linux/irq.h> #include <linux/pci.h> -#include <linux/spinlock.h> #include <asm/mach/pci.h> #include <asm/mach-types.h> @@ -30,97 +29,20 @@ #include <mach/nanoengine.h> #include <mach/hardware.h> -static DEFINE_SPINLOCK(nano_lock); - -static int nanoengine_get_pci_address(struct pci_bus *bus, - unsigned int devfn, int where, void __iomem **address) +static void __iomem *nanoengine_pci_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) { - int ret = PCIBIOS_DEVICE_NOT_FOUND; - unsigned int busnr = bus->number; + if (bus->number != 0 || (devfn >> 3) != 0) + return NULL; - *address = (void __iomem *)NANO_PCI_CONFIG_SPACE_VIRT + + return (void __iomem *)NANO_PCI_CONFIG_SPACE_VIRT + ((bus->number << 16) | (devfn << 8) | (where & ~3)); - - ret = (busnr > 255 || devfn > 255 || where > 255) ? - PCIBIOS_DEVICE_NOT_FOUND : PCIBIOS_SUCCESSFUL; - - return ret; -} - -static int nanoengine_read_config(struct pci_bus *bus, unsigned int devfn, int where, - int size, u32 *val) -{ - int ret; - void __iomem *address; - unsigned long flags; - u32 v; - - /* nanoEngine PCI bridge does not return -1 for a non-existing - * device. We must fake the answer. We know that the only valid - * device is device zero at bus 0, which is the network chip. */ - if (bus->number != 0 || (devfn >> 3) != 0) { - v = -1; - nanoengine_get_pci_address(bus, devfn, where, &address); - goto exit_function; - } - - spin_lock_irqsave(&nano_lock, flags); - - ret = nanoengine_get_pci_address(bus, devfn, where, &address); - if (ret != PCIBIOS_SUCCESSFUL) - return ret; - v = __raw_readl(address); - - spin_unlock_irqrestore(&nano_lock, flags); - - v >>= ((where & 3) * 8); - v &= (unsigned long)(-1) >> ((4 - size) * 8); - -exit_function: - *val = v; - return PCIBIOS_SUCCESSFUL; -} - -static int nanoengine_write_config(struct pci_bus *bus, unsigned int devfn, int where, - int size, u32 val) -{ - int ret; - void __iomem *address; - unsigned long flags; - unsigned shift; - u32 v; - - shift = (where & 3) * 8; - - spin_lock_irqsave(&nano_lock, flags); - - ret = nanoengine_get_pci_address(bus, devfn, where, &address); - if (ret != PCIBIOS_SUCCESSFUL) - return ret; - v = __raw_readl(address); - switch (size) { - case 1: - v &= ~(0xFF << shift); - v |= val << shift; - break; - case 2: - v &= ~(0xFFFF << shift); - v |= val << shift; - break; - case 4: - v = val; - break; - } - __raw_writel(v, address); - - spin_unlock_irqrestore(&nano_lock, flags); - - return PCIBIOS_SUCCESSFUL; } static struct pci_ops pci_nano_ops = { - .read = nanoengine_read_config, - .write = nanoengine_write_config, + .map_bus = nanoengine_pci_map_bus, + .read = pci_generic_config_read32, + .write = pci_generic_config_write32, }; static int __init pci_nanoengine_map_irq(const struct pci_dev *dev, u8 slot, diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 5e65ca8dea6..c7fc009ad21 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -1,5 +1,5 @@ /* - * arch/arm/mm/cache-l2x0.c - L210/L220 cache controller support + * arch/arm/mm/cache-l2x0.c - L210/L220/L310 cache controller support * * Copyright (C) 2007 ARM Limited * @@ -979,7 +979,7 @@ static int __init l2x0_cache_size_of_parse(const struct device_node *np, /* All these l2 caches have the same line = block size actually */ if (!line_size) { if (block_size) { - /* If linesize if not given, it is equal to blocksize */ + /* If linesize is not given, it is equal to blocksize */ line_size = block_size; } else { /* Fall back to known size */ diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index ba1196c968d..082b9f2f7e9 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -98,7 +98,7 @@ #endif #if !defined (CONFIG_ARM_LPAE) && \ (L_PTE_XN+L_PTE_USER+L_PTE_RDONLY+L_PTE_DIRTY+L_PTE_YOUNG+\ - L_PTE_FILE+L_PTE_PRESENT) > L_PTE_SHARED + L_PTE_PRESENT) > L_PTE_SHARED #error Invalid Linux PTE bit settings #endif #endif /* CONFIG_MMU */ diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index c7ca936ebd9..263a2044c65 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -29,10 +29,10 @@ struct start_info _xen_start_info; struct start_info *xen_start_info = &_xen_start_info; -EXPORT_SYMBOL_GPL(xen_start_info); +EXPORT_SYMBOL(xen_start_info); enum xen_domain_type xen_domain_type = XEN_NATIVE; -EXPORT_SYMBOL_GPL(xen_domain_type); +EXPORT_SYMBOL(xen_domain_type); struct shared_info xen_dummy_shared_info; struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index 351b24a979d..793551d15f1 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -149,7 +149,7 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region); struct dma_map_ops *xen_dma_ops; -EXPORT_SYMBOL_GPL(xen_dma_ops); +EXPORT_SYMBOL(xen_dma_ops); static struct dma_map_ops xen_swiotlb_dma_ops = { .mapping_error = xen_swiotlb_dma_mapping_error, diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c index 05485777625..cb7a14c5cd6 100644 --- a/arch/arm/xen/p2m.c +++ b/arch/arm/xen/p2m.c @@ -102,7 +102,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping); int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, - struct gnttab_map_grant_ref *kmap_ops, + struct gnttab_unmap_grant_ref *kunmap_ops, struct page **pages, unsigned int count) { int i; diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 210d632aa5a..4c445057169 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -25,7 +25,6 @@ * Software defined PTE bits definition. */ #define PTE_VALID (_AT(pteval_t, 1) << 0) -#define PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !pte_present() */ #define PTE_DIRTY (_AT(pteval_t, 1) << 55) #define PTE_SPECIAL (_AT(pteval_t, 1) << 56) #define PTE_WRITE (_AT(pteval_t, 1) << 57) @@ -469,13 +468,12 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD]; /* * Encode and decode a swap entry: * bits 0-1: present (must be zero) - * bit 2: PTE_FILE - * bits 3-8: swap type - * bits 9-57: swap offset + * bits 2-7: swap type + * bits 8-57: swap offset */ -#define __SWP_TYPE_SHIFT 3 +#define __SWP_TYPE_SHIFT 2 #define __SWP_TYPE_BITS 6 -#define __SWP_OFFSET_BITS 49 +#define __SWP_OFFSET_BITS 50 #define __SWP_TYPE_MASK ((1 << __SWP_TYPE_BITS) - 1) #define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT) #define __SWP_OFFSET_MASK ((1UL << __SWP_OFFSET_BITS) - 1) @@ -493,18 +491,6 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD]; */ #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS) -/* - * Encode and decode a file entry: - * bits 0-1: present (must be zero) - * bit 2: PTE_FILE - * bits 3-57: file offset / PAGE_SIZE - */ -#define pte_file(pte) (pte_val(pte) & PTE_FILE) -#define pte_to_pgoff(x) (pte_val(x) >> 3) -#define pgoff_to_pte(x) __pte(((x) << 3) | PTE_FILE) - -#define PTE_FILE_MAX_BITS 55 - extern int kern_addr_valid(unsigned long addr); #include <asm-generic/pgtable.h> diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c index d27dd982ff2..f5374065ad5 100644 --- a/arch/arm64/kernel/efi-stub.c +++ b/arch/arm64/kernel/efi-stub.c @@ -13,13 +13,13 @@ #include <asm/efi.h> #include <asm/sections.h> -efi_status_t handle_kernel_image(efi_system_table_t *sys_table, - unsigned long *image_addr, - unsigned long *image_size, - unsigned long *reserve_addr, - unsigned long *reserve_size, - unsigned long dram_base, - efi_loaded_image_t *image) +efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table, + unsigned long *image_addr, + unsigned long *image_size, + unsigned long *reserve_addr, + unsigned long *reserve_size, + unsigned long dram_base, + efi_loaded_image_t *image) { efi_status_t status; unsigned long kernel_size, kernel_memsize = 0; diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c index ce5836c14ec..6f93c24ca80 100644 --- a/arch/arm64/kernel/pci.c +++ b/arch/arm64/kernel/pci.c @@ -46,25 +46,3 @@ int pcibios_add_device(struct pci_dev *dev) return 0; } - - -#ifdef CONFIG_PCI_DOMAINS_GENERIC -static bool dt_domain_found = false; - -void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent) -{ - int domain = of_get_pci_domain_nr(parent->of_node); - - if (domain >= 0) { - dt_domain_found = true; - } else if (dt_domain_found == true) { - dev_err(parent, "Node %s is missing \"linux,pci-domain\" property in DT\n", - parent->of_node->full_name); - return; - } else { - domain = pci_get_new_domain_nr(); - } - - bus->domain_nr = domain; -} -#endif diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 8ba85e9ea38..b334084d367 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -26,6 +26,7 @@ config KVM select KVM_ARM_HOST select KVM_ARM_VGIC select KVM_ARM_TIMER + select SRCU ---help--- Support hosting virtualized guest machines. diff --git a/arch/avr32/include/asm/pgtable.h b/arch/avr32/include/asm/pgtable.h index 4beff97e203..ac7a817e212 100644 --- a/arch/avr32/include/asm/pgtable.h +++ b/arch/avr32/include/asm/pgtable.h @@ -86,9 +86,6 @@ extern struct page *empty_zero_page; #define _PAGE_BIT_PRESENT 10 #define _PAGE_BIT_ACCESSED 11 /* software: page was accessed */ -/* The following flags are only valid when !PRESENT */ -#define _PAGE_BIT_FILE 0 /* software: pagecache or swap? */ - #define _PAGE_WT (1 << _PAGE_BIT_WT) #define _PAGE_DIRTY (1 << _PAGE_BIT_DIRTY) #define _PAGE_EXECUTE (1 << _PAGE_BIT_EXECUTE) @@ -101,7 +98,6 @@ extern struct page *empty_zero_page; /* Software flags */ #define _PAGE_ACCESSED (1 << _PAGE_BIT_ACCESSED) #define _PAGE_PRESENT (1 << _PAGE_BIT_PRESENT) -#define _PAGE_FILE (1 << _PAGE_BIT_FILE) /* * Page types, i.e. sizes. _PAGE_TYPE_NONE corresponds to what is @@ -210,14 +206,6 @@ static inline int pte_special(pte_t pte) return 0; } -/* - * The following only work if pte_present() is not true. - */ -static inline int pte_file(pte_t pte) -{ - return pte_val(pte) & _PAGE_FILE; -} - /* Mutator functions for PTE bits */ static inline pte_t pte_wrprotect(pte_t pte) { @@ -329,7 +317,6 @@ extern void update_mmu_cache(struct vm_area_struct * vma, * Encode and decode a swap entry * * Constraints: - * _PAGE_FILE at bit 0 * _PAGE_TYPE_* at bits 2-3 (for emulating _PAGE_PROTNONE) * _PAGE_PRESENT at bit 10 * @@ -346,18 +333,6 @@ extern void update_mmu_cache(struct vm_area_struct * vma, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -/* - * Encode and decode a nonlinear file mapping entry. We have to - * preserve _PAGE_FILE and _PAGE_PRESENT here. _PAGE_TYPE_* isn't - * necessary, since _PAGE_FILE implies !_PAGE_PROTNONE (?) - */ -#define PTE_FILE_MAX_BITS 30 -#define pte_to_pgoff(pte) (((pte_val(pte) >> 1) & 0x1ff) \ - | ((pte_val(pte) >> 11) << 9)) -#define pgoff_to_pte(off) ((pte_t) { ((((off) & 0x1ff) << 1) \ - | (((off) >> 9) << 11) \ - | _PAGE_FILE) }) - typedef pte_t *pte_addr_t; #define kern_addr_valid(addr) (1) diff --git a/arch/blackfin/include/asm/pgtable.h b/arch/blackfin/include/asm/pgtable.h index 0b049019eba..b88a1558b0b 100644 --- a/arch/blackfin/include/asm/pgtable.h +++ b/arch/blackfin/include/asm/pgtable.h @@ -45,11 +45,6 @@ extern void paging_init(void); #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -static inline int pte_file(pte_t pte) -{ - return 0; -} - #define set_pte(pteptr, pteval) (*(pteptr) = pteval) #define set_pte_at(mm, addr, ptep, pteval) set_pte(ptep, pteval) diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c index dd2af74aff8..7236bdfc71e 100644 --- a/arch/blackfin/mach-common/ints-priority.c +++ b/arch/blackfin/mach-common/ints-priority.c @@ -429,14 +429,6 @@ static void init_software_driven_irq(void) bfin_sec_enable_ssi(37); } -void bfin_sec_resume(void) -{ - bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_RESET); - udelay(100); - bfin_write_SEC_GCTL(SEC_GCTL_EN); - bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_EN | SEC_CCTL_NMI_EN); -} - void handle_sec_sfi_fault(uint32_t gstat) { diff --git a/arch/c6x/include/asm/pgtable.h b/arch/c6x/include/asm/pgtable.h index c0eed5b1886..78d4483ba40 100644 --- a/arch/c6x/include/asm/pgtable.h +++ b/arch/c6x/include/asm/pgtable.h @@ -50,11 +50,6 @@ extern void paging_init(void); #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -static inline int pte_file(pte_t pte) -{ - return 0; -} - #define set_pte(pteptr, pteval) (*(pteptr) = pteval) #define set_pte_at(mm, addr, ptep, pteval) set_pte(ptep, pteval) diff --git a/arch/cris/include/arch-v10/arch/mmu.h b/arch/cris/include/arch-v10/arch/mmu.h index e829e5a37bb..47a5dd21749 100644 --- a/arch/cris/include/arch-v10/arch/mmu.h +++ b/arch/cris/include/arch-v10/arch/mmu.h @@ -58,7 +58,6 @@ typedef struct /* Bits the HW doesn't care about but the kernel uses them in SW */ #define _PAGE_PRESENT (1<<4) /* page present in memory */ -#define _PAGE_FILE (1<<5) /* set: pagecache, unset: swap (when !PRESENT) */ #define _PAGE_ACCESSED (1<<5) /* simulated in software using valid bit */ #define _PAGE_MODIFIED (1<<6) /* simulated in software using we bit */ #define _PAGE_READ (1<<7) /* read-enabled */ @@ -105,6 +104,4 @@ typedef struct #define __S110 PAGE_SHARED #define __S111 PAGE_SHARED -#define PTE_FILE_MAX_BITS 26 - #endif diff --git a/arch/cris/include/arch-v32/arch/mmu.h b/arch/cris/include/arch-v32/arch/mmu.h index c1a13e05e96..e6db1616dee 100644 --- a/arch/cris/include/arch-v32/arch/mmu.h +++ b/arch/cris/include/arch-v32/arch/mmu.h @@ -53,7 +53,6 @@ typedef struct * software. */ #define _PAGE_PRESENT (1 << 5) /* Page is present in memory. */ -#define _PAGE_FILE (1 << 6) /* 1=pagecache, 0=swap (when !present) */ #define _PAGE_ACCESSED (1 << 6) /* Simulated in software using valid bit. */ #define _PAGE_MODIFIED (1 << 7) /* Simulated in software using we bit. */ #define _PAGE_READ (1 << 8) /* Read enabled. */ @@ -108,6 +107,4 @@ typedef struct #define __S110 PAGE_SHARED_EXEC #define __S111 PAGE_SHARED_EXEC -#define PTE_FILE_MAX_BITS 25 - #endif /* _ASM_CRIS_ARCH_MMU_H */ diff --git a/arch/cris/include/asm/pgtable.h b/arch/cris/include/asm/pgtable.h index 8b8c8679322..e824257971c 100644 --- a/arch/cris/include/asm/pgtable.h +++ b/arch/cris/include/asm/pgtable.h @@ -114,7 +114,6 @@ extern unsigned long empty_zero_page; static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_WRITE; } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_MODIFIED; } static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } -static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } static inline int pte_special(pte_t pte) { return 0; } static inline pte_t pte_wrprotect(pte_t pte) @@ -290,9 +289,6 @@ static inline void update_mmu_cache(struct vm_area_struct * vma, */ #define pgtable_cache_init() do { } while (0) -#define pte_to_pgoff(x) (pte_val(x) >> 6) -#define pgoff_to_pte(x) __pte(((x) << 6) | _PAGE_FILE) - typedef pte_t *pte_addr_t; #endif /* __ASSEMBLY__ */ diff --git a/arch/frv/include/asm/pgtable.h b/arch/frv/include/asm/pgtable.h index eb0110acd19..c49699d5902 100644 --- a/arch/frv/include/asm/pgtable.h +++ b/arch/frv/include/asm/pgtable.h @@ -62,10 +62,6 @@ typedef pte_t *pte_addr_t; #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#ifndef __ASSEMBLY__ -static inline int pte_file(pte_t pte) { return 0; } -#endif - #define ZERO_PAGE(vaddr) ({ BUG(); NULL; }) #define swapper_pg_dir ((pgd_t *) NULL) @@ -298,7 +294,6 @@ static inline pmd_t *pmd_offset(pud_t *dir, unsigned long address) #define _PAGE_RESERVED_MASK (xAMPRx_RESERVED8 | xAMPRx_RESERVED13) -#define _PAGE_FILE 0x002 /* set:pagecache unset:swap */ #define _PAGE_PROTNONE 0x000 /* If not present */ #define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY) @@ -463,27 +458,15 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) * Handle swap and file entries * - the PTE is encoded in the following format: * bit 0: Must be 0 (!_PAGE_PRESENT) - * bit 1: Type: 0 for swap, 1 for file (_PAGE_FILE) - * bits 2-7: Swap type - * bits 8-31: Swap offset - * bits 2-31: File pgoff + * bits 1-6: Swap type + * bits 7-31: Swap offset */ -#define __swp_type(x) (((x).val >> 2) & 0x1f) -#define __swp_offset(x) ((x).val >> 8) -#define __swp_entry(type, offset) ((swp_entry_t) { ((type) << 2) | ((offset) << 8) }) +#define __swp_type(x) (((x).val >> 1) & 0x1f) +#define __swp_offset(x) ((x).val >> 7) +#define __swp_entry(type, offset) ((swp_entry_t) { ((type) << 1) | ((offset) << 7) }) #define __pte_to_swp_entry(_pte) ((swp_entry_t) { (_pte).pte }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -static inline int pte_file(pte_t pte) -{ - return pte.pte & _PAGE_FILE; -} - -#define PTE_FILE_MAX_BITS 29 - -#define pte_to_pgoff(PTE) ((PTE).pte >> 2) -#define pgoff_to_pte(off) __pte((off) << 2 | _PAGE_FILE) - /* Needs to be defined here and not in linux/mm.h, as it is arch dependent */ #define PageSkip(page) (0) #define kern_addr_valid(addr) (1) diff --git a/arch/frv/mb93090-mb00/pci-vdk.c b/arch/frv/mb93090-mb00/pci-vdk.c index efa5d65b000..b073f4d771a 100644 --- a/arch/frv/mb93090-mb00/pci-vdk.c +++ b/arch/frv/mb93090-mb00/pci-vdk.c @@ -168,8 +168,8 @@ static int pci_frv_write_config(struct pci_bus *bus, unsigned int devfn, int whe } static struct pci_ops pci_direct_frv = { - pci_frv_read_config, - pci_frv_write_config, + .read = pci_frv_read_config, + .write = pci_frv_write_config, }; /* diff --git a/arch/hexagon/include/asm/pgtable.h b/arch/hexagon/include/asm/pgtable.h index d8bd54fa431..6e35e71d2ae 100644 --- a/arch/hexagon/include/asm/pgtable.h +++ b/arch/hexagon/include/asm/pgtable.h @@ -62,13 +62,6 @@ extern unsigned long zero_page_mask; #define _PAGE_ACCESSED (1<<2) /* - * _PAGE_FILE is only meaningful if _PAGE_PRESENT is false, while - * _PAGE_DIRTY is only meaningful if _PAGE_PRESENT is true. - * So we can overload the bit... - */ -#define _PAGE_FILE _PAGE_DIRTY /* set: pagecache, unset = swap */ - -/* * For now, let's say that Valid and Present are the same thing. * Alternatively, we could say that it's the "or" of R, W, and X * permissions. @@ -456,57 +449,36 @@ static inline int pte_exec(pte_t pte) #define pgtable_cache_init() do { } while (0) /* - * Swap/file PTE definitions. If _PAGE_PRESENT is zero, the rest of the - * PTE is interpreted as swap information. Depending on the _PAGE_FILE - * bit, the remaining free bits are eitehr interpreted as a file offset - * or a swap type/offset tuple. Rather than have the TLB fill handler - * test _PAGE_PRESENT, we're going to reserve the permissions bits - * and set them to all zeros for swap entries, which speeds up the - * miss handler at the cost of 3 bits of offset. That trade-off can - * be revisited if necessary, but Hexagon processor architecture and - * target applications suggest a lot of TLB misses and not much swap space. + * Swap/file PTE definitions. If _PAGE_PRESENT is zero, the rest of the PTE is + * interpreted as swap information. The remaining free bits are interpreted as + * swap type/offset tuple. Rather than have the TLB fill handler test + * _PAGE_PRESENT, we're going to reserve the permissions bits and set them to + * all zeros for swap entries, which speeds up the miss handler at the cost of + * 3 bits of offset. That trade-off can be revisited if necessary, but Hexagon + * processor architecture and target applications suggest a lot of TLB misses + * and not much swap space. * * Format of swap PTE: * bit 0: Present (zero) - * bit 1: _PAGE_FILE (zero) - * bits 2-6: swap type (arch independent layer uses 5 bits max) - * bits 7-9: bits 2:0 of offset - * bits 10-12: effectively _PAGE_PROTNONE (all zero) - * bits 13-31: bits 21:3 of swap offset - * - * Format of file PTE: - * bit 0: Present (zero) - * bit 1: _PAGE_FILE (zero) - * bits 2-9: bits 7:0 of offset - * bits 10-12: effectively _PAGE_PROTNONE (all zero) - * bits 13-31: bits 26:8 of swap offset + * bits 1-5: swap type (arch independent layer uses 5 bits max) + * bits 6-9: bits 3:0 of offset + * bits 10-12: effectively _PAGE_PROTNONE (all zero) + * bits 13-31: bits 22:4 of swap offset * * The split offset makes some of the following macros a little gnarly, * but there's plenty of precedent for this sort of thing. */ -#define PTE_FILE_MAX_BITS 27 /* Used for swap PTEs */ -#define __swp_type(swp_pte) (((swp_pte).val >> 2) & 0x1f) +#define __swp_type(swp_pte) (((swp_pte).val >> 1) & 0x1f) #define __swp_offset(swp_pte) \ - ((((swp_pte).val >> 7) & 0x7) | (((swp_pte).val >> 10) & 0x003ffff8)) + ((((swp_pte).val >> 6) & 0xf) | (((swp_pte).val >> 9) & 0x7ffff0)) #define __swp_entry(type, offset) \ ((swp_entry_t) { \ - ((type << 2) | \ - ((offset & 0x3ffff8) << 10) | ((offset & 0x7) << 7)) }) - -/* Used for file PTEs */ -#define pte_file(pte) \ - ((pte_val(pte) & (_PAGE_FILE | _PAGE_PRESENT)) == _PAGE_FILE) - -#define pte_to_pgoff(pte) \ - (((pte_val(pte) >> 2) & 0xff) | ((pte_val(pte) >> 5) & 0x07ffff00)) - -#define pgoff_to_pte(off) \ - ((pte_t) { ((((off) & 0x7ffff00) << 5) | (((off) & 0xff) << 2)\ - | _PAGE_FILE) }) + ((type << 1) | \ + ((offset & 0x7ffff0) << 9) | ((offset & 0xf) << 6)) }) /* Oh boy. There are a lot of possible arch overrides found in this file. */ #include <asm-generic/pgtable.h> diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index 7935115398a..2f07bb3dda9 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -57,9 +57,6 @@ #define _PAGE_ED (__IA64_UL(1) << 52) /* exception deferral */ #define _PAGE_PROTNONE (__IA64_UL(1) << 63) -/* Valid only for a PTE with the present bit cleared: */ -#define _PAGE_FILE (1 << 1) /* see swap & file pte remarks below */ - #define _PFN_MASK _PAGE_PPN_MASK /* Mask of bits which may be changed by pte_modify(); the odd bits are there for _PAGE_PROTNONE */ #define _PAGE_CHG_MASK (_PAGE_P | _PAGE_PROTNONE | _PAGE_PL_MASK | _PAGE_AR_MASK | _PAGE_ED) @@ -300,7 +297,6 @@ extern unsigned long VMALLOC_END; #define pte_exec(pte) ((pte_val(pte) & _PAGE_AR_RX) != 0) #define pte_dirty(pte) ((pte_val(pte) & _PAGE_D) != 0) #define pte_young(pte) ((pte_val(pte) & _PAGE_A) != 0) -#define pte_file(pte) ((pte_val(pte) & _PAGE_FILE) != 0) #define pte_special(pte) 0 /* @@ -472,27 +468,16 @@ extern void paging_init (void); * * Format of swap pte: * bit 0 : present bit (must be zero) - * bit 1 : _PAGE_FILE (must be zero) - * bits 2- 8: swap-type - * bits 9-62: swap offset - * bit 63 : _PAGE_PROTNONE bit - * - * Format of file pte: - * bit 0 : present bit (must be zero) - * bit 1 : _PAGE_FILE (must be one) - * bits 2-62: file_offset/PAGE_SIZE + * bits 1- 7: swap-type + * bits 8-62: swap offset * bit 63 : _PAGE_PROTNONE bit */ -#define __swp_type(entry) (((entry).val >> 2) & 0x7f) -#define __swp_offset(entry) (((entry).val << 1) >> 10) -#define __swp_entry(type,offset) ((swp_entry_t) { ((type) << 2) | ((long) (offset) << 9) }) +#define __swp_type(entry) (((entry).val >> 1) & 0x7f) +#define __swp_offset(entry) (((entry).val << 1) >> 9) +#define __swp_entry(type,offset) ((swp_entry_t) { ((type) << 1) | ((long) (offset) << 8) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define PTE_FILE_MAX_BITS 61 -#define pte_to_pgoff(pte) ((pte_val(pte) << 1) >> 3) -#define pgoff_to_pte(off) ((pte_t) { ((off) << 2) | _PAGE_FILE }) - /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. diff --git a/arch/ia64/kernel/acpi-ext.c b/arch/ia64/kernel/acpi-ext.c index 8b9318d311a..bd09bf74f18 100644 --- a/arch/ia64/kernel/acpi-ext.c +++ b/arch/ia64/kernel/acpi-ext.c @@ -69,10 +69,10 @@ static acpi_status find_csr_space(struct acpi_resource *resource, void *data) status = acpi_resource_to_address64(resource, &addr); if (ACPI_SUCCESS(status) && addr.resource_type == ACPI_MEMORY_RANGE && - addr.address_length && + addr.address.address_length && addr.producer_consumer == ACPI_CONSUMER) { - space->base = addr.minimum; - space->length = addr.address_length; + space->base = addr.address.minimum; + space->length = addr.address.address_length; return AE_CTRL_TERMINATE; } return AE_OK; /* keep looking */ diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index e795cb84815..2c4498919d3 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -380,9 +380,6 @@ static void __init acpi_madt_oem_check(char *oem_id, char *oem_table_id) static int __init acpi_parse_madt(struct acpi_table_header *table) { - if (!table) - return -EINVAL; - acpi_madt = (struct acpi_table_madt *)table; acpi_madt_rev = acpi_madt->header.revision; @@ -645,9 +642,6 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table) struct acpi_table_header *fadt_header; struct acpi_table_fadt *fadt; - if (!table) - return -EINVAL; - fadt_header = (struct acpi_table_header *)table; if (fadt_header->revision != 3) return -ENODEV; /* Only deal with ACPI 2.0 FADT */ diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c index 900cc93e540..48cc65705db 100644 --- a/arch/ia64/pci/pci.c +++ b/arch/ia64/pci/pci.c @@ -188,12 +188,12 @@ static u64 add_io_space(struct pci_root_info *info, name = (char *)(iospace + 1); - min = addr->minimum; - max = min + addr->address_length - 1; + min = addr->address.minimum; + max = min + addr->address.address_length - 1; if (addr->info.io.translation_type == ACPI_SPARSE_TRANSLATION) sparse = 1; - space_nr = new_space(addr->translation_offset, sparse); + space_nr = new_space(addr->address.translation_offset, sparse); if (space_nr == ~0) goto free_resource; @@ -247,7 +247,7 @@ static acpi_status resource_to_window(struct acpi_resource *resource, if (ACPI_SUCCESS(status) && (addr->resource_type == ACPI_MEMORY_RANGE || addr->resource_type == ACPI_IO_RANGE) && - addr->address_length && + addr->address.address_length && addr->producer_consumer == ACPI_PRODUCER) return AE_OK; @@ -284,7 +284,7 @@ static acpi_status add_window(struct acpi_resource *res, void *data) if (addr.resource_type == ACPI_MEMORY_RANGE) { flags = IORESOURCE_MEM; root = &iomem_resource; - offset = addr.translation_offset; + offset = addr.address.translation_offset; } else if (addr.resource_type == ACPI_IO_RANGE) { flags = IORESOURCE_IO; root = &ioport_resource; @@ -297,8 +297,8 @@ static acpi_status add_window(struct acpi_resource *res, void *data) resource = &info->res[info->res_num]; resource->name = info->name; resource->flags = flags; - resource->start = addr.minimum + offset; - resource->end = resource->start + addr.address_length - 1; + resource->start = addr.address.minimum + offset; + resource->end = resource->start + addr.address.address_length - 1; info->res_offset[info->res_num] = offset; if (insert_resource(root, resource)) { diff --git a/arch/m32r/include/asm/pgtable-2level.h b/arch/m32r/include/asm/pgtable-2level.h index 9cdaf7350ef..8fd8ee70266 100644 --- a/arch/m32r/include/asm/pgtable-2level.h +++ b/arch/m32r/include/asm/pgtable-2level.h @@ -70,9 +70,5 @@ static inline pmd_t *pmd_offset(pgd_t * dir, unsigned long address) #define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) #define pfn_pmd(pfn, prot) __pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) -#define PTE_FILE_MAX_BITS 29 -#define pte_to_pgoff(pte) (((pte_val(pte) >> 2) & 0x7f) | (((pte_val(pte) >> 10)) << 7)) -#define pgoff_to_pte(off) ((pte_t) { (((off) & 0x7f) << 2) | (((off) >> 7) << 10) | _PAGE_FILE }) - #endif /* __KERNEL__ */ #endif /* _ASM_M32R_PGTABLE_2LEVEL_H */ diff --git a/arch/m32r/include/asm/pgtable.h b/arch/m32r/include/asm/pgtable.h index 103ce6710f0..050f7a686e3 100644 --- a/arch/m32r/include/asm/pgtable.h +++ b/arch/m32r/include/asm/pgtable.h @@ -80,8 +80,6 @@ extern unsigned long empty_zero_page[1024]; */ #define _PAGE_BIT_DIRTY 0 /* software: page changed */ -#define _PAGE_BIT_FILE 0 /* when !present: nonlinear file - mapping */ #define _PAGE_BIT_PRESENT 1 /* Valid: page is valid */ #define _PAGE_BIT_GLOBAL 2 /* Global */ #define _PAGE_BIT_LARGE 3 /* Large */ @@ -93,7 +91,6 @@ extern unsigned long empty_zero_page[1024]; #define _PAGE_BIT_PROTNONE 9 /* software: if not present */ #define _PAGE_DIRTY (1UL << _PAGE_BIT_DIRTY) -#define _PAGE_FILE (1UL << _PAGE_BIT_FILE) #define _PAGE_PRESENT (1UL << _PAGE_BIT_PRESENT) #define _PAGE_GLOBAL (1UL << _PAGE_BIT_GLOBAL) #define _PAGE_LARGE (1UL << _PAGE_BIT_LARGE) @@ -206,14 +203,6 @@ static inline int pte_write(pte_t pte) return pte_val(pte) & _PAGE_WRITE; } -/* - * The following only works if pte_present() is not true. - */ -static inline int pte_file(pte_t pte) -{ - return pte_val(pte) & _PAGE_FILE; -} - static inline int pte_special(pte_t pte) { return 0; diff --git a/arch/m68k/atari/atakeyb.c b/arch/m68k/atari/atakeyb.c index 95022b04b62..264db112680 100644 --- a/arch/m68k/atari/atakeyb.c +++ b/arch/m68k/atari/atakeyb.c @@ -170,7 +170,6 @@ repeat: if (acia_stat & ACIA_RDRF) { /* received a character */ scancode = acia.key_data; /* get it or reset the ACIA, I'll get it! */ - tasklet_schedule(&keyboard_tasklet); interpret_scancode: switch (kb_state.state) { case KEYBOARD: @@ -430,14 +429,6 @@ void ikbd_mouse_y0_top(void) } EXPORT_SYMBOL(ikbd_mouse_y0_top); -/* Resume */ -void ikbd_resume(void) -{ - static const char cmd[1] = { 0x11 }; - - ikbd_write(cmd, 1); -} - /* Disable mouse */ void ikbd_mouse_disable(void) { @@ -447,14 +438,6 @@ void ikbd_mouse_disable(void) } EXPORT_SYMBOL(ikbd_mouse_disable); -/* Pause output */ -void ikbd_pause(void) -{ - static const char cmd[1] = { 0x13 }; - - ikbd_write(cmd, 1); -} - /* Set joystick event reporting */ void ikbd_joystick_event_on(void) { @@ -502,56 +485,6 @@ void ikbd_joystick_disable(void) ikbd_write(cmd, 1); } -/* Time-of-day clock set */ -void ikbd_clock_set(int year, int month, int day, int hour, int minute, int second) -{ - char cmd[7] = { 0x1B, year, month, day, hour, minute, second }; - - ikbd_write(cmd, 7); -} - -/* Interrogate time-of-day clock */ -void ikbd_clock_get(int *year, int *month, int *day, int *hour, int *minute, int second) -{ - static const char cmd[1] = { 0x1C }; - - ikbd_write(cmd, 1); -} - -/* Memory load */ -void ikbd_mem_write(int address, int size, char *data) -{ - panic("Attempt to write data into keyboard memory"); -} - -/* Memory read */ -void ikbd_mem_read(int address, char data[6]) -{ - char cmd[3] = { 0x21, address>>8, address&0xFF }; - - ikbd_write(cmd, 3); - - /* receive data and put it in data */ -} - -/* Controller execute */ -void ikbd_exec(int address) -{ - char cmd[3] = { 0x22, address>>8, address&0xFF }; - - ikbd_write(cmd, 3); -} - -/* Status inquiries (0x87-0x9A) not yet implemented */ - -/* Set the state of the caps lock led. */ -void atari_kbd_leds(unsigned int leds) -{ - char cmd[6] = {32, 0, 4, 1, 254 + ((leds & 4) != 0), 0}; - - ikbd_write(cmd, 6); -} - /* * The original code sometimes left the interrupt line of * the ACIAs low forever. I hope, it is fixed now. @@ -571,9 +504,8 @@ int atari_keyb_init(void) kb_state.state = KEYBOARD; kb_state.len = 0; - error = request_irq(IRQ_MFP_ACIA, atari_keyboard_interrupt, - IRQ_TYPE_SLOW, "keyboard,mouse,MIDI", - atari_keyboard_interrupt); + error = request_irq(IRQ_MFP_ACIA, atari_keyboard_interrupt, 0, + "keyboard,mouse,MIDI", atari_keyboard_interrupt); if (error) return error; diff --git a/arch/m68k/atari/stdma.c b/arch/m68k/atari/stdma.c index e5a66596b11..ba65f942d0c 100644 --- a/arch/m68k/atari/stdma.c +++ b/arch/m68k/atari/stdma.c @@ -198,7 +198,7 @@ EXPORT_SYMBOL(stdma_islocked); void __init stdma_init(void) { stdma_isr = NULL; - if (request_irq(IRQ_MFP_FDC, stdma_int, IRQ_TYPE_SLOW | IRQF_SHARED, + if (request_irq(IRQ_MFP_FDC, stdma_int, IRQF_SHARED, "ST-DMA floppy,ACSI,IDE,Falcon-SCSI", stdma_int)) pr_err("Couldn't register ST-DMA interrupt\n"); } diff --git a/arch/m68k/atari/time.c b/arch/m68k/atari/time.c index da8f981c36d..c549b48174e 100644 --- a/arch/m68k/atari/time.c +++ b/arch/m68k/atari/time.c @@ -32,8 +32,7 @@ atari_sched_init(irq_handler_t timer_routine) /* start timer C, div = 1:100 */ st_mfp.tim_ct_cd = (st_mfp.tim_ct_cd & 15) | 0x60; /* install interrupt service routine for MFP Timer C */ - if (request_irq(IRQ_MFP_TIMC, timer_routine, IRQ_TYPE_SLOW, - "timer", timer_routine)) + if (request_irq(IRQ_MFP_TIMC, timer_routine, 0, "timer", timer_routine)) pr_err("Couldn't register timer interrupt\n"); } diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 399df883c8b..1a10a08ebec 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -36,6 +36,7 @@ CONFIG_AMIGA_PCMCIA=y CONFIG_ZORRO_NAMES=y # CONFIG_COMPACTION is not set CONFIG_CLEANCACHE=y +CONFIG_ZPOOL=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m @@ -55,6 +56,8 @@ CONFIG_NET_IPIP=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_GENEVE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -96,6 +99,8 @@ CONFIG_NFT_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m CONFIG_NFT_REJECT=m @@ -142,6 +147,7 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -163,6 +169,7 @@ CONFIG_IP_SET_HASH_IPMARK=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_MAC=m CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m CONFIG_IP_SET_HASH_NETNET=m @@ -170,9 +177,12 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_NF_TABLES_ARP=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NFT_MASQ_IPV4=m +CONFIG_NFT_REDIR_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -181,8 +191,7 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_SYNPROXY=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m CONFIG_IP_NF_TARGET_REDIRECT=m @@ -197,6 +206,8 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m +CONFIG_NFT_MASQ_IPV6=m +CONFIG_NFT_REDIR_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -213,17 +224,43 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_TARGET_SYNPROXY=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_NF_NAT_IPV6=m +CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NFT_BRIDGE_META=m +CONFIG_NFT_BRIDGE_REJECT=m +CONFIG_NF_LOG_BRIDGE=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_IP6=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +CONFIG_BRIDGE_EBT_NFLOG=m CONFIG_IP_DCCP=m # CONFIG_IP_DCCP_CCID3 is not set CONFIG_SCTP_COOKIE_HMAC_SHA1=y CONFIG_RDS=m CONFIG_RDS_TCP=m CONFIG_L2TP=m +CONFIG_BRIDGE=m CONFIG_ATALK=m +CONFIG_6LOWPAN=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m CONFIG_BATMAN_ADV_DAT=y @@ -232,9 +269,10 @@ CONFIG_BATMAN_ADV_MCAST=y CONFIG_NETLINK_DIAG=m CONFIG_NET_MPLS_GSO=m # CONFIG_WIRELESS is not set +# CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FIRMWARE_IN_KERNEL is not set -# CONFIG_FW_LOADER_USER_HELPER is not set CONFIG_CONNECTOR=m CONFIG_PARPORT=m CONFIG_PARPORT_AMIGA=m @@ -299,6 +337,9 @@ CONFIG_NET_TEAM_MODE_ROUNDROBIN=m CONFIG_NET_TEAM_MODE_RANDOM=m CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m CONFIG_NET_TEAM_MODE_LOADBALANCE=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -316,6 +357,8 @@ CONFIG_ARIADNE=y CONFIG_HYDRA=y CONFIG_APNE=y CONFIG_ZORRO8390=y +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_ROCKER is not set # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_SMSC is not set @@ -371,6 +414,7 @@ CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set +# CONFIG_HID_PLANTRONICS is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_MSM6242=m @@ -392,6 +436,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y @@ -407,6 +452,7 @@ CONFIG_HFS_FS=m CONFIG_HFSPLUS_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_MINIX_FS=m CONFIG_OMFS_FS=m @@ -476,10 +522,18 @@ CONFIG_DLM=m CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_STRING_HELPERS=m +CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_LKM=m +CONFIG_TEST_USER_COPY=m +CONFIG_TEST_BPF=m +CONFIG_TEST_FIRMWARE=m +CONFIG_TEST_UDELAY=m +CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m @@ -514,13 +568,10 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DRBG_MENU=m +CONFIG_CRYPTO_DRBG_HASH=y +CONFIG_CRYPTO_DRBG_CTR=y CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m # CONFIG_CRYPTO_HW is not set -CONFIG_XZ_DEC_X86=y -CONFIG_XZ_DEC_POWERPC=y -CONFIG_XZ_DEC_IA64=y -CONFIG_XZ_DEC_ARM=y -CONFIG_XZ_DEC_ARMTHUMB=y -CONFIG_XZ_DEC_SPARC=y CONFIG_XZ_DEC_TEST=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index be16740c074..7859a738c81 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -34,6 +34,7 @@ CONFIG_M68060=y CONFIG_APOLLO=y # CONFIG_COMPACTION is not set CONFIG_CLEANCACHE=y +CONFIG_ZPOOL=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m @@ -53,6 +54,8 @@ CONFIG_NET_IPIP=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_GENEVE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -94,6 +97,8 @@ CONFIG_NFT_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m CONFIG_NFT_REJECT=m @@ -140,6 +145,7 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -161,6 +167,7 @@ CONFIG_IP_SET_HASH_IPMARK=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_MAC=m CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m CONFIG_IP_SET_HASH_NETNET=m @@ -168,9 +175,12 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_NF_TABLES_ARP=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NFT_MASQ_IPV4=m +CONFIG_NFT_REDIR_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -179,8 +189,7 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_SYNPROXY=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m CONFIG_IP_NF_TARGET_REDIRECT=m @@ -195,6 +204,8 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m +CONFIG_NFT_MASQ_IPV6=m +CONFIG_NFT_REDIR_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -211,17 +222,43 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_TARGET_SYNPROXY=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_NF_NAT_IPV6=m +CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NFT_BRIDGE_META=m +CONFIG_NFT_BRIDGE_REJECT=m +CONFIG_NF_LOG_BRIDGE=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_IP6=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +CONFIG_BRIDGE_EBT_NFLOG=m CONFIG_IP_DCCP=m # CONFIG_IP_DCCP_CCID3 is not set CONFIG_SCTP_COOKIE_HMAC_SHA1=y CONFIG_RDS=m CONFIG_RDS_TCP=m CONFIG_L2TP=m +CONFIG_BRIDGE=m CONFIG_ATALK=m +CONFIG_6LOWPAN=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m CONFIG_BATMAN_ADV_DAT=y @@ -230,9 +267,10 @@ CONFIG_BATMAN_ADV_MCAST=y CONFIG_NETLINK_DIAG=m CONFIG_NET_MPLS_GSO=m # CONFIG_WIRELESS is not set +# CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FIRMWARE_IN_KERNEL is not set -# CONFIG_FW_LOADER_USER_HELPER is not set CONFIG_CONNECTOR=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_CRYPTOLOOP=m @@ -281,6 +319,9 @@ CONFIG_NET_TEAM_MODE_ROUNDROBIN=m CONFIG_NET_TEAM_MODE_RANDOM=m CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m CONFIG_NET_TEAM_MODE_LOADBALANCE=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -291,6 +332,8 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_ROCKER is not set # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set @@ -332,6 +375,7 @@ CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set +# CONFIG_HID_PLANTRONICS is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_GENERIC=m @@ -350,6 +394,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y @@ -365,6 +410,7 @@ CONFIG_HFS_FS=m CONFIG_HFSPLUS_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_MINIX_FS=m CONFIG_OMFS_FS=m @@ -434,10 +480,18 @@ CONFIG_DLM=m CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_STRING_HELPERS=m +CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_LKM=m +CONFIG_TEST_USER_COPY=m +CONFIG_TEST_BPF=m +CONFIG_TEST_FIRMWARE=m +CONFIG_TEST_UDELAY=m +CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m @@ -472,13 +526,10 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DRBG_MENU=m +CONFIG_CRYPTO_DRBG_HASH=y +CONFIG_CRYPTO_DRBG_CTR=y CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m # CONFIG_CRYPTO_HW is not set -CONFIG_XZ_DEC_X86=y -CONFIG_XZ_DEC_POWERPC=y -CONFIG_XZ_DEC_IA64=y -CONFIG_XZ_DEC_ARM=y -CONFIG_XZ_DEC_ARMTHUMB=y -CONFIG_XZ_DEC_SPARC=y CONFIG_XZ_DEC_TEST=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 391e185d73b..372593a3b39 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -31,8 +31,10 @@ CONFIG_M68030=y CONFIG_M68040=y CONFIG_M68060=y CONFIG_ATARI=y +CONFIG_ATARI_ROM_ISA=y # CONFIG_COMPACTION is not set CONFIG_CLEANCACHE=y +CONFIG_ZPOOL=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m @@ -52,6 +54,8 @@ CONFIG_NET_IPIP=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_GENEVE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -93,6 +97,8 @@ CONFIG_NFT_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m CONFIG_NFT_REJECT=m @@ -139,6 +145,7 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -160,6 +167,7 @@ CONFIG_IP_SET_HASH_IPMARK=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_MAC=m CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m CONFIG_IP_SET_HASH_NETNET=m @@ -167,9 +175,12 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_NF_TABLES_ARP=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NFT_MASQ_IPV4=m +CONFIG_NFT_REDIR_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -178,8 +189,7 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_SYNPROXY=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m CONFIG_IP_NF_TARGET_REDIRECT=m @@ -194,6 +204,8 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m +CONFIG_NFT_MASQ_IPV6=m +CONFIG_NFT_REDIR_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -210,17 +222,43 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_TARGET_SYNPROXY=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_NF_NAT_IPV6=m +CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NFT_BRIDGE_META=m +CONFIG_NFT_BRIDGE_REJECT=m +CONFIG_NF_LOG_BRIDGE=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_IP6=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +CONFIG_BRIDGE_EBT_NFLOG=m CONFIG_IP_DCCP=m # CONFIG_IP_DCCP_CCID3 is not set CONFIG_SCTP_COOKIE_HMAC_SHA1=y CONFIG_RDS=m CONFIG_RDS_TCP=m CONFIG_L2TP=m +CONFIG_BRIDGE=m CONFIG_ATALK=m +CONFIG_6LOWPAN=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m CONFIG_BATMAN_ADV_DAT=y @@ -229,9 +267,10 @@ CONFIG_BATMAN_ADV_MCAST=y CONFIG_NETLINK_DIAG=m CONFIG_NET_MPLS_GSO=m # CONFIG_WIRELESS is not set +# CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FIRMWARE_IN_KERNEL is not set -# CONFIG_FW_LOADER_USER_HELPER is not set CONFIG_CONNECTOR=m CONFIG_PARPORT=m CONFIG_PARPORT_ATARI=m @@ -289,6 +328,9 @@ CONFIG_NET_TEAM_MODE_ROUNDROBIN=m CONFIG_NET_TEAM_MODE_RANDOM=m CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m CONFIG_NET_TEAM_MODE_LOADBALANCE=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -299,8 +341,12 @@ CONFIG_ATARILANCE=y # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set +CONFIG_NE2000=y +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_ROCKER is not set # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set +CONFIG_SMC91X=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set @@ -345,6 +391,7 @@ CONFIG_DMASOUND_ATARI=m CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m +# CONFIG_HID_PLANTRONICS is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_GENERIC=m # CONFIG_IOMMU_SUPPORT is not set @@ -354,6 +401,8 @@ CONFIG_NATFEAT=y CONFIG_NFBLOCK=y CONFIG_NFCON=y CONFIG_NFETH=y +CONFIG_ATARI_ETHERNAT=y +CONFIG_ATARI_ETHERNEC=y CONFIG_ATARI_DSP56K=m CONFIG_EXT4_FS=y CONFIG_REISERFS_FS=m @@ -367,6 +416,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y @@ -382,6 +432,7 @@ CONFIG_HFS_FS=m CONFIG_HFSPLUS_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_MINIX_FS=m CONFIG_OMFS_FS=m @@ -451,10 +502,18 @@ CONFIG_DLM=m CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_STRING_HELPERS=m +CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_LKM=m +CONFIG_TEST_USER_COPY=m +CONFIG_TEST_BPF=m +CONFIG_TEST_FIRMWARE=m +CONFIG_TEST_UDELAY=m +CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m @@ -489,13 +548,10 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DRBG_MENU=m +CONFIG_CRYPTO_DRBG_HASH=y +CONFIG_CRYPTO_DRBG_CTR=y CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m # CONFIG_CRYPTO_HW is not set -CONFIG_XZ_DEC_X86=y -CONFIG_XZ_DEC_POWERPC=y -CONFIG_XZ_DEC_IA64=y -CONFIG_XZ_DEC_ARM=y -CONFIG_XZ_DEC_ARMTHUMB=y -CONFIG_XZ_DEC_SPARC=y CONFIG_XZ_DEC_TEST=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index d0e705d1a06..f3bd35e76ea 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -32,6 +32,7 @@ CONFIG_VME=y CONFIG_BVME6000=y # CONFIG_COMPACTION is not set CONFIG_CLEANCACHE=y +CONFIG_ZPOOL=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m @@ -51,6 +52,8 @@ CONFIG_NET_IPIP=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_GENEVE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -92,6 +95,8 @@ CONFIG_NFT_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m CONFIG_NFT_REJECT=m @@ -138,6 +143,7 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -159,6 +165,7 @@ CONFIG_IP_SET_HASH_IPMARK=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_MAC=m CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m CONFIG_IP_SET_HASH_NETNET=m @@ -166,9 +173,12 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_NF_TABLES_ARP=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NFT_MASQ_IPV4=m +CONFIG_NFT_REDIR_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -177,8 +187,7 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_SYNPROXY=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m CONFIG_IP_NF_TARGET_REDIRECT=m @@ -193,6 +202,8 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m +CONFIG_NFT_MASQ_IPV6=m +CONFIG_NFT_REDIR_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -209,17 +220,43 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_TARGET_SYNPROXY=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_NF_NAT_IPV6=m +CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NFT_BRIDGE_META=m +CONFIG_NFT_BRIDGE_REJECT=m +CONFIG_NF_LOG_BRIDGE=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_IP6=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +CONFIG_BRIDGE_EBT_NFLOG=m CONFIG_IP_DCCP=m # CONFIG_IP_DCCP_CCID3 is not set CONFIG_SCTP_COOKIE_HMAC_SHA1=y CONFIG_RDS=m CONFIG_RDS_TCP=m CONFIG_L2TP=m +CONFIG_BRIDGE=m CONFIG_ATALK=m +CONFIG_6LOWPAN=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m CONFIG_BATMAN_ADV_DAT=y @@ -228,9 +265,10 @@ CONFIG_BATMAN_ADV_MCAST=y CONFIG_NETLINK_DIAG=m CONFIG_NET_MPLS_GSO=m # CONFIG_WIRELESS is not set +# CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FIRMWARE_IN_KERNEL is not set -# CONFIG_FW_LOADER_USER_HELPER is not set CONFIG_CONNECTOR=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_CRYPTOLOOP=m @@ -280,6 +318,9 @@ CONFIG_NET_TEAM_MODE_ROUNDROBIN=m CONFIG_NET_TEAM_MODE_RANDOM=m CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m CONFIG_NET_TEAM_MODE_LOADBALANCE=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -290,6 +331,8 @@ CONFIG_BVME6000_NET=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_ROCKER is not set # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set @@ -326,6 +369,7 @@ CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set +# CONFIG_HID_PLANTRONICS is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_GENERIC=m @@ -343,6 +387,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y @@ -358,6 +403,7 @@ CONFIG_HFS_FS=m CONFIG_HFSPLUS_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_MINIX_FS=m CONFIG_OMFS_FS=m @@ -427,10 +473,18 @@ CONFIG_DLM=m CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_STRING_HELPERS=m +CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_LKM=m +CONFIG_TEST_USER_COPY=m +CONFIG_TEST_BPF=m +CONFIG_TEST_FIRMWARE=m +CONFIG_TEST_UDELAY=m +CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m @@ -465,13 +519,10 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DRBG_MENU=m +CONFIG_CRYPTO_DRBG_HASH=y +CONFIG_CRYPTO_DRBG_CTR=y CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m # CONFIG_CRYPTO_HW is not set -CONFIG_XZ_DEC_X86=y -CONFIG_XZ_DEC_POWERPC=y -CONFIG_XZ_DEC_IA64=y -CONFIG_XZ_DEC_ARM=y -CONFIG_XZ_DEC_ARMTHUMB=y -CONFIG_XZ_DEC_SPARC=y CONFIG_XZ_DEC_TEST=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index fdc7e967224..9f9793fb2b7 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -34,6 +34,7 @@ CONFIG_M68060=y CONFIG_HP300=y # CONFIG_COMPACTION is not set CONFIG_CLEANCACHE=y +CONFIG_ZPOOL=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m @@ -53,6 +54,8 @@ CONFIG_NET_IPIP=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_GENEVE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -94,6 +97,8 @@ CONFIG_NFT_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m CONFIG_NFT_REJECT=m @@ -140,6 +145,7 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -161,6 +167,7 @@ CONFIG_IP_SET_HASH_IPMARK=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_MAC=m CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m CONFIG_IP_SET_HASH_NETNET=m @@ -168,9 +175,12 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_NF_TABLES_ARP=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NFT_MASQ_IPV4=m +CONFIG_NFT_REDIR_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -179,8 +189,7 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_SYNPROXY=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m CONFIG_IP_NF_TARGET_REDIRECT=m @@ -195,6 +204,8 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m +CONFIG_NFT_MASQ_IPV6=m +CONFIG_NFT_REDIR_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -211,17 +222,43 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_TARGET_SYNPROXY=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_NF_NAT_IPV6=m +CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NFT_BRIDGE_META=m +CONFIG_NFT_BRIDGE_REJECT=m +CONFIG_NF_LOG_BRIDGE=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_IP6=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +CONFIG_BRIDGE_EBT_NFLOG=m CONFIG_IP_DCCP=m # CONFIG_IP_DCCP_CCID3 is not set CONFIG_SCTP_COOKIE_HMAC_SHA1=y CONFIG_RDS=m CONFIG_RDS_TCP=m CONFIG_L2TP=m +CONFIG_BRIDGE=m CONFIG_ATALK=m +CONFIG_6LOWPAN=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m CONFIG_BATMAN_ADV_DAT=y @@ -230,9 +267,10 @@ CONFIG_BATMAN_ADV_MCAST=y CONFIG_NETLINK_DIAG=m CONFIG_NET_MPLS_GSO=m # CONFIG_WIRELESS is not set +# CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FIRMWARE_IN_KERNEL is not set -# CONFIG_FW_LOADER_USER_HELPER is not set CONFIG_CONNECTOR=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_CRYPTOLOOP=m @@ -281,6 +319,9 @@ CONFIG_NET_TEAM_MODE_ROUNDROBIN=m CONFIG_NET_TEAM_MODE_RANDOM=m CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m CONFIG_NET_TEAM_MODE_LOADBALANCE=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -292,6 +333,8 @@ CONFIG_HPLANCE=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_ROCKER is not set # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set @@ -335,6 +378,7 @@ CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set +# CONFIG_HID_PLANTRONICS is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_GENERIC=m @@ -352,6 +396,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y @@ -367,6 +412,7 @@ CONFIG_HFS_FS=m CONFIG_HFSPLUS_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_MINIX_FS=m CONFIG_OMFS_FS=m @@ -436,10 +482,18 @@ CONFIG_DLM=m CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_STRING_HELPERS=m +CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_LKM=m +CONFIG_TEST_USER_COPY=m +CONFIG_TEST_BPF=m +CONFIG_TEST_FIRMWARE=m +CONFIG_TEST_UDELAY=m +CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m @@ -474,13 +528,10 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DRBG_MENU=m +CONFIG_CRYPTO_DRBG_HASH=y +CONFIG_CRYPTO_DRBG_CTR=y CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m # CONFIG_CRYPTO_HW is not set -CONFIG_XZ_DEC_X86=y -CONFIG_XZ_DEC_POWERPC=y -CONFIG_XZ_DEC_IA64=y -CONFIG_XZ_DEC_ARM=y -CONFIG_XZ_DEC_ARMTHUMB=y -CONFIG_XZ_DEC_SPARC=y CONFIG_XZ_DEC_TEST=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 3d345641d5a..89f225c01a0 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -33,6 +33,7 @@ CONFIG_M68KFPU_EMU=y CONFIG_MAC=y # CONFIG_COMPACTION is not set CONFIG_CLEANCACHE=y +CONFIG_ZPOOL=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m @@ -52,6 +53,8 @@ CONFIG_NET_IPIP=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_GENEVE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -93,6 +96,8 @@ CONFIG_NFT_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m CONFIG_NFT_REJECT=m @@ -139,6 +144,7 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -160,6 +166,7 @@ CONFIG_IP_SET_HASH_IPMARK=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_MAC=m CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m CONFIG_IP_SET_HASH_NETNET=m @@ -167,9 +174,12 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_NF_TABLES_ARP=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NFT_MASQ_IPV4=m +CONFIG_NFT_REDIR_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -178,8 +188,7 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_SYNPROXY=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m CONFIG_IP_NF_TARGET_REDIRECT=m @@ -194,6 +203,8 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m +CONFIG_NFT_MASQ_IPV6=m +CONFIG_NFT_REDIR_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -210,20 +221,46 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_TARGET_SYNPROXY=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_NF_NAT_IPV6=m +CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NFT_BRIDGE_META=m +CONFIG_NFT_BRIDGE_REJECT=m +CONFIG_NF_LOG_BRIDGE=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_IP6=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +CONFIG_BRIDGE_EBT_NFLOG=m CONFIG_IP_DCCP=m # CONFIG_IP_DCCP_CCID3 is not set CONFIG_SCTP_COOKIE_HMAC_SHA1=y CONFIG_RDS=m CONFIG_RDS_TCP=m CONFIG_L2TP=m +CONFIG_BRIDGE=m CONFIG_ATALK=m CONFIG_DEV_APPLETALK=m CONFIG_IPDDP=m CONFIG_IPDDP_ENCAP=y +CONFIG_6LOWPAN=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m CONFIG_BATMAN_ADV_DAT=y @@ -232,9 +269,10 @@ CONFIG_BATMAN_ADV_MCAST=y CONFIG_NETLINK_DIAG=m CONFIG_NET_MPLS_GSO=m # CONFIG_WIRELESS is not set +# CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FIRMWARE_IN_KERNEL is not set -# CONFIG_FW_LOADER_USER_HELPER is not set CONFIG_CONNECTOR=m CONFIG_BLK_DEV_SWIM=m CONFIG_BLK_DEV_LOOP=y @@ -297,6 +335,9 @@ CONFIG_NET_TEAM_MODE_ROUNDROBIN=m CONFIG_NET_TEAM_MODE_RANDOM=m CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m CONFIG_NET_TEAM_MODE_LOADBALANCE=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -310,6 +351,8 @@ CONFIG_MAC89x0=y # CONFIG_NET_VENDOR_MICREL is not set CONFIG_MACSONIC=y CONFIG_MAC8390=y +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_ROCKER is not set # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_SMSC is not set @@ -357,6 +400,7 @@ CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set +# CONFIG_HID_PLANTRONICS is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_GENERIC=m @@ -374,6 +418,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y @@ -389,6 +434,7 @@ CONFIG_HFS_FS=m CONFIG_HFSPLUS_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_MINIX_FS=m CONFIG_OMFS_FS=m @@ -458,11 +504,18 @@ CONFIG_DLM=m CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_STRING_HELPERS=m +CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_LKM=m +CONFIG_TEST_USER_COPY=m +CONFIG_TEST_BPF=m +CONFIG_TEST_FIRMWARE=m +CONFIG_TEST_UDELAY=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m @@ -497,13 +550,10 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DRBG_MENU=m +CONFIG_CRYPTO_DRBG_HASH=y +CONFIG_CRYPTO_DRBG_CTR=y CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m # CONFIG_CRYPTO_HW is not set -CONFIG_XZ_DEC_X86=y -CONFIG_XZ_DEC_POWERPC=y -CONFIG_XZ_DEC_IA64=y -CONFIG_XZ_DEC_ARM=y -CONFIG_XZ_DEC_ARMTHUMB=y -CONFIG_XZ_DEC_SPARC=y CONFIG_XZ_DEC_TEST=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 59aa4209600..d3cdb5447a2 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -39,9 +39,11 @@ CONFIG_SUN3X=y CONFIG_Q40=y CONFIG_ZORRO=y CONFIG_AMIGA_PCMCIA=y +CONFIG_ATARI_ROM_ISA=y CONFIG_ZORRO_NAMES=y # CONFIG_COMPACTION is not set CONFIG_CLEANCACHE=y +CONFIG_ZPOOL=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m @@ -61,6 +63,8 @@ CONFIG_NET_IPIP=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_GENEVE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -102,6 +106,8 @@ CONFIG_NFT_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m CONFIG_NFT_REJECT=m @@ -148,6 +154,7 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -169,6 +176,7 @@ CONFIG_IP_SET_HASH_IPMARK=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_MAC=m CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m CONFIG_IP_SET_HASH_NETNET=m @@ -176,9 +184,12 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_NF_TABLES_ARP=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NFT_MASQ_IPV4=m +CONFIG_NFT_REDIR_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -187,8 +198,7 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_SYNPROXY=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m CONFIG_IP_NF_TARGET_REDIRECT=m @@ -203,6 +213,8 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m +CONFIG_NFT_MASQ_IPV6=m +CONFIG_NFT_REDIR_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -219,20 +231,46 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_TARGET_SYNPROXY=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_NF_NAT_IPV6=m +CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NFT_BRIDGE_META=m +CONFIG_NFT_BRIDGE_REJECT=m +CONFIG_NF_LOG_BRIDGE=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_IP6=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +CONFIG_BRIDGE_EBT_NFLOG=m CONFIG_IP_DCCP=m # CONFIG_IP_DCCP_CCID3 is not set CONFIG_SCTP_COOKIE_HMAC_SHA1=y CONFIG_RDS=m CONFIG_RDS_TCP=m CONFIG_L2TP=m +CONFIG_BRIDGE=m CONFIG_ATALK=m CONFIG_DEV_APPLETALK=m CONFIG_IPDDP=m CONFIG_IPDDP_ENCAP=y +CONFIG_6LOWPAN=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m CONFIG_BATMAN_ADV_DAT=y @@ -241,9 +279,10 @@ CONFIG_BATMAN_ADV_MCAST=y CONFIG_NETLINK_DIAG=m CONFIG_NET_MPLS_GSO=m # CONFIG_WIRELESS is not set +# CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FIRMWARE_IN_KERNEL is not set -# CONFIG_FW_LOADER_USER_HELPER is not set CONFIG_CONNECTOR=m CONFIG_PARPORT=m CONFIG_PARPORT_PC=m @@ -329,6 +368,9 @@ CONFIG_NET_TEAM_MODE_ROUNDROBIN=m CONFIG_NET_TEAM_MODE_RANDOM=m CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m CONFIG_NET_TEAM_MODE_LOADBALANCE=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -352,11 +394,14 @@ CONFIG_MVME16x_NET=y CONFIG_MACSONIC=y CONFIG_HYDRA=y CONFIG_MAC8390=y -CONFIG_NE2000=m +CONFIG_NE2000=y CONFIG_APNE=y CONFIG_ZORRO8390=y +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_ROCKER is not set # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set +CONFIG_SMC91X=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set @@ -423,6 +468,7 @@ CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set +# CONFIG_HID_PLANTRONICS is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_MSM6242=m @@ -435,6 +481,8 @@ CONFIG_NATFEAT=y CONFIG_NFBLOCK=y CONFIG_NFCON=y CONFIG_NFETH=y +CONFIG_ATARI_ETHERNAT=y +CONFIG_ATARI_ETHERNEC=y CONFIG_ATARI_DSP56K=m CONFIG_AMIGA_BUILTIN_SERIAL=y CONFIG_SERIAL_CONSOLE=y @@ -450,6 +498,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y @@ -465,6 +514,7 @@ CONFIG_HFS_FS=m CONFIG_HFSPLUS_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_MINIX_FS=m CONFIG_OMFS_FS=m @@ -534,11 +584,18 @@ CONFIG_DLM=m CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_STRING_HELPERS=m +CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_LKM=m +CONFIG_TEST_USER_COPY=m +CONFIG_TEST_BPF=m +CONFIG_TEST_FIRMWARE=m +CONFIG_TEST_UDELAY=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m @@ -573,13 +630,10 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DRBG_MENU=m +CONFIG_CRYPTO_DRBG_HASH=y +CONFIG_CRYPTO_DRBG_CTR=y CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m # CONFIG_CRYPTO_HW is not set -CONFIG_XZ_DEC_X86=y -CONFIG_XZ_DEC_POWERPC=y -CONFIG_XZ_DEC_IA64=y -CONFIG_XZ_DEC_ARM=y -CONFIG_XZ_DEC_ARMTHUMB=y -CONFIG_XZ_DEC_SPARC=y CONFIG_XZ_DEC_TEST=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 066b24af095..b4c76640973 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -31,6 +31,7 @@ CONFIG_VME=y CONFIG_MVME147=y # CONFIG_COMPACTION is not set CONFIG_CLEANCACHE=y +CONFIG_ZPOOL=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m @@ -50,6 +51,8 @@ CONFIG_NET_IPIP=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_GENEVE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -91,6 +94,8 @@ CONFIG_NFT_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m CONFIG_NFT_REJECT=m @@ -137,6 +142,7 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -158,6 +164,7 @@ CONFIG_IP_SET_HASH_IPMARK=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_MAC=m CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m CONFIG_IP_SET_HASH_NETNET=m @@ -165,9 +172,12 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_NF_TABLES_ARP=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NFT_MASQ_IPV4=m +CONFIG_NFT_REDIR_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -176,8 +186,7 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_SYNPROXY=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m CONFIG_IP_NF_TARGET_REDIRECT=m @@ -192,6 +201,8 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m +CONFIG_NFT_MASQ_IPV6=m +CONFIG_NFT_REDIR_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -208,17 +219,43 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_TARGET_SYNPROXY=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_NF_NAT_IPV6=m +CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NFT_BRIDGE_META=m +CONFIG_NFT_BRIDGE_REJECT=m +CONFIG_NF_LOG_BRIDGE=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_IP6=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +CONFIG_BRIDGE_EBT_NFLOG=m CONFIG_IP_DCCP=m # CONFIG_IP_DCCP_CCID3 is not set CONFIG_SCTP_COOKIE_HMAC_SHA1=y CONFIG_RDS=m CONFIG_RDS_TCP=m CONFIG_L2TP=m +CONFIG_BRIDGE=m CONFIG_ATALK=m +CONFIG_6LOWPAN=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m CONFIG_BATMAN_ADV_DAT=y @@ -227,9 +264,10 @@ CONFIG_BATMAN_ADV_MCAST=y CONFIG_NETLINK_DIAG=m CONFIG_NET_MPLS_GSO=m # CONFIG_WIRELESS is not set +# CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FIRMWARE_IN_KERNEL is not set -# CONFIG_FW_LOADER_USER_HELPER is not set CONFIG_CONNECTOR=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_CRYPTOLOOP=m @@ -279,6 +317,9 @@ CONFIG_NET_TEAM_MODE_ROUNDROBIN=m CONFIG_NET_TEAM_MODE_RANDOM=m CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m CONFIG_NET_TEAM_MODE_LOADBALANCE=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -290,6 +331,8 @@ CONFIG_MVME147_NET=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_ROCKER is not set # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set @@ -326,6 +369,7 @@ CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set +# CONFIG_HID_PLANTRONICS is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_GENERIC=m @@ -343,6 +387,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y @@ -358,6 +403,7 @@ CONFIG_HFS_FS=m CONFIG_HFSPLUS_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_MINIX_FS=m CONFIG_OMFS_FS=m @@ -427,10 +473,18 @@ CONFIG_DLM=m CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_STRING_HELPERS=m +CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_LKM=m +CONFIG_TEST_USER_COPY=m +CONFIG_TEST_BPF=m +CONFIG_TEST_FIRMWARE=m +CONFIG_TEST_UDELAY=m +CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m @@ -465,13 +519,10 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DRBG_MENU=m +CONFIG_CRYPTO_DRBG_HASH=y +CONFIG_CRYPTO_DRBG_CTR=y CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m # CONFIG_CRYPTO_HW is not set -CONFIG_XZ_DEC_X86=y -CONFIG_XZ_DEC_POWERPC=y -CONFIG_XZ_DEC_IA64=y -CONFIG_XZ_DEC_ARM=y -CONFIG_XZ_DEC_ARMTHUMB=y -CONFIG_XZ_DEC_SPARC=y CONFIG_XZ_DEC_TEST=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 9326ea664a5..0d4a26f9b58 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -32,6 +32,7 @@ CONFIG_VME=y CONFIG_MVME16x=y # CONFIG_COMPACTION is not set CONFIG_CLEANCACHE=y +CONFIG_ZPOOL=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m @@ -51,6 +52,8 @@ CONFIG_NET_IPIP=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_GENEVE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -92,6 +95,8 @@ CONFIG_NFT_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m CONFIG_NFT_REJECT=m @@ -138,6 +143,7 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -159,6 +165,7 @@ CONFIG_IP_SET_HASH_IPMARK=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_MAC=m CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m CONFIG_IP_SET_HASH_NETNET=m @@ -166,9 +173,12 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_NF_TABLES_ARP=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NFT_MASQ_IPV4=m +CONFIG_NFT_REDIR_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -177,8 +187,7 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_SYNPROXY=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m CONFIG_IP_NF_TARGET_REDIRECT=m @@ -193,6 +202,8 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m +CONFIG_NFT_MASQ_IPV6=m +CONFIG_NFT_REDIR_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -209,17 +220,43 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_TARGET_SYNPROXY=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_NF_NAT_IPV6=m +CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NFT_BRIDGE_META=m +CONFIG_NFT_BRIDGE_REJECT=m +CONFIG_NF_LOG_BRIDGE=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_IP6=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +CONFIG_BRIDGE_EBT_NFLOG=m CONFIG_IP_DCCP=m # CONFIG_IP_DCCP_CCID3 is not set CONFIG_SCTP_COOKIE_HMAC_SHA1=y CONFIG_RDS=m CONFIG_RDS_TCP=m CONFIG_L2TP=m +CONFIG_BRIDGE=m CONFIG_ATALK=m +CONFIG_6LOWPAN=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m CONFIG_BATMAN_ADV_DAT=y @@ -228,9 +265,10 @@ CONFIG_BATMAN_ADV_MCAST=y CONFIG_NETLINK_DIAG=m CONFIG_NET_MPLS_GSO=m # CONFIG_WIRELESS is not set +# CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FIRMWARE_IN_KERNEL is not set -# CONFIG_FW_LOADER_USER_HELPER is not set CONFIG_CONNECTOR=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_CRYPTOLOOP=m @@ -280,6 +318,9 @@ CONFIG_NET_TEAM_MODE_ROUNDROBIN=m CONFIG_NET_TEAM_MODE_RANDOM=m CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m CONFIG_NET_TEAM_MODE_LOADBALANCE=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -290,6 +331,8 @@ CONFIG_MVME16x_NET=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_ROCKER is not set # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set @@ -326,6 +369,7 @@ CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set +# CONFIG_HID_PLANTRONICS is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_GENERIC=m @@ -343,6 +387,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y @@ -358,6 +403,7 @@ CONFIG_HFS_FS=m CONFIG_HFSPLUS_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_MINIX_FS=m CONFIG_OMFS_FS=m @@ -427,11 +473,18 @@ CONFIG_DLM=m CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_STRING_HELPERS=m +CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_LKM=m +CONFIG_TEST_USER_COPY=m +CONFIG_TEST_BPF=m +CONFIG_TEST_FIRMWARE=m +CONFIG_TEST_UDELAY=m CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m @@ -466,13 +519,10 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DRBG_MENU=m +CONFIG_CRYPTO_DRBG_HASH=y +CONFIG_CRYPTO_DRBG_CTR=y CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m # CONFIG_CRYPTO_HW is not set -CONFIG_XZ_DEC_X86=y -CONFIG_XZ_DEC_POWERPC=y -CONFIG_XZ_DEC_IA64=y -CONFIG_XZ_DEC_ARM=y -CONFIG_XZ_DEC_ARMTHUMB=y -CONFIG_XZ_DEC_SPARC=y CONFIG_XZ_DEC_TEST=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index d7d1101e31b..5d581c503fa 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -32,6 +32,7 @@ CONFIG_M68060=y CONFIG_Q40=y # CONFIG_COMPACTION is not set CONFIG_CLEANCACHE=y +CONFIG_ZPOOL=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m @@ -51,6 +52,8 @@ CONFIG_NET_IPIP=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_GENEVE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -92,6 +95,8 @@ CONFIG_NFT_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m CONFIG_NFT_REJECT=m @@ -138,6 +143,7 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -159,6 +165,7 @@ CONFIG_IP_SET_HASH_IPMARK=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_MAC=m CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m CONFIG_IP_SET_HASH_NETNET=m @@ -166,9 +173,12 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_NF_TABLES_ARP=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NFT_MASQ_IPV4=m +CONFIG_NFT_REDIR_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -177,8 +187,7 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_SYNPROXY=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m CONFIG_IP_NF_TARGET_REDIRECT=m @@ -193,6 +202,8 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m +CONFIG_NFT_MASQ_IPV6=m +CONFIG_NFT_REDIR_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -209,17 +220,43 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_TARGET_SYNPROXY=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_NF_NAT_IPV6=m +CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NFT_BRIDGE_META=m +CONFIG_NFT_BRIDGE_REJECT=m +CONFIG_NF_LOG_BRIDGE=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_IP6=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +CONFIG_BRIDGE_EBT_NFLOG=m CONFIG_IP_DCCP=m # CONFIG_IP_DCCP_CCID3 is not set CONFIG_SCTP_COOKIE_HMAC_SHA1=y CONFIG_RDS=m CONFIG_RDS_TCP=m CONFIG_L2TP=m +CONFIG_BRIDGE=m CONFIG_ATALK=m +CONFIG_6LOWPAN=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m CONFIG_BATMAN_ADV_DAT=y @@ -228,9 +265,10 @@ CONFIG_BATMAN_ADV_MCAST=y CONFIG_NETLINK_DIAG=m CONFIG_NET_MPLS_GSO=m # CONFIG_WIRELESS is not set +# CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FIRMWARE_IN_KERNEL is not set -# CONFIG_FW_LOADER_USER_HELPER is not set CONFIG_CONNECTOR=m CONFIG_PARPORT=m CONFIG_PARPORT_PC=m @@ -286,6 +324,9 @@ CONFIG_NET_TEAM_MODE_ROUNDROBIN=m CONFIG_NET_TEAM_MODE_RANDOM=m CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m CONFIG_NET_TEAM_MODE_LOADBALANCE=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -300,6 +341,8 @@ CONFIG_VETH=m # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set CONFIG_NE2000=m +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_ROCKER is not set # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_SMSC is not set @@ -347,6 +390,7 @@ CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set +# CONFIG_HID_PLANTRONICS is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_GENERIC=m @@ -365,6 +409,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y @@ -380,6 +425,7 @@ CONFIG_HFS_FS=m CONFIG_HFSPLUS_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_MINIX_FS=m CONFIG_OMFS_FS=m @@ -449,10 +495,18 @@ CONFIG_DLM=m CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_STRING_HELPERS=m +CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_LKM=m +CONFIG_TEST_USER_COPY=m +CONFIG_TEST_BPF=m +CONFIG_TEST_FIRMWARE=m +CONFIG_TEST_UDELAY=m +CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m @@ -487,13 +541,10 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DRBG_MENU=m +CONFIG_CRYPTO_DRBG_HASH=y +CONFIG_CRYPTO_DRBG_CTR=y CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m # CONFIG_CRYPTO_HW is not set -CONFIG_XZ_DEC_X86=y -CONFIG_XZ_DEC_POWERPC=y -CONFIG_XZ_DEC_IA64=y -CONFIG_XZ_DEC_ARM=y -CONFIG_XZ_DEC_ARMTHUMB=y -CONFIG_XZ_DEC_SPARC=y CONFIG_XZ_DEC_TEST=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 98522e8fb85..c6b49a4a887 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -29,6 +29,7 @@ CONFIG_BOOTINFO_PROC=y CONFIG_SUN3=y # CONFIG_COMPACTION is not set CONFIG_CLEANCACHE=y +CONFIG_ZPOOL=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m @@ -48,6 +49,8 @@ CONFIG_NET_IPIP=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_GENEVE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -89,6 +92,8 @@ CONFIG_NFT_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m CONFIG_NFT_REJECT=m @@ -135,6 +140,7 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -156,6 +162,7 @@ CONFIG_IP_SET_HASH_IPMARK=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_MAC=m CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m CONFIG_IP_SET_HASH_NETNET=m @@ -163,9 +170,12 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_NF_TABLES_ARP=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NFT_MASQ_IPV4=m +CONFIG_NFT_REDIR_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -174,8 +184,7 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_SYNPROXY=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m CONFIG_IP_NF_TARGET_REDIRECT=m @@ -190,6 +199,8 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m +CONFIG_NFT_MASQ_IPV6=m +CONFIG_NFT_REDIR_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -206,17 +217,43 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_TARGET_SYNPROXY=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_NF_NAT_IPV6=m +CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NFT_BRIDGE_META=m +CONFIG_NFT_BRIDGE_REJECT=m +CONFIG_NF_LOG_BRIDGE=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_IP6=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +CONFIG_BRIDGE_EBT_NFLOG=m CONFIG_IP_DCCP=m # CONFIG_IP_DCCP_CCID3 is not set CONFIG_SCTP_COOKIE_HMAC_SHA1=y CONFIG_RDS=m CONFIG_RDS_TCP=m CONFIG_L2TP=m +CONFIG_BRIDGE=m CONFIG_ATALK=m +CONFIG_6LOWPAN=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m CONFIG_BATMAN_ADV_DAT=y @@ -225,9 +262,10 @@ CONFIG_BATMAN_ADV_MCAST=y CONFIG_NETLINK_DIAG=m CONFIG_NET_MPLS_GSO=m # CONFIG_WIRELESS is not set +# CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FIRMWARE_IN_KERNEL is not set -# CONFIG_FW_LOADER_USER_HELPER is not set CONFIG_CONNECTOR=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_CRYPTOLOOP=m @@ -277,6 +315,9 @@ CONFIG_NET_TEAM_MODE_ROUNDROBIN=m CONFIG_NET_TEAM_MODE_RANDOM=m CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m CONFIG_NET_TEAM_MODE_LOADBALANCE=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -287,6 +328,8 @@ CONFIG_SUN3_82586=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_ROCKER is not set # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set @@ -327,6 +370,7 @@ CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set +# CONFIG_HID_PLANTRONICS is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_GENERIC=m @@ -344,6 +388,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y @@ -359,6 +404,7 @@ CONFIG_HFS_FS=m CONFIG_HFSPLUS_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_MINIX_FS=m CONFIG_OMFS_FS=m @@ -428,10 +474,17 @@ CONFIG_DLM=m CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_STRING_HELPERS=m +CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_LKM=m +CONFIG_TEST_USER_COPY=m +CONFIG_TEST_BPF=m +CONFIG_TEST_FIRMWARE=m +CONFIG_TEST_UDELAY=m CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m @@ -466,13 +519,10 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DRBG_MENU=m +CONFIG_CRYPTO_DRBG_HASH=y +CONFIG_CRYPTO_DRBG_CTR=y CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m # CONFIG_CRYPTO_HW is not set -CONFIG_XZ_DEC_X86=y -CONFIG_XZ_DEC_POWERPC=y -CONFIG_XZ_DEC_IA64=y -CONFIG_XZ_DEC_ARM=y -CONFIG_XZ_DEC_ARMTHUMB=y -CONFIG_XZ_DEC_SPARC=y CONFIG_XZ_DEC_TEST=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 5128a8c3f4e..b65785eaff8 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -29,6 +29,7 @@ CONFIG_BOOTINFO_PROC=y CONFIG_SUN3X=y # CONFIG_COMPACTION is not set CONFIG_CLEANCACHE=y +CONFIG_ZPOOL=m # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m @@ -48,6 +49,8 @@ CONFIG_NET_IPIP=m CONFIG_NET_IPGRE_DEMUX=m CONFIG_NET_IPGRE=m CONFIG_NET_IPVTI=m +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_GENEVE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m @@ -89,6 +92,8 @@ CONFIG_NFT_HASH=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m CONFIG_NFT_QUEUE=m CONFIG_NFT_REJECT=m @@ -135,6 +140,7 @@ CONFIG_NETFILTER_XT_MATCH_NFACCT=m CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m +CONFIG_NETFILTER_XT_MATCH_PHYSDEV=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m @@ -156,6 +162,7 @@ CONFIG_IP_SET_HASH_IPMARK=m CONFIG_IP_SET_HASH_IPPORT=m CONFIG_IP_SET_HASH_IPPORTIP=m CONFIG_IP_SET_HASH_IPPORTNET=m +CONFIG_IP_SET_HASH_MAC=m CONFIG_IP_SET_HASH_NETPORTNET=m CONFIG_IP_SET_HASH_NET=m CONFIG_IP_SET_HASH_NETNET=m @@ -163,9 +170,12 @@ CONFIG_IP_SET_HASH_NETPORT=m CONFIG_IP_SET_HASH_NETIFACE=m CONFIG_IP_SET_LIST_SET=m CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_NF_LOG_ARP=m CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_NF_TABLES_ARP=m +CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_NFT_MASQ_IPV4=m +CONFIG_NFT_REDIR_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -174,8 +184,7 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_SYNPROXY=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_NF_NAT_IPV4=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m CONFIG_IP_NF_TARGET_REDIRECT=m @@ -190,6 +199,8 @@ CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m +CONFIG_NFT_MASQ_IPV6=m +CONFIG_NFT_REDIR_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -206,17 +217,43 @@ CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_TARGET_SYNPROXY=m CONFIG_IP6_NF_MANGLE=m CONFIG_IP6_NF_RAW=m -CONFIG_NF_NAT_IPV6=m +CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m CONFIG_IP6_NF_TARGET_NPT=m CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NFT_BRIDGE_META=m +CONFIG_NFT_BRIDGE_REJECT=m +CONFIG_NF_LOG_BRIDGE=m +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_IP6=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +CONFIG_BRIDGE_EBT_NFLOG=m CONFIG_IP_DCCP=m # CONFIG_IP_DCCP_CCID3 is not set CONFIG_SCTP_COOKIE_HMAC_SHA1=y CONFIG_RDS=m CONFIG_RDS_TCP=m CONFIG_L2TP=m +CONFIG_BRIDGE=m CONFIG_ATALK=m +CONFIG_6LOWPAN=m CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=m CONFIG_BATMAN_ADV_DAT=y @@ -225,9 +262,10 @@ CONFIG_BATMAN_ADV_MCAST=y CONFIG_NETLINK_DIAG=m CONFIG_NET_MPLS_GSO=m # CONFIG_WIRELESS is not set +# CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FIRMWARE_IN_KERNEL is not set -# CONFIG_FW_LOADER_USER_HELPER is not set CONFIG_CONNECTOR=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_CRYPTOLOOP=m @@ -277,6 +315,9 @@ CONFIG_NET_TEAM_MODE_ROUNDROBIN=m CONFIG_NET_TEAM_MODE_RANDOM=m CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m CONFIG_NET_TEAM_MODE_LOADBALANCE=m +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m +CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -288,6 +329,8 @@ CONFIG_SUN3LANCE=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_ROCKER is not set # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_STMICRO is not set @@ -327,6 +370,7 @@ CONFIG_HID=m CONFIG_HIDRAW=y CONFIG_UHID=m # CONFIG_HID_GENERIC is not set +# CONFIG_HID_PLANTRONICS is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_GENERIC=m @@ -344,6 +388,7 @@ CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y @@ -359,6 +404,7 @@ CONFIG_HFS_FS=m CONFIG_HFSPLUS_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_MINIX_FS=m CONFIG_OMFS_FS=m @@ -428,10 +474,18 @@ CONFIG_DLM=m CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_STRING_HELPERS=m +CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_LKM=m +CONFIG_TEST_USER_COPY=m +CONFIG_TEST_BPF=m +CONFIG_TEST_FIRMWARE=m +CONFIG_TEST_UDELAY=m +CONFIG_EARLY_PRINTK=y CONFIG_ENCRYPTED_KEYS=m CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_USER=m CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_MCRYPTD=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m @@ -466,13 +520,10 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DRBG_MENU=m +CONFIG_CRYPTO_DRBG_HASH=y +CONFIG_CRYPTO_DRBG_CTR=y CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m # CONFIG_CRYPTO_HW is not set -CONFIG_XZ_DEC_X86=y -CONFIG_XZ_DEC_POWERPC=y -CONFIG_XZ_DEC_IA64=y -CONFIG_XZ_DEC_ARM=y -CONFIG_XZ_DEC_ARMTHUMB=y -CONFIG_XZ_DEC_SPARC=y CONFIG_XZ_DEC_TEST=m diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 9b6c691874b..1517ed1c647 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -6,6 +6,7 @@ generic-y += device.h generic-y += emergency-restart.h generic-y += errno.h generic-y += exec.h +generic-y += futex.h generic-y += hw_irq.h generic-y += ioctl.h generic-y += ipcbuf.h diff --git a/arch/m68k/include/asm/atariints.h b/arch/m68k/include/asm/atariints.h index 953e0ac6855..6321c449562 100644 --- a/arch/m68k/include/asm/atariints.h +++ b/arch/m68k/include/asm/atariints.h @@ -40,11 +40,6 @@ /* convert irq_handler index to vector number */ #define IRQ_SOURCE_TO_VECTOR(i) ((i) + ((i) < 8 ? 0x18 : (0x40-8))) -/* interrupt service types */ -#define IRQ_TYPE_SLOW 0 -#define IRQ_TYPE_FAST 1 -#define IRQ_TYPE_PRIO 2 - /* ST-MFP interrupts */ #define IRQ_MFP_BUSY (8) #define IRQ_MFP_DCD (9) diff --git a/arch/m68k/include/asm/futex.h b/arch/m68k/include/asm/futex.h deleted file mode 100644 index bc868af10c9..00000000000 --- a/arch/m68k/include/asm/futex.h +++ /dev/null @@ -1,94 +0,0 @@ -#ifndef _ASM_M68K_FUTEX_H -#define _ASM_M68K_FUTEX_H - -#ifdef __KERNEL__ -#if !defined(CONFIG_MMU) -#include <asm-generic/futex.h> -#else /* CONFIG_MMU */ - -#include <linux/futex.h> -#include <linux/uaccess.h> -#include <asm/errno.h> - -static inline int -futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, - u32 oldval, u32 newval) -{ - u32 val; - - if (unlikely(get_user(val, uaddr) != 0)) - return -EFAULT; - - if (val == oldval && unlikely(put_user(newval, uaddr) != 0)) - return -EFAULT; - - *uval = val; - - return 0; -} - -static inline int -futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) -{ - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; - int oldval, ret; - u32 tmp; - - if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - pagefault_disable(); /* implies preempt_disable() */ - - ret = -EFAULT; - if (unlikely(get_user(oldval, uaddr) != 0)) - goto out_pagefault_enable; - - ret = 0; - tmp = oldval; - - switch (op) { - case FUTEX_OP_SET: - tmp = oparg; - break; - case FUTEX_OP_ADD: - tmp += oparg; - break; - case FUTEX_OP_OR: - tmp |= oparg; - break; - case FUTEX_OP_ANDN: - tmp &= ~oparg; - break; - case FUTEX_OP_XOR: - tmp ^= oparg; - break; - default: - ret = -ENOSYS; - } - - if (ret == 0 && unlikely(put_user(tmp, uaddr) != 0)) - ret = -EFAULT; - -out_pagefault_enable: - pagefault_enable(); /* subsumes preempt_enable() */ - - if (ret == 0) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; - default: ret = -ENOSYS; - } - } - return ret; -} - -#endif /* CONFIG_MMU */ -#endif /* __KERNEL__ */ -#endif /* _ASM_M68K_FUTEX_H */ diff --git a/arch/m68k/include/asm/macintosh.h b/arch/m68k/include/asm/macintosh.h index 29c7c6c3a5f..42235e7fbee 100644 --- a/arch/m68k/include/asm/macintosh.h +++ b/arch/m68k/include/asm/macintosh.h @@ -55,7 +55,7 @@ struct mac_model #define MAC_SCSI_QUADRA3 4 #define MAC_SCSI_IIFX 5 #define MAC_SCSI_DUO 6 -#define MAC_SCSI_CCL 7 +#define MAC_SCSI_LC 7 #define MAC_SCSI_LATE 8 #define MAC_IDE_NONE 0 diff --git a/arch/m68k/include/asm/mcf_pgtable.h b/arch/m68k/include/asm/mcf_pgtable.h index 3c793682e5d..2500ce04fcc 100644 --- a/arch/m68k/include/asm/mcf_pgtable.h +++ b/arch/m68k/include/asm/mcf_pgtable.h @@ -35,7 +35,6 @@ * hitting hardware. */ #define CF_PAGE_DIRTY 0x00000001 -#define CF_PAGE_FILE 0x00000200 #define CF_PAGE_ACCESSED 0x00001000 #define _PAGE_CACHE040 0x020 /* 68040 cache mode, cachable, copyback */ @@ -243,11 +242,6 @@ static inline int pte_young(pte_t pte) return pte_val(pte) & CF_PAGE_ACCESSED; } -static inline int pte_file(pte_t pte) -{ - return pte_val(pte) & CF_PAGE_FILE; -} - static inline int pte_special(pte_t pte) { return 0; @@ -391,26 +385,13 @@ static inline void cache_page(void *vaddr) *ptep = pte_mkcache(*ptep); } -#define PTE_FILE_MAX_BITS 21 -#define PTE_FILE_SHIFT 11 - -static inline unsigned long pte_to_pgoff(pte_t pte) -{ - return pte_val(pte) >> PTE_FILE_SHIFT; -} - -static inline pte_t pgoff_to_pte(unsigned pgoff) -{ - return __pte((pgoff << PTE_FILE_SHIFT) + CF_PAGE_FILE); -} - /* * Encode and de-code a swap entry (must be !pte_none(e) && !pte_present(e)) */ #define __swp_type(x) ((x).val & 0xFF) -#define __swp_offset(x) ((x).val >> PTE_FILE_SHIFT) +#define __swp_offset(x) ((x).val >> 11) #define __swp_entry(typ, off) ((swp_entry_t) { (typ) | \ - (off << PTE_FILE_SHIFT) }) + (off << 11) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) (__pte((x).val)) diff --git a/arch/m68k/include/asm/motorola_pgtable.h b/arch/m68k/include/asm/motorola_pgtable.h index e0fdd4d0807..0085aab80e5 100644 --- a/arch/m68k/include/asm/motorola_pgtable.h +++ b/arch/m68k/include/asm/motorola_pgtable.h @@ -28,7 +28,6 @@ #define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_NOCACHE) #define _PAGE_PROTNONE 0x004 -#define _PAGE_FILE 0x008 /* pagecache or swap? */ #ifndef __ASSEMBLY__ @@ -168,7 +167,6 @@ static inline void pgd_set(pgd_t *pgdp, pmd_t *pmdp) static inline int pte_write(pte_t pte) { return !(pte_val(pte) & _PAGE_RONLY); } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } -static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } static inline int pte_special(pte_t pte) { return 0; } static inline pte_t pte_wrprotect(pte_t pte) { pte_val(pte) |= _PAGE_RONLY; return pte; } @@ -266,19 +264,6 @@ static inline void cache_page(void *vaddr) } } -#define PTE_FILE_MAX_BITS 28 - -static inline unsigned long pte_to_pgoff(pte_t pte) -{ - return pte.pte >> 4; -} - -static inline pte_t pgoff_to_pte(unsigned off) -{ - pte_t pte = { (off << 4) + _PAGE_FILE }; - return pte; -} - /* Encode and de-code a swap entry (must be !pte_none(e) && !pte_present(e)) */ #define __swp_type(x) (((x).val >> 4) & 0xff) #define __swp_offset(x) ((x).val >> 12) diff --git a/arch/m68k/include/asm/pgtable_no.h b/arch/m68k/include/asm/pgtable_no.h index 11859b86b1f..ac7d87a0233 100644 --- a/arch/m68k/include/asm/pgtable_no.h +++ b/arch/m68k/include/asm/pgtable_no.h @@ -37,8 +37,6 @@ extern void paging_init(void); #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -static inline int pte_file(pte_t pte) { return 0; } - /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. diff --git a/arch/m68k/include/asm/sun3_pgtable.h b/arch/m68k/include/asm/sun3_pgtable.h index f55aa04161e..48657f9fdec 100644 --- a/arch/m68k/include/asm/sun3_pgtable.h +++ b/arch/m68k/include/asm/sun3_pgtable.h @@ -38,8 +38,6 @@ #define _PAGE_PRESENT (SUN3_PAGE_VALID) #define _PAGE_ACCESSED (SUN3_PAGE_ACCESSED) -#define PTE_FILE_MAX_BITS 28 - /* Compound page protection values. */ //todo: work out which ones *should* have SUN3_PAGE_NOCACHE and fix... // is it just PAGE_KERNEL and PAGE_SHARED? @@ -168,7 +166,6 @@ static inline void pgd_clear (pgd_t *pgdp) {} static inline int pte_write(pte_t pte) { return pte_val(pte) & SUN3_PAGE_WRITEABLE; } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & SUN3_PAGE_MODIFIED; } static inline int pte_young(pte_t pte) { return pte_val(pte) & SUN3_PAGE_ACCESSED; } -static inline int pte_file(pte_t pte) { return pte_val(pte) & SUN3_PAGE_ACCESSED; } static inline int pte_special(pte_t pte) { return 0; } static inline pte_t pte_wrprotect(pte_t pte) { pte_val(pte) &= ~SUN3_PAGE_WRITEABLE; return pte; } @@ -202,18 +199,6 @@ static inline pmd_t *pmd_offset (pgd_t *pgd, unsigned long address) return (pmd_t *) pgd; } -static inline unsigned long pte_to_pgoff(pte_t pte) -{ - return pte.pte & SUN3_PAGE_PGNUM_MASK; -} - -static inline pte_t pgoff_to_pte(unsigned off) -{ - pte_t pte = { off + SUN3_PAGE_ACCESSED }; - return pte; -} - - /* Find an entry in the third-level pagetable. */ #define pte_index(address) ((address >> PAGE_SHIFT) & (PTRS_PER_PTE-1)) #define pte_offset_kernel(pmd, address) ((pte_t *) __pmd_page(*pmd) + pte_index(address)) diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c index e9c3756139f..689b47d292a 100644 --- a/arch/m68k/mac/config.c +++ b/arch/m68k/mac/config.c @@ -296,7 +296,7 @@ static struct mac_model mac_data_table[] = { .name = "IIvi", .adb_type = MAC_ADB_IISI, .via_type = MAC_VIA_IICI, - .scsi_type = MAC_SCSI_OLD, + .scsi_type = MAC_SCSI_LC, .scc_type = MAC_SCC_II, .nubus_type = MAC_NUBUS, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -305,7 +305,7 @@ static struct mac_model mac_data_table[] = { .name = "IIvx", .adb_type = MAC_ADB_IISI, .via_type = MAC_VIA_IICI, - .scsi_type = MAC_SCSI_OLD, + .scsi_type = MAC_SCSI_LC, .scc_type = MAC_SCC_II, .nubus_type = MAC_NUBUS, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -320,7 +320,7 @@ static struct mac_model mac_data_table[] = { .name = "Classic II", .adb_type = MAC_ADB_IISI, .via_type = MAC_VIA_IICI, - .scsi_type = MAC_SCSI_OLD, + .scsi_type = MAC_SCSI_LC, .scc_type = MAC_SCC_II, .nubus_type = MAC_NUBUS, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -329,7 +329,7 @@ static struct mac_model mac_data_table[] = { .name = "Color Classic", .adb_type = MAC_ADB_CUDA, .via_type = MAC_VIA_IICI, - .scsi_type = MAC_SCSI_CCL, + .scsi_type = MAC_SCSI_LC, .scc_type = MAC_SCC_II, .nubus_type = MAC_NUBUS, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -338,7 +338,7 @@ static struct mac_model mac_data_table[] = { .name = "Color Classic II", .adb_type = MAC_ADB_CUDA, .via_type = MAC_VIA_IICI, - .scsi_type = MAC_SCSI_CCL, + .scsi_type = MAC_SCSI_LC, .scc_type = MAC_SCC_II, .nubus_type = MAC_NUBUS, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -353,7 +353,7 @@ static struct mac_model mac_data_table[] = { .name = "LC", .adb_type = MAC_ADB_IISI, .via_type = MAC_VIA_IICI, - .scsi_type = MAC_SCSI_OLD, + .scsi_type = MAC_SCSI_LC, .scc_type = MAC_SCC_II, .nubus_type = MAC_NUBUS, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -362,7 +362,7 @@ static struct mac_model mac_data_table[] = { .name = "LC II", .adb_type = MAC_ADB_IISI, .via_type = MAC_VIA_IICI, - .scsi_type = MAC_SCSI_OLD, + .scsi_type = MAC_SCSI_LC, .scc_type = MAC_SCC_II, .nubus_type = MAC_NUBUS, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -371,7 +371,7 @@ static struct mac_model mac_data_table[] = { .name = "LC III", .adb_type = MAC_ADB_IISI, .via_type = MAC_VIA_IICI, - .scsi_type = MAC_SCSI_OLD, + .scsi_type = MAC_SCSI_LC, .scc_type = MAC_SCC_II, .nubus_type = MAC_NUBUS, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -499,7 +499,7 @@ static struct mac_model mac_data_table[] = { .name = "Performa 460", .adb_type = MAC_ADB_IISI, .via_type = MAC_VIA_IICI, - .scsi_type = MAC_SCSI_OLD, + .scsi_type = MAC_SCSI_LC, .scc_type = MAC_SCC_II, .nubus_type = MAC_NUBUS, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -526,7 +526,7 @@ static struct mac_model mac_data_table[] = { .name = "Performa 520", .adb_type = MAC_ADB_CUDA, .via_type = MAC_VIA_IICI, - .scsi_type = MAC_SCSI_CCL, + .scsi_type = MAC_SCSI_LC, .scc_type = MAC_SCC_II, .nubus_type = MAC_NUBUS, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -535,7 +535,7 @@ static struct mac_model mac_data_table[] = { .name = "Performa 550", .adb_type = MAC_ADB_CUDA, .via_type = MAC_VIA_IICI, - .scsi_type = MAC_SCSI_CCL, + .scsi_type = MAC_SCSI_LC, .scc_type = MAC_SCC_II, .nubus_type = MAC_NUBUS, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -567,7 +567,7 @@ static struct mac_model mac_data_table[] = { .name = "TV", .adb_type = MAC_ADB_CUDA, .via_type = MAC_VIA_IICI, - .scsi_type = MAC_SCSI_CCL, + .scsi_type = MAC_SCSI_LC, .scc_type = MAC_SCC_II, .nubus_type = MAC_NUBUS, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -576,7 +576,7 @@ static struct mac_model mac_data_table[] = { .name = "Performa 600", .adb_type = MAC_ADB_IISI, .via_type = MAC_VIA_IICI, - .scsi_type = MAC_SCSI_OLD, + .scsi_type = MAC_SCSI_LC, .scc_type = MAC_SCC_II, .nubus_type = MAC_NUBUS, .floppy_type = MAC_FLOPPY_SWIM_ADDR2, @@ -1109,8 +1109,10 @@ int __init mac_platform_init(void) platform_device_register_simple("mac_scsi", 0, mac_scsi_late_rsrc, ARRAY_SIZE(mac_scsi_late_rsrc)); break; - case MAC_SCSI_CCL: - /* Addresses from the Color Classic Developer Note. + case MAC_SCSI_LC: + /* Addresses from Mac LC data in Designing Cards & Drivers 3ed. + * Also from the Developer Notes for Classic II, LC III, + * Color Classic and IIvx. * $50F0 6000 - $50F0 7FFF: SCSI handshake * $50F1 0000 - $50F1 1FFF: SCSI * $50F1 2000 - $50F1 3FFF: SCSI DMA diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c index 1bb3ce6634d..e6a3b56c648 100644 --- a/arch/m68k/mvme147/config.c +++ b/arch/m68k/mvme147/config.c @@ -168,49 +168,3 @@ int mvme147_set_clock_mmss (unsigned long nowtime) { return 0; } - -/*------------------- Serial console stuff ------------------------*/ - -static void scc_delay (void) -{ - int n; - volatile int trash; - - for (n = 0; n < 20; n++) - trash = n; -} - -static void scc_write (char ch) -{ - volatile char *p = (volatile char *)M147_SCC_A_ADDR; - - do { - scc_delay(); - } - while (!(*p & 4)); - scc_delay(); - *p = 8; - scc_delay(); - *p = ch; -} - - -void m147_scc_write (struct console *co, const char *str, unsigned count) -{ - unsigned long flags; - - local_irq_save(flags); - - while (count--) - { - if (*str == '\n') - scc_write ('\r'); - scc_write (*str++); - } - local_irq_restore(flags); -} - -void mvme147_init_console_port (struct console *co, int cflag) -{ - co->write = m147_scc_write; -} diff --git a/arch/m68k/mvme16x/rtc.c b/arch/m68k/mvme16x/rtc.c index 6ef7a81a3b1..1755e2f7137 100644 --- a/arch/m68k/mvme16x/rtc.c +++ b/arch/m68k/mvme16x/rtc.c @@ -161,4 +161,4 @@ static int __init rtc_MK48T08_init(void) printk(KERN_INFO "MK48T08 Real Time Clock Driver v%s\n", RTC_VERSION); return misc_register(&rtc_dev); } -module_init(rtc_MK48T08_init); +device_initcall(rtc_MK48T08_init); diff --git a/arch/metag/include/asm/pgtable.h b/arch/metag/include/asm/pgtable.h index 0d9dc548729..d0604c0a870 100644 --- a/arch/metag/include/asm/pgtable.h +++ b/arch/metag/include/asm/pgtable.h @@ -47,7 +47,6 @@ */ #define _PAGE_ACCESSED _PAGE_ALWAYS_ZERO_1 #define _PAGE_DIRTY _PAGE_ALWAYS_ZERO_2 -#define _PAGE_FILE _PAGE_ALWAYS_ZERO_3 /* Pages owned, and protected by, the kernel. */ #define _PAGE_KERNEL _PAGE_PRIV @@ -219,7 +218,6 @@ extern unsigned long empty_zero_page; static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_WRITE; } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } -static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } static inline int pte_special(pte_t pte) { return 0; } static inline pte_t pte_wrprotect(pte_t pte) { pte_val(pte) &= (~_PAGE_WRITE); return pte; } @@ -327,10 +325,6 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define PTE_FILE_MAX_BITS 22 -#define pte_to_pgoff(x) (pte_val(x) >> 10) -#define pgoff_to_pte(x) __pte(((x) << 10) | _PAGE_FILE) - #define kern_addr_valid(addr) (1) /* diff --git a/arch/microblaze/boot/Makefile b/arch/microblaze/boot/Makefile index 8e211cc28da..91d2068da1b 100644 --- a/arch/microblaze/boot/Makefile +++ b/arch/microblaze/boot/Makefile @@ -34,5 +34,4 @@ $(obj)/simpleImage.%: vmlinux FORCE $(call if_changed,strip) @echo 'Kernel: $@ is ready' ' (#'`cat .version`')' - -clean-files += simpleImage.*.unstrip linux.bin.ub +clean-files += simpleImage.*.unstrip linux.bin.ub dts/*.dtb diff --git a/arch/microblaze/boot/dts/Makefile b/arch/microblaze/boot/dts/Makefile index c4982d16e55..a3d2e42c3c9 100644 --- a/arch/microblaze/boot/dts/Makefile +++ b/arch/microblaze/boot/dts/Makefile @@ -16,5 +16,3 @@ quiet_cmd_cp = CP $< $@$2 # Rule to build device tree blobs DTC_FLAGS := -p 1024 - -clean-files += *.dtb diff --git a/arch/microblaze/include/asm/delay.h b/arch/microblaze/include/asm/delay.h index 60cb39deb53..ea2a9cd9b15 100644 --- a/arch/microblaze/include/asm/delay.h +++ b/arch/microblaze/include/asm/delay.h @@ -15,7 +15,7 @@ #include <linux/param.h> -extern inline void __delay(unsigned long loops) +static inline void __delay(unsigned long loops) { asm volatile ("# __delay \n\t" \ "1: addi %0, %0, -1\t\n" \ @@ -43,7 +43,7 @@ extern inline void __delay(unsigned long loops) extern unsigned long loops_per_jiffy; -extern inline void __udelay(unsigned int x) +static inline void __udelay(unsigned int x) { unsigned long long tmp = diff --git a/arch/microblaze/include/asm/kgdb.h b/arch/microblaze/include/asm/kgdb.h index 78b17d40b23..ad27acb2b15 100644 --- a/arch/microblaze/include/asm/kgdb.h +++ b/arch/microblaze/include/asm/kgdb.h @@ -23,6 +23,9 @@ static inline void arch_kgdb_breakpoint(void) __asm__ __volatile__("brki r16, 0x18;"); } +struct pt_regs; +asmlinkage void microblaze_kgdb_break(struct pt_regs *regs); + #endif /* __ASSEMBLY__ */ #endif /* __MICROBLAZE_KGDB_H__ */ #endif /* __KERNEL__ */ diff --git a/arch/microblaze/include/asm/linkage.h b/arch/microblaze/include/asm/linkage.h index 3a8e36d057e..0540bbaad89 100644 --- a/arch/microblaze/include/asm/linkage.h +++ b/arch/microblaze/include/asm/linkage.h @@ -1,15 +1 @@ -/* - * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - */ - -#ifndef _ASM_MICROBLAZE_LINKAGE_H -#define _ASM_MICROBLAZE_LINKAGE_H - -#define __ALIGN .align 4 -#define __ALIGN_STR ".align 4" - -#endif /* _ASM_MICROBLAZE_LINKAGE_H */ +#include <asm-generic/linkage.h> diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h index 7fdf7fabc7d..61436d69775 100644 --- a/arch/microblaze/include/asm/pgalloc.h +++ b/arch/microblaze/include/asm/pgalloc.h @@ -60,7 +60,7 @@ extern unsigned long get_zero_page_fast(void); extern void __bad_pte(pmd_t *pmd); -extern inline pgd_t *get_pgd_slow(void) +static inline pgd_t *get_pgd_slow(void) { pgd_t *ret; @@ -70,7 +70,7 @@ extern inline pgd_t *get_pgd_slow(void) return ret; } -extern inline pgd_t *get_pgd_fast(void) +static inline pgd_t *get_pgd_fast(void) { unsigned long *ret; @@ -84,14 +84,14 @@ extern inline pgd_t *get_pgd_fast(void) return (pgd_t *)ret; } -extern inline void free_pgd_fast(pgd_t *pgd) +static inline void free_pgd_fast(pgd_t *pgd) { *(unsigned long **)pgd = pgd_quicklist; pgd_quicklist = (unsigned long *) pgd; pgtable_cache_size++; } -extern inline void free_pgd_slow(pgd_t *pgd) +static inline void free_pgd_slow(pgd_t *pgd) { free_page((unsigned long)pgd); } @@ -146,19 +146,19 @@ static inline pte_t *pte_alloc_one_fast(struct mm_struct *mm, return (pte_t *)ret; } -extern inline void pte_free_fast(pte_t *pte) +static inline void pte_free_fast(pte_t *pte) { *(unsigned long **)pte = pte_quicklist; pte_quicklist = (unsigned long *) pte; pgtable_cache_size++; } -extern inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) +static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { free_page((unsigned long)pte); } -extern inline void pte_free_slow(struct page *ptepage) +static inline void pte_free_slow(struct page *ptepage) { __free_page(ptepage); } diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index df19d0c47be..91b9b46fbb5 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -40,10 +40,6 @@ extern int mem_init_done; #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#ifndef __ASSEMBLY__ -static inline int pte_file(pte_t pte) { return 0; } -#endif /* __ASSEMBLY__ */ - #define ZERO_PAGE(vaddr) ({ BUG(); NULL; }) #define swapper_pg_dir ((pgd_t *) NULL) @@ -207,7 +203,6 @@ static inline pte_t pte_mkspecial(pte_t pte) { return pte; } /* Definitions for MicroBlaze. */ #define _PAGE_GUARDED 0x001 /* G: page is guarded from prefetch */ -#define _PAGE_FILE 0x001 /* when !present: nonlinear file mapping */ #define _PAGE_PRESENT 0x002 /* software: PTE contains a translation */ #define _PAGE_NO_CACHE 0x004 /* I: caching is inhibited */ #define _PAGE_WRITETHRU 0x008 /* W: caching is write-through */ @@ -337,7 +332,6 @@ static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_RW; } static inline int pte_exec(pte_t pte) { return pte_val(pte) & _PAGE_EXEC; } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } -static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } static inline void pte_uncache(pte_t pte) { pte_val(pte) |= _PAGE_NO_CACHE; } static inline void pte_cache(pte_t pte) { pte_val(pte) &= ~_PAGE_NO_CACHE; } @@ -499,11 +493,6 @@ static inline pmd_t *pmd_offset(pgd_t *dir, unsigned long address) #define pte_unmap(pte) kunmap_atomic(pte) -/* Encode and decode a nonlinear file mapping entry */ -#define PTE_FILE_MAX_BITS 29 -#define pte_to_pgoff(pte) (pte_val(pte) >> 3) -#define pgoff_to_pte(off) ((pte_t) { ((off) << 3) | _PAGE_FILE }) - extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; /* diff --git a/arch/microblaze/include/asm/syscall.h b/arch/microblaze/include/asm/syscall.h index 53cfaf34c34..04a5bece816 100644 --- a/arch/microblaze/include/asm/syscall.h +++ b/arch/microblaze/include/asm/syscall.h @@ -97,7 +97,7 @@ static inline void syscall_set_arguments(struct task_struct *task, microblaze_set_syscall_arg(regs, i++, *args++); } -asmlinkage long do_syscall_trace_enter(struct pt_regs *regs); +asmlinkage unsigned long do_syscall_trace_enter(struct pt_regs *regs); asmlinkage void do_syscall_trace_leave(struct pt_regs *regs); static inline int syscall_get_arch(void) diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h index 59a89a64a86..62942fd1267 100644 --- a/arch/microblaze/include/asm/uaccess.h +++ b/arch/microblaze/include/asm/uaccess.h @@ -220,7 +220,7 @@ extern long __user_bad(void); } else { \ __gu_err = -EFAULT; \ } \ - x = (typeof(*(ptr)))__gu_val; \ + x = (__force typeof(*(ptr)))__gu_val; \ __gu_err; \ }) @@ -242,7 +242,7 @@ extern long __user_bad(void); default: \ /* __gu_val = 0; __gu_err = -EINVAL;*/ __gu_err = __user_bad();\ } \ - x = (__typeof__(*(ptr))) __gu_val; \ + x = (__force __typeof__(*(ptr))) __gu_val; \ __gu_err; \ }) @@ -306,7 +306,7 @@ extern long __user_bad(void); #define __put_user_check(x, ptr, size) \ ({ \ - typeof(*(ptr)) volatile __pu_val = x; \ + typeof(*(ptr)) volatile __pu_val = x; \ typeof(*(ptr)) __user *__pu_addr = (ptr); \ int __pu_err = 0; \ \ diff --git a/arch/microblaze/include/asm/unistd.h b/arch/microblaze/include/asm/unistd.h index 0a53362d554..76ed17b56fe 100644 --- a/arch/microblaze/include/asm/unistd.h +++ b/arch/microblaze/include/asm/unistd.h @@ -38,6 +38,6 @@ #endif /* __ASSEMBLY__ */ -#define __NR_syscalls 388 +#define __NR_syscalls 389 #endif /* _ASM_MICROBLAZE_UNISTD_H */ diff --git a/arch/microblaze/include/uapi/asm/unistd.h b/arch/microblaze/include/uapi/asm/unistd.h index c712677f8a2..32850c73be0 100644 --- a/arch/microblaze/include/uapi/asm/unistd.h +++ b/arch/microblaze/include/uapi/asm/unistd.h @@ -403,5 +403,6 @@ #define __NR_getrandom 385 #define __NR_memfd_create 386 #define __NR_bpf 387 +#define __NR_execveat 388 #endif /* _UAPI_ASM_MICROBLAZE_UNISTD_H */ diff --git a/arch/microblaze/kernel/Makefile b/arch/microblaze/kernel/Makefile index 08d50cc55e7..f08bacaf8a9 100644 --- a/arch/microblaze/kernel/Makefile +++ b/arch/microblaze/kernel/Makefile @@ -16,7 +16,7 @@ extra-y := head.o vmlinux.lds obj-y += dma.o exceptions.o \ hw_exception_handler.o intc.o irq.o \ - platform.o process.o prom.o prom_parse.o ptrace.o \ + platform.o process.o prom.o ptrace.o \ reset.o setup.o signal.o sys_microblaze.o timer.o traps.o unwind.o obj-y += cpu/ diff --git a/arch/microblaze/kernel/cpu/cache.c b/arch/microblaze/kernel/cpu/cache.c index a6e44410672..0bde47e4fa6 100644 --- a/arch/microblaze/kernel/cpu/cache.c +++ b/arch/microblaze/kernel/cpu/cache.c @@ -140,10 +140,10 @@ do { \ /* It is used only first parameter for OP - for wic, wdc */ #define CACHE_RANGE_LOOP_1(start, end, line_length, op) \ do { \ - int volatile temp = 0; \ - int align = ~(line_length - 1); \ + unsigned int volatile temp = 0; \ + unsigned int align = ~(line_length - 1); \ end = ((end & align) == end) ? end - line_length : end & align; \ - WARN_ON(end - start < 0); \ + WARN_ON(end < start); \ \ __asm__ __volatile__ (" 1: " #op " %1, r0;" \ "cmpu %0, %1, %2;" \ diff --git a/arch/microblaze/kernel/cpu/cpuinfo-pvr-full.c b/arch/microblaze/kernel/cpu/cpuinfo-pvr-full.c index 93c26cf50de..a32daec96c1 100644 --- a/arch/microblaze/kernel/cpu/cpuinfo-pvr-full.c +++ b/arch/microblaze/kernel/cpu/cpuinfo-pvr-full.c @@ -33,7 +33,7 @@ void set_cpuinfo_pvr_full(struct cpuinfo *ci, struct device_node *cpu) { struct pvr_s pvr; - int temp; /* for saving temp value */ + u32 temp; /* for saving temp value */ get_pvr(&pvr); CI(ver_code, VERSION); diff --git a/arch/microblaze/kernel/cpu/cpuinfo-static.c b/arch/microblaze/kernel/cpu/cpuinfo-static.c index 4854285b26e..85dbda4a08a 100644 --- a/arch/microblaze/kernel/cpu/cpuinfo-static.c +++ b/arch/microblaze/kernel/cpu/cpuinfo-static.c @@ -22,7 +22,7 @@ static const char cpu_ver_string[] = CONFIG_XILINX_MICROBLAZE0_HW_VER; void __init set_cpuinfo_static(struct cpuinfo *ci, struct device_node *cpu) { - int i = 0; + u32 i = 0; ci->use_instr = (fcpu(cpu, "xlnx,use-barrel") ? PVR0_USE_BARREL_MASK : 0) | diff --git a/arch/microblaze/kernel/cpu/cpuinfo.c b/arch/microblaze/kernel/cpu/cpuinfo.c index 234acad79b9..d1dd6e83d59 100644 --- a/arch/microblaze/kernel/cpu/cpuinfo.c +++ b/arch/microblaze/kernel/cpu/cpuinfo.c @@ -41,8 +41,12 @@ const struct cpu_ver_key cpu_ver_lookup[] = { {"8.40.a", 0x18}, {"8.40.b", 0x19}, {"8.50.a", 0x1a}, + {"8.50.b", 0x1c}, + {"8.50.c", 0x1e}, {"9.0", 0x1b}, {"9.1", 0x1d}, + {"9.2", 0x1f}, + {"9.3", 0x20}, {NULL, 0}, }; @@ -61,11 +65,14 @@ const struct family_string_key family_string_lookup[] = { {"spartan3adsp", 0xc}, {"spartan6", 0xd}, {"virtex6", 0xe}, + {"virtex7", 0xf}, /* FIXME There is no key code defined for spartan2 */ {"spartan2", 0xf0}, {"kintex7", 0x10}, {"artix7", 0x11}, {"zynq7000", 0x12}, + {"UltraScale Virtex", 0x13}, + {"UltraScale Kintex", 0x14}, {NULL, 0}, }; diff --git a/arch/microblaze/kernel/intc.c b/arch/microblaze/kernel/intc.c index 15c7c12ea0e..719feee1e04 100644 --- a/arch/microblaze/kernel/intc.c +++ b/arch/microblaze/kernel/intc.c @@ -148,17 +148,17 @@ static int __init xilinx_intc_of_init(struct device_node *intc, ret = of_property_read_u32(intc, "xlnx,num-intr-inputs", &nr_irq); if (ret < 0) { pr_err("%s: unable to read xlnx,num-intr-inputs\n", __func__); - return -EINVAL; + return ret; } ret = of_property_read_u32(intc, "xlnx,kind-of-intr", &intr_mask); if (ret < 0) { pr_err("%s: unable to read xlnx,kind-of-intr\n", __func__); - return -EINVAL; + return ret; } - if (intr_mask > (u32)((1ULL << nr_irq) - 1)) - pr_info(" ERROR: Mismatch in kind-of-intr param\n"); + if (intr_mask >> nr_irq) + pr_warn("%s: mismatch in kind-of-intr param\n", __func__); pr_info("%s: num_irq=%d, edge=0x%x\n", intc->full_name, nr_irq, intr_mask); diff --git a/arch/microblaze/kernel/kgdb.c b/arch/microblaze/kernel/kgdb.c index 09a5e828613..8736af5806a 100644 --- a/arch/microblaze/kernel/kgdb.c +++ b/arch/microblaze/kernel/kgdb.c @@ -12,6 +12,7 @@ #include <linux/io.h> #include <asm/cacheflush.h> #include <asm/asm-offsets.h> +#include <asm/kgdb.h> #include <asm/pvr.h> #define GDB_REG 0 @@ -35,9 +36,10 @@ struct pvr_s pvr; void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) { - int i; + unsigned int i; unsigned long *pt_regb = (unsigned long *)regs; int temp; + /* registers r0 - r31, pc, msr, ear, esr, fsr + do not save pt_mode */ for (i = 0; i < (sizeof(struct pt_regs) / 4) - 1; i++) gdb_regs[i] = pt_regb[i]; @@ -67,7 +69,7 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) { - int i; + unsigned int i; unsigned long *pt_regb = (unsigned long *)regs; /* pt_regs and gdb_regs have the same 37 values. @@ -77,7 +79,7 @@ void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) pt_regb[i] = gdb_regs[i]; } -void microblaze_kgdb_break(struct pt_regs *regs) +asmlinkage void microblaze_kgdb_break(struct pt_regs *regs) { if (kgdb_handle_exception(1, SIGTRAP, 0, regs) != 0) return; @@ -91,7 +93,7 @@ void microblaze_kgdb_break(struct pt_regs *regs) /* untested */ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) { - int i; + unsigned int i; unsigned long *pt_regb = (unsigned long *)(p->thread.regs); /* registers r0 - r31, pc, msr, ear, esr, fsr + do not save pt_mode */ diff --git a/arch/microblaze/kernel/prom_parse.c b/arch/microblaze/kernel/prom_parse.c deleted file mode 100644 index 068762f55fd..00000000000 --- a/arch/microblaze/kernel/prom_parse.c +++ /dev/null @@ -1,35 +0,0 @@ -#undef DEBUG - -#include <linux/export.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/ioport.h> -#include <linux/etherdevice.h> -#include <linux/of_address.h> -#include <asm/prom.h> - -void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, - unsigned long *busno, unsigned long *phys, unsigned long *size) -{ - const u32 *dma_window; - u32 cells; - const unsigned char *prop; - - dma_window = dma_window_prop; - - /* busno is always one cell */ - *busno = *(dma_window++); - - prop = of_get_property(dn, "ibm,#dma-address-cells", NULL); - if (!prop) - prop = of_get_property(dn, "#address-cells", NULL); - - cells = prop ? *(u32 *)prop : of_n_addr_cells(dn); - *phys = of_read_number(dma_window, cells); - - dma_window += cells; - - prop = of_get_property(dn, "ibm,#dma-size-cells", NULL); - cells = prop ? *(u32 *)prop : of_n_size_cells(dn); - *size = of_read_number(dma_window, cells); -} diff --git a/arch/microblaze/kernel/ptrace.c b/arch/microblaze/kernel/ptrace.c index bb10637ce68..8cfa98cadf3 100644 --- a/arch/microblaze/kernel/ptrace.c +++ b/arch/microblaze/kernel/ptrace.c @@ -132,9 +132,9 @@ long arch_ptrace(struct task_struct *child, long request, return rval; } -asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) +asmlinkage unsigned long do_syscall_trace_enter(struct pt_regs *regs) { - long ret = 0; + unsigned long ret = 0; secure_computing_strict(regs->r12); diff --git a/arch/microblaze/kernel/reset.c b/arch/microblaze/kernel/reset.c index fbe58c6554a..bab4c8330ef 100644 --- a/arch/microblaze/kernel/reset.c +++ b/arch/microblaze/kernel/reset.c @@ -9,7 +9,6 @@ #include <linux/init.h> #include <linux/of_platform.h> -#include <asm/prom.h> /* Trigger specific functions */ #ifdef CONFIG_GPIOLIB diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c index 8955a3829cf..235706055b7 100644 --- a/arch/microblaze/kernel/signal.c +++ b/arch/microblaze/kernel/signal.c @@ -158,7 +158,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, { struct rt_sigframe __user *frame; int err = 0, sig = ksig->sig; - int signal; + unsigned long signal; unsigned long address = 0; #ifdef CONFIG_MMU pmd_t *pmdp; @@ -174,7 +174,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, && current_thread_info()->exec_domain->signal_invmap && sig < 32 ? current_thread_info()->exec_domain->signal_invmap[sig] - : sig; + : (unsigned long)sig; if (ksig->ka.sa.sa_flags & SA_SIGINFO) err |= copy_siginfo_to_user(&frame->info, &ksig->info); diff --git a/arch/microblaze/kernel/syscall_table.S b/arch/microblaze/kernel/syscall_table.S index 0166e890486..29c8568ec55 100644 --- a/arch/microblaze/kernel/syscall_table.S +++ b/arch/microblaze/kernel/syscall_table.S @@ -388,3 +388,4 @@ ENTRY(sys_call_table) .long sys_getrandom /* 385 */ .long sys_memfd_create .long sys_bpf + .long sys_execveat diff --git a/arch/microblaze/kernel/unwind.c b/arch/microblaze/kernel/unwind.c index 1f7b8d44966..61c04eed14d 100644 --- a/arch/microblaze/kernel/unwind.c +++ b/arch/microblaze/kernel/unwind.c @@ -59,7 +59,7 @@ struct stack_trace; * * Return - Number of stack bytes the instruction reserves or reclaims */ -inline long get_frame_size(unsigned long instr) +static inline long get_frame_size(unsigned long instr) { return abs((s16)(instr & 0xFFFF)); } diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 3289969ee42..843713c05b7 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2656,27 +2656,21 @@ config TRAD_SIGNALS bool config MIPS32_COMPAT - bool "Kernel support for Linux/MIPS 32-bit binary compatibility" - depends on 64BIT - help - Select this option if you want Linux/MIPS 32-bit binary - compatibility. Since all software available for Linux/MIPS is - currently 32-bit you should say Y here. + bool config COMPAT bool - depends on MIPS32_COMPAT - select ARCH_WANT_OLD_COMPAT_IPC - default y config SYSVIPC_COMPAT bool - depends on COMPAT && SYSVIPC - default y config MIPS32_O32 bool "Kernel support for o32 binaries" - depends on MIPS32_COMPAT + depends on 64BIT + select ARCH_WANT_OLD_COMPAT_IPC + select COMPAT + select MIPS32_COMPAT + select SYSVIPC_COMPAT if SYSVIPC help Select this option if you want to run o32 binaries. These are pure 32-bit binaries as used by the 32-bit Linux/MIPS port. Most of @@ -2686,7 +2680,10 @@ config MIPS32_O32 config MIPS32_N32 bool "Kernel support for n32 binaries" - depends on MIPS32_COMPAT + depends on 64BIT + select COMPAT + select MIPS32_COMPAT + select SYSVIPC_COMPAT if SYSVIPC help Select this option if you want to run n32 binaries. These are 64-bit binaries using 32-bit quantities for addressing and certain diff --git a/arch/mips/boot/elf2ecoff.c b/arch/mips/boot/elf2ecoff.c index 8585078ae50..2a4c52e27f4 100644 --- a/arch/mips/boot/elf2ecoff.c +++ b/arch/mips/boot/elf2ecoff.c @@ -49,7 +49,8 @@ /* * Some extra ELF definitions */ -#define PT_MIPS_REGINFO 0x70000000 /* Register usage information */ +#define PT_MIPS_REGINFO 0x70000000 /* Register usage information */ +#define PT_MIPS_ABIFLAGS 0x70000003 /* Records ABI related flags */ /* -------------------------------------------------------------------- */ @@ -349,39 +350,46 @@ int main(int argc, char *argv[]) for (i = 0; i < ex.e_phnum; i++) { /* Section types we can ignore... */ - if (ph[i].p_type == PT_NULL || ph[i].p_type == PT_NOTE || - ph[i].p_type == PT_PHDR - || ph[i].p_type == PT_MIPS_REGINFO) + switch (ph[i].p_type) { + case PT_NULL: + case PT_NOTE: + case PT_PHDR: + case PT_MIPS_REGINFO: + case PT_MIPS_ABIFLAGS: continue; - /* Section types we can't handle... */ - else if (ph[i].p_type != PT_LOAD) { - fprintf(stderr, - "Program header %d type %d can't be converted.\n", - ex.e_phnum, ph[i].p_type); - exit(1); - } - /* Writable (data) segment? */ - if (ph[i].p_flags & PF_W) { - struct sect ndata, nbss; - ndata.vaddr = ph[i].p_vaddr; - ndata.len = ph[i].p_filesz; - nbss.vaddr = ph[i].p_vaddr + ph[i].p_filesz; - nbss.len = ph[i].p_memsz - ph[i].p_filesz; + case PT_LOAD: + /* Writable (data) segment? */ + if (ph[i].p_flags & PF_W) { + struct sect ndata, nbss; + + ndata.vaddr = ph[i].p_vaddr; + ndata.len = ph[i].p_filesz; + nbss.vaddr = ph[i].p_vaddr + ph[i].p_filesz; + nbss.len = ph[i].p_memsz - ph[i].p_filesz; - combine(&data, &ndata, 0); - combine(&bss, &nbss, 1); - } else { - struct sect ntxt; + combine(&data, &ndata, 0); + combine(&bss, &nbss, 1); + } else { + struct sect ntxt; - ntxt.vaddr = ph[i].p_vaddr; - ntxt.len = ph[i].p_filesz; + ntxt.vaddr = ph[i].p_vaddr; + ntxt.len = ph[i].p_filesz; - combine(&text, &ntxt, 0); + combine(&text, &ntxt, 0); + } + /* Remember the lowest segment start address. */ + if (ph[i].p_vaddr < cur_vma) + cur_vma = ph[i].p_vaddr; + break; + + default: + /* Section types we can't handle... */ + fprintf(stderr, + "Program header %d type %d can't be converted.\n", + ex.e_phnum, ph[i].p_type); + exit(1); } - /* Remember the lowest segment start address. */ - if (ph[i].p_vaddr < cur_vma) - cur_vma = ph[i].p_vaddr; } /* Sections must be in order to be converted... */ diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index ecd903dd1c4..8b1eeffa12e 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -240,9 +240,7 @@ static int octeon_cpu_disable(void) set_cpu_online(cpu, false); cpu_clear(cpu, cpu_callin_map); - local_irq_disable(); octeon_fixup_irqs(); - local_irq_enable(); flush_cache_all(); local_flush_tlb_all(); diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig index f57b96dcf7d..61a4460d67d 100644 --- a/arch/mips/configs/malta_defconfig +++ b/arch/mips/configs/malta_defconfig @@ -132,7 +132,6 @@ CONFIG_IP_NF_MATCH_ECN=m CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_CLUSTERIP=m CONFIG_IP_NF_TARGET_ECN=m @@ -175,7 +174,6 @@ CONFIG_BRIDGE_EBT_MARK_T=m CONFIG_BRIDGE_EBT_REDIRECT=m CONFIG_BRIDGE_EBT_SNAT=m CONFIG_BRIDGE_EBT_LOG=m -CONFIG_BRIDGE_EBT_ULOG=m CONFIG_BRIDGE_EBT_NFLOG=m CONFIG_IP_SCTP=m CONFIG_BRIDGE=m @@ -220,8 +218,6 @@ CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_CLS_IND=y CONFIG_CFG80211=m CONFIG_MAC80211=m -CONFIG_MAC80211_RC_PID=y -CONFIG_MAC80211_RC_DEFAULT_PID=y CONFIG_MAC80211_MESH=y CONFIG_RFKILL=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" @@ -248,19 +244,13 @@ CONFIG_ATA_OVER_ETH=m CONFIG_IDE=y CONFIG_BLK_DEV_IDECD=y CONFIG_IDE_GENERIC=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_PIIX=y -CONFIG_BLK_DEV_IT8213=m -CONFIG_BLK_DEV_TC86C001=m CONFIG_RAID_ATTRS=m -CONFIG_SCSI=m -CONFIG_BLK_DEV_SD=m +CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=m CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m -CONFIG_SCSI_MULTI_LUN=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y CONFIG_SCSI_SCAN_ASYNC=y @@ -273,6 +263,8 @@ CONFIG_SCSI_AACRAID=m CONFIG_SCSI_AIC7XXX=m CONFIG_AIC7XXX_RESET_DELAY_MS=15000 # CONFIG_AIC7XXX_DEBUG_ENABLE is not set +CONFIG_ATA=y +CONFIG_ATA_PIIX=y CONFIG_MD=y CONFIG_BLK_DEV_MD=m CONFIG_MD_LINEAR=m @@ -340,6 +332,7 @@ CONFIG_UIO=m CONFIG_UIO_CIF=m CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y +CONFIG_EXT4_FS=y CONFIG_REISERFS_FS=m CONFIG_REISERFS_PROC_INFO=y CONFIG_REISERFS_FS_XATTR=y @@ -441,4 +434,3 @@ CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m # CONFIG_CRYPTO_ANSI_CPRNG is not set -CONFIG_CRC16=m diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h index 994d2193967..affebb78f5d 100644 --- a/arch/mips/include/asm/fpu.h +++ b/arch/mips/include/asm/fpu.h @@ -64,7 +64,7 @@ static inline int __enable_fpu(enum fpu_mode mode) return SIGFPE; /* set FRE */ - write_c0_config5(read_c0_config5() | MIPS_CONF5_FRE); + set_c0_config5(MIPS_CONF5_FRE); goto fr_common; case FPU_64BIT: @@ -74,8 +74,10 @@ static inline int __enable_fpu(enum fpu_mode mode) #endif /* fall through */ case FPU_32BIT: - /* clear FRE */ - write_c0_config5(read_c0_config5() & ~MIPS_CONF5_FRE); + if (cpu_has_fre) { + /* clear FRE */ + clear_c0_config5(MIPS_CONF5_FRE); + } fr_common: /* set CU1 & change FR appropriately */ fr = (int)mode & FPU_FR_MASK; @@ -182,25 +184,32 @@ static inline int init_fpu(void) int ret = 0; if (cpu_has_fpu) { + unsigned int config5; + ret = __own_fpu(); - if (!ret) { - unsigned int config5 = read_c0_config5(); - - /* - * Ensure FRE is clear whilst running _init_fpu, since - * single precision FP instructions are used. If FRE - * was set then we'll just end up initialising all 32 - * 64b registers. - */ - write_c0_config5(config5 & ~MIPS_CONF5_FRE); - enable_fpu_hazard(); + if (ret) + return ret; + if (!cpu_has_fre) { _init_fpu(); - /* Restore FRE */ - write_c0_config5(config5); - enable_fpu_hazard(); + return 0; } + + /* + * Ensure FRE is clear whilst running _init_fpu, since + * single precision FP instructions are used. If FRE + * was set then we'll just end up initialising all 32 + * 64b registers. + */ + config5 = clear_c0_config5(MIPS_CONF5_FRE); + enable_fpu_hazard(); + + _init_fpu(); + + /* Restore FRE */ + write_c0_config5(config5); + enable_fpu_hazard(); } else fpu_emulator_init_fpu(); diff --git a/arch/mips/include/asm/fw/arc/hinv.h b/arch/mips/include/asm/fw/arc/hinv.h index f8d37d1df5d..9fac64a2635 100644 --- a/arch/mips/include/asm/fw/arc/hinv.h +++ b/arch/mips/include/asm/fw/arc/hinv.h @@ -119,7 +119,7 @@ union key_u { #define SGI_ARCS_REV 10 /* rev .10, 3/04/92 */ #endif -typedef struct component { +typedef struct { CONFIGCLASS Class; CONFIGTYPE Type; IDENTIFIERFLAG Flags; @@ -140,7 +140,7 @@ struct cfgdata { }; /* System ID */ -typedef struct systemid { +typedef struct { CHAR VendorId[8]; CHAR ProductId[8]; } SYSTEMID; @@ -166,7 +166,7 @@ typedef enum memorytype { #endif /* _NT_PROM */ } MEMORYTYPE; -typedef struct memorydescriptor { +typedef struct { MEMORYTYPE Type; LONG BasePage; LONG PageCount; diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h index b95a827d763..59c0901bdd8 100644 --- a/arch/mips/include/asm/mips-cm.h +++ b/arch/mips/include/asm/mips-cm.h @@ -89,9 +89,9 @@ static inline bool mips_cm_has_l2sync(void) /* Macros to ease the creation of register access functions */ #define BUILD_CM_R_(name, off) \ -static inline u32 *addr_gcr_##name(void) \ +static inline u32 __iomem *addr_gcr_##name(void) \ { \ - return (u32 *)(mips_cm_base + (off)); \ + return (u32 __iomem *)(mips_cm_base + (off)); \ } \ \ static inline u32 read_gcr_##name(void) \ diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 5e4aef304b0..5b720d8c274 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -1386,12 +1386,27 @@ do { \ __res; \ }) +#define _write_32bit_cp1_register(dest, val, gas_hardfloat) \ +do { \ + __asm__ __volatile__( \ + " .set push \n" \ + " .set reorder \n" \ + " "STR(gas_hardfloat)" \n" \ + " ctc1 %0,"STR(dest)" \n" \ + " .set pop \n" \ + : : "r" (val)); \ +} while (0) + #ifdef GAS_HAS_SET_HARDFLOAT #define read_32bit_cp1_register(source) \ _read_32bit_cp1_register(source, .set hardfloat) +#define write_32bit_cp1_register(dest, val) \ + _write_32bit_cp1_register(dest, val, .set hardfloat) #else #define read_32bit_cp1_register(source) \ _read_32bit_cp1_register(source, ) +#define write_32bit_cp1_register(dest, val) \ + _write_32bit_cp1_register(dest, val, ) #endif #ifdef HAVE_AS_DSP diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index 68984b612f9..16aa9f23e17 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -161,22 +161,6 @@ pfn_pte(unsigned long pfn, pgprot_t prot) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -/* - * Encode and decode a nonlinear file mapping entry - */ -#define pte_to_pgoff(_pte) ((((_pte).pte >> 1 ) & 0x07) | \ - (((_pte).pte >> 2 ) & 0x38) | \ - (((_pte).pte >> 10) << 6 )) - -#define pgoff_to_pte(off) ((pte_t) { (((off) & 0x07) << 1 ) | \ - (((off) & 0x38) << 2 ) | \ - (((off) >> 6 ) << 10) | \ - _PAGE_FILE }) - -/* - * Bits 0, 4, 8, and 9 are taken, split up 28 bits of offset into this range: - */ -#define PTE_FILE_MAX_BITS 28 #else #if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) @@ -188,13 +172,6 @@ pfn_pte(unsigned long pfn, pgprot_t prot) #define __pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_high }) #define __swp_entry_to_pte(x) ((pte_t) { 0, (x).val }) -/* - * Bits 0 and 1 of pte_high are taken, use the rest for the page offset... - */ -#define pte_to_pgoff(_pte) ((_pte).pte_high >> 2) -#define pgoff_to_pte(off) ((pte_t) { _PAGE_FILE, (off) << 2 }) - -#define PTE_FILE_MAX_BITS 30 #else /* * Constraints: @@ -209,19 +186,6 @@ pfn_pte(unsigned long pfn, pgprot_t prot) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -/* - * Encode and decode a nonlinear file mapping entry - */ -#define pte_to_pgoff(_pte) ((((_pte).pte >> 1) & 0x7) | \ - (((_pte).pte >> 2) & 0x8) | \ - (((_pte).pte >> 8) << 4)) - -#define pgoff_to_pte(off) ((pte_t) { (((off) & 0x7) << 1) | \ - (((off) & 0x8) << 2) | \ - (((off) >> 4) << 8) | \ - _PAGE_FILE }) - -#define PTE_FILE_MAX_BITS 28 #endif /* defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) */ #endif /* defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX) */ diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index e1c49a96807..1659bb91ae2 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -291,13 +291,4 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -/* - * Bits 0, 4, 6, and 7 are taken. Let's leave bits 1, 2, 3, and 5 alone to - * make things easier, and only use the upper 56 bits for the page offset... - */ -#define PTE_FILE_MAX_BITS 56 - -#define pte_to_pgoff(_pte) ((_pte).pte >> 8) -#define pgoff_to_pte(off) ((pte_t) { ((off) << 8) | _PAGE_FILE }) - #endif /* _ASM_PGTABLE_64_H */ diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h index ca11f14f40a..fc807aa5ec8 100644 --- a/arch/mips/include/asm/pgtable-bits.h +++ b/arch/mips/include/asm/pgtable-bits.h @@ -48,8 +48,6 @@ /* * The following bits are implemented in software - * - * _PAGE_FILE semantics: set:pagecache unset:swap */ #define _PAGE_PRESENT_SHIFT (_CACHE_SHIFT + 3) #define _PAGE_PRESENT (1 << _PAGE_PRESENT_SHIFT) @@ -64,7 +62,6 @@ #define _PAGE_SILENT_READ _PAGE_VALID #define _PAGE_SILENT_WRITE _PAGE_DIRTY -#define _PAGE_FILE _PAGE_MODIFIED #define _PFN_SHIFT (PAGE_SHIFT - 12 + _CACHE_SHIFT + 3) @@ -72,8 +69,6 @@ /* * The following are implemented by software - * - * _PAGE_FILE semantics: set:pagecache unset:swap */ #define _PAGE_PRESENT_SHIFT 0 #define _PAGE_PRESENT (1 << _PAGE_PRESENT_SHIFT) @@ -85,8 +80,6 @@ #define _PAGE_ACCESSED (1 << _PAGE_ACCESSED_SHIFT) #define _PAGE_MODIFIED_SHIFT 4 #define _PAGE_MODIFIED (1 << _PAGE_MODIFIED_SHIFT) -#define _PAGE_FILE_SHIFT 4 -#define _PAGE_FILE (1 << _PAGE_FILE_SHIFT) /* * And these are the hardware TLB bits @@ -116,7 +109,6 @@ * The following bits are implemented in software * * _PAGE_READ / _PAGE_READ_SHIFT should be unused if cpu_has_rixi. - * _PAGE_FILE semantics: set:pagecache unset:swap */ #define _PAGE_PRESENT_SHIFT (0) #define _PAGE_PRESENT (1 << _PAGE_PRESENT_SHIFT) @@ -128,7 +120,6 @@ #define _PAGE_ACCESSED (1 << _PAGE_ACCESSED_SHIFT) #define _PAGE_MODIFIED_SHIFT (_PAGE_ACCESSED_SHIFT + 1) #define _PAGE_MODIFIED (1 << _PAGE_MODIFIED_SHIFT) -#define _PAGE_FILE (_PAGE_MODIFIED) #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT /* huge tlb page */ diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 62a6ba383d4..583ff421547 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -231,7 +231,6 @@ extern pgd_t swapper_pg_dir[]; static inline int pte_write(pte_t pte) { return pte.pte_low & _PAGE_WRITE; } static inline int pte_dirty(pte_t pte) { return pte.pte_low & _PAGE_MODIFIED; } static inline int pte_young(pte_t pte) { return pte.pte_low & _PAGE_ACCESSED; } -static inline int pte_file(pte_t pte) { return pte.pte_low & _PAGE_FILE; } static inline pte_t pte_wrprotect(pte_t pte) { @@ -287,7 +286,6 @@ static inline pte_t pte_mkyoung(pte_t pte) static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_WRITE; } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_MODIFIED; } static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } -static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } static inline pte_t pte_wrprotect(pte_t pte) { diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index bb796375373..6499d93ae68 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -29,13 +29,7 @@ static inline long syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { - /* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */ - if ((config_enabled(CONFIG_32BIT) || - test_tsk_thread_flag(task, TIF_32BIT_REGS)) && - (regs->regs[2] == __NR_syscall)) - return regs->regs[4]; - else - return regs->regs[2]; + return current_thread_info()->syscall; } static inline unsigned long mips_get_syscall_arg(unsigned long *arg, diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index 99eea59604e..e4440f92b36 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -36,6 +36,7 @@ struct thread_info { */ struct restart_block restart_block; struct pt_regs *regs; + long syscall; /* syscall number */ }; /* diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h index d001bb1ad17..c03088f9f51 100644 --- a/arch/mips/include/uapi/asm/unistd.h +++ b/arch/mips/include/uapi/asm/unistd.h @@ -376,16 +376,17 @@ #define __NR_getrandom (__NR_Linux + 353) #define __NR_memfd_create (__NR_Linux + 354) #define __NR_bpf (__NR_Linux + 355) +#define __NR_execveat (__NR_Linux + 356) /* * Offset of the last Linux o32 flavoured syscall */ -#define __NR_Linux_syscalls 355 +#define __NR_Linux_syscalls 356 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */ #define __NR_O32_Linux 4000 -#define __NR_O32_Linux_syscalls 355 +#define __NR_O32_Linux_syscalls 356 #if _MIPS_SIM == _MIPS_SIM_ABI64 @@ -709,16 +710,17 @@ #define __NR_getrandom (__NR_Linux + 313) #define __NR_memfd_create (__NR_Linux + 314) #define __NR_bpf (__NR_Linux + 315) +#define __NR_execveat (__NR_Linux + 316) /* * Offset of the last Linux 64-bit flavoured syscall */ -#define __NR_Linux_syscalls 315 +#define __NR_Linux_syscalls 316 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */ #define __NR_64_Linux 5000 -#define __NR_64_Linux_syscalls 315 +#define __NR_64_Linux_syscalls 316 #if _MIPS_SIM == _MIPS_SIM_NABI32 @@ -1046,15 +1048,16 @@ #define __NR_getrandom (__NR_Linux + 317) #define __NR_memfd_create (__NR_Linux + 318) #define __NR_bpf (__NR_Linux + 319) +#define __NR_execveat (__NR_Linux + 320) /* * Offset of the last N32 flavoured syscall */ -#define __NR_Linux_syscalls 319 +#define __NR_Linux_syscalls 320 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */ #define __NR_N32_Linux 6000 -#define __NR_N32_Linux_syscalls 319 +#define __NR_N32_Linux_syscalls 320 #endif /* _UAPI_ASM_UNISTD_H */ diff --git a/arch/mips/jz4740/irq.c b/arch/mips/jz4740/irq.c index 2531da1d3ad..97206b3deb9 100644 --- a/arch/mips/jz4740/irq.c +++ b/arch/mips/jz4740/irq.c @@ -30,6 +30,9 @@ #include <asm/irq_cpu.h> #include <asm/mach-jz4740/base.h> +#include <asm/mach-jz4740/irq.h> + +#include "irq.h" static void __iomem *jz_intc_base; diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c index c92b15df689..a5b5b56485c 100644 --- a/arch/mips/kernel/elf.c +++ b/arch/mips/kernel/elf.c @@ -19,8 +19,8 @@ enum { int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf, bool is_interp, struct arch_elf_state *state) { - struct elfhdr *ehdr = _ehdr; - struct elf_phdr *phdr = _phdr; + struct elf32_hdr *ehdr = _ehdr; + struct elf32_phdr *phdr = _phdr; struct mips_elf_abiflags_v0 abiflags; int ret; @@ -48,7 +48,7 @@ int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf, return 0; } -static inline unsigned get_fp_abi(struct elfhdr *ehdr, int in_abi) +static inline unsigned get_fp_abi(struct elf32_hdr *ehdr, int in_abi) { /* If the ABI requirement is provided, simply return that */ if (in_abi != -1) @@ -65,7 +65,7 @@ static inline unsigned get_fp_abi(struct elfhdr *ehdr, int in_abi) int arch_check_elf(void *_ehdr, bool has_interpreter, struct arch_elf_state *state) { - struct elfhdr *ehdr = _ehdr; + struct elf32_hdr *ehdr = _ehdr; unsigned fp_abi, interp_fp_abi, abi0, abi1; /* Ignore non-O32 binaries */ diff --git a/arch/mips/kernel/irq_cpu.c b/arch/mips/kernel/irq_cpu.c index 590c2c980fd..6eb7a3f515f 100644 --- a/arch/mips/kernel/irq_cpu.c +++ b/arch/mips/kernel/irq_cpu.c @@ -57,6 +57,8 @@ static struct irq_chip mips_cpu_irq_controller = { .irq_mask_ack = mask_mips_irq, .irq_unmask = unmask_mips_irq, .irq_eoi = unmask_mips_irq, + .irq_disable = mask_mips_irq, + .irq_enable = unmask_mips_irq, }; /* @@ -93,6 +95,8 @@ static struct irq_chip mips_mt_cpu_irq_controller = { .irq_mask_ack = mips_mt_cpu_irq_ack, .irq_unmask = unmask_mips_irq, .irq_eoi = unmask_mips_irq, + .irq_disable = mask_mips_irq, + .irq_enable = unmask_mips_irq, }; asmlinkage void __weak plat_irq_dispatch(void) diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index eb76434828e..85bff5d513e 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -82,6 +82,30 @@ void flush_thread(void) { } +int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) +{ + /* + * Save any process state which is live in hardware registers to the + * parent context prior to duplication. This prevents the new child + * state becoming stale if the parent is preempted before copy_thread() + * gets a chance to save the parent's live hardware registers to the + * child context. + */ + preempt_disable(); + + if (is_msa_enabled()) + save_msa(current); + else if (is_fpu_owner()) + _save_fp(current); + + save_dsp(current); + + preempt_enable(); + + *dst = *src; + return 0; +} + int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, struct task_struct *p) { @@ -92,18 +116,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32; - preempt_disable(); - - if (is_msa_enabled()) - save_msa(p); - else if (is_fpu_owner()) - save_fp(p); - - if (cpu_has_dsp) - save_dsp(p); - - preempt_enable(); - /* set up new TSS. */ childregs = (struct pt_regs *) childksp - 1; /* Put the stack after the struct pt_regs. */ diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 9d1487d8329..51045281259 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -770,6 +770,8 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) long ret = 0; user_exit(); + current_thread_info()->syscall = syscall; + if (secure_computing() == -1) return -1; diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 00cad1005a1..6e8de80bb44 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -181,6 +181,7 @@ illegal_syscall: sll t1, t0, 2 beqz v0, einval lw t2, sys_call_table(t1) # syscall routine + sw a0, PT_R2(sp) # call routine directly on restart /* Some syscalls like execve get their arguments from struct pt_regs and claim zero arguments in the syscall table. Thus we have to @@ -580,3 +581,4 @@ EXPORT(sys_call_table) PTR sys_getrandom PTR sys_memfd_create PTR sys_bpf /* 4355 */ + PTR sys_execveat diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 5251565e344..ad4d44635c7 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -435,4 +435,5 @@ EXPORT(sys_call_table) PTR sys_getrandom PTR sys_memfd_create PTR sys_bpf /* 5315 */ + PTR sys_execveat .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 77e74398b82..446cc654da5 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -428,4 +428,5 @@ EXPORT(sysn32_call_table) PTR sys_getrandom PTR sys_memfd_create PTR sys_bpf + PTR compat_sys_execveat /* 6320 */ .size sysn32_call_table,.-sysn32_call_table diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 6f8db9f728e..d07b210fbef 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -186,6 +186,7 @@ LEAF(sys32_syscall) dsll t1, t0, 3 beqz v0, einval ld t2, sys32_call_table(t1) # syscall routine + sd a0, PT_R2(sp) # call routine directly on restart move a0, a1 # shift argument registers move a1, a2 @@ -565,4 +566,5 @@ EXPORT(sys32_call_table) PTR sys_getrandom PTR sys_memfd_create PTR sys_bpf /* 4355 */ + PTR compat_sys_execveat .size sys32_call_table,.-sys32_call_table diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c index 1e0a93c5a3e..e36a859af66 100644 --- a/arch/mips/kernel/smp-cmp.c +++ b/arch/mips/kernel/smp-cmp.c @@ -44,8 +44,8 @@ static void cmp_init_secondary(void) struct cpuinfo_mips *c __maybe_unused = ¤t_cpu_data; /* Assume GIC is present */ - change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 | STATUSF_IP6 | - STATUSF_IP7); + change_c0_status(ST0_IM, STATUSF_IP2 | STATUSF_IP3 | STATUSF_IP4 | + STATUSF_IP5 | STATUSF_IP6 | STATUSF_IP7); /* Enable per-cpu interrupts: platform specific */ diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c index ad86951b73b..17ea705f6c4 100644 --- a/arch/mips/kernel/smp-mt.c +++ b/arch/mips/kernel/smp-mt.c @@ -161,7 +161,8 @@ static void vsmp_init_secondary(void) #ifdef CONFIG_MIPS_GIC /* This is Malta specific: IPI,performance and timer interrupts */ if (gic_present) - change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 | + change_c0_status(ST0_IM, STATUSF_IP2 | STATUSF_IP3 | + STATUSF_IP4 | STATUSF_IP5 | STATUSF_IP6 | STATUSF_IP7); else #endif diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index c94c4e92e17..1c0d8c50b7e 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -123,10 +123,10 @@ asmlinkage void start_secondary(void) unsigned int cpu; cpu_probe(); - cpu_report(); per_cpu_trap_init(false); mips_clockevent_init(); mp_ops->init_secondary(); + cpu_report(); /* * XXX parity protection should be folded in here when it's converted diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index ad3d2031c32..c3b41e24c05 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -1231,7 +1231,8 @@ static int enable_restore_fp_context(int msa) /* Restore the scalar FP control & status register */ if (!was_fpu_owner) - asm volatile("ctc1 %0, $31" : : "r"(current->thread.fpu.fcr31)); + write_32bit_cp1_register(CP1_STATUS, + current->thread.fpu.fcr31); } out: diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index 30e334e823b..2ae12825529 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -20,6 +20,7 @@ config KVM select PREEMPT_NOTIFIERS select ANON_INODES select KVM_MMIO + select SRCU ---help--- Support for hosting Guest kernels. Currently supported on MIPS32 processors. diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index e90b2e89929..30639a6e9b8 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -489,6 +489,8 @@ static void r4k_tlb_configure(void) #ifdef CONFIG_64BIT pg |= PG_ELPA; #endif + if (cpu_has_rixiex) + pg |= PG_IEC; write_c0_pagegrain(pg); } diff --git a/arch/mips/pci/pci-bcm1480.c b/arch/mips/pci/pci-bcm1480.c index 5ec2a7bae02..f2355e3e65a 100644 --- a/arch/mips/pci/pci-bcm1480.c +++ b/arch/mips/pci/pci-bcm1480.c @@ -173,8 +173,8 @@ static int bcm1480_pcibios_write(struct pci_bus *bus, unsigned int devfn, } struct pci_ops bcm1480_pci_ops = { - bcm1480_pcibios_read, - bcm1480_pcibios_write, + .read = bcm1480_pcibios_read, + .write = bcm1480_pcibios_write, }; static struct resource bcm1480_mem_resource = { diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c index d07e04121cc..bedb72bd3a2 100644 --- a/arch/mips/pci/pci-octeon.c +++ b/arch/mips/pci/pci-octeon.c @@ -327,8 +327,8 @@ static int octeon_write_config(struct pci_bus *bus, unsigned int devfn, static struct pci_ops octeon_pci_ops = { - octeon_read_config, - octeon_write_config, + .read = octeon_read_config, + .write = octeon_write_config, }; static struct resource octeon_pci_mem_resource = { diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c index 5e36c33e554..eb4a17ba4a5 100644 --- a/arch/mips/pci/pcie-octeon.c +++ b/arch/mips/pci/pcie-octeon.c @@ -1792,8 +1792,8 @@ static int octeon_dummy_write_config(struct pci_bus *bus, unsigned int devfn, } static struct pci_ops octeon_pcie0_ops = { - octeon_pcie0_read_config, - octeon_pcie0_write_config, + .read = octeon_pcie0_read_config, + .write = octeon_pcie0_write_config, }; static struct resource octeon_pcie0_mem_resource = { @@ -1813,8 +1813,8 @@ static struct pci_controller octeon_pcie0_controller = { }; static struct pci_ops octeon_pcie1_ops = { - octeon_pcie1_read_config, - octeon_pcie1_write_config, + .read = octeon_pcie1_read_config, + .write = octeon_pcie1_write_config, }; static struct resource octeon_pcie1_mem_resource = { @@ -1834,8 +1834,8 @@ static struct pci_controller octeon_pcie1_controller = { }; static struct pci_ops octeon_dummy_ops = { - octeon_dummy_read_config, - octeon_dummy_write_config, + .read = octeon_dummy_read_config, + .write = octeon_dummy_write_config, }; static struct resource octeon_dummy_mem_resource = { diff --git a/arch/mn10300/include/asm/cacheflush.h b/arch/mn10300/include/asm/cacheflush.h index faed90240de..6d6df839948 100644 --- a/arch/mn10300/include/asm/cacheflush.h +++ b/arch/mn10300/include/asm/cacheflush.h @@ -159,13 +159,6 @@ extern void flush_icache_range(unsigned long start, unsigned long end); #define copy_from_user_page(vma, page, vaddr, dst, src, len) \ memcpy(dst, src, len) -/* - * Internal debugging function - */ -#ifdef CONFIG_DEBUG_PAGEALLOC -extern void kernel_map_pages(struct page *page, int numpages, int enable); -#endif - #endif /* __ASSEMBLY__ */ #endif /* _ASM_CACHEFLUSH_H */ diff --git a/arch/mn10300/include/asm/pgtable.h b/arch/mn10300/include/asm/pgtable.h index 2ddaa67e798..629181ae111 100644 --- a/arch/mn10300/include/asm/pgtable.h +++ b/arch/mn10300/include/asm/pgtable.h @@ -134,7 +134,6 @@ extern pte_t kernel_vmalloc_ptes[(VMALLOC_END - VMALLOC_START) / PAGE_SIZE]; #define _PAGE_NX 0 /* no-execute bit */ /* If _PAGE_VALID is clear, we use these: */ -#define _PAGE_FILE xPTEL2_C /* set:pagecache unset:swap */ #define _PAGE_PROTNONE 0x000 /* If not present */ #define __PAGE_PROT_UWAUX 0x010 @@ -241,11 +240,6 @@ static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } static inline int pte_write(pte_t pte) { return pte_val(pte) & __PAGE_PROT_WRITE; } static inline int pte_special(pte_t pte){ return 0; } -/* - * The following only works if pte_present() is not true. - */ -static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } - static inline pte_t pte_rdprotect(pte_t pte) { pte_val(pte) &= ~(__PAGE_PROT_USER|__PAGE_PROT_UWAUX); return pte; @@ -338,16 +332,11 @@ static inline int pte_exec_kernel(pte_t pte) return 1; } -#define PTE_FILE_MAX_BITS 30 - -#define pte_to_pgoff(pte) (pte_val(pte) >> 2) -#define pgoff_to_pte(off) __pte((off) << 2 | _PAGE_FILE) - /* Encode and de-code a swap entry */ -#define __swp_type(x) (((x).val >> 2) & 0x3f) -#define __swp_offset(x) ((x).val >> 8) +#define __swp_type(x) (((x).val >> 1) & 0x3f) +#define __swp_offset(x) ((x).val >> 7) #define __swp_entry(type, offset) \ - ((swp_entry_t) { ((type) << 2) | ((offset) << 8) }) + ((swp_entry_t) { ((type) << 1) | ((offset) << 7) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) __pte((x).val) diff --git a/arch/mn10300/unit-asb2305/pci.c b/arch/mn10300/unit-asb2305/pci.c index 471ff398090..613ca1e55b4 100644 --- a/arch/mn10300/unit-asb2305/pci.c +++ b/arch/mn10300/unit-asb2305/pci.c @@ -228,8 +228,8 @@ static int pci_ampci_write_config(struct pci_bus *bus, unsigned int devfn, } static struct pci_ops pci_direct_ampci = { - pci_ampci_read_config, - pci_ampci_write_config, + .read = pci_ampci_read_config, + .write = pci_ampci_write_config, }; /* diff --git a/arch/nios2/include/asm/pgtable-bits.h b/arch/nios2/include/asm/pgtable-bits.h index ce9e7069aa9..bfddff383e8 100644 --- a/arch/nios2/include/asm/pgtable-bits.h +++ b/arch/nios2/include/asm/pgtable-bits.h @@ -30,6 +30,5 @@ #define _PAGE_PRESENT (1<<25) /* PTE contains a translation */ #define _PAGE_ACCESSED (1<<26) /* page referenced */ #define _PAGE_DIRTY (1<<27) /* dirty page */ -#define _PAGE_FILE (1<<28) /* PTE used for file mapping or swap */ #endif /* _ASM_NIOS2_PGTABLE_BITS_H */ diff --git a/arch/nios2/include/asm/pgtable.h b/arch/nios2/include/asm/pgtable.h index ccbaffd4767..7b292e3a313 100644 --- a/arch/nios2/include/asm/pgtable.h +++ b/arch/nios2/include/asm/pgtable.h @@ -112,8 +112,6 @@ static inline int pte_dirty(pte_t pte) \ { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_young(pte_t pte) \ { return pte_val(pte) & _PAGE_ACCESSED; } -static inline int pte_file(pte_t pte) \ - { return pte_val(pte) & _PAGE_FILE; } static inline int pte_special(pte_t pte) { return 0; } #define pgprot_noncached pgprot_noncached @@ -272,8 +270,7 @@ static inline void pte_clear(struct mm_struct *mm, __FILE__, __LINE__, pgd_val(e)) /* - * Encode and decode a swap entry (must be !pte_none(pte) && !pte_present(pte) - * && !pte_file(pte)): + * Encode and decode a swap entry (must be !pte_none(pte) && !pte_present(pte): * * 31 30 29 28 27 26 25 24 23 22 21 20 19 18 ... 1 0 * 0 0 0 0 type. 0 0 0 0 0 0 offset......... @@ -290,11 +287,6 @@ static inline void pte_clear(struct mm_struct *mm, #define __swp_entry_to_pte(swp) ((pte_t) { (swp).val }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) -/* Encode and decode a nonlinear file mapping entry */ -#define PTE_FILE_MAX_BITS 25 -#define pte_to_pgoff(pte) (pte_val(pte) & 0x1ffffff) -#define pgoff_to_pte(off) __pte(((off) & 0x1ffffff) | _PAGE_FILE) - #define kern_addr_valid(addr) (1) #include <asm-generic/pgtable.h> diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index 34429d5a0cc..d194c0427b2 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -159,9 +159,11 @@ bad_area: bad_area_nosemaphore: /* User mode accesses just cause a SIGSEGV */ if (user_mode(regs)) { - pr_alert("%s: unhandled page fault (%d) at 0x%08lx, " - "cause %ld\n", current->comm, SIGSEGV, address, cause); - show_regs(regs); + if (unhandled_signal(current, SIGSEGV) && printk_ratelimit()) { + pr_info("%s: unhandled page fault (%d) at 0x%08lx, " + "cause %ld\n", current->comm, SIGSEGV, address, cause); + show_regs(regs); + } _exception(SIGSEGV, regs, code, address); return; } diff --git a/arch/openrisc/include/asm/pgtable.h b/arch/openrisc/include/asm/pgtable.h index 37bf6a3ef8f..18994ccb118 100644 --- a/arch/openrisc/include/asm/pgtable.h +++ b/arch/openrisc/include/asm/pgtable.h @@ -125,7 +125,6 @@ extern void paging_init(void); #define _PAGE_CC 0x001 /* software: pte contains a translation */ #define _PAGE_CI 0x002 /* cache inhibit */ #define _PAGE_WBC 0x004 /* write back cache */ -#define _PAGE_FILE 0x004 /* set: pagecache, unset: swap (when !PRESENT) */ #define _PAGE_WOM 0x008 /* weakly ordered memory */ #define _PAGE_A 0x010 /* accessed */ @@ -240,7 +239,6 @@ static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_WRITE; } static inline int pte_exec(pte_t pte) { return pte_val(pte) & _PAGE_EXEC; } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } -static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } static inline int pte_special(pte_t pte) { return 0; } static inline pte_t pte_mkspecial(pte_t pte) { return pte; } @@ -438,12 +436,6 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -/* Encode and decode a nonlinear file mapping entry */ - -#define PTE_FILE_MAX_BITS 26 -#define pte_to_pgoff(x) (pte_val(x) >> 6) -#define pgoff_to_pte(x) __pte(((x) << 6) | _PAGE_FILE) - #define kern_addr_valid(addr) (1) #include <asm-generic/pgtable.h> diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S index 1d3c9c28ac2..f14793306b0 100644 --- a/arch/openrisc/kernel/head.S +++ b/arch/openrisc/kernel/head.S @@ -754,11 +754,6 @@ _dc_enable: /* ===============================================[ page table masks ]=== */ -/* bit 4 is used in hardware as write back cache bit. we never use this bit - * explicitly, so we can reuse it as _PAGE_FILE bit and mask it out when - * writing into hardware pte's - */ - #define DTLB_UP_CONVERT_MASK 0x3fa #define ITLB_UP_CONVERT_MASK 0x3a diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 22b89d1edba..1d49a4a7749 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -146,7 +146,6 @@ extern void purge_tlb_entries(struct mm_struct *, unsigned long); #define _PAGE_GATEWAY_BIT 28 /* (0x008) privilege promotion allowed */ #define _PAGE_DMB_BIT 27 /* (0x010) Data Memory Break enable (B bit) */ #define _PAGE_DIRTY_BIT 26 /* (0x020) Page Dirty (D bit) */ -#define _PAGE_FILE_BIT _PAGE_DIRTY_BIT /* overload this bit */ #define _PAGE_REFTRAP_BIT 25 /* (0x040) Page Ref. Trap enable (T bit) */ #define _PAGE_NO_CACHE_BIT 24 /* (0x080) Uncached Page (U bit) */ #define _PAGE_ACCESSED_BIT 23 /* (0x100) Software: Page Accessed */ @@ -167,13 +166,6 @@ extern void purge_tlb_entries(struct mm_struct *, unsigned long); /* PFN_PTE_SHIFT defines the shift of a PTE value to access the PFN field */ #define PFN_PTE_SHIFT 12 - -/* this is how many bits may be used by the file functions */ -#define PTE_FILE_MAX_BITS (BITS_PER_LONG - PTE_SHIFT) - -#define pte_to_pgoff(pte) (pte_val(pte) >> PTE_SHIFT) -#define pgoff_to_pte(off) ((pte_t) { ((off) << PTE_SHIFT) | _PAGE_FILE }) - #define _PAGE_READ (1 << xlate_pabit(_PAGE_READ_BIT)) #define _PAGE_WRITE (1 << xlate_pabit(_PAGE_WRITE_BIT)) #define _PAGE_RW (_PAGE_READ | _PAGE_WRITE) @@ -186,7 +178,6 @@ extern void purge_tlb_entries(struct mm_struct *, unsigned long); #define _PAGE_ACCESSED (1 << xlate_pabit(_PAGE_ACCESSED_BIT)) #define _PAGE_PRESENT (1 << xlate_pabit(_PAGE_PRESENT_BIT)) #define _PAGE_USER (1 << xlate_pabit(_PAGE_USER_BIT)) -#define _PAGE_FILE (1 << xlate_pabit(_PAGE_FILE_BIT)) #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED) #define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY) @@ -344,7 +335,6 @@ static inline void pgd_clear(pgd_t * pgdp) { } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_WRITE; } -static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } static inline int pte_special(pte_t pte) { return 0; } static inline pte_t pte_mkclean(pte_t pte) { pte_val(pte) &= ~_PAGE_DIRTY; return pte; } diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index 5b9312220e8..30b35fff2de 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -60,13 +60,6 @@ extern void flush_dcache_phys_range(unsigned long start, unsigned long stop); #define copy_from_user_page(vma, page, vaddr, dst, src, len) \ memcpy(dst, src, len) - - -#ifdef CONFIG_DEBUG_PAGEALLOC -/* internal debugging function */ -void kernel_map_pages(struct page *page, int numpages, int enable); -#endif - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_CACHEFLUSH_H */ diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index f5769f19ae2..11850f310fb 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -21,6 +21,7 @@ config KVM select PREEMPT_NOTIFIERS select ANON_INODES select HAVE_KVM_EVENTFD + select SRCU config KVM_BOOK3S_HANDLER bool diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c index f2238759804..94170e4f2ce 100644 --- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c +++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c @@ -399,8 +399,8 @@ static int scc_pciex_write_config(struct pci_bus *bus, unsigned int devfn, } static struct pci_ops scc_pciex_pci_ops = { - scc_pciex_read_config, - scc_pciex_write_config, + .read = scc_pciex_read_config, + .write = scc_pciex_write_config, }; static void pciex_clear_intr_all(unsigned int __iomem *base) diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index 04702db35d4..f4071a67ad0 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -133,17 +133,23 @@ static void __init fixup_bus_range(struct device_node *bridge) |(((unsigned int)(off)) & 0xFCUL) \ |1UL) -static volatile void __iomem *macrisc_cfg_access(struct pci_controller* hose, - u8 bus, u8 dev_fn, u8 offset) +static void __iomem *macrisc_cfg_map_bus(struct pci_bus *bus, + unsigned int dev_fn, + int offset) { unsigned int caddr; + struct pci_controller *hose; - if (bus == hose->first_busno) { + hose = pci_bus_to_host(bus); + if (hose == NULL) + return NULL; + + if (bus->number == hose->first_busno) { if (dev_fn < (11 << 3)) return NULL; caddr = MACRISC_CFA0(dev_fn, offset); } else - caddr = MACRISC_CFA1(bus, dev_fn, offset); + caddr = MACRISC_CFA1(bus->number, dev_fn, offset); /* Uninorth will return garbage if we don't read back the value ! */ do { @@ -154,129 +160,46 @@ static volatile void __iomem *macrisc_cfg_access(struct pci_controller* hose, return hose->cfg_data + offset; } -static int macrisc_read_config(struct pci_bus *bus, unsigned int devfn, - int offset, int len, u32 *val) -{ - struct pci_controller *hose; - volatile void __iomem *addr; - - hose = pci_bus_to_host(bus); - if (hose == NULL) - return PCIBIOS_DEVICE_NOT_FOUND; - if (offset >= 0x100) - return PCIBIOS_BAD_REGISTER_NUMBER; - addr = macrisc_cfg_access(hose, bus->number, devfn, offset); - if (!addr) - return PCIBIOS_DEVICE_NOT_FOUND; - /* - * Note: the caller has already checked that offset is - * suitably aligned and that len is 1, 2 or 4. - */ - switch (len) { - case 1: - *val = in_8(addr); - break; - case 2: - *val = in_le16(addr); - break; - default: - *val = in_le32(addr); - break; - } - return PCIBIOS_SUCCESSFUL; -} - -static int macrisc_write_config(struct pci_bus *bus, unsigned int devfn, - int offset, int len, u32 val) -{ - struct pci_controller *hose; - volatile void __iomem *addr; - - hose = pci_bus_to_host(bus); - if (hose == NULL) - return PCIBIOS_DEVICE_NOT_FOUND; - if (offset >= 0x100) - return PCIBIOS_BAD_REGISTER_NUMBER; - addr = macrisc_cfg_access(hose, bus->number, devfn, offset); - if (!addr) - return PCIBIOS_DEVICE_NOT_FOUND; - /* - * Note: the caller has already checked that offset is - * suitably aligned and that len is 1, 2 or 4. - */ - switch (len) { - case 1: - out_8(addr, val); - break; - case 2: - out_le16(addr, val); - break; - default: - out_le32(addr, val); - break; - } - return PCIBIOS_SUCCESSFUL; -} - static struct pci_ops macrisc_pci_ops = { - .read = macrisc_read_config, - .write = macrisc_write_config, + .map_bus = macrisc_cfg_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, }; #ifdef CONFIG_PPC32 /* * Verify that a specific (bus, dev_fn) exists on chaos */ -static int chaos_validate_dev(struct pci_bus *bus, int devfn, int offset) +static void __iomem *chaos_map_bus(struct pci_bus *bus, unsigned int devfn, + int offset) { struct device_node *np; const u32 *vendor, *device; if (offset >= 0x100) - return PCIBIOS_BAD_REGISTER_NUMBER; + return NULL; np = of_pci_find_child_device(bus->dev.of_node, devfn); if (np == NULL) - return PCIBIOS_DEVICE_NOT_FOUND; + return NULL; vendor = of_get_property(np, "vendor-id", NULL); device = of_get_property(np, "device-id", NULL); if (vendor == NULL || device == NULL) - return PCIBIOS_DEVICE_NOT_FOUND; + return NULL; if ((*vendor == 0x106b) && (*device == 3) && (offset >= 0x10) && (offset != 0x14) && (offset != 0x18) && (offset <= 0x24)) - return PCIBIOS_BAD_REGISTER_NUMBER; - - return PCIBIOS_SUCCESSFUL; -} + return NULL; -static int -chaos_read_config(struct pci_bus *bus, unsigned int devfn, int offset, - int len, u32 *val) -{ - int result = chaos_validate_dev(bus, devfn, offset); - if (result == PCIBIOS_BAD_REGISTER_NUMBER) - *val = ~0U; - if (result != PCIBIOS_SUCCESSFUL) - return result; - return macrisc_read_config(bus, devfn, offset, len, val); -} - -static int -chaos_write_config(struct pci_bus *bus, unsigned int devfn, int offset, - int len, u32 val) -{ - int result = chaos_validate_dev(bus, devfn, offset); - if (result != PCIBIOS_SUCCESSFUL) - return result; - return macrisc_write_config(bus, devfn, offset, len, val); + return macrisc_cfg_map_bus(bus, devfn, offset); } static struct pci_ops chaos_pci_ops = { - .read = chaos_read_config, - .write = chaos_write_config, + .map_bus = chaos_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, }; static void __init setup_chaos(struct pci_controller *hose, @@ -471,15 +394,24 @@ static struct pci_ops u3_ht_pci_ops = |(((unsigned int)(off)) & 0xfcU) \ |1UL) -static volatile void __iomem *u4_pcie_cfg_access(struct pci_controller* hose, - u8 bus, u8 dev_fn, int offset) +static void __iomem *u4_pcie_cfg_map_bus(struct pci_bus *bus, + unsigned int dev_fn, + int offset) { + struct pci_controller *hose; unsigned int caddr; - if (bus == hose->first_busno) { + if (offset >= 0x1000) + return NULL; + + hose = pci_bus_to_host(bus); + if (!hose) + return NULL; + + if (bus->number == hose->first_busno) { caddr = U4_PCIE_CFA0(dev_fn, offset); } else - caddr = U4_PCIE_CFA1(bus, dev_fn, offset); + caddr = U4_PCIE_CFA1(bus->number, dev_fn, offset); /* Uninorth will return garbage if we don't read back the value ! */ do { @@ -490,74 +422,11 @@ static volatile void __iomem *u4_pcie_cfg_access(struct pci_controller* hose, return hose->cfg_data + offset; } -static int u4_pcie_read_config(struct pci_bus *bus, unsigned int devfn, - int offset, int len, u32 *val) -{ - struct pci_controller *hose; - volatile void __iomem *addr; - - hose = pci_bus_to_host(bus); - if (hose == NULL) - return PCIBIOS_DEVICE_NOT_FOUND; - if (offset >= 0x1000) - return PCIBIOS_BAD_REGISTER_NUMBER; - addr = u4_pcie_cfg_access(hose, bus->number, devfn, offset); - if (!addr) - return PCIBIOS_DEVICE_NOT_FOUND; - /* - * Note: the caller has already checked that offset is - * suitably aligned and that len is 1, 2 or 4. - */ - switch (len) { - case 1: - *val = in_8(addr); - break; - case 2: - *val = in_le16(addr); - break; - default: - *val = in_le32(addr); - break; - } - return PCIBIOS_SUCCESSFUL; -} - -static int u4_pcie_write_config(struct pci_bus *bus, unsigned int devfn, - int offset, int len, u32 val) -{ - struct pci_controller *hose; - volatile void __iomem *addr; - - hose = pci_bus_to_host(bus); - if (hose == NULL) - return PCIBIOS_DEVICE_NOT_FOUND; - if (offset >= 0x1000) - return PCIBIOS_BAD_REGISTER_NUMBER; - addr = u4_pcie_cfg_access(hose, bus->number, devfn, offset); - if (!addr) - return PCIBIOS_DEVICE_NOT_FOUND; - /* - * Note: the caller has already checked that offset is - * suitably aligned and that len is 1, 2 or 4. - */ - switch (len) { - case 1: - out_8(addr, val); - break; - case 2: - out_le16(addr, val); - break; - default: - out_le32(addr, val); - break; - } - return PCIBIOS_SUCCESSFUL; -} - static struct pci_ops u4_pcie_pci_ops = { - .read = u4_pcie_read_config, - .write = u4_pcie_write_config, + .map_bus = u4_pcie_cfg_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, }; static void pmac_pci_fixup_u4_of_node(struct pci_dev *dev) diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 6455c1eada1..271b67e7670 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -645,61 +645,21 @@ mapped: return pcie->cfg_type1 + offset; } -static int mpc83xx_pcie_read_config(struct pci_bus *bus, unsigned int devfn, - int offset, int len, u32 *val) -{ - void __iomem *cfg_addr; - - cfg_addr = mpc83xx_pcie_remap_cfg(bus, devfn, offset); - if (!cfg_addr) - return PCIBIOS_DEVICE_NOT_FOUND; - - switch (len) { - case 1: - *val = in_8(cfg_addr); - break; - case 2: - *val = in_le16(cfg_addr); - break; - default: - *val = in_le32(cfg_addr); - break; - } - - return PCIBIOS_SUCCESSFUL; -} - static int mpc83xx_pcie_write_config(struct pci_bus *bus, unsigned int devfn, int offset, int len, u32 val) { struct pci_controller *hose = pci_bus_to_host(bus); - void __iomem *cfg_addr; - - cfg_addr = mpc83xx_pcie_remap_cfg(bus, devfn, offset); - if (!cfg_addr) - return PCIBIOS_DEVICE_NOT_FOUND; /* PPC_INDIRECT_TYPE_SURPRESS_PRIMARY_BUS */ if (offset == PCI_PRIMARY_BUS && bus->number == hose->first_busno) val &= 0xffffff00; - switch (len) { - case 1: - out_8(cfg_addr, val); - break; - case 2: - out_le16(cfg_addr, val); - break; - default: - out_le32(cfg_addr, val); - break; - } - - return PCIBIOS_SUCCESSFUL; + return pci_generic_config_write(bus, devfn, offset, len, val); } static struct pci_ops mpc83xx_pcie_ops = { - .read = mpc83xx_pcie_read_config, + .map_bus = mpc83xx_pcie_remap_cfg, + .read = pci_generic_config_read, .write = mpc83xx_pcie_write_config, }; diff --git a/arch/s390/include/asm/cacheflush.h b/arch/s390/include/asm/cacheflush.h index 3e20383d092..58fae7d098c 100644 --- a/arch/s390/include/asm/cacheflush.h +++ b/arch/s390/include/asm/cacheflush.h @@ -4,10 +4,6 @@ /* Caches aren't brain-dead on the s390. */ #include <asm-generic/cacheflush.h> -#ifdef CONFIG_DEBUG_PAGEALLOC -void kernel_map_pages(struct page *page, int numpages, int enable); -#endif - int set_memory_ro(unsigned long addr, int numpages); int set_memory_rw(unsigned long addr, int numpages); int set_memory_nx(unsigned long addr, int numpages); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 5e102422c9a..ffb1d8ce97a 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -249,10 +249,10 @@ static inline int is_module_addr(void *addr) _PAGE_YOUNG) /* - * handle_pte_fault uses pte_present, pte_none and pte_file to find out the - * pte type WITHOUT holding the page table lock. The _PAGE_PRESENT bit - * is used to distinguish present from not-present ptes. It is changed only - * with the page table lock held. + * handle_pte_fault uses pte_present and pte_none to find out the pte type + * WITHOUT holding the page table lock. The _PAGE_PRESENT bit is used to + * distinguish present from not-present ptes. It is changed only with the page + * table lock held. * * The following table gives the different possible bit combinations for * the pte hardware and software bits in the last 12 bits of a pte: @@ -279,7 +279,6 @@ static inline int is_module_addr(void *addr) * * pte_present is true for the bit pattern .xx...xxxxx1, (pte & 0x001) == 0x001 * pte_none is true for the bit pattern .10...xxxx00, (pte & 0x603) == 0x400 - * pte_file is true for the bit pattern .11...xxxxx0, (pte & 0x601) == 0x600 * pte_swap is true for the bit pattern .10...xxxx10, (pte & 0x603) == 0x402 */ @@ -671,13 +670,6 @@ static inline int pte_swap(pte_t pte) == (_PAGE_INVALID | _PAGE_TYPE); } -static inline int pte_file(pte_t pte) -{ - /* Bit pattern: (pte & 0x601) == 0x600 */ - return (pte_val(pte) & (_PAGE_INVALID | _PAGE_PROTECT | _PAGE_PRESENT)) - == (_PAGE_INVALID | _PAGE_PROTECT); -} - static inline int pte_special(pte_t pte) { return (pte_val(pte) & _PAGE_SPECIAL); @@ -1756,19 +1748,6 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#ifndef CONFIG_64BIT -# define PTE_FILE_MAX_BITS 26 -#else /* CONFIG_64BIT */ -# define PTE_FILE_MAX_BITS 59 -#endif /* CONFIG_64BIT */ - -#define pte_to_pgoff(__pte) \ - ((((__pte).pte >> 12) << 7) + (((__pte).pte >> 1) & 0x7f)) - -#define pgoff_to_pte(__off) \ - ((pte_t) { ((((__off) & 0x7f) << 1) + (((__off) >> 7) << 12)) \ - | _PAGE_INVALID | _PAGE_PROTECT }) - #endif /* !__ASSEMBLY__ */ #define kern_addr_valid(addr) (1) diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 646db9c467d..5fce52cf0e5 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -28,6 +28,7 @@ config KVM select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQFD select HAVE_KVM_IRQ_ROUTING + select SRCU ---help--- Support hosting paravirtualized guest machines using the SIE virtualization capability on the mainframe. This should work diff --git a/arch/score/include/asm/pgtable-bits.h b/arch/score/include/asm/pgtable-bits.h index 7d65a96a82e..0e5c6f46652 100644 --- a/arch/score/include/asm/pgtable-bits.h +++ b/arch/score/include/asm/pgtable-bits.h @@ -6,7 +6,6 @@ #define _PAGE_WRITE (1<<7) /* implemented in software */ #define _PAGE_PRESENT (1<<9) /* implemented in software */ #define _PAGE_MODIFIED (1<<10) /* implemented in software */ -#define _PAGE_FILE (1<<10) #define _PAGE_GLOBAL (1<<0) #define _PAGE_VALID (1<<1) diff --git a/arch/score/include/asm/pgtable.h b/arch/score/include/asm/pgtable.h index db96ad9afc0..5170ffdea64 100644 --- a/arch/score/include/asm/pgtable.h +++ b/arch/score/include/asm/pgtable.h @@ -90,15 +90,6 @@ static inline void pmd_clear(pmd_t *pmdp) ((pte_t *)page_address(pmd_page(*(dir))) + __pte_offset(address)) #define pte_unmap(pte) ((void)(pte)) -/* - * Bits 9(_PAGE_PRESENT) and 10(_PAGE_FILE)are taken, - * split up 30 bits of offset into this range: - */ -#define PTE_FILE_MAX_BITS 30 -#define pte_to_pgoff(_pte) \ - (((_pte).pte & 0x1ff) | (((_pte).pte >> 11) << 9)) -#define pgoff_to_pte(off) \ - ((pte_t) {((off) & 0x1ff) | (((off) >> 9) << 11) | _PAGE_FILE}) #define __pte_to_swp_entry(pte) \ ((swp_entry_t) { pte_val(pte)}) #define __swp_entry_to_pte(x) ((pte_t) {(x).val}) @@ -169,8 +160,8 @@ static inline pgprot_t pgprot_noncached(pgprot_t _prot) } #define __swp_type(x) ((x).val & 0x1f) -#define __swp_offset(x) ((x).val >> 11) -#define __swp_entry(type, offset) ((swp_entry_t){(type) | ((offset) << 11)}) +#define __swp_offset(x) ((x).val >> 10) +#define __swp_entry(type, offset) ((swp_entry_t){(type) | ((offset) << 10)}) extern unsigned long empty_zero_page; extern unsigned long zero_page_mask; @@ -198,11 +189,6 @@ static inline int pte_young(pte_t pte) return pte_val(pte) & _PAGE_ACCESSED; } -static inline int pte_file(pte_t pte) -{ - return pte_val(pte) & _PAGE_FILE; -} - #define pte_special(pte) (0) static inline pte_t pte_wrprotect(pte_t pte) diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 0f09f5285d5..eb4ef274ae9 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -1,7 +1,7 @@ config SUPERH def_bool y select ARCH_MIGHT_HAVE_PC_PARPORT - select EXPERT + select HAVE_PATA_PLATFORM select CLKDEV_LOOKUP select HAVE_IDE if HAS_IOPORT_MAP select HAVE_MEMBLOCK diff --git a/arch/sh/boards/mach-se/7343/irq.c b/arch/sh/boards/mach-se/7343/irq.c index 7646bf0486c..1087dba9b01 100644 --- a/arch/sh/boards/mach-se/7343/irq.c +++ b/arch/sh/boards/mach-se/7343/irq.c @@ -14,9 +14,6 @@ #define DRV_NAME "SE7343-FPGA" #define pr_fmt(fmt) DRV_NAME ": " fmt -#define irq_reg_readl ioread16 -#define irq_reg_writel iowrite16 - #include <linux/init.h> #include <linux/irq.h> #include <linux/interrupt.h> diff --git a/arch/sh/boards/mach-se/7722/irq.c b/arch/sh/boards/mach-se/7722/irq.c index f5e2af1bf04..00e69923262 100644 --- a/arch/sh/boards/mach-se/7722/irq.c +++ b/arch/sh/boards/mach-se/7722/irq.c @@ -11,9 +11,6 @@ #define DRV_NAME "SE7722-FPGA" #define pr_fmt(fmt) DRV_NAME ": " fmt -#define irq_reg_readl ioread16 -#define irq_reg_writel iowrite16 - #include <linux/init.h> #include <linux/irq.h> #include <linux/interrupt.h> diff --git a/arch/sh/include/asm/pgtable_32.h b/arch/sh/include/asm/pgtable_32.h index 0bce3d81569..c646e563abc 100644 --- a/arch/sh/include/asm/pgtable_32.h +++ b/arch/sh/include/asm/pgtable_32.h @@ -26,8 +26,6 @@ * and timing control which (together with bit 0) are moved into the * old-style PTEA on the parts that support it. * - * XXX: Leave the _PAGE_FILE and _PAGE_WT overhaul for a rainy day. - * * SH-X2 MMUs and extended PTEs * * SH-X2 supports an extended mode TLB with split data arrays due to the @@ -51,7 +49,6 @@ #define _PAGE_PRESENT 0x100 /* V-bit : page is valid */ #define _PAGE_PROTNONE 0x200 /* software: if not present */ #define _PAGE_ACCESSED 0x400 /* software: page referenced */ -#define _PAGE_FILE _PAGE_WT /* software: pagecache or swap? */ #define _PAGE_SPECIAL 0x800 /* software: special page */ #define _PAGE_SZ_MASK (_PAGE_SZ0 | _PAGE_SZ1) @@ -105,14 +102,13 @@ static inline unsigned long copy_ptea_attributes(unsigned long x) /* Mask which drops unused bits from the PTEL value */ #if defined(CONFIG_CPU_SH3) #define _PAGE_CLEAR_FLAGS (_PAGE_PROTNONE | _PAGE_ACCESSED| \ - _PAGE_FILE | _PAGE_SZ1 | \ - _PAGE_HW_SHARED) + _PAGE_SZ1 | _PAGE_HW_SHARED) #elif defined(CONFIG_X2TLB) /* Get rid of the legacy PR/SZ bits when using extended mode */ #define _PAGE_CLEAR_FLAGS (_PAGE_PROTNONE | _PAGE_ACCESSED | \ - _PAGE_FILE | _PAGE_PR_MASK | _PAGE_SZ_MASK) + _PAGE_PR_MASK | _PAGE_SZ_MASK) #else -#define _PAGE_CLEAR_FLAGS (_PAGE_PROTNONE | _PAGE_ACCESSED | _PAGE_FILE) +#define _PAGE_CLEAR_FLAGS (_PAGE_PROTNONE | _PAGE_ACCESSED) #endif #define _PAGE_FLAGS_HARDWARE_MASK (phys_addr_mask() & ~(_PAGE_CLEAR_FLAGS)) @@ -343,7 +339,6 @@ static inline void set_pte(pte_t *ptep, pte_t pte) #define pte_not_present(pte) (!((pte).pte_low & _PAGE_PRESENT)) #define pte_dirty(pte) ((pte).pte_low & _PAGE_DIRTY) #define pte_young(pte) ((pte).pte_low & _PAGE_ACCESSED) -#define pte_file(pte) ((pte).pte_low & _PAGE_FILE) #define pte_special(pte) ((pte).pte_low & _PAGE_SPECIAL) #ifdef CONFIG_X2TLB @@ -445,7 +440,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) * Encode and de-code a swap entry * * Constraints: - * _PAGE_FILE at bit 0 * _PAGE_PRESENT at bit 8 * _PAGE_PROTNONE at bit 9 * @@ -453,9 +447,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) * swap offset into bits 10:30. For the 64-bit PTE case, we keep the * preserved bits in the low 32-bits and use the upper 32 as the swap * offset (along with a 5-bit type), following the same approach as x86 - * PAE. This keeps the logic quite simple, and allows for a full 32 - * PTE_FILE_MAX_BITS, as opposed to the 29-bits we're constrained with - * in the pte_low case. + * PAE. This keeps the logic quite simple. * * As is evident by the Alpha code, if we ever get a 64-bit unsigned * long (swp_entry_t) to match up with the 64-bit PTEs, this all becomes @@ -471,13 +463,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #define __pte_to_swp_entry(pte) ((swp_entry_t){ (pte).pte_high }) #define __swp_entry_to_pte(x) ((pte_t){ 0, (x).val }) -/* - * Encode and decode a nonlinear file mapping entry - */ -#define pte_to_pgoff(pte) ((pte).pte_high) -#define pgoff_to_pte(off) ((pte_t) { _PAGE_FILE, (off) }) - -#define PTE_FILE_MAX_BITS 32 #else #define __swp_type(x) ((x).val & 0xff) #define __swp_offset(x) ((x).val >> 10) @@ -485,13 +470,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) >> 1 }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val << 1 }) - -/* - * Encode and decode a nonlinear file mapping entry - */ -#define PTE_FILE_MAX_BITS 29 -#define pte_to_pgoff(pte) (pte_val(pte) >> 1) -#define pgoff_to_pte(off) ((pte_t) { ((off) << 1) | _PAGE_FILE }) #endif #endif /* __ASSEMBLY__ */ diff --git a/arch/sh/include/asm/pgtable_64.h b/arch/sh/include/asm/pgtable_64.h index dda8c82601b..07424968df6 100644 --- a/arch/sh/include/asm/pgtable_64.h +++ b/arch/sh/include/asm/pgtable_64.h @@ -107,7 +107,6 @@ static __inline__ void set_pte(pte_t *pteptr, pte_t pteval) #define _PAGE_DEVICE 0x001 /* CB0: if uncacheable, 1->device (i.e. no write-combining or reordering at bus level) */ #define _PAGE_CACHABLE 0x002 /* CB1: uncachable/cachable */ #define _PAGE_PRESENT 0x004 /* software: page referenced */ -#define _PAGE_FILE 0x004 /* software: only when !present */ #define _PAGE_SIZE0 0x008 /* SZ0-bit : size of page */ #define _PAGE_SIZE1 0x010 /* SZ1-bit : size of page */ #define _PAGE_SHARED 0x020 /* software: reflects PTEH's SH */ @@ -129,7 +128,7 @@ static __inline__ void set_pte(pte_t *pteptr, pte_t pteval) #define _PAGE_WIRED _PAGE_EXT(0x001) /* software: wire the tlb entry */ #define _PAGE_SPECIAL _PAGE_EXT(0x002) -#define _PAGE_CLEAR_FLAGS (_PAGE_PRESENT | _PAGE_FILE | _PAGE_SHARED | \ +#define _PAGE_CLEAR_FLAGS (_PAGE_PRESENT | _PAGE_SHARED | \ _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_WIRED) /* Mask which drops software flags */ @@ -260,7 +259,6 @@ static __inline__ void set_pte(pte_t *pteptr, pte_t pteval) */ static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } -static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_WRITE; } static inline int pte_special(pte_t pte){ return pte_val(pte) & _PAGE_SPECIAL; } @@ -304,11 +302,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -/* Encode and decode a nonlinear file mapping entry */ -#define PTE_FILE_MAX_BITS 29 -#define pte_to_pgoff(pte) (pte_val(pte)) -#define pgoff_to_pte(off) ((pte_t) { (off) | _PAGE_FILE }) - #endif /* !__ASSEMBLY__ */ #define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) diff --git a/arch/sparc/include/asm/cacheflush_64.h b/arch/sparc/include/asm/cacheflush_64.h index 38965379e35..68513c41e10 100644 --- a/arch/sparc/include/asm/cacheflush_64.h +++ b/arch/sparc/include/asm/cacheflush_64.h @@ -74,11 +74,6 @@ void flush_ptrace_access(struct vm_area_struct *, struct page *, #define flush_cache_vmap(start, end) do { } while (0) #define flush_cache_vunmap(start, end) do { } while (0) -#ifdef CONFIG_DEBUG_PAGEALLOC -/* internal debugging function */ -void kernel_map_pages(struct page *page, int numpages, int enable); -#endif - #endif /* !__ASSEMBLY__ */ #endif /* _SPARC64_CACHEFLUSH_H */ diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h index b9b91ae19fe..b2f7dc46a7d 100644 --- a/arch/sparc/include/asm/pgtable_32.h +++ b/arch/sparc/include/asm/pgtable_32.h @@ -221,14 +221,6 @@ static inline int pte_young(pte_t pte) return pte_val(pte) & SRMMU_REF; } -/* - * The following only work if pte_present() is not true. - */ -static inline int pte_file(pte_t pte) -{ - return pte_val(pte) & SRMMU_FILE; -} - static inline int pte_special(pte_t pte) { return 0; @@ -375,22 +367,6 @@ static inline swp_entry_t __swp_entry(unsigned long type, unsigned long offset) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -/* file-offset-in-pte helpers */ -static inline unsigned long pte_to_pgoff(pte_t pte) -{ - return pte_val(pte) >> SRMMU_PTE_FILE_SHIFT; -} - -static inline pte_t pgoff_to_pte(unsigned long pgoff) -{ - return __pte((pgoff << SRMMU_PTE_FILE_SHIFT) | SRMMU_FILE); -} - -/* - * This is made a constant because mm/fremap.c required a constant. - */ -#define PTE_FILE_MAX_BITS 24 - static inline unsigned long __get_phys (unsigned long addr) { diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 1ff9e786416..2ac7873ad6f 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -137,7 +137,6 @@ bool kern_addr_valid(unsigned long addr); #define _PAGE_SOFT_4U _AC(0x0000000000001F80,UL) /* Software bits: */ #define _PAGE_EXEC_4U _AC(0x0000000000001000,UL) /* Executable SW bit */ #define _PAGE_MODIFIED_4U _AC(0x0000000000000800,UL) /* Modified (dirty) */ -#define _PAGE_FILE_4U _AC(0x0000000000000800,UL) /* Pagecache page */ #define _PAGE_ACCESSED_4U _AC(0x0000000000000400,UL) /* Accessed (ref'd) */ #define _PAGE_READ_4U _AC(0x0000000000000200,UL) /* Readable SW Bit */ #define _PAGE_WRITE_4U _AC(0x0000000000000100,UL) /* Writable SW Bit */ @@ -167,7 +166,6 @@ bool kern_addr_valid(unsigned long addr); #define _PAGE_EXEC_4V _AC(0x0000000000000080,UL) /* Executable Page */ #define _PAGE_W_4V _AC(0x0000000000000040,UL) /* Writable */ #define _PAGE_SOFT_4V _AC(0x0000000000000030,UL) /* Software bits */ -#define _PAGE_FILE_4V _AC(0x0000000000000020,UL) /* Pagecache page */ #define _PAGE_PRESENT_4V _AC(0x0000000000000010,UL) /* Present */ #define _PAGE_RESV_4V _AC(0x0000000000000008,UL) /* Reserved */ #define _PAGE_SZ16GB_4V _AC(0x0000000000000007,UL) /* 16GB Page */ @@ -332,22 +330,6 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) } #endif -static inline pte_t pgoff_to_pte(unsigned long off) -{ - off <<= PAGE_SHIFT; - - __asm__ __volatile__( - "\n661: or %0, %2, %0\n" - " .section .sun4v_1insn_patch, \"ax\"\n" - " .word 661b\n" - " or %0, %3, %0\n" - " .previous\n" - : "=r" (off) - : "0" (off), "i" (_PAGE_FILE_4U), "i" (_PAGE_FILE_4V)); - - return __pte(off); -} - static inline pgprot_t pgprot_noncached(pgprot_t prot) { unsigned long val = pgprot_val(prot); @@ -609,22 +591,6 @@ static inline unsigned long pte_exec(pte_t pte) return (pte_val(pte) & mask); } -static inline unsigned long pte_file(pte_t pte) -{ - unsigned long val = pte_val(pte); - - __asm__ __volatile__( - "\n661: and %0, %2, %0\n" - " .section .sun4v_1insn_patch, \"ax\"\n" - " .word 661b\n" - " and %0, %3, %0\n" - " .previous\n" - : "=r" (val) - : "0" (val), "i" (_PAGE_FILE_4U), "i" (_PAGE_FILE_4V)); - - return val; -} - static inline unsigned long pte_present(pte_t pte) { unsigned long val = pte_val(pte); @@ -971,12 +937,6 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -/* File offset in PTE support. */ -unsigned long pte_file(pte_t); -#define pte_to_pgoff(pte) (pte_val(pte) >> PAGE_SHIFT) -pte_t pgoff_to_pte(unsigned long); -#define PTE_FILE_MAX_BITS (64UL - PAGE_SHIFT - 1UL) - int page_in_phys_avail(unsigned long paddr); /* diff --git a/arch/sparc/include/asm/pgtsrmmu.h b/arch/sparc/include/asm/pgtsrmmu.h index 79da17866fa..ae51a111a8c 100644 --- a/arch/sparc/include/asm/pgtsrmmu.h +++ b/arch/sparc/include/asm/pgtsrmmu.h @@ -80,10 +80,6 @@ #define SRMMU_PRIV 0x1c #define SRMMU_PRIV_RDONLY 0x18 -#define SRMMU_FILE 0x40 /* Implemented in software */ - -#define SRMMU_PTE_FILE_SHIFT 8 /* == 32-PTE_FILE_MAX_BITS */ - #define SRMMU_CHG_MASK (0xffffff00 | SRMMU_REF | SRMMU_DIRTY) /* SRMMU swap entry encoding @@ -94,13 +90,13 @@ * oooooooooooooooooootttttRRRRRRRR * fedcba9876543210fedcba9876543210 * - * The bottom 8 bits are reserved for protection and status bits, especially - * FILE and PRESENT. + * The bottom 7 bits are reserved for protection and status bits, especially + * PRESENT. */ #define SRMMU_SWP_TYPE_MASK 0x1f -#define SRMMU_SWP_TYPE_SHIFT SRMMU_PTE_FILE_SHIFT -#define SRMMU_SWP_OFF_MASK 0x7ffff -#define SRMMU_SWP_OFF_SHIFT (SRMMU_PTE_FILE_SHIFT + 5) +#define SRMMU_SWP_TYPE_SHIFT 7 +#define SRMMU_SWP_OFF_MASK 0xfffff +#define SRMMU_SWP_OFF_SHIFT (SRMMU_SWP_TYPE_SHIFT + 5) /* Some day I will implement true fine grained access bits for * user pages because the SRMMU gives us the capabilities to diff --git a/arch/tile/include/asm/pgtable.h b/arch/tile/include/asm/pgtable.h index 5d1950788c6..bc75b6ef2e7 100644 --- a/arch/tile/include/asm/pgtable.h +++ b/arch/tile/include/asm/pgtable.h @@ -285,17 +285,6 @@ extern void start_mm_caching(struct mm_struct *mm); extern void check_mm_caching(struct mm_struct *prev, struct mm_struct *next); /* - * Support non-linear file mappings (see sys_remap_file_pages). - * This is defined by CLIENT1 set but CLIENT0 and _PAGE_PRESENT clear, and the - * file offset in the 32 high bits. - */ -#define _PAGE_FILE HV_PTE_CLIENT1 -#define PTE_FILE_MAX_BITS 32 -#define pte_file(pte) (hv_pte_get_client1(pte) && !hv_pte_get_client0(pte)) -#define pte_to_pgoff(pte) ((pte).val >> 32) -#define pgoff_to_pte(off) ((pte_t) { (((long long)(off)) << 32) | _PAGE_FILE }) - -/* * Encode and de-code a swap entry (see <linux/swapops.h>). * We put the swap file type+offset in the 32 high bits; * I believe we can just leave the low bits clear. diff --git a/arch/tile/kernel/pci.c b/arch/tile/kernel/pci.c index f70c7892fa2..325df47f114 100644 --- a/arch/tile/kernel/pci.c +++ b/arch/tile/kernel/pci.c @@ -245,7 +245,7 @@ static void fixup_read_and_payload_sizes(void) { struct pci_dev *dev = NULL; int smallest_max_payload = 0x1; /* Tile maxes out at 256 bytes. */ - int max_read_size = 0x2; /* Limit to 512 byte reads. */ + int max_read_size = PCI_EXP_DEVCTL_READRQ_512B; u16 new_values; /* Scan for the smallest maximum payload size. */ @@ -258,7 +258,7 @@ static void fixup_read_and_payload_sizes(void) } /* Now, set the max_payload_size for all devices to that value. */ - new_values = (max_read_size << 12) | (smallest_max_payload << 5); + new_values = max_read_size | (smallest_max_payload << 5); for_each_pci_dev(dev) pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_PAYLOAD | PCI_EXP_DEVCTL_READRQ, diff --git a/arch/tile/kvm/Kconfig b/arch/tile/kvm/Kconfig index 2298cb1daff..1e968f7550d 100644 --- a/arch/tile/kvm/Kconfig +++ b/arch/tile/kvm/Kconfig @@ -21,6 +21,7 @@ config KVM depends on HAVE_KVM && MODULES select PREEMPT_NOTIFIERS select ANON_INODES + select SRCU ---help--- Support hosting paravirtualized guest machines. diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c index cd3387370eb..0029b3fb651 100644 --- a/arch/tile/mm/homecache.c +++ b/arch/tile/mm/homecache.c @@ -263,10 +263,6 @@ static int pte_to_home(pte_t pte) /* Update the home of a PTE if necessary (can also be used for a pgprot_t). */ pte_t pte_set_home(pte_t pte, int home) { - /* Check for non-linear file mapping "PTEs" and pass them through. */ - if (pte_file(pte)) - return pte; - #if CHIP_HAS_MMIO() /* Check for MMIO mappings and pass them through. */ if (hv_pte_get_mode(pte) == HV_PTE_MODE_MMIO) diff --git a/arch/um/include/asm/pgtable-2level.h b/arch/um/include/asm/pgtable-2level.h index f534b73e753..7afe86035fa 100644 --- a/arch/um/include/asm/pgtable-2level.h +++ b/arch/um/include/asm/pgtable-2level.h @@ -41,13 +41,4 @@ static inline void pgd_mkuptodate(pgd_t pgd) { } #define pfn_pte(pfn, prot) __pte(pfn_to_phys(pfn) | pgprot_val(prot)) #define pfn_pmd(pfn, prot) __pmd(pfn_to_phys(pfn) | pgprot_val(prot)) -/* - * Bits 0 through 4 are taken - */ -#define PTE_FILE_MAX_BITS 27 - -#define pte_to_pgoff(pte) (pte_val(pte) >> 5) - -#define pgoff_to_pte(off) ((pte_t) { ((off) << 5) + _PAGE_FILE }) - #endif diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-3level.h index 0032f9212e7..344c559c0a1 100644 --- a/arch/um/include/asm/pgtable-3level.h +++ b/arch/um/include/asm/pgtable-3level.h @@ -112,25 +112,5 @@ static inline pmd_t pfn_pmd(pfn_t page_nr, pgprot_t pgprot) return __pmd((page_nr << PAGE_SHIFT) | pgprot_val(pgprot)); } -/* - * Bits 0 through 3 are taken in the low part of the pte, - * put the 32 bits of offset into the high part. - */ -#define PTE_FILE_MAX_BITS 32 - -#ifdef CONFIG_64BIT - -#define pte_to_pgoff(p) ((p).pte >> 32) - -#define pgoff_to_pte(off) ((pte_t) { ((off) << 32) | _PAGE_FILE }) - -#else - -#define pte_to_pgoff(pte) ((pte).pte_high) - -#define pgoff_to_pte(off) ((pte_t) { _PAGE_FILE, (off) }) - -#endif - #endif diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index bf974f712af..2324b624f19 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -18,7 +18,6 @@ #define _PAGE_ACCESSED 0x080 #define _PAGE_DIRTY 0x100 /* If _PAGE_PRESENT is clear, we use these: */ -#define _PAGE_FILE 0x008 /* nonlinear file mapping, saved PTE; unset:swap */ #define _PAGE_PROTNONE 0x010 /* if the user mapped it with PROT_NONE; pte_present gives true */ @@ -151,14 +150,6 @@ static inline int pte_write(pte_t pte) !(pte_get_bits(pte, _PAGE_PROTNONE))); } -/* - * The following only works if pte_present() is not true. - */ -static inline int pte_file(pte_t pte) -{ - return pte_get_bits(pte, _PAGE_FILE); -} - static inline int pte_dirty(pte_t pte) { return pte_get_bits(pte, _PAGE_DIRTY); diff --git a/arch/unicore32/include/asm/pgtable-hwdef.h b/arch/unicore32/include/asm/pgtable-hwdef.h index 7314e859cca..e37fa471c2b 100644 --- a/arch/unicore32/include/asm/pgtable-hwdef.h +++ b/arch/unicore32/include/asm/pgtable-hwdef.h @@ -44,7 +44,6 @@ #define PTE_TYPE_INVALID (3 << 0) #define PTE_PRESENT (1 << 2) -#define PTE_FILE (1 << 3) /* only when !PRESENT */ #define PTE_YOUNG (1 << 3) #define PTE_DIRTY (1 << 4) #define PTE_CACHEABLE (1 << 5) diff --git a/arch/unicore32/include/asm/pgtable.h b/arch/unicore32/include/asm/pgtable.h index ed6f7d000fb..818d0f5598e 100644 --- a/arch/unicore32/include/asm/pgtable.h +++ b/arch/unicore32/include/asm/pgtable.h @@ -283,20 +283,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; #define MAX_SWAPFILES_CHECK() \ BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS) -/* - * Encode and decode a file entry. File entries are stored in the Linux - * page tables as follows: - * - * 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 - * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 - * <----------------------- offset ----------------------> 1 0 0 0 - */ -#define pte_file(pte) (pte_val(pte) & PTE_FILE) -#define pte_to_pgoff(x) (pte_val(x) >> 4) -#define pgoff_to_pte(x) __pte(((x) << 4) | PTE_FILE) - -#define PTE_FILE_MAX_BITS 28 - /* Needs to be defined here and not in linux/mm.h, as it is arch dependent */ /* FIXME: this is not correct */ #define kern_addr_valid(addr) (1) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0dc9d0144a2..33ce9a344e3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -17,6 +17,7 @@ config X86_64 depends on 64BIT select X86_DEV_DMA_OPS select ARCH_USE_CMPXCHG_LOCKREF + select HAVE_LIVEPATCH ### Arch settings config X86 @@ -138,6 +139,7 @@ config X86 select HAVE_ACPI_APEI_NMI if ACPI select ACPI_LEGACY_TABLES_LOOKUP if ACPI select X86_FEATURE_NAMES if PROC_FS + select SRCU config INSTRUCTION_DECODER def_bool y @@ -496,6 +498,17 @@ config X86_INTEL_LPSS things like clock tree (common clock framework) and pincontrol which are needed by the LPSS peripheral drivers. +config X86_AMD_PLATFORM_DEVICE + bool "AMD ACPI2Platform devices support" + depends on ACPI + select COMMON_CLK + select PINCTRL + ---help--- + Select to interpret AMD specific ACPI device to platform device + such as I2C, UART, GPIO found on AMD Carrizo and later chipsets. + I2C and UART depend on COMMON_CLK to set clock. GPIO driver is + implemented under PINCTRL subsystem. + config IOSF_MBI tristate "Intel SoC IOSF Sideband support for SoC platforms" depends on PCI @@ -855,6 +868,10 @@ config SCHED_MC source "kernel/Kconfig.preempt" +config UP_LATE_INIT + def_bool y + depends on !SMP && X86_LOCAL_APIC + config X86_UP_APIC bool "Local APIC support on uniprocessors" depends on X86_32 && !SMP && !X86_32_NON_STANDARD @@ -2012,6 +2029,8 @@ config CMDLINE_OVERRIDE This is used to work around broken boot loaders. This should be set to 'N' under normal conditions. +source "kernel/livepatch/Kconfig" + endmenu config ARCH_ENABLE_MEMORY_HOTPLUG diff --git a/arch/x86/boot/ctype.h b/arch/x86/boot/ctype.h index 25e13403193..020f137df7a 100644 --- a/arch/x86/boot/ctype.h +++ b/arch/x86/boot/ctype.h @@ -1,6 +1,5 @@ -#ifndef BOOT_ISDIGIT_H - -#define BOOT_ISDIGIT_H +#ifndef BOOT_CTYPE_H +#define BOOT_CTYPE_H static inline int isdigit(int ch) { diff --git a/arch/x86/boot/early_serial_console.c b/arch/x86/boot/early_serial_console.c index 5df2869c874..45a07684bba 100644 --- a/arch/x86/boot/early_serial_console.c +++ b/arch/x86/boot/early_serial_console.c @@ -2,8 +2,6 @@ #define DEFAULT_SERIAL_PORT 0x3f8 /* ttyS0 */ -#define XMTRDY 0x20 - #define DLAB 0x80 #define TXR 0 /* Transmit register (WRITE) */ @@ -74,8 +72,8 @@ static void parse_earlyprintk(void) static const int bases[] = { 0x3f8, 0x2f8 }; int idx = 0; - if (!strncmp(arg + pos, "ttyS", 4)) - pos += 4; + /* += strlen("ttyS"); */ + pos += 4; if (arg[pos++] == '1') idx = 1; diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 82e8a1d4465..156ebcab4ad 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -179,8 +179,8 @@ sysenter_dispatch: sysexit_from_sys_call: andl $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) /* clear IF, that popfq doesn't enable interrupts early */ - andl $~0x200,EFLAGS-R11(%rsp) - movl RIP-R11(%rsp),%edx /* User %eip */ + andl $~0x200,EFLAGS-ARGOFFSET(%rsp) + movl RIP-ARGOFFSET(%rsp),%edx /* User %eip */ CFI_REGISTER rip,rdx RESTORE_ARGS 0,24,0,0,0,0 xorq %r8,%r8 diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 465b309af25..92003f3c8a4 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -106,7 +106,14 @@ extern u32 native_safe_apic_wait_icr_idle(void); extern void native_apic_icr_write(u32 low, u32 id); extern u64 native_apic_icr_read(void); -extern int x2apic_mode; +static inline bool apic_is_x2apic_enabled(void) +{ + u64 msr; + + if (rdmsrl_safe(MSR_IA32_APICBASE, &msr)) + return false; + return msr & X2APIC_ENABLE; +} #ifdef CONFIG_X86_X2APIC /* @@ -169,48 +176,23 @@ static inline u64 native_x2apic_icr_read(void) return val; } +extern int x2apic_mode; extern int x2apic_phys; -extern int x2apic_preenabled; -extern void check_x2apic(void); -extern void enable_x2apic(void); +extern void __init check_x2apic(void); +extern void x2apic_setup(void); static inline int x2apic_enabled(void) { - u64 msr; - - if (!cpu_has_x2apic) - return 0; - - rdmsrl(MSR_IA32_APICBASE, msr); - if (msr & X2APIC_ENABLE) - return 1; - return 0; + return cpu_has_x2apic && apic_is_x2apic_enabled(); } #define x2apic_supported() (cpu_has_x2apic) -static inline void x2apic_force_phys(void) -{ - x2apic_phys = 1; -} #else -static inline void disable_x2apic(void) -{ -} -static inline void check_x2apic(void) -{ -} -static inline void enable_x2apic(void) -{ -} -static inline int x2apic_enabled(void) -{ - return 0; -} -static inline void x2apic_force_phys(void) -{ -} +static inline void check_x2apic(void) { } +static inline void x2apic_setup(void) { } +static inline int x2apic_enabled(void) { return 0; } -#define x2apic_preenabled 0 -#define x2apic_supported() 0 +#define x2apic_mode (0) +#define x2apic_supported() (0) #endif extern void enable_IR_x2apic(void); @@ -219,7 +201,6 @@ extern int get_physical_broadcast(void); extern int lapic_get_maxlvt(void); extern void clear_local_APIC(void); -extern void connect_bsp_APIC(void); extern void disconnect_bsp_APIC(int virt_wire_setup); extern void disable_local_APIC(void); extern void lapic_shutdown(void); @@ -227,8 +208,6 @@ extern int verify_local_APIC(void); extern void sync_Arb_IDs(void); extern void init_bsp_APIC(void); extern void setup_local_APIC(void); -extern void end_local_APIC_setup(void); -extern void bsp_end_local_APIC_setup(void); extern void init_apic_mappings(void); void register_lapic_address(unsigned long address); extern void setup_boot_APIC_clock(void); @@ -236,6 +215,9 @@ extern void setup_secondary_APIC_clock(void); extern int APIC_init_uniprocessor(void); extern int apic_force_enable(unsigned long addr); +extern int apic_bsp_setup(bool upmode); +extern void apic_ap_setup(void); + /* * On 32bit this is mach-xxx local */ diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h index 76659b67fd1..1f1297b46f8 100644 --- a/arch/x86/include/asm/calling.h +++ b/arch/x86/include/asm/calling.h @@ -83,7 +83,6 @@ For 32-bit we have the following conventions - kernel is built with #define SS 160 #define ARGOFFSET R11 -#define SWFRAME ORIG_RAX .macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1, rax_enosys=0 subq $9*8+\addskip, %rsp diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index aede2c347bd..90a54851aed 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -174,6 +174,7 @@ #define X86_FEATURE_TOPOEXT ( 6*32+22) /* topology extensions CPUID leafs */ #define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */ #define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ +#define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ #define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */ /* @@ -388,6 +389,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; #define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16) #define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU) #define cpu_has_topoext boot_cpu_has(X86_FEATURE_TOPOEXT) +#define cpu_has_bpext boot_cpu_has(X86_FEATURE_BPEXT) #if __GNUC__ >= 4 extern void warn_pre_alternatives(void); diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 61fd18b83b6..12cb66f6d3a 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -114,5 +114,10 @@ static inline void debug_stack_usage_inc(void) { } static inline void debug_stack_usage_dec(void) { } #endif /* X86_64 */ +#ifdef CONFIG_CPU_SUP_AMD +extern void set_dr_addr_mask(unsigned long mask, int dr); +#else +static inline void set_dr_addr_mask(unsigned long mask, int dr) { } +#endif #endif /* _ASM_X86_DEBUGREG_H */ diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index e97622f5772..0dbc0828229 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -207,7 +207,7 @@ static inline void fpu_fxsave(struct fpu *fpu) if (config_enabled(CONFIG_X86_32)) asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave)); else if (config_enabled(CONFIG_AS_FXSAVEQ)) - asm volatile("fxsaveq %0" : "=m" (fpu->state->fxsave)); + asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state->fxsave)); else { /* Using "rex64; fxsave %0" is broken because, if the memory * operand uses any extended registers for addressing, a second @@ -290,9 +290,11 @@ static inline int fpu_restore_checking(struct fpu *fpu) static inline int restore_fpu_checking(struct task_struct *tsk) { - /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception - is pending. Clear the x87 state here by setting it to fixed - values. "m" is a random variable that should be in L1 */ + /* + * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is + * pending. Clear the x87 state here by setting it to fixed values. + * "m" is a random variable that should be in L1. + */ if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) { asm volatile( "fnclex\n\t" diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index ef1c4d2d41e..6c98be864a7 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -12,6 +12,7 @@ */ struct arch_hw_breakpoint { unsigned long address; + unsigned long mask; u8 len; u8 type; }; diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index ed8089d6909..6eb6fcb83f6 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -40,8 +40,8 @@ extern void __kernel_fpu_end(void); static inline void kernel_fpu_begin(void) { - WARN_ON_ONCE(!irq_fpu_usable()); preempt_disable(); + WARN_ON_ONCE(!irq_fpu_usable()); __kernel_fpu_begin(); } @@ -51,6 +51,10 @@ static inline void kernel_fpu_end(void) preempt_enable(); } +/* Must be called with preempt disabled */ +extern void kernel_fpu_disable(void); +extern void kernel_fpu_enable(void); + /* * Some instructions like VIA's padlock instructions generate a spurious * DNA fault but don't modify SSE registers. And these instructions diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index bf006cce941..2f91685fe1c 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -279,6 +279,11 @@ static inline void disable_ioapic_support(void) { } #define native_ioapic_set_affinity NULL #define native_setup_ioapic_entry NULL #define native_eoi_ioapic_pin NULL + +static inline void setup_IO_APIC(void) { } +static inline void enable_IO_APIC(void) { } +static inline void setup_ioapic_dest(void) { } + #endif #endif /* _ASM_X86_IO_APIC_H */ diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index b7747c4c2cf..6224d316c40 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -33,8 +33,6 @@ struct irq_cfg; #ifdef CONFIG_IRQ_REMAP -extern void setup_irq_remapping_ops(void); -extern int irq_remapping_supported(void); extern void set_irq_remapping_broken(void); extern int irq_remapping_prepare(void); extern int irq_remapping_enable(void); @@ -60,8 +58,6 @@ void irq_remap_modify_chip_defaults(struct irq_chip *chip); #else /* CONFIG_IRQ_REMAP */ -static inline void setup_irq_remapping_ops(void) { } -static inline int irq_remapping_supported(void) { return 0; } static inline void set_irq_remapping_broken(void) { } static inline int irq_remapping_prepare(void) { return -ENODEV; } static inline int irq_remapping_enable(void) { return -ENODEV; } diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h new file mode 100644 index 00000000000..a455a53d789 --- /dev/null +++ b/arch/x86/include/asm/livepatch.h @@ -0,0 +1,46 @@ +/* + * livepatch.h - x86-specific Kernel Live Patching Core + * + * Copyright (C) 2014 Seth Jennings <sjenning@redhat.com> + * Copyright (C) 2014 SUSE + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _ASM_X86_LIVEPATCH_H +#define _ASM_X86_LIVEPATCH_H + +#include <linux/module.h> +#include <linux/ftrace.h> + +#ifdef CONFIG_LIVEPATCH +static inline int klp_check_compiler_support(void) +{ +#ifndef CC_USING_FENTRY + return 1; +#endif + return 0; +} +extern int klp_write_module_reloc(struct module *mod, unsigned long type, + unsigned long loc, unsigned long value); + +static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip) +{ + regs->ip = ip; +} +#else +#error Live patching support is disabled; check CONFIG_LIVEPATCH +#endif + +#endif /* _ASM_X86_LIVEPATCH_H */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 51b26e89593..9b3de99dc00 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -190,7 +190,6 @@ enum mcp_flags { void machine_check_poll(enum mcp_flags flags, mce_banks_t *b); int mce_notify_irq(void); -void mce_notify_process(void); DECLARE_PER_CPU(struct mce, injectm); diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 164e3f8d3c3..fa1195dae42 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -93,8 +93,6 @@ extern raw_spinlock_t pci_config_lock; extern int (*pcibios_enable_irq)(struct pci_dev *dev); extern void (*pcibios_disable_irq)(struct pci_dev *dev); -extern bool mp_should_keep_irq(struct device *dev); - struct pci_raw_ops { int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val); diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 206a87fdd22..fd74a11959d 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -62,44 +62,8 @@ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshi return ((value >> rightshift) & mask) << leftshift; } -/* - * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken, - * split up the 29 bits of offset into this range. - */ -#define PTE_FILE_MAX_BITS 29 -#define PTE_FILE_SHIFT1 (_PAGE_BIT_PRESENT + 1) -#define PTE_FILE_SHIFT2 (_PAGE_BIT_FILE + 1) -#define PTE_FILE_SHIFT3 (_PAGE_BIT_PROTNONE + 1) -#define PTE_FILE_BITS1 (PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1) -#define PTE_FILE_BITS2 (PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1) - -#define PTE_FILE_MASK1 ((1U << PTE_FILE_BITS1) - 1) -#define PTE_FILE_MASK2 ((1U << PTE_FILE_BITS2) - 1) - -#define PTE_FILE_LSHIFT2 (PTE_FILE_BITS1) -#define PTE_FILE_LSHIFT3 (PTE_FILE_BITS1 + PTE_FILE_BITS2) - -static __always_inline pgoff_t pte_to_pgoff(pte_t pte) -{ - return (pgoff_t) - (pte_bitop(pte.pte_low, PTE_FILE_SHIFT1, PTE_FILE_MASK1, 0) + - pte_bitop(pte.pte_low, PTE_FILE_SHIFT2, PTE_FILE_MASK2, PTE_FILE_LSHIFT2) + - pte_bitop(pte.pte_low, PTE_FILE_SHIFT3, -1UL, PTE_FILE_LSHIFT3)); -} - -static __always_inline pte_t pgoff_to_pte(pgoff_t off) -{ - return (pte_t){ - .pte_low = - pte_bitop(off, 0, PTE_FILE_MASK1, PTE_FILE_SHIFT1) + - pte_bitop(off, PTE_FILE_LSHIFT2, PTE_FILE_MASK2, PTE_FILE_SHIFT2) + - pte_bitop(off, PTE_FILE_LSHIFT3, -1UL, PTE_FILE_SHIFT3) + - _PAGE_FILE, - }; -} - /* Encode and de-code a swap entry */ -#define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1) +#define SWP_TYPE_BITS 5 #define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1) #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index 81bb91b49a8..cdaa58c9b39 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -176,18 +176,6 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp) #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp) #endif -/* - * Bits 0, 6 and 7 are taken in the low part of the pte, - * put the 32 bits of offset into the high part. - * - * For soft-dirty tracking 11 bit is taken from - * the low part of pte as well. - */ -#define pte_to_pgoff(pte) ((pte).pte_high) -#define pgoff_to_pte(off) \ - ((pte_t) { { .pte_low = _PAGE_FILE, .pte_high = (off) } }) -#define PTE_FILE_MAX_BITS 32 - /* Encode and de-code a swap entry */ #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5) #define __swp_type(x) (((x).val) & 0x1f) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index e8a5454acc9..0fe03f834fb 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -115,11 +115,6 @@ static inline int pte_write(pte_t pte) return pte_flags(pte) & _PAGE_RW; } -static inline int pte_file(pte_t pte) -{ - return pte_flags(pte) & _PAGE_FILE; -} - static inline int pte_huge(pte_t pte) { return pte_flags(pte) & _PAGE_PSE; @@ -329,21 +324,6 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); } -static inline pte_t pte_file_clear_soft_dirty(pte_t pte) -{ - return pte_clear_flags(pte, _PAGE_SOFT_DIRTY); -} - -static inline pte_t pte_file_mksoft_dirty(pte_t pte) -{ - return pte_set_flags(pte, _PAGE_SOFT_DIRTY); -} - -static inline int pte_file_soft_dirty(pte_t pte) -{ - return pte_flags(pte) & _PAGE_SOFT_DIRTY; -} - #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ /* diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 4572b2f3023..e227970f983 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -133,10 +133,6 @@ static inline int pgd_large(pgd_t pgd) { return 0; } /* PUD - Level3 access */ /* PMD - Level 2 access */ -#define pte_to_pgoff(pte) ((pte_val((pte)) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT) -#define pgoff_to_pte(off) ((pte_t) { .pte = ((off) << PAGE_SHIFT) | \ - _PAGE_FILE }) -#define PTE_FILE_MAX_BITS __PHYSICAL_MASK_SHIFT /* PTE - Level 1 access. */ @@ -145,7 +141,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; } #define pte_unmap(pte) ((void)(pte))/* NOP */ /* Encode and de-code a swap entry */ -#define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1) +#define SWP_TYPE_BITS 5 #ifdef CONFIG_NUMA_BALANCING /* Automatic NUMA balancing needs to be distinguishable from swap entries */ #define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 2) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 25bcd4a8951..5185a4f599e 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -38,8 +38,6 @@ /* If _PAGE_BIT_PRESENT is clear, we use these: */ /* - if the user mapped it with PROT_NONE; pte_present gives true */ #define _PAGE_BIT_PROTNONE _PAGE_BIT_GLOBAL -/* - set: nonlinear file mapping, saved PTE; unset:swap */ -#define _PAGE_BIT_FILE _PAGE_BIT_DIRTY #define _PAGE_PRESENT (_AT(pteval_t, 1) << _PAGE_BIT_PRESENT) #define _PAGE_RW (_AT(pteval_t, 1) << _PAGE_BIT_RW) @@ -114,7 +112,6 @@ #define _PAGE_NX (_AT(pteval_t, 0)) #endif -#define _PAGE_FILE (_AT(pteval_t, 1) << _PAGE_BIT_FILE) #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ diff --git a/arch/x86/include/asm/pmc_atom.h b/arch/x86/include/asm/pmc_atom.h index fc7a17c05d3..bc0fc086655 100644 --- a/arch/x86/include/asm/pmc_atom.h +++ b/arch/x86/include/asm/pmc_atom.h @@ -53,6 +53,28 @@ /* Sleep state counter is in units of of 32us */ #define PMC_TMR_SHIFT 5 +/* Power status of power islands */ +#define PMC_PSS 0x98 + +#define PMC_PSS_BIT_GBE BIT(0) +#define PMC_PSS_BIT_SATA BIT(1) +#define PMC_PSS_BIT_HDA BIT(2) +#define PMC_PSS_BIT_SEC BIT(3) +#define PMC_PSS_BIT_PCIE BIT(4) +#define PMC_PSS_BIT_LPSS BIT(5) +#define PMC_PSS_BIT_LPE BIT(6) +#define PMC_PSS_BIT_DFX BIT(7) +#define PMC_PSS_BIT_USH_CTRL BIT(8) +#define PMC_PSS_BIT_USH_SUS BIT(9) +#define PMC_PSS_BIT_USH_VCCS BIT(10) +#define PMC_PSS_BIT_USH_VCCA BIT(11) +#define PMC_PSS_BIT_OTG_CTRL BIT(12) +#define PMC_PSS_BIT_OTG_VCCS BIT(13) +#define PMC_PSS_BIT_OTG_VCCA_CLK BIT(14) +#define PMC_PSS_BIT_OTG_VCCA BIT(15) +#define PMC_PSS_BIT_USB BIT(16) +#define PMC_PSS_BIT_USB_SUS BIT(17) + /* These registers reflect D3 status of functions */ #define PMC_D3_STS_0 0xA0 diff --git a/arch/x86/include/asm/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h deleted file mode 100644 index 0da7409f0be..00000000000 --- a/arch/x86/include/asm/smpboot_hooks.h +++ /dev/null @@ -1,68 +0,0 @@ -/* two abstractions specific to kernel/smpboot.c, mainly to cater to visws - * which needs to alter them. */ - -static inline void smpboot_clear_io_apic_irqs(void) -{ -#ifdef CONFIG_X86_IO_APIC - io_apic_irqs = 0; -#endif -} - -static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) -{ - unsigned long flags; - - spin_lock_irqsave(&rtc_lock, flags); - CMOS_WRITE(0xa, 0xf); - spin_unlock_irqrestore(&rtc_lock, flags); - local_flush_tlb(); - pr_debug("1.\n"); - *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = - start_eip >> 4; - pr_debug("2.\n"); - *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = - start_eip & 0xf; - pr_debug("3.\n"); -} - -static inline void smpboot_restore_warm_reset_vector(void) -{ - unsigned long flags; - - /* - * Install writable page 0 entry to set BIOS data area. - */ - local_flush_tlb(); - - /* - * Paranoid: Set warm reset code and vector here back - * to default values. - */ - spin_lock_irqsave(&rtc_lock, flags); - CMOS_WRITE(0, 0xf); - spin_unlock_irqrestore(&rtc_lock, flags); - - *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0; -} - -static inline void __init smpboot_setup_io_apic(void) -{ -#ifdef CONFIG_X86_IO_APIC - /* - * Here we can be sure that there is an IO-APIC in the system. Let's - * go and set it up: - */ - if (!skip_ioapic_setup && nr_ioapics) - setup_IO_APIC(); - else { - nr_ioapics = 0; - } -#endif -} - -static inline void smpboot_clear_io_apic(void) -{ -#ifdef CONFIG_X86_IO_APIC - nr_ioapics = 0; -#endif -} diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 547e344a6dc..e82e95abc92 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -75,7 +75,6 @@ struct thread_info { #define TIF_SYSCALL_EMU 6 /* syscall emulation active */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SECCOMP 8 /* secure computing */ -#define TIF_MCE_NOTIFY 10 /* notify userspace of an MCE */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_UPROBE 12 /* breakpointed or singlestepping */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ @@ -100,7 +99,6 @@ struct thread_info { #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) -#define _TIF_MCE_NOTIFY (1 << TIF_MCE_NOTIFY) #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_NOTSC (1 << TIF_NOTSC) @@ -140,7 +138,7 @@ struct thread_info { /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ - (_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME | \ + (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | \ _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE) /* flags to check in __switch_to() */ @@ -170,6 +168,17 @@ static inline struct thread_info *current_thread_info(void) return ti; } +static inline unsigned long current_stack_pointer(void) +{ + unsigned long sp; +#ifdef CONFIG_X86_64 + asm("mov %%rsp,%0" : "=g" (sp)); +#else + asm("mov %%esp,%0" : "=g" (sp)); +#endif + return sp; +} + #else /* !__ASSEMBLY__ */ /* how to get the thread information struct from ASM */ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 707adc6549d..4e49d7dff78 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_TRAPS_H #define _ASM_X86_TRAPS_H +#include <linux/context_tracking_state.h> #include <linux/kprobes.h> #include <asm/debugreg.h> @@ -110,6 +111,11 @@ asmlinkage void smp_thermal_interrupt(void); asmlinkage void mce_threshold_interrupt(void); #endif +extern enum ctx_state ist_enter(struct pt_regs *regs); +extern void ist_exit(struct pt_regs *regs, enum ctx_state prev_state); +extern void ist_begin_non_atomic(struct pt_regs *regs); +extern void ist_end_non_atomic(void); + /* Interrupts/Exceptions */ enum { X86_TRAP_DE = 0, /* 0, Divide-by-zero */ diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 5eea09915a1..358dcd33891 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -55,9 +55,8 @@ extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, struct gnttab_map_grant_ref *kmap_ops, struct page **pages, unsigned int count); extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, - struct gnttab_map_grant_ref *kmap_ops, + struct gnttab_unmap_grant_ref *kunmap_ops, struct page **pages, unsigned int count); -extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn); /* * Helper functions to write or read unsigned long values to/from @@ -154,21 +153,12 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn) return mfn; pfn = mfn_to_pfn_no_overrides(mfn); - if (__pfn_to_mfn(pfn) != mfn) { - /* - * If this appears to be a foreign mfn (because the pfn - * doesn't map back to the mfn), then check the local override - * table to see if there's a better pfn to use. - * - * m2p_find_override_pfn returns ~0 if it doesn't find anything. - */ - pfn = m2p_find_override_pfn(mfn, ~0); - } + if (__pfn_to_mfn(pfn) != mfn) + pfn = ~0; /* - * pfn is ~0 if there are no entries in the m2p for mfn or if the - * entry doesn't map back to the mfn and m2p_override doesn't have a - * valid entry for it. + * pfn is ~0 if there are no entries in the m2p for mfn or the + * entry doesn't map back to the mfn. */ if (pfn == ~0 && __pfn_to_mfn(mfn) == IDENTITY_FRAME(mfn)) pfn = mfn; diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index c8aa65d5602..536240fa9a9 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -152,6 +152,10 @@ #define MSR_CC6_DEMOTION_POLICY_CONFIG 0x00000668 #define MSR_MC6_DEMOTION_POLICY_CONFIG 0x00000669 +#define MSR_CORE_PERF_LIMIT_REASONS 0x00000690 +#define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0 +#define MSR_RING_PERF_LIMIT_REASONS 0x000006B1 + /* Hardware P state interface */ #define MSR_PPERF 0x0000064e #define MSR_PERF_LIMIT_REASONS 0x0000064f @@ -251,6 +255,10 @@ /* Fam 16h MSRs */ #define MSR_F16H_L2I_PERF_CTL 0xc0010230 #define MSR_F16H_L2I_PERF_CTR 0xc0010231 +#define MSR_F16H_DR1_ADDR_MASK 0xc0011019 +#define MSR_F16H_DR2_ADDR_MASK 0xc001101a +#define MSR_F16H_DR3_ADDR_MASK 0xc001101b +#define MSR_F16H_DR0_ADDR_MASK 0xc0011027 /* Fam 15h MSRs */ #define MSR_F15H_PERF_CTL 0xc0010200 @@ -358,6 +366,7 @@ #define MSR_IA32_PERF_STATUS 0x00000198 #define MSR_IA32_PERF_CTL 0x00000199 +#define INTEL_PERF_CTL_MASK 0xffff #define MSR_AMD_PSTATE_DEF_BASE 0xc0010064 #define MSR_AMD_PERF_STATUS 0xc0010063 #define MSR_AMD_PERF_CTL 0xc0010062 diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 5d4502c8b98..73222349696 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -63,6 +63,7 @@ obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-y += apic/ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o +obj-$(CONFIG_LIVEPATCH) += livepatch.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_X86_TSC) += trace_clock.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index b9e30daa088..ae97ed0873c 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -653,6 +653,7 @@ static int acpi_register_gsi_pic(struct device *dev, u32 gsi, return gsi; } +#ifdef CONFIG_X86_LOCAL_APIC static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi, int trigger, int polarity) { @@ -675,6 +676,7 @@ static void acpi_unregister_gsi_ioapic(u32 gsi) mutex_unlock(&acpi_ioapic_lock); #endif } +#endif int (*__acpi_register_gsi)(struct device *dev, u32 gsi, int trigger, int polarity) = acpi_register_gsi_pic; @@ -843,13 +845,7 @@ int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base) static int __init acpi_parse_sbf(struct acpi_table_header *table) { - struct acpi_table_boot *sb; - - sb = (struct acpi_table_boot *)table; - if (!sb) { - printk(KERN_WARNING PREFIX "Unable to map SBF\n"); - return -ENODEV; - } + struct acpi_table_boot *sb = (struct acpi_table_boot *)table; sbf_port = sb->cmos_index; /* Save CMOS port */ @@ -863,13 +859,7 @@ static struct resource *hpet_res __initdata; static int __init acpi_parse_hpet(struct acpi_table_header *table) { - struct acpi_table_hpet *hpet_tbl; - - hpet_tbl = (struct acpi_table_hpet *)table; - if (!hpet_tbl) { - printk(KERN_WARNING PREFIX "Unable to map HPET\n"); - return -ENODEV; - } + struct acpi_table_hpet *hpet_tbl = (struct acpi_table_hpet *)table; if (hpet_tbl->address.space_id != ACPI_SPACE_MEM) { printk(KERN_WARNING PREFIX "HPET timers must be located in " diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index b708738d016..6a7c23ff21d 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -135,14 +135,6 @@ static inline void apbt_clear_mapping(void) apbt_virt_address = NULL; } -/* - * APBT timer interrupt enable / disable - */ -static inline int is_apbt_capable(void) -{ - return apbt_virt_address ? 1 : 0; -} - static int __init apbt_clockevent_register(void) { struct sfi_timer_table_entry *mtmr; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 29b5b18afa2..b665d241efa 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -134,9 +134,6 @@ static inline void imcr_apic_to_pic(void) */ static int force_enable_local_apic __initdata; -/* Control whether x2APIC mode is enabled or not */ -static bool nox2apic __initdata; - /* * APIC command line parameters */ @@ -161,33 +158,6 @@ static __init int setup_apicpmtimer(char *s) __setup("apicpmtimer", setup_apicpmtimer); #endif -int x2apic_mode; -#ifdef CONFIG_X86_X2APIC -/* x2apic enabled before OS handover */ -int x2apic_preenabled; -static int x2apic_disabled; -static int __init setup_nox2apic(char *str) -{ - if (x2apic_enabled()) { - int apicid = native_apic_msr_read(APIC_ID); - - if (apicid >= 255) { - pr_warning("Apicid: %08x, cannot enforce nox2apic\n", - apicid); - return 0; - } - - pr_warning("x2apic already enabled. will disable it\n"); - } else - setup_clear_cpu_cap(X86_FEATURE_X2APIC); - - nox2apic = true; - - return 0; -} -early_param("nox2apic", setup_nox2apic); -#endif - unsigned long mp_lapic_addr; int disable_apic; /* Disable local APIC timer from the kernel commandline or via dmi quirk */ @@ -1475,7 +1445,7 @@ void setup_local_APIC(void) #endif } -void end_local_APIC_setup(void) +static void end_local_APIC_setup(void) { lapic_setup_esr(); @@ -1492,116 +1462,184 @@ void end_local_APIC_setup(void) apic_pm_activate(); } -void __init bsp_end_local_APIC_setup(void) +/* + * APIC setup function for application processors. Called from smpboot.c + */ +void apic_ap_setup(void) { + setup_local_APIC(); end_local_APIC_setup(); - - /* - * Now that local APIC setup is completed for BP, configure the fault - * handling for interrupt remapping. - */ - irq_remap_enable_fault_handling(); - } #ifdef CONFIG_X86_X2APIC -/* - * Need to disable xapic and x2apic at the same time and then enable xapic mode - */ -static inline void __disable_x2apic(u64 msr) -{ - wrmsrl(MSR_IA32_APICBASE, - msr & ~(X2APIC_ENABLE | XAPIC_ENABLE)); - wrmsrl(MSR_IA32_APICBASE, msr & ~X2APIC_ENABLE); -} +int x2apic_mode; -static __init void disable_x2apic(void) +enum { + X2APIC_OFF, + X2APIC_ON, + X2APIC_DISABLED, +}; +static int x2apic_state; + +static inline void __x2apic_disable(void) { u64 msr; - if (!cpu_has_x2apic) + if (cpu_has_apic) return; rdmsrl(MSR_IA32_APICBASE, msr); - if (msr & X2APIC_ENABLE) { - u32 x2apic_id = read_apic_id(); - - if (x2apic_id >= 255) - panic("Cannot disable x2apic, id: %08x\n", x2apic_id); + if (!(msr & X2APIC_ENABLE)) + return; + /* Disable xapic and x2apic first and then reenable xapic mode */ + wrmsrl(MSR_IA32_APICBASE, msr & ~(X2APIC_ENABLE | XAPIC_ENABLE)); + wrmsrl(MSR_IA32_APICBASE, msr & ~X2APIC_ENABLE); + printk_once(KERN_INFO "x2apic disabled\n"); +} - pr_info("Disabling x2apic\n"); - __disable_x2apic(msr); +static inline void __x2apic_enable(void) +{ + u64 msr; - if (nox2apic) { - clear_cpu_cap(&cpu_data(0), X86_FEATURE_X2APIC); - setup_clear_cpu_cap(X86_FEATURE_X2APIC); - } + rdmsrl(MSR_IA32_APICBASE, msr); + if (msr & X2APIC_ENABLE) + return; + wrmsrl(MSR_IA32_APICBASE, msr | X2APIC_ENABLE); + printk_once(KERN_INFO "x2apic enabled\n"); +} - x2apic_disabled = 1; - x2apic_mode = 0; +static int __init setup_nox2apic(char *str) +{ + if (x2apic_enabled()) { + int apicid = native_apic_msr_read(APIC_ID); - register_lapic_address(mp_lapic_addr); + if (apicid >= 255) { + pr_warning("Apicid: %08x, cannot enforce nox2apic\n", + apicid); + return 0; + } + pr_warning("x2apic already enabled.\n"); + __x2apic_disable(); } + setup_clear_cpu_cap(X86_FEATURE_X2APIC); + x2apic_state = X2APIC_DISABLED; + x2apic_mode = 0; + return 0; } +early_param("nox2apic", setup_nox2apic); -void check_x2apic(void) +/* Called from cpu_init() to enable x2apic on (secondary) cpus */ +void x2apic_setup(void) { - if (x2apic_enabled()) { - pr_info("x2apic enabled by BIOS, switching to x2apic ops\n"); - x2apic_preenabled = x2apic_mode = 1; + /* + * If x2apic is not in ON state, disable it if already enabled + * from BIOS. + */ + if (x2apic_state != X2APIC_ON) { + __x2apic_disable(); + return; } + __x2apic_enable(); } -void enable_x2apic(void) +static __init void x2apic_disable(void) { - u64 msr; + u32 x2apic_id; - rdmsrl(MSR_IA32_APICBASE, msr); - if (x2apic_disabled) { - __disable_x2apic(msr); + if (x2apic_state != X2APIC_ON) + goto out; + + x2apic_id = read_apic_id(); + if (x2apic_id >= 255) + panic("Cannot disable x2apic, id: %08x\n", x2apic_id); + + __x2apic_disable(); + register_lapic_address(mp_lapic_addr); +out: + x2apic_state = X2APIC_DISABLED; + x2apic_mode = 0; +} + +static __init void x2apic_enable(void) +{ + if (x2apic_state != X2APIC_OFF) return; - } - if (!x2apic_mode) + x2apic_mode = 1; + x2apic_state = X2APIC_ON; + __x2apic_enable(); +} + +static __init void try_to_enable_x2apic(int remap_mode) +{ + if (x2apic_state == X2APIC_DISABLED) return; - if (!(msr & X2APIC_ENABLE)) { - printk_once(KERN_INFO "Enabling x2apic\n"); - wrmsrl(MSR_IA32_APICBASE, msr | X2APIC_ENABLE); + if (remap_mode != IRQ_REMAP_X2APIC_MODE) { + /* IR is required if there is APIC ID > 255 even when running + * under KVM + */ + if (max_physical_apicid > 255 || + (IS_ENABLED(CONFIG_HYPERVISOR_GUEST) && + !hypervisor_x2apic_available())) { + pr_info("x2apic: IRQ remapping doesn't support X2APIC mode\n"); + x2apic_disable(); + return; + } + + /* + * without IR all CPUs can be addressed by IOAPIC/MSI + * only in physical mode + */ + x2apic_phys = 1; } + x2apic_enable(); } -#endif /* CONFIG_X86_X2APIC */ -int __init enable_IR(void) +void __init check_x2apic(void) { -#ifdef CONFIG_IRQ_REMAP - if (!irq_remapping_supported()) { - pr_debug("intr-remapping not supported\n"); - return -1; + if (x2apic_enabled()) { + pr_info("x2apic: enabled by BIOS, switching to x2apic ops\n"); + x2apic_mode = 1; + x2apic_state = X2APIC_ON; + } else if (!cpu_has_x2apic) { + x2apic_state = X2APIC_DISABLED; } +} +#else /* CONFIG_X86_X2APIC */ +static int __init validate_x2apic(void) +{ + if (!apic_is_x2apic_enabled()) + return 0; + /* + * Checkme: Can we simply turn off x2apic here instead of panic? + */ + panic("BIOS has enabled x2apic but kernel doesn't support x2apic, please disable x2apic in BIOS.\n"); +} +early_initcall(validate_x2apic); - if (!x2apic_preenabled && skip_ioapic_setup) { - pr_info("Skipped enabling intr-remap because of skipping " - "io-apic setup\n"); +static inline void try_to_enable_x2apic(int remap_mode) { } +static inline void __x2apic_enable(void) { } +#endif /* !CONFIG_X86_X2APIC */ + +static int __init try_to_enable_IR(void) +{ +#ifdef CONFIG_X86_IO_APIC + if (!x2apic_enabled() && skip_ioapic_setup) { + pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n"); return -1; } - - return irq_remapping_enable(); #endif - return -1; + return irq_remapping_enable(); } void __init enable_IR_x2apic(void) { unsigned long flags; - int ret, x2apic_enabled = 0; - int hardware_init_ret; - - /* Make sure irq_remap_ops are initialized */ - setup_irq_remapping_ops(); + int ret, ir_stat; - hardware_init_ret = irq_remapping_prepare(); - if (hardware_init_ret && !x2apic_supported()) + ir_stat = irq_remapping_prepare(); + if (ir_stat < 0 && !x2apic_supported()) return; ret = save_ioapic_entries(); @@ -1614,49 +1652,13 @@ void __init enable_IR_x2apic(void) legacy_pic->mask_all(); mask_ioapic_entries(); - if (x2apic_preenabled && nox2apic) - disable_x2apic(); - - if (hardware_init_ret) - ret = -1; - else - ret = enable_IR(); - - if (!x2apic_supported()) - goto skip_x2apic; + /* If irq_remapping_prepare() succeded, try to enable it */ + if (ir_stat >= 0) + ir_stat = try_to_enable_IR(); + /* ir_stat contains the remap mode or an error code */ + try_to_enable_x2apic(ir_stat); - if (ret < 0) { - /* IR is required if there is APIC ID > 255 even when running - * under KVM - */ - if (max_physical_apicid > 255 || - !hypervisor_x2apic_available()) { - if (x2apic_preenabled) - disable_x2apic(); - goto skip_x2apic; - } - /* - * without IR all CPUs can be addressed by IOAPIC/MSI - * only in physical mode - */ - x2apic_force_phys(); - } - - if (ret == IRQ_REMAP_XAPIC_MODE) { - pr_info("x2apic not enabled, IRQ remapping is in xapic mode\n"); - goto skip_x2apic; - } - - x2apic_enabled = 1; - - if (x2apic_supported() && !x2apic_mode) { - x2apic_mode = 1; - enable_x2apic(); - pr_info("Enabled x2apic\n"); - } - -skip_x2apic: - if (ret < 0) /* IR enabling failed */ + if (ir_stat < 0) restore_ioapic_entries(); legacy_pic->restore_mask(); local_irq_restore(flags); @@ -1847,82 +1849,8 @@ void __init register_lapic_address(unsigned long address) } } -/* - * This initializes the IO-APIC and APIC hardware if this is - * a UP kernel. - */ int apic_version[MAX_LOCAL_APIC]; -int __init APIC_init_uniprocessor(void) -{ - if (disable_apic) { - pr_info("Apic disabled\n"); - return -1; - } -#ifdef CONFIG_X86_64 - if (!cpu_has_apic) { - disable_apic = 1; - pr_info("Apic disabled by BIOS\n"); - return -1; - } -#else - if (!smp_found_config && !cpu_has_apic) - return -1; - - /* - * Complain if the BIOS pretends there is one. - */ - if (!cpu_has_apic && - APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) { - pr_err("BIOS bug, local APIC 0x%x not detected!...\n", - boot_cpu_physical_apicid); - return -1; - } -#endif - - default_setup_apic_routing(); - - verify_local_APIC(); - connect_bsp_APIC(); - -#ifdef CONFIG_X86_64 - apic_write(APIC_ID, SET_APIC_ID(boot_cpu_physical_apicid)); -#else - /* - * Hack: In case of kdump, after a crash, kernel might be booting - * on a cpu with non-zero lapic id. But boot_cpu_physical_apicid - * might be zero if read from MP tables. Get it from LAPIC. - */ -# ifdef CONFIG_CRASH_DUMP - boot_cpu_physical_apicid = read_apic_id(); -# endif -#endif - physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); - setup_local_APIC(); - -#ifdef CONFIG_X86_IO_APIC - /* - * Now enable IO-APICs, actually call clear_IO_APIC - * We need clear_IO_APIC before enabling error vector - */ - if (!skip_ioapic_setup && nr_ioapics) - enable_IO_APIC(); -#endif - - bsp_end_local_APIC_setup(); - -#ifdef CONFIG_X86_IO_APIC - if (smp_found_config && !skip_ioapic_setup && nr_ioapics) - setup_IO_APIC(); - else { - nr_ioapics = 0; - } -#endif - - x86_init.timers.setup_percpu_clockev(); - return 0; -} - /* * Local APIC interrupts */ @@ -2027,7 +1955,7 @@ __visible void smp_trace_error_interrupt(struct pt_regs *regs) /** * connect_bsp_APIC - attach the APIC to the interrupt system */ -void __init connect_bsp_APIC(void) +static void __init connect_bsp_APIC(void) { #ifdef CONFIG_X86_32 if (pic_mode) { @@ -2274,6 +2202,100 @@ void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v)) } } +static void __init apic_bsp_up_setup(void) +{ +#ifdef CONFIG_X86_64 + apic_write(APIC_ID, SET_APIC_ID(boot_cpu_physical_apicid)); +#else + /* + * Hack: In case of kdump, after a crash, kernel might be booting + * on a cpu with non-zero lapic id. But boot_cpu_physical_apicid + * might be zero if read from MP tables. Get it from LAPIC. + */ +# ifdef CONFIG_CRASH_DUMP + boot_cpu_physical_apicid = read_apic_id(); +# endif +#endif + physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); +} + +/** + * apic_bsp_setup - Setup function for local apic and io-apic + * @upmode: Force UP mode (for APIC_init_uniprocessor) + * + * Returns: + * apic_id of BSP APIC + */ +int __init apic_bsp_setup(bool upmode) +{ + int id; + + connect_bsp_APIC(); + if (upmode) + apic_bsp_up_setup(); + setup_local_APIC(); + + if (x2apic_mode) + id = apic_read(APIC_LDR); + else + id = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + + enable_IO_APIC(); + end_local_APIC_setup(); + irq_remap_enable_fault_handling(); + setup_IO_APIC(); + /* Setup local timer */ + x86_init.timers.setup_percpu_clockev(); + return id; +} + +/* + * This initializes the IO-APIC and APIC hardware if this is + * a UP kernel. + */ +int __init APIC_init_uniprocessor(void) +{ + if (disable_apic) { + pr_info("Apic disabled\n"); + return -1; + } +#ifdef CONFIG_X86_64 + if (!cpu_has_apic) { + disable_apic = 1; + pr_info("Apic disabled by BIOS\n"); + return -1; + } +#else + if (!smp_found_config && !cpu_has_apic) + return -1; + + /* + * Complain if the BIOS pretends there is one. + */ + if (!cpu_has_apic && + APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) { + pr_err("BIOS bug, local APIC 0x%x not detected!...\n", + boot_cpu_physical_apicid); + return -1; + } +#endif + + if (!smp_found_config) + disable_ioapic_support(); + + default_setup_apic_routing(); + verify_local_APIC(); + apic_bsp_setup(true); + return 0; +} + +#ifdef CONFIG_UP_LATE_INIT +void __init up_late_init(void) +{ + APIC_init_uniprocessor(); +} +#endif + /* * Power management */ @@ -2359,9 +2381,9 @@ static void lapic_resume(void) mask_ioapic_entries(); legacy_pic->mask_all(); - if (x2apic_mode) - enable_x2apic(); - else { + if (x2apic_mode) { + __x2apic_enable(); + } else { /* * Make sure the APICBASE points to the right address * diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 3f5f60406ab..f4dc2462a1a 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1507,7 +1507,10 @@ void __init enable_IO_APIC(void) int i8259_apic, i8259_pin; int apic, pin; - if (!nr_legacy_irqs()) + if (skip_ioapic_setup) + nr_ioapics = 0; + + if (!nr_legacy_irqs() || !nr_ioapics) return; for_each_ioapic_pin(apic, pin) { @@ -2295,7 +2298,7 @@ static inline void __init check_timer(void) } local_irq_disable(); apic_printk(APIC_QUIET, KERN_INFO "..... failed :(.\n"); - if (x2apic_preenabled) + if (apic_is_x2apic_enabled()) apic_printk(APIC_QUIET, KERN_INFO "Perhaps problem with the pre-enabled x2apic mode\n" "Try booting with x2apic and interrupt-remapping disabled in the bios.\n"); @@ -2373,9 +2376,9 @@ void __init setup_IO_APIC(void) { int ioapic; - /* - * calling enable_IO_APIC() is moved to setup_local_APIC for BP - */ + if (skip_ioapic_setup || !nr_ioapics) + return; + io_apic_irqs = nr_legacy_irqs() ? ~PIC_IRQS : ~0UL; apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n"); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 15c5df92f74..a220239cea6 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -869,3 +869,22 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) return false; } + +void set_dr_addr_mask(unsigned long mask, int dr) +{ + if (!cpu_has_bpext) + return; + + switch (dr) { + case 0: + wrmsr(MSR_F16H_DR0_ADDR_MASK, mask, 0); + break; + case 1: + case 2: + case 3: + wrmsr(MSR_F16H_DR1_ADDR_MASK - 1 + dr, mask, 0); + break; + default: + break; + } +} diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c6049650c09..b15bffcaba6 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -491,17 +491,18 @@ u16 __read_mostly tlb_lld_2m[NR_INFO]; u16 __read_mostly tlb_lld_4m[NR_INFO]; u16 __read_mostly tlb_lld_1g[NR_INFO]; -void cpu_detect_tlb(struct cpuinfo_x86 *c) +static void cpu_detect_tlb(struct cpuinfo_x86 *c) { if (this_cpu->c_detect_tlb) this_cpu->c_detect_tlb(c); - printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" - "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n", + pr_info("Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n", tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES], - tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES], - tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES], - tlb_lld_1g[ENTRIES]); + tlb_lli_4m[ENTRIES]); + + pr_info("Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n", + tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES], + tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]); } void detect_ht(struct cpuinfo_x86 *c) @@ -1332,7 +1333,7 @@ void cpu_init(void) barrier(); x86_configure_nx(); - enable_x2apic(); + x2apic_setup(); /* * set up and load the per-CPU TSS diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 9cc6b6f25f4..94d7dcb1214 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -487,10 +487,8 @@ static void init_intel(struct cpuinfo_x86 *c) rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); if ((epb & 0xF) == ENERGY_PERF_BIAS_PERFORMANCE) { - printk_once(KERN_WARNING "ENERGY_PERF_BIAS:" - " Set to 'normal', was 'performance'\n" - "ENERGY_PERF_BIAS: View and update with" - " x86_energy_perf_policy(8)\n"); + pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n"); + pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n"); epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL; wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index d2c611699cd..cdfed795396 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -43,6 +43,7 @@ #include <linux/export.h> #include <asm/processor.h> +#include <asm/traps.h> #include <asm/mce.h> #include <asm/msr.h> @@ -115,7 +116,7 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. */ -ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain); +static ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain); /* Do initial initialization of a struct mce */ void mce_setup(struct mce *m) @@ -311,7 +312,7 @@ static void wait_for_panic(void) panic("Panicing machine check CPU died"); } -static void mce_panic(char *msg, struct mce *final, char *exp) +static void mce_panic(const char *msg, struct mce *final, char *exp) { int i, apei_err = 0; @@ -529,7 +530,7 @@ static void mce_schedule_work(void) schedule_work(this_cpu_ptr(&mce_work)); } -DEFINE_PER_CPU(struct irq_work, mce_irq_work); +static DEFINE_PER_CPU(struct irq_work, mce_irq_work); static void mce_irq_work_cb(struct irq_work *entry) { @@ -735,7 +736,7 @@ static atomic_t mce_callin; /* * Check if a timeout waiting for other CPUs happened. */ -static int mce_timed_out(u64 *t) +static int mce_timed_out(u64 *t, const char *msg) { /* * The others already did panic for some reason. @@ -750,8 +751,7 @@ static int mce_timed_out(u64 *t) goto out; if ((s64)*t < SPINUNIT) { if (mca_cfg.tolerant <= 1) - mce_panic("Timeout synchronizing machine check over CPUs", - NULL, NULL); + mce_panic(msg, NULL, NULL); cpu_missing = 1; return 1; } @@ -867,7 +867,8 @@ static int mce_start(int *no_way_out) * Wait for everyone. */ while (atomic_read(&mce_callin) != cpus) { - if (mce_timed_out(&timeout)) { + if (mce_timed_out(&timeout, + "Timeout: Not all CPUs entered broadcast exception handler")) { atomic_set(&global_nwo, 0); return -1; } @@ -892,7 +893,8 @@ static int mce_start(int *no_way_out) * only seen by one CPU before cleared, avoiding duplicates. */ while (atomic_read(&mce_executing) < order) { - if (mce_timed_out(&timeout)) { + if (mce_timed_out(&timeout, + "Timeout: Subject CPUs unable to finish machine check processing")) { atomic_set(&global_nwo, 0); return -1; } @@ -936,7 +938,8 @@ static int mce_end(int order) * loops. */ while (atomic_read(&mce_executing) <= cpus) { - if (mce_timed_out(&timeout)) + if (mce_timed_out(&timeout, + "Timeout: Monarch CPU unable to finish machine check processing")) goto reset; ndelay(SPINUNIT); } @@ -949,7 +952,8 @@ static int mce_end(int order) * Subject: Wait for Monarch to finish. */ while (atomic_read(&mce_executing) != 0) { - if (mce_timed_out(&timeout)) + if (mce_timed_out(&timeout, + "Timeout: Monarch CPU did not finish machine check processing")) goto reset; ndelay(SPINUNIT); } @@ -1003,51 +1007,6 @@ static void mce_clear_state(unsigned long *toclear) } /* - * Need to save faulting physical address associated with a process - * in the machine check handler some place where we can grab it back - * later in mce_notify_process() - */ -#define MCE_INFO_MAX 16 - -struct mce_info { - atomic_t inuse; - struct task_struct *t; - __u64 paddr; - int restartable; -} mce_info[MCE_INFO_MAX]; - -static void mce_save_info(__u64 addr, int c) -{ - struct mce_info *mi; - - for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++) { - if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) { - mi->t = current; - mi->paddr = addr; - mi->restartable = c; - return; - } - } - - mce_panic("Too many concurrent recoverable errors", NULL, NULL); -} - -static struct mce_info *mce_find_info(void) -{ - struct mce_info *mi; - - for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++) - if (atomic_read(&mi->inuse) && mi->t == current) - return mi; - return NULL; -} - -static void mce_clear_info(struct mce_info *mi) -{ - atomic_set(&mi->inuse, 0); -} - -/* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. * @@ -1063,6 +1022,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) { struct mca_config *cfg = &mca_cfg; struct mce m, *final; + enum ctx_state prev_state; int i; int worst = 0; int severity; @@ -1084,6 +1044,10 @@ void do_machine_check(struct pt_regs *regs, long error_code) DECLARE_BITMAP(toclear, MAX_NR_BANKS); DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); char *msg = "Unknown"; + u64 recover_paddr = ~0ull; + int flags = MF_ACTION_REQUIRED; + + prev_state = ist_enter(regs); this_cpu_inc(mce_exception_count); @@ -1203,9 +1167,9 @@ void do_machine_check(struct pt_regs *regs, long error_code) if (no_way_out) mce_panic("Fatal machine check on current CPU", &m, msg); if (worst == MCE_AR_SEVERITY) { - /* schedule action before return to userland */ - mce_save_info(m.addr, m.mcgstatus & MCG_STATUS_RIPV); - set_thread_flag(TIF_MCE_NOTIFY); + recover_paddr = m.addr; + if (!(m.mcgstatus & MCG_STATUS_RIPV)) + flags |= MF_MUST_KILL; } else if (kill_it) { force_sig(SIGBUS, current); } @@ -1216,6 +1180,27 @@ void do_machine_check(struct pt_regs *regs, long error_code) mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); out: sync_core(); + + if (recover_paddr == ~0ull) + goto done; + + pr_err("Uncorrected hardware memory error in user-access at %llx", + recover_paddr); + /* + * We must call memory_failure() here even if the current process is + * doomed. We still need to mark the page as poisoned and alert any + * other users of the page. + */ + ist_begin_non_atomic(regs); + local_irq_enable(); + if (memory_failure(recover_paddr >> PAGE_SHIFT, MCE_VECTOR, flags) < 0) { + pr_err("Memory error not recovered"); + force_sig(SIGBUS, current); + } + local_irq_disable(); + ist_end_non_atomic(); +done: + ist_exit(regs, prev_state); } EXPORT_SYMBOL_GPL(do_machine_check); @@ -1233,42 +1218,6 @@ int memory_failure(unsigned long pfn, int vector, int flags) #endif /* - * Called in process context that interrupted by MCE and marked with - * TIF_MCE_NOTIFY, just before returning to erroneous userland. - * This code is allowed to sleep. - * Attempt possible recovery such as calling the high level VM handler to - * process any corrupted pages, and kill/signal current process if required. - * Action required errors are handled here. - */ -void mce_notify_process(void) -{ - unsigned long pfn; - struct mce_info *mi = mce_find_info(); - int flags = MF_ACTION_REQUIRED; - - if (!mi) - mce_panic("Lost physical address for unconsumed uncorrectable error", NULL, NULL); - pfn = mi->paddr >> PAGE_SHIFT; - - clear_thread_flag(TIF_MCE_NOTIFY); - - pr_err("Uncorrected hardware memory error in user-access at %llx", - mi->paddr); - /* - * We must call memory_failure() here even if the current process is - * doomed. We still need to mark the page as poisoned and alert any - * other users of the page. - */ - if (!mi->restartable) - flags |= MF_MUST_KILL; - if (memory_failure(pfn, MCE_VECTOR, flags) < 0) { - pr_err("Memory error not recovered"); - force_sig(SIGBUS, current); - } - mce_clear_info(mi); -} - -/* * Action optional processing happens here (picking up * from the list of faulting pages that do_machine_check() * placed into the "ring"). diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c index a3042989398..ec2663a708e 100644 --- a/arch/x86/kernel/cpu/mcheck/p5.c +++ b/arch/x86/kernel/cpu/mcheck/p5.c @@ -8,6 +8,7 @@ #include <linux/smp.h> #include <asm/processor.h> +#include <asm/traps.h> #include <asm/mce.h> #include <asm/msr.h> @@ -17,8 +18,11 @@ int mce_p5_enabled __read_mostly; /* Machine check handler for Pentium class Intel CPUs: */ static void pentium_machine_check(struct pt_regs *regs, long error_code) { + enum ctx_state prev_state; u32 loaddr, hi, lotype; + prev_state = ist_enter(regs); + rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi); rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi); @@ -33,6 +37,8 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code) } add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); + + ist_exit(regs, prev_state); } /* Set up machine check reporting for processors with Intel style MCE: */ diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c index 7dc5564d0cd..bd5d46a3221 100644 --- a/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/arch/x86/kernel/cpu/mcheck/winchip.c @@ -7,14 +7,19 @@ #include <linux/types.h> #include <asm/processor.h> +#include <asm/traps.h> #include <asm/mce.h> #include <asm/msr.h> /* Machine check handler for WinChip C6: */ static void winchip_machine_check(struct pt_regs *regs, long error_code) { + enum ctx_state prev_state = ist_enter(regs); + printk(KERN_EMERG "CPU0: Machine Check Exception.\n"); add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); + + ist_exit(regs, prev_state); } /* Set up machine check reporting on the Winchip C6 series */ diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 15c29096136..36a83617eb2 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -552,7 +552,7 @@ static int __init microcode_init(void) int error; if (paravirt_enabled() || dis_ucode_ldr) - return 0; + return -EINVAL; if (c->x86_vendor == X86_VENDOR_INTEL) microcode_ops = init_intel_microcode(); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index dd2f07ae9d0..46201deee92 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -184,9 +184,9 @@ void __init e820_print_map(char *who) * overwritten in the same location, starting at biosmap. * * The integer pointed to by pnr_map must be valid on entry (the - * current number of valid entries located at biosmap) and will - * be updated on return, with the new number of valid entries - * (something no more than max_nr_map.) + * current number of valid entries located at biosmap). If the + * sanitizing succeeds the *pnr_map will be updated with the new + * number of valid entries (something no more than max_nr_map). * * The return value from sanitize_e820_map() is zero if it * successfully 'sanitized' the map entries passed in, and is -1 @@ -561,23 +561,15 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, void __init update_e820(void) { - u32 nr_map; - - nr_map = e820.nr_map; - if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map)) + if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map)) return; - e820.nr_map = nr_map; printk(KERN_INFO "e820: modified physical RAM map:\n"); e820_print_map("modified"); } static void __init update_e820_saved(void) { - u32 nr_map; - - nr_map = e820_saved.nr_map; - if (sanitize_e820_map(e820_saved.map, ARRAY_SIZE(e820_saved.map), &nr_map)) - return; - e820_saved.nr_map = nr_map; + sanitize_e820_map(e820_saved.map, ARRAY_SIZE(e820_saved.map), + &e820_saved.nr_map); } #define MAX_GAP_END 0x100000000ull /* @@ -898,11 +890,9 @@ early_param("memmap", parse_memmap_opt); void __init finish_e820_parsing(void) { if (userdef) { - u32 nr = e820.nr_map; - - if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr) < 0) + if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), + &e820.nr_map) < 0) early_panic("Invalid user supplied memory map"); - e820.nr_map = nr; printk(KERN_INFO "e820: user-defined physical RAM map:\n"); e820_print_map("user"); diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 9ebaf63ba18..db13655c3a2 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -143,7 +143,8 @@ ENDPROC(native_usergs_sysret64) movq \tmp,RSP+\offset(%rsp) movq $__USER_DS,SS+\offset(%rsp) movq $__USER_CS,CS+\offset(%rsp) - movq $-1,RCX+\offset(%rsp) + movq RIP+\offset(%rsp),\tmp /* get rip */ + movq \tmp,RCX+\offset(%rsp) /* copy it to rcx as sysret would do */ movq R11+\offset(%rsp),\tmp /* get eflags */ movq \tmp,EFLAGS+\offset(%rsp) .endm @@ -155,27 +156,6 @@ ENDPROC(native_usergs_sysret64) movq \tmp,R11+\offset(%rsp) .endm - .macro FAKE_STACK_FRAME child_rip - /* push in order ss, rsp, eflags, cs, rip */ - xorl %eax, %eax - pushq_cfi $__KERNEL_DS /* ss */ - /*CFI_REL_OFFSET ss,0*/ - pushq_cfi %rax /* rsp */ - CFI_REL_OFFSET rsp,0 - pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) /* eflags - interrupts on */ - /*CFI_REL_OFFSET rflags,0*/ - pushq_cfi $__KERNEL_CS /* cs */ - /*CFI_REL_OFFSET cs,0*/ - pushq_cfi \child_rip /* rip */ - CFI_REL_OFFSET rip,0 - pushq_cfi %rax /* orig rax */ - .endm - - .macro UNFAKE_STACK_FRAME - addq $8*6, %rsp - CFI_ADJUST_CFA_OFFSET -(6*8) - .endm - /* * initial frame state for interrupts (and exceptions without error code) */ @@ -238,51 +218,6 @@ ENDPROC(native_usergs_sysret64) CFI_REL_OFFSET r15, R15+\offset .endm -/* save partial stack frame */ - .macro SAVE_ARGS_IRQ - cld - /* start from rbp in pt_regs and jump over */ - movq_cfi rdi, (RDI-RBP) - movq_cfi rsi, (RSI-RBP) - movq_cfi rdx, (RDX-RBP) - movq_cfi rcx, (RCX-RBP) - movq_cfi rax, (RAX-RBP) - movq_cfi r8, (R8-RBP) - movq_cfi r9, (R9-RBP) - movq_cfi r10, (R10-RBP) - movq_cfi r11, (R11-RBP) - - /* Save rbp so that we can unwind from get_irq_regs() */ - movq_cfi rbp, 0 - - /* Save previous stack value */ - movq %rsp, %rsi - - leaq -RBP(%rsp),%rdi /* arg1 for handler */ - testl $3, CS-RBP(%rsi) - je 1f - SWAPGS - /* - * irq_count is used to check if a CPU is already on an interrupt stack - * or not. While this is essentially redundant with preempt_count it is - * a little cheaper to use a separate counter in the PDA (short of - * moving irq_enter into assembly, which would be too much work) - */ -1: incl PER_CPU_VAR(irq_count) - cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp - CFI_DEF_CFA_REGISTER rsi - - /* Store previous stack value */ - pushq %rsi - CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \ - 0x77 /* DW_OP_breg7 */, 0, \ - 0x06 /* DW_OP_deref */, \ - 0x08 /* DW_OP_const1u */, SS+8-RBP, \ - 0x22 /* DW_OP_plus */ - /* We entered an interrupt context - irqs are off: */ - TRACE_IRQS_OFF - .endm - ENTRY(save_paranoid) XCPT_FRAME 1 RDI+8 cld @@ -426,15 +361,12 @@ system_call_fastpath: * Has incomplete stack frame and undefined top of stack. */ ret_from_sys_call: - movl $_TIF_ALLWORK_MASK,%edi - /* edi: flagmask */ -sysret_check: + testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + jnz int_ret_from_sys_call_fixup /* Go the the slow path */ + LOCKDEP_SYS_EXIT DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - movl TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET),%edx - andl %edi,%edx - jnz sysret_careful CFI_REMEMBER_STATE /* * sysretq will re-enable interrupts: @@ -448,49 +380,10 @@ sysret_check: USERGS_SYSRET64 CFI_RESTORE_STATE - /* Handle reschedules */ - /* edx: work, edi: workmask */ -sysret_careful: - bt $TIF_NEED_RESCHED,%edx - jnc sysret_signal - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - pushq_cfi %rdi - SCHEDULE_USER - popq_cfi %rdi - jmp sysret_check - /* Handle a signal */ -sysret_signal: - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) -#ifdef CONFIG_AUDITSYSCALL - bt $TIF_SYSCALL_AUDIT,%edx - jc sysret_audit -#endif - /* - * We have a signal, or exit tracing or single-step. - * These all wind up with the iret return path anyway, - * so just join that path right now. - */ +int_ret_from_sys_call_fixup: FIXUP_TOP_OF_STACK %r11, -ARGOFFSET - jmp int_check_syscall_exit_work - -#ifdef CONFIG_AUDITSYSCALL - /* - * Return fast path for syscall audit. Call __audit_syscall_exit() - * directly and then jump back to the fast path with TIF_SYSCALL_AUDIT - * masked off. - */ -sysret_audit: - movq RAX-ARGOFFSET(%rsp),%rsi /* second arg, syscall return value */ - cmpq $-MAX_ERRNO,%rsi /* is it < -MAX_ERRNO? */ - setbe %al /* 1 if so, 0 if not */ - movzbl %al,%edi /* zero-extend that into %edi */ - call __audit_syscall_exit - movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi - jmp sysret_check -#endif /* CONFIG_AUDITSYSCALL */ + jmp int_ret_from_sys_call /* Do syscall tracing */ tracesys: @@ -626,19 +519,6 @@ END(\label) FORK_LIKE vfork FIXED_FRAME stub_iopl, sys_iopl -ENTRY(ptregscall_common) - DEFAULT_FRAME 1 8 /* offset 8: return address */ - RESTORE_TOP_OF_STACK %r11, 8 - movq_cfi_restore R15+8, r15 - movq_cfi_restore R14+8, r14 - movq_cfi_restore R13+8, r13 - movq_cfi_restore R12+8, r12 - movq_cfi_restore RBP+8, rbp - movq_cfi_restore RBX+8, rbx - ret $REST_SKIP /* pop extended registers */ - CFI_ENDPROC -END(ptregscall_common) - ENTRY(stub_execve) CFI_STARTPROC addq $8, %rsp @@ -779,7 +659,48 @@ END(interrupt) /* reserve pt_regs for scratch regs and rbp */ subq $ORIG_RAX-RBP, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP - SAVE_ARGS_IRQ + cld + /* start from rbp in pt_regs and jump over */ + movq_cfi rdi, (RDI-RBP) + movq_cfi rsi, (RSI-RBP) + movq_cfi rdx, (RDX-RBP) + movq_cfi rcx, (RCX-RBP) + movq_cfi rax, (RAX-RBP) + movq_cfi r8, (R8-RBP) + movq_cfi r9, (R9-RBP) + movq_cfi r10, (R10-RBP) + movq_cfi r11, (R11-RBP) + + /* Save rbp so that we can unwind from get_irq_regs() */ + movq_cfi rbp, 0 + + /* Save previous stack value */ + movq %rsp, %rsi + + leaq -RBP(%rsp),%rdi /* arg1 for handler */ + testl $3, CS-RBP(%rsi) + je 1f + SWAPGS + /* + * irq_count is used to check if a CPU is already on an interrupt stack + * or not. While this is essentially redundant with preempt_count it is + * a little cheaper to use a separate counter in the PDA (short of + * moving irq_enter into assembly, which would be too much work) + */ +1: incl PER_CPU_VAR(irq_count) + cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp + CFI_DEF_CFA_REGISTER rsi + + /* Store previous stack value */ + pushq %rsi + CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \ + 0x77 /* DW_OP_breg7 */, 0, \ + 0x06 /* DW_OP_deref */, \ + 0x08 /* DW_OP_const1u */, SS+8-RBP, \ + 0x22 /* DW_OP_plus */ + /* We entered an interrupt context - irqs are off: */ + TRACE_IRQS_OFF + call \func .endm @@ -831,6 +752,60 @@ retint_swapgs: /* return to user-space */ */ DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_IRETQ + + /* + * Try to use SYSRET instead of IRET if we're returning to + * a completely clean 64-bit userspace context. + */ + movq (RCX-R11)(%rsp), %rcx + cmpq %rcx,(RIP-R11)(%rsp) /* RCX == RIP */ + jne opportunistic_sysret_failed + + /* + * On Intel CPUs, sysret with non-canonical RCX/RIP will #GP + * in kernel space. This essentially lets the user take over + * the kernel, since userspace controls RSP. It's not worth + * testing for canonicalness exactly -- this check detects any + * of the 17 high bits set, which is true for non-canonical + * or kernel addresses. (This will pessimize vsyscall=native. + * Big deal.) + * + * If virtual addresses ever become wider, this will need + * to be updated to remain correct on both old and new CPUs. + */ + .ifne __VIRTUAL_MASK_SHIFT - 47 + .error "virtual address width changed -- sysret checks need update" + .endif + shr $__VIRTUAL_MASK_SHIFT, %rcx + jnz opportunistic_sysret_failed + + cmpq $__USER_CS,(CS-R11)(%rsp) /* CS must match SYSRET */ + jne opportunistic_sysret_failed + + movq (R11-ARGOFFSET)(%rsp), %r11 + cmpq %r11,(EFLAGS-ARGOFFSET)(%rsp) /* R11 == RFLAGS */ + jne opportunistic_sysret_failed + + testq $X86_EFLAGS_RF,%r11 /* sysret can't restore RF */ + jnz opportunistic_sysret_failed + + /* nothing to check for RSP */ + + cmpq $__USER_DS,(SS-ARGOFFSET)(%rsp) /* SS must match SYSRET */ + jne opportunistic_sysret_failed + + /* + * We win! This label is here just for ease of understanding + * perf profiles. Nothing jumps here. + */ +irq_return_via_sysret: + CFI_REMEMBER_STATE + RESTORE_ARGS 1,8,1 + movq (RSP-RIP)(%rsp),%rsp + USERGS_SYSRET64 + CFI_RESTORE_STATE + +opportunistic_sysret_failed: SWAPGS jmp restore_args @@ -1048,6 +1023,11 @@ ENTRY(\sym) CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 .if \paranoid + .if \paranoid == 1 + CFI_REMEMBER_STATE + testl $3, CS(%rsp) /* If coming from userspace, switch */ + jnz 1f /* stacks. */ + .endif call save_paranoid .else call error_entry @@ -1088,6 +1068,36 @@ ENTRY(\sym) jmp error_exit /* %ebx: no swapgs flag */ .endif + .if \paranoid == 1 + CFI_RESTORE_STATE + /* + * Paranoid entry from userspace. Switch stacks and treat it + * as a normal entry. This means that paranoid handlers + * run in real process context if user_mode(regs). + */ +1: + call error_entry + + DEFAULT_FRAME 0 + + movq %rsp,%rdi /* pt_regs pointer */ + call sync_regs + movq %rax,%rsp /* switch stack */ + + movq %rsp,%rdi /* pt_regs pointer */ + + .if \has_error_code + movq ORIG_RAX(%rsp),%rsi /* get error code */ + movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ + .else + xorl %esi,%esi /* no error code */ + .endif + + call \do_sym + + jmp error_exit /* %ebx: no swapgs flag */ + .endif + CFI_ENDPROC END(\sym) .endm @@ -1108,7 +1118,7 @@ idtentry overflow do_overflow has_error_code=0 idtentry bounds do_bounds has_error_code=0 idtentry invalid_op do_invalid_op has_error_code=0 idtentry device_not_available do_device_not_available has_error_code=0 -idtentry double_fault do_double_fault has_error_code=1 paranoid=1 +idtentry double_fault do_double_fault has_error_code=1 paranoid=2 idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0 idtentry invalid_TSS do_invalid_TSS has_error_code=1 idtentry segment_not_present do_segment_not_present has_error_code=1 @@ -1289,16 +1299,14 @@ idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector( #endif /* - * "Paranoid" exit path from exception stack. - * Paranoid because this is used by NMIs and cannot take - * any kernel state for granted. - * We don't do kernel preemption checks here, because only - * NMI should be common and it does not enable IRQs and - * cannot get reschedule ticks. + * "Paranoid" exit path from exception stack. This is invoked + * only on return from non-NMI IST interrupts that came + * from kernel space. * - * "trace" is 0 for the NMI handler only, because irq-tracing - * is fundamentally NMI-unsafe. (we cannot change the soft and - * hard flags at once, atomically) + * We may be returning to very strange contexts (e.g. very early + * in syscall entry), so checking for preemption here would + * be complicated. Fortunately, we there's no good reason + * to try to handle preemption here. */ /* ebx: no swapgs flag */ @@ -1308,43 +1316,14 @@ ENTRY(paranoid_exit) TRACE_IRQS_OFF_DEBUG testl %ebx,%ebx /* swapgs needed? */ jnz paranoid_restore - testl $3,CS(%rsp) - jnz paranoid_userspace -paranoid_swapgs: TRACE_IRQS_IRETQ 0 SWAPGS_UNSAFE_STACK RESTORE_ALL 8 - jmp irq_return + INTERRUPT_RETURN paranoid_restore: TRACE_IRQS_IRETQ_DEBUG 0 RESTORE_ALL 8 - jmp irq_return -paranoid_userspace: - GET_THREAD_INFO(%rcx) - movl TI_flags(%rcx),%ebx - andl $_TIF_WORK_MASK,%ebx - jz paranoid_swapgs - movq %rsp,%rdi /* &pt_regs */ - call sync_regs - movq %rax,%rsp /* switch stack for scheduling */ - testl $_TIF_NEED_RESCHED,%ebx - jnz paranoid_schedule - movl %ebx,%edx /* arg3: thread flags */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - xorl %esi,%esi /* arg2: oldset */ - movq %rsp,%rdi /* arg1: &pt_regs */ - call do_notify_resume - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - jmp paranoid_userspace -paranoid_schedule: - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_ANY) - SCHEDULE_USER - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_OFF - jmp paranoid_userspace + INTERRUPT_RETURN CFI_ENDPROC END(paranoid_exit) diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 3d5fb509bde..7114ba220fd 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -126,6 +126,8 @@ int arch_install_hw_breakpoint(struct perf_event *bp) *dr7 |= encode_dr7(i, info->len, info->type); set_debugreg(*dr7, 7); + if (info->mask) + set_dr_addr_mask(info->mask, i); return 0; } @@ -161,29 +163,8 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) *dr7 &= ~__encode_dr7(i, info->len, info->type); set_debugreg(*dr7, 7); -} - -static int get_hbp_len(u8 hbp_len) -{ - unsigned int len_in_bytes = 0; - - switch (hbp_len) { - case X86_BREAKPOINT_LEN_1: - len_in_bytes = 1; - break; - case X86_BREAKPOINT_LEN_2: - len_in_bytes = 2; - break; - case X86_BREAKPOINT_LEN_4: - len_in_bytes = 4; - break; -#ifdef CONFIG_X86_64 - case X86_BREAKPOINT_LEN_8: - len_in_bytes = 8; - break; -#endif - } - return len_in_bytes; + if (info->mask) + set_dr_addr_mask(0, i); } /* @@ -196,7 +177,7 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp) struct arch_hw_breakpoint *info = counter_arch_bp(bp); va = info->address; - len = get_hbp_len(info->len); + len = bp->attr.bp_len; return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } @@ -277,6 +258,8 @@ static int arch_build_bp_info(struct perf_event *bp) } /* Len */ + info->mask = 0; + switch (bp->attr.bp_len) { case HW_BREAKPOINT_LEN_1: info->len = X86_BREAKPOINT_LEN_1; @@ -293,11 +276,17 @@ static int arch_build_bp_info(struct perf_event *bp) break; #endif default: - return -EINVAL; + if (!is_power_of_2(bp->attr.bp_len)) + return -EINVAL; + if (!cpu_has_bpext) + return -EOPNOTSUPP; + info->mask = bp->attr.bp_len - 1; + info->len = X86_BREAKPOINT_LEN_1; } return 0; } + /* * Validate the arch-specific HW Breakpoint register settings */ @@ -312,11 +301,11 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) if (ret) return ret; - ret = -EINVAL; - switch (info->len) { case X86_BREAKPOINT_LEN_1: align = 0; + if (info->mask) + align = info->mask; break; case X86_BREAKPOINT_LEN_2: align = 1; @@ -330,7 +319,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) break; #endif default: - return ret; + WARN_ON_ONCE(1); } /* diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index a9a4229f616..81049ffab2d 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -19,6 +19,19 @@ #include <asm/fpu-internal.h> #include <asm/user.h> +static DEFINE_PER_CPU(bool, in_kernel_fpu); + +void kernel_fpu_disable(void) +{ + WARN_ON(this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, true); +} + +void kernel_fpu_enable(void) +{ + this_cpu_write(in_kernel_fpu, false); +} + /* * Were we in an interrupt that interrupted kernel mode? * @@ -33,6 +46,9 @@ */ static inline bool interrupted_kernel_fpu_idle(void) { + if (this_cpu_read(in_kernel_fpu)) + return false; + if (use_eager_fpu()) return __thread_has_fpu(current); @@ -73,10 +89,10 @@ void __kernel_fpu_begin(void) { struct task_struct *me = current; + this_cpu_write(in_kernel_fpu, true); + if (__thread_has_fpu(me)) { - __thread_clear_has_fpu(me); __save_init_fpu(me); - /* We do 'stts()' in __kernel_fpu_end() */ } else if (!use_eager_fpu()) { this_cpu_write(fpu_owner_task, NULL); clts(); @@ -86,19 +102,16 @@ EXPORT_SYMBOL(__kernel_fpu_begin); void __kernel_fpu_end(void) { - if (use_eager_fpu()) { - /* - * For eager fpu, most the time, tsk_used_math() is true. - * Restore the user math as we are done with the kernel usage. - * At few instances during thread exit, signal handling etc, - * tsk_used_math() is false. Those few places will take proper - * actions, so we don't need to restore the math here. - */ - if (likely(tsk_used_math(current))) - math_state_restore(); - } else { + struct task_struct *me = current; + + if (__thread_has_fpu(me)) { + if (WARN_ON(restore_fpu_checking(me))) + drop_init_fpu(me); + } else if (!use_eager_fpu()) { stts(); } + + this_cpu_write(in_kernel_fpu, false); } EXPORT_SYMBOL(__kernel_fpu_end); diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 63ce838e5a5..28d28f5eb8f 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -69,16 +69,9 @@ static void call_on_stack(void *func, void *stack) : "memory", "cc", "edx", "ecx", "eax"); } -/* how to get the current stack pointer from C */ -#define current_stack_pointer ({ \ - unsigned long sp; \ - asm("mov %%esp,%0" : "=g" (sp)); \ - sp; \ -}) - static inline void *current_stack(void) { - return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1)); + return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1)); } static inline int @@ -103,7 +96,7 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) /* Save the next esp at the bottom of the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer; + *prev_esp = current_stack_pointer(); if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp); @@ -156,7 +149,7 @@ void do_softirq_own_stack(void) /* Push the previous esp onto the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer; + *prev_esp = current_stack_pointer(); call_on_stack(__do_softirq, isp); } diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c new file mode 100644 index 00000000000..ff3c3101d00 --- /dev/null +++ b/arch/x86/kernel/livepatch.c @@ -0,0 +1,90 @@ +/* + * livepatch.c - x86-specific Kernel Live Patching Core + * + * Copyright (C) 2014 Seth Jennings <sjenning@redhat.com> + * Copyright (C) 2014 SUSE + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/module.h> +#include <linux/uaccess.h> +#include <asm/cacheflush.h> +#include <asm/page_types.h> +#include <asm/elf.h> +#include <asm/livepatch.h> + +/** + * klp_write_module_reloc() - write a relocation in a module + * @mod: module in which the section to be modified is found + * @type: ELF relocation type (see asm/elf.h) + * @loc: address that the relocation should be written to + * @value: relocation value (sym address + addend) + * + * This function writes a relocation to the specified location for + * a particular module. + */ +int klp_write_module_reloc(struct module *mod, unsigned long type, + unsigned long loc, unsigned long value) +{ + int ret, numpages, size = 4; + bool readonly; + unsigned long val; + unsigned long core = (unsigned long)mod->module_core; + unsigned long core_ro_size = mod->core_ro_size; + unsigned long core_size = mod->core_size; + + switch (type) { + case R_X86_64_NONE: + return 0; + case R_X86_64_64: + val = value; + size = 8; + break; + case R_X86_64_32: + val = (u32)value; + break; + case R_X86_64_32S: + val = (s32)value; + break; + case R_X86_64_PC32: + val = (u32)(value - loc); + break; + default: + /* unsupported relocation type */ + return -EINVAL; + } + + if (loc < core || loc >= core + core_size) + /* loc does not point to any symbol inside the module */ + return -EINVAL; + + if (loc < core + core_ro_size) + readonly = true; + else + readonly = false; + + /* determine if the relocation spans a page boundary */ + numpages = ((loc & PAGE_MASK) == ((loc + size) & PAGE_MASK)) ? 1 : 2; + + if (readonly) + set_memory_rw(loc & PAGE_MASK, numpages); + + ret = probe_kernel_write((void *)loc, &val, size); + + if (readonly) + set_memory_ro(loc & PAGE_MASK, numpages); + + return ret; +} diff --git a/arch/x86/kernel/pmc_atom.c b/arch/x86/kernel/pmc_atom.c index 0ee5025e0fa..d66a4fe6cae 100644 --- a/arch/x86/kernel/pmc_atom.c +++ b/arch/x86/kernel/pmc_atom.c @@ -25,8 +25,6 @@ #include <asm/pmc_atom.h> -#define DRIVER_NAME KBUILD_MODNAME - struct pmc_dev { u32 base_addr; void __iomem *regmap; @@ -38,12 +36,12 @@ struct pmc_dev { static struct pmc_dev pmc_device; static u32 acpi_base_addr; -struct pmc_dev_map { +struct pmc_bit_map { const char *name; u32 bit_mask; }; -static const struct pmc_dev_map dev_map[] = { +static const struct pmc_bit_map dev_map[] = { {"0 - LPSS1_F0_DMA", BIT_LPSS1_F0_DMA}, {"1 - LPSS1_F1_PWM1", BIT_LPSS1_F1_PWM1}, {"2 - LPSS1_F2_PWM2", BIT_LPSS1_F2_PWM2}, @@ -82,6 +80,27 @@ static const struct pmc_dev_map dev_map[] = { {"35 - DFX", BIT_DFX}, }; +static const struct pmc_bit_map pss_map[] = { + {"0 - GBE", PMC_PSS_BIT_GBE}, + {"1 - SATA", PMC_PSS_BIT_SATA}, + {"2 - HDA", PMC_PSS_BIT_HDA}, + {"3 - SEC", PMC_PSS_BIT_SEC}, + {"4 - PCIE", PMC_PSS_BIT_PCIE}, + {"5 - LPSS", PMC_PSS_BIT_LPSS}, + {"6 - LPE", PMC_PSS_BIT_LPE}, + {"7 - DFX", PMC_PSS_BIT_DFX}, + {"8 - USH_CTRL", PMC_PSS_BIT_USH_CTRL}, + {"9 - USH_SUS", PMC_PSS_BIT_USH_SUS}, + {"10 - USH_VCCS", PMC_PSS_BIT_USH_VCCS}, + {"11 - USH_VCCA", PMC_PSS_BIT_USH_VCCA}, + {"12 - OTG_CTRL", PMC_PSS_BIT_OTG_CTRL}, + {"13 - OTG_VCCS", PMC_PSS_BIT_OTG_VCCS}, + {"14 - OTG_VCCA_CLK", PMC_PSS_BIT_OTG_VCCA_CLK}, + {"15 - OTG_VCCA", PMC_PSS_BIT_OTG_VCCA}, + {"16 - USB", PMC_PSS_BIT_USB}, + {"17 - USB_SUS", PMC_PSS_BIT_USB_SUS}, +}; + static inline u32 pmc_reg_read(struct pmc_dev *pmc, int reg_offset) { return readl(pmc->regmap + reg_offset); @@ -169,6 +188,32 @@ static const struct file_operations pmc_dev_state_ops = { .release = single_release, }; +static int pmc_pss_state_show(struct seq_file *s, void *unused) +{ + struct pmc_dev *pmc = s->private; + u32 pss = pmc_reg_read(pmc, PMC_PSS); + int pss_index; + + for (pss_index = 0; pss_index < ARRAY_SIZE(pss_map); pss_index++) { + seq_printf(s, "Island: %-32s\tState: %s\n", + pss_map[pss_index].name, + pss_map[pss_index].bit_mask & pss ? "Off" : "On"); + } + return 0; +} + +static int pmc_pss_state_open(struct inode *inode, struct file *file) +{ + return single_open(file, pmc_pss_state_show, inode->i_private); +} + +static const struct file_operations pmc_pss_state_ops = { + .open = pmc_pss_state_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static int pmc_sleep_tmr_show(struct seq_file *s, void *unused) { struct pmc_dev *pmc = s->private; @@ -202,11 +247,7 @@ static const struct file_operations pmc_sleep_tmr_ops = { static void pmc_dbgfs_unregister(struct pmc_dev *pmc) { - if (!pmc->dbgfs_dir) - return; - debugfs_remove_recursive(pmc->dbgfs_dir); - pmc->dbgfs_dir = NULL; } static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev) @@ -217,19 +258,29 @@ static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev) if (!dir) return -ENOMEM; + pmc->dbgfs_dir = dir; + f = debugfs_create_file("dev_state", S_IFREG | S_IRUGO, dir, pmc, &pmc_dev_state_ops); if (!f) { - dev_err(&pdev->dev, "dev_states register failed\n"); + dev_err(&pdev->dev, "dev_state register failed\n"); goto err; } + + f = debugfs_create_file("pss_state", S_IFREG | S_IRUGO, + dir, pmc, &pmc_pss_state_ops); + if (!f) { + dev_err(&pdev->dev, "pss_state register failed\n"); + goto err; + } + f = debugfs_create_file("sleep_state", S_IFREG | S_IRUGO, dir, pmc, &pmc_sleep_tmr_ops); if (!f) { dev_err(&pdev->dev, "sleep_state register failed\n"); goto err; } - pmc->dbgfs_dir = dir; + return 0; err: pmc_dbgfs_unregister(pmc); @@ -292,7 +343,6 @@ MODULE_DEVICE_TABLE(pci, pmc_pci_ids); static int __init pmc_atom_init(void) { - int err = -ENODEV; struct pci_dev *pdev = NULL; const struct pci_device_id *ent; @@ -306,14 +356,11 @@ static int __init pmc_atom_init(void) */ for_each_pci_dev(pdev) { ent = pci_match_id(pmc_pci_ids, pdev); - if (ent) { - err = pmc_setup_dev(pdev); - goto out; - } + if (ent) + return pmc_setup_dev(pdev); } /* Device not found. */ -out: - return err; + return -ENODEV; } module_init(pmc_atom_init); diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index ca9622a25e9..fe3dbfe0c4a 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -170,7 +170,7 @@ static struct platform_device rtc_device = { static __init int add_rtc_cmos(void) { #ifdef CONFIG_PNP - static const char * const const ids[] __initconst = + static const char * const ids[] __initconst = { "PNP0b00", "PNP0b01", "PNP0b02", }; struct pnp_dev *dev; struct pnp_id *id; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index ab4734e5411..c4648adadd7 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -431,15 +431,13 @@ static void __init parse_setup_data(void) pa_data = boot_params.hdr.setup_data; while (pa_data) { - u32 data_len, map_len, data_type; + u32 data_len, data_type; - map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK), - (u64)sizeof(struct setup_data)); - data = early_memremap(pa_data, map_len); + data = early_memremap(pa_data, sizeof(*data)); data_len = data->len + sizeof(struct setup_data); data_type = data->type; pa_next = data->next; - early_iounmap(data, map_len); + early_iounmap(data, sizeof(*data)); switch (data_type) { case SETUP_E820_EXT: diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index ed37a768d0f..2a33c8f6831 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -740,12 +740,6 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) { user_exit(); -#ifdef CONFIG_X86_MCE - /* notify userspace of pending MCEs */ - if (thread_info_flags & _TIF_MCE_NOTIFY) - mce_notify_process(); -#endif /* CONFIG_X86_64 && CONFIG_X86_MCE */ - if (thread_info_flags & _TIF_UPROBE) uprobe_notify_resume(regs); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6d7022c683e..febc6aabc72 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -73,7 +73,6 @@ #include <asm/setup.h> #include <asm/uv/uv.h> #include <linux/mc146818rtc.h> -#include <asm/smpboot_hooks.h> #include <asm/i8259.h> #include <asm/realmode.h> #include <asm/misc.h> @@ -104,6 +103,43 @@ EXPORT_PER_CPU_SYMBOL(cpu_info); atomic_t init_deasserted; +static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) +{ + unsigned long flags; + + spin_lock_irqsave(&rtc_lock, flags); + CMOS_WRITE(0xa, 0xf); + spin_unlock_irqrestore(&rtc_lock, flags); + local_flush_tlb(); + pr_debug("1.\n"); + *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = + start_eip >> 4; + pr_debug("2.\n"); + *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = + start_eip & 0xf; + pr_debug("3.\n"); +} + +static inline void smpboot_restore_warm_reset_vector(void) +{ + unsigned long flags; + + /* + * Install writable page 0 entry to set BIOS data area. + */ + local_flush_tlb(); + + /* + * Paranoid: Set warm reset code and vector here back + * to default values. + */ + spin_lock_irqsave(&rtc_lock, flags); + CMOS_WRITE(0, 0xf); + spin_unlock_irqrestore(&rtc_lock, flags); + + *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0; +} + /* * Report back to the Boot Processor during boot time or to the caller processor * during CPU online. @@ -136,8 +172,7 @@ static void smp_callin(void) * CPU, first the APIC. (this is probably redundant on most * boards) */ - setup_local_APIC(); - end_local_APIC_setup(); + apic_ap_setup(); /* * Need to setup vector mappings before we enable interrupts. @@ -955,9 +990,12 @@ void arch_disable_smp_support(void) */ static __init void disable_smp(void) { + pr_info("SMP disabled\n"); + + disable_ioapic_support(); + init_cpu_present(cpumask_of(0)); init_cpu_possible(cpumask_of(0)); - smpboot_clear_io_apic_irqs(); if (smp_found_config) physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); @@ -967,6 +1005,13 @@ static __init void disable_smp(void) cpumask_set_cpu(0, cpu_core_mask(0)); } +enum { + SMP_OK, + SMP_NO_CONFIG, + SMP_NO_APIC, + SMP_FORCE_UP, +}; + /* * Various sanity checks. */ @@ -1014,10 +1059,7 @@ static int __init smp_sanity_check(unsigned max_cpus) if (!smp_found_config && !acpi_lapic) { preempt_enable(); pr_notice("SMP motherboard not detected\n"); - disable_smp(); - if (APIC_init_uniprocessor()) - pr_notice("Local APIC not detected. Using dummy APIC emulation.\n"); - return -1; + return SMP_NO_CONFIG; } /* @@ -1041,9 +1083,7 @@ static int __init smp_sanity_check(unsigned max_cpus) boot_cpu_physical_apicid); pr_err("... forcing use of dummy APIC emulation (tell your hw vendor)\n"); } - smpboot_clear_io_apic(); - disable_ioapic_support(); - return -1; + return SMP_NO_APIC; } verify_local_APIC(); @@ -1053,15 +1093,10 @@ static int __init smp_sanity_check(unsigned max_cpus) */ if (!max_cpus) { pr_info("SMP mode deactivated\n"); - smpboot_clear_io_apic(); - - connect_bsp_APIC(); - setup_local_APIC(); - bsp_end_local_APIC_setup(); - return -1; + return SMP_FORCE_UP; } - return 0; + return SMP_OK; } static void __init smp_cpu_index_default(void) @@ -1101,10 +1136,21 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) } set_cpu_sibling_map(0); - if (smp_sanity_check(max_cpus) < 0) { - pr_info("SMP disabled\n"); + switch (smp_sanity_check(max_cpus)) { + case SMP_NO_CONFIG: disable_smp(); + if (APIC_init_uniprocessor()) + pr_notice("Local APIC not detected. Using dummy APIC emulation.\n"); return; + case SMP_NO_APIC: + disable_smp(); + return; + case SMP_FORCE_UP: + disable_smp(); + apic_bsp_setup(false); + return; + case SMP_OK: + break; } default_setup_apic_routing(); @@ -1115,33 +1161,10 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) /* Or can we switch back to PIC here? */ } - connect_bsp_APIC(); - - /* - * Switch from PIC to APIC mode. - */ - setup_local_APIC(); - - if (x2apic_mode) - cpu0_logical_apicid = apic_read(APIC_LDR); - else - cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); - - /* - * Enable IO APIC before setting up error vector - */ - if (!skip_ioapic_setup && nr_ioapics) - enable_IO_APIC(); - - bsp_end_local_APIC_setup(); - smpboot_setup_io_apic(); - /* - * Set up local APIC timer on boot CPU. - */ + cpu0_logical_apicid = apic_bsp_setup(false); pr_info("CPU%d: ", 0); print_cpu_info(&cpu_data(0)); - x86_init.timers.setup_percpu_clockev(); if (is_uv_system()) uv_system_init(); @@ -1177,9 +1200,7 @@ void __init native_smp_cpus_done(unsigned int max_cpus) nmi_selftest(); impress_friends(); -#ifdef CONFIG_X86_IO_APIC setup_ioapic_dest(); -#endif mtrr_aps_init(); } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 88900e28802..9d2073e2ecc 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -108,6 +108,88 @@ static inline void preempt_conditional_cli(struct pt_regs *regs) preempt_count_dec(); } +enum ctx_state ist_enter(struct pt_regs *regs) +{ + enum ctx_state prev_state; + + if (user_mode_vm(regs)) { + /* Other than that, we're just an exception. */ + prev_state = exception_enter(); + } else { + /* + * We might have interrupted pretty much anything. In + * fact, if we're a machine check, we can even interrupt + * NMI processing. We don't want in_nmi() to return true, + * but we need to notify RCU. + */ + rcu_nmi_enter(); + prev_state = IN_KERNEL; /* the value is irrelevant. */ + } + + /* + * We are atomic because we're on the IST stack (or we're on x86_32, + * in which case we still shouldn't schedule). + * + * This must be after exception_enter(), because exception_enter() + * won't do anything if in_interrupt() returns true. + */ + preempt_count_add(HARDIRQ_OFFSET); + + /* This code is a bit fragile. Test it. */ + rcu_lockdep_assert(rcu_is_watching(), "ist_enter didn't work"); + + return prev_state; +} + +void ist_exit(struct pt_regs *regs, enum ctx_state prev_state) +{ + /* Must be before exception_exit. */ + preempt_count_sub(HARDIRQ_OFFSET); + + if (user_mode_vm(regs)) + return exception_exit(prev_state); + else + rcu_nmi_exit(); +} + +/** + * ist_begin_non_atomic() - begin a non-atomic section in an IST exception + * @regs: regs passed to the IST exception handler + * + * IST exception handlers normally cannot schedule. As a special + * exception, if the exception interrupted userspace code (i.e. + * user_mode_vm(regs) would return true) and the exception was not + * a double fault, it can be safe to schedule. ist_begin_non_atomic() + * begins a non-atomic section within an ist_enter()/ist_exit() region. + * Callers are responsible for enabling interrupts themselves inside + * the non-atomic section, and callers must call is_end_non_atomic() + * before ist_exit(). + */ +void ist_begin_non_atomic(struct pt_regs *regs) +{ + BUG_ON(!user_mode_vm(regs)); + + /* + * Sanity check: we need to be on the normal thread stack. This + * will catch asm bugs and any attempt to use ist_preempt_enable + * from double_fault. + */ + BUG_ON(((current_stack_pointer() ^ this_cpu_read_stable(kernel_stack)) + & ~(THREAD_SIZE - 1)) != 0); + + preempt_count_sub(HARDIRQ_OFFSET); +} + +/** + * ist_end_non_atomic() - begin a non-atomic section in an IST exception + * + * Ends a non-atomic section started with ist_begin_non_atomic(). + */ +void ist_end_non_atomic(void) +{ + preempt_count_add(HARDIRQ_OFFSET); +} + static nokprobe_inline int do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, struct pt_regs *regs, long error_code) @@ -251,6 +333,8 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) * end up promoting it to a doublefault. In that case, modify * the stack to make it look like we just entered the #GP * handler from user space, similar to bad_iret. + * + * No need for ist_enter here because we don't use RCU. */ if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY && regs->cs == __KERNEL_CS && @@ -263,12 +347,12 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */ regs->ip = (unsigned long)general_protection; regs->sp = (unsigned long)&normal_regs->orig_ax; + return; } #endif - exception_enter(); - /* Return not checked because double check cannot be ignored */ + ist_enter(regs); /* Discard prev_state because we won't return. */ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); tsk->thread.error_code = error_code; @@ -434,7 +518,7 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) if (poke_int3_handler(regs)) return; - prev_state = exception_enter(); + prev_state = ist_enter(regs); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) @@ -460,33 +544,20 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) preempt_conditional_cli(regs); debug_stack_usage_dec(); exit: - exception_exit(prev_state); + ist_exit(regs, prev_state); } NOKPROBE_SYMBOL(do_int3); #ifdef CONFIG_X86_64 /* - * Help handler running on IST stack to switch back to user stack - * for scheduling or signal handling. The actual stack switch is done in - * entry.S + * Help handler running on IST stack to switch off the IST stack if the + * interrupted code was in user mode. The actual stack switch is done in + * entry_64.S */ asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs) { - struct pt_regs *regs = eregs; - /* Did already sync */ - if (eregs == (struct pt_regs *)eregs->sp) - ; - /* Exception from user space */ - else if (user_mode(eregs)) - regs = task_pt_regs(current); - /* - * Exception from kernel and interrupts are enabled. Move to - * kernel process stack. - */ - else if (eregs->flags & X86_EFLAGS_IF) - regs = (struct pt_regs *)(eregs->sp -= sizeof(struct pt_regs)); - if (eregs != regs) - *regs = *eregs; + struct pt_regs *regs = task_pt_regs(current); + *regs = *eregs; return regs; } NOKPROBE_SYMBOL(sync_regs); @@ -554,7 +625,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) unsigned long dr6; int si_code; - prev_state = exception_enter(); + prev_state = ist_enter(regs); get_debugreg(dr6, 6); @@ -629,7 +700,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_dec(); exit: - exception_exit(prev_state); + ist_exit(regs, prev_state); } NOKPROBE_SYMBOL(do_debug); @@ -788,18 +859,16 @@ void math_state_restore(void) local_irq_disable(); } + /* Avoid __kernel_fpu_begin() right after __thread_fpu_begin() */ + kernel_fpu_disable(); __thread_fpu_begin(tsk); - - /* - * Paranoid restore. send a SIGSEGV if we fail to restore the state. - */ if (unlikely(restore_fpu_checking(tsk))) { drop_init_fpu(tsk); force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); - return; + } else { + tsk->thread.fpu_counter++; } - - tsk->thread.fpu_counter++; + kernel_fpu_enable(); } EXPORT_SYMBOL_GPL(math_state_restore); diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index f9d16ff56c6..7dc7ba577ec 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -40,6 +40,7 @@ config KVM select HAVE_KVM_MSI select HAVE_KVM_CPU_RELAX_INTERCEPT select KVM_VFIO + select SRCU ---help--- Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 8b977ebf938..bca0aa3a003 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -178,4 +178,15 @@ static __init int setup_hugepagesz(char *opt) return 1; } __setup("hugepagesz=", setup_hugepagesz); + +#ifdef CONFIG_CMA +static __init int gigantic_pages_init(void) +{ + /* With CMA we can allocate gigantic pages at runtime */ + if (cpu_has_gbpages && !size_to_hstate(1UL << PUD_SHIFT)) + hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); + return 0; +} +arch_initcall(gigantic_pages_init); +#endif #endif diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 079c3b6a3ff..649da47d382 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -608,7 +608,7 @@ void __init init_mem_mapping(void) * * * On x86, access has to be given to the first megabyte of ram because that area - * contains bios code and data regions used by X and dosemu and similar apps. + * contains BIOS code and data regions used by X and dosemu and similar apps. * Access has to be given to non-kernel-ram areas as well, these contain the PCI * mmio resources as well as potential bios/acpi data regions. */ diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index cfd1b132b8e..6ac273832f2 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -10,9 +10,6 @@ struct pci_root_info { struct acpi_device *bridge; char name[16]; - unsigned int res_num; - struct resource *res; - resource_size_t *res_offset; struct pci_sysdata sd; #ifdef CONFIG_PCI_MMCONFIG bool mcfg_added; @@ -218,130 +215,41 @@ static void teardown_mcfg_map(struct pci_root_info *info) } #endif -static acpi_status resource_to_addr(struct acpi_resource *resource, - struct acpi_resource_address64 *addr) -{ - acpi_status status; - struct acpi_resource_memory24 *memory24; - struct acpi_resource_memory32 *memory32; - struct acpi_resource_fixed_memory32 *fixed_memory32; - - memset(addr, 0, sizeof(*addr)); - switch (resource->type) { - case ACPI_RESOURCE_TYPE_MEMORY24: - memory24 = &resource->data.memory24; - addr->resource_type = ACPI_MEMORY_RANGE; - addr->minimum = memory24->minimum; - addr->address_length = memory24->address_length; - addr->maximum = addr->minimum + addr->address_length - 1; - return AE_OK; - case ACPI_RESOURCE_TYPE_MEMORY32: - memory32 = &resource->data.memory32; - addr->resource_type = ACPI_MEMORY_RANGE; - addr->minimum = memory32->minimum; - addr->address_length = memory32->address_length; - addr->maximum = addr->minimum + addr->address_length - 1; - return AE_OK; - case ACPI_RESOURCE_TYPE_FIXED_MEMORY32: - fixed_memory32 = &resource->data.fixed_memory32; - addr->resource_type = ACPI_MEMORY_RANGE; - addr->minimum = fixed_memory32->address; - addr->address_length = fixed_memory32->address_length; - addr->maximum = addr->minimum + addr->address_length - 1; - return AE_OK; - case ACPI_RESOURCE_TYPE_ADDRESS16: - case ACPI_RESOURCE_TYPE_ADDRESS32: - case ACPI_RESOURCE_TYPE_ADDRESS64: - status = acpi_resource_to_address64(resource, addr); - if (ACPI_SUCCESS(status) && - (addr->resource_type == ACPI_MEMORY_RANGE || - addr->resource_type == ACPI_IO_RANGE) && - addr->address_length > 0) { - return AE_OK; - } - break; - } - return AE_ERROR; -} - -static acpi_status count_resource(struct acpi_resource *acpi_res, void *data) +static void validate_resources(struct device *dev, struct list_head *crs_res, + unsigned long type) { - struct pci_root_info *info = data; - struct acpi_resource_address64 addr; - acpi_status status; - - status = resource_to_addr(acpi_res, &addr); - if (ACPI_SUCCESS(status)) - info->res_num++; - return AE_OK; -} - -static acpi_status setup_resource(struct acpi_resource *acpi_res, void *data) -{ - struct pci_root_info *info = data; - struct resource *res; - struct acpi_resource_address64 addr; - acpi_status status; - unsigned long flags; - u64 start, orig_end, end; - - status = resource_to_addr(acpi_res, &addr); - if (!ACPI_SUCCESS(status)) - return AE_OK; - - if (addr.resource_type == ACPI_MEMORY_RANGE) { - flags = IORESOURCE_MEM; - if (addr.info.mem.caching == ACPI_PREFETCHABLE_MEMORY) - flags |= IORESOURCE_PREFETCH; - } else if (addr.resource_type == ACPI_IO_RANGE) { - flags = IORESOURCE_IO; - } else - return AE_OK; - - start = addr.minimum + addr.translation_offset; - orig_end = end = addr.maximum + addr.translation_offset; - - /* Exclude non-addressable range or non-addressable portion of range */ - end = min(end, (u64)iomem_resource.end); - if (end <= start) { - dev_info(&info->bridge->dev, - "host bridge window [%#llx-%#llx] " - "(ignored, not CPU addressable)\n", start, orig_end); - return AE_OK; - } else if (orig_end != end) { - dev_info(&info->bridge->dev, - "host bridge window [%#llx-%#llx] " - "([%#llx-%#llx] ignored, not CPU addressable)\n", - start, orig_end, end + 1, orig_end); - } + LIST_HEAD(list); + struct resource *res1, *res2, *root = NULL; + struct resource_entry *tmp, *entry, *entry2; - res = &info->res[info->res_num]; - res->name = info->name; - res->flags = flags; - res->start = start; - res->end = end; - info->res_offset[info->res_num] = addr.translation_offset; - info->res_num++; + BUG_ON((type & (IORESOURCE_MEM | IORESOURCE_IO)) == 0); + root = (type & IORESOURCE_MEM) ? &iomem_resource : &ioport_resource; - if (!pci_use_crs) - dev_printk(KERN_DEBUG, &info->bridge->dev, - "host bridge window %pR (ignored)\n", res); + list_splice_init(crs_res, &list); + resource_list_for_each_entry_safe(entry, tmp, &list) { + bool free = false; + resource_size_t end; - return AE_OK; -} - -static void coalesce_windows(struct pci_root_info *info, unsigned long type) -{ - int i, j; - struct resource *res1, *res2; - - for (i = 0; i < info->res_num; i++) { - res1 = &info->res[i]; + res1 = entry->res; if (!(res1->flags & type)) - continue; + goto next; + + /* Exclude non-addressable range or non-addressable portion */ + end = min(res1->end, root->end); + if (end <= res1->start) { + dev_info(dev, "host bridge window %pR (ignored, not CPU addressable)\n", + res1); + free = true; + goto next; + } else if (res1->end != end) { + dev_info(dev, "host bridge window %pR ([%#llx-%#llx] ignored, not CPU addressable)\n", + res1, (unsigned long long)end + 1, + (unsigned long long)res1->end); + res1->end = end; + } - for (j = i + 1; j < info->res_num; j++) { - res2 = &info->res[j]; + resource_list_for_each_entry(entry2, crs_res) { + res2 = entry2->res; if (!(res2->flags & type)) continue; @@ -353,118 +261,92 @@ static void coalesce_windows(struct pci_root_info *info, unsigned long type) if (resource_overlaps(res1, res2)) { res2->start = min(res1->start, res2->start); res2->end = max(res1->end, res2->end); - dev_info(&info->bridge->dev, - "host bridge window expanded to %pR; %pR ignored\n", + dev_info(dev, "host bridge window expanded to %pR; %pR ignored\n", res2, res1); - res1->flags = 0; + free = true; + goto next; } } + +next: + resource_list_del(entry); + if (free) + resource_list_free_entry(entry); + else + resource_list_add_tail(entry, crs_res); } } static void add_resources(struct pci_root_info *info, - struct list_head *resources) + struct list_head *resources, + struct list_head *crs_res) { - int i; - struct resource *res, *root, *conflict; - - coalesce_windows(info, IORESOURCE_MEM); - coalesce_windows(info, IORESOURCE_IO); + struct resource_entry *entry, *tmp; + struct resource *res, *conflict, *root = NULL; - for (i = 0; i < info->res_num; i++) { - res = &info->res[i]; + validate_resources(&info->bridge->dev, crs_res, IORESOURCE_MEM); + validate_resources(&info->bridge->dev, crs_res, IORESOURCE_IO); + resource_list_for_each_entry_safe(entry, tmp, crs_res) { + res = entry->res; if (res->flags & IORESOURCE_MEM) root = &iomem_resource; else if (res->flags & IORESOURCE_IO) root = &ioport_resource; else - continue; + BUG_ON(res); conflict = insert_resource_conflict(root, res); - if (conflict) + if (conflict) { dev_info(&info->bridge->dev, "ignoring host bridge window %pR (conflicts with %s %pR)\n", res, conflict->name, conflict); - else - pci_add_resource_offset(resources, res, - info->res_offset[i]); + resource_list_destroy_entry(entry); + } } -} -static void free_pci_root_info_res(struct pci_root_info *info) -{ - kfree(info->res); - info->res = NULL; - kfree(info->res_offset); - info->res_offset = NULL; - info->res_num = 0; + list_splice_tail(crs_res, resources); } -static void __release_pci_root_info(struct pci_root_info *info) +static void release_pci_root_info(struct pci_host_bridge *bridge) { - int i; struct resource *res; + struct resource_entry *entry; + struct pci_root_info *info = bridge->release_data; - for (i = 0; i < info->res_num; i++) { - res = &info->res[i]; - - if (!res->parent) - continue; - - if (!(res->flags & (IORESOURCE_MEM | IORESOURCE_IO))) - continue; - - release_resource(res); + resource_list_for_each_entry(entry, &bridge->windows) { + res = entry->res; + if (res->parent && + (res->flags & (IORESOURCE_MEM | IORESOURCE_IO))) + release_resource(res); } - free_pci_root_info_res(info); - teardown_mcfg_map(info); - kfree(info); } -static void release_pci_root_info(struct pci_host_bridge *bridge) -{ - struct pci_root_info *info = bridge->release_data; - - __release_pci_root_info(info); -} - static void probe_pci_root_info(struct pci_root_info *info, struct acpi_device *device, - int busnum, int domain) + int busnum, int domain, + struct list_head *list) { - size_t size; + int ret; + struct resource_entry *entry; sprintf(info->name, "PCI Bus %04x:%02x", domain, busnum); info->bridge = device; - - info->res_num = 0; - acpi_walk_resources(device->handle, METHOD_NAME__CRS, count_resource, - info); - if (!info->res_num) - return; - - size = sizeof(*info->res) * info->res_num; - info->res = kzalloc_node(size, GFP_KERNEL, info->sd.node); - if (!info->res) { - info->res_num = 0; - return; - } - - size = sizeof(*info->res_offset) * info->res_num; - info->res_num = 0; - info->res_offset = kzalloc_node(size, GFP_KERNEL, info->sd.node); - if (!info->res_offset) { - kfree(info->res); - info->res = NULL; - return; - } - - acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource, - info); + ret = acpi_dev_get_resources(device, list, + acpi_dev_filter_resource_type_cb, + (void *)(IORESOURCE_IO | IORESOURCE_MEM)); + if (ret < 0) + dev_warn(&device->dev, + "failed to parse _CRS method, error code %d\n", ret); + else if (ret == 0) + dev_dbg(&device->dev, + "no IO and memory resources present in _CRS\n"); + else + resource_list_for_each_entry(entry, list) + entry->res->name = info->name; } struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) @@ -473,6 +355,8 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) struct pci_root_info *info; int domain = root->segment; int busnum = root->secondary.start; + struct resource_entry *res_entry; + LIST_HEAD(crs_res); LIST_HEAD(resources); struct pci_bus *bus; struct pci_sysdata *sd; @@ -520,18 +404,22 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) memcpy(bus->sysdata, sd, sizeof(*sd)); kfree(info); } else { - probe_pci_root_info(info, device, busnum, domain); - /* insert busn res at first */ pci_add_resource(&resources, &root->secondary); + /* * _CRS with no apertures is normal, so only fall back to * defaults or native bridge info if we're ignoring _CRS. */ - if (pci_use_crs) - add_resources(info, &resources); - else { - free_pci_root_info_res(info); + probe_pci_root_info(info, device, busnum, domain, &crs_res); + if (pci_use_crs) { + add_resources(info, &resources, &crs_res); + } else { + resource_list_for_each_entry(res_entry, &crs_res) + dev_printk(KERN_DEBUG, &device->dev, + "host bridge window %pR (ignored)\n", + res_entry->res); + resource_list_free(&crs_res); x86_pci_root_bus_resources(busnum, &resources); } @@ -546,8 +434,9 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) to_pci_host_bridge(bus->bridge), release_pci_root_info, info); } else { - pci_free_resource_list(&resources); - __release_pci_root_info(info); + resource_list_free(&resources); + teardown_mcfg_map(info); + kfree(info); } } diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c index f3a2cfc1412..7bcf06a7cd1 100644 --- a/arch/x86/pci/bus_numa.c +++ b/arch/x86/pci/bus_numa.c @@ -31,7 +31,7 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources) { struct pci_root_info *info = x86_find_pci_root_info(bus); struct pci_root_res *root_res; - struct pci_host_bridge_window *window; + struct resource_entry *window; bool found = false; if (!info) @@ -41,7 +41,7 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources) bus); /* already added by acpi ? */ - list_for_each_entry(window, resources, list) + resource_list_for_each_entry(window, resources) if (window->res->flags & IORESOURCE_BUS) { found = true; break; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 2fb384724eb..3d2612b6869 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -513,6 +513,31 @@ void __init pcibios_set_cache_line_size(void) } } +/* + * Some device drivers assume dev->irq won't change after calling + * pci_disable_device(). So delay releasing of IRQ resource to driver + * unbinding time. Otherwise it will break PM subsystem and drivers + * like xen-pciback etc. + */ +static int pci_irq_notifier(struct notifier_block *nb, unsigned long action, + void *data) +{ + struct pci_dev *dev = to_pci_dev(data); + + if (action != BUS_NOTIFY_UNBOUND_DRIVER) + return NOTIFY_DONE; + + if (pcibios_disable_irq) + pcibios_disable_irq(dev); + + return NOTIFY_OK; +} + +static struct notifier_block pci_irq_nb = { + .notifier_call = pci_irq_notifier, + .priority = INT_MIN, +}; + int __init pcibios_init(void) { if (!raw_pci_ops) { @@ -525,6 +550,9 @@ int __init pcibios_init(void) if (pci_bf_sort >= pci_force_bf) pci_sort_breadthfirst(); + + bus_register_notifier(&pci_bus_type, &pci_irq_nb); + return 0; } @@ -683,12 +711,6 @@ int pcibios_enable_device(struct pci_dev *dev, int mask) return 0; } -void pcibios_disable_device (struct pci_dev *dev) -{ - if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq) - pcibios_disable_irq(dev); -} - int pci_ext_cfg_avail(void) { if (raw_pci_ext_ops) diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 44b9271580b..efb849323c7 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -234,10 +234,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) static void intel_mid_pci_irq_disable(struct pci_dev *dev) { - if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed && - dev->irq > 0) { + if (dev->irq_managed && dev->irq > 0) { mp_unmap_irq(dev->irq); dev->irq_managed = 0; + dev->irq = 0; } } @@ -293,7 +293,6 @@ static void mrst_power_off_unused_dev(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0801, mrst_power_off_unused_dev); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0809, mrst_power_off_unused_dev); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x080C, mrst_power_off_unused_dev); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0812, mrst_power_off_unused_dev); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0815, mrst_power_off_unused_dev); /* diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 5dc6ca5e174..e71b3dbd87b 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1256,22 +1256,9 @@ static int pirq_enable_irq(struct pci_dev *dev) return 0; } -bool mp_should_keep_irq(struct device *dev) -{ - if (dev->power.is_prepared) - return true; -#ifdef CONFIG_PM - if (dev->power.runtime_status == RPM_SUSPENDING) - return true; -#endif - - return false; -} - static void pirq_disable_irq(struct pci_dev *dev) { - if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) && - dev->irq_managed && dev->irq) { + if (io_apic_assign_pci_irqs && dev->irq_managed && dev->irq) { mp_unmap_irq(dev->irq); dev->irq = 0; dev->irq_managed = 0; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 326198a4434..dd30b7e08bc 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -397,12 +397,12 @@ static acpi_status check_mcfg_resource(struct acpi_resource *res, void *data) status = acpi_resource_to_address64(res, &address); if (ACPI_FAILURE(status) || - (address.address_length <= 0) || + (address.address.address_length <= 0) || (address.resource_type != ACPI_MEMORY_RANGE)) return AE_OK; - if ((mcfg_res->start >= address.minimum) && - (mcfg_res->end < (address.minimum + address.address_length))) { + if ((mcfg_res->start >= address.address.minimum) && + (mcfg_res->end < (address.address.minimum + address.address.address_length))) { mcfg_res->flags = 1; return AE_CTRL_TERMINATE; } @@ -610,6 +610,32 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header) return 0; } +#ifdef CONFIG_ACPI_APEI +extern int (*arch_apei_filter_addr)(int (*func)(__u64 start, __u64 size, + void *data), void *data); + +static int pci_mmcfg_for_each_region(int (*func)(__u64 start, __u64 size, + void *data), void *data) +{ + struct pci_mmcfg_region *cfg; + int rc; + + if (list_empty(&pci_mmcfg_list)) + return 0; + + list_for_each_entry(cfg, &pci_mmcfg_list, list) { + rc = func(cfg->res.start, resource_size(&cfg->res), data); + if (rc) + return rc; + } + + return 0; +} +#define set_apei_filter() (arch_apei_filter_addr = pci_mmcfg_for_each_region) +#else +#define set_apei_filter() +#endif + static void __init __pci_mmcfg_init(int early) { pci_mmcfg_reject_broken(early); @@ -644,6 +670,8 @@ void __init pci_mmcfg_early_init(void) else acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); __pci_mmcfg_init(1); + + set_apei_filter(); } } diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 9098d880c47..d22f4b5bbc0 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -298,12 +298,16 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) map_irq.entry_nr = nvec; } else if (type == PCI_CAP_ID_MSIX) { int pos; + unsigned long flags; u32 table_offset, bir; pos = dev->msix_cap; pci_read_config_dword(dev, pos + PCI_MSIX_TABLE, &table_offset); bir = (u8)(table_offset & PCI_MSIX_TABLE_BIR); + flags = pci_resource_flags(dev, bir); + if (!flags || (flags & IORESOURCE_UNSET)) + return -EINVAL; map_irq.table_base = pci_resource_start(dev, bir); map_irq.entry_nr = msidesc->msi_attrib.entry_nr; diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 5a4affe025e..09297c8e1fc 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -205,4 +205,4 @@ $(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE PHONY += vdso_install $(vdso_img_insttargets) vdso_install: $(vdso_img_insttargets) FORCE -clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80* +clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80* vdso64* diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 5c1f9ace7ae..adca9e2b655 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1489,7 +1489,7 @@ static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) native_set_pte(ptep, pte); } -static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) +static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn) { struct mmuext_op op; op.cmd = cmd; @@ -1657,7 +1657,7 @@ void __init xen_reserve_top(void) * Like __va(), but returns address in the kernel mapping (which is * all we have until the physical memory mapping has been set up. */ -static void *__ka(phys_addr_t paddr) +static void * __init __ka(phys_addr_t paddr) { #ifdef CONFIG_X86_64 return (void *)(paddr + __START_KERNEL_map); @@ -1667,7 +1667,7 @@ static void *__ka(phys_addr_t paddr) } /* Convert a machine address to physical address */ -static unsigned long m2p(phys_addr_t maddr) +static unsigned long __init m2p(phys_addr_t maddr) { phys_addr_t paddr; @@ -1678,13 +1678,14 @@ static unsigned long m2p(phys_addr_t maddr) } /* Convert a machine address to kernel virtual */ -static void *m2v(phys_addr_t maddr) +static void * __init m2v(phys_addr_t maddr) { return __ka(m2p(maddr)); } /* Set the page permissions on an identity-mapped pages */ -static void set_page_prot_flags(void *addr, pgprot_t prot, unsigned long flags) +static void __init set_page_prot_flags(void *addr, pgprot_t prot, + unsigned long flags) { unsigned long pfn = __pa(addr) >> PAGE_SHIFT; pte_t pte = pfn_pte(pfn, prot); @@ -1696,7 +1697,7 @@ static void set_page_prot_flags(void *addr, pgprot_t prot, unsigned long flags) if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags)) BUG(); } -static void set_page_prot(void *addr, pgprot_t prot) +static void __init set_page_prot(void *addr, pgprot_t prot) { return set_page_prot_flags(addr, prot, UVMF_NONE); } @@ -1733,10 +1734,8 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) { pte_t pte; -#ifdef CONFIG_X86_32 if (pfn > max_pfn_mapped) max_pfn_mapped = pfn; -#endif if (!pte_none(pte_page[pteidx])) continue; @@ -1769,7 +1768,7 @@ void __init xen_setup_machphys_mapping(void) } #ifdef CONFIG_X86_64 -static void convert_pfn_mfn(void *v) +static void __init convert_pfn_mfn(void *v) { pte_t *pte = v; int i; diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 70fb5075c90..f18fd1d411f 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -84,8 +84,6 @@ #define PMDS_PER_MID_PAGE (P2M_MID_PER_PAGE / PTRS_PER_PTE) -static void __init m2p_override_init(void); - unsigned long *xen_p2m_addr __read_mostly; EXPORT_SYMBOL_GPL(xen_p2m_addr); unsigned long xen_p2m_size __read_mostly; @@ -402,8 +400,6 @@ void __init xen_vmalloc_p2m_tree(void) xen_p2m_size = xen_max_p2m_pfn; xen_inv_extra_mem(); - - m2p_override_init(); } unsigned long get_phys_to_machine(unsigned long pfn) @@ -652,100 +648,21 @@ bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) return true; } -#define M2P_OVERRIDE_HASH_SHIFT 10 -#define M2P_OVERRIDE_HASH (1 << M2P_OVERRIDE_HASH_SHIFT) - -static struct list_head *m2p_overrides; -static DEFINE_SPINLOCK(m2p_override_lock); - -static void __init m2p_override_init(void) -{ - unsigned i; - - m2p_overrides = alloc_bootmem_align( - sizeof(*m2p_overrides) * M2P_OVERRIDE_HASH, - sizeof(unsigned long)); - - for (i = 0; i < M2P_OVERRIDE_HASH; i++) - INIT_LIST_HEAD(&m2p_overrides[i]); -} - -static unsigned long mfn_hash(unsigned long mfn) -{ - return hash_long(mfn, M2P_OVERRIDE_HASH_SHIFT); -} - -/* Add an MFN override for a particular page */ -static int m2p_add_override(unsigned long mfn, struct page *page, - struct gnttab_map_grant_ref *kmap_op) -{ - unsigned long flags; - unsigned long pfn; - unsigned long uninitialized_var(address); - unsigned level; - pte_t *ptep = NULL; - - pfn = page_to_pfn(page); - if (!PageHighMem(page)) { - address = (unsigned long)__va(pfn << PAGE_SHIFT); - ptep = lookup_address(address, &level); - if (WARN(ptep == NULL || level != PG_LEVEL_4K, - "m2p_add_override: pfn %lx not mapped", pfn)) - return -EINVAL; - } - - if (kmap_op != NULL) { - if (!PageHighMem(page)) { - struct multicall_space mcs = - xen_mc_entry(sizeof(*kmap_op)); - - MULTI_grant_table_op(mcs.mc, - GNTTABOP_map_grant_ref, kmap_op, 1); - - xen_mc_issue(PARAVIRT_LAZY_MMU); - } - } - spin_lock_irqsave(&m2p_override_lock, flags); - list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]); - spin_unlock_irqrestore(&m2p_override_lock, flags); - - /* p2m(m2p(mfn)) == mfn: the mfn is already present somewhere in - * this domain. Set the FOREIGN_FRAME_BIT in the p2m for the other - * pfn so that the following mfn_to_pfn(mfn) calls will return the - * pfn from the m2p_override (the backend pfn) instead. - * We need to do this because the pages shared by the frontend - * (xen-blkfront) can be already locked (lock_page, called by - * do_read_cache_page); when the userspace backend tries to use them - * with direct_IO, mfn_to_pfn returns the pfn of the frontend, so - * do_blockdev_direct_IO is going to try to lock the same pages - * again resulting in a deadlock. - * As a side effect get_user_pages_fast might not be safe on the - * frontend pages while they are being shared with the backend, - * because mfn_to_pfn (that ends up being called by GUPF) will - * return the backend pfn rather than the frontend pfn. */ - pfn = mfn_to_pfn_no_overrides(mfn); - if (__pfn_to_mfn(pfn) == mfn) - set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)); - - return 0; -} - int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, struct gnttab_map_grant_ref *kmap_ops, struct page **pages, unsigned int count) { int i, ret = 0; - bool lazy = false; pte_t *pte; if (xen_feature(XENFEAT_auto_translated_physmap)) return 0; - if (kmap_ops && - !in_interrupt() && - paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { - arch_enter_lazy_mmu_mode(); - lazy = true; + if (kmap_ops) { + ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, + kmap_ops, count); + if (ret) + goto out; } for (i = 0; i < count; i++) { @@ -764,170 +681,28 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, } pfn = page_to_pfn(pages[i]); - WARN_ON(PagePrivate(pages[i])); - SetPagePrivate(pages[i]); - set_page_private(pages[i], mfn); - pages[i]->index = pfn_to_mfn(pfn); + WARN(pfn_to_mfn(pfn) != INVALID_P2M_ENTRY, "page must be ballooned"); if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) { ret = -ENOMEM; goto out; } - - if (kmap_ops) { - ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]); - if (ret) - goto out; - } } out: - if (lazy) - arch_leave_lazy_mmu_mode(); - return ret; } EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping); -static struct page *m2p_find_override(unsigned long mfn) -{ - unsigned long flags; - struct list_head *bucket; - struct page *p, *ret; - - if (unlikely(!m2p_overrides)) - return NULL; - - ret = NULL; - bucket = &m2p_overrides[mfn_hash(mfn)]; - - spin_lock_irqsave(&m2p_override_lock, flags); - - list_for_each_entry(p, bucket, lru) { - if (page_private(p) == mfn) { - ret = p; - break; - } - } - - spin_unlock_irqrestore(&m2p_override_lock, flags); - - return ret; -} - -static int m2p_remove_override(struct page *page, - struct gnttab_map_grant_ref *kmap_op, - unsigned long mfn) -{ - unsigned long flags; - unsigned long pfn; - unsigned long uninitialized_var(address); - unsigned level; - pte_t *ptep = NULL; - - pfn = page_to_pfn(page); - - if (!PageHighMem(page)) { - address = (unsigned long)__va(pfn << PAGE_SHIFT); - ptep = lookup_address(address, &level); - - if (WARN(ptep == NULL || level != PG_LEVEL_4K, - "m2p_remove_override: pfn %lx not mapped", pfn)) - return -EINVAL; - } - - spin_lock_irqsave(&m2p_override_lock, flags); - list_del(&page->lru); - spin_unlock_irqrestore(&m2p_override_lock, flags); - - if (kmap_op != NULL) { - if (!PageHighMem(page)) { - struct multicall_space mcs; - struct gnttab_unmap_and_replace *unmap_op; - struct page *scratch_page = get_balloon_scratch_page(); - unsigned long scratch_page_address = (unsigned long) - __va(page_to_pfn(scratch_page) << PAGE_SHIFT); - - /* - * It might be that we queued all the m2p grant table - * hypercalls in a multicall, then m2p_remove_override - * get called before the multicall has actually been - * issued. In this case handle is going to -1 because - * it hasn't been modified yet. - */ - if (kmap_op->handle == -1) - xen_mc_flush(); - /* - * Now if kmap_op->handle is negative it means that the - * hypercall actually returned an error. - */ - if (kmap_op->handle == GNTST_general_error) { - pr_warn("m2p_remove_override: pfn %lx mfn %lx, failed to modify kernel mappings", - pfn, mfn); - put_balloon_scratch_page(); - return -1; - } - - xen_mc_batch(); - - mcs = __xen_mc_entry( - sizeof(struct gnttab_unmap_and_replace)); - unmap_op = mcs.args; - unmap_op->host_addr = kmap_op->host_addr; - unmap_op->new_addr = scratch_page_address; - unmap_op->handle = kmap_op->handle; - - MULTI_grant_table_op(mcs.mc, - GNTTABOP_unmap_and_replace, unmap_op, 1); - - mcs = __xen_mc_entry(0); - MULTI_update_va_mapping(mcs.mc, scratch_page_address, - pfn_pte(page_to_pfn(scratch_page), - PAGE_KERNEL_RO), 0); - - xen_mc_issue(PARAVIRT_LAZY_MMU); - - kmap_op->host_addr = 0; - put_balloon_scratch_page(); - } - } - - /* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present - * somewhere in this domain, even before being added to the - * m2p_override (see comment above in m2p_add_override). - * If there are no other entries in the m2p_override corresponding - * to this mfn, then remove the FOREIGN_FRAME_BIT from the p2m for - * the original pfn (the one shared by the frontend): the backend - * cannot do any IO on this page anymore because it has been - * unshared. Removing the FOREIGN_FRAME_BIT from the p2m entry of - * the original pfn causes mfn_to_pfn(mfn) to return the frontend - * pfn again. */ - mfn &= ~FOREIGN_FRAME_BIT; - pfn = mfn_to_pfn_no_overrides(mfn); - if (__pfn_to_mfn(pfn) == FOREIGN_FRAME(mfn) && - m2p_find_override(mfn) == NULL) - set_phys_to_machine(pfn, mfn); - - return 0; -} - int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, - struct gnttab_map_grant_ref *kmap_ops, + struct gnttab_unmap_grant_ref *kunmap_ops, struct page **pages, unsigned int count) { int i, ret = 0; - bool lazy = false; if (xen_feature(XENFEAT_auto_translated_physmap)) return 0; - if (kmap_ops && - !in_interrupt() && - paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { - arch_enter_lazy_mmu_mode(); - lazy = true; - } - for (i = 0; i < count; i++) { unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i])); unsigned long pfn = page_to_pfn(pages[i]); @@ -937,36 +712,16 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, goto out; } - set_page_private(pages[i], INVALID_P2M_ENTRY); - WARN_ON(!PagePrivate(pages[i])); - ClearPagePrivate(pages[i]); - set_phys_to_machine(pfn, pages[i]->index); - - if (kmap_ops) - ret = m2p_remove_override(pages[i], &kmap_ops[i], mfn); - if (ret) - goto out; + set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } - + if (kunmap_ops) + ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, + kunmap_ops, count); out: - if (lazy) - arch_leave_lazy_mmu_mode(); return ret; } EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping); -unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn) -{ - struct page *p = m2p_find_override(mfn); - unsigned long ret = pfn; - - if (p) - ret = page_to_pfn(p); - - return ret; -} -EXPORT_SYMBOL_GPL(m2p_find_override_pfn); - #ifdef CONFIG_XEN_DEBUG_FS #include <linux/debugfs.h> #include "debugfs.h" diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 865e56cea7a..55f388ef481 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -32,16 +32,6 @@ #include "p2m.h" #include "mmu.h" -/* These are code, but not functions. Defined in entry.S */ -extern const char xen_hypervisor_callback[]; -extern const char xen_failsafe_callback[]; -#ifdef CONFIG_X86_64 -extern asmlinkage void nmi(void); -#endif -extern void xen_sysenter_target(void); -extern void xen_syscall_target(void); -extern void xen_syscall32_target(void); - /* Amount of extra memory space we add to the e820 ranges */ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; @@ -74,7 +64,7 @@ static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY; */ #define EXTRA_MEM_RATIO (10) -static void __init xen_add_extra_mem(u64 start, u64 size) +static void __init xen_add_extra_mem(phys_addr_t start, phys_addr_t size) { int i; @@ -97,10 +87,10 @@ static void __init xen_add_extra_mem(u64 start, u64 size) memblock_reserve(start, size); } -static void __init xen_del_extra_mem(u64 start, u64 size) +static void __init xen_del_extra_mem(phys_addr_t start, phys_addr_t size) { int i; - u64 start_r, size_r; + phys_addr_t start_r, size_r; for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { start_r = xen_extra_mem[i].start; @@ -267,7 +257,7 @@ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, static void __init xen_update_mem_tables(unsigned long pfn, unsigned long mfn) { struct mmu_update update = { - .ptr = ((unsigned long long)mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE, + .ptr = ((uint64_t)mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE, .val = pfn }; @@ -545,20 +535,21 @@ static unsigned long __init xen_get_max_pages(void) return min(max_pages, MAX_DOMAIN_PAGES); } -static void xen_align_and_add_e820_region(u64 start, u64 size, int type) +static void __init xen_align_and_add_e820_region(phys_addr_t start, + phys_addr_t size, int type) { - u64 end = start + size; + phys_addr_t end = start + size; /* Align RAM regions to page boundaries. */ if (type == E820_RAM) { start = PAGE_ALIGN(start); - end &= ~((u64)PAGE_SIZE - 1); + end &= ~((phys_addr_t)PAGE_SIZE - 1); } e820_add_region(start, end - start, type); } -void xen_ignore_unusable(struct e820entry *list, size_t map_size) +static void __init xen_ignore_unusable(struct e820entry *list, size_t map_size) { struct e820entry *entry; unsigned int i; @@ -577,7 +568,7 @@ char * __init xen_memory_setup(void) static struct e820entry map[E820MAX] __initdata; unsigned long max_pfn = xen_start_info->nr_pages; - unsigned long long mem_end; + phys_addr_t mem_end; int rc; struct xen_memory_map memmap; unsigned long max_pages; @@ -652,16 +643,16 @@ char * __init xen_memory_setup(void) extra_pages); i = 0; while (i < memmap.nr_entries) { - u64 addr = map[i].addr; - u64 size = map[i].size; + phys_addr_t addr = map[i].addr; + phys_addr_t size = map[i].size; u32 type = map[i].type; if (type == E820_RAM) { if (addr < mem_end) { size = min(size, mem_end - addr); } else if (extra_pages) { - size = min(size, (u64)extra_pages * PAGE_SIZE); - extra_pages -= size / PAGE_SIZE; + size = min(size, PFN_PHYS(extra_pages)); + extra_pages -= PFN_DOWN(size); xen_add_extra_mem(addr, size); xen_max_p2m_pfn = PFN_DOWN(addr + size); } else diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 4c071aeb841..08e8489c47f 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -507,7 +507,7 @@ static int xen_cpu_disable(void) static void xen_cpu_die(unsigned int cpu) { while (xen_pv_domain() && HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) { - current->state = TASK_UNINTERRUPTIBLE; + __set_current_state(TASK_UNINTERRUPTIBLE); schedule_timeout(HZ/10); } diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 69087341d9a..55da33b1d51 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -479,6 +479,10 @@ static void __init xen_time_init(void) int cpu = smp_processor_id(); struct timespec tp; + /* As Dom0 is never moved, no penalty on using TSC there */ + if (xen_initial_domain()) + xen_clocksource.rating = 275; + clocksource_register_hz(&xen_clocksource, NSEC_PER_SEC); if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL) == 0) { diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 5686bd9d58c..9e195c68354 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -10,6 +10,12 @@ extern const char xen_hypervisor_callback[]; extern const char xen_failsafe_callback[]; +void xen_sysenter_target(void); +#ifdef CONFIG_X86_64 +void xen_syscall_target(void); +void xen_syscall32_target(void); +#endif + extern void *xen_initial_gdt; struct trap_info; diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index 872bf0194e6..01b80dce9d6 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -89,8 +89,6 @@ * (PAGE_NONE)| PPN | 0 | 00 | ADW | 01 | 11 | 11 | * +-----------------------------------------+ * swap | index | type | 01 | 11 | 00 | - * +- - - - - - - - - - - - - - - - - - - - -+ - * file | file offset | 01 | 11 | 10 | * +-----------------------------------------+ * * For T1050 hardware and earlier the layout differs for present and (PAGE_NONE) @@ -111,7 +109,6 @@ * index swap offset / PAGE_SIZE (bit 11-31: 21 bits -> 8 GB) * (note that the index is always non-zero) * type swap type (5 bits -> 32 types) - * file offset 26-bit offset into the file, in increments of PAGE_SIZE * * Notes: * - (PROT_NONE) is a special case of 'present' but causes an exception for @@ -144,7 +141,6 @@ #define _PAGE_HW_VALID 0x00 #define _PAGE_NONE 0x0f #endif -#define _PAGE_FILE (1<<1) /* file mapped page, only if !present */ #define _PAGE_USER (1<<4) /* user access (ring=1) */ @@ -260,7 +256,6 @@ static inline void pgtable_cache_init(void) { } static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_WRITABLE; } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } -static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } static inline int pte_special(pte_t pte) { return 0; } static inline pte_t pte_wrprotect(pte_t pte) @@ -390,11 +385,6 @@ ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#define PTE_FILE_MAX_BITS 26 -#define pte_to_pgoff(pte) (pte_val(pte) >> 6) -#define pgoff_to_pte(off) \ - ((pte_t) { ((off) << 6) | _PAGE_CA_INVALID | _PAGE_FILE | _PAGE_USER }) - #endif /* !defined (__ASSEMBLY__) */ diff --git a/block/partitions/efi.c b/block/partitions/efi.c index 56d08fd75b1..26cb624ace0 100644 --- a/block/partitions/efi.c +++ b/block/partitions/efi.c @@ -715,7 +715,7 @@ int efi_partition(struct parsed_partitions *state) state->parts[i + 1].flags = ADDPART_FLAG_RAID; info = &state->parts[i + 1].info; - efi_guid_unparse(&ptes[i].unique_partition_guid, info->uuid); + efi_guid_to_str(&ptes[i].unique_partition_guid, info->uuid); /* Naively convert UTF16-LE to 7 bits. */ label_max = min(ARRAY_SIZE(info->volname) - 1, diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 8951cefb0a9..e6c3ddd9266 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -315,6 +315,12 @@ config ACPI_HOTPLUG_MEMORY To compile this driver as a module, choose M here: the module will be called acpi_memhotplug. +config ACPI_HOTPLUG_IOAPIC + bool + depends on PCI + depends on X86_IO_APIC + default y + config ACPI_SBS tristate "Smart Battery System" depends on X86 diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index f74317cc1ca..b18cd2151dd 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -40,7 +40,7 @@ acpi-$(CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC) += processor_pdc.o acpi-y += ec.o acpi-$(CONFIG_ACPI_DOCK) += dock.o acpi-y += pci_root.o pci_link.o pci_irq.o -acpi-y += acpi_lpss.o +acpi-y += acpi_lpss.o acpi_apd.o acpi-y += acpi_platform.o acpi-y += acpi_pnp.o acpi-y += int340x_thermal.o @@ -70,6 +70,7 @@ obj-$(CONFIG_ACPI_PROCESSOR) += processor.o obj-y += container.o obj-$(CONFIG_ACPI_THERMAL) += thermal.o obj-y += acpi_memhotplug.o +obj-$(CONFIG_ACPI_HOTPLUG_IOAPIC) += ioapic.o obj-$(CONFIG_ACPI_BATTERY) += battery.o obj-$(CONFIG_ACPI_SBS) += sbshc.o obj-$(CONFIG_ACPI_SBS) += sbs.o diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c new file mode 100644 index 00000000000..3984ea96e5f --- /dev/null +++ b/drivers/acpi/acpi_apd.c @@ -0,0 +1,150 @@ +/* + * AMD ACPI support for ACPI2platform device. + * + * Copyright (c) 2014,2015 AMD Corporation. + * Authors: Ken Xue <Ken.Xue@amd.com> + * Wu, Jeff <Jeff.Wu@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/clk-provider.h> +#include <linux/platform_device.h> +#include <linux/pm_domain.h> +#include <linux/clkdev.h> +#include <linux/acpi.h> +#include <linux/err.h> +#include <linux/clk.h> +#include <linux/pm.h> + +#include "internal.h" + +ACPI_MODULE_NAME("acpi_apd"); +struct apd_private_data; + +/** + * ACPI_APD_SYSFS : add device attributes in sysfs + * ACPI_APD_PM : attach power domain to device + */ +#define ACPI_APD_SYSFS BIT(0) +#define ACPI_APD_PM BIT(1) + +/** + * struct apd_device_desc - a descriptor for apd device + * @flags: device flags like %ACPI_APD_SYSFS, %ACPI_APD_PM + * @fixed_clk_rate: fixed rate input clock source for acpi device; + * 0 means no fixed rate input clock source + * @setup: a hook routine to set device resource during create platform device + * + * Device description defined as acpi_device_id.driver_data + */ +struct apd_device_desc { + unsigned int flags; + unsigned int fixed_clk_rate; + int (*setup)(struct apd_private_data *pdata); +}; + +struct apd_private_data { + struct clk *clk; + struct acpi_device *adev; + const struct apd_device_desc *dev_desc; +}; + +#ifdef CONFIG_X86_AMD_PLATFORM_DEVICE +#define APD_ADDR(desc) ((unsigned long)&desc) + +static int acpi_apd_setup(struct apd_private_data *pdata) +{ + const struct apd_device_desc *dev_desc = pdata->dev_desc; + struct clk *clk = ERR_PTR(-ENODEV); + + if (dev_desc->fixed_clk_rate) { + clk = clk_register_fixed_rate(&pdata->adev->dev, + dev_name(&pdata->adev->dev), + NULL, CLK_IS_ROOT, + dev_desc->fixed_clk_rate); + clk_register_clkdev(clk, NULL, dev_name(&pdata->adev->dev)); + pdata->clk = clk; + } + + return 0; +} + +static struct apd_device_desc cz_i2c_desc = { + .setup = acpi_apd_setup, + .fixed_clk_rate = 133000000, +}; + +static struct apd_device_desc cz_uart_desc = { + .setup = acpi_apd_setup, + .fixed_clk_rate = 48000000, +}; + +#else + +#define APD_ADDR(desc) (0UL) + +#endif /* CONFIG_X86_AMD_PLATFORM_DEVICE */ + +/** +* Create platform device during acpi scan attach handle. +* Return value > 0 on success of creating device. +*/ +static int acpi_apd_create_device(struct acpi_device *adev, + const struct acpi_device_id *id) +{ + const struct apd_device_desc *dev_desc = (void *)id->driver_data; + struct apd_private_data *pdata; + struct platform_device *pdev; + int ret; + + if (!dev_desc) { + pdev = acpi_create_platform_device(adev); + return IS_ERR_OR_NULL(pdev) ? PTR_ERR(pdev) : 1; + } + + pdata = kzalloc(sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return -ENOMEM; + + pdata->adev = adev; + pdata->dev_desc = dev_desc; + + if (dev_desc->setup) { + ret = dev_desc->setup(pdata); + if (ret) + goto err_out; + } + + adev->driver_data = pdata; + pdev = acpi_create_platform_device(adev); + if (!IS_ERR_OR_NULL(pdev)) + return 1; + + ret = PTR_ERR(pdev); + adev->driver_data = NULL; + + err_out: + kfree(pdata); + return ret; +} + +static const struct acpi_device_id acpi_apd_device_ids[] = { + /* Generic apd devices */ + { "AMD0010", APD_ADDR(cz_i2c_desc) }, + { "AMD0020", APD_ADDR(cz_uart_desc) }, + { "AMD0030", }, + { } +}; + +static struct acpi_scan_handler apd_handler = { + .ids = acpi_apd_device_ids, + .attach = acpi_apd_create_device, +}; + +void __init acpi_apd_init(void) +{ + acpi_scan_add_handler(&apd_handler); +} diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index e75737fd7ee..02e835f3cf8 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -125,7 +125,7 @@ static struct lpss_device_desc lpt_dev_desc = { }; static struct lpss_device_desc lpt_i2c_dev_desc = { - .flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_LTR, + .flags = LPSS_CLK | LPSS_LTR, .prv_offset = 0x800, }; @@ -307,7 +307,7 @@ static int acpi_lpss_create_device(struct acpi_device *adev, { struct lpss_device_desc *dev_desc; struct lpss_private_data *pdata; - struct resource_list_entry *rentry; + struct resource_entry *rentry; struct list_head resource_list; struct platform_device *pdev; int ret; @@ -327,13 +327,15 @@ static int acpi_lpss_create_device(struct acpi_device *adev, goto err_out; list_for_each_entry(rentry, &resource_list, node) - if (resource_type(&rentry->res) == IORESOURCE_MEM) { + if (resource_type(rentry->res) == IORESOURCE_MEM) { if (dev_desc->prv_size_override) pdata->mmio_size = dev_desc->prv_size_override; else - pdata->mmio_size = resource_size(&rentry->res); - pdata->mmio_base = ioremap(rentry->res.start, + pdata->mmio_size = resource_size(rentry->res); + pdata->mmio_base = ioremap(rentry->res->start, pdata->mmio_size); + if (!pdata->mmio_base) + goto err_out; break; } diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index 23e2319ead4..ee28f4d1562 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -101,8 +101,8 @@ acpi_memory_get_resource(struct acpi_resource *resource, void *context) /* Can we combine the resource range information? */ if ((info->caching == address64.info.mem.caching) && (info->write_protect == address64.info.mem.write_protect) && - (info->start_addr + info->length == address64.minimum)) { - info->length += address64.address_length; + (info->start_addr + info->length == address64.address.minimum)) { + info->length += address64.address.address_length; return AE_OK; } } @@ -114,8 +114,8 @@ acpi_memory_get_resource(struct acpi_resource *resource, void *context) INIT_LIST_HEAD(&new->list); new->caching = address64.info.mem.caching; new->write_protect = address64.info.mem.write_protect; - new->start_addr = address64.minimum; - new->length = address64.address_length; + new->start_addr = address64.address.minimum; + new->length = address64.address.address_length; list_add_tail(&new->list, &mem_device->res_list); return AE_OK; diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c index 6ba8beb6b9d..1284138e42a 100644 --- a/drivers/acpi/acpi_platform.c +++ b/drivers/acpi/acpi_platform.c @@ -45,7 +45,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev) struct platform_device *pdev = NULL; struct acpi_device *acpi_parent; struct platform_device_info pdevinfo; - struct resource_list_entry *rentry; + struct resource_entry *rentry; struct list_head resource_list; struct resource *resources = NULL; int count; @@ -71,7 +71,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev) } count = 0; list_for_each_entry(rentry, &resource_list, node) - resources[count++] = rentry->res; + resources[count++] = *rentry->res; acpi_dev_free_resource_list(&resource_list); } diff --git a/drivers/acpi/acpica/acapps.h b/drivers/acpi/acpica/acapps.h index 3d2c88289da..d863016565b 100644 --- a/drivers/acpi/acpica/acapps.h +++ b/drivers/acpi/acpica/acapps.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -47,7 +47,7 @@ /* Common info for tool signons */ #define ACPICA_NAME "Intel ACPI Component Architecture" -#define ACPICA_COPYRIGHT "Copyright (c) 2000 - 2014 Intel Corporation" +#define ACPICA_COPYRIGHT "Copyright (c) 2000 - 2015 Intel Corporation" #if ACPI_MACHINE_WIDTH == 64 #define ACPI_WIDTH "-64" diff --git a/drivers/acpi/acpica/accommon.h b/drivers/acpi/acpica/accommon.h index 6f1c616910a..853aa2dbdb6 100644 --- a/drivers/acpi/acpica/accommon.h +++ b/drivers/acpi/acpica/accommon.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h index 1d026ff1683..4169bb87a99 100644 --- a/drivers/acpi/acpica/acdebug.h +++ b/drivers/acpi/acpica/acdebug.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acdispat.h b/drivers/acpi/acpica/acdispat.h index d3e2cc395d7..408f04bcaab 100644 --- a/drivers/acpi/acpica/acdispat.h +++ b/drivers/acpi/acpica/acdispat.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h index 7a7811a9fc2..228704b7865 100644 --- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -143,8 +143,6 @@ acpi_ev_match_gpe_method(acpi_handle obj_handle, acpi_status acpi_ev_walk_gpe_list(acpi_gpe_callback gpe_walk_callback, void *context); -u8 acpi_ev_valid_gpe_event(struct acpi_gpe_event_info *gpe_event_info); - acpi_status acpi_ev_get_gpe_device(struct acpi_gpe_xrupt_info *gpe_xrupt_info, struct acpi_gpe_block_info *gpe_block, void *context); diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h index 7f60582d0c8..a165d25343e 100644 --- a/drivers/acpi/acpica/acglobal.h +++ b/drivers/acpi/acpica/acglobal.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h index c318d3e2789..196a5524455 100644 --- a/drivers/acpi/acpica/achware.h +++ b/drivers/acpi/acpica/achware.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acinterp.h b/drivers/acpi/acpica/acinterp.h index b01f71ce052..1886bde54b5 100644 --- a/drivers/acpi/acpica/acinterp.h +++ b/drivers/acpi/acpica/acinterp.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h index 680d23bbae7..7add32e5d8c 100644 --- a/drivers/acpi/acpica/aclocal.h +++ b/drivers/acpi/acpica/aclocal.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h index 4bceb11c738..cf607fe69db 100644 --- a/drivers/acpi/acpica/acmacros.h +++ b/drivers/acpi/acpica/acmacros.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h index ee1c040f321..952fbe0b723 100644 --- a/drivers/acpi/acpica/acnamesp.h +++ b/drivers/acpi/acpica/acnamesp.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h index 8abb393dafa..3e9720e1f34 100644 --- a/drivers/acpi/acpica/acobject.h +++ b/drivers/acpi/acpica/acobject.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acopcode.h b/drivers/acpi/acpica/acopcode.h index dda0e6affcf..a5f17de45ac 100644 --- a/drivers/acpi/acpica/acopcode.h +++ b/drivers/acpi/acpica/acopcode.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acparser.h b/drivers/acpi/acpica/acparser.h index 6168b85463e..74a390c6db1 100644 --- a/drivers/acpi/acpica/acparser.h +++ b/drivers/acpi/acpica/acparser.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h index bd3908d26c4..a972d11c97c 100644 --- a/drivers/acpi/acpica/acpredef.h +++ b/drivers/acpi/acpica/acpredef.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acresrc.h b/drivers/acpi/acpica/acresrc.h index 4b008e8884a..efc4c7124cc 100644 --- a/drivers/acpi/acpica/acresrc.h +++ b/drivers/acpi/acpica/acresrc.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acstruct.h b/drivers/acpi/acpica/acstruct.h index cf7346110bd..d14b547b7cd 100644 --- a/drivers/acpi/acpica/acstruct.h +++ b/drivers/acpi/acpica/acstruct.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/actables.h b/drivers/acpi/acpica/actables.h index 1afe46e44da..1c127a43017 100644 --- a/drivers/acpi/acpica/actables.h +++ b/drivers/acpi/acpica/actables.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h index 486d342e74b..c2f03e8774a 100644 --- a/drivers/acpi/acpica/acutils.h +++ b/drivers/acpi/acpica/acutils.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/amlcode.h b/drivers/acpi/acpica/amlcode.h index 5908ccec6ae..3a95068fc11 100644 --- a/drivers/acpi/acpica/amlcode.h +++ b/drivers/acpi/acpica/amlcode.h @@ -7,7 +7,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/amlresrc.h b/drivers/acpi/acpica/amlresrc.h index 3a0beeb86ba..ee0cdd60b93 100644 --- a/drivers/acpi/acpica/amlresrc.h +++ b/drivers/acpi/acpica/amlresrc.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsargs.c b/drivers/acpi/acpica/dsargs.c index 720b1cdda71..3e6989738e8 100644 --- a/drivers/acpi/acpica/dsargs.c +++ b/drivers/acpi/acpica/dsargs.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dscontrol.c b/drivers/acpi/acpica/dscontrol.c index 8daf9de82b7..39da9da62bb 100644 --- a/drivers/acpi/acpica/dscontrol.c +++ b/drivers/acpi/acpica/dscontrol.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c index c5766619667..43b40de9048 100644 --- a/drivers/acpi/acpica/dsfield.c +++ b/drivers/acpi/acpica/dsfield.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c index aee5e45f6d3..bbe74bcebba 100644 --- a/drivers/acpi/acpica/dsinit.c +++ b/drivers/acpi/acpica/dsinit.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c index 3c7f7378b94..d72565a3c64 100644 --- a/drivers/acpi/acpica/dsmethod.c +++ b/drivers/acpi/acpica/dsmethod.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsmthdat.c b/drivers/acpi/acpica/dsmthdat.c index b67522df01a..2e4c42b377e 100644 --- a/drivers/acpi/acpica/dsmthdat.c +++ b/drivers/acpi/acpica/dsmthdat.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsobject.c b/drivers/acpi/acpica/dsobject.c index a1e7e6b6fcf..8a7b07b6adc 100644 --- a/drivers/acpi/acpica/dsobject.c +++ b/drivers/acpi/acpica/dsobject.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c index 6c0759c0db4..77244182ff0 100644 --- a/drivers/acpi/acpica/dsopcode.c +++ b/drivers/acpi/acpica/dsopcode.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsutils.c b/drivers/acpi/acpica/dsutils.c index 9f74795e226..e5ff89bcb3f 100644 --- a/drivers/acpi/acpica/dsutils.c +++ b/drivers/acpi/acpica/dsutils.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dswexec.c b/drivers/acpi/acpica/dswexec.c index f7f5107e754..df54d46225c 100644 --- a/drivers/acpi/acpica/dswexec.c +++ b/drivers/acpi/acpica/dswexec.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c index 15623da2620..843942fb4be 100644 --- a/drivers/acpi/acpica/dswload.c +++ b/drivers/acpi/acpica/dswload.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c index 2ac28d29730..fcaa30c611f 100644 --- a/drivers/acpi/acpica/dswload2.c +++ b/drivers/acpi/acpica/dswload2.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dswscope.c b/drivers/acpi/acpica/dswscope.c index 9d6e2c1de1f..43b3ea40c0b 100644 --- a/drivers/acpi/acpica/dswscope.c +++ b/drivers/acpi/acpica/dswscope.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dswstate.c b/drivers/acpi/acpica/dswstate.c index 24f7d5ea678..89ac2022465 100644 --- a/drivers/acpi/acpica/dswstate.c +++ b/drivers/acpi/acpica/dswstate.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evevent.c b/drivers/acpi/acpica/evevent.c index c7bffff9ed3..bf6873f95e7 100644 --- a/drivers/acpi/acpica/evevent.c +++ b/drivers/acpi/acpica/evevent.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evglock.c b/drivers/acpi/acpica/evglock.c index 3393a73ca0d..b78dc7c6d5d 100644 --- a/drivers/acpi/acpica/evglock.c +++ b/drivers/acpi/acpica/evglock.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c index aa70154cf4f..5ed064e8673 100644 --- a/drivers/acpi/acpica/evgpe.c +++ b/drivers/acpi/acpica/evgpe.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -114,17 +114,6 @@ acpi_status acpi_ev_enable_gpe(struct acpi_gpe_event_info *gpe_event_info) ACPI_FUNCTION_TRACE(ev_enable_gpe); - /* - * We will only allow a GPE to be enabled if it has either an associated - * method (_Lxx/_Exx) or a handler, or is using the implicit notify - * feature. Otherwise, the GPE will be immediately disabled by - * acpi_ev_gpe_dispatch the first time it fires. - */ - if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) == - ACPI_GPE_DISPATCH_NONE) { - return_ACPI_STATUS(AE_NO_HANDLER); - } - /* Clear the GPE (of stale events) */ status = acpi_hw_clear_gpe(gpe_event_info); @@ -339,7 +328,11 @@ u32 acpi_ev_gpe_detect(struct acpi_gpe_xrupt_info *gpe_xrupt_list) { acpi_status status; struct acpi_gpe_block_info *gpe_block; + struct acpi_namespace_node *gpe_device; struct acpi_gpe_register_info *gpe_register_info; + struct acpi_gpe_event_info *gpe_event_info; + u32 gpe_number; + struct acpi_gpe_handler_info *gpe_handler_info; u32 int_status = ACPI_INTERRUPT_NOT_HANDLED; u8 enabled_status_byte; u32 status_reg; @@ -367,6 +360,8 @@ u32 acpi_ev_gpe_detect(struct acpi_gpe_xrupt_info *gpe_xrupt_list) gpe_block = gpe_xrupt_list->gpe_block_list_head; while (gpe_block) { + gpe_device = gpe_block->node; + /* * Read all of the 8-bit GPE status and enable registers in this GPE * block, saving all of them. Find all currently active GP events. @@ -442,16 +437,68 @@ u32 acpi_ev_gpe_detect(struct acpi_gpe_xrupt_info *gpe_xrupt_list) /* Examine one GPE bit */ + gpe_event_info = + &gpe_block-> + event_info[((acpi_size) i * + ACPI_GPE_REGISTER_WIDTH) + j]; + gpe_number = + j + gpe_register_info->base_gpe_number; + if (enabled_status_byte & (1 << j)) { - /* - * Found an active GPE. Dispatch the event to a handler - * or method. - */ - int_status |= - acpi_ev_gpe_dispatch(gpe_block-> - node, - &gpe_block-> - event_info[((acpi_size) i * ACPI_GPE_REGISTER_WIDTH) + j], j + gpe_register_info->base_gpe_number); + + /* Invoke global event handler if present */ + + acpi_gpe_count++; + if (acpi_gbl_global_event_handler) { + acpi_gbl_global_event_handler + (ACPI_EVENT_TYPE_GPE, + gpe_device, gpe_number, + acpi_gbl_global_event_handler_context); + } + + /* Found an active GPE */ + + if (ACPI_GPE_DISPATCH_TYPE + (gpe_event_info->flags) == + ACPI_GPE_DISPATCH_RAW_HANDLER) { + + /* Dispatch the event to a raw handler */ + + gpe_handler_info = + gpe_event_info->dispatch. + handler; + + /* + * There is no protection around the namespace node + * and the GPE handler to ensure a safe destruction + * because: + * 1. The namespace node is expected to always + * exist after loading a table. + * 2. The GPE handler is expected to be flushed by + * acpi_os_wait_events_complete() before the + * destruction. + */ + acpi_os_release_lock + (acpi_gbl_gpe_lock, flags); + int_status |= + gpe_handler_info-> + address(gpe_device, + gpe_number, + gpe_handler_info-> + context); + flags = + acpi_os_acquire_lock + (acpi_gbl_gpe_lock); + } else { + /* + * Dispatch the event to a standard handler or + * method. + */ + int_status |= + acpi_ev_gpe_dispatch + (gpe_device, gpe_event_info, + gpe_number); + } } } } @@ -484,52 +531,15 @@ unlock_and_exit: static void ACPI_SYSTEM_XFACE acpi_ev_asynch_execute_gpe_method(void *context) { struct acpi_gpe_event_info *gpe_event_info = context; - acpi_status status; - struct acpi_gpe_event_info *local_gpe_event_info; + acpi_status status = AE_OK; struct acpi_evaluate_info *info; struct acpi_gpe_notify_info *notify; ACPI_FUNCTION_TRACE(ev_asynch_execute_gpe_method); - /* Allocate a local GPE block */ - - local_gpe_event_info = - ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_gpe_event_info)); - if (!local_gpe_event_info) { - ACPI_EXCEPTION((AE_INFO, AE_NO_MEMORY, "while handling a GPE")); - return_VOID; - } - - status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS); - if (ACPI_FAILURE(status)) { - ACPI_FREE(local_gpe_event_info); - return_VOID; - } - - /* Must revalidate the gpe_number/gpe_block */ - - if (!acpi_ev_valid_gpe_event(gpe_event_info)) { - status = acpi_ut_release_mutex(ACPI_MTX_EVENTS); - ACPI_FREE(local_gpe_event_info); - return_VOID; - } - - /* - * Take a snapshot of the GPE info for this level - we copy the info to - * prevent a race condition with remove_handler/remove_block. - */ - ACPI_MEMCPY(local_gpe_event_info, gpe_event_info, - sizeof(struct acpi_gpe_event_info)); - - status = acpi_ut_release_mutex(ACPI_MTX_EVENTS); - if (ACPI_FAILURE(status)) { - ACPI_FREE(local_gpe_event_info); - return_VOID; - } - /* Do the correct dispatch - normal method or implicit notify */ - switch (local_gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) { + switch (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags)) { case ACPI_GPE_DISPATCH_NOTIFY: /* * Implicit notify. @@ -542,7 +552,7 @@ static void ACPI_SYSTEM_XFACE acpi_ev_asynch_execute_gpe_method(void *context) * June 2012: Expand implicit notify mechanism to support * notifies on multiple device objects. */ - notify = local_gpe_event_info->dispatch.notify_list; + notify = gpe_event_info->dispatch.notify_list; while (ACPI_SUCCESS(status) && notify) { status = acpi_ev_queue_notify_request(notify->device_node, @@ -566,7 +576,7 @@ static void ACPI_SYSTEM_XFACE acpi_ev_asynch_execute_gpe_method(void *context) * _Lxx/_Exx control method that corresponds to this GPE */ info->prefix_node = - local_gpe_event_info->dispatch.method_node; + gpe_event_info->dispatch.method_node; info->flags = ACPI_IGNORE_RETURN_VALUE; status = acpi_ns_evaluate(info); @@ -576,25 +586,27 @@ static void ACPI_SYSTEM_XFACE acpi_ev_asynch_execute_gpe_method(void *context) if (ACPI_FAILURE(status)) { ACPI_EXCEPTION((AE_INFO, status, "while evaluating GPE method [%4.4s]", - acpi_ut_get_node_name - (local_gpe_event_info->dispatch. - method_node))); + acpi_ut_get_node_name(gpe_event_info-> + dispatch. + method_node))); } break; default: - return_VOID; /* Should never happen */ + goto error_exit; /* Should never happen */ } /* Defer enabling of GPE until all notify handlers are done */ status = acpi_os_execute(OSL_NOTIFY_HANDLER, - acpi_ev_asynch_enable_gpe, - local_gpe_event_info); - if (ACPI_FAILURE(status)) { - ACPI_FREE(local_gpe_event_info); + acpi_ev_asynch_enable_gpe, gpe_event_info); + if (ACPI_SUCCESS(status)) { + return_VOID; } + +error_exit: + acpi_ev_asynch_enable_gpe(gpe_event_info); return_VOID; } @@ -622,7 +634,6 @@ static void ACPI_SYSTEM_XFACE acpi_ev_asynch_enable_gpe(void *context) (void)acpi_ev_finish_gpe(gpe_event_info); acpi_os_release_lock(acpi_gbl_gpe_lock, flags); - ACPI_FREE(gpe_event_info); return; } @@ -692,15 +703,6 @@ acpi_ev_gpe_dispatch(struct acpi_namespace_node *gpe_device, ACPI_FUNCTION_TRACE(ev_gpe_dispatch); - /* Invoke global event handler if present */ - - acpi_gpe_count++; - if (acpi_gbl_global_event_handler) { - acpi_gbl_global_event_handler(ACPI_EVENT_TYPE_GPE, gpe_device, - gpe_number, - acpi_gbl_global_event_handler_context); - } - /* * Always disable the GPE so that it does not keep firing before * any asynchronous activity completes (either from the execution @@ -741,7 +743,7 @@ acpi_ev_gpe_dispatch(struct acpi_namespace_node *gpe_device, * If there is neither a handler nor a method, leave the GPE * disabled. */ - switch (gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) { + switch (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags)) { case ACPI_GPE_DISPATCH_HANDLER: /* Invoke the installed handler (at interrupt level) */ diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c index d86699eea33..e0f24c50451 100644 --- a/drivers/acpi/acpica/evgpeblk.c +++ b/drivers/acpi/acpica/evgpeblk.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -474,10 +474,12 @@ acpi_ev_initialize_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info, * Ignore GPEs that have no corresponding _Lxx/_Exx method * and GPEs that are used to wake the system */ - if (((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) == + if ((ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) == ACPI_GPE_DISPATCH_NONE) - || ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) - == ACPI_GPE_DISPATCH_HANDLER) + || (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) == + ACPI_GPE_DISPATCH_HANDLER) + || (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) == + ACPI_GPE_DISPATCH_RAW_HANDLER) || (gpe_event_info->flags & ACPI_GPE_CAN_WAKE)) { continue; } diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c index 7be92837987..8840296d5b2 100644 --- a/drivers/acpi/acpica/evgpeinit.c +++ b/drivers/acpi/acpica/evgpeinit.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -401,15 +401,17 @@ acpi_ev_match_gpe_method(acpi_handle obj_handle, return_ACPI_STATUS(AE_OK); } - if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) == - ACPI_GPE_DISPATCH_HANDLER) { + if ((ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) == + ACPI_GPE_DISPATCH_HANDLER) || + (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) == + ACPI_GPE_DISPATCH_RAW_HANDLER)) { /* If there is already a handler, ignore this GPE method */ return_ACPI_STATUS(AE_OK); } - if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) == + if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) == ACPI_GPE_DISPATCH_METHOD) { /* * If there is already a method, ignore this method. But check diff --git a/drivers/acpi/acpica/evgpeutil.c b/drivers/acpi/acpica/evgpeutil.c index 17e4bbfdb09..3a958f3612f 100644 --- a/drivers/acpi/acpica/evgpeutil.c +++ b/drivers/acpi/acpica/evgpeutil.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -108,53 +108,6 @@ unlock_and_exit: /******************************************************************************* * - * FUNCTION: acpi_ev_valid_gpe_event - * - * PARAMETERS: gpe_event_info - Info for this GPE - * - * RETURN: TRUE if the gpe_event is valid - * - * DESCRIPTION: Validate a GPE event. DO NOT CALL FROM INTERRUPT LEVEL. - * Should be called only when the GPE lists are semaphore locked - * and not subject to change. - * - ******************************************************************************/ - -u8 acpi_ev_valid_gpe_event(struct acpi_gpe_event_info *gpe_event_info) -{ - struct acpi_gpe_xrupt_info *gpe_xrupt_block; - struct acpi_gpe_block_info *gpe_block; - - ACPI_FUNCTION_ENTRY(); - - /* No need for spin lock since we are not changing any list elements */ - - /* Walk the GPE interrupt levels */ - - gpe_xrupt_block = acpi_gbl_gpe_xrupt_list_head; - while (gpe_xrupt_block) { - gpe_block = gpe_xrupt_block->gpe_block_list_head; - - /* Walk the GPE blocks on this interrupt level */ - - while (gpe_block) { - if ((&gpe_block->event_info[0] <= gpe_event_info) && - (&gpe_block->event_info[gpe_block->gpe_count] > - gpe_event_info)) { - return (TRUE); - } - - gpe_block = gpe_block->next; - } - - gpe_xrupt_block = gpe_xrupt_block->next; - } - - return (FALSE); -} - -/******************************************************************************* - * * FUNCTION: acpi_ev_get_gpe_device * * PARAMETERS: GPE_WALK_CALLBACK @@ -371,8 +324,10 @@ acpi_ev_delete_gpe_handlers(struct acpi_gpe_xrupt_info *gpe_xrupt_info, ACPI_GPE_REGISTER_WIDTH) + j]; - if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) == - ACPI_GPE_DISPATCH_HANDLER) { + if ((ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) == + ACPI_GPE_DISPATCH_HANDLER) || + (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) == + ACPI_GPE_DISPATCH_RAW_HANDLER)) { /* Delete an installed handler block */ @@ -380,10 +335,8 @@ acpi_ev_delete_gpe_handlers(struct acpi_gpe_xrupt_info *gpe_xrupt_info, gpe_event_info->dispatch.handler = NULL; gpe_event_info->flags &= ~ACPI_GPE_DISPATCH_MASK; - } else - if ((gpe_event_info-> - flags & ACPI_GPE_DISPATCH_MASK) == - ACPI_GPE_DISPATCH_NOTIFY) { + } else if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) + == ACPI_GPE_DISPATCH_NOTIFY) { /* Delete the implicit notification device list */ diff --git a/drivers/acpi/acpica/evhandler.c b/drivers/acpi/acpica/evhandler.c index 78ac29351c9..74e8595f5a2 100644 --- a/drivers/acpi/acpica/evhandler.c +++ b/drivers/acpi/acpica/evhandler.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evmisc.c b/drivers/acpi/acpica/evmisc.c index 24ea3424981..f7c9dfe7b99 100644 --- a/drivers/acpi/acpica/evmisc.c +++ b/drivers/acpi/acpica/evmisc.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index 8eb8575e8c1..9abace3401f 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c index 1b148a440d6..da323390bb7 100644 --- a/drivers/acpi/acpica/evrgnini.c +++ b/drivers/acpi/acpica/evrgnini.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evsci.c b/drivers/acpi/acpica/evsci.c index 29630e30382..0366703d297 100644 --- a/drivers/acpi/acpica/evsci.c +++ b/drivers/acpi/acpica/evsci.c @@ -6,7 +6,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c index 55a58f3ec8d..81f2d9e87fa 100644 --- a/drivers/acpi/acpica/evxface.c +++ b/drivers/acpi/acpica/evxface.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -51,6 +51,16 @@ #define _COMPONENT ACPI_EVENTS ACPI_MODULE_NAME("evxface") +#if (!ACPI_REDUCED_HARDWARE) +/* Local prototypes */ +static acpi_status +acpi_ev_install_gpe_handler(acpi_handle gpe_device, + u32 gpe_number, + u32 type, + u8 is_raw_handler, + acpi_gpe_handler address, void *context); + +#endif /******************************************************************************* @@ -76,6 +86,7 @@ ACPI_MODULE_NAME("evxface") * handlers. * ******************************************************************************/ + acpi_status acpi_install_notify_handler(acpi_handle device, u32 handler_type, @@ -717,32 +728,37 @@ ACPI_EXPORT_SYMBOL(acpi_remove_fixed_event_handler) /******************************************************************************* * - * FUNCTION: acpi_install_gpe_handler + * FUNCTION: acpi_ev_install_gpe_handler * * PARAMETERS: gpe_device - Namespace node for the GPE (NULL for FADT * defined GPEs) * gpe_number - The GPE number within the GPE block * type - Whether this GPE should be treated as an * edge- or level-triggered interrupt. + * is_raw_handler - Whether this GPE should be handled using + * the special GPE handler mode. * address - Address of the handler * context - Value passed to the handler on each GPE * * RETURN: Status * - * DESCRIPTION: Install a handler for a General Purpose Event. + * DESCRIPTION: Internal function to install a handler for a General Purpose + * Event. * ******************************************************************************/ -acpi_status -acpi_install_gpe_handler(acpi_handle gpe_device, - u32 gpe_number, - u32 type, acpi_gpe_handler address, void *context) +static acpi_status +acpi_ev_install_gpe_handler(acpi_handle gpe_device, + u32 gpe_number, + u32 type, + u8 is_raw_handler, + acpi_gpe_handler address, void *context) { struct acpi_gpe_event_info *gpe_event_info; struct acpi_gpe_handler_info *handler; acpi_status status; acpi_cpu_flags flags; - ACPI_FUNCTION_TRACE(acpi_install_gpe_handler); + ACPI_FUNCTION_TRACE(ev_install_gpe_handler); /* Parameter validation */ @@ -775,8 +791,10 @@ acpi_install_gpe_handler(acpi_handle gpe_device, /* Make sure that there isn't a handler there already */ - if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) == - ACPI_GPE_DISPATCH_HANDLER) { + if ((ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) == + ACPI_GPE_DISPATCH_HANDLER) || + (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) == + ACPI_GPE_DISPATCH_RAW_HANDLER)) { status = AE_ALREADY_EXISTS; goto free_and_exit; } @@ -793,9 +811,10 @@ acpi_install_gpe_handler(acpi_handle gpe_device, * automatically during initialization, in which case it has to be * disabled now to avoid spurious execution of the handler. */ - if (((handler->original_flags & ACPI_GPE_DISPATCH_METHOD) || - (handler->original_flags & ACPI_GPE_DISPATCH_NOTIFY)) && - gpe_event_info->runtime_count) { + if (((ACPI_GPE_DISPATCH_TYPE(handler->original_flags) == + ACPI_GPE_DISPATCH_METHOD) || + (ACPI_GPE_DISPATCH_TYPE(handler->original_flags) == + ACPI_GPE_DISPATCH_NOTIFY)) && gpe_event_info->runtime_count) { handler->originally_enabled = TRUE; (void)acpi_ev_remove_gpe_reference(gpe_event_info); @@ -816,7 +835,10 @@ acpi_install_gpe_handler(acpi_handle gpe_device, gpe_event_info->flags &= ~(ACPI_GPE_XRUPT_TYPE_MASK | ACPI_GPE_DISPATCH_MASK); - gpe_event_info->flags |= (u8)(type | ACPI_GPE_DISPATCH_HANDLER); + gpe_event_info->flags |= + (u8)(type | + (is_raw_handler ? ACPI_GPE_DISPATCH_RAW_HANDLER : + ACPI_GPE_DISPATCH_HANDLER)); acpi_os_release_lock(acpi_gbl_gpe_lock, flags); @@ -830,10 +852,78 @@ free_and_exit: goto unlock_and_exit; } +/******************************************************************************* + * + * FUNCTION: acpi_install_gpe_handler + * + * PARAMETERS: gpe_device - Namespace node for the GPE (NULL for FADT + * defined GPEs) + * gpe_number - The GPE number within the GPE block + * type - Whether this GPE should be treated as an + * edge- or level-triggered interrupt. + * address - Address of the handler + * context - Value passed to the handler on each GPE + * + * RETURN: Status + * + * DESCRIPTION: Install a handler for a General Purpose Event. + * + ******************************************************************************/ + +acpi_status +acpi_install_gpe_handler(acpi_handle gpe_device, + u32 gpe_number, + u32 type, acpi_gpe_handler address, void *context) +{ + acpi_status status; + + ACPI_FUNCTION_TRACE(acpi_install_gpe_handler); + + status = + acpi_ev_install_gpe_handler(gpe_device, gpe_number, type, FALSE, + address, context); + + return_ACPI_STATUS(status); +} + ACPI_EXPORT_SYMBOL(acpi_install_gpe_handler) /******************************************************************************* * + * FUNCTION: acpi_install_gpe_raw_handler + * + * PARAMETERS: gpe_device - Namespace node for the GPE (NULL for FADT + * defined GPEs) + * gpe_number - The GPE number within the GPE block + * type - Whether this GPE should be treated as an + * edge- or level-triggered interrupt. + * address - Address of the handler + * context - Value passed to the handler on each GPE + * + * RETURN: Status + * + * DESCRIPTION: Install a handler for a General Purpose Event. + * + ******************************************************************************/ +acpi_status +acpi_install_gpe_raw_handler(acpi_handle gpe_device, + u32 gpe_number, + u32 type, acpi_gpe_handler address, void *context) +{ + acpi_status status; + + ACPI_FUNCTION_TRACE(acpi_install_gpe_raw_handler); + + status = acpi_ev_install_gpe_handler(gpe_device, gpe_number, type, TRUE, + address, context); + + return_ACPI_STATUS(status); +} + +ACPI_EXPORT_SYMBOL(acpi_install_gpe_raw_handler) + +/******************************************************************************* + * * FUNCTION: acpi_remove_gpe_handler * * PARAMETERS: gpe_device - Namespace node for the GPE (NULL for FADT @@ -880,8 +970,10 @@ acpi_remove_gpe_handler(acpi_handle gpe_device, /* Make sure that a handler is indeed installed */ - if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) != - ACPI_GPE_DISPATCH_HANDLER) { + if ((ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) != + ACPI_GPE_DISPATCH_HANDLER) && + (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) != + ACPI_GPE_DISPATCH_RAW_HANDLER)) { status = AE_NOT_EXIST; goto unlock_and_exit; } @@ -896,6 +988,7 @@ acpi_remove_gpe_handler(acpi_handle gpe_device, /* Remove the handler */ handler = gpe_event_info->dispatch.handler; + gpe_event_info->dispatch.handler = NULL; /* Restore Method node (if any), set dispatch flags */ @@ -909,9 +1002,10 @@ acpi_remove_gpe_handler(acpi_handle gpe_device, * enabled, it should be enabled at this point to restore the * post-initialization configuration. */ - if (((handler->original_flags & ACPI_GPE_DISPATCH_METHOD) || - (handler->original_flags & ACPI_GPE_DISPATCH_NOTIFY)) && - handler->originally_enabled) { + if (((ACPI_GPE_DISPATCH_TYPE(handler->original_flags) == + ACPI_GPE_DISPATCH_METHOD) || + (ACPI_GPE_DISPATCH_TYPE(handler->original_flags) == + ACPI_GPE_DISPATCH_NOTIFY)) && handler->originally_enabled) { (void)acpi_ev_add_gpe_reference(gpe_event_info); } diff --git a/drivers/acpi/acpica/evxfevnt.c b/drivers/acpi/acpica/evxfevnt.c index bb8cbf5961b..df06a23c419 100644 --- a/drivers/acpi/acpica/evxfevnt.c +++ b/drivers/acpi/acpica/evxfevnt.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c index e889a5304ab..70eb47e3d72 100644 --- a/drivers/acpi/acpica/evxfgpe.c +++ b/drivers/acpi/acpica/evxfgpe.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -132,7 +132,7 @@ acpi_status acpi_enable_gpe(acpi_handle gpe_device, u32 gpe_number) */ gpe_event_info = acpi_ev_get_gpe_event_info(gpe_device, gpe_number); if (gpe_event_info) { - if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) != + if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) != ACPI_GPE_DISPATCH_NONE) { status = acpi_ev_add_gpe_reference(gpe_event_info); } else { @@ -183,6 +183,77 @@ acpi_status acpi_disable_gpe(acpi_handle gpe_device, u32 gpe_number) ACPI_EXPORT_SYMBOL(acpi_disable_gpe) +/******************************************************************************* + * + * FUNCTION: acpi_set_gpe + * + * PARAMETERS: gpe_device - Parent GPE Device. NULL for GPE0/GPE1 + * gpe_number - GPE level within the GPE block + * action - ACPI_GPE_ENABLE or ACPI_GPE_DISABLE + * + * RETURN: Status + * + * DESCRIPTION: Enable or disable an individual GPE. This function bypasses + * the reference count mechanism used in the acpi_enable_gpe(), + * acpi_disable_gpe() interfaces. + * This API is typically used by the GPE raw handler mode driver + * to switch between the polling mode and the interrupt mode after + * the driver has enabled the GPE. + * The APIs should be invoked in this order: + * acpi_enable_gpe() <- Ensure the reference count > 0 + * acpi_set_gpe(ACPI_GPE_DISABLE) <- Enter polling mode + * acpi_set_gpe(ACPI_GPE_ENABLE) <- Leave polling mode + * acpi_disable_gpe() <- Decrease the reference count + * + * Note: If a GPE is shared by 2 silicon components, then both the drivers + * should support GPE polling mode or disabling the GPE for long period + * for one driver may break the other. So use it with care since all + * firmware _Lxx/_Exx handlers currently rely on the GPE interrupt mode. + * + ******************************************************************************/ +acpi_status acpi_set_gpe(acpi_handle gpe_device, u32 gpe_number, u8 action) +{ + struct acpi_gpe_event_info *gpe_event_info; + acpi_status status; + acpi_cpu_flags flags; + + ACPI_FUNCTION_TRACE(acpi_set_gpe); + + flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock); + + /* Ensure that we have a valid GPE number */ + + gpe_event_info = acpi_ev_get_gpe_event_info(gpe_device, gpe_number); + if (!gpe_event_info) { + status = AE_BAD_PARAMETER; + goto unlock_and_exit; + } + + /* Perform the action */ + + switch (action) { + case ACPI_GPE_ENABLE: + + status = acpi_hw_low_set_gpe(gpe_event_info, ACPI_GPE_ENABLE); + break; + + case ACPI_GPE_DISABLE: + + status = acpi_hw_low_set_gpe(gpe_event_info, ACPI_GPE_DISABLE); + break; + + default: + + status = AE_BAD_PARAMETER; + break; + } + +unlock_and_exit: + acpi_os_release_lock(acpi_gbl_gpe_lock, flags); + return_ACPI_STATUS(status); +} + +ACPI_EXPORT_SYMBOL(acpi_set_gpe) /******************************************************************************* * @@ -313,7 +384,7 @@ acpi_setup_gpe_for_wake(acpi_handle wake_device, * known as an "implicit notify". Note: The GPE is assumed to be * level-triggered (for windows compatibility). */ - if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) == + if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) == ACPI_GPE_DISPATCH_NONE) { /* * This is the first device for implicit notify on this GPE. @@ -327,7 +398,7 @@ acpi_setup_gpe_for_wake(acpi_handle wake_device, * If we already have an implicit notify on this GPE, add * this device to the notify list. */ - if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) == + if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) == ACPI_GPE_DISPATCH_NOTIFY) { /* Ensure that the device is not already in the list */ @@ -530,6 +601,49 @@ unlock_and_exit: ACPI_EXPORT_SYMBOL(acpi_get_gpe_status) +/******************************************************************************* + * + * FUNCTION: acpi_finish_gpe + * + * PARAMETERS: gpe_device - Namespace node for the GPE Block + * (NULL for FADT defined GPEs) + * gpe_number - GPE level within the GPE block + * + * RETURN: Status + * + * DESCRIPTION: Clear and conditionally reenable a GPE. This completes the GPE + * processing. Intended for use by asynchronous host-installed + * GPE handlers. The GPE is only reenabled if the enable_for_run bit + * is set in the GPE info. + * + ******************************************************************************/ +acpi_status acpi_finish_gpe(acpi_handle gpe_device, u32 gpe_number) +{ + struct acpi_gpe_event_info *gpe_event_info; + acpi_status status; + acpi_cpu_flags flags; + + ACPI_FUNCTION_TRACE(acpi_finish_gpe); + + flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock); + + /* Ensure that we have a valid GPE number */ + + gpe_event_info = acpi_ev_get_gpe_event_info(gpe_device, gpe_number); + if (!gpe_event_info) { + status = AE_BAD_PARAMETER; + goto unlock_and_exit; + } + + status = acpi_ev_finish_gpe(gpe_event_info); + +unlock_and_exit: + acpi_os_release_lock(acpi_gbl_gpe_lock, flags); + return_ACPI_STATUS(status); +} + +ACPI_EXPORT_SYMBOL(acpi_finish_gpe) + /****************************************************************************** * * FUNCTION: acpi_disable_all_gpes @@ -604,7 +718,6 @@ ACPI_EXPORT_SYMBOL(acpi_enable_all_runtime_gpes) * all GPE blocks. * ******************************************************************************/ - acpi_status acpi_enable_all_wakeup_gpes(void) { acpi_status status; diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index 2d6f187939c..f21afbab03f 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c index 7d2949420db..6e0df2b9d5a 100644 --- a/drivers/acpi/acpica/exconfig.c +++ b/drivers/acpi/acpica/exconfig.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exconvrt.c b/drivers/acpi/acpica/exconvrt.c index c545386fee9..89a976b4ccf 100644 --- a/drivers/acpi/acpica/exconvrt.c +++ b/drivers/acpi/acpica/exconvrt.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/excreate.c b/drivers/acpi/acpica/excreate.c index 95d23dabcfb..aaeea4840aa 100644 --- a/drivers/acpi/acpica/excreate.c +++ b/drivers/acpi/acpica/excreate.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exdebug.c b/drivers/acpi/acpica/exdebug.c index 6fbfad47518..e67d0aca3fe 100644 --- a/drivers/acpi/acpica/exdebug.c +++ b/drivers/acpi/acpica/exdebug.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c index 0f23c3f2678..7c213b6b647 100644 --- a/drivers/acpi/acpica/exdump.c +++ b/drivers/acpi/acpica/exdump.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c index b994845ed35..c161dd974f7 100644 --- a/drivers/acpi/acpica/exfield.c +++ b/drivers/acpi/acpica/exfield.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c index 1d1b27a96c5..49479927e7f 100644 --- a/drivers/acpi/acpica/exfldio.c +++ b/drivers/acpi/acpica/exfldio.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exmisc.c b/drivers/acpi/acpica/exmisc.c index 2207e624f53..b56fc9d6f48 100644 --- a/drivers/acpi/acpica/exmisc.c +++ b/drivers/acpi/acpica/exmisc.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exmutex.c b/drivers/acpi/acpica/exmutex.c index b49ea2a95f4..472030f2b5b 100644 --- a/drivers/acpi/acpica/exmutex.c +++ b/drivers/acpi/acpica/exmutex.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c index dbb03b544e8..453b00c3017 100644 --- a/drivers/acpi/acpica/exnames.c +++ b/drivers/acpi/acpica/exnames.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exoparg1.c b/drivers/acpi/acpica/exoparg1.c index 1b8e9410440..77930683ab7 100644 --- a/drivers/acpi/acpica/exoparg1.c +++ b/drivers/acpi/acpica/exoparg1.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exoparg2.c b/drivers/acpi/acpica/exoparg2.c index 2ede656ee26..fcc618aa206 100644 --- a/drivers/acpi/acpica/exoparg2.c +++ b/drivers/acpi/acpica/exoparg2.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exoparg3.c b/drivers/acpi/acpica/exoparg3.c index 363767cf01e..b813fed95e5 100644 --- a/drivers/acpi/acpica/exoparg3.c +++ b/drivers/acpi/acpica/exoparg3.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exoparg6.c b/drivers/acpi/acpica/exoparg6.c index 29e9e99f7fe..c930edda3f6 100644 --- a/drivers/acpi/acpica/exoparg6.c +++ b/drivers/acpi/acpica/exoparg6.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c index 118e942005e..4c2836dc825 100644 --- a/drivers/acpi/acpica/exprep.c +++ b/drivers/acpi/acpica/exprep.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c index cd5288a257a..0fe188e238e 100644 --- a/drivers/acpi/acpica/exregion.c +++ b/drivers/acpi/acpica/exregion.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exresnte.c b/drivers/acpi/acpica/exresnte.c index ab060261b43..c7e3b929aa8 100644 --- a/drivers/acpi/acpica/exresnte.c +++ b/drivers/acpi/acpica/exresnte.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exresolv.c b/drivers/acpi/acpica/exresolv.c index 3cde553bcbe..b6b7f3af29e 100644 --- a/drivers/acpi/acpica/exresolv.c +++ b/drivers/acpi/acpica/exresolv.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exresop.c b/drivers/acpi/acpica/exresop.c index 3af8de3fcea..d2964af9ad4 100644 --- a/drivers/acpi/acpica/exresop.c +++ b/drivers/acpi/acpica/exresop.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exstore.c b/drivers/acpi/acpica/exstore.c index daf49f7ea31..a7eee2400ce 100644 --- a/drivers/acpi/acpica/exstore.c +++ b/drivers/acpi/acpica/exstore.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exstoren.c b/drivers/acpi/acpica/exstoren.c index 04bd16c08f9..3101607b4ef 100644 --- a/drivers/acpi/acpica/exstoren.c +++ b/drivers/acpi/acpica/exstoren.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exstorob.c b/drivers/acpi/acpica/exstorob.c index fd11018b016..6fa3c8d8fc5 100644 --- a/drivers/acpi/acpica/exstorob.c +++ b/drivers/acpi/acpica/exstorob.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exsystem.c b/drivers/acpi/acpica/exsystem.c index f7da64123ed..05450656fe3 100644 --- a/drivers/acpi/acpica/exsystem.c +++ b/drivers/acpi/acpica/exsystem.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exutils.c b/drivers/acpi/acpica/exutils.c index d9d72dff2a7..3f4225e95d9 100644 --- a/drivers/acpi/acpica/exutils.c +++ b/drivers/acpi/acpica/exutils.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwacpi.c b/drivers/acpi/acpica/hwacpi.c index 1e66d960fc1..e5c5949f908 100644 --- a/drivers/acpi/acpica/hwacpi.c +++ b/drivers/acpi/acpica/hwacpi.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwesleep.c b/drivers/acpi/acpica/hwesleep.c index 858fdd6be59..e5599f61080 100644 --- a/drivers/acpi/acpica/hwesleep.c +++ b/drivers/acpi/acpica/hwesleep.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c index 494027f5c06..84bc550f4f1 100644 --- a/drivers/acpi/acpica/hwgpe.c +++ b/drivers/acpi/acpica/hwgpe.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -54,6 +54,10 @@ acpi_hw_enable_wakeup_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info, struct acpi_gpe_block_info *gpe_block, void *context); +static acpi_status +acpi_hw_gpe_enable_write(u8 enable_mask, + struct acpi_gpe_register_info *gpe_register_info); + /****************************************************************************** * * FUNCTION: acpi_hw_get_gpe_register_bit @@ -146,7 +150,7 @@ acpi_hw_low_set_gpe(struct acpi_gpe_event_info *gpe_event_info, u32 action) status = acpi_hw_write(enable_mask, &gpe_register_info->enable_address); if (ACPI_SUCCESS(status) && (action & ACPI_GPE_SAVE_MASK)) { - gpe_register_info->enable_mask = enable_mask; + gpe_register_info->enable_mask = (u8)enable_mask; } return (status); } @@ -221,7 +225,7 @@ acpi_hw_get_gpe_status(struct acpi_gpe_event_info * gpe_event_info, /* GPE currently handled? */ - if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) != + if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) != ACPI_GPE_DISPATCH_NONE) { local_event_status |= ACPI_EVENT_FLAG_HAS_HANDLER; } diff --git a/drivers/acpi/acpica/hwpci.c b/drivers/acpi/acpica/hwpci.c index 6aade8e1d2a..c5214dec498 100644 --- a/drivers/acpi/acpica/hwpci.c +++ b/drivers/acpi/acpica/hwpci.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c index a4c34d2c556..3cf77afd142 100644 --- a/drivers/acpi/acpica/hwregs.c +++ b/drivers/acpi/acpica/hwregs.c @@ -6,7 +6,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c index d590693eb54..7d21cae6d60 100644 --- a/drivers/acpi/acpica/hwsleep.c +++ b/drivers/acpi/acpica/hwsleep.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c index 76ab5c1a814..675c709a300 100644 --- a/drivers/acpi/acpica/hwtimer.c +++ b/drivers/acpi/acpica/hwtimer.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c index 6b919127cd9..2bd33fe56cb 100644 --- a/drivers/acpi/acpica/hwvalid.c +++ b/drivers/acpi/acpica/hwvalid.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c index 96d007df65e..5f97468df8f 100644 --- a/drivers/acpi/acpica/hwxface.c +++ b/drivers/acpi/acpica/hwxface.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c index 6921c7f3d20..3b376769882 100644 --- a/drivers/acpi/acpica/hwxfsleep.c +++ b/drivers/acpi/acpica/hwxfsleep.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c index f1249e3463b..24fa19a76d7 100644 --- a/drivers/acpi/acpica/nsaccess.c +++ b/drivers/acpi/acpica/nsaccess.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsalloc.c b/drivers/acpi/acpica/nsalloc.c index 607eb9e5150..e107f929d9c 100644 --- a/drivers/acpi/acpica/nsalloc.c +++ b/drivers/acpi/acpica/nsalloc.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsarguments.c b/drivers/acpi/acpica/nsarguments.c index 80fcfc8c9c1..5d347a71bd0 100644 --- a/drivers/acpi/acpica/nsarguments.c +++ b/drivers/acpi/acpica/nsarguments.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsconvert.c b/drivers/acpi/acpica/nsconvert.c index b55642c4ee5..1a8b39c8d96 100644 --- a/drivers/acpi/acpica/nsconvert.c +++ b/drivers/acpi/acpica/nsconvert.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c index 3d88ef4a3e0..80f097eb738 100644 --- a/drivers/acpi/acpica/nsdump.c +++ b/drivers/acpi/acpica/nsdump.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsdumpdv.c b/drivers/acpi/acpica/nsdumpdv.c index 42d37109aa5..7dc367e6fe0 100644 --- a/drivers/acpi/acpica/nsdumpdv.c +++ b/drivers/acpi/acpica/nsdumpdv.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nseval.c b/drivers/acpi/acpica/nseval.c index e634a05974d..7bcc68f57af 100644 --- a/drivers/acpi/acpica/nseval.c +++ b/drivers/acpi/acpica/nseval.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c index a3fb7e4c080..4a85c451798 100644 --- a/drivers/acpi/acpica/nsinit.c +++ b/drivers/acpi/acpica/nsinit.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsload.c b/drivers/acpi/acpica/nsload.c index 7c9d0181f34..bd6cd4a8131 100644 --- a/drivers/acpi/acpica/nsload.c +++ b/drivers/acpi/acpica/nsload.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsnames.c b/drivers/acpi/acpica/nsnames.c index 7eee0a6f02f..d293d974803 100644 --- a/drivers/acpi/acpica/nsnames.c +++ b/drivers/acpi/acpica/nsnames.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsobject.c b/drivers/acpi/acpica/nsobject.c index a42ee9d6970..677bc9330e6 100644 --- a/drivers/acpi/acpica/nsobject.c +++ b/drivers/acpi/acpica/nsobject.c @@ -6,7 +6,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c index e83cff31754..c95a119767b 100644 --- a/drivers/acpi/acpica/nsparse.c +++ b/drivers/acpi/acpica/nsparse.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nspredef.c b/drivers/acpi/acpica/nspredef.c index 392910ffbed..0eb54315b4b 100644 --- a/drivers/acpi/acpica/nspredef.c +++ b/drivers/acpi/acpica/nspredef.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsprepkg.c b/drivers/acpi/acpica/nsprepkg.c index 1b13b921dda..8b79958b7ac 100644 --- a/drivers/acpi/acpica/nsprepkg.c +++ b/drivers/acpi/acpica/nsprepkg.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c index 7e417aa5c91..151fcd95ba8 100644 --- a/drivers/acpi/acpica/nsrepair.c +++ b/drivers/acpi/acpica/nsrepair.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c index b09e6bef72b..c30672d2387 100644 --- a/drivers/acpi/acpica/nsrepair2.c +++ b/drivers/acpi/acpica/nsrepair2.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nssearch.c b/drivers/acpi/acpica/nssearch.c index af1cc42a8aa..4a9d4a66016 100644 --- a/drivers/acpi/acpica/nssearch.c +++ b/drivers/acpi/acpica/nssearch.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c index 4a5e3f5c0ff..6ad02008c0c 100644 --- a/drivers/acpi/acpica/nsutils.c +++ b/drivers/acpi/acpica/nsutils.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nswalk.c b/drivers/acpi/acpica/nswalk.c index 4758a1f2ce2..c68609a2bc1 100644 --- a/drivers/acpi/acpica/nswalk.c +++ b/drivers/acpi/acpica/nswalk.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsxfeval.c b/drivers/acpi/acpica/nsxfeval.c index 4bd558bf10d..b6030a2deee 100644 --- a/drivers/acpi/acpica/nsxfeval.c +++ b/drivers/acpi/acpica/nsxfeval.c @@ -6,7 +6,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c index 8c6c11ce976..d66c326485d 100644 --- a/drivers/acpi/acpica/nsxfname.c +++ b/drivers/acpi/acpica/nsxfname.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsxfobj.c b/drivers/acpi/acpica/nsxfobj.c index dae9401be7a..793383501f8 100644 --- a/drivers/acpi/acpica/nsxfobj.c +++ b/drivers/acpi/acpica/nsxfobj.c @@ -6,7 +6,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -53,50 +53,6 @@ ACPI_MODULE_NAME("nsxfobj") /******************************************************************************* * - * FUNCTION: acpi_get_id - * - * PARAMETERS: Handle - Handle of object whose id is desired - * ret_id - Where the id will be placed - * - * RETURN: Status - * - * DESCRIPTION: This routine returns the owner id associated with a handle - * - ******************************************************************************/ -acpi_status acpi_get_id(acpi_handle handle, acpi_owner_id * ret_id) -{ - struct acpi_namespace_node *node; - acpi_status status; - - /* Parameter Validation */ - - if (!ret_id) { - return (AE_BAD_PARAMETER); - } - - status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE); - if (ACPI_FAILURE(status)) { - return (status); - } - - /* Convert and validate the handle */ - - node = acpi_ns_validate_handle(handle); - if (!node) { - (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); - return (AE_BAD_PARAMETER); - } - - *ret_id = node->owner_id; - - status = acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); - return (status); -} - -ACPI_EXPORT_SYMBOL(acpi_get_id) - -/******************************************************************************* - * * FUNCTION: acpi_get_type * * PARAMETERS: handle - Handle of object whose type is desired diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c index 314d314340a..6d038770577 100644 --- a/drivers/acpi/acpica/psargs.c +++ b/drivers/acpi/acpica/psargs.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c index b058e2390fd..90437227d79 100644 --- a/drivers/acpi/acpica/psloop.c +++ b/drivers/acpi/acpica/psloop.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psobject.c b/drivers/acpi/acpica/psobject.c index a6885077d59..2f5ddd806c5 100644 --- a/drivers/acpi/acpica/psobject.c +++ b/drivers/acpi/acpica/psobject.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psopcode.c b/drivers/acpi/acpica/psopcode.c index 1755d2ac565..1af4a405e35 100644 --- a/drivers/acpi/acpica/psopcode.c +++ b/drivers/acpi/acpica/psopcode.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psopinfo.c b/drivers/acpi/acpica/psopinfo.c index 0d8d37ffd04..e18e7c47f48 100644 --- a/drivers/acpi/acpica/psopinfo.c +++ b/drivers/acpi/acpica/psopinfo.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psparse.c b/drivers/acpi/acpica/psparse.c index 6d27b597394..a555f7f7b9a 100644 --- a/drivers/acpi/acpica/psparse.c +++ b/drivers/acpi/acpica/psparse.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psscope.c b/drivers/acpi/acpica/psscope.c index 32d250feea2..9d669cc6cb6 100644 --- a/drivers/acpi/acpica/psscope.c +++ b/drivers/acpi/acpica/psscope.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/pstree.c b/drivers/acpi/acpica/pstree.c index 0b64181e772..89984f30add 100644 --- a/drivers/acpi/acpica/pstree.c +++ b/drivers/acpi/acpica/pstree.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psutils.c b/drivers/acpi/acpica/psutils.c index 3cd48802eed..960505ab409 100644 --- a/drivers/acpi/acpica/psutils.c +++ b/drivers/acpi/acpica/psutils.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/pswalk.c b/drivers/acpi/acpica/pswalk.c index 9cb07e1e76d..ba5f6917128 100644 --- a/drivers/acpi/acpica/pswalk.c +++ b/drivers/acpi/acpica/pswalk.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psxface.c b/drivers/acpi/acpica/psxface.c index e135acaa5e1..841a5ea0609 100644 --- a/drivers/acpi/acpica/psxface.c +++ b/drivers/acpi/acpica/psxface.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsaddr.c b/drivers/acpi/acpica/rsaddr.c index 916fd095ff3..66d406e8fe3 100644 --- a/drivers/acpi/acpica/rsaddr.c +++ b/drivers/acpi/acpica/rsaddr.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -74,7 +74,7 @@ struct acpi_rsconvert_info acpi_rs_convert_address16[5] = { * Address Translation Offset * Address Length */ - {ACPI_RSC_MOVE16, ACPI_RS_OFFSET(data.address16.granularity), + {ACPI_RSC_MOVE16, ACPI_RS_OFFSET(data.address16.address.granularity), AML_OFFSET(address16.granularity), 5}, @@ -112,7 +112,7 @@ struct acpi_rsconvert_info acpi_rs_convert_address32[5] = { * Address Translation Offset * Address Length */ - {ACPI_RSC_MOVE32, ACPI_RS_OFFSET(data.address32.granularity), + {ACPI_RSC_MOVE32, ACPI_RS_OFFSET(data.address32.address.granularity), AML_OFFSET(address32.granularity), 5}, @@ -150,7 +150,7 @@ struct acpi_rsconvert_info acpi_rs_convert_address64[5] = { * Address Translation Offset * Address Length */ - {ACPI_RSC_MOVE64, ACPI_RS_OFFSET(data.address64.granularity), + {ACPI_RSC_MOVE64, ACPI_RS_OFFSET(data.address64.address.granularity), AML_OFFSET(address64.granularity), 5}, @@ -194,7 +194,8 @@ struct acpi_rsconvert_info acpi_rs_convert_ext_address64[5] = { * Address Length * Type-Specific Attribute */ - {ACPI_RSC_MOVE64, ACPI_RS_OFFSET(data.ext_address64.granularity), + {ACPI_RSC_MOVE64, + ACPI_RS_OFFSET(data.ext_address64.address.granularity), AML_OFFSET(ext_address64.granularity), 6} }; diff --git a/drivers/acpi/acpica/rscalc.c b/drivers/acpi/acpica/rscalc.c index 689556744b0..cb739a69493 100644 --- a/drivers/acpi/acpica/rscalc.c +++ b/drivers/acpi/acpica/rscalc.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rscreate.c b/drivers/acpi/acpica/rscreate.c index 049d9c22a0f..15434e4c9b3 100644 --- a/drivers/acpi/acpica/rscreate.c +++ b/drivers/acpi/acpica/rscreate.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsdump.c b/drivers/acpi/acpica/rsdump.c index c3c56b5a978..1539394c8c5 100644 --- a/drivers/acpi/acpica/rsdump.c +++ b/drivers/acpi/acpica/rsdump.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsdumpinfo.c b/drivers/acpi/acpica/rsdumpinfo.c index 2f9332d5c97..b29d9ec63d1 100644 --- a/drivers/acpi/acpica/rsdumpinfo.c +++ b/drivers/acpi/acpica/rsdumpinfo.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -183,15 +183,15 @@ struct acpi_rsdump_info acpi_rs_dump_address16[8] = { {ACPI_RSD_TITLE, ACPI_RSD_TABLE_SIZE(acpi_rs_dump_address16), "16-Bit WORD Address Space", NULL}, {ACPI_RSD_ADDRESS, 0, NULL, NULL}, - {ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.granularity), "Granularity", - NULL}, - {ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.minimum), "Address Minimum", - NULL}, - {ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.maximum), "Address Maximum", - NULL}, - {ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.translation_offset), + {ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.address.granularity), + "Granularity", NULL}, + {ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.address.minimum), + "Address Minimum", NULL}, + {ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.address.maximum), + "Address Maximum", NULL}, + {ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.address.translation_offset), "Translation Offset", NULL}, - {ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.address_length), + {ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.address.address_length), "Address Length", NULL}, {ACPI_RSD_SOURCE, ACPI_RSD_OFFSET(address16.resource_source), NULL, NULL} }; @@ -200,15 +200,15 @@ struct acpi_rsdump_info acpi_rs_dump_address32[8] = { {ACPI_RSD_TITLE, ACPI_RSD_TABLE_SIZE(acpi_rs_dump_address32), "32-Bit DWORD Address Space", NULL}, {ACPI_RSD_ADDRESS, 0, NULL, NULL}, - {ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.granularity), "Granularity", - NULL}, - {ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.minimum), "Address Minimum", - NULL}, - {ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.maximum), "Address Maximum", - NULL}, - {ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.translation_offset), + {ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.address.granularity), + "Granularity", NULL}, + {ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.address.minimum), + "Address Minimum", NULL}, + {ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.address.maximum), + "Address Maximum", NULL}, + {ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.address.translation_offset), "Translation Offset", NULL}, - {ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.address_length), + {ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.address.address_length), "Address Length", NULL}, {ACPI_RSD_SOURCE, ACPI_RSD_OFFSET(address32.resource_source), NULL, NULL} }; @@ -217,15 +217,15 @@ struct acpi_rsdump_info acpi_rs_dump_address64[8] = { {ACPI_RSD_TITLE, ACPI_RSD_TABLE_SIZE(acpi_rs_dump_address64), "64-Bit QWORD Address Space", NULL}, {ACPI_RSD_ADDRESS, 0, NULL, NULL}, - {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.granularity), "Granularity", - NULL}, - {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.minimum), "Address Minimum", - NULL}, - {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.maximum), "Address Maximum", - NULL}, - {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.translation_offset), + {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.address.granularity), + "Granularity", NULL}, + {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.address.minimum), + "Address Minimum", NULL}, + {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.address.maximum), + "Address Maximum", NULL}, + {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.address.translation_offset), "Translation Offset", NULL}, - {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.address_length), + {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.address.address_length), "Address Length", NULL}, {ACPI_RSD_SOURCE, ACPI_RSD_OFFSET(address64.resource_source), NULL, NULL} }; @@ -234,15 +234,16 @@ struct acpi_rsdump_info acpi_rs_dump_ext_address64[8] = { {ACPI_RSD_TITLE, ACPI_RSD_TABLE_SIZE(acpi_rs_dump_ext_address64), "64-Bit Extended Address Space", NULL}, {ACPI_RSD_ADDRESS, 0, NULL, NULL}, - {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.granularity), + {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.address.granularity), "Granularity", NULL}, - {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.minimum), + {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.address.minimum), "Address Minimum", NULL}, - {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.maximum), + {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.address.maximum), "Address Maximum", NULL}, - {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.translation_offset), + {ACPI_RSD_UINT64, + ACPI_RSD_OFFSET(ext_address64.address.translation_offset), "Translation Offset", NULL}, - {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.address_length), + {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.address.address_length), "Address Length", NULL}, {ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.type_specific), "Type-Specific Attribute", NULL} diff --git a/drivers/acpi/acpica/rsinfo.c b/drivers/acpi/acpica/rsinfo.c index 9d3f8a9a24b..edecfc67597 100644 --- a/drivers/acpi/acpica/rsinfo.c +++ b/drivers/acpi/acpica/rsinfo.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsio.c b/drivers/acpi/acpica/rsio.c index 19d64873290..5adba018bab 100644 --- a/drivers/acpi/acpica/rsio.c +++ b/drivers/acpi/acpica/rsio.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsirq.c b/drivers/acpi/acpica/rsirq.c index 3461f7db26d..07cfa70a475 100644 --- a/drivers/acpi/acpica/rsirq.c +++ b/drivers/acpi/acpica/rsirq.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rslist.c b/drivers/acpi/acpica/rslist.c index 77291293af6..50d5be2ee06 100644 --- a/drivers/acpi/acpica/rslist.c +++ b/drivers/acpi/acpica/rslist.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsmemory.c b/drivers/acpi/acpica/rsmemory.c index eab4483ff5f..c6b80862030 100644 --- a/drivers/acpi/acpica/rsmemory.c +++ b/drivers/acpi/acpica/rsmemory.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsmisc.c b/drivers/acpi/acpica/rsmisc.c index 41eea4bc089..1fe49d22366 100644 --- a/drivers/acpi/acpica/rsmisc.c +++ b/drivers/acpi/acpica/rsmisc.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsserial.c b/drivers/acpi/acpica/rsserial.c index 9e8407223d9..4c8c6fe6ea7 100644 --- a/drivers/acpi/acpica/rsserial.c +++ b/drivers/acpi/acpica/rsserial.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsutils.c b/drivers/acpi/acpica/rsutils.c index 897a5ceb042..ece3cd60cc6 100644 --- a/drivers/acpi/acpica/rsutils.c +++ b/drivers/acpi/acpica/rsutils.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsxface.c b/drivers/acpi/acpica/rsxface.c index 877ab920213..8e6276df022 100644 --- a/drivers/acpi/acpica/rsxface.c +++ b/drivers/acpi/acpica/rsxface.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -60,11 +60,11 @@ ACPI_MODULE_NAME("rsxface") ACPI_COPY_FIELD(out, in, min_address_fixed); \ ACPI_COPY_FIELD(out, in, max_address_fixed); \ ACPI_COPY_FIELD(out, in, info); \ - ACPI_COPY_FIELD(out, in, granularity); \ - ACPI_COPY_FIELD(out, in, minimum); \ - ACPI_COPY_FIELD(out, in, maximum); \ - ACPI_COPY_FIELD(out, in, translation_offset); \ - ACPI_COPY_FIELD(out, in, address_length); \ + ACPI_COPY_FIELD(out, in, address.granularity); \ + ACPI_COPY_FIELD(out, in, address.minimum); \ + ACPI_COPY_FIELD(out, in, address.maximum); \ + ACPI_COPY_FIELD(out, in, address.translation_offset); \ + ACPI_COPY_FIELD(out, in, address.address_length); \ ACPI_COPY_FIELD(out, in, resource_source); /* Local prototypes */ static acpi_status diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c index f499c10ceb4..6a144957aad 100644 --- a/drivers/acpi/acpica/tbdata.c +++ b/drivers/acpi/acpica/tbdata.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c index 41519a95808..7d2486005e3 100644 --- a/drivers/acpi/acpica/tbfadt.c +++ b/drivers/acpi/acpica/tbfadt.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbfind.c b/drivers/acpi/acpica/tbfind.c index cb947700206..0b879fcfef6 100644 --- a/drivers/acpi/acpica/tbfind.c +++ b/drivers/acpi/acpica/tbfind.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c index 755b90c40dd..9bad45e63a4 100644 --- a/drivers/acpi/acpica/tbinstal.c +++ b/drivers/acpi/acpica/tbinstal.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c index df3bb20ea32..ef16c06e509 100644 --- a/drivers/acpi/acpica/tbprint.c +++ b/drivers/acpi/acpica/tbprint.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c index 6b1ca9991b9..6559a58439c 100644 --- a/drivers/acpi/acpica/tbutils.c +++ b/drivers/acpi/acpica/tbutils.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c index 6482b0ded65..60e94f87f27 100644 --- a/drivers/acpi/acpica/tbxface.c +++ b/drivers/acpi/acpica/tbxface.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -265,45 +265,6 @@ ACPI_EXPORT_SYMBOL(acpi_get_table_header) /******************************************************************************* * - * FUNCTION: acpi_unload_table_id - * - * PARAMETERS: id - Owner ID of the table to be removed. - * - * RETURN: Status - * - * DESCRIPTION: This routine is used to force the unload of a table (by id) - * - ******************************************************************************/ -acpi_status acpi_unload_table_id(acpi_owner_id id) -{ - int i; - acpi_status status = AE_NOT_EXIST; - - ACPI_FUNCTION_TRACE(acpi_unload_table_id); - - /* Find table in the global table list */ - for (i = 0; i < acpi_gbl_root_table_list.current_table_count; ++i) { - if (id != acpi_gbl_root_table_list.tables[i].owner_id) { - continue; - } - /* - * Delete all namespace objects owned by this table. Note that these - * objects can appear anywhere in the namespace by virtue of the AML - * "Scope" operator. Thus, we need to track ownership by an ID, not - * simply a position within the hierarchy - */ - acpi_tb_delete_namespace_by_owner(i); - status = acpi_tb_release_owner_id(i); - acpi_tb_set_table_loaded_flag(i, FALSE); - break; - } - return_ACPI_STATUS(status); -} - -ACPI_EXPORT_SYMBOL(acpi_unload_table_id) - -/******************************************************************************* - * * FUNCTION: acpi_get_table_with_size * * PARAMETERS: signature - ACPI signature of needed table diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c index ab5308b81aa..aadb3002a2d 100644 --- a/drivers/acpi/acpica/tbxfload.c +++ b/drivers/acpi/acpica/tbxfload.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c index 43a54af2b54..eac52cf14f1 100644 --- a/drivers/acpi/acpica/tbxfroot.c +++ b/drivers/acpi/acpica/tbxfroot.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utaddress.c b/drivers/acpi/acpica/utaddress.c index a1acec9d2ef..1279f50da75 100644 --- a/drivers/acpi/acpica/utaddress.c +++ b/drivers/acpi/acpica/utaddress.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utalloc.c b/drivers/acpi/acpica/utalloc.c index efac83c606d..61d8f6d186d 100644 --- a/drivers/acpi/acpica/utalloc.c +++ b/drivers/acpi/acpica/utalloc.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utbuffer.c b/drivers/acpi/acpica/utbuffer.c index 038ea887f56..242bd071f00 100644 --- a/drivers/acpi/acpica/utbuffer.c +++ b/drivers/acpi/acpica/utbuffer.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utcache.c b/drivers/acpi/acpica/utcache.c index 78fde0aac48..eacc5eee362 100644 --- a/drivers/acpi/acpica/utcache.c +++ b/drivers/acpi/acpica/utcache.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c index ff601c0f7c7..c37ec5035f4 100644 --- a/drivers/acpi/acpica/utcopy.c +++ b/drivers/acpi/acpica/utcopy.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c index e516254c63b..57078e3ea9b 100644 --- a/drivers/acpi/acpica/utdebug.c +++ b/drivers/acpi/acpica/utdebug.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c index 40e923e675f..988e23b7795 100644 --- a/drivers/acpi/acpica/utdecode.c +++ b/drivers/acpi/acpica/utdecode.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utdelete.c b/drivers/acpi/acpica/utdelete.c index a3516de213f..71fce389fd4 100644 --- a/drivers/acpi/acpica/utdelete.c +++ b/drivers/acpi/acpica/utdelete.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/uterror.c b/drivers/acpi/acpica/uterror.c index 8e544d4688c..9ef80f2828e 100644 --- a/drivers/acpi/acpica/uterror.c +++ b/drivers/acpi/acpica/uterror.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/uteval.c b/drivers/acpi/acpica/uteval.c index 8fed1482d22..6c738fa0cd4 100644 --- a/drivers/acpi/acpica/uteval.c +++ b/drivers/acpi/acpica/uteval.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utexcep.c b/drivers/acpi/acpica/utexcep.c index 0403dcaabaf..743a0ae9fb1 100644 --- a/drivers/acpi/acpica/utexcep.c +++ b/drivers/acpi/acpica/utexcep.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utfileio.c b/drivers/acpi/acpica/utfileio.c index 4e263a8cc6f..7e1168be39f 100644 --- a/drivers/acpi/acpica/utfileio.c +++ b/drivers/acpi/acpica/utfileio.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c index 77ceac715f2..5e8df9177da 100644 --- a/drivers/acpi/acpica/utglobal.c +++ b/drivers/acpi/acpica/utglobal.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/uthex.c b/drivers/acpi/acpica/uthex.c index 9afa9441b18..aa448278ba2 100644 --- a/drivers/acpi/acpica/uthex.c +++ b/drivers/acpi/acpica/uthex.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utids.c b/drivers/acpi/acpica/utids.c index 4b12880e5b1..27431cfc1c4 100644 --- a/drivers/acpi/acpica/utids.c +++ b/drivers/acpi/acpica/utids.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utinit.c b/drivers/acpi/acpica/utinit.c index 77120ec9ea8..e402e07b484 100644 --- a/drivers/acpi/acpica/utinit.c +++ b/drivers/acpi/acpica/utinit.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utlock.c b/drivers/acpi/acpica/utlock.c index dc6e96547f1..089f78bbd59 100644 --- a/drivers/acpi/acpica/utlock.c +++ b/drivers/acpi/acpica/utlock.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utmath.c b/drivers/acpi/acpica/utmath.c index d44dee6ee10..f9ff100f015 100644 --- a/drivers/acpi/acpica/utmath.c +++ b/drivers/acpi/acpica/utmath.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utmisc.c b/drivers/acpi/acpica/utmisc.c index 2e2bb14e109..56bbacd576f 100644 --- a/drivers/acpi/acpica/utmisc.c +++ b/drivers/acpi/acpica/utmisc.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c index 82717fff9ff..37b8b58fcd5 100644 --- a/drivers/acpi/acpica/utmutex.c +++ b/drivers/acpi/acpica/utmutex.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utobject.c b/drivers/acpi/acpica/utobject.c index dfa9009bfc8..7d83efe1ea2 100644 --- a/drivers/acpi/acpica/utobject.c +++ b/drivers/acpi/acpica/utobject.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utosi.c b/drivers/acpi/acpica/utosi.c index 685766fc6ca..574cd311831 100644 --- a/drivers/acpi/acpica/utosi.c +++ b/drivers/acpi/acpica/utosi.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utownerid.c b/drivers/acpi/acpica/utownerid.c index 36bec57ebd2..2959217067c 100644 --- a/drivers/acpi/acpica/utownerid.c +++ b/drivers/acpi/acpica/utownerid.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utpredef.c b/drivers/acpi/acpica/utpredef.c index db30caff130..29e449935a8 100644 --- a/drivers/acpi/acpica/utpredef.c +++ b/drivers/acpi/acpica/utpredef.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utprint.c b/drivers/acpi/acpica/utprint.c index 0ce3f5a0dd6..82ca9142e10 100644 --- a/drivers/acpi/acpica/utprint.c +++ b/drivers/acpi/acpica/utprint.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utresrc.c b/drivers/acpi/acpica/utresrc.c index bc1ff820c7d..b3505dbc715 100644 --- a/drivers/acpi/acpica/utresrc.c +++ b/drivers/acpi/acpica/utresrc.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utstate.c b/drivers/acpi/acpica/utstate.c index 1cc97a752c1..8274cc16edc 100644 --- a/drivers/acpi/acpica/utstate.c +++ b/drivers/acpi/acpica/utstate.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c index 6dc54b3c28b..83b6c52490d 100644 --- a/drivers/acpi/acpica/utstring.c +++ b/drivers/acpi/acpica/utstring.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c index 7d0ee969d78..130dd9f96f0 100644 --- a/drivers/acpi/acpica/uttrack.c +++ b/drivers/acpi/acpica/uttrack.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utuuid.c b/drivers/acpi/acpica/utuuid.c index 4dc33130f13..c6149a21214 100644 --- a/drivers/acpi/acpica/utuuid.c +++ b/drivers/acpi/acpica/utuuid.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c index 49c873c6875..0929187bdce 100644 --- a/drivers/acpi/acpica/utxface.c +++ b/drivers/acpi/acpica/utxface.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utxferror.c b/drivers/acpi/acpica/utxferror.c index 88ef77f3cf8..306e785f941 100644 --- a/drivers/acpi/acpica/utxferror.c +++ b/drivers/acpi/acpica/utxferror.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c index b1fd6886e43..083a7689188 100644 --- a/drivers/acpi/acpica/utxfinit.c +++ b/drivers/acpi/acpica/utxfinit.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utxfmutex.c b/drivers/acpi/acpica/utxfmutex.c index 2a0f9e04d3a..f2606af3364 100644 --- a/drivers/acpi/acpica/utxfmutex.c +++ b/drivers/acpi/acpica/utxfmutex.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index 2cd7bdd6c8b..a85ac07f3da 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -449,7 +449,7 @@ int apei_resources_sub(struct apei_resources *resources1, } EXPORT_SYMBOL_GPL(apei_resources_sub); -static int apei_get_nvs_callback(__u64 start, __u64 size, void *data) +static int apei_get_res_callback(__u64 start, __u64 size, void *data) { struct apei_resources *resources = data; return apei_res_add(&resources->iomem, start, size); @@ -457,7 +457,15 @@ static int apei_get_nvs_callback(__u64 start, __u64 size, void *data) static int apei_get_nvs_resources(struct apei_resources *resources) { - return acpi_nvs_for_each_region(apei_get_nvs_callback, resources); + return acpi_nvs_for_each_region(apei_get_res_callback, resources); +} + +int (*arch_apei_filter_addr)(int (*func)(__u64 start, __u64 size, + void *data), void *data); +static int apei_get_arch_resources(struct apei_resources *resources) + +{ + return arch_apei_filter_addr(apei_get_res_callback, resources); } /* @@ -470,7 +478,7 @@ int apei_resources_request(struct apei_resources *resources, { struct apei_res *res, *res_bak = NULL; struct resource *r; - struct apei_resources nvs_resources; + struct apei_resources nvs_resources, arch_res; int rc; rc = apei_resources_sub(resources, &apei_resources_all); @@ -485,10 +493,20 @@ int apei_resources_request(struct apei_resources *resources, apei_resources_init(&nvs_resources); rc = apei_get_nvs_resources(&nvs_resources); if (rc) - goto res_fini; + goto nvs_res_fini; rc = apei_resources_sub(resources, &nvs_resources); if (rc) - goto res_fini; + goto nvs_res_fini; + + if (arch_apei_filter_addr) { + apei_resources_init(&arch_res); + rc = apei_get_arch_resources(&arch_res); + if (rc) + goto arch_res_fini; + rc = apei_resources_sub(resources, &arch_res); + if (rc) + goto arch_res_fini; + } rc = -EINVAL; list_for_each_entry(res, &resources->iomem, list) { @@ -536,7 +554,9 @@ err_unmap_iomem: break; release_mem_region(res->start, res->end - res->start); } -res_fini: +arch_res_fini: + apei_resources_fini(&arch_res); +nvs_res_fini: apei_resources_fini(&nvs_resources); return rc; } diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index c0d44d394ca..735db11a9b0 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -1027,7 +1027,6 @@ EXPORT_SYMBOL_GPL(acpi_subsys_freeze); static struct dev_pm_domain acpi_general_pm_domain = { .ops = { -#ifdef CONFIG_PM .runtime_suspend = acpi_subsys_runtime_suspend, .runtime_resume = acpi_subsys_runtime_resume, #ifdef CONFIG_PM_SLEEP @@ -1041,7 +1040,6 @@ static struct dev_pm_domain acpi_general_pm_domain = { .poweroff_late = acpi_subsys_suspend_late, .restore_early = acpi_subsys_resume_early, #endif -#endif }, }; diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 1b5853f384e..14d0c89ada2 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1,8 +1,8 @@ /* - * ec.c - ACPI Embedded Controller Driver (v2.2) + * ec.c - ACPI Embedded Controller Driver (v3) * - * Copyright (C) 2001-2014 Intel Corporation - * Author: 2014 Lv Zheng <lv.zheng@intel.com> + * Copyright (C) 2001-2015 Intel Corporation + * Author: 2014, 2015 Lv Zheng <lv.zheng@intel.com> * 2006, 2007 Alexey Starikovskiy <alexey.y.starikovskiy@intel.com> * 2006 Denis Sadykov <denis.m.sadykov@intel.com> * 2004 Luming Yu <luming.yu@intel.com> @@ -31,6 +31,7 @@ /* Uncomment next line to get verbose printout */ /* #define DEBUG */ +#define DEBUG_REF 0 #define pr_fmt(fmt) "ACPI : EC: " fmt #include <linux/kernel.h> @@ -71,20 +72,32 @@ enum ec_command { #define ACPI_EC_DELAY 500 /* Wait 500ms max. during EC ops */ #define ACPI_EC_UDELAY_GLK 1000 /* Wait 1ms max. to get global lock */ #define ACPI_EC_MSI_UDELAY 550 /* Wait 550us for MSI EC */ +#define ACPI_EC_UDELAY_POLL 1000 /* Wait 1ms for EC transaction polling */ #define ACPI_EC_CLEAR_MAX 100 /* Maximum number of events to query * when trying to clear the EC */ enum { - EC_FLAGS_QUERY_PENDING, /* Query is pending */ - EC_FLAGS_GPE_STORM, /* GPE storm detected */ + EC_FLAGS_EVENT_ENABLED, /* Event is enabled */ + EC_FLAGS_EVENT_PENDING, /* Event is pending */ + EC_FLAGS_EVENT_DETECTED, /* Event is detected */ EC_FLAGS_HANDLERS_INSTALLED, /* Handlers for GPE and * OpReg are installed */ - EC_FLAGS_BLOCKED, /* Transactions are blocked */ + EC_FLAGS_STARTED, /* Driver is started */ + EC_FLAGS_STOPPED, /* Driver is stopped */ + EC_FLAGS_COMMAND_STORM, /* GPE storms occurred to the + * current command processing */ }; #define ACPI_EC_COMMAND_POLL 0x01 /* Available for command byte */ #define ACPI_EC_COMMAND_COMPLETE 0x02 /* Completed last byte */ +#define ec_debug_ref(ec, fmt, ...) \ + do { \ + if (DEBUG_REF) \ + pr_debug("%lu: " fmt, ec->reference_count, \ + ## __VA_ARGS__); \ + } while (0) + /* ec.c is compiled in acpi namespace so this shows up as acpi.ec_delay param */ static unsigned int ec_delay __read_mostly = ACPI_EC_DELAY; module_param(ec_delay, uint, 0644); @@ -105,6 +118,7 @@ struct acpi_ec_query_handler { acpi_handle handle; void *data; u8 query_bit; + struct kref kref; }; struct transaction { @@ -117,8 +131,12 @@ struct transaction { u8 wlen; u8 rlen; u8 flags; + unsigned long timestamp; }; +static int acpi_ec_query(struct acpi_ec *ec, u8 *data); +static void advance_transaction(struct acpi_ec *ec); + struct acpi_ec *boot_ec, *first_ec; EXPORT_SYMBOL(first_ec); @@ -129,7 +147,28 @@ static int EC_FLAGS_CLEAR_ON_RESUME; /* Needs acpi_ec_clear() on boot/resume */ static int EC_FLAGS_QUERY_HANDSHAKE; /* Needs QR_EC issued when SCI_EVT set */ /* -------------------------------------------------------------------------- - * Transaction Management + * Device Flags + * -------------------------------------------------------------------------- */ + +static bool acpi_ec_started(struct acpi_ec *ec) +{ + return test_bit(EC_FLAGS_STARTED, &ec->flags) && + !test_bit(EC_FLAGS_STOPPED, &ec->flags); +} + +static bool acpi_ec_flushed(struct acpi_ec *ec) +{ + return ec->reference_count == 1; +} + +static bool acpi_ec_has_pending_event(struct acpi_ec *ec) +{ + return test_bit(EC_FLAGS_EVENT_DETECTED, &ec->flags) || + test_bit(EC_FLAGS_EVENT_PENDING, &ec->flags); +} + +/* -------------------------------------------------------------------------- + * EC Registers * -------------------------------------------------------------------------- */ static inline u8 acpi_ec_read_status(struct acpi_ec *ec) @@ -151,6 +190,7 @@ static inline u8 acpi_ec_read_data(struct acpi_ec *ec) { u8 x = inb(ec->data_addr); + ec->curr->timestamp = jiffies; pr_debug("EC_DATA(R) = 0x%2.2x\n", x); return x; } @@ -159,12 +199,14 @@ static inline void acpi_ec_write_cmd(struct acpi_ec *ec, u8 command) { pr_debug("EC_SC(W) = 0x%2.2x\n", command); outb(command, ec->command_addr); + ec->curr->timestamp = jiffies; } static inline void acpi_ec_write_data(struct acpi_ec *ec, u8 data) { pr_debug("EC_DATA(W) = 0x%2.2x\n", data); outb(data, ec->data_addr); + ec->curr->timestamp = jiffies; } #ifdef DEBUG @@ -188,6 +230,203 @@ static const char *acpi_ec_cmd_string(u8 cmd) #define acpi_ec_cmd_string(cmd) "UNDEF" #endif +/* -------------------------------------------------------------------------- + * GPE Registers + * -------------------------------------------------------------------------- */ + +static inline bool acpi_ec_is_gpe_raised(struct acpi_ec *ec) +{ + acpi_event_status gpe_status = 0; + + (void)acpi_get_gpe_status(NULL, ec->gpe, &gpe_status); + return (gpe_status & ACPI_EVENT_FLAG_SET) ? true : false; +} + +static inline void acpi_ec_enable_gpe(struct acpi_ec *ec, bool open) +{ + if (open) + acpi_enable_gpe(NULL, ec->gpe); + else { + BUG_ON(ec->reference_count < 1); + acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_ENABLE); + } + if (acpi_ec_is_gpe_raised(ec)) { + /* + * On some platforms, EN=1 writes cannot trigger GPE. So + * software need to manually trigger a pseudo GPE event on + * EN=1 writes. + */ + pr_debug("***** Polling quirk *****\n"); + advance_transaction(ec); + } +} + +static inline void acpi_ec_disable_gpe(struct acpi_ec *ec, bool close) +{ + if (close) + acpi_disable_gpe(NULL, ec->gpe); + else { + BUG_ON(ec->reference_count < 1); + acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_DISABLE); + } +} + +static inline void acpi_ec_clear_gpe(struct acpi_ec *ec) +{ + /* + * GPE STS is a W1C register, which means: + * 1. Software can clear it without worrying about clearing other + * GPEs' STS bits when the hardware sets them in parallel. + * 2. As long as software can ensure only clearing it when it is + * set, hardware won't set it in parallel. + * So software can clear GPE in any contexts. + * Warning: do not move the check into advance_transaction() as the + * EC commands will be sent without GPE raised. + */ + if (!acpi_ec_is_gpe_raised(ec)) + return; + acpi_clear_gpe(NULL, ec->gpe); +} + +/* -------------------------------------------------------------------------- + * Transaction Management + * -------------------------------------------------------------------------- */ + +static void acpi_ec_submit_request(struct acpi_ec *ec) +{ + ec->reference_count++; + if (ec->reference_count == 1) + acpi_ec_enable_gpe(ec, true); +} + +static void acpi_ec_complete_request(struct acpi_ec *ec) +{ + bool flushed = false; + + ec->reference_count--; + if (ec->reference_count == 0) + acpi_ec_disable_gpe(ec, true); + flushed = acpi_ec_flushed(ec); + if (flushed) + wake_up(&ec->wait); +} + +static void acpi_ec_set_storm(struct acpi_ec *ec, u8 flag) +{ + if (!test_bit(flag, &ec->flags)) { + acpi_ec_disable_gpe(ec, false); + pr_debug("+++++ Polling enabled +++++\n"); + set_bit(flag, &ec->flags); + } +} + +static void acpi_ec_clear_storm(struct acpi_ec *ec, u8 flag) +{ + if (test_bit(flag, &ec->flags)) { + clear_bit(flag, &ec->flags); + acpi_ec_enable_gpe(ec, false); + pr_debug("+++++ Polling disabled +++++\n"); + } +} + +/* + * acpi_ec_submit_flushable_request() - Increase the reference count unless + * the flush operation is not in + * progress + * @ec: the EC device + * @allow_event: whether event should be handled + * + * This function must be used before taking a new action that should hold + * the reference count. If this function returns false, then the action + * must be discarded or it will prevent the flush operation from being + * completed. + * + * During flushing, QR_EC command need to pass this check when there is a + * pending event, so that the reference count held for the pending event + * can be decreased by the completion of the QR_EC command. + */ +static bool acpi_ec_submit_flushable_request(struct acpi_ec *ec, + bool allow_event) +{ + if (!acpi_ec_started(ec)) { + if (!allow_event || !acpi_ec_has_pending_event(ec)) + return false; + } + acpi_ec_submit_request(ec); + return true; +} + +static void acpi_ec_submit_event(struct acpi_ec *ec) +{ + if (!test_bit(EC_FLAGS_EVENT_DETECTED, &ec->flags) || + !test_bit(EC_FLAGS_EVENT_ENABLED, &ec->flags)) + return; + /* Hold reference for pending event */ + if (!acpi_ec_submit_flushable_request(ec, true)) + return; + ec_debug_ref(ec, "Increase event\n"); + if (!test_and_set_bit(EC_FLAGS_EVENT_PENDING, &ec->flags)) { + pr_debug("***** Event query started *****\n"); + schedule_work(&ec->work); + return; + } + acpi_ec_complete_request(ec); + ec_debug_ref(ec, "Decrease event\n"); +} + +static void acpi_ec_complete_event(struct acpi_ec *ec) +{ + if (ec->curr->command == ACPI_EC_COMMAND_QUERY) { + clear_bit(EC_FLAGS_EVENT_PENDING, &ec->flags); + pr_debug("***** Event query stopped *****\n"); + /* Unhold reference for pending event */ + acpi_ec_complete_request(ec); + ec_debug_ref(ec, "Decrease event\n"); + /* Check if there is another SCI_EVT detected */ + acpi_ec_submit_event(ec); + } +} + +static void acpi_ec_submit_detection(struct acpi_ec *ec) +{ + /* Hold reference for query submission */ + if (!acpi_ec_submit_flushable_request(ec, false)) + return; + ec_debug_ref(ec, "Increase query\n"); + if (!test_and_set_bit(EC_FLAGS_EVENT_DETECTED, &ec->flags)) { + pr_debug("***** Event detection blocked *****\n"); + acpi_ec_submit_event(ec); + return; + } + acpi_ec_complete_request(ec); + ec_debug_ref(ec, "Decrease query\n"); +} + +static void acpi_ec_complete_detection(struct acpi_ec *ec) +{ + if (ec->curr->command == ACPI_EC_COMMAND_QUERY) { + clear_bit(EC_FLAGS_EVENT_DETECTED, &ec->flags); + pr_debug("***** Event detetion unblocked *****\n"); + /* Unhold reference for query submission */ + acpi_ec_complete_request(ec); + ec_debug_ref(ec, "Decrease query\n"); + } +} + +static void acpi_ec_enable_event(struct acpi_ec *ec) +{ + unsigned long flags; + + spin_lock_irqsave(&ec->lock, flags); + set_bit(EC_FLAGS_EVENT_ENABLED, &ec->flags); + /* + * An event may be pending even with SCI_EVT=0, so QR_EC should + * always be issued right after started. + */ + acpi_ec_submit_detection(ec); + spin_unlock_irqrestore(&ec->lock, flags); +} + static int ec_transaction_completed(struct acpi_ec *ec) { unsigned long flags; @@ -200,7 +439,7 @@ static int ec_transaction_completed(struct acpi_ec *ec) return ret; } -static bool advance_transaction(struct acpi_ec *ec) +static void advance_transaction(struct acpi_ec *ec) { struct transaction *t; u8 status; @@ -208,6 +447,12 @@ static bool advance_transaction(struct acpi_ec *ec) pr_debug("===== %s (%d) =====\n", in_interrupt() ? "IRQ" : "TASK", smp_processor_id()); + /* + * By always clearing STS before handling all indications, we can + * ensure a hardware STS 0->1 change after this clearing can always + * trigger a GPE interrupt. + */ + acpi_ec_clear_gpe(ec); status = acpi_ec_read_status(ec); t = ec->curr; if (!t) @@ -223,6 +468,7 @@ static bool advance_transaction(struct acpi_ec *ec) t->rdata[t->ri++] = acpi_ec_read_data(ec); if (t->rlen == t->ri) { t->flags |= ACPI_EC_COMMAND_COMPLETE; + acpi_ec_complete_event(ec); if (t->command == ACPI_EC_COMMAND_QUERY) pr_debug("***** Command(%s) hardware completion *****\n", acpi_ec_cmd_string(t->command)); @@ -233,25 +479,29 @@ static bool advance_transaction(struct acpi_ec *ec) } else if (t->wlen == t->wi && (status & ACPI_EC_FLAG_IBF) == 0) { t->flags |= ACPI_EC_COMMAND_COMPLETE; + acpi_ec_complete_event(ec); wakeup = true; } - return wakeup; + goto out; } else { if (EC_FLAGS_QUERY_HANDSHAKE && !(status & ACPI_EC_FLAG_SCI) && (t->command == ACPI_EC_COMMAND_QUERY)) { t->flags |= ACPI_EC_COMMAND_POLL; + acpi_ec_complete_detection(ec); t->rdata[t->ri++] = 0x00; t->flags |= ACPI_EC_COMMAND_COMPLETE; + acpi_ec_complete_event(ec); pr_debug("***** Command(%s) software completion *****\n", acpi_ec_cmd_string(t->command)); wakeup = true; } else if ((status & ACPI_EC_FLAG_IBF) == 0) { acpi_ec_write_cmd(ec, t->command); t->flags |= ACPI_EC_COMMAND_POLL; + acpi_ec_complete_detection(ec); } else goto err; - return wakeup; + goto out; } err: /* @@ -259,28 +509,27 @@ err: * otherwise will take a not handled IRQ as a false one. */ if (!(status & ACPI_EC_FLAG_SCI)) { - if (in_interrupt() && t) - ++t->irq_count; + if (in_interrupt() && t) { + if (t->irq_count < ec_storm_threshold) + ++t->irq_count; + /* Allow triggering on 0 threshold */ + if (t->irq_count == ec_storm_threshold) + acpi_ec_set_storm(ec, EC_FLAGS_COMMAND_STORM); + } } - return wakeup; +out: + if (status & ACPI_EC_FLAG_SCI) + acpi_ec_submit_detection(ec); + if (wakeup && in_interrupt()) + wake_up(&ec->wait); } static void start_transaction(struct acpi_ec *ec) { ec->curr->irq_count = ec->curr->wi = ec->curr->ri = 0; ec->curr->flags = 0; - (void)advance_transaction(ec); -} - -static int acpi_ec_sync_query(struct acpi_ec *ec, u8 *data); - -static int ec_check_sci_sync(struct acpi_ec *ec, u8 state) -{ - if (state & ACPI_EC_FLAG_SCI) { - if (!test_and_set_bit(EC_FLAGS_QUERY_PENDING, &ec->flags)) - return acpi_ec_sync_query(ec, NULL); - } - return 0; + ec->curr->timestamp = jiffies; + advance_transaction(ec); } static int ec_poll(struct acpi_ec *ec) @@ -291,20 +540,25 @@ static int ec_poll(struct acpi_ec *ec) while (repeat--) { unsigned long delay = jiffies + msecs_to_jiffies(ec_delay); + unsigned long usecs = ACPI_EC_UDELAY_POLL; do { /* don't sleep with disabled interrupts */ if (EC_FLAGS_MSI || irqs_disabled()) { - udelay(ACPI_EC_MSI_UDELAY); + usecs = ACPI_EC_MSI_UDELAY; + udelay(usecs); if (ec_transaction_completed(ec)) return 0; } else { if (wait_event_timeout(ec->wait, ec_transaction_completed(ec), - msecs_to_jiffies(1))) + usecs_to_jiffies(usecs))) return 0; } spin_lock_irqsave(&ec->lock, flags); - (void)advance_transaction(ec); + if (time_after(jiffies, + ec->curr->timestamp + + usecs_to_jiffies(usecs))) + advance_transaction(ec); spin_unlock_irqrestore(&ec->lock, flags); } while (time_before(jiffies, delay)); pr_debug("controller reset, restart transaction\n"); @@ -325,21 +579,29 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec, udelay(ACPI_EC_MSI_UDELAY); /* start transaction */ spin_lock_irqsave(&ec->lock, tmp); + /* Enable GPE for command processing (IBF=0/OBF=1) */ + if (!acpi_ec_submit_flushable_request(ec, true)) { + ret = -EINVAL; + goto unlock; + } + ec_debug_ref(ec, "Increase command\n"); /* following two actions should be kept atomic */ ec->curr = t; pr_debug("***** Command(%s) started *****\n", acpi_ec_cmd_string(t->command)); start_transaction(ec); - if (ec->curr->command == ACPI_EC_COMMAND_QUERY) { - clear_bit(EC_FLAGS_QUERY_PENDING, &ec->flags); - pr_debug("***** Event stopped *****\n"); - } spin_unlock_irqrestore(&ec->lock, tmp); ret = ec_poll(ec); spin_lock_irqsave(&ec->lock, tmp); + if (t->irq_count == ec_storm_threshold) + acpi_ec_clear_storm(ec, EC_FLAGS_COMMAND_STORM); pr_debug("***** Command(%s) stopped *****\n", acpi_ec_cmd_string(t->command)); ec->curr = NULL; + /* Disable GPE for command processing (IBF=0/OBF=1) */ + acpi_ec_complete_request(ec); + ec_debug_ref(ec, "Decrease command\n"); +unlock: spin_unlock_irqrestore(&ec->lock, tmp); return ret; } @@ -354,10 +616,6 @@ static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t) if (t->rdata) memset(t->rdata, 0, t->rlen); mutex_lock(&ec->mutex); - if (test_bit(EC_FLAGS_BLOCKED, &ec->flags)) { - status = -EINVAL; - goto unlock; - } if (ec->global_lock) { status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk); if (ACPI_FAILURE(status)) { @@ -365,26 +623,11 @@ static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t) goto unlock; } } - /* disable GPE during transaction if storm is detected */ - if (test_bit(EC_FLAGS_GPE_STORM, &ec->flags)) { - /* It has to be disabled, so that it doesn't trigger. */ - acpi_disable_gpe(NULL, ec->gpe); - } status = acpi_ec_transaction_unlocked(ec, t); - /* check if we received SCI during transaction */ - ec_check_sci_sync(ec, acpi_ec_read_status(ec)); - if (test_bit(EC_FLAGS_GPE_STORM, &ec->flags)) { + if (test_bit(EC_FLAGS_COMMAND_STORM, &ec->flags)) msleep(1); - /* It is safe to enable the GPE outside of the transaction. */ - acpi_enable_gpe(NULL, ec->gpe); - } else if (t->irq_count > ec_storm_threshold) { - pr_info("GPE storm detected(%d GPEs), " - "transactions will use polling mode\n", - t->irq_count); - set_bit(EC_FLAGS_GPE_STORM, &ec->flags); - } if (ec->global_lock) acpi_release_global_lock(glk); unlock: @@ -500,7 +743,7 @@ static void acpi_ec_clear(struct acpi_ec *ec) u8 value = 0; for (i = 0; i < ACPI_EC_CLEAR_MAX; i++) { - status = acpi_ec_sync_query(ec, &value); + status = acpi_ec_query(ec, &value); if (status || !value) break; } @@ -511,6 +754,57 @@ static void acpi_ec_clear(struct acpi_ec *ec) pr_info("%d stale EC events cleared\n", i); } +static void acpi_ec_start(struct acpi_ec *ec, bool resuming) +{ + unsigned long flags; + + spin_lock_irqsave(&ec->lock, flags); + if (!test_and_set_bit(EC_FLAGS_STARTED, &ec->flags)) { + pr_debug("+++++ Starting EC +++++\n"); + /* Enable GPE for event processing (SCI_EVT=1) */ + if (!resuming) { + acpi_ec_submit_request(ec); + ec_debug_ref(ec, "Increase driver\n"); + } + pr_info("+++++ EC started +++++\n"); + } + spin_unlock_irqrestore(&ec->lock, flags); +} + +static bool acpi_ec_stopped(struct acpi_ec *ec) +{ + unsigned long flags; + bool flushed; + + spin_lock_irqsave(&ec->lock, flags); + flushed = acpi_ec_flushed(ec); + spin_unlock_irqrestore(&ec->lock, flags); + return flushed; +} + +static void acpi_ec_stop(struct acpi_ec *ec, bool suspending) +{ + unsigned long flags; + + spin_lock_irqsave(&ec->lock, flags); + if (acpi_ec_started(ec)) { + pr_debug("+++++ Stopping EC +++++\n"); + set_bit(EC_FLAGS_STOPPED, &ec->flags); + spin_unlock_irqrestore(&ec->lock, flags); + wait_event(ec->wait, acpi_ec_stopped(ec)); + spin_lock_irqsave(&ec->lock, flags); + /* Disable GPE for event processing (SCI_EVT=1) */ + if (!suspending) { + acpi_ec_complete_request(ec); + ec_debug_ref(ec, "Decrease driver\n"); + } + clear_bit(EC_FLAGS_STARTED, &ec->flags); + clear_bit(EC_FLAGS_STOPPED, &ec->flags); + pr_info("+++++ EC stopped +++++\n"); + } + spin_unlock_irqrestore(&ec->lock, flags); +} + void acpi_ec_block_transactions(void) { struct acpi_ec *ec = first_ec; @@ -520,7 +814,7 @@ void acpi_ec_block_transactions(void) mutex_lock(&ec->mutex); /* Prevent transactions from being carried out */ - set_bit(EC_FLAGS_BLOCKED, &ec->flags); + acpi_ec_stop(ec, true); mutex_unlock(&ec->mutex); } @@ -531,14 +825,11 @@ void acpi_ec_unblock_transactions(void) if (!ec) return; - mutex_lock(&ec->mutex); /* Allow transactions to be carried out again */ - clear_bit(EC_FLAGS_BLOCKED, &ec->flags); + acpi_ec_start(ec, true); if (EC_FLAGS_CLEAR_ON_RESUME) acpi_ec_clear(ec); - - mutex_unlock(&ec->mutex); } void acpi_ec_unblock_transactions_early(void) @@ -548,36 +839,33 @@ void acpi_ec_unblock_transactions_early(void) * atomic context during wakeup, so we don't need to acquire the mutex). */ if (first_ec) - clear_bit(EC_FLAGS_BLOCKED, &first_ec->flags); + acpi_ec_start(first_ec, true); } -static int acpi_ec_query_unlocked(struct acpi_ec *ec, u8 *data) +/* -------------------------------------------------------------------------- + Event Management + -------------------------------------------------------------------------- */ +static struct acpi_ec_query_handler * +acpi_ec_get_query_handler(struct acpi_ec_query_handler *handler) { - int result; - u8 d; - struct transaction t = {.command = ACPI_EC_COMMAND_QUERY, - .wdata = NULL, .rdata = &d, - .wlen = 0, .rlen = 1}; + if (handler) + kref_get(&handler->kref); + return handler; +} - if (!ec || !data) - return -EINVAL; - /* - * Query the EC to find out which _Qxx method we need to evaluate. - * Note that successful completion of the query causes the ACPI_EC_SCI - * bit to be cleared (and thus clearing the interrupt source). - */ - result = acpi_ec_transaction_unlocked(ec, &t); - if (result) - return result; - if (!d) - return -ENODATA; - *data = d; - return 0; +static void acpi_ec_query_handler_release(struct kref *kref) +{ + struct acpi_ec_query_handler *handler = + container_of(kref, struct acpi_ec_query_handler, kref); + + kfree(handler); +} + +static void acpi_ec_put_query_handler(struct acpi_ec_query_handler *handler) +{ + kref_put(&handler->kref, acpi_ec_query_handler_release); } -/* -------------------------------------------------------------------------- - Event Management - -------------------------------------------------------------------------- */ int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit, acpi_handle handle, acpi_ec_query_func func, void *data) @@ -593,6 +881,7 @@ int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit, handler->func = func; handler->data = data; mutex_lock(&ec->mutex); + kref_init(&handler->kref); list_add(&handler->node, &ec->list); mutex_unlock(&ec->mutex); return 0; @@ -602,15 +891,18 @@ EXPORT_SYMBOL_GPL(acpi_ec_add_query_handler); void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit) { struct acpi_ec_query_handler *handler, *tmp; + LIST_HEAD(free_list); mutex_lock(&ec->mutex); list_for_each_entry_safe(handler, tmp, &ec->list, node) { if (query_bit == handler->query_bit) { - list_del(&handler->node); - kfree(handler); + list_del_init(&handler->node); + list_add(&handler->node, &free_list); } } mutex_unlock(&ec->mutex); + list_for_each_entry(handler, &free_list, node) + acpi_ec_put_query_handler(handler); } EXPORT_SYMBOL_GPL(acpi_ec_remove_query_handler); @@ -626,59 +918,58 @@ static void acpi_ec_run(void *cxt) else if (handler->handle) acpi_evaluate_object(handler->handle, NULL, NULL, NULL); pr_debug("##### Query(0x%02x) stopped #####\n", handler->query_bit); - kfree(handler); + acpi_ec_put_query_handler(handler); } -static int acpi_ec_sync_query(struct acpi_ec *ec, u8 *data) +static int acpi_ec_query(struct acpi_ec *ec, u8 *data) { u8 value = 0; - int status; - struct acpi_ec_query_handler *handler, *copy; + int result; + acpi_status status; + struct acpi_ec_query_handler *handler; + struct transaction t = {.command = ACPI_EC_COMMAND_QUERY, + .wdata = NULL, .rdata = &value, + .wlen = 0, .rlen = 1}; - status = acpi_ec_query_unlocked(ec, &value); + /* + * Query the EC to find out which _Qxx method we need to evaluate. + * Note that successful completion of the query causes the ACPI_EC_SCI + * bit to be cleared (and thus clearing the interrupt source). + */ + result = acpi_ec_transaction(ec, &t); + if (result) + return result; if (data) *data = value; - if (status) - return status; + if (!value) + return -ENODATA; + mutex_lock(&ec->mutex); list_for_each_entry(handler, &ec->list, node) { if (value == handler->query_bit) { /* have custom handler for this bit */ - copy = kmalloc(sizeof(*handler), GFP_KERNEL); - if (!copy) - return -ENOMEM; - memcpy(copy, handler, sizeof(*copy)); + handler = acpi_ec_get_query_handler(handler); pr_debug("##### Query(0x%02x) scheduled #####\n", handler->query_bit); - return acpi_os_execute((copy->func) ? + status = acpi_os_execute((handler->func) ? OSL_NOTIFY_HANDLER : OSL_GPE_HANDLER, - acpi_ec_run, copy); + acpi_ec_run, handler); + if (ACPI_FAILURE(status)) + result = -EBUSY; + break; } } - return 0; -} - -static void acpi_ec_gpe_query(void *ec_cxt) -{ - struct acpi_ec *ec = ec_cxt; - - if (!ec) - return; - mutex_lock(&ec->mutex); - acpi_ec_sync_query(ec, NULL); mutex_unlock(&ec->mutex); + return result; } -static int ec_check_sci(struct acpi_ec *ec, u8 state) +static void acpi_ec_gpe_poller(struct work_struct *work) { - if (state & ACPI_EC_FLAG_SCI) { - if (!test_and_set_bit(EC_FLAGS_QUERY_PENDING, &ec->flags)) { - pr_debug("***** Event started *****\n"); - return acpi_os_execute(OSL_NOTIFY_HANDLER, - acpi_ec_gpe_query, ec); - } - } - return 0; + struct acpi_ec *ec = container_of(work, struct acpi_ec, work); + + pr_debug("***** Event poller started *****\n"); + acpi_ec_query(ec, NULL); + pr_debug("***** Event poller stopped *****\n"); } static u32 acpi_ec_gpe_handler(acpi_handle gpe_device, @@ -688,11 +979,9 @@ static u32 acpi_ec_gpe_handler(acpi_handle gpe_device, struct acpi_ec *ec = data; spin_lock_irqsave(&ec->lock, flags); - if (advance_transaction(ec)) - wake_up(&ec->wait); + advance_transaction(ec); spin_unlock_irqrestore(&ec->lock, flags); - ec_check_sci(ec, acpi_ec_read_status(ec)); - return ACPI_INTERRUPT_HANDLED | ACPI_REENABLE_GPE; + return ACPI_INTERRUPT_HANDLED; } /* -------------------------------------------------------------------------- @@ -750,11 +1039,11 @@ static struct acpi_ec *make_acpi_ec(void) if (!ec) return NULL; - ec->flags = 1 << EC_FLAGS_QUERY_PENDING; mutex_init(&ec->mutex); init_waitqueue_head(&ec->wait); INIT_LIST_HEAD(&ec->list); spin_lock_init(&ec->lock); + INIT_WORK(&ec->work, acpi_ec_gpe_poller); return ec; } @@ -810,13 +1099,13 @@ static int ec_install_handlers(struct acpi_ec *ec) if (test_bit(EC_FLAGS_HANDLERS_INSTALLED, &ec->flags)) return 0; - status = acpi_install_gpe_handler(NULL, ec->gpe, + status = acpi_install_gpe_raw_handler(NULL, ec->gpe, ACPI_GPE_EDGE_TRIGGERED, &acpi_ec_gpe_handler, ec); if (ACPI_FAILURE(status)) return -ENODEV; - acpi_enable_gpe(NULL, ec->gpe); + acpi_ec_start(ec, false); status = acpi_install_address_space_handler(ec->handle, ACPI_ADR_SPACE_EC, &acpi_ec_space_handler, @@ -831,7 +1120,7 @@ static int ec_install_handlers(struct acpi_ec *ec) pr_err("Fail in evaluating the _REG object" " of EC device. Broken bios is suspected.\n"); } else { - acpi_disable_gpe(NULL, ec->gpe); + acpi_ec_stop(ec, false); acpi_remove_gpe_handler(NULL, ec->gpe, &acpi_ec_gpe_handler); return -ENODEV; @@ -846,7 +1135,7 @@ static void ec_remove_handlers(struct acpi_ec *ec) { if (!test_bit(EC_FLAGS_HANDLERS_INSTALLED, &ec->flags)) return; - acpi_disable_gpe(NULL, ec->gpe); + acpi_ec_stop(ec, false); if (ACPI_FAILURE(acpi_remove_address_space_handler(ec->handle, ACPI_ADR_SPACE_EC, &acpi_ec_space_handler))) pr_err("failed to remove space handler\n"); @@ -900,14 +1189,11 @@ static int acpi_ec_add(struct acpi_device *device) ret = ec_install_handlers(ec); /* EC is fully operational, allow queries */ - clear_bit(EC_FLAGS_QUERY_PENDING, &ec->flags); + acpi_ec_enable_event(ec); /* Clear stale _Q events if hardware might require that */ - if (EC_FLAGS_CLEAR_ON_RESUME) { - mutex_lock(&ec->mutex); + if (EC_FLAGS_CLEAR_ON_RESUME) acpi_ec_clear(ec); - mutex_unlock(&ec->mutex); - } return ret; } diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 163e82f536f..56b321aa2b1 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -35,6 +35,13 @@ void acpi_int340x_thermal_init(void); int acpi_sysfs_init(void); void acpi_container_init(void); void acpi_memory_hotplug_init(void); +#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC +int acpi_ioapic_add(struct acpi_pci_root *root); +int acpi_ioapic_remove(struct acpi_pci_root *root); +#else +static inline int acpi_ioapic_add(struct acpi_pci_root *root) { return 0; } +static inline int acpi_ioapic_remove(struct acpi_pci_root *root) { return 0; } +#endif #ifdef CONFIG_ACPI_DOCK void register_dock_dependent_device(struct acpi_device *adev, acpi_handle dshandle); @@ -68,6 +75,8 @@ static inline void acpi_debugfs_init(void) { return; } #endif void acpi_lpss_init(void); +void acpi_apd_init(void); + acpi_status acpi_hotplug_schedule(struct acpi_device *adev, u32 src); bool acpi_queue_hotplug_work(struct work_struct *work); void acpi_device_hotplug(struct acpi_device *adev, u32 src); @@ -122,11 +131,13 @@ struct acpi_ec { unsigned long data_addr; unsigned long global_lock; unsigned long flags; + unsigned long reference_count; struct mutex mutex; wait_queue_head_t wait; struct list_head list; struct transaction *curr; spinlock_t lock; + struct work_struct work; }; extern struct acpi_ec *first_ec; diff --git a/drivers/acpi/ioapic.c b/drivers/acpi/ioapic.c new file mode 100644 index 00000000000..ccdc8db16bb --- /dev/null +++ b/drivers/acpi/ioapic.c @@ -0,0 +1,229 @@ +/* + * IOAPIC/IOxAPIC/IOSAPIC driver + * + * Copyright (C) 2009 Fujitsu Limited. + * (c) Copyright 2009 Hewlett-Packard Development Company, L.P. + * + * Copyright (C) 2014 Intel Corporation + * + * 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. + * + * Based on original drivers/pci/ioapic.c + * Yinghai Lu <yinghai@kernel.org> + * Jiang Liu <jiang.liu@intel.com> + */ + +/* + * This driver manages I/O APICs added by hotplug after boot. + * We try to claim all I/O APIC devices, but those present at boot were + * registered when we parsed the ACPI MADT. + */ + +#define pr_fmt(fmt) "ACPI : IOAPIC: " fmt + +#include <linux/slab.h> +#include <linux/acpi.h> +#include <linux/pci.h> +#include <acpi/acpi.h> + +struct acpi_pci_ioapic { + acpi_handle root_handle; + acpi_handle handle; + u32 gsi_base; + struct resource res; + struct pci_dev *pdev; + struct list_head list; +}; + +static LIST_HEAD(ioapic_list); +static DEFINE_MUTEX(ioapic_list_lock); + +static acpi_status setup_res(struct acpi_resource *acpi_res, void *data) +{ + struct resource *res = data; + struct resource_win win; + + res->flags = 0; + if (acpi_dev_filter_resource_type(acpi_res, IORESOURCE_MEM) == 0) + return AE_OK; + + if (!acpi_dev_resource_memory(acpi_res, res)) { + if (acpi_dev_resource_address_space(acpi_res, &win) || + acpi_dev_resource_ext_address_space(acpi_res, &win)) + *res = win.res; + } + if ((res->flags & IORESOURCE_PREFETCH) || + (res->flags & IORESOURCE_DISABLED)) + res->flags = 0; + + return AE_CTRL_TERMINATE; +} + +static bool acpi_is_ioapic(acpi_handle handle, char **type) +{ + acpi_status status; + struct acpi_device_info *info; + char *hid = NULL; + bool match = false; + + if (!acpi_has_method(handle, "_GSB")) + return false; + + status = acpi_get_object_info(handle, &info); + if (ACPI_SUCCESS(status)) { + if (info->valid & ACPI_VALID_HID) + hid = info->hardware_id.string; + if (hid) { + if (strcmp(hid, "ACPI0009") == 0) { + *type = "IOxAPIC"; + match = true; + } else if (strcmp(hid, "ACPI000A") == 0) { + *type = "IOAPIC"; + match = true; + } + } + kfree(info); + } + + return match; +} + +static acpi_status handle_ioapic_add(acpi_handle handle, u32 lvl, + void *context, void **rv) +{ + acpi_status status; + unsigned long long gsi_base; + struct acpi_pci_ioapic *ioapic; + struct pci_dev *dev = NULL; + struct resource *res = NULL; + char *type = NULL; + + if (!acpi_is_ioapic(handle, &type)) + return AE_OK; + + mutex_lock(&ioapic_list_lock); + list_for_each_entry(ioapic, &ioapic_list, list) + if (ioapic->handle == handle) { + mutex_unlock(&ioapic_list_lock); + return AE_OK; + } + + status = acpi_evaluate_integer(handle, "_GSB", NULL, &gsi_base); + if (ACPI_FAILURE(status)) { + acpi_handle_warn(handle, "failed to evaluate _GSB method\n"); + goto exit; + } + + ioapic = kzalloc(sizeof(*ioapic), GFP_KERNEL); + if (!ioapic) { + pr_err("cannot allocate memory for new IOAPIC\n"); + goto exit; + } else { + ioapic->root_handle = (acpi_handle)context; + ioapic->handle = handle; + ioapic->gsi_base = (u32)gsi_base; + INIT_LIST_HEAD(&ioapic->list); + } + + if (acpi_ioapic_registered(handle, (u32)gsi_base)) + goto done; + + dev = acpi_get_pci_dev(handle); + if (dev && pci_resource_len(dev, 0)) { + if (pci_enable_device(dev) < 0) + goto exit_put; + pci_set_master(dev); + if (pci_request_region(dev, 0, type)) + goto exit_disable; + res = &dev->resource[0]; + ioapic->pdev = dev; + } else { + pci_dev_put(dev); + dev = NULL; + + res = &ioapic->res; + acpi_walk_resources(handle, METHOD_NAME__CRS, setup_res, res); + if (res->flags == 0) { + acpi_handle_warn(handle, "failed to get resource\n"); + goto exit_free; + } else if (request_resource(&iomem_resource, res)) { + acpi_handle_warn(handle, "failed to insert resource\n"); + goto exit_free; + } + } + + if (acpi_register_ioapic(handle, res->start, (u32)gsi_base)) { + acpi_handle_warn(handle, "failed to register IOAPIC\n"); + goto exit_release; + } +done: + list_add(&ioapic->list, &ioapic_list); + mutex_unlock(&ioapic_list_lock); + + if (dev) + dev_info(&dev->dev, "%s at %pR, GSI %u\n", + type, res, (u32)gsi_base); + else + acpi_handle_info(handle, "%s at %pR, GSI %u\n", + type, res, (u32)gsi_base); + + return AE_OK; + +exit_release: + if (dev) + pci_release_region(dev, 0); + else + release_resource(res); +exit_disable: + if (dev) + pci_disable_device(dev); +exit_put: + pci_dev_put(dev); +exit_free: + kfree(ioapic); +exit: + mutex_unlock(&ioapic_list_lock); + *(acpi_status *)rv = AE_ERROR; + return AE_OK; +} + +int acpi_ioapic_add(struct acpi_pci_root *root) +{ + acpi_status status, retval = AE_OK; + + status = acpi_walk_namespace(ACPI_TYPE_DEVICE, root->device->handle, + UINT_MAX, handle_ioapic_add, NULL, + root->device->handle, (void **)&retval); + + return ACPI_SUCCESS(status) && ACPI_SUCCESS(retval) ? 0 : -ENODEV; +} + +int acpi_ioapic_remove(struct acpi_pci_root *root) +{ + int retval = 0; + struct acpi_pci_ioapic *ioapic, *tmp; + + mutex_lock(&ioapic_list_lock); + list_for_each_entry_safe(ioapic, tmp, &ioapic_list, list) { + if (root->device->handle != ioapic->root_handle) + continue; + + if (acpi_unregister_ioapic(ioapic->handle, ioapic->gsi_base)) + retval = -EBUSY; + + if (ioapic->pdev) { + pci_release_region(ioapic->pdev, 0); + pci_disable_device(ioapic->pdev); + pci_dev_put(ioapic->pdev); + } else if (ioapic->res.flags && ioapic->res.parent) { + release_resource(&ioapic->res); + } + list_del(&ioapic->list); + kfree(ioapic); + } + mutex_unlock(&ioapic_list_lock); + + return retval; +} diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c index 24b5476449a..1333cbdc3ea 100644 --- a/drivers/acpi/numa.c +++ b/drivers/acpi/numa.c @@ -177,12 +177,7 @@ static int __init slit_valid(struct acpi_table_slit *slit) static int __init acpi_parse_slit(struct acpi_table_header *table) { - struct acpi_table_slit *slit; - - if (!table) - return -EINVAL; - - slit = (struct acpi_table_slit *)table; + struct acpi_table_slit *slit = (struct acpi_table_slit *)table; if (!slit_valid(slit)) { printk(KERN_INFO "ACPI: SLIT table looks invalid. Not used.\n"); @@ -260,11 +255,8 @@ acpi_parse_memory_affinity(struct acpi_subtable_header * header, static int __init acpi_parse_srat(struct acpi_table_header *table) { - struct acpi_table_srat *srat; - if (!table) - return -EINVAL; + struct acpi_table_srat *srat = (struct acpi_table_srat *)table; - srat = (struct acpi_table_srat *)table; acpi_srat_revision = srat->header.revision; /* Real work done in acpi_table_parse_srat below. */ diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index b1def411c0b..e7f718d6918 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -485,14 +485,6 @@ void acpi_pci_irq_disable(struct pci_dev *dev) if (!pin || !dev->irq_managed || dev->irq <= 0) return; - /* Keep IOAPIC pin configuration when suspending */ - if (dev->dev.power.is_prepared) - return; -#ifdef CONFIG_PM - if (dev->dev.power.runtime_status == RPM_SUSPENDING) - return; -#endif - entry = acpi_pci_irq_lookup(dev, pin); if (!entry) return; @@ -513,5 +505,6 @@ void acpi_pci_irq_disable(struct pci_dev *dev) if (gsi >= 0) { acpi_unregister_gsi(gsi); dev->irq_managed = 0; + dev->irq = 0; } } diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index c6bcb8c719d..68a5f712cd1 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -112,10 +112,10 @@ get_root_bridge_busnr_callback(struct acpi_resource *resource, void *data) if (ACPI_FAILURE(status)) return AE_OK; - if ((address.address_length > 0) && + if ((address.address.address_length > 0) && (address.resource_type == ACPI_BUS_NUMBER_RANGE)) { - res->start = address.minimum; - res->end = address.minimum + address.address_length - 1; + res->start = address.address.minimum; + res->end = address.address.minimum + address.address.address_length - 1; } return AE_OK; @@ -621,6 +621,7 @@ static int acpi_pci_root_add(struct acpi_device *device, if (hotadd) { pcibios_resource_survey_bus(root->bus); pci_assign_unassigned_root_bus_resources(root->bus); + acpi_ioapic_add(root); } pci_lock_rescan_remove(); @@ -644,6 +645,8 @@ static void acpi_pci_root_remove(struct acpi_device *device) pci_stop_root_bus(root->bus); + WARN_ON(acpi_ioapic_remove(root)); + device_set_run_wake(root->bus->bridge, false); pci_acpi_remove_bus_pm_notifier(device); diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index 02e48394276..7962651cdbd 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -4,6 +4,10 @@ * * Alex Chiang <achiang@hp.com> * - Unified x86/ia64 implementations + * + * I/O APIC hotplug support + * Yinghai Lu <yinghai@kernel.org> + * Jiang Liu <jiang.liu@intel.com> */ #include <linux/export.h> #include <linux/acpi.h> @@ -12,6 +16,21 @@ #define _COMPONENT ACPI_PROCESSOR_COMPONENT ACPI_MODULE_NAME("processor_core"); +static struct acpi_table_madt *get_madt_table(void) +{ + static struct acpi_table_madt *madt; + static int read_madt; + + if (!read_madt) { + if (ACPI_FAILURE(acpi_get_table(ACPI_SIG_MADT, 0, + (struct acpi_table_header **)&madt))) + madt = NULL; + read_madt++; + } + + return madt; +} + static int map_lapic_id(struct acpi_subtable_header *entry, u32 acpi_id, int *apic_id) { @@ -67,17 +86,10 @@ static int map_lsapic_id(struct acpi_subtable_header *entry, static int map_madt_entry(int type, u32 acpi_id) { unsigned long madt_end, entry; - static struct acpi_table_madt *madt; - static int read_madt; int phys_id = -1; /* CPU hardware ID */ + struct acpi_table_madt *madt; - if (!read_madt) { - if (ACPI_FAILURE(acpi_get_table(ACPI_SIG_MADT, 0, - (struct acpi_table_header **)&madt))) - madt = NULL; - read_madt++; - } - + madt = get_madt_table(); if (!madt) return phys_id; @@ -203,3 +215,96 @@ int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id) return acpi_map_cpuid(phys_id, acpi_id); } EXPORT_SYMBOL_GPL(acpi_get_cpuid); + +#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC +static int get_ioapic_id(struct acpi_subtable_header *entry, u32 gsi_base, + u64 *phys_addr, int *ioapic_id) +{ + struct acpi_madt_io_apic *ioapic = (struct acpi_madt_io_apic *)entry; + + if (ioapic->global_irq_base != gsi_base) + return 0; + + *phys_addr = ioapic->address; + *ioapic_id = ioapic->id; + return 1; +} + +static int parse_madt_ioapic_entry(u32 gsi_base, u64 *phys_addr) +{ + struct acpi_subtable_header *hdr; + unsigned long madt_end, entry; + struct acpi_table_madt *madt; + int apic_id = -1; + + madt = get_madt_table(); + if (!madt) + return apic_id; + + entry = (unsigned long)madt; + madt_end = entry + madt->header.length; + + /* Parse all entries looking for a match. */ + entry += sizeof(struct acpi_table_madt); + while (entry + sizeof(struct acpi_subtable_header) < madt_end) { + hdr = (struct acpi_subtable_header *)entry; + if (hdr->type == ACPI_MADT_TYPE_IO_APIC && + get_ioapic_id(hdr, gsi_base, phys_addr, &apic_id)) + break; + else + entry += hdr->length; + } + + return apic_id; +} + +static int parse_mat_ioapic_entry(acpi_handle handle, u32 gsi_base, + u64 *phys_addr) +{ + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + struct acpi_subtable_header *header; + union acpi_object *obj; + int apic_id = -1; + + if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer))) + goto exit; + + if (!buffer.length || !buffer.pointer) + goto exit; + + obj = buffer.pointer; + if (obj->type != ACPI_TYPE_BUFFER || + obj->buffer.length < sizeof(struct acpi_subtable_header)) + goto exit; + + header = (struct acpi_subtable_header *)obj->buffer.pointer; + if (header->type == ACPI_MADT_TYPE_IO_APIC) + get_ioapic_id(header, gsi_base, phys_addr, &apic_id); + +exit: + kfree(buffer.pointer); + return apic_id; +} + +/** + * acpi_get_ioapic_id - Get IOAPIC ID and physical address matching @gsi_base + * @handle: ACPI object for IOAPIC device + * @gsi_base: GSI base to match with + * @phys_addr: Pointer to store physical address of matching IOAPIC record + * + * Walk resources returned by ACPI_MAT method, then ACPI MADT table, to search + * for an ACPI IOAPIC record matching @gsi_base. + * Return IOAPIC id and store physical address in @phys_addr if found a match, + * otherwise return <0. + */ +int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr) +{ + int apic_id; + + apic_id = parse_mat_ioapic_entry(handle, gsi_base, phys_addr); + if (apic_id == -1) + apic_id = parse_madt_ioapic_entry(gsi_base, phys_addr); + + return apic_id; +} +#endif /* CONFIG_ACPI_HOTPLUG_IOAPIC */ diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 87b704e4187..c256bd7fbd7 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -681,15 +681,13 @@ static int acpi_idle_bm_check(void) } /** - * acpi_idle_do_entry - a helper function that does C2 and C3 type entry + * acpi_idle_do_entry - enter idle state using the appropriate method * @cx: cstate data * * Caller disables interrupt before call and enables interrupt after return. */ -static inline void acpi_idle_do_entry(struct acpi_processor_cx *cx) +static void acpi_idle_do_entry(struct acpi_processor_cx *cx) { - /* Don't trace irqs off for idle */ - stop_critical_timings(); if (cx->entry_method == ACPI_CSTATE_FFH) { /* Call into architectural FFH based C-state */ acpi_processor_ffh_cstate_enter(cx); @@ -703,38 +701,9 @@ static inline void acpi_idle_do_entry(struct acpi_processor_cx *cx) gets asserted in time to freeze execution properly. */ inl(acpi_gbl_FADT.xpm_timer_block.address); } - start_critical_timings(); } /** - * acpi_idle_enter_c1 - enters an ACPI C1 state-type - * @dev: the target CPU - * @drv: cpuidle driver containing cpuidle state info - * @index: index of target state - * - * This is equivalent to the HALT instruction. - */ -static int acpi_idle_enter_c1(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) -{ - struct acpi_processor *pr; - struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); - - pr = __this_cpu_read(processors); - - if (unlikely(!pr)) - return -EINVAL; - - lapic_timer_state_broadcast(pr, cx, 1); - acpi_idle_do_entry(cx); - - lapic_timer_state_broadcast(pr, cx, 0); - - return index; -} - - -/** * acpi_idle_play_dead - enters an ACPI state for long-term idle (i.e. off-lining) * @dev: the target CPU * @index: the index of suggested state @@ -761,47 +730,11 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index) return 0; } -/** - * acpi_idle_enter_simple - enters an ACPI state without BM handling - * @dev: the target CPU - * @drv: cpuidle driver with cpuidle state information - * @index: the index of suggested state - */ -static int acpi_idle_enter_simple(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) +static bool acpi_idle_fallback_to_c1(struct acpi_processor *pr) { - struct acpi_processor *pr; - struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); - - pr = __this_cpu_read(processors); - - if (unlikely(!pr)) - return -EINVAL; - -#ifdef CONFIG_HOTPLUG_CPU - if ((cx->type != ACPI_STATE_C1) && (num_online_cpus() > 1) && - !pr->flags.has_cst && - !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED)) - return acpi_idle_enter_c1(dev, drv, CPUIDLE_DRIVER_STATE_START); -#endif - - /* - * Must be done before busmaster disable as we might need to - * access HPET ! - */ - lapic_timer_state_broadcast(pr, cx, 1); - - if (cx->type == ACPI_STATE_C3) - ACPI_FLUSH_CPU_CACHE(); - - /* Tell the scheduler that we are going deep-idle: */ - sched_clock_idle_sleep_event(); - acpi_idle_do_entry(cx); - - sched_clock_idle_wakeup_event(0); - - lapic_timer_state_broadcast(pr, cx, 0); - return index; + return IS_ENABLED(CONFIG_HOTPLUG_CPU) && num_online_cpus() > 1 && + !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED) && + !pr->flags.has_cst; } static int c3_cpu_count; @@ -809,44 +742,14 @@ static DEFINE_RAW_SPINLOCK(c3_lock); /** * acpi_idle_enter_bm - enters C3 with proper BM handling - * @dev: the target CPU - * @drv: cpuidle driver containing state data - * @index: the index of suggested state - * - * If BM is detected, the deepest non-C3 idle state is entered instead. + * @pr: Target processor + * @cx: Target state context */ -static int acpi_idle_enter_bm(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) +static void acpi_idle_enter_bm(struct acpi_processor *pr, + struct acpi_processor_cx *cx) { - struct acpi_processor *pr; - struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); - - pr = __this_cpu_read(processors); - - if (unlikely(!pr)) - return -EINVAL; - -#ifdef CONFIG_HOTPLUG_CPU - if ((cx->type != ACPI_STATE_C1) && (num_online_cpus() > 1) && - !pr->flags.has_cst && - !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED)) - return acpi_idle_enter_c1(dev, drv, CPUIDLE_DRIVER_STATE_START); -#endif - - if (!cx->bm_sts_skip && acpi_idle_bm_check()) { - if (drv->safe_state_index >= 0) { - return drv->states[drv->safe_state_index].enter(dev, - drv, drv->safe_state_index); - } else { - acpi_safe_halt(); - return -EBUSY; - } - } - acpi_unlazy_tlb(smp_processor_id()); - /* Tell the scheduler that we are going deep-idle: */ - sched_clock_idle_sleep_event(); /* * Must be done before busmaster disable as we might need to * access HPET ! @@ -856,37 +759,71 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev, /* * disable bus master * bm_check implies we need ARB_DIS - * !bm_check implies we need cache flush * bm_control implies whether we can do ARB_DIS * * That leaves a case where bm_check is set and bm_control is * not set. In that case we cannot do much, we enter C3 * without doing anything. */ - if (pr->flags.bm_check && pr->flags.bm_control) { + if (pr->flags.bm_control) { raw_spin_lock(&c3_lock); c3_cpu_count++; /* Disable bus master arbitration when all CPUs are in C3 */ if (c3_cpu_count == num_online_cpus()) acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 1); raw_spin_unlock(&c3_lock); - } else if (!pr->flags.bm_check) { - ACPI_FLUSH_CPU_CACHE(); } acpi_idle_do_entry(cx); /* Re-enable bus master arbitration */ - if (pr->flags.bm_check && pr->flags.bm_control) { + if (pr->flags.bm_control) { raw_spin_lock(&c3_lock); acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 0); c3_cpu_count--; raw_spin_unlock(&c3_lock); } - sched_clock_idle_wakeup_event(0); + lapic_timer_state_broadcast(pr, cx, 0); +} + +static int acpi_idle_enter(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); + struct acpi_processor *pr; + + pr = __this_cpu_read(processors); + if (unlikely(!pr)) + return -EINVAL; + + if (cx->type != ACPI_STATE_C1) { + if (acpi_idle_fallback_to_c1(pr)) { + index = CPUIDLE_DRIVER_STATE_START; + cx = per_cpu(acpi_cstate[index], dev->cpu); + } else if (cx->type == ACPI_STATE_C3 && pr->flags.bm_check) { + if (cx->bm_sts_skip || !acpi_idle_bm_check()) { + acpi_idle_enter_bm(pr, cx); + return index; + } else if (drv->safe_state_index >= 0) { + index = drv->safe_state_index; + cx = per_cpu(acpi_cstate[index], dev->cpu); + } else { + acpi_safe_halt(); + return -EBUSY; + } + } + } + + lapic_timer_state_broadcast(pr, cx, 1); + + if (cx->type == ACPI_STATE_C3) + ACPI_FLUSH_CPU_CACHE(); + + acpi_idle_do_entry(cx); lapic_timer_state_broadcast(pr, cx, 0); + return index; } @@ -981,27 +918,12 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr) strncpy(state->desc, cx->desc, CPUIDLE_DESC_LEN); state->exit_latency = cx->latency; state->target_residency = cx->latency * latency_factor; + state->enter = acpi_idle_enter; state->flags = 0; - switch (cx->type) { - case ACPI_STATE_C1: - - state->enter = acpi_idle_enter_c1; - state->enter_dead = acpi_idle_play_dead; - drv->safe_state_index = count; - break; - - case ACPI_STATE_C2: - state->enter = acpi_idle_enter_simple; + if (cx->type == ACPI_STATE_C1 || cx->type == ACPI_STATE_C2) { state->enter_dead = acpi_idle_play_dead; drv->safe_state_index = count; - break; - - case ACPI_STATE_C3: - state->enter = pr->flags.bm_check ? - acpi_idle_enter_bm : - acpi_idle_enter_simple; - break; } count++; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 782a0d15c25..4752b993998 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -34,21 +34,34 @@ #define valid_IRQ(i) (true) #endif -static unsigned long acpi_dev_memresource_flags(u64 len, u8 write_protect, - bool window) +static bool acpi_dev_resource_len_valid(u64 start, u64 end, u64 len, bool io) { - unsigned long flags = IORESOURCE_MEM; + u64 reslen = end - start + 1; - if (len == 0) - flags |= IORESOURCE_DISABLED; + /* + * CHECKME: len might be required to check versus a minimum + * length as well. 1 for io is fine, but for memory it does + * not make any sense at all. + */ + if (len && reslen && reslen == len && start <= end) + return true; - if (write_protect == ACPI_READ_WRITE_MEMORY) - flags |= IORESOURCE_MEM_WRITEABLE; + pr_info("ACPI: invalid or unassigned resource %s [%016llx - %016llx] length [%016llx]\n", + io ? "io" : "mem", start, end, len); + + return false; +} + +static void acpi_dev_memresource_flags(struct resource *res, u64 len, + u8 write_protect) +{ + res->flags = IORESOURCE_MEM; - if (window) - flags |= IORESOURCE_WINDOW; + if (!acpi_dev_resource_len_valid(res->start, res->end, len, false)) + res->flags |= IORESOURCE_DISABLED | IORESOURCE_UNSET; - return flags; + if (write_protect == ACPI_READ_WRITE_MEMORY) + res->flags |= IORESOURCE_MEM_WRITEABLE; } static void acpi_dev_get_memresource(struct resource *res, u64 start, u64 len, @@ -56,7 +69,7 @@ static void acpi_dev_get_memresource(struct resource *res, u64 start, u64 len, { res->start = start; res->end = start + len - 1; - res->flags = acpi_dev_memresource_flags(len, write_protect, false); + acpi_dev_memresource_flags(res, len, write_protect); } /** @@ -67,6 +80,11 @@ static void acpi_dev_get_memresource(struct resource *res, u64 start, u64 len, * Check if the given ACPI resource object represents a memory resource and * if that's the case, use the information in it to populate the generic * resource object pointed to by @res. + * + * Return: + * 1) false with res->flags setting to zero: not the expected resource type + * 2) false with IORESOURCE_DISABLED in res->flags: valid unassigned resource + * 3) true: valid assigned resource */ bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res) { @@ -77,60 +95,52 @@ bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res) switch (ares->type) { case ACPI_RESOURCE_TYPE_MEMORY24: memory24 = &ares->data.memory24; - if (!memory24->minimum && !memory24->address_length) - return false; - acpi_dev_get_memresource(res, memory24->minimum, - memory24->address_length, + acpi_dev_get_memresource(res, memory24->minimum << 8, + memory24->address_length << 8, memory24->write_protect); break; case ACPI_RESOURCE_TYPE_MEMORY32: memory32 = &ares->data.memory32; - if (!memory32->minimum && !memory32->address_length) - return false; acpi_dev_get_memresource(res, memory32->minimum, memory32->address_length, memory32->write_protect); break; case ACPI_RESOURCE_TYPE_FIXED_MEMORY32: fixed_memory32 = &ares->data.fixed_memory32; - if (!fixed_memory32->address && !fixed_memory32->address_length) - return false; acpi_dev_get_memresource(res, fixed_memory32->address, fixed_memory32->address_length, fixed_memory32->write_protect); break; default: + res->flags = 0; return false; } - return true; + + return !(res->flags & IORESOURCE_DISABLED); } EXPORT_SYMBOL_GPL(acpi_dev_resource_memory); -static unsigned int acpi_dev_ioresource_flags(u64 start, u64 end, u8 io_decode, - bool window) +static void acpi_dev_ioresource_flags(struct resource *res, u64 len, + u8 io_decode) { - int flags = IORESOURCE_IO; + res->flags = IORESOURCE_IO; - if (io_decode == ACPI_DECODE_16) - flags |= IORESOURCE_IO_16BIT_ADDR; + if (!acpi_dev_resource_len_valid(res->start, res->end, len, true)) + res->flags |= IORESOURCE_DISABLED | IORESOURCE_UNSET; - if (start > end || end >= 0x10003) - flags |= IORESOURCE_DISABLED; + if (res->end >= 0x10003) + res->flags |= IORESOURCE_DISABLED | IORESOURCE_UNSET; - if (window) - flags |= IORESOURCE_WINDOW; - - return flags; + if (io_decode == ACPI_DECODE_16) + res->flags |= IORESOURCE_IO_16BIT_ADDR; } static void acpi_dev_get_ioresource(struct resource *res, u64 start, u64 len, u8 io_decode) { - u64 end = start + len - 1; - res->start = start; - res->end = end; - res->flags = acpi_dev_ioresource_flags(start, end, io_decode, false); + res->end = start + len - 1; + acpi_dev_ioresource_flags(res, len, io_decode); } /** @@ -141,6 +151,11 @@ static void acpi_dev_get_ioresource(struct resource *res, u64 start, u64 len, * Check if the given ACPI resource object represents an I/O resource and * if that's the case, use the information in it to populate the generic * resource object pointed to by @res. + * + * Return: + * 1) false with res->flags setting to zero: not the expected resource type + * 2) false with IORESOURCE_DISABLED in res->flags: valid unassigned resource + * 3) true: valid assigned resource */ bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res) { @@ -150,135 +165,143 @@ bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res) switch (ares->type) { case ACPI_RESOURCE_TYPE_IO: io = &ares->data.io; - if (!io->minimum && !io->address_length) - return false; acpi_dev_get_ioresource(res, io->minimum, io->address_length, io->io_decode); break; case ACPI_RESOURCE_TYPE_FIXED_IO: fixed_io = &ares->data.fixed_io; - if (!fixed_io->address && !fixed_io->address_length) - return false; acpi_dev_get_ioresource(res, fixed_io->address, fixed_io->address_length, ACPI_DECODE_10); break; default: + res->flags = 0; return false; } - return true; + + return !(res->flags & IORESOURCE_DISABLED); } EXPORT_SYMBOL_GPL(acpi_dev_resource_io); -/** - * acpi_dev_resource_address_space - Extract ACPI address space information. - * @ares: Input ACPI resource object. - * @res: Output generic resource object. - * - * Check if the given ACPI resource object represents an address space resource - * and if that's the case, use the information in it to populate the generic - * resource object pointed to by @res. - */ -bool acpi_dev_resource_address_space(struct acpi_resource *ares, - struct resource *res) +static bool acpi_decode_space(struct resource_win *win, + struct acpi_resource_address *addr, + struct acpi_address64_attribute *attr) { - acpi_status status; - struct acpi_resource_address64 addr; - bool window; - u64 len; - u8 io_decode; + u8 iodec = attr->granularity == 0xfff ? ACPI_DECODE_10 : ACPI_DECODE_16; + bool wp = addr->info.mem.write_protect; + u64 len = attr->address_length; + struct resource *res = &win->res; - switch (ares->type) { - case ACPI_RESOURCE_TYPE_ADDRESS16: - case ACPI_RESOURCE_TYPE_ADDRESS32: - case ACPI_RESOURCE_TYPE_ADDRESS64: - break; - default: - return false; - } + /* + * Filter out invalid descriptor according to ACPI Spec 5.0, section + * 6.4.3.5 Address Space Resource Descriptors. + */ + if ((addr->min_address_fixed != addr->max_address_fixed && len) || + (addr->min_address_fixed && addr->max_address_fixed && !len)) + pr_debug("ACPI: Invalid address space min_addr_fix %d, max_addr_fix %d, len %llx\n", + addr->min_address_fixed, addr->max_address_fixed, len); - status = acpi_resource_to_address64(ares, &addr); - if (ACPI_FAILURE(status)) - return false; + res->start = attr->minimum; + res->end = attr->maximum; - res->start = addr.minimum; - res->end = addr.maximum; - window = addr.producer_consumer == ACPI_PRODUCER; + /* + * For bridges that translate addresses across the bridge, + * translation_offset is the offset that must be added to the + * address on the secondary side to obtain the address on the + * primary side. Non-bridge devices must list 0 for all Address + * Translation offset bits. + */ + if (addr->producer_consumer == ACPI_PRODUCER) { + res->start += attr->translation_offset; + res->end += attr->translation_offset; + } else if (attr->translation_offset) { + pr_debug("ACPI: translation_offset(%lld) is invalid for non-bridge device.\n", + attr->translation_offset); + } - switch(addr.resource_type) { + switch (addr->resource_type) { case ACPI_MEMORY_RANGE: - len = addr.maximum - addr.minimum + 1; - res->flags = acpi_dev_memresource_flags(len, - addr.info.mem.write_protect, - window); + acpi_dev_memresource_flags(res, len, wp); break; case ACPI_IO_RANGE: - io_decode = addr.granularity == 0xfff ? - ACPI_DECODE_10 : ACPI_DECODE_16; - res->flags = acpi_dev_ioresource_flags(addr.minimum, - addr.maximum, - io_decode, window); + acpi_dev_ioresource_flags(res, len, iodec); break; case ACPI_BUS_NUMBER_RANGE: res->flags = IORESOURCE_BUS; break; default: - res->flags = 0; + return false; } - return true; + win->offset = attr->translation_offset; + + if (addr->producer_consumer == ACPI_PRODUCER) + res->flags |= IORESOURCE_WINDOW; + + if (addr->info.mem.caching == ACPI_PREFETCHABLE_MEMORY) + res->flags |= IORESOURCE_PREFETCH; + + return !(res->flags & IORESOURCE_DISABLED); +} + +/** + * acpi_dev_resource_address_space - Extract ACPI address space information. + * @ares: Input ACPI resource object. + * @win: Output generic resource object. + * + * Check if the given ACPI resource object represents an address space resource + * and if that's the case, use the information in it to populate the generic + * resource object pointed to by @win. + * + * Return: + * 1) false with win->res.flags setting to zero: not the expected resource type + * 2) false with IORESOURCE_DISABLED in win->res.flags: valid unassigned + * resource + * 3) true: valid assigned resource + */ +bool acpi_dev_resource_address_space(struct acpi_resource *ares, + struct resource_win *win) +{ + struct acpi_resource_address64 addr; + + win->res.flags = 0; + if (ACPI_FAILURE(acpi_resource_to_address64(ares, &addr))) + return false; + + return acpi_decode_space(win, (struct acpi_resource_address *)&addr, + &addr.address); } EXPORT_SYMBOL_GPL(acpi_dev_resource_address_space); /** * acpi_dev_resource_ext_address_space - Extract ACPI address space information. * @ares: Input ACPI resource object. - * @res: Output generic resource object. + * @win: Output generic resource object. * * Check if the given ACPI resource object represents an extended address space * resource and if that's the case, use the information in it to populate the - * generic resource object pointed to by @res. + * generic resource object pointed to by @win. + * + * Return: + * 1) false with win->res.flags setting to zero: not the expected resource type + * 2) false with IORESOURCE_DISABLED in win->res.flags: valid unassigned + * resource + * 3) true: valid assigned resource */ bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, - struct resource *res) + struct resource_win *win) { struct acpi_resource_extended_address64 *ext_addr; - bool window; - u64 len; - u8 io_decode; + win->res.flags = 0; if (ares->type != ACPI_RESOURCE_TYPE_EXTENDED_ADDRESS64) return false; ext_addr = &ares->data.ext_address64; - res->start = ext_addr->minimum; - res->end = ext_addr->maximum; - window = ext_addr->producer_consumer == ACPI_PRODUCER; - - switch(ext_addr->resource_type) { - case ACPI_MEMORY_RANGE: - len = ext_addr->maximum - ext_addr->minimum + 1; - res->flags = acpi_dev_memresource_flags(len, - ext_addr->info.mem.write_protect, - window); - break; - case ACPI_IO_RANGE: - io_decode = ext_addr->granularity == 0xfff ? - ACPI_DECODE_10 : ACPI_DECODE_16; - res->flags = acpi_dev_ioresource_flags(ext_addr->minimum, - ext_addr->maximum, - io_decode, window); - break; - case ACPI_BUS_NUMBER_RANGE: - res->flags = IORESOURCE_BUS; - break; - default: - res->flags = 0; - } - - return true; + return acpi_decode_space(win, (struct acpi_resource_address *)ext_addr, + &ext_addr->address); } EXPORT_SYMBOL_GPL(acpi_dev_resource_ext_address_space); @@ -310,7 +333,7 @@ static void acpi_dev_irqresource_disabled(struct resource *res, u32 gsi) { res->start = gsi; res->end = gsi; - res->flags = IORESOURCE_IRQ | IORESOURCE_DISABLED; + res->flags = IORESOURCE_IRQ | IORESOURCE_DISABLED | IORESOURCE_UNSET; } static void acpi_dev_get_irqresource(struct resource *res, u32 gsi, @@ -369,6 +392,11 @@ static void acpi_dev_get_irqresource(struct resource *res, u32 gsi, * represented by the resource and populate the generic resource object pointed * to by @res accordingly. If the registration of the GSI is not successful, * IORESOURCE_DISABLED will be set it that object's flags. + * + * Return: + * 1) false with res->flags setting to zero: not the expected resource type + * 2) false with IORESOURCE_DISABLED in res->flags: valid unassigned resource + * 3) true: valid assigned resource */ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res) @@ -402,6 +430,7 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, ext_irq->sharable, false); break; default: + res->flags = 0; return false; } @@ -415,12 +444,7 @@ EXPORT_SYMBOL_GPL(acpi_dev_resource_interrupt); */ void acpi_dev_free_resource_list(struct list_head *list) { - struct resource_list_entry *rentry, *re; - - list_for_each_entry_safe(rentry, re, list, node) { - list_del(&rentry->node); - kfree(rentry); - } + resource_list_free(list); } EXPORT_SYMBOL_GPL(acpi_dev_free_resource_list); @@ -432,18 +456,19 @@ struct res_proc_context { int error; }; -static acpi_status acpi_dev_new_resource_entry(struct resource *r, +static acpi_status acpi_dev_new_resource_entry(struct resource_win *win, struct res_proc_context *c) { - struct resource_list_entry *rentry; + struct resource_entry *rentry; - rentry = kmalloc(sizeof(*rentry), GFP_KERNEL); + rentry = resource_list_create_entry(NULL, 0); if (!rentry) { c->error = -ENOMEM; return AE_NO_MEMORY; } - rentry->res = *r; - list_add_tail(&rentry->node, c->list); + *rentry->res = win->res; + rentry->offset = win->offset; + resource_list_add_tail(rentry, c->list); c->count++; return AE_OK; } @@ -452,7 +477,8 @@ static acpi_status acpi_dev_process_resource(struct acpi_resource *ares, void *context) { struct res_proc_context *c = context; - struct resource r; + struct resource_win win; + struct resource *res = &win.res; int i; if (c->preproc) { @@ -467,18 +493,18 @@ static acpi_status acpi_dev_process_resource(struct acpi_resource *ares, } } - memset(&r, 0, sizeof(r)); + memset(&win, 0, sizeof(win)); - if (acpi_dev_resource_memory(ares, &r) - || acpi_dev_resource_io(ares, &r) - || acpi_dev_resource_address_space(ares, &r) - || acpi_dev_resource_ext_address_space(ares, &r)) - return acpi_dev_new_resource_entry(&r, c); + if (acpi_dev_resource_memory(ares, res) + || acpi_dev_resource_io(ares, res) + || acpi_dev_resource_address_space(ares, &win) + || acpi_dev_resource_ext_address_space(ares, &win)) + return acpi_dev_new_resource_entry(&win, c); - for (i = 0; acpi_dev_resource_interrupt(ares, i, &r); i++) { + for (i = 0; acpi_dev_resource_interrupt(ares, i, res); i++) { acpi_status status; - status = acpi_dev_new_resource_entry(&r, c); + status = acpi_dev_new_resource_entry(&win, c); if (ACPI_FAILURE(status)) return status; } @@ -503,7 +529,7 @@ static acpi_status acpi_dev_process_resource(struct acpi_resource *ares, * returned as the final error code. * * The resultant struct resource objects are put on the list pointed to by - * @list, that must be empty initially, as members of struct resource_list_entry + * @list, that must be empty initially, as members of struct resource_entry * objects. Callers of this routine should use %acpi_dev_free_resource_list() to * free that list. * @@ -538,3 +564,58 @@ int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, return c.count; } EXPORT_SYMBOL_GPL(acpi_dev_get_resources); + +/** + * acpi_dev_filter_resource_type - Filter ACPI resource according to resource + * types + * @ares: Input ACPI resource object. + * @types: Valid resource types of IORESOURCE_XXX + * + * This is a hepler function to support acpi_dev_get_resources(), which filters + * ACPI resource objects according to resource types. + */ +int acpi_dev_filter_resource_type(struct acpi_resource *ares, + unsigned long types) +{ + unsigned long type = 0; + + switch (ares->type) { + case ACPI_RESOURCE_TYPE_MEMORY24: + case ACPI_RESOURCE_TYPE_MEMORY32: + case ACPI_RESOURCE_TYPE_FIXED_MEMORY32: + type = IORESOURCE_MEM; + break; + case ACPI_RESOURCE_TYPE_IO: + case ACPI_RESOURCE_TYPE_FIXED_IO: + type = IORESOURCE_IO; + break; + case ACPI_RESOURCE_TYPE_IRQ: + case ACPI_RESOURCE_TYPE_EXTENDED_IRQ: + type = IORESOURCE_IRQ; + break; + case ACPI_RESOURCE_TYPE_DMA: + case ACPI_RESOURCE_TYPE_FIXED_DMA: + type = IORESOURCE_DMA; + break; + case ACPI_RESOURCE_TYPE_GENERIC_REGISTER: + type = IORESOURCE_REG; + break; + case ACPI_RESOURCE_TYPE_ADDRESS16: + case ACPI_RESOURCE_TYPE_ADDRESS32: + case ACPI_RESOURCE_TYPE_ADDRESS64: + case ACPI_RESOURCE_TYPE_EXTENDED_ADDRESS64: + if (ares->data.address.resource_type == ACPI_MEMORY_RANGE) + type = IORESOURCE_MEM; + else if (ares->data.address.resource_type == ACPI_IO_RANGE) + type = IORESOURCE_IO; + else if (ares->data.address.resource_type == + ACPI_BUS_NUMBER_RANGE) + type = IORESOURCE_BUS; + break; + default: + break; + } + + return (type & types) ? 0 : 1; +} +EXPORT_SYMBOL_GPL(acpi_dev_filter_resource_type); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index dc4d8960684..bbca7830e18 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2544,6 +2544,7 @@ int __init acpi_scan_init(void) acpi_pci_link_init(); acpi_processor_init(); acpi_lpss_init(); + acpi_apd_init(); acpi_cmos_rtc_init(); acpi_container_init(); acpi_memory_hotplug_init(); diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 8aa9254a387..7f251dd1a68 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -321,7 +321,7 @@ static struct dmi_system_id acpisleep_dmi_table[] __initdata = { {}, }; -static void acpi_sleep_dmi_check(void) +static void __init acpi_sleep_dmi_check(void) { int year; diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index 032db459370..88a4f99dd2a 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -522,6 +522,24 @@ static struct dmi_system_id video_dmi_table[] __initdata = { DMI_MATCH(DMI_PRODUCT_NAME, "370R4E/370R4V/370R5E/3570RE/370R5V"), }, }, + { + /* https://bugzilla.redhat.com/show_bug.cgi?id=1186097 */ + .callback = video_disable_native_backlight, + .ident = "SAMSUNG 3570R/370R/470R/450R/510R/4450RV", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), + DMI_MATCH(DMI_PRODUCT_NAME, "3570R/370R/470R/450R/510R/4450RV"), + }, + }, + { + /* https://bugzilla.redhat.com/show_bug.cgi?id=1094948 */ + .callback = video_disable_native_backlight, + .ident = "SAMSUNG 730U3E/740U3E", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), + DMI_MATCH(DMI_PRODUCT_NAME, "730U3E/740U3E"), + }, + }, { /* https://bugzilla.redhat.com/show_bug.cgi?id=1163574 */ diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 40f0e34f17a..71262e08648 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -333,7 +333,7 @@ struct ahci_host_priv { u32 em_msg_type; /* EM message type */ bool got_runtime_pm; /* Did we do pm_runtime_get? */ struct clk *clks[AHCI_MAX_CLKS]; /* Optional */ - struct regulator *target_pwr; /* Optional */ + struct regulator **target_pwrs; /* Optional */ /* * If platform uses PHYs. There is a 1:1 relation between the port number and * the PHY position in this array. @@ -354,6 +354,10 @@ extern int ahci_ignore_sss; extern struct device_attribute *ahci_shost_attrs[]; extern struct device_attribute *ahci_sdev_attrs[]; +/* + * This must be instantiated by the edge drivers. Read the comments + * for ATA_BASE_SHT + */ #define AHCI_SHT(drv_name) \ ATA_NCQ_SHT(drv_name), \ .can_queue = AHCI_MAX_CMDS - 1, \ diff --git a/drivers/ata/ahci_da850.c b/drivers/ata/ahci_da850.c index ce8a7a6d6c7..267a3d3e79f 100644 --- a/drivers/ata/ahci_da850.c +++ b/drivers/ata/ahci_da850.c @@ -16,6 +16,8 @@ #include <linux/ahci_platform.h> #include "ahci.h" +#define DRV_NAME "ahci_da850" + /* SATA PHY Control Register offset from AHCI base */ #define SATA_P0PHYCR_REG 0x178 @@ -59,6 +61,10 @@ static const struct ata_port_info ahci_da850_port_info = { .port_ops = &ahci_platform_ops, }; +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int ahci_da850_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -85,7 +91,8 @@ static int ahci_da850_probe(struct platform_device *pdev) da850_sata_init(dev, pwrdn_reg, hpriv->mmio); - rc = ahci_platform_init_host(pdev, hpriv, &ahci_da850_port_info); + rc = ahci_platform_init_host(pdev, hpriv, &ahci_da850_port_info, + &ahci_platform_sht); if (rc) goto disable_resources; @@ -102,7 +109,7 @@ static struct platform_driver ahci_da850_driver = { .probe = ahci_da850_probe, .remove = ata_platform_remove_one, .driver = { - .name = "ahci_da850", + .name = DRV_NAME, .pm = &ahci_da850_pm_ops, }, }; diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c index 35d51c59a37..3f3a7db208a 100644 --- a/drivers/ata/ahci_imx.c +++ b/drivers/ata/ahci_imx.c @@ -28,6 +28,8 @@ #include <linux/libata.h> #include "ahci.h" +#define DRV_NAME "ahci-imx" + enum { /* Timer 1-ms Register */ IMX_TIMER1MS = 0x00e0, @@ -221,11 +223,9 @@ static int imx_sata_enable(struct ahci_host_priv *hpriv) if (imxpriv->no_device) return 0; - if (hpriv->target_pwr) { - ret = regulator_enable(hpriv->target_pwr); - if (ret) - return ret; - } + ret = ahci_platform_enable_regulators(hpriv); + if (ret) + return ret; ret = clk_prepare_enable(imxpriv->sata_ref_clk); if (ret < 0) @@ -270,8 +270,7 @@ static int imx_sata_enable(struct ahci_host_priv *hpriv) disable_clk: clk_disable_unprepare(imxpriv->sata_ref_clk); disable_regulator: - if (hpriv->target_pwr) - regulator_disable(hpriv->target_pwr); + ahci_platform_disable_regulators(hpriv); return ret; } @@ -291,8 +290,7 @@ static void imx_sata_disable(struct ahci_host_priv *hpriv) clk_disable_unprepare(imxpriv->sata_ref_clk); - if (hpriv->target_pwr) - regulator_disable(hpriv->target_pwr); + ahci_platform_disable_regulators(hpriv); } static void ahci_imx_error_handler(struct ata_port *ap) @@ -524,6 +522,10 @@ static u32 imx_ahci_parse_props(struct device *dev, return reg_value; } +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int imx_ahci_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -620,7 +622,8 @@ static int imx_ahci_probe(struct platform_device *pdev) reg_val = clk_get_rate(imxpriv->ahb_clk) / 1000; writel(reg_val, hpriv->mmio + IMX_TIMER1MS); - ret = ahci_platform_init_host(pdev, hpriv, &ahci_imx_port_info); + ret = ahci_platform_init_host(pdev, hpriv, &ahci_imx_port_info, + &ahci_platform_sht); if (ret) goto disable_sata; @@ -678,7 +681,7 @@ static struct platform_driver imx_ahci_driver = { .probe = imx_ahci_probe, .remove = ata_platform_remove_one, .driver = { - .name = "ahci-imx", + .name = DRV_NAME, .of_match_table = imx_ahci_of_match, .pm = &ahci_imx_pm_ops, }, diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c index 64bb08432b6..23716dd8a7e 100644 --- a/drivers/ata/ahci_mvebu.c +++ b/drivers/ata/ahci_mvebu.c @@ -19,6 +19,8 @@ #include <linux/platform_device.h> #include "ahci.h" +#define DRV_NAME "ahci-mvebu" + #define AHCI_VENDOR_SPECIFIC_0_ADDR 0xa0 #define AHCI_VENDOR_SPECIFIC_0_DATA 0xa4 @@ -67,6 +69,10 @@ static const struct ata_port_info ahci_mvebu_port_info = { .port_ops = &ahci_platform_ops, }; +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int ahci_mvebu_probe(struct platform_device *pdev) { struct ahci_host_priv *hpriv; @@ -88,7 +94,8 @@ static int ahci_mvebu_probe(struct platform_device *pdev) ahci_mvebu_mbus_config(hpriv, dram); ahci_mvebu_regret_option(hpriv); - rc = ahci_platform_init_host(pdev, hpriv, &ahci_mvebu_port_info); + rc = ahci_platform_init_host(pdev, hpriv, &ahci_mvebu_port_info, + &ahci_platform_sht); if (rc) goto disable_resources; @@ -114,7 +121,7 @@ static struct platform_driver ahci_mvebu_driver = { .probe = ahci_mvebu_probe, .remove = ata_platform_remove_one, .driver = { - .name = "ahci-mvebu", + .name = DRV_NAME, .of_match_table = ahci_mvebu_of_match, }, }; diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c index 18d53983704..78d6ae0b90c 100644 --- a/drivers/ata/ahci_platform.c +++ b/drivers/ata/ahci_platform.c @@ -22,6 +22,8 @@ #include <linux/ahci_platform.h> #include "ahci.h" +#define DRV_NAME "ahci" + static const struct ata_port_info ahci_port_info = { .flags = AHCI_FLAG_COMMON, .pio_mask = ATA_PIO4, @@ -29,6 +31,10 @@ static const struct ata_port_info ahci_port_info = { .port_ops = &ahci_platform_ops, }; +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int ahci_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -46,7 +52,8 @@ static int ahci_probe(struct platform_device *pdev) if (of_device_is_compatible(dev->of_node, "hisilicon,hisi-ahci")) hpriv->flags |= AHCI_HFLAG_NO_FBS | AHCI_HFLAG_NO_NCQ; - rc = ahci_platform_init_host(pdev, hpriv, &ahci_port_info); + rc = ahci_platform_init_host(pdev, hpriv, &ahci_port_info, + &ahci_platform_sht); if (rc) goto disable_resources; @@ -75,7 +82,7 @@ static struct platform_driver ahci_driver = { .probe = ahci_probe, .remove = ata_platform_remove_one, .driver = { - .name = "ahci", + .name = DRV_NAME, .of_match_table = ahci_of_match, .pm = &ahci_pm_ops, }, diff --git a/drivers/ata/ahci_st.c b/drivers/ata/ahci_st.c index 2f9e8317cc1..bc971af262e 100644 --- a/drivers/ata/ahci_st.c +++ b/drivers/ata/ahci_st.c @@ -23,6 +23,8 @@ #include "ahci.h" +#define DRV_NAME "st_ahci" + #define ST_AHCI_OOBR 0xbc #define ST_AHCI_OOBR_WE BIT(31) #define ST_AHCI_OOBR_CWMIN_SHIFT 24 @@ -140,6 +142,10 @@ static const struct ata_port_info st_ahci_port_info = { .port_ops = &st_ahci_port_ops, }; +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int st_ahci_probe(struct platform_device *pdev) { struct st_ahci_drv_data *drv_data; @@ -166,7 +172,8 @@ static int st_ahci_probe(struct platform_device *pdev) if (err) return err; - err = ahci_platform_init_host(pdev, hpriv, &st_ahci_port_info); + err = ahci_platform_init_host(pdev, hpriv, &st_ahci_port_info, + &ahci_platform_sht); if (err) { ahci_platform_disable_resources(hpriv); return err; @@ -229,7 +236,7 @@ MODULE_DEVICE_TABLE(of, st_ahci_match); static struct platform_driver st_ahci_driver = { .driver = { - .name = "st_ahci", + .name = DRV_NAME, .pm = &st_ahci_pm_ops, .of_match_table = of_match_ptr(st_ahci_match), }, diff --git a/drivers/ata/ahci_sunxi.c b/drivers/ata/ahci_sunxi.c index e2e0da539a2..b2643743016 100644 --- a/drivers/ata/ahci_sunxi.c +++ b/drivers/ata/ahci_sunxi.c @@ -27,6 +27,8 @@ #include <linux/regulator/consumer.h> #include "ahci.h" +#define DRV_NAME "ahci-sunxi" + /* Insmod parameters */ static bool enable_pmp; module_param(enable_pmp, bool, 0); @@ -169,6 +171,10 @@ static const struct ata_port_info ahci_sunxi_port_info = { .port_ops = &ahci_platform_ops, }; +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int ahci_sunxi_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -200,7 +206,8 @@ static int ahci_sunxi_probe(struct platform_device *pdev) if (!enable_pmp) hpriv->flags |= AHCI_HFLAG_NO_PMP; - rc = ahci_platform_init_host(pdev, hpriv, &ahci_sunxi_port_info); + rc = ahci_platform_init_host(pdev, hpriv, &ahci_sunxi_port_info, + &ahci_platform_sht); if (rc) goto disable_resources; @@ -251,7 +258,7 @@ static struct platform_driver ahci_sunxi_driver = { .probe = ahci_sunxi_probe, .remove = ata_platform_remove_one, .driver = { - .name = "ahci-sunxi", + .name = DRV_NAME, .of_match_table = ahci_sunxi_of_match, .pm = &ahci_sunxi_pm_ops, }, diff --git a/drivers/ata/ahci_tegra.c b/drivers/ata/ahci_tegra.c index 032904402c9..3a62eb246d8 100644 --- a/drivers/ata/ahci_tegra.c +++ b/drivers/ata/ahci_tegra.c @@ -31,6 +31,8 @@ #include "ahci.h" +#define DRV_NAME "tegra-ahci" + #define SATA_CONFIGURATION_0 0x180 #define SATA_CONFIGURATION_EN_FPCI BIT(0) @@ -289,6 +291,10 @@ static const struct of_device_id tegra_ahci_of_match[] = { }; MODULE_DEVICE_TABLE(of, tegra_ahci_of_match); +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int tegra_ahci_probe(struct platform_device *pdev) { struct ahci_host_priv *hpriv; @@ -354,7 +360,8 @@ static int tegra_ahci_probe(struct platform_device *pdev) if (ret) return ret; - ret = ahci_platform_init_host(pdev, hpriv, &ahci_tegra_port_info); + ret = ahci_platform_init_host(pdev, hpriv, &ahci_tegra_port_info, + &ahci_platform_sht); if (ret) goto deinit_controller; @@ -370,7 +377,7 @@ static struct platform_driver tegra_ahci_driver = { .probe = tegra_ahci_probe, .remove = ata_platform_remove_one, .driver = { - .name = "tegra-ahci", + .name = DRV_NAME, .of_match_table = tegra_ahci_of_match, }, /* LP0 suspend support not implemented */ diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index cbcd2081035..2e8bb603e44 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -30,6 +30,8 @@ #include <linux/phy/phy.h> #include "ahci.h" +#define DRV_NAME "xgene-ahci" + /* Max # of disk per a controller */ #define MAX_AHCI_CHN_PERCTR 2 @@ -85,6 +87,7 @@ struct xgene_ahci_context { struct ahci_host_priv *hpriv; struct device *dev; u8 last_cmd[MAX_AHCI_CHN_PERCTR]; /* tracking the last command issued*/ + u32 class[MAX_AHCI_CHN_PERCTR]; /* tracking the class of device */ void __iomem *csr_core; /* Core CSR address of IP */ void __iomem *csr_diag; /* Diag CSR address of IP */ void __iomem *csr_axi; /* AXI CSR address of IP */ @@ -105,17 +108,69 @@ static int xgene_ahci_init_memram(struct xgene_ahci_context *ctx) } /** + * xgene_ahci_poll_reg_val- Poll a register on a specific value. + * @ap : ATA port of interest. + * @reg : Register of interest. + * @val : Value to be attained. + * @interval : waiting interval for polling. + * @timeout : timeout for achieving the value. + */ +static int xgene_ahci_poll_reg_val(struct ata_port *ap, + void __iomem *reg, unsigned + int val, unsigned long interval, + unsigned long timeout) +{ + unsigned long deadline; + unsigned int tmp; + + tmp = ioread32(reg); + deadline = ata_deadline(jiffies, timeout); + + while (tmp != val && time_before(jiffies, deadline)) { + ata_msleep(ap, interval); + tmp = ioread32(reg); + } + + return tmp; +} + +/** * xgene_ahci_restart_engine - Restart the dma engine. * @ap : ATA port of interest * - * Restarts the dma engine inside the controller. + * Waits for completion of multiple commands and restarts + * the DMA engine inside the controller. */ static int xgene_ahci_restart_engine(struct ata_port *ap) { struct ahci_host_priv *hpriv = ap->host->private_data; + struct ahci_port_priv *pp = ap->private_data; + void __iomem *port_mmio = ahci_port_base(ap); + u32 fbs; + + /* + * In case of PMP multiple IDENTIFY DEVICE commands can be + * issued inside PxCI. So need to poll PxCI for the + * completion of outstanding IDENTIFY DEVICE commands before + * we restart the DMA engine. + */ + if (xgene_ahci_poll_reg_val(ap, port_mmio + + PORT_CMD_ISSUE, 0x0, 1, 100)) + return -EBUSY; ahci_stop_engine(ap); ahci_start_fis_rx(ap); + + /* + * Enable the PxFBS.FBS_EN bit as it + * gets cleared due to stopping the engine. + */ + if (pp->fbs_supported) { + fbs = readl(port_mmio + PORT_FBS); + writel(fbs | PORT_FBS_EN, port_mmio + PORT_FBS); + fbs = readl(port_mmio + PORT_FBS); + } + hpriv->start_engine(ap); return 0; @@ -125,11 +180,17 @@ static int xgene_ahci_restart_engine(struct ata_port *ap) * xgene_ahci_qc_issue - Issue commands to the device * @qc: Command to issue * - * Due to Hardware errata for IDENTIFY DEVICE command and PACKET - * command of ATAPI protocol set, the controller cannot clear the BSY bit - * after receiving the PIO setup FIS. This results in the DMA state machine - * going into the CMFatalErrorUpdate state and locks up. By restarting the - * DMA engine, it removes the controller out of lock up state. + * Due to Hardware errata for IDENTIFY DEVICE command, the controller cannot + * clear the BSY bit after receiving the PIO setup FIS. This results in the dma + * state machine goes into the CMFatalErrorUpdate state and locks up. By + * restarting the dma engine, it removes the controller out of lock up state. + * + * Due to H/W errata, the controller is unable to save the PMP + * field fetched from command header before sending the H2D FIS. + * When the device returns the PMP port field in the D2H FIS, there is + * a mismatch and results in command completion failure. The + * workaround is to write the pmp value to PxFBS.DEV field before issuing + * any command to PMP. */ static unsigned int xgene_ahci_qc_issue(struct ata_queued_cmd *qc) { @@ -137,9 +198,23 @@ static unsigned int xgene_ahci_qc_issue(struct ata_queued_cmd *qc) struct ahci_host_priv *hpriv = ap->host->private_data; struct xgene_ahci_context *ctx = hpriv->plat_data; int rc = 0; + u32 port_fbs; + void *port_mmio = ahci_port_base(ap); + + /* + * Write the pmp value to PxFBS.DEV + * for case of Port Mulitplier. + */ + if (ctx->class[ap->port_no] == ATA_DEV_PMP) { + port_fbs = readl(port_mmio + PORT_FBS); + port_fbs &= ~PORT_FBS_DEV_MASK; + port_fbs |= qc->dev->link->pmp << PORT_FBS_DEV_OFFSET; + writel(port_fbs, port_mmio + PORT_FBS); + } if (unlikely((ctx->last_cmd[ap->port_no] == ATA_CMD_ID_ATA) || - (ctx->last_cmd[ap->port_no] == ATA_CMD_PACKET))) + (ctx->last_cmd[ap->port_no] == ATA_CMD_PACKET) || + (ctx->last_cmd[ap->port_no] == ATA_CMD_SMART))) xgene_ahci_restart_engine(ap); rc = ahci_qc_issue(qc); @@ -365,16 +440,119 @@ static void xgene_ahci_host_stop(struct ata_host *host) ahci_platform_disable_resources(hpriv); } +/** + * xgene_ahci_pmp_softreset - Issue the softreset to the drives connected + * to Port Multiplier. + * @link: link to reset + * @class: Return value to indicate class of device + * @deadline: deadline jiffies for the operation + * + * Due to H/W errata, the controller is unable to save the PMP + * field fetched from command header before sending the H2D FIS. + * When the device returns the PMP port field in the D2H FIS, there is + * a mismatch and results in command completion failure. The workaround + * is to write the pmp value to PxFBS.DEV field before issuing any command + * to PMP. + */ +static int xgene_ahci_pmp_softreset(struct ata_link *link, unsigned int *class, + unsigned long deadline) +{ + int pmp = sata_srst_pmp(link); + struct ata_port *ap = link->ap; + u32 rc; + void *port_mmio = ahci_port_base(ap); + u32 port_fbs; + + /* + * Set PxFBS.DEV field with pmp + * value. + */ + port_fbs = readl(port_mmio + PORT_FBS); + port_fbs &= ~PORT_FBS_DEV_MASK; + port_fbs |= pmp << PORT_FBS_DEV_OFFSET; + writel(port_fbs, port_mmio + PORT_FBS); + + rc = ahci_do_softreset(link, class, pmp, deadline, ahci_check_ready); + + return rc; +} + +/** + * xgene_ahci_softreset - Issue the softreset to the drive. + * @link: link to reset + * @class: Return value to indicate class of device + * @deadline: deadline jiffies for the operation + * + * Due to H/W errata, the controller is unable to save the PMP + * field fetched from command header before sending the H2D FIS. + * When the device returns the PMP port field in the D2H FIS, there is + * a mismatch and results in command completion failure. The workaround + * is to write the pmp value to PxFBS.DEV field before issuing any command + * to PMP. Here is the algorithm to detect PMP : + * + * 1. Save the PxFBS value + * 2. Program PxFBS.DEV with pmp value send by framework. Framework sends + * 0xF for both PMP/NON-PMP initially + * 3. Issue softreset + * 4. If signature class is PMP goto 6 + * 5. restore the original PxFBS and goto 3 + * 6. return + */ +static int xgene_ahci_softreset(struct ata_link *link, unsigned int *class, + unsigned long deadline) +{ + int pmp = sata_srst_pmp(link); + struct ata_port *ap = link->ap; + struct ahci_host_priv *hpriv = ap->host->private_data; + struct xgene_ahci_context *ctx = hpriv->plat_data; + void *port_mmio = ahci_port_base(ap); + u32 port_fbs; + u32 port_fbs_save; + u32 retry = 1; + u32 rc; + + port_fbs_save = readl(port_mmio + PORT_FBS); + + /* + * Set PxFBS.DEV field with pmp + * value. + */ + port_fbs = readl(port_mmio + PORT_FBS); + port_fbs &= ~PORT_FBS_DEV_MASK; + port_fbs |= pmp << PORT_FBS_DEV_OFFSET; + writel(port_fbs, port_mmio + PORT_FBS); + +softreset_retry: + rc = ahci_do_softreset(link, class, pmp, + deadline, ahci_check_ready); + + ctx->class[ap->port_no] = *class; + if (*class != ATA_DEV_PMP) { + /* + * Retry for normal drives without + * setting PxFBS.DEV field with pmp value. + */ + if (retry--) { + writel(port_fbs_save, port_mmio + PORT_FBS); + goto softreset_retry; + } + } + + return rc; +} + static struct ata_port_operations xgene_ahci_ops = { .inherits = &ahci_ops, .host_stop = xgene_ahci_host_stop, .hardreset = xgene_ahci_hardreset, .read_id = xgene_ahci_read_id, .qc_issue = xgene_ahci_qc_issue, + .softreset = xgene_ahci_softreset, + .pmp_softreset = xgene_ahci_pmp_softreset }; static const struct ata_port_info xgene_ahci_port_info = { - .flags = AHCI_FLAG_COMMON, + .flags = AHCI_FLAG_COMMON | ATA_FLAG_PMP, .pio_mask = ATA_PIO4, .udma_mask = ATA_UDMA6, .port_ops = &xgene_ahci_ops, @@ -446,6 +624,10 @@ static int xgene_ahci_mux_select(struct xgene_ahci_context *ctx) return val & CFG_SATA_ENET_SELECT_MASK ? -1 : 0; } +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + static int xgene_ahci_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -523,7 +705,8 @@ static int xgene_ahci_probe(struct platform_device *pdev) skip_clk_phy: hpriv->flags = AHCI_HFLAG_NO_PMP | AHCI_HFLAG_NO_NCQ; - rc = ahci_platform_init_host(pdev, hpriv, &xgene_ahci_port_info); + rc = ahci_platform_init_host(pdev, hpriv, &xgene_ahci_port_info, + &ahci_platform_sht); if (rc) goto disable_resources; @@ -545,7 +728,7 @@ static struct platform_driver xgene_ahci_driver = { .probe = xgene_ahci_probe, .remove = ata_platform_remove_one, .driver = { - .name = "xgene-ahci", + .name = DRV_NAME, .of_match_table = xgene_ahci_of_match, }, }; diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 0b03f905669..d89305d289f 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -24,6 +24,7 @@ #include <linux/ahci_platform.h> #include <linux/phy/phy.h> #include <linux/pm_runtime.h> +#include <linux/of_platform.h> #include "ahci.h" static void ahci_host_stop(struct ata_host *host); @@ -34,10 +35,6 @@ struct ata_port_operations ahci_platform_ops = { }; EXPORT_SYMBOL_GPL(ahci_platform_ops); -static struct scsi_host_template ahci_platform_sht = { - AHCI_SHT("ahci_platform"), -}; - /** * ahci_platform_enable_phys - Enable PHYs * @hpriv: host private area to store config values @@ -54,9 +51,6 @@ static int ahci_platform_enable_phys(struct ahci_host_priv *hpriv) int rc, i; for (i = 0; i < hpriv->nports; i++) { - if (!hpriv->phys[i]) - continue; - rc = phy_init(hpriv->phys[i]); if (rc) goto disable_phys; @@ -89,9 +83,6 @@ static void ahci_platform_disable_phys(struct ahci_host_priv *hpriv) int i; for (i = 0; i < hpriv->nports; i++) { - if (!hpriv->phys[i]) - continue; - phy_power_off(hpriv->phys[i]); phy_exit(hpriv->phys[i]); } @@ -144,6 +135,59 @@ void ahci_platform_disable_clks(struct ahci_host_priv *hpriv) EXPORT_SYMBOL_GPL(ahci_platform_disable_clks); /** + * ahci_platform_enable_regulators - Enable regulators + * @hpriv: host private area to store config values + * + * This function enables all the regulators found in + * hpriv->target_pwrs, if any. If a regulator fails to be enabled, it + * disables all the regulators already enabled in reverse order and + * returns an error. + * + * RETURNS: + * 0 on success otherwise a negative error code + */ +int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv) +{ + int rc, i; + + for (i = 0; i < hpriv->nports; i++) { + if (!hpriv->target_pwrs[i]) + continue; + + rc = regulator_enable(hpriv->target_pwrs[i]); + if (rc) + goto disable_target_pwrs; + } + + return 0; + +disable_target_pwrs: + while (--i >= 0) + if (hpriv->target_pwrs[i]) + regulator_disable(hpriv->target_pwrs[i]); + + return rc; +} +EXPORT_SYMBOL_GPL(ahci_platform_enable_regulators); + +/** + * ahci_platform_disable_regulators - Disable regulators + * @hpriv: host private area to store config values + * + * This function disables all regulators found in hpriv->target_pwrs. + */ +void ahci_platform_disable_regulators(struct ahci_host_priv *hpriv) +{ + int i; + + for (i = 0; i < hpriv->nports; i++) { + if (!hpriv->target_pwrs[i]) + continue; + regulator_disable(hpriv->target_pwrs[i]); + } +} +EXPORT_SYMBOL_GPL(ahci_platform_disable_regulators); +/** * ahci_platform_enable_resources - Enable platform resources * @hpriv: host private area to store config values * @@ -163,11 +207,9 @@ int ahci_platform_enable_resources(struct ahci_host_priv *hpriv) { int rc; - if (hpriv->target_pwr) { - rc = regulator_enable(hpriv->target_pwr); - if (rc) - return rc; - } + rc = ahci_platform_enable_regulators(hpriv); + if (rc) + return rc; rc = ahci_platform_enable_clks(hpriv); if (rc) @@ -183,8 +225,8 @@ disable_clks: ahci_platform_disable_clks(hpriv); disable_regulator: - if (hpriv->target_pwr) - regulator_disable(hpriv->target_pwr); + ahci_platform_disable_regulators(hpriv); + return rc; } EXPORT_SYMBOL_GPL(ahci_platform_enable_resources); @@ -205,8 +247,7 @@ void ahci_platform_disable_resources(struct ahci_host_priv *hpriv) ahci_platform_disable_clks(hpriv); - if (hpriv->target_pwr) - regulator_disable(hpriv->target_pwr); + ahci_platform_disable_regulators(hpriv); } EXPORT_SYMBOL_GPL(ahci_platform_disable_resources); @@ -222,6 +263,69 @@ static void ahci_platform_put_resources(struct device *dev, void *res) for (c = 0; c < AHCI_MAX_CLKS && hpriv->clks[c]; c++) clk_put(hpriv->clks[c]); + /* + * The regulators are tied to child node device and not to the + * SATA device itself. So we can't use devm for automatically + * releasing them. We have to do it manually here. + */ + for (c = 0; c < hpriv->nports; c++) + if (hpriv->target_pwrs && hpriv->target_pwrs[c]) + regulator_put(hpriv->target_pwrs[c]); + + kfree(hpriv->target_pwrs); +} + +static int ahci_platform_get_phy(struct ahci_host_priv *hpriv, u32 port, + struct device *dev, struct device_node *node) +{ + int rc; + + hpriv->phys[port] = devm_of_phy_get(dev, node, NULL); + + if (!IS_ERR(hpriv->phys[port])) + return 0; + + rc = PTR_ERR(hpriv->phys[port]); + switch (rc) { + case -ENOSYS: + /* No PHY support. Check if PHY is required. */ + if (of_find_property(node, "phys", NULL)) { + dev_err(dev, + "couldn't get PHY in node %s: ENOSYS\n", + node->name); + break; + } + case -ENODEV: + /* continue normally */ + hpriv->phys[port] = NULL; + rc = 0; + break; + + default: + dev_err(dev, + "couldn't get PHY in node %s: %d\n", + node->name, rc); + + break; + } + + return rc; +} + +static int ahci_platform_get_regulator(struct ahci_host_priv *hpriv, u32 port, + struct device *dev) +{ + struct regulator *target_pwr; + int rc = 0; + + target_pwr = regulator_get_optional(dev, "target"); + + if (!IS_ERR(target_pwr)) + hpriv->target_pwrs[port] = target_pwr; + else + rc = PTR_ERR(target_pwr); + + return rc; } /** @@ -246,7 +350,7 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev) struct ahci_host_priv *hpriv; struct clk *clk; struct device_node *child; - int i, enabled_ports = 0, rc = -ENOMEM; + int i, sz, enabled_ports = 0, rc = -ENOMEM, child_nodes; u32 mask_port_map = 0; if (!devres_open_group(dev, NULL, GFP_KERNEL)) @@ -267,14 +371,6 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev) goto err_out; } - hpriv->target_pwr = devm_regulator_get_optional(dev, "target"); - if (IS_ERR(hpriv->target_pwr)) { - rc = PTR_ERR(hpriv->target_pwr); - if (rc == -EPROBE_DEFER) - goto err_out; - hpriv->target_pwr = NULL; - } - for (i = 0; i < AHCI_MAX_CLKS; i++) { /* * For now we must use clk_get(dev, NULL) for the first clock, @@ -296,19 +392,33 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev) hpriv->clks[i] = clk; } - hpriv->nports = of_get_child_count(dev->of_node); + hpriv->nports = child_nodes = of_get_child_count(dev->of_node); - if (hpriv->nports) { - hpriv->phys = devm_kzalloc(dev, - hpriv->nports * sizeof(*hpriv->phys), - GFP_KERNEL); - if (!hpriv->phys) { - rc = -ENOMEM; - goto err_out; - } + /* + * If no sub-node was found, we still need to set nports to + * one in order to be able to use the + * ahci_platform_[en|dis]able_[phys|regulators] functions. + */ + if (!child_nodes) + hpriv->nports = 1; + sz = hpriv->nports * sizeof(*hpriv->phys); + hpriv->phys = devm_kzalloc(dev, sz, GFP_KERNEL); + if (!hpriv->phys) { + rc = -ENOMEM; + goto err_out; + } + sz = hpriv->nports * sizeof(*hpriv->target_pwrs); + hpriv->target_pwrs = kzalloc(sz, GFP_KERNEL); + if (!hpriv->target_pwrs) { + rc = -ENOMEM; + goto err_out; + } + + if (child_nodes) { for_each_child_of_node(dev->of_node, child) { u32 port; + struct platform_device *port_dev __maybe_unused; if (!of_device_is_available(child)) continue; @@ -322,17 +432,24 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev) dev_warn(dev, "invalid port number %d\n", port); continue; } - mask_port_map |= BIT(port); - hpriv->phys[port] = devm_of_phy_get(dev, child, NULL); - if (IS_ERR(hpriv->phys[port])) { - rc = PTR_ERR(hpriv->phys[port]); - dev_err(dev, - "couldn't get PHY in node %s: %d\n", - child->name, rc); - goto err_out; +#ifdef CONFIG_OF_ADDRESS + of_platform_device_create(child, NULL, NULL); + + port_dev = of_find_device_by_node(child); + + if (port_dev) { + rc = ahci_platform_get_regulator(hpriv, port, + &port_dev->dev); + if (rc == -EPROBE_DEFER) + goto err_out; } +#endif + + rc = ahci_platform_get_phy(hpriv, port, dev, child); + if (rc) + goto err_out; enabled_ports++; } @@ -349,38 +466,14 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev) * If no sub-node was found, keep this for device tree * compatibility */ - struct phy *phy = devm_phy_get(dev, "sata-phy"); - if (!IS_ERR(phy)) { - hpriv->phys = devm_kzalloc(dev, sizeof(*hpriv->phys), - GFP_KERNEL); - if (!hpriv->phys) { - rc = -ENOMEM; - goto err_out; - } - - hpriv->phys[0] = phy; - hpriv->nports = 1; - } else { - rc = PTR_ERR(phy); - switch (rc) { - case -ENOSYS: - /* No PHY support. Check if PHY is required. */ - if (of_find_property(dev->of_node, "phys", NULL)) { - dev_err(dev, "couldn't get sata-phy: ENOSYS\n"); - goto err_out; - } - case -ENODEV: - /* continue normally */ - hpriv->phys = NULL; - break; - - default: - goto err_out; + rc = ahci_platform_get_phy(hpriv, 0, dev, dev->of_node); + if (rc) + goto err_out; - } - } + rc = ahci_platform_get_regulator(hpriv, 0, dev); + if (rc == -EPROBE_DEFER) + goto err_out; } - pm_runtime_enable(dev); pm_runtime_get_sync(dev); hpriv->got_runtime_pm = true; @@ -399,6 +492,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_get_resources); * @pdev: platform device pointer for the host * @hpriv: ahci-host private data for the host * @pi_template: template for the ata_port_info to use + * @sht: scsi_host_template to use when registering * * This function does all the usual steps needed to bring up an * ahci-platform host, note any necessary resources (ie clks, phys, etc.) @@ -409,7 +503,8 @@ EXPORT_SYMBOL_GPL(ahci_platform_get_resources); */ int ahci_platform_init_host(struct platform_device *pdev, struct ahci_host_priv *hpriv, - const struct ata_port_info *pi_template) + const struct ata_port_info *pi_template, + struct scsi_host_template *sht) { struct device *dev = &pdev->dev; struct ata_port_info pi = *pi_template; @@ -493,7 +588,7 @@ int ahci_platform_init_host(struct platform_device *pdev, ahci_init_controller(host); ahci_print_info(host, "platform"); - return ahci_host_activate(host, irq, &ahci_platform_sht); + return ahci_host_activate(host, irq, sht); } EXPORT_SYMBOL_GPL(ahci_platform_init_host); diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index d1a05f9bb91..4b0d5e71858 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -1752,33 +1752,6 @@ unsigned ata_exec_internal(struct ata_device *dev, } /** - * ata_do_simple_cmd - execute simple internal command - * @dev: Device to which the command is sent - * @cmd: Opcode to execute - * - * Execute a 'simple' command, that only consists of the opcode - * 'cmd' itself, without filling any other registers - * - * LOCKING: - * Kernel thread context (may sleep). - * - * RETURNS: - * Zero on success, AC_ERR_* mask on failure - */ -unsigned int ata_do_simple_cmd(struct ata_device *dev, u8 cmd) -{ - struct ata_taskfile tf; - - ata_tf_init(dev, &tf); - - tf.command = cmd; - tf.flags |= ATA_TFLAG_DEVICE; - tf.protocol = ATA_PROT_NODATA; - - return ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0); -} - -/** * ata_pio_need_iordy - check if iordy needed * @adev: ATA device * diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 8d00c2638be..a9f5aed32d3 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -1635,7 +1635,6 @@ unsigned int atapi_eh_request_sense(struct ata_device *dev, DPRINTK("ATAPI request sense\n"); - /* FIXME: is this needed? */ memset(sense_buf, 0, SCSI_SENSE_BUFFERSIZE); /* initialize sense_buf with the error register, diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 6abd17a85b1..280729325eb 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1995,8 +1995,8 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf) VPRINTK("ENTER\n"); - /* set scsi removeable (RMB) bit per ata bit */ - if (ata_id_removeable(args->id)) + /* set scsi removable (RMB) bit per ata bit */ + if (ata_id_removable(args->id)) hdr[1] |= (1 << 7); if (args->dev->class == ATA_DEV_ZAC) { diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index 5f4e0cca56e..82ebe263d2f 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -76,7 +76,6 @@ extern unsigned ata_exec_internal_sg(struct ata_device *dev, struct ata_taskfile *tf, const u8 *cdb, int dma_dir, struct scatterlist *sg, unsigned int n_elem, unsigned long timeout); -extern unsigned int ata_do_simple_cmd(struct ata_device *dev, u8 cmd); extern int ata_wait_ready(struct ata_link *link, unsigned long deadline, int (*check_ready)(struct ata_link *link)); extern int ata_dev_read_id(struct ata_device *dev, unsigned int *p_class, diff --git a/drivers/ata/pata_cs5530.c b/drivers/ata/pata_cs5530.c index 48ae4b43447..f9ca72e937e 100644 --- a/drivers/ata/pata_cs5530.c +++ b/drivers/ata/pata_cs5530.c @@ -276,10 +276,8 @@ static int cs5530_init_chip(void) pci_dev_put(cs5530_0); return 0; fail_put: - if (master_0) - pci_dev_put(master_0); - if (cs5530_0) - pci_dev_put(cs5530_0); + pci_dev_put(master_0); + pci_dev_put(cs5530_0); return -ENODEV; } diff --git a/drivers/ata/pata_of_platform.c b/drivers/ata/pata_of_platform.c index dcc408abe17..b6b7af894d9 100644 --- a/drivers/ata/pata_of_platform.c +++ b/drivers/ata/pata_of_platform.c @@ -16,6 +16,12 @@ #include <linux/ata_platform.h> #include <linux/libata.h> +#define DRV_NAME "pata_of_platform" + +static struct scsi_host_template pata_platform_sht = { + ATA_PIO_SHT(DRV_NAME), +}; + static int pata_of_platform_probe(struct platform_device *ofdev) { int ret; @@ -63,7 +69,7 @@ static int pata_of_platform_probe(struct platform_device *ofdev) pio_mask |= (1 << pio_mode) - 1; return __pata_platform_probe(&ofdev->dev, &io_res, &ctl_res, irq_res, - reg_shift, pio_mask); + reg_shift, pio_mask, &pata_platform_sht); } static struct of_device_id pata_of_platform_match[] = { @@ -74,7 +80,7 @@ MODULE_DEVICE_TABLE(of, pata_of_platform_match); static struct platform_driver pata_of_platform_driver = { .driver = { - .name = "pata_of_platform", + .name = DRV_NAME, .of_match_table = pata_of_platform_match, }, .probe = pata_of_platform_probe, diff --git a/drivers/ata/pata_pdc2027x.c b/drivers/ata/pata_pdc2027x.c index 4d06a5cda98..dca8251b1ae 100644 --- a/drivers/ata/pata_pdc2027x.c +++ b/drivers/ata/pata_pdc2027x.c @@ -28,6 +28,7 @@ #include <linux/blkdev.h> #include <linux/delay.h> #include <linux/device.h> +#include <linux/ktime.h> #include <scsi/scsi.h> #include <scsi/scsi_host.h> #include <scsi/scsi_cmnd.h> @@ -605,7 +606,7 @@ static long pdc_detect_pll_input_clock(struct ata_host *host) void __iomem *mmio_base = host->iomap[PDC_MMIO_BAR]; u32 scr; long start_count, end_count; - struct timeval start_time, end_time; + ktime_t start_time, end_time; long pll_clock, usec_elapsed; /* Start the test mode */ @@ -616,14 +617,14 @@ static long pdc_detect_pll_input_clock(struct ata_host *host) /* Read current counter value */ start_count = pdc_read_counter(host); - do_gettimeofday(&start_time); + start_time = ktime_get(); /* Let the counter run for 100 ms. */ mdelay(100); /* Read the counter values again */ end_count = pdc_read_counter(host); - do_gettimeofday(&end_time); + end_time = ktime_get(); /* Stop the test mode */ scr = ioread32(mmio_base + PDC_SYS_CTL); @@ -632,8 +633,7 @@ static long pdc_detect_pll_input_clock(struct ata_host *host) ioread32(mmio_base + PDC_SYS_CTL); /* flush */ /* calculate the input clock in Hz */ - usec_elapsed = (end_time.tv_sec - start_time.tv_sec) * 1000000 + - (end_time.tv_usec - start_time.tv_usec); + usec_elapsed = (long) ktime_us_delta(end_time, start_time); pll_clock = ((start_count - end_count) & 0x3fffffff) / 100 * (100000000 / usec_elapsed); diff --git a/drivers/ata/pata_platform.c b/drivers/ata/pata_platform.c index 1eedfe46d7c..c503ded87bb 100644 --- a/drivers/ata/pata_platform.c +++ b/drivers/ata/pata_platform.c @@ -78,6 +78,7 @@ static void pata_platform_setup_port(struct ata_ioports *ioaddr, * @irq_res: Resource representing IRQ and its flags * @ioport_shift: I/O port shift * @__pio_mask: PIO mask + * @sht: scsi_host_template to use when registering * * Register a platform bus IDE interface. Such interfaces are PIO and we * assume do not support IRQ sharing. @@ -99,7 +100,8 @@ static void pata_platform_setup_port(struct ata_ioports *ioaddr, */ int __pata_platform_probe(struct device *dev, struct resource *io_res, struct resource *ctl_res, struct resource *irq_res, - unsigned int ioport_shift, int __pio_mask) + unsigned int ioport_shift, int __pio_mask, + struct scsi_host_template *sht) { struct ata_host *host; struct ata_port *ap; @@ -170,7 +172,7 @@ int __pata_platform_probe(struct device *dev, struct resource *io_res, /* activate */ return ata_host_activate(host, irq, irq ? ata_sff_interrupt : NULL, - irq_flags, &pata_platform_sht); + irq_flags, sht); } EXPORT_SYMBOL_GPL(__pata_platform_probe); @@ -216,7 +218,7 @@ static int pata_platform_probe(struct platform_device *pdev) return __pata_platform_probe(&pdev->dev, io_res, ctl_res, irq_res, pp_info ? pp_info->ioport_shift : 0, - pio_mask); + pio_mask, &pata_platform_sht); } static struct platform_driver pata_platform_driver = { diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c index 8e8248179d2..fdb0f2879ea 100644 --- a/drivers/ata/sata_dwc_460ex.c +++ b/drivers/ata/sata_dwc_460ex.c @@ -48,6 +48,18 @@ #define DRV_NAME "sata-dwc" #define DRV_VERSION "1.3" +#ifndef out_le32 +#define out_le32(a, v) __raw_writel(__cpu_to_le32(v), (void __iomem *)(a)) +#endif + +#ifndef in_le32 +#define in_le32(a) __le32_to_cpu(__raw_readl((void __iomem *)(a))) +#endif + +#ifndef NO_IRQ +#define NO_IRQ 0 +#endif + /* SATA DMA driver Globals */ #define DMA_NUM_CHANS 1 #define DMA_NUM_CHAN_REGS 8 @@ -273,7 +285,7 @@ struct sata_dwc_device { struct device *dev; /* generic device struct */ struct ata_probe_ent *pe; /* ptr to probe-ent */ struct ata_host *host; - u8 *reg_base; + u8 __iomem *reg_base; struct sata_dwc_regs *sata_dwc_regs; /* DW Synopsys SATA specific */ int irq_dma; }; @@ -323,7 +335,9 @@ struct sata_dwc_host_priv { struct device *dwc_dev; int dma_channel; }; -struct sata_dwc_host_priv host_pvt; + +static struct sata_dwc_host_priv host_pvt; + /* * Prototypes */ @@ -580,9 +594,9 @@ static int map_sg_to_lli(struct scatterlist *sg, int num_elems, sms_val = 0; dms_val = 1 + host_pvt.dma_channel; - dev_dbg(host_pvt.dwc_dev, "%s: sg=%p nelem=%d lli=%p dma_lli=0x%08x" - " dmadr=0x%08x\n", __func__, sg, num_elems, lli, (u32)dma_lli, - (u32)dmadr_addr); + dev_dbg(host_pvt.dwc_dev, + "%s: sg=%p nelem=%d lli=%p dma_lli=0x%pad dmadr=0x%p\n", + __func__, sg, num_elems, lli, &dma_lli, dmadr_addr); bl = get_burst_length_encode(AHB_DMA_BRST_DFLT); @@ -773,7 +787,7 @@ static void dma_dwc_exit(struct sata_dwc_device *hsdev) { dev_dbg(host_pvt.dwc_dev, "%s:\n", __func__); if (host_pvt.sata_dma_regs) { - iounmap(host_pvt.sata_dma_regs); + iounmap((void __iomem *)host_pvt.sata_dma_regs); host_pvt.sata_dma_regs = NULL; } @@ -818,7 +832,7 @@ static int sata_dwc_scr_read(struct ata_link *link, unsigned int scr, u32 *val) return -EINVAL; } - *val = in_le32((void *)link->ap->ioaddr.scr_addr + (scr * 4)); + *val = in_le32(link->ap->ioaddr.scr_addr + (scr * 4)); dev_dbg(link->ap->dev, "%s: id=%d reg=%d val=val=0x%08x\n", __func__, link->ap->print_id, scr, *val); @@ -834,21 +848,19 @@ static int sata_dwc_scr_write(struct ata_link *link, unsigned int scr, u32 val) __func__, scr); return -EINVAL; } - out_le32((void *)link->ap->ioaddr.scr_addr + (scr * 4), val); + out_le32(link->ap->ioaddr.scr_addr + (scr * 4), val); return 0; } static u32 core_scr_read(unsigned int scr) { - return in_le32((void __iomem *)(host_pvt.scr_addr_sstatus) +\ - (scr * 4)); + return in_le32(host_pvt.scr_addr_sstatus + (scr * 4)); } static void core_scr_write(unsigned int scr, u32 val) { - out_le32((void __iomem *)(host_pvt.scr_addr_sstatus) + (scr * 4), - val); + out_le32(host_pvt.scr_addr_sstatus + (scr * 4), val); } static void clear_serror(void) @@ -856,7 +868,6 @@ static void clear_serror(void) u32 val; val = core_scr_read(SCR_ERROR); core_scr_write(SCR_ERROR, val); - } static void clear_interrupt_bit(struct sata_dwc_device *hsdev, u32 bit) @@ -1256,24 +1267,24 @@ static void sata_dwc_enable_interrupts(struct sata_dwc_device *hsdev) static void sata_dwc_setup_port(struct ata_ioports *port, unsigned long base) { - port->cmd_addr = (void *)base + 0x00; - port->data_addr = (void *)base + 0x00; + port->cmd_addr = (void __iomem *)base + 0x00; + port->data_addr = (void __iomem *)base + 0x00; - port->error_addr = (void *)base + 0x04; - port->feature_addr = (void *)base + 0x04; + port->error_addr = (void __iomem *)base + 0x04; + port->feature_addr = (void __iomem *)base + 0x04; - port->nsect_addr = (void *)base + 0x08; + port->nsect_addr = (void __iomem *)base + 0x08; - port->lbal_addr = (void *)base + 0x0c; - port->lbam_addr = (void *)base + 0x10; - port->lbah_addr = (void *)base + 0x14; + port->lbal_addr = (void __iomem *)base + 0x0c; + port->lbam_addr = (void __iomem *)base + 0x10; + port->lbah_addr = (void __iomem *)base + 0x14; - port->device_addr = (void *)base + 0x18; - port->command_addr = (void *)base + 0x1c; - port->status_addr = (void *)base + 0x1c; + port->device_addr = (void __iomem *)base + 0x18; + port->command_addr = (void __iomem *)base + 0x1c; + port->status_addr = (void __iomem *)base + 0x1c; - port->altstatus_addr = (void *)base + 0x20; - port->ctl_addr = (void *)base + 0x20; + port->altstatus_addr = (void __iomem *)base + 0x20; + port->ctl_addr = (void __iomem *)base + 0x20; } /* @@ -1314,7 +1325,7 @@ static int sata_dwc_port_start(struct ata_port *ap) for (i = 0; i < SATA_DWC_QCMD_MAX; i++) hsdevp->cmd_issued[i] = SATA_DWC_CMD_ISSUED_NOT; - ap->bmdma_prd = 0; /* set these so libata doesn't use them */ + ap->bmdma_prd = NULL; /* set these so libata doesn't use them */ ap->bmdma_prd_dma = 0; /* @@ -1511,8 +1522,8 @@ static void sata_dwc_qc_prep_by_tag(struct ata_queued_cmd *qc, u8 tag) dma_chan = dma_dwc_xfer_setup(sg, qc->n_elem, hsdevp->llit[tag], hsdevp->llit_dma[tag], - (void *__iomem)(&hsdev->sata_dwc_regs->\ - dmadr), qc->dma_dir); + (void __iomem *)&hsdev->sata_dwc_regs->dmadr, + qc->dma_dir); if (dma_chan < 0) { dev_err(ap->dev, "%s: dma_dwc_xfer_setup returns err %d\n", __func__, dma_chan); @@ -1585,8 +1596,8 @@ static void sata_dwc_error_handler(struct ata_port *ap) ata_sff_error_handler(ap); } -int sata_dwc_hardreset(struct ata_link *link, unsigned int *class, - unsigned long deadline) +static int sata_dwc_hardreset(struct ata_link *link, unsigned int *class, + unsigned long deadline) { struct sata_dwc_device *hsdev = HSDEV_FROM_AP(link->ap); int ret; @@ -1618,7 +1629,7 @@ static struct scsi_host_template sata_dwc_sht = { * max of 1. This will get fixed in in a future release. */ .sg_tablesize = LIBATA_MAX_PRD, - .can_queue = ATA_DEF_QUEUE, /* ATA_MAX_QUEUE */ + /* .can_queue = ATA_MAX_QUEUE, */ .dma_boundary = ATA_DMA_BOUNDARY, }; @@ -1655,7 +1666,7 @@ static int sata_dwc_probe(struct platform_device *ofdev) struct sata_dwc_device *hsdev; u32 idr, versionr; char *ver = (char *)&versionr; - u8 *base = NULL; + u8 __iomem *base; int err = 0; int irq; struct ata_host *host; @@ -1665,12 +1676,12 @@ static int sata_dwc_probe(struct platform_device *ofdev) u32 dma_chan; /* Allocate DWC SATA device */ - hsdev = kzalloc(sizeof(*hsdev), GFP_KERNEL); - if (hsdev == NULL) { - dev_err(&ofdev->dev, "kmalloc failed for hsdev\n"); - err = -ENOMEM; - goto error; - } + host = ata_host_alloc_pinfo(&ofdev->dev, ppi, SATA_DWC_MAX_PORTS); + hsdev = devm_kzalloc(&ofdev->dev, sizeof(*hsdev), GFP_KERNEL); + if (!host || !hsdev) + return -ENOMEM; + + host->private_data = hsdev; if (of_property_read_u32(np, "dma-channel", &dma_chan)) { dev_warn(&ofdev->dev, "no dma-channel property set." @@ -1680,12 +1691,11 @@ static int sata_dwc_probe(struct platform_device *ofdev) host_pvt.dma_channel = dma_chan; /* Ioremap SATA registers */ - base = of_iomap(ofdev->dev.of_node, 0); + base = of_iomap(np, 0); if (!base) { dev_err(&ofdev->dev, "ioremap failed for SATA register" " address\n"); - err = -ENODEV; - goto error_kmalloc; + return -ENODEV; } hsdev->reg_base = base; dev_dbg(&ofdev->dev, "ioremap done for SATA register address\n"); @@ -1693,16 +1703,6 @@ static int sata_dwc_probe(struct platform_device *ofdev) /* Synopsys DWC SATA specific Registers */ hsdev->sata_dwc_regs = (void *__iomem)(base + SATA_DWC_REG_OFFSET); - /* Allocate and fill host */ - host = ata_host_alloc_pinfo(&ofdev->dev, ppi, SATA_DWC_MAX_PORTS); - if (!host) { - dev_err(&ofdev->dev, "ata_host_alloc_pinfo failed\n"); - err = -ENOMEM; - goto error_iomap; - } - - host->private_data = hsdev; - /* Setup port */ host->ports[0]->ioaddr.cmd_addr = base; host->ports[0]->ioaddr.scr_addr = base + SATA_DWC_SCR_OFFSET; @@ -1716,7 +1716,7 @@ static int sata_dwc_probe(struct platform_device *ofdev) idr, ver[0], ver[1], ver[2]); /* Get SATA DMA interrupt number */ - irq = irq_of_parse_and_map(ofdev->dev.of_node, 1); + irq = irq_of_parse_and_map(np, 1); if (irq == NO_IRQ) { dev_err(&ofdev->dev, "no SATA DMA irq\n"); err = -ENODEV; @@ -1724,7 +1724,7 @@ static int sata_dwc_probe(struct platform_device *ofdev) } /* Get physical SATA DMA register base address */ - host_pvt.sata_dma_regs = of_iomap(ofdev->dev.of_node, 1); + host_pvt.sata_dma_regs = (void *)of_iomap(np, 1); if (!(host_pvt.sata_dma_regs)) { dev_err(&ofdev->dev, "ioremap failed for AHBDMA register" " address\n"); @@ -1744,7 +1744,7 @@ static int sata_dwc_probe(struct platform_device *ofdev) sata_dwc_enable_interrupts(hsdev); /* Get SATA interrupt number */ - irq = irq_of_parse_and_map(ofdev->dev.of_node, 0); + irq = irq_of_parse_and_map(np, 0); if (irq == NO_IRQ) { dev_err(&ofdev->dev, "no SATA DMA irq\n"); err = -ENODEV; @@ -1770,9 +1770,6 @@ error_dma_iomap: iounmap((void __iomem *)host_pvt.sata_dma_regs); error_iomap: iounmap(base); -error_kmalloc: - kfree(hsdev); -error: return err; } @@ -1783,15 +1780,12 @@ static int sata_dwc_remove(struct platform_device *ofdev) struct sata_dwc_device *hsdev = host->private_data; ata_host_detach(host); - dev_set_drvdata(dev, NULL); /* Free SATA DMA resources */ dma_dwc_exit(hsdev); iounmap((void __iomem *)host_pvt.sata_dma_regs); iounmap(hsdev->reg_base); - kfree(hsdev); - kfree(host); dev_dbg(&ofdev->dev, "done\n"); return 0; } diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index f9a0e34eb11..f8c33e3772b 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -4185,8 +4185,7 @@ err: clk_disable_unprepare(hpriv->port_clks[port]); clk_put(hpriv->port_clks[port]); } - if (hpriv->port_phys[port]) - phy_power_off(hpriv->port_phys[port]); + phy_power_off(hpriv->port_phys[port]); } return rc; @@ -4216,8 +4215,7 @@ static int mv_platform_remove(struct platform_device *pdev) clk_disable_unprepare(hpriv->port_clks[port]); clk_put(hpriv->port_clks[port]); } - if (hpriv->port_phys[port]) - phy_power_off(hpriv->port_phys[port]); + phy_power_off(hpriv->port_phys[port]); } return 0; } diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index cb0d2e644af..d49a5193b7d 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -2,8 +2,8 @@ * Renesas R-Car SATA driver * * Author: Vladimir Barinov <source@cogentembedded.com> - * Copyright (C) 2013 Cogent Embedded, Inc. - * Copyright (C) 2013 Renesas Solutions Corp. + * Copyright (C) 2013-2015 Cogent Embedded, Inc. + * Copyright (C) 2013-2015 Renesas Solutions Corp. * * 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 @@ -992,9 +992,30 @@ static int sata_rcar_resume(struct device *dev) return 0; } +static int sata_rcar_restore(struct device *dev) +{ + struct ata_host *host = dev_get_drvdata(dev); + struct sata_rcar_priv *priv = host->private_data; + + clk_prepare_enable(priv->clk); + + sata_rcar_setup_port(host); + + /* initialize host controller */ + sata_rcar_init_controller(host); + + ata_host_resume(host); + + return 0; +} + static const struct dev_pm_ops sata_rcar_pm_ops = { .suspend = sata_rcar_suspend, .resume = sata_rcar_resume, + .freeze = sata_rcar_suspend, + .thaw = sata_rcar_resume, + .poweroff = sata_rcar_suspend, + .restore = sata_rcar_restore, }; #endif diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c index b0f138806bb..f32b802b98f 100644 --- a/drivers/base/power/common.c +++ b/drivers/base/power/common.c @@ -19,8 +19,8 @@ * @dev: Device to handle. * * If power.subsys_data is NULL, point it to a new object, otherwise increment - * its reference counter. Return 1 if a new object has been created, otherwise - * return 0 or error code. + * its reference counter. Return 0 if new object has been created or refcount + * increased, otherwise negative error code. */ int dev_pm_get_subsys_data(struct device *dev) { @@ -56,13 +56,11 @@ EXPORT_SYMBOL_GPL(dev_pm_get_subsys_data); * @dev: Device to handle. * * If the reference counter of power.subsys_data is zero after dropping the - * reference, power.subsys_data is removed. Return 1 if that happens or 0 - * otherwise. + * reference, power.subsys_data is removed. */ -int dev_pm_put_subsys_data(struct device *dev) +void dev_pm_put_subsys_data(struct device *dev) { struct pm_subsys_data *psd; - int ret = 1; spin_lock_irq(&dev->power.lock); @@ -70,18 +68,14 @@ int dev_pm_put_subsys_data(struct device *dev) if (!psd) goto out; - if (--psd->refcount == 0) { + if (--psd->refcount == 0) dev->power.subsys_data = NULL; - } else { + else psd = NULL; - ret = 0; - } out: spin_unlock_irq(&dev->power.lock); kfree(psd); - - return ret; } EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data); diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 0d8780c04a5..ba4abbe4693 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -344,14 +344,7 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb, struct device *dev; gpd_data = container_of(nb, struct generic_pm_domain_data, nb); - - mutex_lock(&gpd_data->lock); dev = gpd_data->base.dev; - if (!dev) { - mutex_unlock(&gpd_data->lock); - return NOTIFY_DONE; - } - mutex_unlock(&gpd_data->lock); for (;;) { struct generic_pm_domain *genpd; @@ -1384,25 +1377,66 @@ EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron); #endif /* CONFIG_PM_SLEEP */ -static struct generic_pm_domain_data *__pm_genpd_alloc_dev_data(struct device *dev) +static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev, + struct generic_pm_domain *genpd, + struct gpd_timing_data *td) { struct generic_pm_domain_data *gpd_data; + int ret; + + ret = dev_pm_get_subsys_data(dev); + if (ret) + return ERR_PTR(ret); gpd_data = kzalloc(sizeof(*gpd_data), GFP_KERNEL); - if (!gpd_data) - return NULL; + if (!gpd_data) { + ret = -ENOMEM; + goto err_put; + } + + if (td) + gpd_data->td = *td; - mutex_init(&gpd_data->lock); + gpd_data->base.dev = dev; + gpd_data->need_restore = -1; + gpd_data->td.constraint_changed = true; + gpd_data->td.effective_constraint_ns = -1; gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier; - dev_pm_qos_add_notifier(dev, &gpd_data->nb); + + spin_lock_irq(&dev->power.lock); + + if (dev->power.subsys_data->domain_data) { + ret = -EINVAL; + goto err_free; + } + + dev->power.subsys_data->domain_data = &gpd_data->base; + dev->pm_domain = &genpd->domain; + + spin_unlock_irq(&dev->power.lock); + return gpd_data; + + err_free: + spin_unlock_irq(&dev->power.lock); + kfree(gpd_data); + err_put: + dev_pm_put_subsys_data(dev); + return ERR_PTR(ret); } -static void __pm_genpd_free_dev_data(struct device *dev, - struct generic_pm_domain_data *gpd_data) +static void genpd_free_dev_data(struct device *dev, + struct generic_pm_domain_data *gpd_data) { - dev_pm_qos_remove_notifier(dev, &gpd_data->nb); + spin_lock_irq(&dev->power.lock); + + dev->pm_domain = NULL; + dev->power.subsys_data->domain_data = NULL; + + spin_unlock_irq(&dev->power.lock); + kfree(gpd_data); + dev_pm_put_subsys_data(dev); } /** @@ -1414,8 +1448,7 @@ static void __pm_genpd_free_dev_data(struct device *dev, int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, struct gpd_timing_data *td) { - struct generic_pm_domain_data *gpd_data_new, *gpd_data = NULL; - struct pm_domain_data *pdd; + struct generic_pm_domain_data *gpd_data; int ret = 0; dev_dbg(dev, "%s()\n", __func__); @@ -1423,9 +1456,9 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev)) return -EINVAL; - gpd_data_new = __pm_genpd_alloc_dev_data(dev); - if (!gpd_data_new) - return -ENOMEM; + gpd_data = genpd_alloc_dev_data(dev, genpd, td); + if (IS_ERR(gpd_data)) + return PTR_ERR(gpd_data); genpd_acquire_lock(genpd); @@ -1434,50 +1467,22 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, goto out; } - list_for_each_entry(pdd, &genpd->dev_list, list_node) - if (pdd->dev == dev) { - ret = -EINVAL; - goto out; - } - - ret = dev_pm_get_subsys_data(dev); + ret = genpd->attach_dev ? genpd->attach_dev(genpd, dev) : 0; if (ret) goto out; genpd->device_count++; genpd->max_off_time_changed = true; - spin_lock_irq(&dev->power.lock); - - dev->pm_domain = &genpd->domain; - if (dev->power.subsys_data->domain_data) { - gpd_data = to_gpd_data(dev->power.subsys_data->domain_data); - } else { - gpd_data = gpd_data_new; - dev->power.subsys_data->domain_data = &gpd_data->base; - } - gpd_data->refcount++; - if (td) - gpd_data->td = *td; - - spin_unlock_irq(&dev->power.lock); - - if (genpd->attach_dev) - genpd->attach_dev(genpd, dev); - - mutex_lock(&gpd_data->lock); - gpd_data->base.dev = dev; list_add_tail(&gpd_data->base.list_node, &genpd->dev_list); - gpd_data->need_restore = -1; - gpd_data->td.constraint_changed = true; - gpd_data->td.effective_constraint_ns = -1; - mutex_unlock(&gpd_data->lock); out: genpd_release_lock(genpd); - if (gpd_data != gpd_data_new) - __pm_genpd_free_dev_data(dev, gpd_data_new); + if (ret) + genpd_free_dev_data(dev, gpd_data); + else + dev_pm_qos_add_notifier(dev, &gpd_data->nb); return ret; } @@ -1504,7 +1509,6 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, { struct generic_pm_domain_data *gpd_data; struct pm_domain_data *pdd; - bool remove = false; int ret = 0; dev_dbg(dev, "%s()\n", __func__); @@ -1514,6 +1518,11 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, || pd_to_genpd(dev->pm_domain) != genpd) return -EINVAL; + /* The above validation also means we have existing domain_data. */ + pdd = dev->power.subsys_data->domain_data; + gpd_data = to_gpd_data(pdd); + dev_pm_qos_remove_notifier(dev, &gpd_data->nb); + genpd_acquire_lock(genpd); if (genpd->prepared_count > 0) { @@ -1527,58 +1536,22 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, if (genpd->detach_dev) genpd->detach_dev(genpd, dev); - spin_lock_irq(&dev->power.lock); - - dev->pm_domain = NULL; - pdd = dev->power.subsys_data->domain_data; list_del_init(&pdd->list_node); - gpd_data = to_gpd_data(pdd); - if (--gpd_data->refcount == 0) { - dev->power.subsys_data->domain_data = NULL; - remove = true; - } - - spin_unlock_irq(&dev->power.lock); - - mutex_lock(&gpd_data->lock); - pdd->dev = NULL; - mutex_unlock(&gpd_data->lock); genpd_release_lock(genpd); - dev_pm_put_subsys_data(dev); - if (remove) - __pm_genpd_free_dev_data(dev, gpd_data); + genpd_free_dev_data(dev, gpd_data); return 0; out: genpd_release_lock(genpd); + dev_pm_qos_add_notifier(dev, &gpd_data->nb); return ret; } /** - * pm_genpd_dev_need_restore - Set/unset the device's "need restore" flag. - * @dev: Device to set/unset the flag for. - * @val: The new value of the device's "need restore" flag. - */ -void pm_genpd_dev_need_restore(struct device *dev, bool val) -{ - struct pm_subsys_data *psd; - unsigned long flags; - - spin_lock_irqsave(&dev->power.lock, flags); - - psd = dev_to_psd(dev); - if (psd && psd->domain_data) - to_gpd_data(psd->domain_data)->need_restore = val ? 1 : 0; - - spin_unlock_irqrestore(&dev->power.lock, flags); -} -EXPORT_SYMBOL_GPL(pm_genpd_dev_need_restore); - -/** * pm_genpd_add_subdomain - Add a subdomain to an I/O PM domain. * @genpd: Master PM domain to add the subdomain to. * @subdomain: Subdomain to be added. diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c index 106c6935930..15bf29974c3 100644 --- a/drivers/base/power/opp.c +++ b/drivers/base/power/opp.c @@ -117,20 +117,20 @@ do { \ } while (0) /** - * find_device_opp() - find device_opp struct using device pointer + * _find_device_opp() - find device_opp struct using device pointer * @dev: device pointer used to lookup device OPPs * * Search list of device OPPs for one containing matching device. Does a RCU * reader operation to grab the pointer needed. * - * Returns pointer to 'struct device_opp' if found, otherwise -ENODEV or + * Return: pointer to 'struct device_opp' if found, otherwise -ENODEV or * -EINVAL based on type of error. * * Locking: This function must be called under rcu_read_lock(). device_opp * is a RCU protected pointer. This means that device_opp is valid as long * as we are under RCU lock. */ -static struct device_opp *find_device_opp(struct device *dev) +static struct device_opp *_find_device_opp(struct device *dev) { struct device_opp *tmp_dev_opp, *dev_opp = ERR_PTR(-ENODEV); @@ -153,7 +153,7 @@ static struct device_opp *find_device_opp(struct device *dev) * dev_pm_opp_get_voltage() - Gets the voltage corresponding to an available opp * @opp: opp for which voltage has to be returned for * - * Return voltage in micro volt corresponding to the opp, else + * Return: voltage in micro volt corresponding to the opp, else * return 0 * * Locking: This function must be called under rcu_read_lock(). opp is a rcu @@ -169,6 +169,8 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) struct dev_pm_opp *tmp_opp; unsigned long v = 0; + opp_rcu_lockdep_assert(); + tmp_opp = rcu_dereference(opp); if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available) pr_err("%s: Invalid parameters\n", __func__); @@ -183,7 +185,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage); * dev_pm_opp_get_freq() - Gets the frequency corresponding to an available opp * @opp: opp for which frequency has to be returned for * - * Return frequency in hertz corresponding to the opp, else + * Return: frequency in hertz corresponding to the opp, else * return 0 * * Locking: This function must be called under rcu_read_lock(). opp is a rcu @@ -199,6 +201,8 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp) struct dev_pm_opp *tmp_opp; unsigned long f = 0; + opp_rcu_lockdep_assert(); + tmp_opp = rcu_dereference(opp); if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available) pr_err("%s: Invalid parameters\n", __func__); @@ -213,7 +217,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq); * dev_pm_opp_get_opp_count() - Get number of opps available in the opp list * @dev: device for which we do this operation * - * This function returns the number of available opps if there are any, + * Return: This function returns the number of available opps if there are any, * else returns 0 if none or the corresponding error value. * * Locking: This function takes rcu_read_lock(). @@ -226,7 +230,7 @@ int dev_pm_opp_get_opp_count(struct device *dev) rcu_read_lock(); - dev_opp = find_device_opp(dev); + dev_opp = _find_device_opp(dev); if (IS_ERR(dev_opp)) { count = PTR_ERR(dev_opp); dev_err(dev, "%s: device OPP not found (%d)\n", @@ -251,9 +255,9 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count); * @freq: frequency to search for * @available: true/false - match for available opp * - * Searches for exact match in the opp list and returns pointer to the matching - * opp if found, else returns ERR_PTR in case of error and should be handled - * using IS_ERR. Error return values can be: + * Return: Searches for exact match in the opp list and returns pointer to the + * matching opp if found, else returns ERR_PTR in case of error and should + * be handled using IS_ERR. Error return values can be: * EINVAL: for bad pointer * ERANGE: no match found for search * ENODEV: if device not found in list of registered devices @@ -280,7 +284,7 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, opp_rcu_lockdep_assert(); - dev_opp = find_device_opp(dev); + dev_opp = _find_device_opp(dev); if (IS_ERR(dev_opp)) { int r = PTR_ERR(dev_opp); dev_err(dev, "%s: device OPP not found (%d)\n", __func__, r); @@ -307,7 +311,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact); * Search for the matching ceil *available* OPP from a starting freq * for a device. * - * Returns matching *opp and refreshes *freq accordingly, else returns + * Return: matching *opp and refreshes *freq accordingly, else returns * ERR_PTR in case of error and should be handled using IS_ERR. Error return * values can be: * EINVAL: for bad pointer @@ -333,7 +337,7 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, return ERR_PTR(-EINVAL); } - dev_opp = find_device_opp(dev); + dev_opp = _find_device_opp(dev); if (IS_ERR(dev_opp)) return ERR_CAST(dev_opp); @@ -357,7 +361,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil); * Search for the matching floor *available* OPP from a starting freq * for a device. * - * Returns matching *opp and refreshes *freq accordingly, else returns + * Return: matching *opp and refreshes *freq accordingly, else returns * ERR_PTR in case of error and should be handled using IS_ERR. Error return * values can be: * EINVAL: for bad pointer @@ -383,7 +387,7 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, return ERR_PTR(-EINVAL); } - dev_opp = find_device_opp(dev); + dev_opp = _find_device_opp(dev); if (IS_ERR(dev_opp)) return ERR_CAST(dev_opp); @@ -403,7 +407,16 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, } EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor); -static struct device_opp *add_device_opp(struct device *dev) +/** + * _add_device_opp() - Allocate a new device OPP table + * @dev: device for which we do this operation + * + * New device node which uses OPPs - used when multiple devices with OPP tables + * are maintained. + * + * Return: valid device_opp pointer if success, else NULL. + */ +static struct device_opp *_add_device_opp(struct device *dev) { struct device_opp *dev_opp; @@ -424,8 +437,35 @@ static struct device_opp *add_device_opp(struct device *dev) return dev_opp; } -static int dev_pm_opp_add_dynamic(struct device *dev, unsigned long freq, - unsigned long u_volt, bool dynamic) +/** + * _opp_add_dynamic() - Allocate a dynamic OPP. + * @dev: device for which we do this operation + * @freq: Frequency in Hz for this OPP + * @u_volt: Voltage in uVolts for this OPP + * @dynamic: Dynamically added OPPs. + * + * This function adds an opp definition to the opp list and returns status. + * The opp is made available by default and it can be controlled using + * dev_pm_opp_enable/disable functions and may be removed by dev_pm_opp_remove. + * + * NOTE: "dynamic" parameter impacts OPPs added by the of_init_opp_table and + * freed by of_free_opp_table. + * + * Locking: The internal device_opp 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. + * + * Return: + * 0 On success OR + * Duplicate OPPs (both freq and volt are same) and opp->available + * -EEXIST Freq are same and volt are different OR + * Duplicate OPPs (both freq and volt are same) and !opp->available + * -ENOMEM Memory allocation failure + */ +static int _opp_add_dynamic(struct device *dev, unsigned long freq, + long u_volt, bool dynamic) { struct device_opp *dev_opp = NULL; struct dev_pm_opp *opp, *new_opp; @@ -449,9 +489,9 @@ static int dev_pm_opp_add_dynamic(struct device *dev, unsigned long freq, new_opp->dynamic = dynamic; /* Check for existing list for 'dev' */ - dev_opp = find_device_opp(dev); + dev_opp = _find_device_opp(dev); if (IS_ERR(dev_opp)) { - dev_opp = add_device_opp(dev); + dev_opp = _add_device_opp(dev); if (!dev_opp) { ret = -ENOMEM; goto free_opp; @@ -519,34 +559,53 @@ free_opp: * mutex cannot be locked. * * Return: - * 0: On success OR + * 0 On success OR * Duplicate OPPs (both freq and volt are same) and opp->available - * -EEXIST: Freq are same and volt are different OR + * -EEXIST Freq are same and volt are different OR * Duplicate OPPs (both freq and volt are same) and !opp->available - * -ENOMEM: Memory allocation failure + * -ENOMEM Memory allocation failure */ int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt) { - return dev_pm_opp_add_dynamic(dev, freq, u_volt, true); + return _opp_add_dynamic(dev, freq, u_volt, true); } EXPORT_SYMBOL_GPL(dev_pm_opp_add); -static void kfree_opp_rcu(struct rcu_head *head) +/** + * _kfree_opp_rcu() - Free OPP RCU handler + * @head: RCU head + */ +static void _kfree_opp_rcu(struct rcu_head *head) { struct dev_pm_opp *opp = container_of(head, struct dev_pm_opp, rcu_head); kfree_rcu(opp, rcu_head); } -static void kfree_device_rcu(struct rcu_head *head) +/** + * _kfree_device_rcu() - Free device_opp RCU handler + * @head: RCU head + */ +static void _kfree_device_rcu(struct rcu_head *head) { struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head); kfree_rcu(device_opp, rcu_head); } -static void __dev_pm_opp_remove(struct device_opp *dev_opp, - struct dev_pm_opp *opp) +/** + * _opp_remove() - Remove an OPP from a table definition + * @dev_opp: points back to the device_opp struct this opp belongs to + * @opp: pointer to the OPP to remove + * + * This function removes an opp definition from the opp list. + * + * Locking: The internal device_opp and opp structures are RCU protected. + * It is assumed that the caller holds required mutex for an RCU updater + * strategy. + */ +static void _opp_remove(struct device_opp *dev_opp, + struct dev_pm_opp *opp) { /* * Notify the changes in the availability of the operable @@ -554,12 +613,12 @@ static void __dev_pm_opp_remove(struct device_opp *dev_opp, */ srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp); list_del_rcu(&opp->node); - call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, kfree_opp_rcu); + call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu); if (list_empty(&dev_opp->opp_list)) { list_del_rcu(&dev_opp->node); call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head, - kfree_device_rcu); + _kfree_device_rcu); } } @@ -569,6 +628,12 @@ static void __dev_pm_opp_remove(struct device_opp *dev_opp, * @freq: OPP to remove with matching 'freq' * * This function removes an opp from the opp list. + * + * Locking: The internal device_opp 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_remove(struct device *dev, unsigned long freq) { @@ -579,7 +644,7 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq) /* Hold our list modification lock here */ mutex_lock(&dev_opp_list_lock); - dev_opp = find_device_opp(dev); + dev_opp = _find_device_opp(dev); if (IS_ERR(dev_opp)) goto unlock; @@ -596,14 +661,14 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq) goto unlock; } - __dev_pm_opp_remove(dev_opp, opp); + _opp_remove(dev_opp, opp); unlock: mutex_unlock(&dev_opp_list_lock); } EXPORT_SYMBOL_GPL(dev_pm_opp_remove); /** - * opp_set_availability() - helper to set the availability of an opp + * _opp_set_availability() - helper to set the availability of an opp * @dev: device for which we do this operation * @freq: OPP frequency to modify availability * @availability_req: availability status requested for this opp @@ -611,7 +676,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_remove); * Set the availability of an OPP with an RCU operation, opp_{enable,disable} * share a common logic which is isolated here. * - * Returns -EINVAL for bad pointers, -ENOMEM if no memory available for the + * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the * copy operation, returns 0 if no modifcation was done OR modification was * successful. * @@ -621,8 +686,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_remove); * that this function is *NOT* called under RCU protection or in contexts where * mutex locking or synchronize_rcu() blocking calls cannot be used. */ -static int opp_set_availability(struct device *dev, unsigned long freq, - bool availability_req) +static int _opp_set_availability(struct device *dev, unsigned long freq, + bool availability_req) { struct device_opp *dev_opp; struct dev_pm_opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV); @@ -638,7 +703,7 @@ static int opp_set_availability(struct device *dev, unsigned long freq, mutex_lock(&dev_opp_list_lock); /* Find the device_opp */ - dev_opp = find_device_opp(dev); + dev_opp = _find_device_opp(dev); if (IS_ERR(dev_opp)) { r = PTR_ERR(dev_opp); dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r); @@ -668,7 +733,7 @@ static int opp_set_availability(struct device *dev, unsigned long freq, list_replace_rcu(&opp->node, &new_opp->node); mutex_unlock(&dev_opp_list_lock); - call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, kfree_opp_rcu); + call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu); /* Notify the change of the OPP availability */ if (availability_req) @@ -700,10 +765,14 @@ unlock: * integrity of the internal data structures. Callers should ensure that * this function is *NOT* called under RCU protection or in contexts where * mutex locking or synchronize_rcu() blocking calls cannot be used. + * + * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the + * copy operation, returns 0 if no modifcation was done OR modification was + * successful. */ int dev_pm_opp_enable(struct device *dev, unsigned long freq) { - return opp_set_availability(dev, freq, true); + return _opp_set_availability(dev, freq, true); } EXPORT_SYMBOL_GPL(dev_pm_opp_enable); @@ -722,26 +791,41 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_enable); * integrity of the internal data structures. Callers should ensure that * this function is *NOT* called under RCU protection or in contexts where * mutex locking or synchronize_rcu() blocking calls cannot be used. + * + * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the + * copy operation, returns 0 if no modifcation was done OR modification was + * successful. */ int dev_pm_opp_disable(struct device *dev, unsigned long freq) { - return opp_set_availability(dev, freq, false); + return _opp_set_availability(dev, freq, false); } EXPORT_SYMBOL_GPL(dev_pm_opp_disable); /** * dev_pm_opp_get_notifier() - find notifier_head of the device with opp * @dev: device pointer used to lookup device OPPs. + * + * Return: pointer to notifier head if found, otherwise -ENODEV or + * -EINVAL based on type of error casted as pointer. value must be checked + * with IS_ERR to determine valid pointer or error result. + * + * Locking: This function must be called under rcu_read_lock(). dev_opp is a RCU + * protected pointer. The reason for the same is that the opp pointer which is + * returned will remain valid for use with opp_get_{voltage, freq} only while + * under the locked area. The pointer returned must be used prior to unlocking + * with rcu_read_unlock() to maintain the integrity of the pointer. */ struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev) { - struct device_opp *dev_opp = find_device_opp(dev); + struct device_opp *dev_opp = _find_device_opp(dev); if (IS_ERR(dev_opp)) return ERR_CAST(dev_opp); /* matching type */ return &dev_opp->srcu_head; } +EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier); #ifdef CONFIG_OF /** @@ -749,6 +833,22 @@ struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev) * @dev: device pointer used to lookup device OPPs. * * Register the initial OPP table with the OPP library for given device. + * + * Locking: The internal device_opp and opp structures are RCU protected. + * Hence this function indirectly 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. + * + * Return: + * 0 On success OR + * Duplicate OPPs (both freq and volt are same) and opp->available + * -EEXIST Freq are same and volt are different OR + * Duplicate OPPs (both freq and volt are same) and !opp->available + * -ENOMEM Memory allocation failure + * -ENODEV when 'operating-points' property is not found or is invalid data + * in device node. + * -ENODATA when empty 'operating-points' property is found */ int of_init_opp_table(struct device *dev) { @@ -777,7 +877,7 @@ int of_init_opp_table(struct device *dev) unsigned long freq = be32_to_cpup(val++) * 1000; unsigned long volt = be32_to_cpup(val++); - if (dev_pm_opp_add_dynamic(dev, freq, volt, false)) + if (_opp_add_dynamic(dev, freq, volt, false)) dev_warn(dev, "%s: Failed to add OPP %ld\n", __func__, freq); nr -= 2; @@ -792,6 +892,12 @@ EXPORT_SYMBOL_GPL(of_init_opp_table); * @dev: device pointer used to lookup device OPPs. * * Free OPPs created using static entries present in DT. + * + * Locking: The internal device_opp and opp structures are RCU protected. + * Hence this function indirectly 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 of_free_opp_table(struct device *dev) { @@ -799,7 +905,7 @@ void of_free_opp_table(struct device *dev) struct dev_pm_opp *opp, *tmp; /* Check for existing list for 'dev' */ - dev_opp = find_device_opp(dev); + dev_opp = _find_device_opp(dev); if (IS_ERR(dev_opp)) { int error = PTR_ERR(dev_opp); if (error != -ENODEV) @@ -816,7 +922,7 @@ void of_free_opp_table(struct device *dev) /* Free static OPPs */ list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) { if (!opp->dynamic) - __dev_pm_opp_remove(dev_opp, opp); + _opp_remove(dev_opp, opp); } mutex_unlock(&dev_opp_list_lock); diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c index a8fe4c1a8d0..e56d538d039 100644 --- a/drivers/base/power/qos.c +++ b/drivers/base/power/qos.c @@ -64,6 +64,8 @@ enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask) struct pm_qos_flags *pqf; s32 val; + lockdep_assert_held(&dev->power.lock); + if (IS_ERR_OR_NULL(qos)) return PM_QOS_FLAGS_UNDEFINED; @@ -104,6 +106,8 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_flags); */ s32 __dev_pm_qos_read_value(struct device *dev) { + lockdep_assert_held(&dev->power.lock); + return IS_ERR_OR_NULL(dev->power.qos) ? 0 : pm_qos_read_value(&dev->power.qos->resume_latency); } diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index 0da5865df5b..beb8b27d462 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -51,9 +51,11 @@ struct regmap_async { struct regmap { union { struct mutex mutex; - spinlock_t spinlock; + struct { + spinlock_t spinlock; + unsigned long spinlock_flags; + }; }; - unsigned long spinlock_flags; regmap_lock lock; regmap_unlock unlock; void *lock_arg; /* This is passed to lock/unlock functions */ @@ -233,6 +235,10 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, void regmap_async_complete_cb(struct regmap_async *async, int ret); +enum regmap_endian regmap_get_val_endian(struct device *dev, + const struct regmap_bus *bus, + const struct regmap_config *config); + extern struct regcache_ops regcache_rbtree_ops; extern struct regcache_ops regcache_lzo_ops; extern struct regcache_ops regcache_flat_ops; diff --git a/drivers/base/regmap/regmap-ac97.c b/drivers/base/regmap/regmap-ac97.c index e4c45d2299c..8d304e2a943 100644 --- a/drivers/base/regmap/regmap-ac97.c +++ b/drivers/base/regmap/regmap-ac97.c @@ -74,8 +74,8 @@ static int regmap_ac97_reg_write(void *context, unsigned int reg, } static const struct regmap_bus ac97_regmap_bus = { - .reg_write = regmap_ac97_reg_write, - .reg_read = regmap_ac97_reg_read, + .reg_write = regmap_ac97_reg_write, + .reg_read = regmap_ac97_reg_read, }; /** diff --git a/drivers/base/regmap/regmap-i2c.c b/drivers/base/regmap/regmap-i2c.c index 053150a7f9f..4b76e33110a 100644 --- a/drivers/base/regmap/regmap-i2c.c +++ b/drivers/base/regmap/regmap-i2c.c @@ -14,6 +14,7 @@ #include <linux/i2c.h> #include <linux/module.h> +#include "internal.h" static int regmap_smbus_byte_reg_read(void *context, unsigned int reg, unsigned int *val) @@ -87,6 +88,42 @@ static struct regmap_bus regmap_smbus_word = { .reg_read = regmap_smbus_word_reg_read, }; +static int regmap_smbus_word_read_swapped(void *context, unsigned int reg, + unsigned int *val) +{ + struct device *dev = context; + struct i2c_client *i2c = to_i2c_client(dev); + int ret; + + if (reg > 0xff) + return -EINVAL; + + ret = i2c_smbus_read_word_swapped(i2c, reg); + if (ret < 0) + return ret; + + *val = ret; + + return 0; +} + +static int regmap_smbus_word_write_swapped(void *context, unsigned int reg, + unsigned int val) +{ + struct device *dev = context; + struct i2c_client *i2c = to_i2c_client(dev); + + if (val > 0xffff || reg > 0xff) + return -EINVAL; + + return i2c_smbus_write_word_swapped(i2c, reg, val); +} + +static struct regmap_bus regmap_smbus_word_swapped = { + .reg_write = regmap_smbus_word_write_swapped, + .reg_read = regmap_smbus_word_read_swapped, +}; + static int regmap_i2c_write(void *context, const void *data, size_t count) { struct device *dev = context; @@ -180,7 +217,14 @@ static const struct regmap_bus *regmap_get_i2c_bus(struct i2c_client *i2c, else if (config->val_bits == 16 && config->reg_bits == 8 && i2c_check_functionality(i2c->adapter, I2C_FUNC_SMBUS_WORD_DATA)) - return ®map_smbus_word; + switch (regmap_get_val_endian(&i2c->dev, NULL, config)) { + case REGMAP_ENDIAN_LITTLE: + return ®map_smbus_word; + case REGMAP_ENDIAN_BIG: + return ®map_smbus_word_swapped; + default: /* everything else is not supported */ + break; + } else if (config->val_bits == 8 && config->reg_bits == 8 && i2c_check_functionality(i2c->adapter, I2C_FUNC_SMBUS_BYTE_DATA)) diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index d2f8a818d20..f99b098ddab 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -473,9 +473,9 @@ static enum regmap_endian regmap_get_reg_endian(const struct regmap_bus *bus, return REGMAP_ENDIAN_BIG; } -static enum regmap_endian regmap_get_val_endian(struct device *dev, - const struct regmap_bus *bus, - const struct regmap_config *config) +enum regmap_endian regmap_get_val_endian(struct device *dev, + const struct regmap_bus *bus, + const struct regmap_config *config) { struct device_node *np; enum regmap_endian endian; @@ -513,6 +513,7 @@ static enum regmap_endian regmap_get_val_endian(struct device *dev, /* Use this if no other value was found */ return REGMAP_ENDIAN_BIG; } +EXPORT_SYMBOL_GPL(regmap_get_val_endian); /** * regmap_init(): Initialise register map diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 63fc7f06a01..2a04d341e59 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -47,6 +47,7 @@ #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> #include <xen/balloon.h> +#include <xen/grant_table.h> #include "common.h" /* @@ -100,7 +101,7 @@ module_param(log_stats, int, 0644); #define BLKBACK_INVALID_HANDLE (~0) -/* Number of free pages to remove on each call to free_xenballooned_pages */ +/* Number of free pages to remove on each call to gnttab_free_pages */ #define NUM_BATCH_FREE_PAGES 10 static inline int get_free_page(struct xen_blkif *blkif, struct page **page) @@ -111,7 +112,7 @@ static inline int get_free_page(struct xen_blkif *blkif, struct page **page) if (list_empty(&blkif->free_pages)) { BUG_ON(blkif->free_pages_num != 0); spin_unlock_irqrestore(&blkif->free_pages_lock, flags); - return alloc_xenballooned_pages(1, page, false); + return gnttab_alloc_pages(1, page); } BUG_ON(blkif->free_pages_num == 0); page[0] = list_first_entry(&blkif->free_pages, struct page, lru); @@ -151,14 +152,14 @@ static inline void shrink_free_pagepool(struct xen_blkif *blkif, int num) blkif->free_pages_num--; if (++num_pages == NUM_BATCH_FREE_PAGES) { spin_unlock_irqrestore(&blkif->free_pages_lock, flags); - free_xenballooned_pages(num_pages, page); + gnttab_free_pages(num_pages, page); spin_lock_irqsave(&blkif->free_pages_lock, flags); num_pages = 0; } } spin_unlock_irqrestore(&blkif->free_pages_lock, flags); if (num_pages != 0) - free_xenballooned_pages(num_pages, page); + gnttab_free_pages(num_pages, page); } #define vaddr(page) ((unsigned long)pfn_to_kaddr(page_to_pfn(page))) @@ -262,6 +263,17 @@ static void put_persistent_gnt(struct xen_blkif *blkif, atomic_dec(&blkif->persistent_gnt_in_use); } +static void free_persistent_gnts_unmap_callback(int result, + struct gntab_unmap_queue_data *data) +{ + struct completion *c = data->data; + + /* BUG_ON used to reproduce existing behaviour, + but is this the best way to deal with this? */ + BUG_ON(result); + complete(c); +} + static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root, unsigned int num) { @@ -269,8 +281,17 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root, struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST]; struct persistent_gnt *persistent_gnt; struct rb_node *n; - int ret = 0; int segs_to_unmap = 0; + struct gntab_unmap_queue_data unmap_data; + struct completion unmap_completion; + + init_completion(&unmap_completion); + + unmap_data.data = &unmap_completion; + unmap_data.done = &free_persistent_gnts_unmap_callback; + unmap_data.pages = pages; + unmap_data.unmap_ops = unmap; + unmap_data.kunmap_ops = NULL; foreach_grant_safe(persistent_gnt, n, root, node) { BUG_ON(persistent_gnt->handle == @@ -285,9 +306,11 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root, if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST || !rb_next(&persistent_gnt->node)) { - ret = gnttab_unmap_refs(unmap, NULL, pages, - segs_to_unmap); - BUG_ON(ret); + + unmap_data.count = segs_to_unmap; + gnttab_unmap_refs_async(&unmap_data); + wait_for_completion(&unmap_completion); + put_free_pages(blkif, pages, segs_to_unmap); segs_to_unmap = 0; } @@ -653,18 +676,14 @@ void xen_blkbk_free_caches(struct xen_blkif *blkif) shrink_free_pagepool(blkif, 0 /* All */); } -/* - * Unmap the grant references, and also remove the M2P over-rides - * used in the 'pending_req'. - */ -static void xen_blkbk_unmap(struct xen_blkif *blkif, - struct grant_page *pages[], - int num) +static unsigned int xen_blkbk_unmap_prepare( + struct xen_blkif *blkif, + struct grant_page **pages, + unsigned int num, + struct gnttab_unmap_grant_ref *unmap_ops, + struct page **unmap_pages) { - struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST]; - struct page *unmap_pages[BLKIF_MAX_SEGMENTS_PER_REQUEST]; unsigned int i, invcount = 0; - int ret; for (i = 0; i < num; i++) { if (pages[i]->persistent_gnt != NULL) { @@ -674,21 +693,95 @@ static void xen_blkbk_unmap(struct xen_blkif *blkif, if (pages[i]->handle == BLKBACK_INVALID_HANDLE) continue; unmap_pages[invcount] = pages[i]->page; - gnttab_set_unmap_op(&unmap[invcount], vaddr(pages[i]->page), + gnttab_set_unmap_op(&unmap_ops[invcount], vaddr(pages[i]->page), GNTMAP_host_map, pages[i]->handle); pages[i]->handle = BLKBACK_INVALID_HANDLE; - if (++invcount == BLKIF_MAX_SEGMENTS_PER_REQUEST) { - ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, - invcount); + invcount++; + } + + return invcount; +} + +static void xen_blkbk_unmap_and_respond_callback(int result, struct gntab_unmap_queue_data *data) +{ + struct pending_req* pending_req = (struct pending_req*) (data->data); + struct xen_blkif *blkif = pending_req->blkif; + + /* BUG_ON used to reproduce existing behaviour, + but is this the best way to deal with this? */ + BUG_ON(result); + + put_free_pages(blkif, data->pages, data->count); + make_response(blkif, pending_req->id, + pending_req->operation, pending_req->status); + free_req(blkif, pending_req); + /* + * Make sure the request is freed before releasing blkif, + * or there could be a race between free_req and the + * cleanup done in xen_blkif_free during shutdown. + * + * NB: The fact that we might try to wake up pending_free_wq + * before drain_complete (in case there's a drain going on) + * it's not a problem with our current implementation + * because we can assure there's no thread waiting on + * pending_free_wq if there's a drain going on, but it has + * to be taken into account if the current model is changed. + */ + if (atomic_dec_and_test(&blkif->inflight) && atomic_read(&blkif->drain)) { + complete(&blkif->drain_complete); + } + xen_blkif_put(blkif); +} + +static void xen_blkbk_unmap_and_respond(struct pending_req *req) +{ + struct gntab_unmap_queue_data* work = &req->gnttab_unmap_data; + struct xen_blkif *blkif = req->blkif; + struct grant_page **pages = req->segments; + unsigned int invcount; + + invcount = xen_blkbk_unmap_prepare(blkif, pages, req->nr_pages, + req->unmap, req->unmap_pages); + + work->data = req; + work->done = xen_blkbk_unmap_and_respond_callback; + work->unmap_ops = req->unmap; + work->kunmap_ops = NULL; + work->pages = req->unmap_pages; + work->count = invcount; + + gnttab_unmap_refs_async(&req->gnttab_unmap_data); +} + + +/* + * Unmap the grant references. + * + * This could accumulate ops up to the batch size to reduce the number + * of hypercalls, but since this is only used in error paths there's + * no real need. + */ +static void xen_blkbk_unmap(struct xen_blkif *blkif, + struct grant_page *pages[], + int num) +{ + struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct page *unmap_pages[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + unsigned int invcount = 0; + int ret; + + while (num) { + unsigned int batch = min(num, BLKIF_MAX_SEGMENTS_PER_REQUEST); + + invcount = xen_blkbk_unmap_prepare(blkif, pages, batch, + unmap, unmap_pages); + if (invcount) { + ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount); BUG_ON(ret); put_free_pages(blkif, unmap_pages, invcount); - invcount = 0; } - } - if (invcount) { - ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount); - BUG_ON(ret); - put_free_pages(blkif, unmap_pages, invcount); + pages += batch; + num -= batch; } } @@ -982,32 +1075,8 @@ static void __end_block_io_op(struct pending_req *pending_req, int error) * the grant references associated with 'request' and provide * the proper response on the ring. */ - if (atomic_dec_and_test(&pending_req->pendcnt)) { - struct xen_blkif *blkif = pending_req->blkif; - - xen_blkbk_unmap(blkif, - pending_req->segments, - pending_req->nr_pages); - make_response(blkif, pending_req->id, - pending_req->operation, pending_req->status); - free_req(blkif, pending_req); - /* - * Make sure the request is freed before releasing blkif, - * or there could be a race between free_req and the - * cleanup done in xen_blkif_free during shutdown. - * - * NB: The fact that we might try to wake up pending_free_wq - * before drain_complete (in case there's a drain going on) - * it's not a problem with our current implementation - * because we can assure there's no thread waiting on - * pending_free_wq if there's a drain going on, but it has - * to be taken into account if the current model is changed. - */ - if (atomic_dec_and_test(&blkif->inflight) && atomic_read(&blkif->drain)) { - complete(&blkif->drain_complete); - } - xen_blkif_put(blkif); - } + if (atomic_dec_and_test(&pending_req->pendcnt)) + xen_blkbk_unmap_and_respond(pending_req); } /* diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index f65b807e323..cc90a840e61 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -350,6 +350,9 @@ struct pending_req { struct grant_page *indirect_pages[MAX_INDIRECT_PAGES]; struct seg_buf seg[MAX_INDIRECT_SEGMENTS]; struct bio *biolist[MAX_INDIRECT_SEGMENTS]; + struct gnttab_unmap_grant_ref unmap[MAX_INDIRECT_SEGMENTS]; + struct page *unmap_pages[MAX_INDIRECT_SEGMENTS]; + struct gntab_unmap_queue_data gnttab_unmap_data; }; diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index d5d4cd82b9f..5c0baa9ffc6 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -976,8 +976,8 @@ static acpi_status hpet_resources(struct acpi_resource *res, void *data) status = acpi_resource_to_address64(res, &addr); if (ACPI_SUCCESS(status)) { - hdp->hd_phys_address = addr.minimum; - hdp->hd_address = ioremap(addr.minimum, addr.address_length); + hdp->hd_phys_address = addr.address.minimum; + hdp->hd_address = ioremap(addr.address.minimum, addr.address.address_length); if (hpet_is_known(hdp)) { iounmap(hdp->hd_address); diff --git a/drivers/char/random.c b/drivers/char/random.c index 04645c09fe5..9cd6968e2f9 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -569,19 +569,19 @@ static void fast_mix(struct fast_pool *f) __u32 c = f->pool[2], d = f->pool[3]; a += b; c += d; - b = rol32(a, 6); d = rol32(c, 27); + b = rol32(b, 6); d = rol32(d, 27); d ^= a; b ^= c; a += b; c += d; - b = rol32(a, 16); d = rol32(c, 14); + b = rol32(b, 16); d = rol32(d, 14); d ^= a; b ^= c; a += b; c += d; - b = rol32(a, 6); d = rol32(c, 27); + b = rol32(b, 6); d = rol32(d, 27); d ^= a; b ^= c; a += b; c += d; - b = rol32(a, 16); d = rol32(c, 14); + b = rol32(b, 16); d = rol32(d, 14); d ^= a; b ^= c; f->pool[0] = a; f->pool[1] = b; diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index 3f44f292d06..91f86131bb7 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -13,6 +13,7 @@ config COMMON_CLK bool select HAVE_CLK_PREPARE select CLKDEV_LOOKUP + select SRCU ---help--- The common clock framework is a single definition of struct clk, useful across many platforms, as well as an diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index 29b2ef5a68b..a171fef2c2b 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -2,6 +2,7 @@ menu "CPU Frequency scaling" config CPU_FREQ bool "CPU Frequency scaling" + select SRCU help CPU Frequency scaling allows you to change the clock speed of CPUs on the fly. This is a nice method to save power, because diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86 index 89ae88f9189..c59bdcb8321 100644 --- a/drivers/cpufreq/Kconfig.x86 +++ b/drivers/cpufreq/Kconfig.x86 @@ -57,6 +57,16 @@ config X86_ACPI_CPUFREQ_CPB By enabling this option the acpi_cpufreq driver provides the old entry in addition to the new boost ones, for compatibility reasons. +config X86_SFI_CPUFREQ + tristate "SFI Performance-States driver" + depends on X86_INTEL_MID && SFI + help + This adds a CPUFreq driver for some Silvermont based Intel Atom + architectures like Z34xx and Z35xx which enumerate processor + performance states through SFI. + + If in doubt, say N. + config ELAN_CPUFREQ tristate "AMD Elan SC400 and SC410" depends on MELAN diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index b3ca7b0b2c3..8b4220ac888 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -41,6 +41,7 @@ obj-$(CONFIG_X86_P4_CLOCKMOD) += p4-clockmod.o obj-$(CONFIG_X86_CPUFREQ_NFORCE2) += cpufreq-nforce2.o obj-$(CONFIG_X86_INTEL_PSTATE) += intel_pstate.o obj-$(CONFIG_X86_AMD_FREQ_SENSITIVITY) += amd_freq_sensitivity.o +obj-$(CONFIG_X86_SFI_CPUFREQ) += sfi-cpufreq.o ################################################################################## # ARM SoC drivers diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index fde97d6e31d..bab67db54b7 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -320,8 +320,7 @@ static int cpufreq_exit(struct cpufreq_policy *policy) { struct private_data *priv = policy->driver_data; - if (priv->cdev) - cpufreq_cooling_unregister(priv->cdev); + cpufreq_cooling_unregister(priv->cdev); dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); of_free_opp_table(priv->cpu_dev); clk_put(policy->clk); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 46bed4f81cd..28e59a48b35 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -27,9 +27,21 @@ #include <linux/mutex.h> #include <linux/slab.h> #include <linux/suspend.h> +#include <linux/syscore_ops.h> #include <linux/tick.h> #include <trace/events/power.h> +/* Macros to iterate over lists */ +/* Iterate over online CPUs policies */ +static LIST_HEAD(cpufreq_policy_list); +#define for_each_policy(__policy) \ + list_for_each_entry(__policy, &cpufreq_policy_list, policy_list) + +/* Iterate over governors */ +static LIST_HEAD(cpufreq_governor_list); +#define for_each_governor(__governor) \ + list_for_each_entry(__governor, &cpufreq_governor_list, governor_list) + /** * The "cpufreq driver" - the arch- or hardware-dependent low * level driver of CPUFreq support, and its spinlock. This lock @@ -40,7 +52,6 @@ static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data); static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data_fallback); static DEFINE_RWLOCK(cpufreq_driver_lock); DEFINE_MUTEX(cpufreq_governor_lock); -static LIST_HEAD(cpufreq_policy_list); /* This one keeps track of the previously set governor of a removed CPU */ static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor); @@ -62,7 +73,7 @@ static DECLARE_RWSEM(cpufreq_rwsem); /* internal prototypes */ static int __cpufreq_governor(struct cpufreq_policy *policy, unsigned int event); -static unsigned int __cpufreq_get(unsigned int cpu); +static unsigned int __cpufreq_get(struct cpufreq_policy *policy); static void handle_update(struct work_struct *work); /** @@ -93,7 +104,6 @@ void disable_cpufreq(void) { off = 1; } -static LIST_HEAD(cpufreq_governor_list); static DEFINE_MUTEX(cpufreq_governor_mutex); bool have_governor_per_policy(void) @@ -202,7 +212,7 @@ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) struct cpufreq_policy *policy = NULL; unsigned long flags; - if (cpufreq_disabled() || (cpu >= nr_cpu_ids)) + if (cpu >= nr_cpu_ids) return NULL; if (!down_read_trylock(&cpufreq_rwsem)) @@ -229,9 +239,6 @@ EXPORT_SYMBOL_GPL(cpufreq_cpu_get); void cpufreq_cpu_put(struct cpufreq_policy *policy) { - if (cpufreq_disabled()) - return; - kobject_put(&policy->kobj); up_read(&cpufreq_rwsem); } @@ -249,12 +256,12 @@ EXPORT_SYMBOL_GPL(cpufreq_cpu_put); * systems as each CPU might be scaled differently. So, use the arch * per-CPU loops_per_jiffy value wherever possible. */ -#ifndef CONFIG_SMP -static unsigned long l_p_j_ref; -static unsigned int l_p_j_ref_freq; - static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) { +#ifndef CONFIG_SMP + static unsigned long l_p_j_ref; + static unsigned int l_p_j_ref_freq; + if (ci->flags & CPUFREQ_CONST_LOOPS) return; @@ -270,13 +277,8 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) pr_debug("scaling loops_per_jiffy to %lu for frequency %u kHz\n", loops_per_jiffy, ci->new); } -} -#else -static inline void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) -{ - return; -} #endif +} static void __cpufreq_notify_transition(struct cpufreq_policy *policy, struct cpufreq_freqs *freqs, unsigned int state) @@ -432,11 +434,11 @@ static ssize_t store_boost(struct kobject *kobj, struct attribute *attr, } define_one_global_rw(boost); -static struct cpufreq_governor *__find_governor(const char *str_governor) +static struct cpufreq_governor *find_governor(const char *str_governor) { struct cpufreq_governor *t; - list_for_each_entry(t, &cpufreq_governor_list, governor_list) + for_each_governor(t) if (!strncasecmp(str_governor, t->name, CPUFREQ_NAME_LEN)) return t; @@ -463,12 +465,12 @@ static int cpufreq_parse_governor(char *str_governor, unsigned int *policy, *policy = CPUFREQ_POLICY_POWERSAVE; err = 0; } - } else if (has_target()) { + } else { struct cpufreq_governor *t; mutex_lock(&cpufreq_governor_mutex); - t = __find_governor(str_governor); + t = find_governor(str_governor); if (t == NULL) { int ret; @@ -478,7 +480,7 @@ static int cpufreq_parse_governor(char *str_governor, unsigned int *policy, mutex_lock(&cpufreq_governor_mutex); if (ret == 0) - t = __find_governor(str_governor); + t = find_governor(str_governor); } if (t != NULL) { @@ -513,8 +515,7 @@ show_one(cpuinfo_transition_latency, cpuinfo.transition_latency); show_one(scaling_min_freq, min); show_one(scaling_max_freq, max); -static ssize_t show_scaling_cur_freq( - struct cpufreq_policy *policy, char *buf) +static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf) { ssize_t ret; @@ -563,7 +564,7 @@ store_one(scaling_max_freq, max); static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy, char *buf) { - unsigned int cur_freq = __cpufreq_get(policy->cpu); + unsigned int cur_freq = __cpufreq_get(policy); if (!cur_freq) return sprintf(buf, "<unknown>"); return sprintf(buf, "%u\n", cur_freq); @@ -639,7 +640,7 @@ static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy, goto out; } - list_for_each_entry(t, &cpufreq_governor_list, governor_list) { + for_each_governor(t) { if (i >= (ssize_t) ((PAGE_SIZE / sizeof(char)) - (CPUFREQ_NAME_LEN + 2))) goto out; @@ -902,7 +903,7 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy, /* set up files for this cpu device */ drv_attr = cpufreq_driver->attr; - while ((drv_attr) && (*drv_attr)) { + while (drv_attr && *drv_attr) { ret = sysfs_create_file(&policy->kobj, &((*drv_attr)->attr)); if (ret) return ret; @@ -936,7 +937,7 @@ static void cpufreq_init_policy(struct cpufreq_policy *policy) memcpy(&new_policy, policy, sizeof(*policy)); /* Update governor of new_policy to the governor used before hotplug */ - gov = __find_governor(per_cpu(cpufreq_cpu_governor, policy->cpu)); + gov = find_governor(per_cpu(cpufreq_cpu_governor, policy->cpu)); if (gov) pr_debug("Restoring governor %s for cpu %d\n", policy->governor->name, policy->cpu); @@ -958,7 +959,6 @@ static void cpufreq_init_policy(struct cpufreq_policy *policy) } } -#ifdef CONFIG_HOTPLUG_CPU static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu, struct device *dev) { @@ -996,7 +996,6 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, return sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq"); } -#endif static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu) { @@ -1033,6 +1032,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(void) init_rwsem(&policy->rwsem); spin_lock_init(&policy->transition_lock); init_waitqueue_head(&policy->transition_wait); + init_completion(&policy->kobj_unregister); + INIT_WORK(&policy->update, handle_update); return policy; @@ -1091,15 +1092,9 @@ static int update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu, } down_write(&policy->rwsem); - - policy->last_cpu = policy->cpu; policy->cpu = cpu; - up_write(&policy->rwsem); - blocking_notifier_call_chain(&cpufreq_policy_notifier_list, - CPUFREQ_UPDATE_POLICY_CPU, policy); - return 0; } @@ -1110,41 +1105,32 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) struct cpufreq_policy *policy; unsigned long flags; bool recover_policy = cpufreq_suspended; -#ifdef CONFIG_HOTPLUG_CPU - struct cpufreq_policy *tpolicy; -#endif if (cpu_is_offline(cpu)) return 0; pr_debug("adding CPU %u\n", cpu); -#ifdef CONFIG_SMP /* check whether a different CPU already registered this * CPU because it is in the same boat. */ - policy = cpufreq_cpu_get(cpu); - if (unlikely(policy)) { - cpufreq_cpu_put(policy); + policy = cpufreq_cpu_get_raw(cpu); + if (unlikely(policy)) return 0; - } -#endif if (!down_read_trylock(&cpufreq_rwsem)) return 0; -#ifdef CONFIG_HOTPLUG_CPU /* Check if this cpu was hot-unplugged earlier and has siblings */ read_lock_irqsave(&cpufreq_driver_lock, flags); - list_for_each_entry(tpolicy, &cpufreq_policy_list, policy_list) { - if (cpumask_test_cpu(cpu, tpolicy->related_cpus)) { + for_each_policy(policy) { + if (cpumask_test_cpu(cpu, policy->related_cpus)) { read_unlock_irqrestore(&cpufreq_driver_lock, flags); - ret = cpufreq_add_policy_cpu(tpolicy, cpu, dev); + ret = cpufreq_add_policy_cpu(policy, cpu, dev); up_read(&cpufreq_rwsem); return ret; } } read_unlock_irqrestore(&cpufreq_driver_lock, flags); -#endif /* * Restore the saved policy when doing light-weight init and fall back @@ -1171,9 +1157,6 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) cpumask_copy(policy->cpus, cpumask_of(cpu)); - init_completion(&policy->kobj_unregister); - INIT_WORK(&policy->update, handle_update); - /* call driver. From then on the cpufreq must be able * to accept all calls to ->verify and ->setpolicy for this CPU */ @@ -1371,11 +1354,10 @@ static int __cpufreq_remove_dev_prepare(struct device *dev, pr_err("%s: Failed to stop governor\n", __func__); return ret; } - } - if (!cpufreq_driver->setpolicy) strncpy(per_cpu(cpufreq_cpu_governor, cpu), policy->governor->name, CPUFREQ_NAME_LEN); + } down_read(&policy->rwsem); cpus = cpumask_weight(policy->cpus); @@ -1416,9 +1398,10 @@ static int __cpufreq_remove_dev_finish(struct device *dev, unsigned long flags; struct cpufreq_policy *policy; - read_lock_irqsave(&cpufreq_driver_lock, flags); + write_lock_irqsave(&cpufreq_driver_lock, flags); policy = per_cpu(cpufreq_cpu_data, cpu); - read_unlock_irqrestore(&cpufreq_driver_lock, flags); + per_cpu(cpufreq_cpu_data, cpu) = NULL; + write_unlock_irqrestore(&cpufreq_driver_lock, flags); if (!policy) { pr_debug("%s: No cpu_data found\n", __func__); @@ -1473,7 +1456,6 @@ static int __cpufreq_remove_dev_finish(struct device *dev, } } - per_cpu(cpufreq_cpu_data, cpu) = NULL; return 0; } @@ -1510,30 +1492,23 @@ static void handle_update(struct work_struct *work) /** * cpufreq_out_of_sync - If actual and saved CPU frequency differs, we're * in deep trouble. - * @cpu: cpu number - * @old_freq: CPU frequency the kernel thinks the CPU runs at + * @policy: policy managing CPUs * @new_freq: CPU frequency the CPU actually runs at * * We adjust to current frequency first, and need to clean up later. * So either call to cpufreq_update_policy() or schedule handle_update()). */ -static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq, +static void cpufreq_out_of_sync(struct cpufreq_policy *policy, unsigned int new_freq) { - struct cpufreq_policy *policy; struct cpufreq_freqs freqs; - unsigned long flags; pr_debug("Warning: CPU frequency out of sync: cpufreq and timing core thinks of %u, is %u kHz\n", - old_freq, new_freq); + policy->cur, new_freq); - freqs.old = old_freq; + freqs.old = policy->cur; freqs.new = new_freq; - read_lock_irqsave(&cpufreq_driver_lock, flags); - policy = per_cpu(cpufreq_cpu_data, cpu); - read_unlock_irqrestore(&cpufreq_driver_lock, flags); - cpufreq_freq_transition_begin(policy, &freqs); cpufreq_freq_transition_end(policy, &freqs, 0); } @@ -1583,22 +1558,21 @@ unsigned int cpufreq_quick_get_max(unsigned int cpu) } EXPORT_SYMBOL(cpufreq_quick_get_max); -static unsigned int __cpufreq_get(unsigned int cpu) +static unsigned int __cpufreq_get(struct cpufreq_policy *policy) { - struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu); unsigned int ret_freq = 0; if (!cpufreq_driver->get) return ret_freq; - ret_freq = cpufreq_driver->get(cpu); + ret_freq = cpufreq_driver->get(policy->cpu); if (ret_freq && policy->cur && !(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) { /* verify no discrepancy between actual and saved value exists */ if (unlikely(ret_freq != policy->cur)) { - cpufreq_out_of_sync(cpu, policy->cur, ret_freq); + cpufreq_out_of_sync(policy, ret_freq); schedule_work(&policy->update); } } @@ -1619,7 +1593,7 @@ unsigned int cpufreq_get(unsigned int cpu) if (policy) { down_read(&policy->rwsem); - ret_freq = __cpufreq_get(cpu); + ret_freq = __cpufreq_get(policy); up_read(&policy->rwsem); cpufreq_cpu_put(policy); @@ -1682,7 +1656,7 @@ void cpufreq_suspend(void) pr_debug("%s: Suspending Governors\n", __func__); - list_for_each_entry(policy, &cpufreq_policy_list, policy_list) { + for_each_policy(policy) { if (__cpufreq_governor(policy, CPUFREQ_GOV_STOP)) pr_err("%s: Failed to stop governor for policy: %p\n", __func__, policy); @@ -1716,7 +1690,7 @@ void cpufreq_resume(void) pr_debug("%s: Resuming Governors\n", __func__); - list_for_each_entry(policy, &cpufreq_policy_list, policy_list) { + for_each_policy(policy) { if (cpufreq_driver->resume && cpufreq_driver->resume(policy)) pr_err("%s: Failed to resume driver: %p\n", __func__, policy); @@ -2006,10 +1980,6 @@ int cpufreq_driver_target(struct cpufreq_policy *policy, } EXPORT_SYMBOL_GPL(cpufreq_driver_target); -/* - * when "event" is CPUFREQ_GOV_LIMITS - */ - static int __cpufreq_governor(struct cpufreq_policy *policy, unsigned int event) { @@ -2107,7 +2077,7 @@ int cpufreq_register_governor(struct cpufreq_governor *governor) governor->initialized = 0; err = -EBUSY; - if (__find_governor(governor->name) == NULL) { + if (!find_governor(governor->name)) { err = 0; list_add(&governor->governor_list, &cpufreq_governor_list); } @@ -2307,8 +2277,7 @@ int cpufreq_update_policy(unsigned int cpu) policy->cur = new_policy.cur; } else { if (policy->cur != new_policy.cur && has_target()) - cpufreq_out_of_sync(cpu, policy->cur, - new_policy.cur); + cpufreq_out_of_sync(policy, new_policy.cur); } } @@ -2364,7 +2333,7 @@ static int cpufreq_boost_set_sw(int state) struct cpufreq_policy *policy; int ret = -EINVAL; - list_for_each_entry(policy, &cpufreq_policy_list, policy_list) { + for_each_policy(policy) { freq_table = cpufreq_frequency_get_table(policy->cpu); if (freq_table) { ret = cpufreq_frequency_table_cpuinfo(policy, @@ -2454,9 +2423,6 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) pr_debug("trying to register driver %s\n", driver_data->name); - if (driver_data->setpolicy) - driver_data->flags |= CPUFREQ_CONST_LOOPS; - write_lock_irqsave(&cpufreq_driver_lock, flags); if (cpufreq_driver) { write_unlock_irqrestore(&cpufreq_driver_lock, flags); @@ -2465,6 +2431,9 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) cpufreq_driver = driver_data; write_unlock_irqrestore(&cpufreq_driver_lock, flags); + if (driver_data->setpolicy) + driver_data->flags |= CPUFREQ_CONST_LOOPS; + if (cpufreq_boost_supported()) { /* * Check if driver provides function to enable boost - @@ -2485,23 +2454,12 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) if (ret) goto err_boost_unreg; - if (!(cpufreq_driver->flags & CPUFREQ_STICKY)) { - int i; - ret = -ENODEV; - - /* check for at least one working CPU */ - for (i = 0; i < nr_cpu_ids; i++) - if (cpu_possible(i) && per_cpu(cpufreq_cpu_data, i)) { - ret = 0; - break; - } - + if (!(cpufreq_driver->flags & CPUFREQ_STICKY) && + list_empty(&cpufreq_policy_list)) { /* if all ->init() calls failed, unregister */ - if (ret) { - pr_debug("no CPU initialized for driver %s\n", - driver_data->name); - goto err_if_unreg; - } + pr_debug("%s: No CPU initialized for driver %s\n", __func__, + driver_data->name); + goto err_if_unreg; } register_hotcpu_notifier(&cpufreq_cpu_notifier); @@ -2556,6 +2514,14 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver) } EXPORT_SYMBOL_GPL(cpufreq_unregister_driver); +/* + * Stop cpufreq at shutdown to make sure it isn't holding any locks + * or mutexes when secondary CPUs are halted. + */ +static struct syscore_ops cpufreq_syscore_ops = { + .shutdown = cpufreq_suspend, +}; + static int __init cpufreq_core_init(void) { if (cpufreq_disabled()) @@ -2564,6 +2530,8 @@ static int __init cpufreq_core_init(void) cpufreq_global_kobject = kobject_create(); BUG_ON(!cpufreq_global_kobject); + register_syscore_ops(&cpufreq_syscore_ops); + return 0; } core_initcall(cpufreq_core_init); diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index 0cd9b4dcef9..5e370a30a96 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -18,7 +18,6 @@ static spinlock_t cpufreq_stats_lock; struct cpufreq_stats { - unsigned int cpu; unsigned int total_trans; unsigned long long last_time; unsigned int max_state; @@ -31,50 +30,33 @@ struct cpufreq_stats { #endif }; -static DEFINE_PER_CPU(struct cpufreq_stats *, cpufreq_stats_table); - -struct cpufreq_stats_attribute { - struct attribute attr; - ssize_t(*show) (struct cpufreq_stats *, char *); -}; - -static int cpufreq_stats_update(unsigned int cpu) +static int cpufreq_stats_update(struct cpufreq_stats *stats) { - struct cpufreq_stats *stat; - unsigned long long cur_time; + unsigned long long cur_time = get_jiffies_64(); - cur_time = get_jiffies_64(); spin_lock(&cpufreq_stats_lock); - stat = per_cpu(cpufreq_stats_table, cpu); - if (stat->time_in_state) - stat->time_in_state[stat->last_index] += - cur_time - stat->last_time; - stat->last_time = cur_time; + stats->time_in_state[stats->last_index] += cur_time - stats->last_time; + stats->last_time = cur_time; spin_unlock(&cpufreq_stats_lock); return 0; } static ssize_t show_total_trans(struct cpufreq_policy *policy, char *buf) { - struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, policy->cpu); - if (!stat) - return 0; - return sprintf(buf, "%d\n", - per_cpu(cpufreq_stats_table, stat->cpu)->total_trans); + return sprintf(buf, "%d\n", policy->stats->total_trans); } static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf) { + struct cpufreq_stats *stats = policy->stats; ssize_t len = 0; int i; - struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, policy->cpu); - if (!stat) - return 0; - cpufreq_stats_update(stat->cpu); - for (i = 0; i < stat->state_num; i++) { - len += sprintf(buf + len, "%u %llu\n", stat->freq_table[i], + + cpufreq_stats_update(stats); + for (i = 0; i < stats->state_num; i++) { + len += sprintf(buf + len, "%u %llu\n", stats->freq_table[i], (unsigned long long) - jiffies_64_to_clock_t(stat->time_in_state[i])); + jiffies_64_to_clock_t(stats->time_in_state[i])); } return len; } @@ -82,38 +64,35 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf) #ifdef CONFIG_CPU_FREQ_STAT_DETAILS static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf) { + struct cpufreq_stats *stats = policy->stats; ssize_t len = 0; int i, j; - struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, policy->cpu); - if (!stat) - return 0; - cpufreq_stats_update(stat->cpu); len += snprintf(buf + len, PAGE_SIZE - len, " From : To\n"); len += snprintf(buf + len, PAGE_SIZE - len, " : "); - for (i = 0; i < stat->state_num; i++) { + for (i = 0; i < stats->state_num; i++) { if (len >= PAGE_SIZE) break; len += snprintf(buf + len, PAGE_SIZE - len, "%9u ", - stat->freq_table[i]); + stats->freq_table[i]); } if (len >= PAGE_SIZE) return PAGE_SIZE; len += snprintf(buf + len, PAGE_SIZE - len, "\n"); - for (i = 0; i < stat->state_num; i++) { + for (i = 0; i < stats->state_num; i++) { if (len >= PAGE_SIZE) break; len += snprintf(buf + len, PAGE_SIZE - len, "%9u: ", - stat->freq_table[i]); + stats->freq_table[i]); - for (j = 0; j < stat->state_num; j++) { + for (j = 0; j < stats->state_num; j++) { if (len >= PAGE_SIZE) break; len += snprintf(buf + len, PAGE_SIZE - len, "%9u ", - stat->trans_table[i*stat->max_state+j]); + stats->trans_table[i*stats->max_state+j]); } if (len >= PAGE_SIZE) break; @@ -142,28 +121,29 @@ static struct attribute_group stats_attr_group = { .name = "stats" }; -static int freq_table_get_index(struct cpufreq_stats *stat, unsigned int freq) +static int freq_table_get_index(struct cpufreq_stats *stats, unsigned int freq) { int index; - for (index = 0; index < stat->max_state; index++) - if (stat->freq_table[index] == freq) + for (index = 0; index < stats->max_state; index++) + if (stats->freq_table[index] == freq) return index; return -1; } static void __cpufreq_stats_free_table(struct cpufreq_policy *policy) { - struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, policy->cpu); + struct cpufreq_stats *stats = policy->stats; - if (!stat) + /* Already freed */ + if (!stats) return; - pr_debug("%s: Free stat table\n", __func__); + pr_debug("%s: Free stats table\n", __func__); sysfs_remove_group(&policy->kobj, &stats_attr_group); - kfree(stat->time_in_state); - kfree(stat); - per_cpu(cpufreq_stats_table, policy->cpu) = NULL; + kfree(stats->time_in_state); + kfree(stats); + policy->stats = NULL; } static void cpufreq_stats_free_table(unsigned int cpu) @@ -174,37 +154,33 @@ static void cpufreq_stats_free_table(unsigned int cpu) if (!policy) return; - if (cpufreq_frequency_get_table(policy->cpu)) - __cpufreq_stats_free_table(policy); + __cpufreq_stats_free_table(policy); cpufreq_cpu_put(policy); } static int __cpufreq_stats_create_table(struct cpufreq_policy *policy) { - unsigned int i, count = 0, ret = 0; - struct cpufreq_stats *stat; + unsigned int i = 0, count = 0, ret = -ENOMEM; + struct cpufreq_stats *stats; unsigned int alloc_size; unsigned int cpu = policy->cpu; struct cpufreq_frequency_table *pos, *table; + /* We need cpufreq table for creating stats table */ table = cpufreq_frequency_get_table(cpu); if (unlikely(!table)) return 0; - if (per_cpu(cpufreq_stats_table, cpu)) - return -EBUSY; - stat = kzalloc(sizeof(*stat), GFP_KERNEL); - if ((stat) == NULL) - return -ENOMEM; - - ret = sysfs_create_group(&policy->kobj, &stats_attr_group); - if (ret) - goto error_out; + /* stats already initialized */ + if (policy->stats) + return -EEXIST; - stat->cpu = cpu; - per_cpu(cpufreq_stats_table, cpu) = stat; + stats = kzalloc(sizeof(*stats), GFP_KERNEL); + if (!stats) + return -ENOMEM; + /* Find total allocation size */ cpufreq_for_each_valid_entry(pos, table) count++; @@ -213,32 +189,40 @@ static int __cpufreq_stats_create_table(struct cpufreq_policy *policy) #ifdef CONFIG_CPU_FREQ_STAT_DETAILS alloc_size += count * count * sizeof(int); #endif - stat->max_state = count; - stat->time_in_state = kzalloc(alloc_size, GFP_KERNEL); - if (!stat->time_in_state) { - ret = -ENOMEM; - goto error_alloc; - } - stat->freq_table = (unsigned int *)(stat->time_in_state + count); + + /* Allocate memory for time_in_state/freq_table/trans_table in one go */ + stats->time_in_state = kzalloc(alloc_size, GFP_KERNEL); + if (!stats->time_in_state) + goto free_stat; + + stats->freq_table = (unsigned int *)(stats->time_in_state + count); #ifdef CONFIG_CPU_FREQ_STAT_DETAILS - stat->trans_table = stat->freq_table + count; + stats->trans_table = stats->freq_table + count; #endif - i = 0; + + stats->max_state = count; + + /* Find valid-unique entries */ cpufreq_for_each_valid_entry(pos, table) - if (freq_table_get_index(stat, pos->frequency) == -1) - stat->freq_table[i++] = pos->frequency; - stat->state_num = i; - spin_lock(&cpufreq_stats_lock); - stat->last_time = get_jiffies_64(); - stat->last_index = freq_table_get_index(stat, policy->cur); - spin_unlock(&cpufreq_stats_lock); - return 0; -error_alloc: - sysfs_remove_group(&policy->kobj, &stats_attr_group); -error_out: - kfree(stat); - per_cpu(cpufreq_stats_table, cpu) = NULL; + if (freq_table_get_index(stats, pos->frequency) == -1) + stats->freq_table[i++] = pos->frequency; + + stats->state_num = i; + stats->last_time = get_jiffies_64(); + stats->last_index = freq_table_get_index(stats, policy->cur); + + policy->stats = stats; + ret = sysfs_create_group(&policy->kobj, &stats_attr_group); + if (!ret) + return 0; + + /* We failed, release resources */ + policy->stats = NULL; + kfree(stats->time_in_state); +free_stat: + kfree(stats); + return ret; } @@ -259,30 +243,12 @@ static void cpufreq_stats_create_table(unsigned int cpu) cpufreq_cpu_put(policy); } -static void cpufreq_stats_update_policy_cpu(struct cpufreq_policy *policy) -{ - struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, - policy->last_cpu); - - pr_debug("Updating stats_table for new_cpu %u from last_cpu %u\n", - policy->cpu, policy->last_cpu); - per_cpu(cpufreq_stats_table, policy->cpu) = per_cpu(cpufreq_stats_table, - policy->last_cpu); - per_cpu(cpufreq_stats_table, policy->last_cpu) = NULL; - stat->cpu = policy->cpu; -} - static int cpufreq_stat_notifier_policy(struct notifier_block *nb, unsigned long val, void *data) { int ret = 0; struct cpufreq_policy *policy = data; - if (val == CPUFREQ_UPDATE_POLICY_CPU) { - cpufreq_stats_update_policy_cpu(policy); - return 0; - } - if (val == CPUFREQ_CREATE_POLICY) ret = __cpufreq_stats_create_table(policy); else if (val == CPUFREQ_REMOVE_POLICY) @@ -295,35 +261,45 @@ static int cpufreq_stat_notifier_trans(struct notifier_block *nb, unsigned long val, void *data) { struct cpufreq_freqs *freq = data; - struct cpufreq_stats *stat; + struct cpufreq_policy *policy = cpufreq_cpu_get(freq->cpu); + struct cpufreq_stats *stats; int old_index, new_index; - if (val != CPUFREQ_POSTCHANGE) + if (!policy) { + pr_err("%s: No policy found\n", __func__); return 0; + } - stat = per_cpu(cpufreq_stats_table, freq->cpu); - if (!stat) - return 0; + if (val != CPUFREQ_POSTCHANGE) + goto put_policy; - old_index = stat->last_index; - new_index = freq_table_get_index(stat, freq->new); + if (!policy->stats) { + pr_debug("%s: No stats found\n", __func__); + goto put_policy; + } - /* We can't do stat->time_in_state[-1]= .. */ - if (old_index == -1 || new_index == -1) - return 0; + stats = policy->stats; + + old_index = stats->last_index; + new_index = freq_table_get_index(stats, freq->new); - cpufreq_stats_update(freq->cpu); + /* We can't do stats->time_in_state[-1]= .. */ + if (old_index == -1 || new_index == -1) + goto put_policy; if (old_index == new_index) - return 0; + goto put_policy; - spin_lock(&cpufreq_stats_lock); - stat->last_index = new_index; + cpufreq_stats_update(stats); + + stats->last_index = new_index; #ifdef CONFIG_CPU_FREQ_STAT_DETAILS - stat->trans_table[old_index * stat->max_state + new_index]++; + stats->trans_table[old_index * stats->max_state + new_index]++; #endif - stat->total_trans++; - spin_unlock(&cpufreq_stats_lock); + stats->total_trans++; + +put_policy: + cpufreq_cpu_put(policy); return 0; } @@ -374,8 +350,7 @@ static void __exit cpufreq_stats_exit(void) } MODULE_AUTHOR("Zou Nan hai <nanhai.zou@intel.com>"); -MODULE_DESCRIPTION("'cpufreq_stats' - A driver to export cpufreq stats " - "through sysfs filesystem"); +MODULE_DESCRIPTION("Export cpufreq stats via sysfs"); MODULE_LICENSE("GPL"); module_init(cpufreq_stats_init); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 742eefba12c..872c5772c5d 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -148,6 +148,8 @@ struct perf_limits { int32_t min_perf; int max_policy_pct; int max_sysfs_pct; + int min_policy_pct; + int min_sysfs_pct; }; static struct perf_limits limits = { @@ -159,6 +161,8 @@ static struct perf_limits limits = { .min_perf = 0, .max_policy_pct = 100, .max_sysfs_pct = 100, + .min_policy_pct = 0, + .min_sysfs_pct = 0, }; static inline void pid_reset(struct _pid *pid, int setpoint, int busy, @@ -338,6 +342,33 @@ static void __init intel_pstate_debug_expose_params(void) return sprintf(buf, "%u\n", limits.object); \ } +static ssize_t show_turbo_pct(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct cpudata *cpu; + int total, no_turbo, turbo_pct; + uint32_t turbo_fp; + + cpu = all_cpu_data[0]; + + total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1; + no_turbo = cpu->pstate.max_pstate - cpu->pstate.min_pstate + 1; + turbo_fp = div_fp(int_tofp(no_turbo), int_tofp(total)); + turbo_pct = 100 - fp_toint(mul_fp(turbo_fp, int_tofp(100))); + return sprintf(buf, "%u\n", turbo_pct); +} + +static ssize_t show_num_pstates(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct cpudata *cpu; + int total; + + cpu = all_cpu_data[0]; + total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1; + return sprintf(buf, "%u\n", total); +} + static ssize_t show_no_turbo(struct kobject *kobj, struct attribute *attr, char *buf) { @@ -404,7 +435,9 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b, ret = sscanf(buf, "%u", &input); if (ret != 1) return -EINVAL; - limits.min_perf_pct = clamp_t(int, input, 0 , 100); + + limits.min_sysfs_pct = clamp_t(int, input, 0 , 100); + limits.min_perf_pct = max(limits.min_policy_pct, limits.min_sysfs_pct); limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100)); if (hwp_active) @@ -418,11 +451,15 @@ show_one(min_perf_pct, min_perf_pct); define_one_global_rw(no_turbo); define_one_global_rw(max_perf_pct); define_one_global_rw(min_perf_pct); +define_one_global_ro(turbo_pct); +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 }; @@ -825,6 +862,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = { ICPU(0x46, core_params), ICPU(0x47, core_params), ICPU(0x4c, byt_params), + ICPU(0x4e, core_params), ICPU(0x4f, core_params), ICPU(0x56, core_params), {} @@ -887,7 +925,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) if (!policy->cpuinfo.max_freq) return -ENODEV; - if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) { + if (policy->policy == CPUFREQ_POLICY_PERFORMANCE && + policy->max >= policy->cpuinfo.max_freq) { + limits.min_policy_pct = 100; limits.min_perf_pct = 100; limits.min_perf = int_tofp(1); limits.max_policy_pct = 100; @@ -897,8 +937,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) return 0; } - limits.min_perf_pct = (policy->min * 100) / policy->cpuinfo.max_freq; - limits.min_perf_pct = clamp_t(int, limits.min_perf_pct, 0 , 100); + 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.min_perf_pct = max(limits.min_policy_pct, limits.min_sysfs_pct); limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100)); limits.max_policy_pct = (policy->max * 100) / policy->cpuinfo.max_freq; @@ -978,6 +1019,7 @@ static struct cpufreq_driver intel_pstate_driver = { static int __initdata no_load; static int __initdata no_hwp; +static int __initdata hwp_only; static unsigned int force_load; static int intel_pstate_msrs_not_valid(void) @@ -1175,6 +1217,9 @@ static int __init intel_pstate_init(void) if (cpu_has(c,X86_FEATURE_HWP) && !no_hwp) intel_pstate_hwp_enable(); + if (!hwp_active && hwp_only) + goto out; + rc = cpufreq_register_driver(&intel_pstate_driver); if (rc) goto out; @@ -1209,6 +1254,8 @@ static int __init intel_pstate_setup(char *str) no_hwp = 1; if (!strcmp(str, "force")) force_load = 1; + if (!strcmp(str, "hwp_only")) + hwp_only = 1; return 0; } early_param("intel_pstate", intel_pstate_setup); diff --git a/drivers/cpufreq/ls1x-cpufreq.c b/drivers/cpufreq/ls1x-cpufreq.c index 25fbd6a1374..f0913eee2f5 100644 --- a/drivers/cpufreq/ls1x-cpufreq.c +++ b/drivers/cpufreq/ls1x-cpufreq.c @@ -210,7 +210,6 @@ out: static struct platform_driver ls1x_cpufreq_platdrv = { .driver = { .name = "ls1x-cpufreq", - .owner = THIS_MODULE, }, .probe = ls1x_cpufreq_probe, .remove = ls1x_cpufreq_remove, diff --git a/drivers/cpufreq/sfi-cpufreq.c b/drivers/cpufreq/sfi-cpufreq.c new file mode 100644 index 00000000000..ffa3389e535 --- /dev/null +++ b/drivers/cpufreq/sfi-cpufreq.c @@ -0,0 +1,136 @@ +/* + * SFI Performance States Driver + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * Author: Vishwesh M Rudramuni <vishwesh.m.rudramuni@intel.com> + * Author: Srinidhi Kasagar <srinidhi.kasagar@intel.com> + */ + +#include <linux/cpufreq.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/sfi.h> +#include <linux/slab.h> +#include <linux/smp.h> + +#include <asm/msr.h> + +struct cpufreq_frequency_table *freq_table; +static struct sfi_freq_table_entry *sfi_cpufreq_array; +static int num_freq_table_entries; + +static int sfi_parse_freq(struct sfi_table_header *table) +{ + struct sfi_table_simple *sb; + struct sfi_freq_table_entry *pentry; + int totallen; + + sb = (struct sfi_table_simple *)table; + num_freq_table_entries = SFI_GET_NUM_ENTRIES(sb, + struct sfi_freq_table_entry); + if (num_freq_table_entries <= 1) { + pr_err("No p-states discovered\n"); + return -ENODEV; + } + + pentry = (struct sfi_freq_table_entry *)sb->pentry; + totallen = num_freq_table_entries * sizeof(*pentry); + + sfi_cpufreq_array = kzalloc(totallen, GFP_KERNEL); + if (!sfi_cpufreq_array) + return -ENOMEM; + + memcpy(sfi_cpufreq_array, pentry, totallen); + + return 0; +} + +static int sfi_cpufreq_target(struct cpufreq_policy *policy, unsigned int index) +{ + unsigned int next_perf_state = 0; /* Index into perf table */ + u32 lo, hi; + + next_perf_state = policy->freq_table[index].driver_data; + + rdmsr_on_cpu(policy->cpu, MSR_IA32_PERF_CTL, &lo, &hi); + lo = (lo & ~INTEL_PERF_CTL_MASK) | + ((u32) sfi_cpufreq_array[next_perf_state].ctrl_val & + INTEL_PERF_CTL_MASK); + wrmsr_on_cpu(policy->cpu, MSR_IA32_PERF_CTL, lo, hi); + + return 0; +} + +static int sfi_cpufreq_cpu_init(struct cpufreq_policy *policy) +{ + policy->shared_type = CPUFREQ_SHARED_TYPE_HW; + policy->cpuinfo.transition_latency = 100000; /* 100us */ + + return cpufreq_table_validate_and_show(policy, freq_table); +} + +static struct cpufreq_driver sfi_cpufreq_driver = { + .flags = CPUFREQ_CONST_LOOPS, + .verify = cpufreq_generic_frequency_table_verify, + .target_index = sfi_cpufreq_target, + .init = sfi_cpufreq_cpu_init, + .name = "sfi-cpufreq", + .attr = cpufreq_generic_attr, +}; + +static int __init sfi_cpufreq_init(void) +{ + int ret, i; + + /* parse the freq table from SFI */ + ret = sfi_table_parse(SFI_SIG_FREQ, NULL, NULL, sfi_parse_freq); + if (ret) + return ret; + + freq_table = kzalloc(sizeof(*freq_table) * + (num_freq_table_entries + 1), GFP_KERNEL); + if (!freq_table) { + ret = -ENOMEM; + goto err_free_array; + } + + for (i = 0; i < num_freq_table_entries; i++) { + freq_table[i].driver_data = i; + freq_table[i].frequency = sfi_cpufreq_array[i].freq_mhz * 1000; + } + freq_table[i].frequency = CPUFREQ_TABLE_END; + + ret = cpufreq_register_driver(&sfi_cpufreq_driver); + if (ret) + goto err_free_tbl; + + return ret; + +err_free_tbl: + kfree(freq_table); +err_free_array: + kfree(sfi_cpufreq_array); + return ret; +} +late_initcall(sfi_cpufreq_init); + +static void __exit sfi_cpufreq_exit(void) +{ + cpufreq_unregister_driver(&sfi_cpufreq_driver); + kfree(freq_table); + kfree(sfi_cpufreq_array); +} +module_exit(sfi_cpufreq_exit); + +MODULE_AUTHOR("Vishwesh M Rudramuni <vishwesh.m.rudramuni@intel.com>"); +MODULE_DESCRIPTION("SFI Performance-States Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpuidle/cpuidle-big_little.c b/drivers/cpuidle/cpuidle-big_little.c index e3e225fe6b4..40c34faffe5 100644 --- a/drivers/cpuidle/cpuidle-big_little.c +++ b/drivers/cpuidle/cpuidle-big_little.c @@ -182,6 +182,10 @@ static int __init bl_idle_init(void) */ if (!of_match_node(compatible_machine_match, root)) return -ENODEV; + + if (!mcpm_is_available()) + return -EUNATCH; + /* * For now the differentiation between little and big cores * is based on the part number. A7 cores are considered little diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig index faf4e70c42e..64281bb2f65 100644 --- a/drivers/devfreq/Kconfig +++ b/drivers/devfreq/Kconfig @@ -1,5 +1,6 @@ menuconfig PM_DEVFREQ bool "Generic Dynamic Voltage and Frequency Scaling (DVFS) support" + select SRCU help A device may have a list of frequencies and voltages available. devfreq, a generic DVFS framework can be registered for a device @@ -87,4 +88,16 @@ config ARM_EXYNOS5_BUS_DEVFREQ It reads PPMU counters of memory controllers and adjusts the operating frequencies and voltages with OPP support. +config ARM_TEGRA_DEVFREQ + tristate "Tegra DEVFREQ Driver" + depends on ARCH_TEGRA_124_SOC + select DEVFREQ_GOV_SIMPLE_ONDEMAND + select PM_OPP + help + This adds the DEVFREQ driver for the Tegra family of SoCs. + It reads ACTMON counters of memory controllers and adjusts the + operating frequencies and voltages with OPP support. + +source "drivers/devfreq/event/Kconfig" + endif # PM_DEVFREQ diff --git a/drivers/devfreq/Makefile b/drivers/devfreq/Makefile index 16138c9e0d5..5134f9ee983 100644 --- a/drivers/devfreq/Makefile +++ b/drivers/devfreq/Makefile @@ -1,4 +1,5 @@ obj-$(CONFIG_PM_DEVFREQ) += devfreq.o +obj-$(CONFIG_PM_DEVFREQ_EVENT) += devfreq-event.o obj-$(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND) += governor_simpleondemand.o obj-$(CONFIG_DEVFREQ_GOV_PERFORMANCE) += governor_performance.o obj-$(CONFIG_DEVFREQ_GOV_POWERSAVE) += governor_powersave.o @@ -7,3 +8,7 @@ obj-$(CONFIG_DEVFREQ_GOV_USERSPACE) += governor_userspace.o # DEVFREQ Drivers obj-$(CONFIG_ARM_EXYNOS4_BUS_DEVFREQ) += exynos/ obj-$(CONFIG_ARM_EXYNOS5_BUS_DEVFREQ) += exynos/ +obj-$(CONFIG_ARM_TEGRA_DEVFREQ) += tegra-devfreq.o + +# DEVFREQ Event Drivers +obj-$(CONFIG_PM_DEVFREQ_EVENT) += event/ diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c new file mode 100644 index 00000000000..f304a0289ed --- /dev/null +++ b/drivers/devfreq/devfreq-event.c @@ -0,0 +1,494 @@ +/* + * devfreq-event: a framework to provide raw data and events of devfreq devices + * + * Copyright (C) 2015 Samsung Electronics + * Author: Chanwoo Choi <cw00.choi@samsung.com> + * + * 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. + * + * This driver is based on drivers/devfreq/devfreq.c. + */ + +#include <linux/devfreq-event.h> +#include <linux/kernel.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/list.h> +#include <linux/of.h> + +static struct class *devfreq_event_class; + +/* The list of all devfreq event list */ +static LIST_HEAD(devfreq_event_list); +static DEFINE_MUTEX(devfreq_event_list_lock); + +#define to_devfreq_event(DEV) container_of(DEV, struct devfreq_event_dev, dev) + +/** + * devfreq_event_enable_edev() - Enable the devfreq-event dev and increase + * the enable_count of devfreq-event dev. + * @edev : the devfreq-event device + * + * Note that this function increase the enable_count and enable the + * devfreq-event device. The devfreq-event device should be enabled before + * using it by devfreq device. + */ +int devfreq_event_enable_edev(struct devfreq_event_dev *edev) +{ + int ret = 0; + + if (!edev || !edev->desc) + return -EINVAL; + + mutex_lock(&edev->lock); + if (edev->desc->ops && edev->desc->ops->enable + && edev->enable_count == 0) { + ret = edev->desc->ops->enable(edev); + if (ret < 0) + goto err; + } + edev->enable_count++; +err: + mutex_unlock(&edev->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(devfreq_event_enable_edev); + +/** + * devfreq_event_disable_edev() - Disable the devfreq-event dev and decrease + * the enable_count of the devfreq-event dev. + * @edev : the devfreq-event device + * + * Note that this function decrease the enable_count and disable the + * devfreq-event device. After the devfreq-event device is disabled, + * devfreq device can't use the devfreq-event device for get/set/reset + * operations. + */ +int devfreq_event_disable_edev(struct devfreq_event_dev *edev) +{ + int ret = 0; + + if (!edev || !edev->desc) + return -EINVAL; + + mutex_lock(&edev->lock); + if (edev->enable_count <= 0) { + dev_warn(&edev->dev, "unbalanced enable_count\n"); + ret = -EIO; + goto err; + } + + if (edev->desc->ops && edev->desc->ops->disable + && edev->enable_count == 1) { + ret = edev->desc->ops->disable(edev); + if (ret < 0) + goto err; + } + edev->enable_count--; +err: + mutex_unlock(&edev->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(devfreq_event_disable_edev); + +/** + * devfreq_event_is_enabled() - Check whether devfreq-event dev is enabled or + * not. + * @edev : the devfreq-event device + * + * Note that this function check whether devfreq-event dev is enabled or not. + * If return true, the devfreq-event dev is enabeld. If return false, the + * devfreq-event dev is disabled. + */ +bool devfreq_event_is_enabled(struct devfreq_event_dev *edev) +{ + bool enabled = false; + + if (!edev || !edev->desc) + return enabled; + + mutex_lock(&edev->lock); + + if (edev->enable_count > 0) + enabled = true; + + mutex_unlock(&edev->lock); + + return enabled; +} +EXPORT_SYMBOL_GPL(devfreq_event_is_enabled); + +/** + * devfreq_event_set_event() - Set event to devfreq-event dev to start. + * @edev : the devfreq-event device + * + * Note that this function set the event to the devfreq-event device to start + * for getting the event data which could be various event type. + */ +int devfreq_event_set_event(struct devfreq_event_dev *edev) +{ + int ret; + + if (!edev || !edev->desc) + return -EINVAL; + + if (!edev->desc->ops || !edev->desc->ops->set_event) + return -EINVAL; + + if (!devfreq_event_is_enabled(edev)) + return -EPERM; + + mutex_lock(&edev->lock); + ret = edev->desc->ops->set_event(edev); + mutex_unlock(&edev->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(devfreq_event_set_event); + +/** + * devfreq_event_get_event() - Get {load|total}_count from devfreq-event dev. + * @edev : the devfreq-event device + * @edata : the calculated data of devfreq-event device + * + * Note that this function get the calculated event data from devfreq-event dev + * after stoping the progress of whole sequence of devfreq-event dev. + */ +int devfreq_event_get_event(struct devfreq_event_dev *edev, + struct devfreq_event_data *edata) +{ + int ret; + + if (!edev || !edev->desc) + return -EINVAL; + + if (!edev->desc->ops || !edev->desc->ops->get_event) + return -EINVAL; + + if (!devfreq_event_is_enabled(edev)) + return -EINVAL; + + edata->total_count = edata->load_count = 0; + + mutex_lock(&edev->lock); + ret = edev->desc->ops->get_event(edev, edata); + if (ret < 0) + edata->total_count = edata->load_count = 0; + mutex_unlock(&edev->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(devfreq_event_get_event); + +/** + * devfreq_event_reset_event() - Reset all opeations of devfreq-event dev. + * @edev : the devfreq-event device + * + * Note that this function stop all operations of devfreq-event dev and reset + * the current event data to make the devfreq-event device into initial state. + */ +int devfreq_event_reset_event(struct devfreq_event_dev *edev) +{ + int ret = 0; + + if (!edev || !edev->desc) + return -EINVAL; + + if (!devfreq_event_is_enabled(edev)) + return -EPERM; + + mutex_lock(&edev->lock); + if (edev->desc->ops && edev->desc->ops->reset) + ret = edev->desc->ops->reset(edev); + mutex_unlock(&edev->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(devfreq_event_reset_event); + +/** + * devfreq_event_get_edev_by_phandle() - Get the devfreq-event dev from + * devicetree. + * @dev : the pointer to the given device + * @index : the index into list of devfreq-event device + * + * Note that this function return the pointer of devfreq-event device. + */ +struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(struct device *dev, + int index) +{ + struct device_node *node; + struct devfreq_event_dev *edev; + + if (!dev->of_node) { + dev_err(dev, "device does not have a device node entry\n"); + return ERR_PTR(-EINVAL); + } + + node = of_parse_phandle(dev->of_node, "devfreq-events", index); + if (!node) { + dev_err(dev, "failed to get phandle in %s node\n", + dev->of_node->full_name); + return ERR_PTR(-ENODEV); + } + + mutex_lock(&devfreq_event_list_lock); + list_for_each_entry(edev, &devfreq_event_list, node) { + if (!strcmp(edev->desc->name, node->name)) + goto out; + } + edev = NULL; +out: + mutex_unlock(&devfreq_event_list_lock); + + if (!edev) { + dev_err(dev, "unable to get devfreq-event device : %s\n", + node->name); + of_node_put(node); + return ERR_PTR(-ENODEV); + } + + of_node_put(node); + + return edev; +} +EXPORT_SYMBOL_GPL(devfreq_event_get_edev_by_phandle); + +/** + * devfreq_event_get_edev_count() - Get the count of devfreq-event dev + * @dev : the pointer to the given device + * + * Note that this function return the count of devfreq-event devices. + */ +int devfreq_event_get_edev_count(struct device *dev) +{ + int count; + + if (!dev->of_node) { + dev_err(dev, "device does not have a device node entry\n"); + return -EINVAL; + } + + count = of_property_count_elems_of_size(dev->of_node, "devfreq-events", + sizeof(u32)); + if (count < 0 ) { + dev_err(dev, + "failed to get the count of devfreq-event in %s node\n", + dev->of_node->full_name); + return count; + } + + return count; +} +EXPORT_SYMBOL_GPL(devfreq_event_get_edev_count); + +static void devfreq_event_release_edev(struct device *dev) +{ + struct devfreq_event_dev *edev = to_devfreq_event(dev); + + kfree(edev); +} + +/** + * devfreq_event_add_edev() - Add new devfreq-event device. + * @dev : the device owning the devfreq-event device being created + * @desc : the devfreq-event device's decriptor which include essential + * data for devfreq-event device. + * + * Note that this function add new devfreq-event device to devfreq-event class + * list and register the device of the devfreq-event device. + */ +struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev, + struct devfreq_event_desc *desc) +{ + struct devfreq_event_dev *edev; + static atomic_t event_no = ATOMIC_INIT(0); + int ret; + + if (!dev || !desc) + return ERR_PTR(-EINVAL); + + if (!desc->name || !desc->ops) + return ERR_PTR(-EINVAL); + + if (!desc->ops->set_event || !desc->ops->get_event) + return ERR_PTR(-EINVAL); + + edev = kzalloc(sizeof(struct devfreq_event_dev), GFP_KERNEL); + if (!edev) + return ERR_PTR(-ENOMEM); + + mutex_init(&edev->lock); + edev->desc = desc; + edev->enable_count = 0; + edev->dev.parent = dev; + edev->dev.class = devfreq_event_class; + edev->dev.release = devfreq_event_release_edev; + + dev_set_name(&edev->dev, "event.%d", atomic_inc_return(&event_no) - 1); + ret = device_register(&edev->dev); + if (ret < 0) { + put_device(&edev->dev); + return ERR_PTR(ret); + } + dev_set_drvdata(&edev->dev, edev); + + INIT_LIST_HEAD(&edev->node); + + mutex_lock(&devfreq_event_list_lock); + list_add(&edev->node, &devfreq_event_list); + mutex_unlock(&devfreq_event_list_lock); + + return edev; +} +EXPORT_SYMBOL_GPL(devfreq_event_add_edev); + +/** + * devfreq_event_remove_edev() - Remove the devfreq-event device registered. + * @dev : the devfreq-event device + * + * Note that this function remove the registered devfreq-event device. + */ +int devfreq_event_remove_edev(struct devfreq_event_dev *edev) +{ + if (!edev) + return -EINVAL; + + WARN_ON(edev->enable_count); + + mutex_lock(&devfreq_event_list_lock); + list_del(&edev->node); + mutex_unlock(&devfreq_event_list_lock); + + device_unregister(&edev->dev); + + return 0; +} +EXPORT_SYMBOL_GPL(devfreq_event_remove_edev); + +static int devm_devfreq_event_match(struct device *dev, void *res, void *data) +{ + struct devfreq_event_dev **r = res; + + if (WARN_ON(!r || !*r)) + return 0; + + return *r == data; +} + +static void devm_devfreq_event_release(struct device *dev, void *res) +{ + devfreq_event_remove_edev(*(struct devfreq_event_dev **)res); +} + +/** + * devm_devfreq_event_add_edev() - Resource-managed devfreq_event_add_edev() + * @dev : the device owning the devfreq-event device being created + * @desc : the devfreq-event device's decriptor which include essential + * data for devfreq-event device. + * + * Note that this function manages automatically the memory of devfreq-event + * device using device resource management and simplify the free operation + * for memory of devfreq-event device. + */ +struct devfreq_event_dev *devm_devfreq_event_add_edev(struct device *dev, + struct devfreq_event_desc *desc) +{ + struct devfreq_event_dev **ptr, *edev; + + ptr = devres_alloc(devm_devfreq_event_release, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return ERR_PTR(-ENOMEM); + + edev = devfreq_event_add_edev(dev, desc); + if (IS_ERR(edev)) { + devres_free(ptr); + return ERR_PTR(-ENOMEM); + } + + *ptr = edev; + devres_add(dev, ptr); + + return edev; +} +EXPORT_SYMBOL_GPL(devm_devfreq_event_add_edev); + +/** + * devm_devfreq_event_remove_edev()- Resource-managed devfreq_event_remove_edev() + * @dev : the device owning the devfreq-event device being created + * @edev : the devfreq-event device + * + * Note that this function manages automatically the memory of devfreq-event + * device using device resource management. + */ +void devm_devfreq_event_remove_edev(struct device *dev, + struct devfreq_event_dev *edev) +{ + WARN_ON(devres_release(dev, devm_devfreq_event_release, + devm_devfreq_event_match, edev)); +} +EXPORT_SYMBOL_GPL(devm_devfreq_event_remove_edev); + +/* + * Device attributes for devfreq-event class. + */ +static ssize_t name_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct devfreq_event_dev *edev = to_devfreq_event(dev); + + if (!edev || !edev->desc) + return -EINVAL; + + return sprintf(buf, "%s\n", edev->desc->name); +} +static DEVICE_ATTR_RO(name); + +static ssize_t enable_count_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct devfreq_event_dev *edev = to_devfreq_event(dev); + + if (!edev || !edev->desc) + return -EINVAL; + + return sprintf(buf, "%d\n", edev->enable_count); +} +static DEVICE_ATTR_RO(enable_count); + +static struct attribute *devfreq_event_attrs[] = { + &dev_attr_name.attr, + &dev_attr_enable_count.attr, + NULL, +}; +ATTRIBUTE_GROUPS(devfreq_event); + +static int __init devfreq_event_init(void) +{ + devfreq_event_class = class_create(THIS_MODULE, "devfreq-event"); + if (IS_ERR(devfreq_event_class)) { + pr_err("%s: couldn't create class\n", __FILE__); + return PTR_ERR(devfreq_event_class); + } + + devfreq_event_class->dev_groups = devfreq_event_groups; + + return 0; +} +subsys_initcall(devfreq_event_init); + +static void __exit devfreq_event_exit(void) +{ + class_destroy(devfreq_event_class); +} +module_exit(devfreq_event_exit); + +MODULE_AUTHOR("Chanwoo Choi <cw00.choi@samsung.com>"); +MODULE_DESCRIPTION("DEVFREQ-Event class support"); +MODULE_LICENSE("GPL"); diff --git a/drivers/devfreq/event/Kconfig b/drivers/devfreq/event/Kconfig new file mode 100644 index 00000000000..a11720affc3 --- /dev/null +++ b/drivers/devfreq/event/Kconfig @@ -0,0 +1,25 @@ +menuconfig PM_DEVFREQ_EVENT + bool "DEVFREQ-Event device Support" + help + The devfreq-event device provide the raw data and events which + indicate the current state of devfreq-event device. The provided + data from devfreq-event device is used to monitor the state of + device and determine the suitable size of resource to reduce the + wasted resource. + + The devfreq-event device can support the various type of events + (e.g., raw data, utilization, latency, bandwidth). The events + may be used by devfreq governor and other subsystem. + +if PM_DEVFREQ_EVENT + +config DEVFREQ_EVENT_EXYNOS_PPMU + bool "EXYNOS PPMU (Platform Performance Monitoring Unit) DEVFREQ event Driver" + depends on ARCH_EXYNOS + select PM_OPP + help + This add the devfreq-event driver for Exynos SoC. It provides PPMU + (Platform Performance Monitoring Unit) counters to estimate the + utilization of each module. + +endif # PM_DEVFREQ_EVENT diff --git a/drivers/devfreq/event/Makefile b/drivers/devfreq/event/Makefile new file mode 100644 index 00000000000..be146ead79c --- /dev/null +++ b/drivers/devfreq/event/Makefile @@ -0,0 +1,2 @@ +# Exynos DEVFREQ Event Drivers +obj-$(CONFIG_DEVFREQ_EVENT_EXYNOS_PPMU) += exynos-ppmu.o diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c new file mode 100644 index 00000000000..135be0aada9 --- /dev/null +++ b/drivers/devfreq/event/exynos-ppmu.c @@ -0,0 +1,374 @@ +/* + * exynos_ppmu.c - EXYNOS PPMU (Platform Performance Monitoring Unit) support + * + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Author : Chanwoo Choi <cw00.choi@samsung.com> + * + * 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. + * + * This driver is based on drivers/devfreq/exynos/exynos_ppmu.c + */ + +#include <linux/clk.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/of_address.h> +#include <linux/platform_device.h> +#include <linux/suspend.h> +#include <linux/devfreq-event.h> + +#include "exynos-ppmu.h" + +struct exynos_ppmu_data { + void __iomem *base; + struct clk *clk; +}; + +struct exynos_ppmu { + struct devfreq_event_dev **edev; + struct devfreq_event_desc *desc; + unsigned int num_events; + + struct device *dev; + struct mutex lock; + + struct exynos_ppmu_data ppmu; +}; + +#define PPMU_EVENT(name) \ + { "ppmu-event0-"#name, PPMU_PMNCNT0 }, \ + { "ppmu-event1-"#name, PPMU_PMNCNT1 }, \ + { "ppmu-event2-"#name, PPMU_PMNCNT2 }, \ + { "ppmu-event3-"#name, PPMU_PMNCNT3 } + +struct __exynos_ppmu_events { + char *name; + int id; +} ppmu_events[] = { + /* For Exynos3250, Exynos4 and Exynos5260 */ + PPMU_EVENT(g3d), + PPMU_EVENT(fsys), + + /* For Exynos4 SoCs and Exynos3250 */ + PPMU_EVENT(dmc0), + PPMU_EVENT(dmc1), + PPMU_EVENT(cpu), + PPMU_EVENT(rightbus), + PPMU_EVENT(leftbus), + PPMU_EVENT(lcd0), + PPMU_EVENT(camif), + + /* Only for Exynos3250 and Exynos5260 */ + PPMU_EVENT(mfc), + + /* Only for Exynos4 SoCs */ + PPMU_EVENT(mfc-left), + PPMU_EVENT(mfc-right), + + /* Only for Exynos5260 SoCs */ + PPMU_EVENT(drex0-s0), + PPMU_EVENT(drex0-s1), + PPMU_EVENT(drex1-s0), + PPMU_EVENT(drex1-s1), + PPMU_EVENT(eagle), + PPMU_EVENT(kfc), + PPMU_EVENT(isp), + PPMU_EVENT(fimc), + PPMU_EVENT(gscl), + PPMU_EVENT(mscl), + PPMU_EVENT(fimd0x), + PPMU_EVENT(fimd1x), + { /* sentinel */ }, +}; + +static int exynos_ppmu_find_ppmu_id(struct devfreq_event_dev *edev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(ppmu_events); i++) + if (!strcmp(edev->desc->name, ppmu_events[i].name)) + return ppmu_events[i].id; + + return -EINVAL; +} + +static int exynos_ppmu_disable(struct devfreq_event_dev *edev) +{ + struct exynos_ppmu *info = devfreq_event_get_drvdata(edev); + u32 pmnc; + + /* Disable all counters */ + __raw_writel(PPMU_CCNT_MASK | + PPMU_PMCNT0_MASK | + PPMU_PMCNT1_MASK | + PPMU_PMCNT2_MASK | + PPMU_PMCNT3_MASK, + info->ppmu.base + PPMU_CNTENC); + + /* Disable PPMU */ + pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC); + pmnc &= ~PPMU_PMNC_ENABLE_MASK; + __raw_writel(pmnc, info->ppmu.base + PPMU_PMNC); + + return 0; +} + +static int exynos_ppmu_set_event(struct devfreq_event_dev *edev) +{ + struct exynos_ppmu *info = devfreq_event_get_drvdata(edev); + int id = exynos_ppmu_find_ppmu_id(edev); + u32 pmnc, cntens; + + if (id < 0) + return id; + + /* Enable specific counter */ + cntens = __raw_readl(info->ppmu.base + PPMU_CNTENS); + cntens |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id)); + __raw_writel(cntens, info->ppmu.base + PPMU_CNTENS); + + /* Set the event of Read/Write data count */ + __raw_writel(PPMU_RO_DATA_CNT | PPMU_WO_DATA_CNT, + info->ppmu.base + PPMU_BEVTxSEL(id)); + + /* Reset cycle counter/performance counter and enable PPMU */ + pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC); + pmnc &= ~(PPMU_PMNC_ENABLE_MASK + | PPMU_PMNC_COUNTER_RESET_MASK + | PPMU_PMNC_CC_RESET_MASK); + pmnc |= (PPMU_ENABLE << PPMU_PMNC_ENABLE_SHIFT); + pmnc |= (PPMU_ENABLE << PPMU_PMNC_COUNTER_RESET_SHIFT); + pmnc |= (PPMU_ENABLE << PPMU_PMNC_CC_RESET_SHIFT); + __raw_writel(pmnc, info->ppmu.base + PPMU_PMNC); + + return 0; +} + +static int exynos_ppmu_get_event(struct devfreq_event_dev *edev, + struct devfreq_event_data *edata) +{ + struct exynos_ppmu *info = devfreq_event_get_drvdata(edev); + int id = exynos_ppmu_find_ppmu_id(edev); + u32 pmnc, cntenc; + + if (id < 0) + return -EINVAL; + + /* Disable PPMU */ + pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC); + pmnc &= ~PPMU_PMNC_ENABLE_MASK; + __raw_writel(pmnc, info->ppmu.base + PPMU_PMNC); + + /* Read cycle count */ + edata->total_count = __raw_readl(info->ppmu.base + PPMU_CCNT); + + /* Read performance count */ + switch (id) { + case PPMU_PMNCNT0: + case PPMU_PMNCNT1: + case PPMU_PMNCNT2: + edata->load_count + = __raw_readl(info->ppmu.base + PPMU_PMNCT(id)); + break; + case PPMU_PMNCNT3: + edata->load_count = + ((__raw_readl(info->ppmu.base + PPMU_PMCNT3_HIGH) << 8) + | __raw_readl(info->ppmu.base + PPMU_PMCNT3_LOW)); + break; + default: + return -EINVAL; + } + + /* Disable specific counter */ + cntenc = __raw_readl(info->ppmu.base + PPMU_CNTENC); + cntenc |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id)); + __raw_writel(cntenc, info->ppmu.base + PPMU_CNTENC); + + dev_dbg(&edev->dev, "%s (event: %ld/%ld)\n", edev->desc->name, + edata->load_count, edata->total_count); + + return 0; +} + +static struct devfreq_event_ops exynos_ppmu_ops = { + .disable = exynos_ppmu_disable, + .set_event = exynos_ppmu_set_event, + .get_event = exynos_ppmu_get_event, +}; + +static int of_get_devfreq_events(struct device_node *np, + struct exynos_ppmu *info) +{ + struct devfreq_event_desc *desc; + struct device *dev = info->dev; + struct device_node *events_np, *node; + int i, j, count; + + events_np = of_get_child_by_name(np, "events"); + if (!events_np) { + dev_err(dev, + "failed to get child node of devfreq-event devices\n"); + return -EINVAL; + } + + count = of_get_child_count(events_np); + desc = devm_kzalloc(dev, sizeof(*desc) * count, GFP_KERNEL); + if (!desc) + return -ENOMEM; + info->num_events = count; + + j = 0; + for_each_child_of_node(events_np, node) { + for (i = 0; i < ARRAY_SIZE(ppmu_events); i++) { + if (!ppmu_events[i].name) + continue; + + if (!of_node_cmp(node->name, ppmu_events[i].name)) + break; + } + + if (i == ARRAY_SIZE(ppmu_events)) { + dev_warn(dev, + "don't know how to configure events : %s\n", + node->name); + continue; + } + + desc[j].ops = &exynos_ppmu_ops; + desc[j].driver_data = info; + + of_property_read_string(node, "event-name", &desc[j].name); + + j++; + + of_node_put(node); + } + info->desc = desc; + + of_node_put(events_np); + + return 0; +} + +static int exynos_ppmu_parse_dt(struct exynos_ppmu *info) +{ + struct device *dev = info->dev; + struct device_node *np = dev->of_node; + int ret = 0; + + if (!np) { + dev_err(dev, "failed to find devicetree node\n"); + return -EINVAL; + } + + /* Maps the memory mapped IO to control PPMU register */ + info->ppmu.base = of_iomap(np, 0); + if (IS_ERR_OR_NULL(info->ppmu.base)) { + dev_err(dev, "failed to map memory region\n"); + return -ENOMEM; + } + + info->ppmu.clk = devm_clk_get(dev, "ppmu"); + if (IS_ERR(info->ppmu.clk)) { + info->ppmu.clk = NULL; + dev_warn(dev, "cannot get PPMU clock\n"); + } + + ret = of_get_devfreq_events(np, info); + if (ret < 0) { + dev_err(dev, "failed to parse exynos ppmu dt node\n"); + goto err; + } + + return 0; + +err: + iounmap(info->ppmu.base); + + return ret; +} + +static int exynos_ppmu_probe(struct platform_device *pdev) +{ + struct exynos_ppmu *info; + struct devfreq_event_dev **edev; + struct devfreq_event_desc *desc; + int i, ret = 0, size; + + info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL); + if (!info) + return -ENOMEM; + + mutex_init(&info->lock); + info->dev = &pdev->dev; + + /* Parse dt data to get resource */ + ret = exynos_ppmu_parse_dt(info); + if (ret < 0) { + dev_err(&pdev->dev, + "failed to parse devicetree for resource\n"); + return ret; + } + desc = info->desc; + + size = sizeof(struct devfreq_event_dev *) * info->num_events; + info->edev = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + if (!info->edev) { + dev_err(&pdev->dev, + "failed to allocate memory devfreq-event devices\n"); + return -ENOMEM; + } + edev = info->edev; + platform_set_drvdata(pdev, info); + + for (i = 0; i < info->num_events; i++) { + edev[i] = devm_devfreq_event_add_edev(&pdev->dev, &desc[i]); + if (IS_ERR(edev)) { + ret = PTR_ERR(edev); + dev_err(&pdev->dev, + "failed to add devfreq-event device\n"); + goto err; + } + } + + clk_prepare_enable(info->ppmu.clk); + + return 0; +err: + iounmap(info->ppmu.base); + + return ret; +} + +static int exynos_ppmu_remove(struct platform_device *pdev) +{ + struct exynos_ppmu *info = platform_get_drvdata(pdev); + + clk_disable_unprepare(info->ppmu.clk); + iounmap(info->ppmu.base); + + return 0; +} + +static struct of_device_id exynos_ppmu_id_match[] = { + { .compatible = "samsung,exynos-ppmu", }, + { /* sentinel */ }, +}; + +static struct platform_driver exynos_ppmu_driver = { + .probe = exynos_ppmu_probe, + .remove = exynos_ppmu_remove, + .driver = { + .name = "exynos-ppmu", + .of_match_table = exynos_ppmu_id_match, + }, +}; +module_platform_driver(exynos_ppmu_driver); + +MODULE_DESCRIPTION("Exynos PPMU(Platform Performance Monitoring Unit) driver"); +MODULE_AUTHOR("Chanwoo Choi <cw00.choi@samsung.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/devfreq/event/exynos-ppmu.h b/drivers/devfreq/event/exynos-ppmu.h new file mode 100644 index 00000000000..4e831d48c13 --- /dev/null +++ b/drivers/devfreq/event/exynos-ppmu.h @@ -0,0 +1,93 @@ +/* + * exynos_ppmu.h - EXYNOS PPMU header file + * + * Copyright (c) 2015 Samsung Electronics Co., Ltd. + * Author : Chanwoo Choi <cw00.choi@samsung.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __EXYNOS_PPMU_H__ +#define __EXYNOS_PPMU_H__ + +enum ppmu_state { + PPMU_DISABLE = 0, + PPMU_ENABLE, +}; + +enum ppmu_counter { + PPMU_PMNCNT0 = 0, + PPMU_PMNCNT1, + PPMU_PMNCNT2, + PPMU_PMNCNT3, + + PPMU_PMNCNT_MAX, +}; + +enum ppmu_event_type { + PPMU_RO_BUSY_CYCLE_CNT = 0x0, + PPMU_WO_BUSY_CYCLE_CNT = 0x1, + PPMU_RW_BUSY_CYCLE_CNT = 0x2, + PPMU_RO_REQUEST_CNT = 0x3, + PPMU_WO_REQUEST_CNT = 0x4, + PPMU_RO_DATA_CNT = 0x5, + PPMU_WO_DATA_CNT = 0x6, + PPMU_RO_LATENCY = 0x12, + PPMU_WO_LATENCY = 0x16, +}; + +enum ppmu_reg { + /* PPC control register */ + PPMU_PMNC = 0x00, + PPMU_CNTENS = 0x10, + PPMU_CNTENC = 0x20, + PPMU_INTENS = 0x30, + PPMU_INTENC = 0x40, + PPMU_FLAG = 0x50, + + /* Cycle Counter and Performance Event Counter Register */ + PPMU_CCNT = 0x100, + PPMU_PMCNT0 = 0x110, + PPMU_PMCNT1 = 0x120, + PPMU_PMCNT2 = 0x130, + PPMU_PMCNT3_HIGH = 0x140, + PPMU_PMCNT3_LOW = 0x150, + + /* Bus Event Generator */ + PPMU_BEVT0SEL = 0x1000, + PPMU_BEVT1SEL = 0x1100, + PPMU_BEVT2SEL = 0x1200, + PPMU_BEVT3SEL = 0x1300, + PPMU_COUNTER_RESET = 0x1810, + PPMU_READ_OVERFLOW_CNT = 0x1810, + PPMU_READ_UNDERFLOW_CNT = 0x1814, + PPMU_WRITE_OVERFLOW_CNT = 0x1850, + PPMU_WRITE_UNDERFLOW_CNT = 0x1854, + PPMU_READ_PENDING_CNT = 0x1880, + PPMU_WRITE_PENDING_CNT = 0x1884 +}; + +/* PMNC register */ +#define PPMU_PMNC_CC_RESET_SHIFT 2 +#define PPMU_PMNC_COUNTER_RESET_SHIFT 1 +#define PPMU_PMNC_ENABLE_SHIFT 0 +#define PPMU_PMNC_START_MODE_MASK BIT(16) +#define PPMU_PMNC_CC_DIVIDER_MASK BIT(3) +#define PPMU_PMNC_CC_RESET_MASK BIT(2) +#define PPMU_PMNC_COUNTER_RESET_MASK BIT(1) +#define PPMU_PMNC_ENABLE_MASK BIT(0) + +/* CNTENS/CNTENC/INTENS/INTENC/FLAG register */ +#define PPMU_CCNT_MASK BIT(31) +#define PPMU_PMCNT3_MASK BIT(3) +#define PPMU_PMCNT2_MASK BIT(2) +#define PPMU_PMCNT1_MASK BIT(1) +#define PPMU_PMCNT0_MASK BIT(0) + +/* PPMU_PMNCTx/PPMU_BETxSEL registers */ +#define PPMU_PMNCT(x) (PPMU_PMCNT0 + (0x10 * x)) +#define PPMU_BEVTxSEL(x) (PPMU_BEVT0SEL + (0x100 * x)) + +#endif /* __EXYNOS_PPMU_H__ */ diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c new file mode 100644 index 00000000000..34790961af5 --- /dev/null +++ b/drivers/devfreq/tegra-devfreq.c @@ -0,0 +1,718 @@ +/* + * A devfreq driver for NVIDIA Tegra SoCs + * + * Copyright (c) 2014 NVIDIA CORPORATION. All rights reserved. + * Copyright (C) 2014 Google, Inc + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + * + */ + +#include <linux/clk.h> +#include <linux/cpufreq.h> +#include <linux/devfreq.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/pm_opp.h> +#include <linux/reset.h> + +#include "governor.h" + +#define ACTMON_GLB_STATUS 0x0 +#define ACTMON_GLB_PERIOD_CTRL 0x4 + +#define ACTMON_DEV_CTRL 0x0 +#define ACTMON_DEV_CTRL_K_VAL_SHIFT 10 +#define ACTMON_DEV_CTRL_ENB_PERIODIC BIT(18) +#define ACTMON_DEV_CTRL_AVG_BELOW_WMARK_EN BIT(20) +#define ACTMON_DEV_CTRL_AVG_ABOVE_WMARK_EN BIT(21) +#define ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_NUM_SHIFT 23 +#define ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_NUM_SHIFT 26 +#define ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN BIT(29) +#define ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN BIT(30) +#define ACTMON_DEV_CTRL_ENB BIT(31) + +#define ACTMON_DEV_UPPER_WMARK 0x4 +#define ACTMON_DEV_LOWER_WMARK 0x8 +#define ACTMON_DEV_INIT_AVG 0xc +#define ACTMON_DEV_AVG_UPPER_WMARK 0x10 +#define ACTMON_DEV_AVG_LOWER_WMARK 0x14 +#define ACTMON_DEV_COUNT_WEIGHT 0x18 +#define ACTMON_DEV_AVG_COUNT 0x20 +#define ACTMON_DEV_INTR_STATUS 0x24 + +#define ACTMON_INTR_STATUS_CLEAR 0xffffffff + +#define ACTMON_DEV_INTR_CONSECUTIVE_UPPER BIT(31) +#define ACTMON_DEV_INTR_CONSECUTIVE_LOWER BIT(30) + +#define ACTMON_ABOVE_WMARK_WINDOW 1 +#define ACTMON_BELOW_WMARK_WINDOW 3 +#define ACTMON_BOOST_FREQ_STEP 16000 + +/* activity counter is incremented every 256 memory transactions, and each + * transaction takes 4 EMC clocks for Tegra124; So the COUNT_WEIGHT is + * 4 * 256 = 1024. + */ +#define ACTMON_COUNT_WEIGHT 0x400 + +/* + * ACTMON_AVERAGE_WINDOW_LOG2: default value for @DEV_CTRL_K_VAL, which + * translates to 2 ^ (K_VAL + 1). ex: 2 ^ (6 + 1) = 128 + */ +#define ACTMON_AVERAGE_WINDOW_LOG2 6 +#define ACTMON_SAMPLING_PERIOD 12 /* ms */ +#define ACTMON_DEFAULT_AVG_BAND 6 /* 1/10 of % */ + +#define KHZ 1000 + +/* Assume that the bus is saturated if the utilization is 25% */ +#define BUS_SATURATION_RATIO 25 + +/** + * struct tegra_devfreq_device_config - configuration specific to an ACTMON + * device + * + * Coefficients and thresholds are in % + */ +struct tegra_devfreq_device_config { + u32 offset; + u32 irq_mask; + + unsigned int boost_up_coeff; + unsigned int boost_down_coeff; + unsigned int boost_up_threshold; + unsigned int boost_down_threshold; + u32 avg_dependency_threshold; +}; + +enum tegra_actmon_device { + MCALL = 0, + MCCPU, +}; + +static struct tegra_devfreq_device_config actmon_device_configs[] = { + { + /* MCALL */ + .offset = 0x1c0, + .irq_mask = 1 << 26, + .boost_up_coeff = 200, + .boost_down_coeff = 50, + .boost_up_threshold = 60, + .boost_down_threshold = 40, + }, + { + /* MCCPU */ + .offset = 0x200, + .irq_mask = 1 << 25, + .boost_up_coeff = 800, + .boost_down_coeff = 90, + .boost_up_threshold = 27, + .boost_down_threshold = 10, + .avg_dependency_threshold = 50000, + }, +}; + +/** + * struct tegra_devfreq_device - state specific to an ACTMON device + * + * Frequencies are in kHz. + */ +struct tegra_devfreq_device { + const struct tegra_devfreq_device_config *config; + + void __iomem *regs; + u32 avg_band_freq; + u32 avg_count; + + unsigned long target_freq; + unsigned long boost_freq; +}; + +struct tegra_devfreq { + struct devfreq *devfreq; + + struct platform_device *pdev; + struct reset_control *reset; + struct clk *clock; + void __iomem *regs; + + spinlock_t lock; + + struct clk *emc_clock; + unsigned long max_freq; + unsigned long cur_freq; + struct notifier_block rate_change_nb; + + struct tegra_devfreq_device devices[ARRAY_SIZE(actmon_device_configs)]; +}; + +struct tegra_actmon_emc_ratio { + unsigned long cpu_freq; + unsigned long emc_freq; +}; + +static struct tegra_actmon_emc_ratio actmon_emc_ratios[] = { + { 1400000, ULONG_MAX }, + { 1200000, 750000 }, + { 1100000, 600000 }, + { 1000000, 500000 }, + { 800000, 375000 }, + { 500000, 200000 }, + { 250000, 100000 }, +}; + +static unsigned long do_percent(unsigned long val, unsigned int pct) +{ + return val * pct / 100; +} + +static void tegra_devfreq_update_avg_wmark(struct tegra_devfreq_device *dev) +{ + u32 avg = dev->avg_count; + u32 band = dev->avg_band_freq * ACTMON_SAMPLING_PERIOD; + + writel(avg + band, dev->regs + ACTMON_DEV_AVG_UPPER_WMARK); + avg = max(avg, band); + writel(avg - band, dev->regs + ACTMON_DEV_AVG_LOWER_WMARK); +} + +static void tegra_devfreq_update_wmark(struct tegra_devfreq *tegra, + struct tegra_devfreq_device *dev) +{ + u32 val = tegra->cur_freq * ACTMON_SAMPLING_PERIOD; + + writel(do_percent(val, dev->config->boost_up_threshold), + dev->regs + ACTMON_DEV_UPPER_WMARK); + + writel(do_percent(val, dev->config->boost_down_threshold), + dev->regs + ACTMON_DEV_LOWER_WMARK); +} + +static void actmon_write_barrier(struct tegra_devfreq *tegra) +{ + /* ensure the update has reached the ACTMON */ + wmb(); + readl(tegra->regs + ACTMON_GLB_STATUS); +} + +static irqreturn_t actmon_isr(int irq, void *data) +{ + struct tegra_devfreq *tegra = data; + struct tegra_devfreq_device *dev = NULL; + unsigned long flags; + u32 val; + unsigned int i; + + val = readl(tegra->regs + ACTMON_GLB_STATUS); + + for (i = 0; i < ARRAY_SIZE(tegra->devices); i++) { + if (val & tegra->devices[i].config->irq_mask) { + dev = tegra->devices + i; + break; + } + } + + if (!dev) + return IRQ_NONE; + + spin_lock_irqsave(&tegra->lock, flags); + + dev->avg_count = readl(dev->regs + ACTMON_DEV_AVG_COUNT); + tegra_devfreq_update_avg_wmark(dev); + + val = readl(dev->regs + ACTMON_DEV_INTR_STATUS); + if (val & ACTMON_DEV_INTR_CONSECUTIVE_UPPER) { + val = readl(dev->regs + ACTMON_DEV_CTRL) | + ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN | + ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN; + + /* + * new_boost = min(old_boost * up_coef + step, max_freq) + */ + dev->boost_freq = do_percent(dev->boost_freq, + dev->config->boost_up_coeff); + dev->boost_freq += ACTMON_BOOST_FREQ_STEP; + if (dev->boost_freq >= tegra->max_freq) { + dev->boost_freq = tegra->max_freq; + val &= ~ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN; + } + writel(val, dev->regs + ACTMON_DEV_CTRL); + } else if (val & ACTMON_DEV_INTR_CONSECUTIVE_LOWER) { + val = readl(dev->regs + ACTMON_DEV_CTRL) | + ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN | + ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN; + + /* + * new_boost = old_boost * down_coef + * or 0 if (old_boost * down_coef < step / 2) + */ + dev->boost_freq = do_percent(dev->boost_freq, + dev->config->boost_down_coeff); + if (dev->boost_freq < (ACTMON_BOOST_FREQ_STEP >> 1)) { + dev->boost_freq = 0; + val &= ~ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN; + } + writel(val, dev->regs + ACTMON_DEV_CTRL); + } + + if (dev->config->avg_dependency_threshold) { + val = readl(dev->regs + ACTMON_DEV_CTRL); + if (dev->avg_count >= dev->config->avg_dependency_threshold) + val |= ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN; + else if (dev->boost_freq == 0) + val &= ~ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN; + writel(val, dev->regs + ACTMON_DEV_CTRL); + } + + writel(ACTMON_INTR_STATUS_CLEAR, dev->regs + ACTMON_DEV_INTR_STATUS); + + actmon_write_barrier(tegra); + + spin_unlock_irqrestore(&tegra->lock, flags); + + return IRQ_WAKE_THREAD; +} + +static unsigned long actmon_cpu_to_emc_rate(struct tegra_devfreq *tegra, + unsigned long cpu_freq) +{ + unsigned int i; + struct tegra_actmon_emc_ratio *ratio = actmon_emc_ratios; + + for (i = 0; i < ARRAY_SIZE(actmon_emc_ratios); i++, ratio++) { + if (cpu_freq >= ratio->cpu_freq) { + if (ratio->emc_freq >= tegra->max_freq) + return tegra->max_freq; + else + return ratio->emc_freq; + } + } + + return 0; +} + +static void actmon_update_target(struct tegra_devfreq *tegra, + struct tegra_devfreq_device *dev) +{ + unsigned long cpu_freq = 0; + unsigned long static_cpu_emc_freq = 0; + unsigned int avg_sustain_coef; + unsigned long flags; + + if (dev->config->avg_dependency_threshold) { + cpu_freq = cpufreq_get(0); + static_cpu_emc_freq = actmon_cpu_to_emc_rate(tegra, cpu_freq); + } + + spin_lock_irqsave(&tegra->lock, flags); + + dev->target_freq = dev->avg_count / ACTMON_SAMPLING_PERIOD; + avg_sustain_coef = 100 * 100 / dev->config->boost_up_threshold; + dev->target_freq = do_percent(dev->target_freq, avg_sustain_coef); + dev->target_freq += dev->boost_freq; + + if (dev->avg_count >= dev->config->avg_dependency_threshold) + dev->target_freq = max(dev->target_freq, static_cpu_emc_freq); + + spin_unlock_irqrestore(&tegra->lock, flags); +} + +static irqreturn_t actmon_thread_isr(int irq, void *data) +{ + struct tegra_devfreq *tegra = data; + + mutex_lock(&tegra->devfreq->lock); + update_devfreq(tegra->devfreq); + mutex_unlock(&tegra->devfreq->lock); + + return IRQ_HANDLED; +} + +static int tegra_actmon_rate_notify_cb(struct notifier_block *nb, + unsigned long action, void *ptr) +{ + struct clk_notifier_data *data = ptr; + struct tegra_devfreq *tegra = container_of(nb, struct tegra_devfreq, + rate_change_nb); + unsigned int i; + unsigned long flags; + + spin_lock_irqsave(&tegra->lock, flags); + + switch (action) { + case POST_RATE_CHANGE: + tegra->cur_freq = data->new_rate / KHZ; + + for (i = 0; i < ARRAY_SIZE(tegra->devices); i++) + tegra_devfreq_update_wmark(tegra, tegra->devices + i); + + actmon_write_barrier(tegra); + break; + case PRE_RATE_CHANGE: + /* fall through */ + case ABORT_RATE_CHANGE: + break; + }; + + spin_unlock_irqrestore(&tegra->lock, flags); + + return NOTIFY_OK; +} + +static void tegra_actmon_configure_device(struct tegra_devfreq *tegra, + struct tegra_devfreq_device *dev) +{ + u32 val; + + dev->avg_band_freq = tegra->max_freq * ACTMON_DEFAULT_AVG_BAND / KHZ; + dev->target_freq = tegra->cur_freq; + + dev->avg_count = tegra->cur_freq * ACTMON_SAMPLING_PERIOD; + writel(dev->avg_count, dev->regs + ACTMON_DEV_INIT_AVG); + + tegra_devfreq_update_avg_wmark(dev); + tegra_devfreq_update_wmark(tegra, dev); + + writel(ACTMON_COUNT_WEIGHT, dev->regs + ACTMON_DEV_COUNT_WEIGHT); + writel(ACTMON_INTR_STATUS_CLEAR, dev->regs + ACTMON_DEV_INTR_STATUS); + + val = 0; + val |= ACTMON_DEV_CTRL_ENB_PERIODIC | + ACTMON_DEV_CTRL_AVG_ABOVE_WMARK_EN | + ACTMON_DEV_CTRL_AVG_BELOW_WMARK_EN; + val |= (ACTMON_AVERAGE_WINDOW_LOG2 - 1) + << ACTMON_DEV_CTRL_K_VAL_SHIFT; + val |= (ACTMON_BELOW_WMARK_WINDOW - 1) + << ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_NUM_SHIFT; + val |= (ACTMON_ABOVE_WMARK_WINDOW - 1) + << ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_NUM_SHIFT; + val |= ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN | + ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN; + + writel(val, dev->regs + ACTMON_DEV_CTRL); + + actmon_write_barrier(tegra); + + val = readl(dev->regs + ACTMON_DEV_CTRL); + val |= ACTMON_DEV_CTRL_ENB; + writel(val, dev->regs + ACTMON_DEV_CTRL); + + actmon_write_barrier(tegra); +} + +static int tegra_devfreq_suspend(struct device *dev) +{ + struct platform_device *pdev; + struct tegra_devfreq *tegra; + struct tegra_devfreq_device *actmon_dev; + unsigned int i; + u32 val; + + pdev = container_of(dev, struct platform_device, dev); + tegra = platform_get_drvdata(pdev); + + for (i = 0; i < ARRAY_SIZE(tegra->devices); i++) { + actmon_dev = &tegra->devices[i]; + + val = readl(actmon_dev->regs + ACTMON_DEV_CTRL); + val &= ~ACTMON_DEV_CTRL_ENB; + writel(val, actmon_dev->regs + ACTMON_DEV_CTRL); + + writel(ACTMON_INTR_STATUS_CLEAR, + actmon_dev->regs + ACTMON_DEV_INTR_STATUS); + + actmon_write_barrier(tegra); + } + + return 0; +} + +static int tegra_devfreq_resume(struct device *dev) +{ + struct platform_device *pdev; + struct tegra_devfreq *tegra; + struct tegra_devfreq_device *actmon_dev; + unsigned int i; + + pdev = container_of(dev, struct platform_device, dev); + tegra = platform_get_drvdata(pdev); + + for (i = 0; i < ARRAY_SIZE(tegra->devices); i++) { + actmon_dev = &tegra->devices[i]; + + tegra_actmon_configure_device(tegra, actmon_dev); + } + + return 0; +} + +static int tegra_devfreq_target(struct device *dev, unsigned long *freq, + u32 flags) +{ + struct platform_device *pdev; + struct tegra_devfreq *tegra; + struct dev_pm_opp *opp; + unsigned long rate = *freq * KHZ; + + pdev = container_of(dev, struct platform_device, dev); + tegra = platform_get_drvdata(pdev); + + rcu_read_lock(); + opp = devfreq_recommended_opp(dev, &rate, flags); + if (IS_ERR(opp)) { + rcu_read_unlock(); + dev_err(dev, "Failed to find opp for %lu KHz\n", *freq); + return PTR_ERR(opp); + } + rate = dev_pm_opp_get_freq(opp); + rcu_read_unlock(); + + /* TODO: Once we have per-user clk constraints, set a floor */ + clk_set_rate(tegra->emc_clock, rate); + + /* TODO: Set voltage as well */ + + return 0; +} + +static int tegra_devfreq_get_dev_status(struct device *dev, + struct devfreq_dev_status *stat) +{ + struct platform_device *pdev; + struct tegra_devfreq *tegra; + struct tegra_devfreq_device *actmon_dev; + + pdev = container_of(dev, struct platform_device, dev); + tegra = platform_get_drvdata(pdev); + + stat->current_frequency = tegra->cur_freq; + + /* To be used by the tegra governor */ + stat->private_data = tegra; + + /* The below are to be used by the other governors */ + + actmon_dev = &tegra->devices[MCALL]; + + /* Number of cycles spent on memory access */ + stat->busy_time = actmon_dev->avg_count; + + /* The bus can be considered to be saturated way before 100% */ + stat->busy_time *= 100 / BUS_SATURATION_RATIO; + + /* Number of cycles in a sampling period */ + stat->total_time = ACTMON_SAMPLING_PERIOD * tegra->cur_freq; + + return 0; +} + +static int tegra_devfreq_get_target(struct devfreq *devfreq, + unsigned long *freq) +{ + struct devfreq_dev_status stat; + struct tegra_devfreq *tegra; + struct tegra_devfreq_device *dev; + unsigned long target_freq = 0; + unsigned int i; + int err; + + err = devfreq->profile->get_dev_status(devfreq->dev.parent, &stat); + if (err) + return err; + + tegra = stat.private_data; + + for (i = 0; i < ARRAY_SIZE(tegra->devices); i++) { + dev = &tegra->devices[i]; + + actmon_update_target(tegra, dev); + + target_freq = max(target_freq, dev->target_freq); + } + + *freq = target_freq; + + return 0; +} + +static int tegra_devfreq_event_handler(struct devfreq *devfreq, + unsigned int event, void *data) +{ + return 0; +} + +static struct devfreq_governor tegra_devfreq_governor = { + .name = "tegra", + .get_target_freq = tegra_devfreq_get_target, + .event_handler = tegra_devfreq_event_handler, +}; + +static struct devfreq_dev_profile tegra_devfreq_profile = { + .polling_ms = 0, + .target = tegra_devfreq_target, + .get_dev_status = tegra_devfreq_get_dev_status, +}; + +static int tegra_devfreq_probe(struct platform_device *pdev) +{ + struct tegra_devfreq *tegra; + struct tegra_devfreq_device *dev; + struct resource *res; + unsigned long max_freq; + unsigned int i; + int irq; + int err; + + tegra = devm_kzalloc(&pdev->dev, sizeof(*tegra), GFP_KERNEL); + if (!tegra) + return -ENOMEM; + + spin_lock_init(&tegra->lock); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(&pdev->dev, "Failed to get regs resource\n"); + return -ENODEV; + } + + tegra->regs = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(tegra->regs)) { + dev_err(&pdev->dev, "Failed to get IO memory\n"); + return PTR_ERR(tegra->regs); + } + + tegra->reset = devm_reset_control_get(&pdev->dev, "actmon"); + if (IS_ERR(tegra->reset)) { + dev_err(&pdev->dev, "Failed to get reset\n"); + return PTR_ERR(tegra->reset); + } + + tegra->clock = devm_clk_get(&pdev->dev, "actmon"); + if (IS_ERR(tegra->clock)) { + dev_err(&pdev->dev, "Failed to get actmon clock\n"); + return PTR_ERR(tegra->clock); + } + + tegra->emc_clock = devm_clk_get(&pdev->dev, "emc"); + if (IS_ERR(tegra->emc_clock)) { + dev_err(&pdev->dev, "Failed to get emc clock\n"); + return PTR_ERR(tegra->emc_clock); + } + + err = of_init_opp_table(&pdev->dev); + if (err) { + dev_err(&pdev->dev, "Failed to init operating point table\n"); + return err; + } + + tegra->rate_change_nb.notifier_call = tegra_actmon_rate_notify_cb; + err = clk_notifier_register(tegra->emc_clock, &tegra->rate_change_nb); + if (err) { + dev_err(&pdev->dev, + "Failed to register rate change notifier\n"); + return err; + } + + reset_control_assert(tegra->reset); + + err = clk_prepare_enable(tegra->clock); + if (err) { + reset_control_deassert(tegra->reset); + return err; + } + + reset_control_deassert(tegra->reset); + + max_freq = clk_round_rate(tegra->emc_clock, ULONG_MAX); + tegra->max_freq = max_freq / KHZ; + + clk_set_rate(tegra->emc_clock, max_freq); + + tegra->cur_freq = clk_get_rate(tegra->emc_clock) / KHZ; + + writel(ACTMON_SAMPLING_PERIOD - 1, + tegra->regs + ACTMON_GLB_PERIOD_CTRL); + + for (i = 0; i < ARRAY_SIZE(actmon_device_configs); i++) { + dev = tegra->devices + i; + dev->config = actmon_device_configs + i; + dev->regs = tegra->regs + dev->config->offset; + + tegra_actmon_configure_device(tegra, tegra->devices + i); + } + + err = devfreq_add_governor(&tegra_devfreq_governor); + if (err) { + dev_err(&pdev->dev, "Failed to add governor\n"); + return err; + } + + tegra_devfreq_profile.initial_freq = clk_get_rate(tegra->emc_clock); + tegra->devfreq = devm_devfreq_add_device(&pdev->dev, + &tegra_devfreq_profile, + "tegra", + NULL); + + irq = platform_get_irq(pdev, 0); + err = devm_request_threaded_irq(&pdev->dev, irq, actmon_isr, + actmon_thread_isr, IRQF_SHARED, + "tegra-devfreq", tegra); + if (err) { + dev_err(&pdev->dev, "Interrupt request failed\n"); + return err; + } + + platform_set_drvdata(pdev, tegra); + + return 0; +} + +static int tegra_devfreq_remove(struct platform_device *pdev) +{ + struct tegra_devfreq *tegra = platform_get_drvdata(pdev); + + clk_notifier_unregister(tegra->emc_clock, &tegra->rate_change_nb); + + clk_disable_unprepare(tegra->clock); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(tegra_devfreq_pm_ops, + tegra_devfreq_suspend, + tegra_devfreq_resume); + +static struct of_device_id tegra_devfreq_of_match[] = { + { .compatible = "nvidia,tegra124-actmon" }, + { }, +}; + +static struct platform_driver tegra_devfreq_driver = { + .probe = tegra_devfreq_probe, + .remove = tegra_devfreq_remove, + .driver = { + .name = "tegra-devfreq", + .owner = THIS_MODULE, + .of_match_table = tegra_devfreq_of_match, + .pm = &tegra_devfreq_pm_ops, + }, +}; +module_platform_driver(tegra_devfreq_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Tegra devfreq driver"); +MODULE_AUTHOR("Tomeu Vizoso <tomeu.vizoso@collabora.com>"); +MODULE_DEVICE_TABLE(of, tegra_devfreq_of_match); diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c index de361a156b3..5a635646e05 100644 --- a/drivers/dma/acpi-dma.c +++ b/drivers/dma/acpi-dma.c @@ -43,7 +43,7 @@ static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp, { const struct acpi_csrt_shared_info *si; struct list_head resource_list; - struct resource_list_entry *rentry; + struct resource_entry *rentry; resource_size_t mem = 0, irq = 0; int ret; @@ -56,10 +56,10 @@ static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp, return 0; list_for_each_entry(rentry, &resource_list, node) { - if (resource_type(&rentry->res) == IORESOURCE_MEM) - mem = rentry->res.start; - else if (resource_type(&rentry->res) == IORESOURCE_IRQ) - irq = rentry->res.start; + if (resource_type(rentry->res) == IORESOURCE_MEM) + mem = rentry->res->start; + else if (resource_type(rentry->res) == IORESOURCE_IRQ) + irq = rentry->res->start; } acpi_dev_free_resource_list(&resource_list); diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 49c265255a0..cb59619df23 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -385,4 +385,11 @@ config EDAC_ALTERA_MC preloader must initialize the SDRAM before loading the kernel. +config EDAC_SYNOPSYS + tristate "Synopsys DDR Memory Controller" + depends on EDAC_MM_EDAC && ARCH_ZYNQ + help + Support for error detection and correction on the Synopsys DDR + memory controller. + endif # EDAC diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index d40c69a04df..b255f362b1d 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -67,3 +67,4 @@ obj-$(CONFIG_EDAC_OCTEON_LMC) += octeon_edac-lmc.o obj-$(CONFIG_EDAC_OCTEON_PCI) += octeon_edac-pci.o obj-$(CONFIG_EDAC_ALTERA_MC) += altera_edac.o +obj-$(CONFIG_EDAC_SYNOPSYS) += synopsys_edac.o diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 670d2829c54..c84eecb191e 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -157,7 +157,7 @@ struct dev_ch_attribute { }; #define DEVICE_CHANNEL(_name, _mode, _show, _store, _var) \ - struct dev_ch_attribute dev_attr_legacy_##_name = \ + static struct dev_ch_attribute dev_attr_legacy_##_name = \ { __ATTR(_name, _mode, _show, _store), (_var) } #define to_channel(k) (container_of(k, struct dev_ch_attribute, attr)->channel) @@ -850,20 +850,20 @@ static const struct file_operations debug_fake_inject_fops = { #endif /* default Control file */ -DEVICE_ATTR(reset_counters, S_IWUSR, NULL, mci_reset_counters_store); +static DEVICE_ATTR(reset_counters, S_IWUSR, NULL, mci_reset_counters_store); /* default Attribute files */ -DEVICE_ATTR(mc_name, S_IRUGO, mci_ctl_name_show, NULL); -DEVICE_ATTR(size_mb, S_IRUGO, mci_size_mb_show, NULL); -DEVICE_ATTR(seconds_since_reset, S_IRUGO, mci_seconds_show, NULL); -DEVICE_ATTR(ue_noinfo_count, S_IRUGO, mci_ue_noinfo_show, NULL); -DEVICE_ATTR(ce_noinfo_count, S_IRUGO, mci_ce_noinfo_show, NULL); -DEVICE_ATTR(ue_count, S_IRUGO, mci_ue_count_show, NULL); -DEVICE_ATTR(ce_count, S_IRUGO, mci_ce_count_show, NULL); -DEVICE_ATTR(max_location, S_IRUGO, mci_max_location_show, NULL); +static DEVICE_ATTR(mc_name, S_IRUGO, mci_ctl_name_show, NULL); +static DEVICE_ATTR(size_mb, S_IRUGO, mci_size_mb_show, NULL); +static DEVICE_ATTR(seconds_since_reset, S_IRUGO, mci_seconds_show, NULL); +static DEVICE_ATTR(ue_noinfo_count, S_IRUGO, mci_ue_noinfo_show, NULL); +static DEVICE_ATTR(ce_noinfo_count, S_IRUGO, mci_ce_noinfo_show, NULL); +static DEVICE_ATTR(ue_count, S_IRUGO, mci_ue_count_show, NULL); +static DEVICE_ATTR(ce_count, S_IRUGO, mci_ce_count_show, NULL); +static DEVICE_ATTR(max_location, S_IRUGO, mci_max_location_show, NULL); /* memory scrubber attribute file */ -DEVICE_ATTR(sdram_scrub_rate, 0, NULL, NULL); +static DEVICE_ATTR(sdram_scrub_rate, 0, NULL, NULL); static struct attribute *mci_attrs[] = { &dev_attr_reset_counters.attr, @@ -989,7 +989,7 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci) err = bus_register(mci->bus); if (err < 0) - return err; + goto fail_free_name; /* get the /sys/devices/system/edac subsys reference */ mci->dev.type = &mci_attr_type; @@ -1005,9 +1005,7 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci) err = device_add(&mci->dev); if (err < 0) { edac_dbg(1, "failure: create device %s\n", dev_name(&mci->dev)); - bus_unregister(mci->bus); - kfree(mci->bus->name); - return err; + goto fail_unregister_bus; } if (mci->set_sdram_scrub_rate || mci->get_sdram_scrub_rate) { @@ -1015,15 +1013,16 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci) dev_attr_sdram_scrub_rate.attr.mode |= S_IRUGO; dev_attr_sdram_scrub_rate.show = &mci_sdram_scrub_rate_show; } + if (mci->set_sdram_scrub_rate) { dev_attr_sdram_scrub_rate.attr.mode |= S_IWUSR; dev_attr_sdram_scrub_rate.store = &mci_sdram_scrub_rate_store; } - err = device_create_file(&mci->dev, - &dev_attr_sdram_scrub_rate); + + err = device_create_file(&mci->dev, &dev_attr_sdram_scrub_rate); if (err) { edac_dbg(1, "failure: create sdram_scrub_rate\n"); - goto fail2; + goto fail_unregister_dev; } } /* @@ -1032,8 +1031,9 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci) for (i = 0; i < mci->tot_dimms; i++) { struct dimm_info *dimm = mci->dimms[i]; /* Only expose populated DIMMs */ - if (dimm->nr_pages == 0) + if (!dimm->nr_pages) continue; + #ifdef CONFIG_EDAC_DEBUG edac_dbg(1, "creating dimm%d, located at ", i); if (edac_debug_level >= 1) { @@ -1048,14 +1048,14 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci) err = edac_create_dimm_object(mci, dimm, i); if (err) { edac_dbg(1, "failure: create dimm %d obj\n", i); - goto fail; + goto fail_unregister_dimm; } } #ifdef CONFIG_EDAC_LEGACY_SYSFS err = edac_create_csrow_objects(mci); if (err < 0) - goto fail; + goto fail_unregister_dimm; #endif #ifdef CONFIG_EDAC_DEBUG @@ -1063,16 +1063,19 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci) #endif return 0; -fail: +fail_unregister_dimm: for (i--; i >= 0; i--) { struct dimm_info *dimm = mci->dimms[i]; - if (dimm->nr_pages == 0) + if (!dimm->nr_pages) continue; + device_unregister(&dimm->dev); } -fail2: +fail_unregister_dev: device_unregister(&mci->dev); +fail_unregister_bus: bus_unregister(mci->bus); +fail_free_name: kfree(mci->bus->name); return err; } diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c index 6247d186177..e9f8a393915 100644 --- a/drivers/edac/i5100_edac.c +++ b/drivers/edac/i5100_edac.c @@ -279,11 +279,6 @@ static inline u32 i5100_recmema_rank(u32 a) return i5100_nrecmema_rank(a); } -static inline u32 i5100_recmema_dm_buf_id(u32 a) -{ - return i5100_nrecmema_dm_buf_id(a); -} - static inline u32 i5100_recmemb_cas(u32 a) { return i5100_nrecmemb_cas(a); diff --git a/drivers/edac/mce_amd_inj.c b/drivers/edac/mce_amd_inj.c index 0bd91a802c6..f7681b553fd 100644 --- a/drivers/edac/mce_amd_inj.c +++ b/drivers/edac/mce_amd_inj.c @@ -197,7 +197,7 @@ static int inj_bank_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(bank_fops, inj_bank_get, inj_bank_set, "%llu\n"); -struct dfs_node { +static struct dfs_node { char *name; struct dentry *d; const struct file_operations *fops; diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c index ffb1a9a15cc..1fa76a588af 100644 --- a/drivers/edac/mpc85xx_edac.c +++ b/drivers/edac/mpc85xx_edac.c @@ -1,5 +1,5 @@ /* - * Freescale MPC85xx Memory Controller kenel module + * Freescale MPC85xx Memory Controller kernel module * * Parts Copyrighted (c) 2013 by Freescale Semiconductor, Inc. * diff --git a/drivers/edac/mpc85xx_edac.h b/drivers/edac/mpc85xx_edac.h index 8c625643622..4498baf9ce0 100644 --- a/drivers/edac/mpc85xx_edac.h +++ b/drivers/edac/mpc85xx_edac.h @@ -1,5 +1,5 @@ /* - * Freescale MPC85xx Memory Controller kenel module + * Freescale MPC85xx Memory Controller kernel module * Author: Dave Jiang <djiang@mvista.com> * * 2006-2007 (c) MontaVista Software, Inc. This file is licensed under diff --git a/drivers/edac/mv64x60_edac.c b/drivers/edac/mv64x60_edac.c index 6366e880f97..0574e1bbe45 100644 --- a/drivers/edac/mv64x60_edac.c +++ b/drivers/edac/mv64x60_edac.c @@ -789,7 +789,8 @@ static int mv64x60_mc_err_probe(struct platform_device *pdev) ctl = (ctl & 0xff00ffff) | 0x10000; out_le32(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CNTL, ctl); - if (edac_mc_add_mc(mci)) { + res = edac_mc_add_mc(mci); + if (res) { edac_dbg(3, "failed edac_mc_add_mc()\n"); goto err; } diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c new file mode 100644 index 00000000000..1c9691535e1 --- /dev/null +++ b/drivers/edac/synopsys_edac.c @@ -0,0 +1,535 @@ +/* + * Synopsys DDR ECC Driver + * This driver is based on ppc4xx_edac.c drivers + * + * Copyright (C) 2012 - 2014 Xilinx, Inc. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details + */ + +#include <linux/edac.h> +#include <linux/module.h> +#include <linux/platform_device.h> + +#include "edac_core.h" + +/* Number of cs_rows needed per memory controller */ +#define SYNPS_EDAC_NR_CSROWS 1 + +/* Number of channels per memory controller */ +#define SYNPS_EDAC_NR_CHANS 1 + +/* Granularity of reported error in bytes */ +#define SYNPS_EDAC_ERR_GRAIN 1 + +#define SYNPS_EDAC_MSG_SIZE 256 + +#define SYNPS_EDAC_MOD_STRING "synps_edac" +#define SYNPS_EDAC_MOD_VER "1" + +/* Synopsys DDR memory controller registers that are relevant to ECC */ +#define CTRL_OFST 0x0 +#define T_ZQ_OFST 0xA4 + +/* ECC control register */ +#define ECC_CTRL_OFST 0xC4 +/* ECC log register */ +#define CE_LOG_OFST 0xC8 +/* ECC address register */ +#define CE_ADDR_OFST 0xCC +/* ECC data[31:0] register */ +#define CE_DATA_31_0_OFST 0xD0 + +/* Uncorrectable error info registers */ +#define UE_LOG_OFST 0xDC +#define UE_ADDR_OFST 0xE0 +#define UE_DATA_31_0_OFST 0xE4 + +#define STAT_OFST 0xF0 +#define SCRUB_OFST 0xF4 + +/* Control register bit field definitions */ +#define CTRL_BW_MASK 0xC +#define CTRL_BW_SHIFT 2 + +#define DDRCTL_WDTH_16 1 +#define DDRCTL_WDTH_32 0 + +/* ZQ register bit field definitions */ +#define T_ZQ_DDRMODE_MASK 0x2 + +/* ECC control register bit field definitions */ +#define ECC_CTRL_CLR_CE_ERR 0x2 +#define ECC_CTRL_CLR_UE_ERR 0x1 + +/* ECC correctable/uncorrectable error log register definitions */ +#define LOG_VALID 0x1 +#define CE_LOG_BITPOS_MASK 0xFE +#define CE_LOG_BITPOS_SHIFT 1 + +/* ECC correctable/uncorrectable error address register definitions */ +#define ADDR_COL_MASK 0xFFF +#define ADDR_ROW_MASK 0xFFFF000 +#define ADDR_ROW_SHIFT 12 +#define ADDR_BANK_MASK 0x70000000 +#define ADDR_BANK_SHIFT 28 + +/* ECC statistic register definitions */ +#define STAT_UECNT_MASK 0xFF +#define STAT_CECNT_MASK 0xFF00 +#define STAT_CECNT_SHIFT 8 + +/* ECC scrub register definitions */ +#define SCRUB_MODE_MASK 0x7 +#define SCRUB_MODE_SECDED 0x4 + +/** + * struct ecc_error_info - ECC error log information + * @row: Row number + * @col: Column number + * @bank: Bank number + * @bitpos: Bit position + * @data: Data causing the error + */ +struct ecc_error_info { + u32 row; + u32 col; + u32 bank; + u32 bitpos; + u32 data; +}; + +/** + * struct synps_ecc_status - ECC status information to report + * @ce_cnt: Correctable error count + * @ue_cnt: Uncorrectable error count + * @ceinfo: Correctable error log information + * @ueinfo: Uncorrectable error log information + */ +struct synps_ecc_status { + u32 ce_cnt; + u32 ue_cnt; + struct ecc_error_info ceinfo; + struct ecc_error_info ueinfo; +}; + +/** + * struct synps_edac_priv - DDR memory controller private instance data + * @baseaddr: Base address of the DDR controller + * @message: Buffer for framing the event specific info + * @stat: ECC status information + * @ce_cnt: Correctable Error count + * @ue_cnt: Uncorrectable Error count + */ +struct synps_edac_priv { + void __iomem *baseaddr; + char message[SYNPS_EDAC_MSG_SIZE]; + struct synps_ecc_status stat; + u32 ce_cnt; + u32 ue_cnt; +}; + +/** + * synps_edac_geterror_info - Get the current ecc error info + * @base: Pointer to the base address of the ddr memory controller + * @p: Pointer to the synopsys ecc status structure + * + * Determines there is any ecc error or not + * + * Return: one if there is no error otherwise returns zero + */ +static int synps_edac_geterror_info(void __iomem *base, + struct synps_ecc_status *p) +{ + u32 regval, clearval = 0; + + regval = readl(base + STAT_OFST); + if (!regval) + return 1; + + p->ce_cnt = (regval & STAT_CECNT_MASK) >> STAT_CECNT_SHIFT; + p->ue_cnt = regval & STAT_UECNT_MASK; + + regval = readl(base + CE_LOG_OFST); + if (!(p->ce_cnt && (regval & LOG_VALID))) + goto ue_err; + + p->ceinfo.bitpos = (regval & CE_LOG_BITPOS_MASK) >> CE_LOG_BITPOS_SHIFT; + regval = readl(base + CE_ADDR_OFST); + p->ceinfo.row = (regval & ADDR_ROW_MASK) >> ADDR_ROW_SHIFT; + p->ceinfo.col = regval & ADDR_COL_MASK; + p->ceinfo.bank = (regval & ADDR_BANK_MASK) >> ADDR_BANK_SHIFT; + p->ceinfo.data = readl(base + CE_DATA_31_0_OFST); + edac_dbg(3, "ce bit position: %d data: %d\n", p->ceinfo.bitpos, + p->ceinfo.data); + clearval = ECC_CTRL_CLR_CE_ERR; + +ue_err: + regval = readl(base + UE_LOG_OFST); + if (!(p->ue_cnt && (regval & LOG_VALID))) + goto out; + + regval = readl(base + UE_ADDR_OFST); + p->ueinfo.row = (regval & ADDR_ROW_MASK) >> ADDR_ROW_SHIFT; + p->ueinfo.col = regval & ADDR_COL_MASK; + p->ueinfo.bank = (regval & ADDR_BANK_MASK) >> ADDR_BANK_SHIFT; + p->ueinfo.data = readl(base + UE_DATA_31_0_OFST); + clearval |= ECC_CTRL_CLR_UE_ERR; + +out: + writel(clearval, base + ECC_CTRL_OFST); + writel(0x0, base + ECC_CTRL_OFST); + + return 0; +} + +/** + * synps_edac_handle_error - Handle controller error types CE and UE + * @mci: Pointer to the edac memory controller instance + * @p: Pointer to the synopsys ecc status structure + * + * Handles the controller ECC correctable and un correctable error. + */ +static void synps_edac_handle_error(struct mem_ctl_info *mci, + struct synps_ecc_status *p) +{ + struct synps_edac_priv *priv = mci->pvt_info; + struct ecc_error_info *pinf; + + if (p->ce_cnt) { + pinf = &p->ceinfo; + snprintf(priv->message, SYNPS_EDAC_MSG_SIZE, + "DDR ECC error type :%s Row %d Bank %d Col %d ", + "CE", pinf->row, pinf->bank, pinf->col); + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, + p->ce_cnt, 0, 0, 0, 0, 0, -1, + priv->message, ""); + } + + if (p->ue_cnt) { + pinf = &p->ueinfo; + snprintf(priv->message, SYNPS_EDAC_MSG_SIZE, + "DDR ECC error type :%s Row %d Bank %d Col %d ", + "UE", pinf->row, pinf->bank, pinf->col); + edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, + p->ue_cnt, 0, 0, 0, 0, 0, -1, + priv->message, ""); + } + + memset(p, 0, sizeof(*p)); +} + +/** + * synps_edac_check - Check controller for ECC errors + * @mci: Pointer to the edac memory controller instance + * + * Used to check and post ECC errors. Called by the polling thread + */ +static void synps_edac_check(struct mem_ctl_info *mci) +{ + struct synps_edac_priv *priv = mci->pvt_info; + int status; + + status = synps_edac_geterror_info(priv->baseaddr, &priv->stat); + if (status) + return; + + priv->ce_cnt += priv->stat.ce_cnt; + priv->ue_cnt += priv->stat.ue_cnt; + synps_edac_handle_error(mci, &priv->stat); + + edac_dbg(3, "Total error count ce %d ue %d\n", + priv->ce_cnt, priv->ue_cnt); +} + +/** + * synps_edac_get_dtype - Return the controller memory width + * @base: Pointer to the ddr memory controller base address + * + * Get the EDAC device type width appropriate for the current controller + * configuration. + * + * Return: a device type width enumeration. + */ +static enum dev_type synps_edac_get_dtype(const void __iomem *base) +{ + enum dev_type dt; + u32 width; + + width = readl(base + CTRL_OFST); + width = (width & CTRL_BW_MASK) >> CTRL_BW_SHIFT; + + switch (width) { + case DDRCTL_WDTH_16: + dt = DEV_X2; + break; + case DDRCTL_WDTH_32: + dt = DEV_X4; + break; + default: + dt = DEV_UNKNOWN; + } + + return dt; +} + +/** + * synps_edac_get_eccstate - Return the controller ecc enable/disable status + * @base: Pointer to the ddr memory controller base address + * + * Get the ECC enable/disable status for the controller + * + * Return: a ecc status boolean i.e true/false - enabled/disabled. + */ +static bool synps_edac_get_eccstate(void __iomem *base) +{ + enum dev_type dt; + u32 ecctype; + bool state = false; + + dt = synps_edac_get_dtype(base); + if (dt == DEV_UNKNOWN) + return state; + + ecctype = readl(base + SCRUB_OFST) & SCRUB_MODE_MASK; + if ((ecctype == SCRUB_MODE_SECDED) && (dt == DEV_X2)) + state = true; + + return state; +} + +/** + * synps_edac_get_memsize - reads the size of the attached memory device + * + * Return: the memory size in bytes + */ +static u32 synps_edac_get_memsize(void) +{ + struct sysinfo inf; + + si_meminfo(&inf); + + return inf.totalram * inf.mem_unit; +} + +/** + * synps_edac_get_mtype - Returns controller memory type + * @base: pointer to the synopsys ecc status structure + * + * Get the EDAC memory type appropriate for the current controller + * configuration. + * + * Return: a memory type enumeration. + */ +static enum mem_type synps_edac_get_mtype(const void __iomem *base) +{ + enum mem_type mt; + u32 memtype; + + memtype = readl(base + T_ZQ_OFST); + + if (memtype & T_ZQ_DDRMODE_MASK) + mt = MEM_DDR3; + else + mt = MEM_DDR2; + + return mt; +} + +/** + * synps_edac_init_csrows - Initialize the cs row data + * @mci: Pointer to the edac memory controller instance + * + * Initializes the chip select rows associated with the EDAC memory + * controller instance + * + * Return: Unconditionally 0. + */ +static int synps_edac_init_csrows(struct mem_ctl_info *mci) +{ + struct csrow_info *csi; + struct dimm_info *dimm; + struct synps_edac_priv *priv = mci->pvt_info; + u32 size; + int row, j; + + for (row = 0; row < mci->nr_csrows; row++) { + csi = mci->csrows[row]; + size = synps_edac_get_memsize(); + + for (j = 0; j < csi->nr_channels; j++) { + dimm = csi->channels[j]->dimm; + dimm->edac_mode = EDAC_FLAG_SECDED; + dimm->mtype = synps_edac_get_mtype(priv->baseaddr); + dimm->nr_pages = (size >> PAGE_SHIFT) / csi->nr_channels; + dimm->grain = SYNPS_EDAC_ERR_GRAIN; + dimm->dtype = synps_edac_get_dtype(priv->baseaddr); + } + } + + return 0; +} + +/** + * synps_edac_mc_init - Initialize driver instance + * @mci: Pointer to the edac memory controller instance + * @pdev: Pointer to the platform_device struct + * + * Performs initialization of the EDAC memory controller instance and + * related driver-private data associated with the memory controller the + * instance is bound to. + * + * Return: Always zero. + */ +static int synps_edac_mc_init(struct mem_ctl_info *mci, + struct platform_device *pdev) +{ + int status; + struct synps_edac_priv *priv; + + mci->pdev = &pdev->dev; + priv = mci->pvt_info; + platform_set_drvdata(pdev, mci); + + /* Initialize controller capabilities and configuration */ + mci->mtype_cap = MEM_FLAG_DDR3 | MEM_FLAG_DDR2; + mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_SECDED; + mci->scrub_cap = SCRUB_HW_SRC; + mci->scrub_mode = SCRUB_NONE; + + mci->edac_cap = EDAC_FLAG_SECDED; + mci->ctl_name = "synps_ddr_controller"; + mci->dev_name = SYNPS_EDAC_MOD_STRING; + mci->mod_name = SYNPS_EDAC_MOD_VER; + mci->mod_ver = "1"; + + edac_op_state = EDAC_OPSTATE_POLL; + mci->edac_check = synps_edac_check; + mci->ctl_page_to_phys = NULL; + + status = synps_edac_init_csrows(mci); + + return status; +} + +/** + * synps_edac_mc_probe - Check controller and bind driver + * @pdev: Pointer to the platform_device struct + * + * Probes a specific controller instance for binding with the driver. + * + * Return: 0 if the controller instance was successfully bound to the + * driver; otherwise, < 0 on error. + */ +static int synps_edac_mc_probe(struct platform_device *pdev) +{ + struct mem_ctl_info *mci; + struct edac_mc_layer layers[2]; + struct synps_edac_priv *priv; + int rc; + struct resource *res; + void __iomem *baseaddr; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + baseaddr = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(baseaddr)) + return PTR_ERR(baseaddr); + + if (!synps_edac_get_eccstate(baseaddr)) { + edac_printk(KERN_INFO, EDAC_MC, "ECC not enabled\n"); + return -ENXIO; + } + + layers[0].type = EDAC_MC_LAYER_CHIP_SELECT; + layers[0].size = SYNPS_EDAC_NR_CSROWS; + layers[0].is_virt_csrow = true; + layers[1].type = EDAC_MC_LAYER_CHANNEL; + layers[1].size = SYNPS_EDAC_NR_CHANS; + layers[1].is_virt_csrow = false; + + mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, + sizeof(struct synps_edac_priv)); + if (!mci) { + edac_printk(KERN_ERR, EDAC_MC, + "Failed memory allocation for mc instance\n"); + return -ENOMEM; + } + + priv = mci->pvt_info; + priv->baseaddr = baseaddr; + rc = synps_edac_mc_init(mci, pdev); + if (rc) { + edac_printk(KERN_ERR, EDAC_MC, + "Failed to initialize instance\n"); + goto free_edac_mc; + } + + rc = edac_mc_add_mc(mci); + if (rc) { + edac_printk(KERN_ERR, EDAC_MC, + "Failed to register with EDAC core\n"); + goto free_edac_mc; + } + + /* + * Start capturing the correctable and uncorrectable errors. A write of + * 0 starts the counters. + */ + writel(0x0, baseaddr + ECC_CTRL_OFST); + return rc; + +free_edac_mc: + edac_mc_free(mci); + + return rc; +} + +/** + * synps_edac_mc_remove - Unbind driver from controller + * @pdev: Pointer to the platform_device struct + * + * Return: Unconditionally 0 + */ +static int synps_edac_mc_remove(struct platform_device *pdev) +{ + struct mem_ctl_info *mci = platform_get_drvdata(pdev); + + edac_mc_del_mc(&pdev->dev); + edac_mc_free(mci); + + return 0; +} + +static struct of_device_id synps_edac_match[] = { + { .compatible = "xlnx,zynq-ddrc-a05", }, + { /* end of table */ } +}; + +MODULE_DEVICE_TABLE(of, synps_edac_match); + +static struct platform_driver synps_edac_mc_driver = { + .driver = { + .name = "synopsys-edac", + .of_match_table = synps_edac_match, + }, + .probe = synps_edac_mc_probe, + .remove = synps_edac_mc_remove, +}; + +module_platform_driver(synps_edac_mc_driver); + +MODULE_AUTHOR("Xilinx Inc"); +MODULE_DESCRIPTION("Synopsys DDR ECC driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index f712d47f30d..8de4da5c9ab 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -12,11 +12,11 @@ config EFI_VARS Note that using this driver in concert with efibootmgr requires at least test release version 0.5.0-test3 or later, which is - available from Matt Domsch's website located at: + available from: <http://linux.dell.com/efibootmgr/testing/efibootmgr-0.5.0-test3.tar.gz> Subsequent efibootmgr releases may be found at: - <http://linux.dell.com/efibootmgr> + <http://github.com/vathpela/efibootmgr> config EFI_VARS_PSTORE tristate "Register efivars backend for pstore" diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 9035c1b74d5..fccb464928c 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -115,15 +115,24 @@ EFI_ATTR_SHOW(fw_vendor); EFI_ATTR_SHOW(runtime); EFI_ATTR_SHOW(config_table); +static ssize_t fw_platform_size_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", efi_enabled(EFI_64BIT) ? 64 : 32); +} + static struct kobj_attribute efi_attr_fw_vendor = __ATTR_RO(fw_vendor); static struct kobj_attribute efi_attr_runtime = __ATTR_RO(runtime); static struct kobj_attribute efi_attr_config_table = __ATTR_RO(config_table); +static struct kobj_attribute efi_attr_fw_platform_size = + __ATTR_RO(fw_platform_size); static struct attribute *efi_subsys_attrs[] = { &efi_attr_systab.attr, &efi_attr_fw_vendor.attr, &efi_attr_runtime.attr, &efi_attr_config_table.attr, + &efi_attr_fw_platform_size.attr, NULL, }; @@ -272,15 +281,10 @@ static __init int match_config_table(efi_guid_t *guid, unsigned long table, efi_config_table_type_t *table_types) { - u8 str[EFI_VARIABLE_GUID_LEN + 1]; int i; if (table_types) { - efi_guid_unparse(guid, str); - for (i = 0; efi_guidcmp(table_types[i].guid, NULL_GUID); i++) { - efi_guid_unparse(&table_types[i].guid, str); - if (!efi_guidcmp(*guid, table_types[i].guid)) { *(table_types[i].ptr) = table; pr_cont(" %s=0x%lx ", @@ -403,8 +407,7 @@ static int __init fdt_find_uefi_params(unsigned long node, const char *uname, u64 val; int i, len; - if (depth != 1 || - (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0)) + if (depth != 1 || strcmp(uname, "chosen") != 0) return 0; for (i = 0; i < ARRAY_SIZE(dt_params); i++) { diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index f256ecd8a17..7b2e0496e0c 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -39,7 +39,7 @@ * fix locking per Peter Chubb's findings * * 25 Mar 2002 - Matt Domsch <Matt_Domsch@dell.com> - * move uuid_unparse() to include/asm-ia64/efi.h:efi_guid_unparse() + * move uuid_unparse() to include/asm-ia64/efi.h:efi_guid_to_str() * * 12 Feb 2002 - Matt Domsch <Matt_Domsch@dell.com> * use list_for_each_safe when deleting vars. @@ -128,7 +128,7 @@ efivar_guid_read(struct efivar_entry *entry, char *buf) if (!entry || !buf) return 0; - efi_guid_unparse(&var->VendorGuid, str); + efi_guid_to_str(&var->VendorGuid, str); str += strlen(str); str += sprintf(str, "\n"); @@ -569,7 +569,7 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var) private variables from another's. */ *(short_name + strlen(short_name)) = '-'; - efi_guid_unparse(&new_var->var.VendorGuid, + efi_guid_to_str(&new_var->var.VendorGuid, short_name + strlen(short_name)); new_var->kobj.kset = efivars_kset; diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index b14bc2b9fb4..8902f52e099 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -24,3 +24,17 @@ lib-y := efi-stub-helper.o lib-$(CONFIG_EFI_ARMSTUB) += arm-stub.o fdt.o CFLAGS_fdt.o += -I$(srctree)/scripts/dtc/libfdt/ + +# +# arm64 puts the stub in the kernel proper, which will unnecessarily retain all +# code indefinitely unless it is annotated as __init/__initdata/__initconst etc. +# So let's apply the __init annotations at the section level, by prefixing +# the section names directly. This will ensure that even all the inline string +# literals are covered. +# +extra-$(CONFIG_ARM64) := $(lib-y) +lib-$(CONFIG_ARM64) := $(patsubst %.o,%.init.o,$(lib-y)) + +OBJCOPYFLAGS := --prefix-alloc-sections=.init +$(obj)/%.init.o: $(obj)/%.o FORCE + $(call if_changed,objcopy) diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index eb48a1a1a57..2b3814702dc 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -17,10 +17,10 @@ #include "efistub.h" -static int __init efi_secureboot_enabled(efi_system_table_t *sys_table_arg) +static int efi_secureboot_enabled(efi_system_table_t *sys_table_arg) { - static efi_guid_t const var_guid __initconst = EFI_GLOBAL_VARIABLE_GUID; - static efi_char16_t const var_name[] __initconst = { + static efi_guid_t const var_guid = EFI_GLOBAL_VARIABLE_GUID; + static efi_char16_t const var_name[] = { 'S', 'e', 'c', 'u', 'r', 'e', 'B', 'o', 'o', 't', 0 }; efi_get_variable_t *f_getvar = sys_table_arg->runtime->get_variable; @@ -164,7 +164,7 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table, * for both archictectures, with the arch-specific code provided in the * handle_kernel_image() function. */ -unsigned long __init efi_entry(void *handle, efi_system_table_t *sys_table, +unsigned long efi_entry(void *handle, efi_system_table_t *sys_table, unsigned long *image_addr) { efi_loaded_image_t *image; diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index a920fec8fe8..d073e394638 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -66,25 +66,29 @@ efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg, unsigned long key; u32 desc_version; - *map_size = sizeof(*m) * 32; -again: + *map_size = 0; + *desc_size = 0; + key = 0; + status = efi_call_early(get_memory_map, map_size, NULL, + &key, desc_size, &desc_version); + if (status != EFI_BUFFER_TOO_SMALL) + return EFI_LOAD_ERROR; + /* * Add an additional efi_memory_desc_t because we're doing an * allocation which may be in a new descriptor region. */ - *map_size += sizeof(*m); + *map_size += *desc_size; status = efi_call_early(allocate_pool, EFI_LOADER_DATA, *map_size, (void **)&m); if (status != EFI_SUCCESS) goto fail; - *desc_size = 0; - key = 0; status = efi_call_early(get_memory_map, map_size, m, &key, desc_size, &desc_version); if (status == EFI_BUFFER_TOO_SMALL) { efi_call_early(free_pool, m); - goto again; + return EFI_LOAD_ERROR; } if (status != EFI_SUCCESS) @@ -101,7 +105,7 @@ fail: } -unsigned long __init get_dram_base(efi_system_table_t *sys_table_arg) +unsigned long get_dram_base(efi_system_table_t *sys_table_arg) { efi_status_t status; unsigned long map_size; diff --git a/drivers/firmware/efi/runtime-map.c b/drivers/firmware/efi/runtime-map.c index 018c29a2661..87b8e3b900d 100644 --- a/drivers/firmware/efi/runtime-map.c +++ b/drivers/firmware/efi/runtime-map.c @@ -191,7 +191,7 @@ int __init efi_runtime_map_init(struct kobject *efi_kobj) return 0; out_add_entry: - for (j = i - 1; j > 0; j--) { + for (j = i - 1; j >= 0; j--) { entry = *(map_entries + j); kobject_put(&entry->kobj); } diff --git a/drivers/gpu/drm/drm_vma_manager.c b/drivers/gpu/drm/drm_vma_manager.c index 63b47120507..68c1f32fb08 100644 --- a/drivers/gpu/drm/drm_vma_manager.c +++ b/drivers/gpu/drm/drm_vma_manager.c @@ -50,8 +50,7 @@ * * You must not use multiple offset managers on a single address_space. * Otherwise, mm-core will be unable to tear down memory mappings as the VM will - * no longer be linear. Please use VM_NONLINEAR in that case and implement your - * own offset managers. + * no longer be linear. * * This offset manager works on page-based addresses. That is, every argument * and return code (with the exception of drm_vma_node_offset_addr()) is given diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index dfdc2697002..152b006833c 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -147,6 +147,16 @@ config HID_BELKIN ---help--- Support for Belkin Flip KVM and Wireless keyboard. +config HID_BETOP_FF + tristate "Betop Production Inc. force feedback support" + depends on USB_HID + select INPUT_FF_MEMLESS + ---help--- + Say Y here if you want to enable force feedback support for devices by + BETOP Production Ltd. + Currently the following devices are known to be supported: + - BETOP 2185 PC & BFM MODE + config HID_CHERRY tristate "Cherry Cymotion keyboard" if EXPERT depends on HID @@ -389,7 +399,7 @@ config HID_LOGITECH_HIDPP Say Y if you want support for Logitech devices relying on the HID++ specification. Such devices are the various Logitech Touchpads (T650, T651, TK820), some mice (Zone Touch mouse), or even keyboards (Solar - Keayboard). + Keyboard). config LOGITECH_FF bool "Logitech force feedback support" diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile index debd15b44b5..6f19958dfc3 100644 --- a/drivers/hid/Makefile +++ b/drivers/hid/Makefile @@ -2,10 +2,7 @@ # Makefile for the HID driver # hid-y := hid-core.o hid-input.o - -ifdef CONFIG_DEBUG_FS - hid-objs += hid-debug.o -endif +hid-$(CONFIG_DEBUG_FS) += hid-debug.o obj-$(CONFIG_HID) += hid.o obj-$(CONFIG_UHID) += uhid.o @@ -15,23 +12,13 @@ obj-$(CONFIG_HID_GENERIC) += hid-generic.o hid-$(CONFIG_HIDRAW) += hidraw.o hid-logitech-y := hid-lg.o -ifdef CONFIG_LOGITECH_FF - hid-logitech-y += hid-lgff.o -endif -ifdef CONFIG_LOGIRUMBLEPAD2_FF - hid-logitech-y += hid-lg2ff.o -endif -ifdef CONFIG_LOGIG940_FF - hid-logitech-y += hid-lg3ff.o -endif -ifdef CONFIG_LOGIWHEELS_FF - hid-logitech-y += hid-lg4ff.o -endif +hid-logitech-$(CONFIG_LOGITECH_FF) += hid-lgff.o +hid-logitech-$(CONFIG_LOGIRUMBLEPAD2_FF) += hid-lg2ff.o +hid-logitech-$(CONFIG_LOGIG940_FF) += hid-lg3ff.o +hid-logitech-$(CONFIG_LOGIWHEELS_FF) += hid-lg4ff.o hid-wiimote-y := hid-wiimote-core.o hid-wiimote-modules.o -ifdef CONFIG_DEBUG_FS - hid-wiimote-y += hid-wiimote-debug.o -endif +hid-wiimote-$(CONFIG_DEBUG_FS) += hid-wiimote-debug.o obj-$(CONFIG_HID_A4TECH) += hid-a4tech.o obj-$(CONFIG_HID_ACRUX) += hid-axff.o @@ -39,6 +26,7 @@ obj-$(CONFIG_HID_APPLE) += hid-apple.o obj-$(CONFIG_HID_APPLEIR) += hid-appleir.o obj-$(CONFIG_HID_AUREAL) += hid-aureal.o obj-$(CONFIG_HID_BELKIN) += hid-belkin.o +obj-$(CONFIG_HID_BETOP_FF) += hid-betopff.o obj-$(CONFIG_HID_CHERRY) += hid-cherry.o obj-$(CONFIG_HID_CHICONY) += hid-chicony.o obj-$(CONFIG_HID_CP2112) += hid-cp2112.o @@ -76,24 +64,12 @@ obj-$(CONFIG_HID_PENMOUNT) += hid-penmount.o obj-$(CONFIG_HID_PETALYNX) += hid-petalynx.o obj-$(CONFIG_HID_PICOLCD) += hid-picolcd.o hid-picolcd-y += hid-picolcd_core.o -ifdef CONFIG_HID_PICOLCD_FB -hid-picolcd-y += hid-picolcd_fb.o -endif -ifdef CONFIG_HID_PICOLCD_BACKLIGHT -hid-picolcd-y += hid-picolcd_backlight.o -endif -ifdef CONFIG_HID_PICOLCD_LCD -hid-picolcd-y += hid-picolcd_lcd.o -endif -ifdef CONFIG_HID_PICOLCD_LEDS -hid-picolcd-y += hid-picolcd_leds.o -endif -ifdef CONFIG_HID_PICOLCD_CIR -hid-picolcd-y += hid-picolcd_cir.o -endif -ifdef CONFIG_DEBUG_FS -hid-picolcd-y += hid-picolcd_debugfs.o -endif +hid-picolcd-$(CONFIG_HID_PICOLCD_FB) += hid-picolcd_fb.o +hid-picolcd-$(CONFIG_HID_PICOLCD_BACKLIGHT) += hid-picolcd_backlight.o +hid-picolcd-$(CONFIG_HID_PICOLCD_LCD) += hid-picolcd_lcd.o +hid-picolcd-$(CONFIG_HID_PICOLCD_LEDS) += hid-picolcd_leds.o +hid-picolcd-$(CONFIG_HID_PICOLCD_CIR) += hid-picolcd_cir.o +hid-picolcd-$(CONFIG_DEBUG_FS) += hid-picolcd_debugfs.o obj-$(CONFIG_HID_PLANTRONICS) += hid-plantronics.o obj-$(CONFIG_HID_PRIMAX) += hid-primax.o diff --git a/drivers/hid/hid-betopff.c b/drivers/hid/hid-betopff.c new file mode 100644 index 00000000000..69cfc8dc6af --- /dev/null +++ b/drivers/hid/hid-betopff.c @@ -0,0 +1,160 @@ +/* + * Force feedback support for Betop based devices + * + * The devices are distributed under various names and the same USB device ID + * can be used in both adapters and actual game controllers. + * + * 0x11c2:0x2208 "BTP2185 BFM mode Joystick" + * - tested with BTP2185 BFM Mode. + * + * 0x11C0:0x5506 "BTP2185 PC mode Joystick" + * - tested with BTP2185 PC Mode. + * + * 0x8380:0x1850 "BTP2185 V2 PC mode USB Gamepad" + * - tested with BTP2185 PC Mode with another version. + * + * 0x20bc:0x5500 "BTP2185 V2 BFM mode Joystick" + * - tested with BTP2171s. + * Copyright (c) 2014 Huang Bo <huangbobupt@163.com> + */ + +/* + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + + +#include <linux/input.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/hid.h> + +#include "hid-ids.h" + +struct betopff_device { + struct hid_report *report; +}; + +static int hid_betopff_play(struct input_dev *dev, void *data, + struct ff_effect *effect) +{ + struct hid_device *hid = input_get_drvdata(dev); + struct betopff_device *betopff = data; + __u16 left, right; + + left = effect->u.rumble.strong_magnitude; + right = effect->u.rumble.weak_magnitude; + + betopff->report->field[2]->value[0] = left / 256; + betopff->report->field[3]->value[0] = right / 256; + + hid_hw_request(hid, betopff->report, HID_REQ_SET_REPORT); + + return 0; +} + +static int betopff_init(struct hid_device *hid) +{ + struct betopff_device *betopff; + struct hid_report *report; + struct hid_input *hidinput = + list_first_entry(&hid->inputs, struct hid_input, list); + struct list_head *report_list = + &hid->report_enum[HID_OUTPUT_REPORT].report_list; + struct input_dev *dev = hidinput->input; + int field_count = 0; + int error; + int i, j; + + if (list_empty(report_list)) { + hid_err(hid, "no output reports found\n"); + return -ENODEV; + } + + report = list_first_entry(report_list, struct hid_report, list); + /* + * Actually there are 4 fields for 4 Bytes as below: + * ----------------------------------------- + * Byte0 Byte1 Byte2 Byte3 + * 0x00 0x00 left_motor right_motor + * ----------------------------------------- + * Do init them with default value. + */ + for (i = 0; i < report->maxfield; i++) { + for (j = 0; j < report->field[i]->report_count; j++) { + report->field[i]->value[j] = 0x00; + field_count++; + } + } + + if (field_count < 4) { + hid_err(hid, "not enough fields in the report: %d\n", + field_count); + return -ENODEV; + } + + betopff = kzalloc(sizeof(*betopff), GFP_KERNEL); + if (!betopff) + return -ENOMEM; + + set_bit(FF_RUMBLE, dev->ffbit); + + error = input_ff_create_memless(dev, betopff, hid_betopff_play); + if (error) { + kfree(betopff); + return error; + } + + betopff->report = report; + hid_hw_request(hid, betopff->report, HID_REQ_SET_REPORT); + + hid_info(hid, "Force feedback for betop devices by huangbo <huangbobupt@163.com>\n"); + + return 0; +} + +static int betop_probe(struct hid_device *hdev, const struct hid_device_id *id) +{ + int ret; + + if (id->driver_data) + hdev->quirks |= HID_QUIRK_MULTI_INPUT; + + ret = hid_parse(hdev); + if (ret) { + hid_err(hdev, "parse failed\n"); + goto err; + } + + ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT & ~HID_CONNECT_FF); + if (ret) { + hid_err(hdev, "hw start failed\n"); + goto err; + } + + betopff_init(hdev); + + return 0; +err: + return ret; +} + +static const struct hid_device_id betop_devices[] = { + { HID_USB_DEVICE(USB_VENDOR_ID_BETOP_2185BFM, 0x2208) }, + { HID_USB_DEVICE(USB_VENDOR_ID_BETOP_2185PC, 0x5506) }, + { HID_USB_DEVICE(USB_VENDOR_ID_BETOP_2185V2PC, 0x1850) }, + { HID_USB_DEVICE(USB_VENDOR_ID_BETOP_2185V2BFM, 0x5500) }, + { } +}; +MODULE_DEVICE_TABLE(hid, betop_devices); + +static struct hid_driver betop_driver = { + .name = "betop", + .id_table = betop_devices, + .probe = betop_probe, +}; +module_hid_driver(betop_driver); + +MODULE_LICENSE("GPL"); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 8b638792cb4..db4fb6e1cc5 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -698,15 +698,25 @@ static void hid_scan_feature_usage(struct hid_parser *parser, u32 usage) static void hid_scan_collection(struct hid_parser *parser, unsigned type) { struct hid_device *hid = parser->device; + int i; if (((parser->global.usage_page << 16) == HID_UP_SENSOR) && type == HID_COLLECTION_PHYSICAL) hid->group = HID_GROUP_SENSOR_HUB; if (hid->vendor == USB_VENDOR_ID_MICROSOFT && - hid->product == USB_DEVICE_ID_MS_TYPE_COVER_3 && + (hid->product == USB_DEVICE_ID_MS_TYPE_COVER_3 || + hid->product == USB_DEVICE_ID_MS_TYPE_COVER_3_JP) && hid->group == HID_GROUP_MULTITOUCH) hid->group = HID_GROUP_GENERIC; + + if ((parser->global.usage_page << 16) == HID_UP_GENDESK) + for (i = 0; i < parser->local.usage_index; i++) + if (parser->local.usage[i] == HID_GD_POINTER) + parser->scan_flags |= HID_SCAN_FLAG_GD_POINTER; + + if ((parser->global.usage_page << 16) >= HID_UP_MSVENDOR) + parser->scan_flags |= HID_SCAN_FLAG_VENDOR_SPECIFIC; } static int hid_scan_main(struct hid_parser *parser, struct hid_item *item) @@ -792,11 +802,14 @@ static int hid_scan_report(struct hid_device *hid) hid->group = HID_GROUP_WACOM; break; case USB_VENDOR_ID_SYNAPTICS: - if ((hid->group == HID_GROUP_GENERIC) && - (hid->bus != BUS_USB || hid->type == HID_TYPE_USBMOUSE)) - /* hid-rmi should only bind to the mouse interface of - * composite USB devices */ - hid->group = HID_GROUP_RMI; + if (hid->group == HID_GROUP_GENERIC) + if ((parser->scan_flags & HID_SCAN_FLAG_VENDOR_SPECIFIC) + && (parser->scan_flags & HID_SCAN_FLAG_GD_POINTER)) + /* + * hid-rmi should take care of them, + * not hid-generic + */ + hid->group = HID_GROUP_RMI; break; } @@ -1757,6 +1770,10 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) }, { HID_USB_DEVICE(USB_VENDOR_ID_AUREAL, USB_DEVICE_ID_AUREAL_W01RN) }, { HID_USB_DEVICE(USB_VENDOR_ID_BELKIN, USB_DEVICE_ID_FLIP_KVM) }, + { HID_USB_DEVICE(USB_VENDOR_ID_BETOP_2185BFM, 0x2208) }, + { HID_USB_DEVICE(USB_VENDOR_ID_BETOP_2185PC, 0x5506) }, + { HID_USB_DEVICE(USB_VENDOR_ID_BETOP_2185V2PC, 0x1850) }, + { HID_USB_DEVICE(USB_VENDOR_ID_BETOP_2185V2BFM, 0x5500) }, { HID_USB_DEVICE(USB_VENDOR_ID_BTC, USB_DEVICE_ID_BTC_EMPREX_REMOTE) }, { HID_USB_DEVICE(USB_VENDOR_ID_BTC, USB_DEVICE_ID_BTC_EMPREX_REMOTE_2) }, { HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_CYMOTION) }, @@ -1861,6 +1878,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_WIRELESS_OPTICAL_DESKTOP_3_0) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_OFFICE_KB) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3) }, + { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3_JP) }, { HID_USB_DEVICE(USB_VENDOR_ID_MONTEREY, USB_DEVICE_ID_GENIUS_KB29E) }, { HID_USB_DEVICE(USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GT683R_LED_PANEL) }, { HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN) }, @@ -1971,6 +1989,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_BT) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO, USB_DEVICE_ID_NINTENDO_WIIMOTE) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO, USB_DEVICE_ID_NINTENDO_WIIMOTE2) }, + { HID_USB_DEVICE(USB_VENDOR_ID_RAZER, USB_DEVICE_ID_RAZER_BLADE_14) }, { } }; @@ -2328,6 +2347,7 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_MCC, USB_DEVICE_ID_MCC_PMD1208LS) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICKIT1) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICKIT2) }, + { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICK16F1454) }, { HID_USB_DEVICE(USB_VENDOR_ID_NATIONAL_SEMICONDUCTOR, USB_DEVICE_ID_N_S_HARMONY) }, { HID_USB_DEVICE(USB_VENDOR_ID_ONTRAK, USB_DEVICE_ID_ONTRAK_ADU100) }, { HID_USB_DEVICE(USB_VENDOR_ID_ONTRAK, USB_DEVICE_ID_ONTRAK_ADU100 + 20) }, diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c index 31fad641b74..6039f071fab 100644 --- a/drivers/hid/hid-hyperv.c +++ b/drivers/hid/hid-hyperv.c @@ -381,7 +381,7 @@ static void mousevsc_on_channel_callback(void *context) static int mousevsc_connect_to_vsp(struct hv_device *device) { int ret = 0; - int t; + unsigned long t; struct mousevsc_dev *input_dev = hv_get_drvdata(device); struct mousevsc_prt_msg *request; struct mousevsc_prt_msg *response; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 9243359c182..46edb4d3ed2 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -189,6 +189,11 @@ #define USB_VENDOR_ID_BERKSHIRE 0x0c98 #define USB_DEVICE_ID_BERKSHIRE_PCWD 0x1140 +#define USB_VENDOR_ID_BETOP_2185BFM 0x11c2 +#define USB_VENDOR_ID_BETOP_2185PC 0x11c0 +#define USB_VENDOR_ID_BETOP_2185V2PC 0x8380 +#define USB_VENDOR_ID_BETOP_2185V2BFM 0x20bc + #define USB_VENDOR_ID_BTC 0x046e #define USB_DEVICE_ID_BTC_EMPREX_REMOTE 0x5578 #define USB_DEVICE_ID_BTC_EMPREX_REMOTE_2 0x5577 @@ -638,6 +643,7 @@ #define USB_DEVICE_ID_PICKIT2 0x0033 #define USB_DEVICE_ID_PICOLCD 0xc002 #define USB_DEVICE_ID_PICOLCD_BOOTLOADER 0xf002 +#define USB_DEVICE_ID_PICK16F1454 0x0042 #define USB_VENDOR_ID_MICROSOFT 0x045e #define USB_DEVICE_ID_SIDEWINDER_GV 0x003b @@ -654,6 +660,7 @@ #define USB_DEVICE_ID_MS_TOUCH_COVER_2 0x07a7 #define USB_DEVICE_ID_MS_TYPE_COVER_2 0x07a9 #define USB_DEVICE_ID_MS_TYPE_COVER_3 0x07dc +#define USB_DEVICE_ID_MS_TYPE_COVER_3_JP 0x07dd #define USB_VENDOR_ID_MOJO 0x8282 #define USB_DEVICE_ID_RETRO_ADAPTER 0x3201 @@ -768,6 +775,9 @@ #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3001 0x3001 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008 0x3008 +#define USB_VENDOR_ID_RAZER 0x1532 +#define USB_DEVICE_ID_RAZER_BLADE_14 0x011D + #define USB_VENDOR_ID_REALTEK 0x0bda #define USB_DEVICE_ID_REALTEK_READER 0x0152 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 9505605b6e2..052869d0ab7 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -306,10 +306,13 @@ static enum power_supply_property hidinput_battery_props[] = { static const struct hid_device_id hid_battery_quirks[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, - USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO), - HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, + USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO), + HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, + USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI), + HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, - USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI), + USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI), HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO), @@ -1104,6 +1107,23 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct return; } + /* + * Ignore reports for absolute data if the data didn't change. This is + * not only an optimization but also fixes 'dead' key reports. Some + * RollOver implementations for localized keys (like BACKSLASH/PIPE; HID + * 0x31 and 0x32) report multiple keys, even though a localized keyboard + * can only have one of them physically available. The 'dead' keys + * report constant 0. As all map to the same keycode, they'd confuse + * the input layer. If we filter the 'dead' keys on the HID level, we + * skip the keycode translation and only forward real events. + */ + if (!(field->flags & (HID_MAIN_ITEM_RELATIVE | + HID_MAIN_ITEM_BUFFERED_BYTE)) && + (field->flags & HID_MAIN_ITEM_VARIABLE) && + usage->usage_index < field->maxusage && + value == field->value[usage->usage_index]) + return; + /* report the usage code as scancode if the key status has changed */ if (usage->type == EV_KEY && !!test_bit(usage->code, input->key) != value) input_event(input, EV_MSC, MSC_SCAN, usage->hid); diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index 4c55f4d9579..c4c3f095252 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -38,6 +38,7 @@ struct lenovo_drvdata_tpkbd { struct lenovo_drvdata_cptkbd { bool fn_lock; + int sensitivity; }; #define map_key_clear(c) hid_map_usage_clear(hi, usage, bit, max, EV_KEY, (c)) @@ -91,6 +92,38 @@ static int lenovo_input_mapping_cptkbd(struct hid_device *hdev, case 0x00fa: /* Fn-Esc: Fn-lock toggle */ map_key_clear(KEY_FN_ESC); return 1; + case 0x00fb: /* Middle mouse button (in native mode) */ + map_key_clear(BTN_MIDDLE); + return 1; + } + } + + /* Compatibility middle/wheel mappings should be ignored */ + if (usage->hid == HID_GD_WHEEL) + return -1; + if ((usage->hid & HID_USAGE_PAGE) == HID_UP_BUTTON && + (usage->hid & HID_USAGE) == 0x003) + return -1; + if ((usage->hid & HID_USAGE_PAGE) == HID_UP_CONSUMER && + (usage->hid & HID_USAGE) == 0x238) + return -1; + + /* Map wheel emulation reports: 0xffa1 = USB, 0xff10 = BT */ + if ((usage->hid & HID_USAGE_PAGE) == 0xff100000 || + (usage->hid & HID_USAGE_PAGE) == 0xffa10000) { + field->flags |= HID_MAIN_ITEM_RELATIVE | HID_MAIN_ITEM_VARIABLE; + field->logical_minimum = -127; + field->logical_maximum = 127; + + switch (usage->hid & HID_USAGE) { + case 0x0000: + hid_map_usage(hi, usage, bit, max, EV_REL, 0x06); + return 1; + case 0x0001: + hid_map_usage(hi, usage, bit, max, EV_REL, 0x08); + return 1; + default: + return -1; } } @@ -145,6 +178,7 @@ static void lenovo_features_set_cptkbd(struct hid_device *hdev) struct lenovo_drvdata_cptkbd *cptkbd_data = hid_get_drvdata(hdev); ret = lenovo_send_cmd_cptkbd(hdev, 0x05, cptkbd_data->fn_lock); + ret = lenovo_send_cmd_cptkbd(hdev, 0x02, cptkbd_data->sensitivity); if (ret) hid_err(hdev, "Fn-lock setting failed: %d\n", ret); } @@ -179,13 +213,50 @@ static ssize_t attr_fn_lock_store_cptkbd(struct device *dev, return count; } +static ssize_t attr_sensitivity_show_cptkbd(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct lenovo_drvdata_cptkbd *cptkbd_data = hid_get_drvdata(hdev); + + return snprintf(buf, PAGE_SIZE, "%u\n", + cptkbd_data->sensitivity); +} + +static ssize_t attr_sensitivity_store_cptkbd(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t count) +{ + struct hid_device *hdev = container_of(dev, struct hid_device, dev); + struct lenovo_drvdata_cptkbd *cptkbd_data = hid_get_drvdata(hdev); + int value; + + if (kstrtoint(buf, 10, &value) || value < 1 || value > 255) + return -EINVAL; + + cptkbd_data->sensitivity = value; + lenovo_features_set_cptkbd(hdev); + + return count; +} + + static struct device_attribute dev_attr_fn_lock_cptkbd = __ATTR(fn_lock, S_IWUSR | S_IRUGO, attr_fn_lock_show_cptkbd, attr_fn_lock_store_cptkbd); +static struct device_attribute dev_attr_sensitivity_cptkbd = + __ATTR(sensitivity, S_IWUSR | S_IRUGO, + attr_sensitivity_show_cptkbd, + attr_sensitivity_store_cptkbd); + + static struct attribute *lenovo_attributes_cptkbd[] = { &dev_attr_fn_lock_cptkbd.attr, + &dev_attr_sensitivity_cptkbd.attr, NULL }; @@ -594,8 +665,14 @@ static int lenovo_probe_cptkbd(struct hid_device *hdev) if (ret) hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret); - /* Turn Fn-Lock on by default */ + /* Switch middle button to native mode */ + ret = lenovo_send_cmd_cptkbd(hdev, 0x09, 0x01); + if (ret) + hid_warn(hdev, "Failed to switch middle button: %d\n", ret); + + /* Set keyboard settings to known state */ cptkbd_data->fn_lock = true; + cptkbd_data->sensitivity = 0x05; lenovo_features_set_cptkbd(hdev); ret = sysfs_create_group(&hdev->dev.kobj, &lenovo_attr_group_cptkbd); diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c index 7835717bc02..db0dd9b17e5 100644 --- a/drivers/hid/hid-lg4ff.c +++ b/drivers/hid/hid-lg4ff.c @@ -49,10 +49,6 @@ static void hid_lg4ff_set_range_dfp(struct hid_device *hid, u16 range); static void hid_lg4ff_set_range_g25(struct hid_device *hid, u16 range); -static ssize_t lg4ff_range_show(struct device *dev, struct device_attribute *attr, char *buf); -static ssize_t lg4ff_range_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); - -static DEVICE_ATTR(range, S_IRWXU | S_IRWXG | S_IROTH, lg4ff_range_show, lg4ff_range_store); struct lg4ff_device_entry { __u32 product_id; @@ -416,7 +412,8 @@ static void hid_lg4ff_switch_native(struct hid_device *hid, const struct lg4ff_n } /* Read current range and display it in terminal */ -static ssize_t lg4ff_range_show(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t range_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct hid_device *hid = to_hid_device(dev); struct lg4ff_device_entry *entry; @@ -441,7 +438,8 @@ static ssize_t lg4ff_range_show(struct device *dev, struct device_attribute *att /* Set range to user specified value, call appropriate function * according to the type of the wheel */ -static ssize_t lg4ff_range_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) +static ssize_t range_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct hid_device *hid = to_hid_device(dev); struct lg4ff_device_entry *entry; @@ -472,6 +470,7 @@ static ssize_t lg4ff_range_store(struct device *dev, struct device_attribute *at return count; } +static DEVICE_ATTR_RW(range); #ifdef CONFIG_LEDS_CLASS static void lg4ff_set_leds(struct hid_device *hid, __u8 leds) diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index a93cefe0e52..e77658cd037 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -89,6 +89,7 @@ struct hidpp_device { struct hid_device *hid_dev; struct mutex send_mutex; void *send_receive_buf; + char *name; /* will never be NULL and should not be freed */ wait_queue_head_t wait; bool answer_available; u8 protocol_major; @@ -105,6 +106,7 @@ struct hidpp_device { }; +/* HID++ 1.0 error codes */ #define HIDPP_ERROR 0x8f #define HIDPP_ERROR_SUCCESS 0x00 #define HIDPP_ERROR_INVALID_SUBID 0x01 @@ -119,6 +121,8 @@ struct hidpp_device { #define HIDPP_ERROR_REQUEST_UNAVAILABLE 0x0a #define HIDPP_ERROR_INVALID_PARAM_VALUE 0x0b #define HIDPP_ERROR_WRONG_PIN_CODE 0x0c +/* HID++ 2.0 error codes */ +#define HIDPP20_ERROR 0xff static void hidpp_connect_event(struct hidpp_device *hidpp_dev); @@ -192,9 +196,16 @@ static int hidpp_send_message_sync(struct hidpp_device *hidpp, } if (response->report_id == REPORT_ID_HIDPP_SHORT && - response->fap.feature_index == HIDPP_ERROR) { + response->rap.sub_id == HIDPP_ERROR) { + ret = response->rap.params[1]; + dbg_hid("%s:got hidpp error %02X\n", __func__, ret); + goto exit; + } + + if (response->report_id == REPORT_ID_HIDPP_LONG && + response->fap.feature_index == HIDPP20_ERROR) { ret = response->fap.params[1]; - dbg_hid("__hidpp_send_report got hidpp error %02X\n", ret); + dbg_hid("%s:got hidpp 2.0 error %02X\n", __func__, ret); goto exit; } @@ -271,7 +282,8 @@ static inline bool hidpp_match_answer(struct hidpp_report *question, static inline bool hidpp_match_error(struct hidpp_report *question, struct hidpp_report *answer) { - return (answer->fap.feature_index == HIDPP_ERROR) && + return ((answer->rap.sub_id == HIDPP_ERROR) || + (answer->fap.feature_index == HIDPP20_ERROR)) && (answer->fap.funcindex_clientid == question->fap.feature_index) && (answer->fap.params[0] == question->fap.funcindex_clientid); } @@ -903,24 +915,24 @@ static int wtp_allocate(struct hid_device *hdev, const struct hid_device_id *id) return 0; }; -static void wtp_connect(struct hid_device *hdev, bool connected) +static int wtp_connect(struct hid_device *hdev, bool connected) { struct hidpp_device *hidpp = hid_get_drvdata(hdev); struct wtp_data *wd = hidpp->private_data; int ret; if (!connected) - return; + return 0; if (!wd->x_size) { ret = wtp_get_config(hidpp); if (ret) { hid_err(hdev, "Can not get wtp config: %d\n", ret); - return; + return ret; } } - hidpp_touchpad_set_raw_report_state(hidpp, wd->mt_feature_index, + return hidpp_touchpad_set_raw_report_state(hidpp, wd->mt_feature_index, true, true); } @@ -965,7 +977,7 @@ static int hidpp_raw_hidpp_event(struct hidpp_device *hidpp, u8 *data, /* * If the mutex is locked then we have a pending answer from a - * previoulsly sent command + * previously sent command. */ if (unlikely(mutex_is_locked(&hidpp->send_mutex))) { /* @@ -996,9 +1008,6 @@ static int hidpp_raw_hidpp_event(struct hidpp_device *hidpp, u8 *data, return 1; } - if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP) - return wtp_raw_event(hidpp->hid_dev, data, size); - return 0; } @@ -1006,7 +1015,9 @@ static int hidpp_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *data, int size) { struct hidpp_device *hidpp = hid_get_drvdata(hdev); + int ret = 0; + /* Generic HID++ processing. */ switch (data[0]) { case REPORT_ID_HIDPP_LONG: if (size != HIDPP_REPORT_LONG_LENGTH) { @@ -1014,16 +1025,23 @@ static int hidpp_raw_event(struct hid_device *hdev, struct hid_report *report, size); return 1; } - return hidpp_raw_hidpp_event(hidpp, data, size); + ret = hidpp_raw_hidpp_event(hidpp, data, size); + break; case REPORT_ID_HIDPP_SHORT: if (size != HIDPP_REPORT_SHORT_LENGTH) { hid_err(hdev, "received hid++ report of bad size (%d)", size); return 1; } - return hidpp_raw_hidpp_event(hidpp, data, size); + ret = hidpp_raw_hidpp_event(hidpp, data, size); + break; } + /* If no report is available for further processing, skip calling + * raw_event of subclasses. */ + if (ret != 0) + return ret; + if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP) return wtp_raw_event(hdev, data, size); @@ -1070,6 +1088,7 @@ static void hidpp_input_close(struct input_dev *dev) static struct input_dev *hidpp_allocate_input(struct hid_device *hdev) { struct input_dev *input_dev = devm_input_allocate_device(&hdev->dev); + struct hidpp_device *hidpp = hid_get_drvdata(hdev); if (!input_dev) return NULL; @@ -1078,7 +1097,7 @@ static struct input_dev *hidpp_allocate_input(struct hid_device *hdev) input_dev->open = hidpp_input_open; input_dev->close = hidpp_input_close; - input_dev->name = hdev->name; + input_dev->name = hidpp->name; input_dev->phys = hdev->phys; input_dev->uniq = hdev->uniq; input_dev->id.bustype = hdev->bus; @@ -1098,8 +1117,11 @@ static void hidpp_connect_event(struct hidpp_device *hidpp) struct input_dev *input; char *name, *devm_name; - if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP) - wtp_connect(hdev, connected); + if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP) { + ret = wtp_connect(hdev, connected); + if (ret) + return; + } if (!connected || hidpp->delayed_input) return; @@ -1117,22 +1139,28 @@ static void hidpp_connect_event(struct hidpp_device *hidpp) hid_info(hdev, "HID++ %u.%u device connected.\n", hidpp->protocol_major, hidpp->protocol_minor); + if (!hidpp->name || hidpp->name == hdev->name) { + name = hidpp_get_device_name(hidpp); + if (!name) { + hid_err(hdev, + "unable to retrieve the name of the device"); + return; + } + + devm_name = devm_kasprintf(&hdev->dev, GFP_KERNEL, "%s", name); + kfree(name); + if (!devm_name) + return; + + hidpp->name = devm_name; + } + input = hidpp_allocate_input(hdev); if (!input) { hid_err(hdev, "cannot allocate new input device: %d\n", ret); return; } - name = hidpp_get_device_name(hidpp); - if (!name) { - hid_err(hdev, "unable to retrieve the name of the device"); - } else { - devm_name = devm_kasprintf(&hdev->dev, GFP_KERNEL, "%s", name); - if (devm_name) - input->name = devm_name; - kfree(name); - } - hidpp_populate_input(hidpp, input, false); ret = input_register_device(input); @@ -1155,6 +1183,7 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id) return -ENOMEM; hidpp->hid_dev = hdev; + hidpp->name = hdev->name; hid_set_drvdata(hdev, hidpp); hidpp->quirks = id->driver_data; diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c index cacda43f6a6..fbaea6eb882 100644 --- a/drivers/hid/hid-microsoft.c +++ b/drivers/hid/hid-microsoft.c @@ -276,6 +276,8 @@ static const struct hid_device_id ms_devices[] = { .driver_data = MS_DUPLICATE_USAGES }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3), .driver_data = MS_HIDINPUT }, + { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3_JP), + .driver_data = MS_HIDINPUT }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_BT), .driver_data = MS_PRESENTER }, diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c index b51200fe2f3..49d4fe4f598 100644 --- a/drivers/hid/hid-rmi.c +++ b/drivers/hid/hid-rmi.c @@ -33,6 +33,10 @@ #define RMI_READ_DATA_PENDING BIT(1) #define RMI_STARTED BIT(2) +/* device flags */ +#define RMI_DEVICE BIT(0) +#define RMI_DEVICE_HAS_PHYS_BUTTONS BIT(1) + enum rmi_mode_type { RMI_MODE_OFF = 0, RMI_MODE_ATTN_REPORTS = 1, @@ -118,6 +122,8 @@ struct rmi_data { struct work_struct reset_work; struct hid_device *hdev; + + unsigned long device_flags; }; #define RMI_PAGE(addr) (((addr) >> 8) & 0xff) @@ -452,9 +458,32 @@ static int rmi_raw_event(struct hid_device *hdev, return rmi_read_data_event(hdev, data, size); case RMI_ATTN_REPORT_ID: return rmi_input_event(hdev, data, size); - case RMI_MOUSE_REPORT_ID: + default: + return 1; + } + + return 0; +} + +static int rmi_event(struct hid_device *hdev, struct hid_field *field, + struct hid_usage *usage, __s32 value) +{ + struct rmi_data *data = hid_get_drvdata(hdev); + + if ((data->device_flags & RMI_DEVICE) && + (field->application == HID_GD_POINTER || + field->application == HID_GD_MOUSE)) { + if (data->device_flags & RMI_DEVICE_HAS_PHYS_BUTTONS) { + if ((usage->hid & HID_USAGE_PAGE) == HID_UP_BUTTON) + return 0; + + if ((usage->hid == HID_GD_X || usage->hid == HID_GD_Y) + && !value) + return 1; + } + rmi_schedule_reset(hdev); - break; + return 1; } return 0; @@ -856,6 +885,9 @@ static void rmi_input_configured(struct hid_device *hdev, struct hid_input *hi) if (ret) return; + if (!(data->device_flags & RMI_DEVICE)) + return; + /* Allow incoming hid reports */ hid_device_io_start(hdev); @@ -914,8 +946,38 @@ static int rmi_input_mapping(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) { - /* we want to make HID ignore the advertised HID collection */ - return -1; + struct rmi_data *data = hid_get_drvdata(hdev); + + /* + * we want to make HID ignore the advertised HID collection + * for RMI deivces + */ + if (data->device_flags & RMI_DEVICE) { + if ((data->device_flags & RMI_DEVICE_HAS_PHYS_BUTTONS) && + ((usage->hid & HID_USAGE_PAGE) == HID_UP_BUTTON)) + return 0; + + return -1; + } + + return 0; +} + +static int rmi_check_valid_report_id(struct hid_device *hdev, unsigned type, + unsigned id, struct hid_report **report) +{ + int i; + + *report = hdev->report_enum[type].report_id_hash[id]; + if (*report) { + for (i = 0; i < (*report)->maxfield; i++) { + unsigned app = (*report)->field[i]->application; + if ((app & HID_USAGE_PAGE) >= HID_UP_MSVENDOR) + return 1; + } + } + + return 0; } static int rmi_probe(struct hid_device *hdev, const struct hid_device_id *id) @@ -925,6 +987,7 @@ static int rmi_probe(struct hid_device *hdev, const struct hid_device_id *id) size_t alloc_size; struct hid_report *input_report; struct hid_report *output_report; + struct hid_report *feature_report; data = devm_kzalloc(&hdev->dev, sizeof(struct rmi_data), GFP_KERNEL); if (!data) @@ -943,27 +1006,37 @@ static int rmi_probe(struct hid_device *hdev, const struct hid_device_id *id) return ret; } - input_report = hdev->report_enum[HID_INPUT_REPORT] - .report_id_hash[RMI_ATTN_REPORT_ID]; - if (!input_report) { - hid_err(hdev, "device does not have expected input report\n"); - ret = -ENODEV; - return ret; + if (id->driver_data) + data->device_flags = id->driver_data; + + /* + * Check for the RMI specific report ids. If they are misisng + * simply return and let the events be processed by hid-input + */ + if (!rmi_check_valid_report_id(hdev, HID_FEATURE_REPORT, + RMI_SET_RMI_MODE_REPORT_ID, &feature_report)) { + hid_dbg(hdev, "device does not have set mode feature report\n"); + goto start; } - data->input_report_size = (input_report->size >> 3) + 1 /* report id */; + if (!rmi_check_valid_report_id(hdev, HID_INPUT_REPORT, + RMI_ATTN_REPORT_ID, &input_report)) { + hid_dbg(hdev, "device does not have attention input report\n"); + goto start; + } - output_report = hdev->report_enum[HID_OUTPUT_REPORT] - .report_id_hash[RMI_WRITE_REPORT_ID]; - if (!output_report) { - hid_err(hdev, "device does not have expected output report\n"); - ret = -ENODEV; - return ret; + data->input_report_size = hid_report_len(input_report); + + if (!rmi_check_valid_report_id(hdev, HID_OUTPUT_REPORT, + RMI_WRITE_REPORT_ID, &output_report)) { + hid_dbg(hdev, + "device does not have rmi write output report\n"); + goto start; } - data->output_report_size = (output_report->size >> 3) - + 1 /* report id */; + data->output_report_size = hid_report_len(output_report); + data->device_flags |= RMI_DEVICE; alloc_size = data->output_report_size + data->input_report_size; data->writeReport = devm_kzalloc(&hdev->dev, alloc_size, GFP_KERNEL); @@ -978,13 +1051,15 @@ static int rmi_probe(struct hid_device *hdev, const struct hid_device_id *id) mutex_init(&data->page_mutex); +start: ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT); if (ret) { hid_err(hdev, "hw start failed\n"); return ret; } - if (!test_bit(RMI_STARTED, &data->flags)) + if ((data->device_flags & RMI_DEVICE) && + !test_bit(RMI_STARTED, &data->flags)) /* * The device maybe in the bootloader if rmi_input_configured * failed to find F11 in the PDT. Print an error, but don't @@ -1007,6 +1082,8 @@ static void rmi_remove(struct hid_device *hdev) } static const struct hid_device_id rmi_id[] = { + { HID_USB_DEVICE(USB_VENDOR_ID_RAZER, USB_DEVICE_ID_RAZER_BLADE_14), + .driver_data = RMI_DEVICE_HAS_PHYS_BUTTONS }, { HID_DEVICE(HID_BUS_ANY, HID_GROUP_RMI, HID_ANY_ID, HID_ANY_ID) }, { } }; @@ -1017,6 +1094,7 @@ static struct hid_driver rmi_driver = { .id_table = rmi_id, .probe = rmi_probe, .remove = rmi_remove, + .event = rmi_event, .raw_event = rmi_raw_event, .input_mapping = rmi_input_mapping, .input_configured = rmi_input_configured, diff --git a/drivers/hid/usbhid/Makefile b/drivers/hid/usbhid/Makefile index db3cf31c6fa..890f2914a8f 100644 --- a/drivers/hid/usbhid/Makefile +++ b/drivers/hid/usbhid/Makefile @@ -2,17 +2,9 @@ # Makefile for the USB input drivers # -# Multipart objects. usbhid-y := hid-core.o hid-quirks.o - -# Optional parts of multipart objects. - -ifeq ($(CONFIG_USB_HIDDEV),y) - usbhid-y += hiddev.o -endif -ifeq ($(CONFIG_HID_PID),y) - usbhid-y += hid-pidff.o -endif +usbhid-$(CONFIG_USB_HIDDEV) += hiddev.o +usbhid-$(CONFIG_HID_PID) += hid-pidff.o obj-$(CONFIG_USB_HID) += usbhid.o obj-$(CONFIG_USB_KBD) += usbkbd.o diff --git a/drivers/hid/usbhid/hid-pidff.c b/drivers/hid/usbhid/hid-pidff.c index 10b61670278..0b531c6a76a 100644 --- a/drivers/hid/usbhid/hid-pidff.c +++ b/drivers/hid/usbhid/hid-pidff.c @@ -1252,6 +1252,8 @@ int hid_pidff_init(struct hid_device *hid) pidff->hid = hid; + hid_device_io_start(hid); + pidff_find_reports(hid, HID_OUTPUT_REPORT, pidff); pidff_find_reports(hid, HID_FEATURE_REPORT, pidff); @@ -1315,9 +1317,13 @@ int hid_pidff_init(struct hid_device *hid) hid_info(dev, "Force feedback for USB HID PID devices by Anssi Hannula <anssi.hannula@gmail.com>\n"); + hid_device_io_stop(hid); + return 0; fail: + hid_device_io_stop(hid); + kfree(pidff); return error; } diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index b27b3d33eba..9be99a67bfe 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -80,6 +80,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET }, { USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS, HID_QUIRK_NOGET }, { USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3, HID_QUIRK_NO_INIT_REPORTS }, + { USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3_JP, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GT683R_LED_PANEL, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_NEXIO, USB_DEVICE_ID_NEXIO_MULTITOUCH_PTI0750, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_NOVATEK, USB_DEVICE_ID_NOVATEK_MOUSE, HID_QUIRK_NO_INIT_REPORTS }, diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 654202941d3..f0568a7e6de 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -173,10 +173,8 @@ static void wacom_usage_mapping(struct hid_device *hdev, { struct wacom *wacom = hid_get_drvdata(hdev); struct wacom_features *features = &wacom->wacom_wac.features; - bool finger = (field->logical == HID_DG_FINGER) || - (field->physical == HID_DG_FINGER); - bool pen = (field->logical == HID_DG_STYLUS) || - (field->physical == HID_DG_STYLUS); + bool finger = WACOM_FINGER_FIELD(field); + bool pen = WACOM_PEN_FIELD(field); /* * Requiring Stylus Usage will ignore boot mouse @@ -405,6 +403,9 @@ static int wacom_query_tablet_data(struct hid_device *hdev, else if (features->type == WACOM_24HDT || features->type == CINTIQ_HYBRID) { return wacom_set_device_mode(hdev, 18, 3, 2); } + else if (features->type == WACOM_27QHDT) { + return wacom_set_device_mode(hdev, 131, 3, 2); + } } else if (features->device_type == BTN_TOOL_PEN) { if (features->type <= BAMBOO_PT && features->type != WIRELESS) { return wacom_set_device_mode(hdev, 2, 2, 2); diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index ac7447c7b82..1a6507999a6 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -15,7 +15,6 @@ #include "wacom_wac.h" #include "wacom.h" #include <linux/input/mt.h> -#include <linux/hid.h> /* resolution for penabled devices */ #define WACOM_PL_RES 20 @@ -444,9 +443,6 @@ static int wacom_intuos_inout(struct wacom_wac *wacom) /* Enter report */ if ((data[1] & 0xfc) == 0xc0) { - if (features->quirks & WACOM_QUIRK_MULTI_INPUT) - wacom->shared->stylus_in_proximity = true; - /* serial number of the tool */ wacom->serial[idx] = ((data[3] & 0x0f) << 28) + (data[4] << 20) + (data[5] << 12) + @@ -535,24 +531,46 @@ static int wacom_intuos_inout(struct wacom_wac *wacom) return 1; } + /* + * don't report events for invalid data + */ /* older I4 styli don't work with new Cintiqs */ - if (!((wacom->id[idx] >> 20) & 0x01) && - (features->type == WACOM_21UX2)) + if ((!((wacom->id[idx] >> 20) & 0x01) && + (features->type == WACOM_21UX2)) || + /* Only large Intuos support Lense Cursor */ + (wacom->tool[idx] == BTN_TOOL_LENS && + (features->type == INTUOS3 || + features->type == INTUOS3S || + features->type == INTUOS4 || + features->type == INTUOS4S || + features->type == INTUOS5 || + features->type == INTUOS5S || + features->type == INTUOSPM || + features->type == INTUOSPS)) || + /* Cintiq doesn't send data when RDY bit isn't set */ + (features->type == CINTIQ && !(data[1] & 0x40))) return 1; - /* Range Report */ - if ((data[1] & 0xfe) == 0x20) { + if (features->quirks & WACOM_QUIRK_MULTI_INPUT) + wacom->shared->stylus_in_proximity = true; + + /* in Range while exiting */ + if (((data[1] & 0xfe) == 0x20) && wacom->reporting_data) { input_report_key(input, BTN_TOUCH, 0); input_report_abs(input, ABS_PRESSURE, 0); input_report_abs(input, ABS_DISTANCE, wacom->features.distance_max); - if (features->quirks & WACOM_QUIRK_MULTI_INPUT) - wacom->shared->stylus_in_proximity = true; + return 2; } /* Exit report */ if ((data[1] & 0xfe) == 0x80) { if (features->quirks & WACOM_QUIRK_MULTI_INPUT) wacom->shared->stylus_in_proximity = false; + wacom->reporting_data = false; + + /* don't report exit if we don't know the ID */ + if (!wacom->id[idx]) + return 1; /* * Reset all states otherwise we lose the initial states @@ -586,6 +604,11 @@ static int wacom_intuos_inout(struct wacom_wac *wacom) wacom->id[idx] = 0; return 2; } + + /* don't report other events if we don't know the ID */ + if (!wacom->id[idx]) + return 1; + return 0; } @@ -633,6 +656,8 @@ static int wacom_intuos_irq(struct wacom_wac *wacom) data[0] != WACOM_REPORT_INTUOSREAD && data[0] != WACOM_REPORT_INTUOSWRITE && data[0] != WACOM_REPORT_INTUOSPAD && + data[0] != WACOM_REPORT_CINTIQ && + data[0] != WACOM_REPORT_CINTIQPAD && data[0] != WACOM_REPORT_INTUOS5PAD) { dev_dbg(input->dev.parent, "%s: received unknown report #%d\n", __func__, data[0]); @@ -644,7 +669,8 @@ static int wacom_intuos_irq(struct wacom_wac *wacom) idx = data[1] & 0x01; /* pad packets. Works as a second tool and is always in prox */ - if (data[0] == WACOM_REPORT_INTUOSPAD || data[0] == WACOM_REPORT_INTUOS5PAD) { + if (data[0] == WACOM_REPORT_INTUOSPAD || data[0] == WACOM_REPORT_INTUOS5PAD || + data[0] == WACOM_REPORT_CINTIQPAD) { input = wacom->pad_input; if (features->type >= INTUOS4S && features->type <= INTUOS4L) { input_report_key(input, BTN_0, (data[2] & 0x01)); @@ -744,6 +770,14 @@ static int wacom_intuos_irq(struct wacom_wac *wacom) } else { input_report_abs(input, ABS_MISC, 0); } + } else if (features->type == WACOM_27QHD) { + input_report_key(input, KEY_PROG1, data[2] & 0x01); + input_report_key(input, KEY_PROG2, data[2] & 0x02); + input_report_key(input, KEY_PROG3, data[2] & 0x04); + + input_report_abs(input, ABS_X, be16_to_cpup((__be16 *)&data[4])); + input_report_abs(input, ABS_Y, be16_to_cpup((__be16 *)&data[6])); + input_report_abs(input, ABS_Z, be16_to_cpup((__be16 *)&data[8])); } else if (features->type == CINTIQ_HYBRID) { /* * Do not send hardware buttons under Android. They @@ -760,6 +794,12 @@ static int wacom_intuos_irq(struct wacom_wac *wacom) input_report_key(input, BTN_7, (data[4] & 0x40)); /* Left */ input_report_key(input, BTN_8, (data[4] & 0x80)); /* Down */ input_report_key(input, BTN_0, (data[3] & 0x01)); /* Center */ + + if (data[4] | (data[3] & 0x01)) { + input_report_abs(input, ABS_MISC, PAD_DEVICE_ID); + } else { + input_report_abs(input, ABS_MISC, 0); + } } else if (features->type >= INTUOS5S && features->type <= INTUOSPL) { int i; @@ -843,28 +883,6 @@ static int wacom_intuos_irq(struct wacom_wac *wacom) if (result) return result - 1; - /* don't proceed if we don't know the ID */ - if (!wacom->id[idx]) - return 0; - - /* Only large Intuos support Lense Cursor */ - if (wacom->tool[idx] == BTN_TOOL_LENS && - (features->type == INTUOS3 || - features->type == INTUOS3S || - features->type == INTUOS4 || - features->type == INTUOS4S || - features->type == INTUOS5 || - features->type == INTUOS5S || - features->type == INTUOSPM || - features->type == INTUOSPS)) { - - return 0; - } - - /* Cintiq doesn't send data when RDY bit isn't set */ - if (features->type == CINTIQ && !(data[1] & 0x40)) - return 0; - if (features->type >= INTUOS3S) { input_report_abs(input, ABS_X, (data[2] << 9) | (data[3] << 1) | ((data[9] >> 1) & 1)); input_report_abs(input, ABS_Y, (data[4] << 9) | (data[5] << 1) | (data[9] & 1)); @@ -951,6 +969,7 @@ static int wacom_intuos_irq(struct wacom_wac *wacom) input_report_abs(input, ABS_MISC, wacom->id[idx]); /* report tool id */ input_report_key(input, wacom->tool[idx], 1); input_event(input, EV_MSC, MSC_SERIAL, wacom->serial[idx]); + wacom->reporting_data = true; return 1; } @@ -1019,8 +1038,20 @@ static int wacom_24hdt_irq(struct wacom_wac *wacom) struct input_dev *input = wacom->input; unsigned char *data = wacom->data; int i; - int current_num_contacts = data[61]; + int current_num_contacts = 0; int contacts_to_send = 0; + int num_contacts_left = 4; /* maximum contacts per packet */ + int byte_per_packet = WACOM_BYTES_PER_24HDT_PACKET; + int y_offset = 2; + + if (wacom->features.type == WACOM_27QHDT) { + current_num_contacts = data[63]; + num_contacts_left = 10; + byte_per_packet = WACOM_BYTES_PER_QHDTHID_PACKET; + y_offset = 0; + } else { + current_num_contacts = data[61]; + } /* * First packet resets the counter since only the first @@ -1029,12 +1060,11 @@ static int wacom_24hdt_irq(struct wacom_wac *wacom) if (current_num_contacts) wacom->num_contacts_left = current_num_contacts; - /* There are at most 4 contacts per packet */ - contacts_to_send = min(4, wacom->num_contacts_left); + contacts_to_send = min(num_contacts_left, wacom->num_contacts_left); for (i = 0; i < contacts_to_send; i++) { - int offset = (WACOM_BYTES_PER_24HDT_PACKET * i) + 1; - bool touch = data[offset] & 0x1 && !wacom->shared->stylus_in_proximity; + int offset = (byte_per_packet * i) + 1; + bool touch = (data[offset] & 0x1) && !wacom->shared->stylus_in_proximity; int slot = input_mt_get_slot_by_key(input, data[offset + 1]); if (slot < 0) @@ -1044,18 +1074,23 @@ static int wacom_24hdt_irq(struct wacom_wac *wacom) if (touch) { int t_x = get_unaligned_le16(&data[offset + 2]); - int c_x = get_unaligned_le16(&data[offset + 4]); - int t_y = get_unaligned_le16(&data[offset + 6]); - int c_y = get_unaligned_le16(&data[offset + 8]); - int w = get_unaligned_le16(&data[offset + 10]); - int h = get_unaligned_le16(&data[offset + 12]); + int t_y = get_unaligned_le16(&data[offset + 4 + y_offset]); input_report_abs(input, ABS_MT_POSITION_X, t_x); input_report_abs(input, ABS_MT_POSITION_Y, t_y); - input_report_abs(input, ABS_MT_TOUCH_MAJOR, min(w,h)); - input_report_abs(input, ABS_MT_WIDTH_MAJOR, min(w, h) + int_dist(t_x, t_y, c_x, c_y)); - input_report_abs(input, ABS_MT_WIDTH_MINOR, min(w, h)); - input_report_abs(input, ABS_MT_ORIENTATION, w > h); + + if (wacom->features.type != WACOM_27QHDT) { + int c_x = get_unaligned_le16(&data[offset + 4]); + int c_y = get_unaligned_le16(&data[offset + 8]); + int w = get_unaligned_le16(&data[offset + 10]); + int h = get_unaligned_le16(&data[offset + 12]); + + input_report_abs(input, ABS_MT_TOUCH_MAJOR, min(w,h)); + input_report_abs(input, ABS_MT_WIDTH_MAJOR, + min(w, h) + int_dist(t_x, t_y, c_x, c_y)); + input_report_abs(input, ABS_MT_WIDTH_MINOR, min(w, h)); + input_report_abs(input, ABS_MT_ORIENTATION, w > h); + } } } input_mt_report_pointer_emulation(input, true); @@ -1064,6 +1099,7 @@ static int wacom_24hdt_irq(struct wacom_wac *wacom) if (wacom->num_contacts_left <= 0) wacom->num_contacts_left = 0; + wacom->shared->touch_down = (wacom->num_contacts_left > 0); return 1; } @@ -1092,7 +1128,7 @@ static int wacom_mt_touch(struct wacom_wac *wacom) for (i = 0; i < contacts_to_send; i++) { int offset = (WACOM_BYTES_PER_MT_PACKET + x_offset) * i + 3; - bool touch = data[offset] & 0x1; + bool touch = (data[offset] & 0x1) && !wacom->shared->stylus_in_proximity; int id = get_unaligned_le16(&data[offset + 1]); int slot = input_mt_get_slot_by_key(input, id); @@ -1114,6 +1150,7 @@ static int wacom_mt_touch(struct wacom_wac *wacom) if (wacom->num_contacts_left < 0) wacom->num_contacts_left = 0; + wacom->shared->touch_down = (wacom->num_contacts_left > 0); return 1; } @@ -1514,13 +1551,6 @@ static void wacom_wac_finger_report(struct hid_device *hdev, wacom_wac->shared->touch_down = wacom_wac_finger_count_touches(hdev); } -#define WACOM_PEN_FIELD(f) (((f)->logical == HID_DG_STYLUS) || \ - ((f)->physical == HID_DG_STYLUS) || \ - ((f)->application == HID_DG_PEN)) -#define WACOM_FINGER_FIELD(f) (((f)->logical == HID_DG_FINGER) || \ - ((f)->physical == HID_DG_FINGER) || \ - ((f)->application == HID_DG_TOUCHSCREEN)) - void wacom_wac_usage_mapping(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage) { @@ -1891,6 +1921,7 @@ void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len) case WACOM_21UX2: case WACOM_22HD: case WACOM_24HD: + case WACOM_27QHD: case DTK: case CINTIQ_HYBRID: sync = wacom_intuos_irq(wacom_wac); @@ -1901,6 +1932,7 @@ void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len) break; case WACOM_24HDT: + case WACOM_27QHDT: sync = wacom_24hdt_irq(wacom_wac); break; @@ -2086,32 +2118,17 @@ int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev, wacom_abs_set_axis(input_dev, wacom_wac); switch (features->type) { - case WACOM_MO: - case WACOM_G4: - /* fall through */ - - case GRAPHIRE: - input_set_capability(input_dev, EV_REL, REL_WHEEL); - - __set_bit(BTN_LEFT, input_dev->keybit); - __set_bit(BTN_RIGHT, input_dev->keybit); - __set_bit(BTN_MIDDLE, input_dev->keybit); - - __set_bit(BTN_TOOL_RUBBER, input_dev->keybit); - __set_bit(BTN_TOOL_PEN, input_dev->keybit); - __set_bit(BTN_TOOL_MOUSE, input_dev->keybit); - __set_bit(BTN_STYLUS, input_dev->keybit); - __set_bit(BTN_STYLUS2, input_dev->keybit); - - __set_bit(INPUT_PROP_POINTER, input_dev->propbit); - break; - case GRAPHIRE_BT: __clear_bit(ABS_MISC, input_dev->absbit); + + case WACOM_MO: + case WACOM_G4: input_set_abs_params(input_dev, ABS_DISTANCE, 0, features->distance_max, 0, 0); + /* fall through */ + case GRAPHIRE: input_set_capability(input_dev, EV_REL, REL_WHEEL); __set_bit(BTN_LEFT, input_dev->keybit); @@ -2127,31 +2144,15 @@ int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev, __set_bit(INPUT_PROP_POINTER, input_dev->propbit); break; + case WACOM_27QHD: case WACOM_24HD: - input_set_abs_params(input_dev, ABS_Z, -900, 899, 0, 0); - input_abs_set_res(input_dev, ABS_Z, 287); - input_set_abs_params(input_dev, ABS_THROTTLE, 0, 71, 0, 0); - /* fall through */ - case DTK: - __set_bit(INPUT_PROP_DIRECT, input_dev->propbit); - - wacom_setup_cintiq(wacom_wac); - break; - case WACOM_22HD: case WACOM_21UX2: case WACOM_BEE: case CINTIQ: - input_set_abs_params(input_dev, ABS_Z, -900, 899, 0, 0); - input_abs_set_res(input_dev, ABS_Z, 287); - - __set_bit(INPUT_PROP_DIRECT, input_dev->propbit); - - wacom_setup_cintiq(wacom_wac); - break; - case WACOM_13HD: + case CINTIQ_HYBRID: input_set_abs_params(input_dev, ABS_Z, -900, 899, 0, 0); input_abs_set_res(input_dev, ABS_Z, 287); __set_bit(INPUT_PROP_DIRECT, input_dev->propbit); @@ -2161,6 +2162,10 @@ int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev, case INTUOS3: case INTUOS3L: case INTUOS3S: + case INTUOS4: + case INTUOS4WL: + case INTUOS4L: + case INTUOS4S: input_set_abs_params(input_dev, ABS_Z, -900, 899, 0, 0); input_abs_set_res(input_dev, ABS_Z, 287); /* fall through */ @@ -2199,17 +2204,6 @@ int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev, } break; - case INTUOS4: - case INTUOS4WL: - case INTUOS4L: - case INTUOS4S: - input_set_abs_params(input_dev, ABS_Z, -900, 899, 0, 0); - input_abs_set_res(input_dev, ABS_Z, 287); - wacom_setup_intuos(wacom_wac); - - __set_bit(INPUT_PROP_POINTER, input_dev->propbit); - break; - case WACOM_24HDT: if (features->device_type == BTN_TOOL_FINGER) { input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0, features->x_max, 0, 0); @@ -2219,6 +2213,7 @@ int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev, } /* fall through */ + case WACOM_27QHDT: case MTSCREEN: case MTTPC: case MTTPC_B: @@ -2305,14 +2300,6 @@ int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev, 0, 0); } break; - - case CINTIQ_HYBRID: - input_set_abs_params(input_dev, ABS_Z, -900, 899, 0, 0); - input_abs_set_res(input_dev, ABS_Z, 287); - __set_bit(INPUT_PROP_DIRECT, input_dev->propbit); - - wacom_setup_cintiq(wacom_wac); - break; } return 0; } @@ -2374,6 +2361,19 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev, input_set_abs_params(input_dev, ABS_THROTTLE, 0, 71, 0, 0); break; + case WACOM_27QHD: + __set_bit(KEY_PROG1, input_dev->keybit); + __set_bit(KEY_PROG2, input_dev->keybit); + __set_bit(KEY_PROG3, input_dev->keybit); + input_set_abs_params(input_dev, ABS_X, -2048, 2048, 0, 0); + input_abs_set_res(input_dev, ABS_X, 1024); /* points/g */ + input_set_abs_params(input_dev, ABS_Y, -2048, 2048, 0, 0); + input_abs_set_res(input_dev, ABS_Y, 1024); + input_set_abs_params(input_dev, ABS_Z, -2048, 2048, 0, 0); + input_abs_set_res(input_dev, ABS_Z, 1024); + __set_bit(INPUT_PROP_ACCELEROMETER, input_dev->propbit); + break; + case DTK: for (i = 0; i < 6; i++) __set_bit(BTN_0 + i, input_dev->keybit); @@ -2724,6 +2724,18 @@ static const struct wacom_features wacom_features_0xF6 = { "Wacom Cintiq 24HD touch", .type = WACOM_24HDT, /* Touch */ .oVid = USB_VENDOR_ID_WACOM, .oPid = 0xf8, .touch_max = 10, .check_for_hid_type = true, .hid_type = HID_TYPE_USBNONE }; +static const struct wacom_features wacom_features_0x32A = + { "Wacom Cintiq 27QHD", 119740, 67520, 2047, + 63, WACOM_27QHD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, + WACOM_27QHD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES }; +static const struct wacom_features wacom_features_0x32B = + { "Wacom Cintiq 27QHD touch", 119740, 67520, 2047, 63, + WACOM_27QHD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, + WACOM_CINTIQ_OFFSET, WACOM_CINTIQ_OFFSET, + .oVid = USB_VENDOR_ID_WACOM, .oPid = 0x32C }; +static const struct wacom_features wacom_features_0x32C = + { "Wacom Cintiq 27QHD touch", .type = WACOM_27QHDT, + .oVid = USB_VENDOR_ID_WACOM, .oPid = 0x32B, .touch_max = 10 }; static const struct wacom_features wacom_features_0x3F = { "Wacom Cintiq 21UX", 87200, 65600, 1023, 63, CINTIQ, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES }; @@ -3090,6 +3102,9 @@ const struct hid_device_id wacom_ids[] = { { USB_DEVICE_WACOM(0x315) }, { USB_DEVICE_WACOM(0x317) }, { USB_DEVICE_WACOM(0x323) }, + { USB_DEVICE_WACOM(0x32A) }, + { USB_DEVICE_WACOM(0x32B) }, + { USB_DEVICE_WACOM(0x32C) }, { USB_DEVICE_WACOM(0x32F) }, { USB_DEVICE_WACOM(0x4001) }, { USB_DEVICE_WACOM(0x4004) }, diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h index bfad815cda8..021ee1c1980 100644 --- a/drivers/hid/wacom_wac.h +++ b/drivers/hid/wacom_wac.h @@ -10,9 +10,10 @@ #define WACOM_WAC_H #include <linux/types.h> +#include <linux/hid.h> /* maximum packet length for USB devices */ -#define WACOM_PKGLEN_MAX 68 +#define WACOM_PKGLEN_MAX 192 #define WACOM_NAME_MAX 64 @@ -36,6 +37,7 @@ /* wacom data size per MT contact */ #define WACOM_BYTES_PER_MT_PACKET 11 #define WACOM_BYTES_PER_24HDT_PACKET 14 +#define WACOM_BYTES_PER_QHDTHID_PACKET 6 /* device IDs */ #define STYLUS_DEVICE_ID 0x02 @@ -57,6 +59,8 @@ #define WACOM_REPORT_TPCMT 13 #define WACOM_REPORT_TPCMT2 3 #define WACOM_REPORT_TPCHID 15 +#define WACOM_REPORT_CINTIQ 16 +#define WACOM_REPORT_CINTIQPAD 17 #define WACOM_REPORT_TPCST 16 #define WACOM_REPORT_DTUS 17 #define WACOM_REPORT_TPC1FGE 18 @@ -71,6 +75,14 @@ #define WACOM_QUIRK_MONITOR 0x0008 #define WACOM_QUIRK_BATTERY 0x0010 +#define WACOM_PEN_FIELD(f) (((f)->logical == HID_DG_STYLUS) || \ + ((f)->physical == HID_DG_STYLUS) || \ + ((f)->physical == HID_DG_PEN) || \ + ((f)->application == HID_DG_PEN)) +#define WACOM_FINGER_FIELD(f) (((f)->logical == HID_DG_FINGER) || \ + ((f)->physical == HID_DG_FINGER) || \ + ((f)->application == HID_DG_TOUCHSCREEN)) + enum { PENPARTNER = 0, GRAPHIRE, @@ -100,6 +112,7 @@ enum { WACOM_22HD, DTK, WACOM_24HD, + WACOM_27QHD, CINTIQ_HYBRID, CINTIQ, WACOM_BEE, @@ -108,6 +121,7 @@ enum { WIRELESS, BAMBOO_PT, WACOM_24HDT, + WACOM_27QHDT, TABLETPC, /* add new TPC below */ TABLETPCE, TABLETPC2FG, @@ -180,6 +194,7 @@ struct wacom_wac { int tool[2]; int id[2]; __u32 serial[2]; + bool reporting_data; struct wacom_features features; struct wacom_shared *shared; struct input_dev *input; diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 4d6b26979fb..bb3725b672c 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -861,8 +861,8 @@ static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx) break; case ACPI_RESOURCE_TYPE_ADDRESS64: - hyperv_mmio.start = res->data.address64.minimum; - hyperv_mmio.end = res->data.address64.maximum; + hyperv_mmio.start = res->data.address64.address.minimum; + hyperv_mmio.end = res->data.address64.address.maximum; break; } diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index a7de26d1ac8..d931cbbed24 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -1389,6 +1389,7 @@ config SENSORS_ADS1015 config SENSORS_ADS7828 tristate "Texas Instruments ADS7828 and compatibles" depends on I2C + select REGMAP_I2C help If you say yes here you get support for Texas Instruments ADS7828 and ADS7830 8-channel A/D converters. ADS7828 resolution is 12-bit, while @@ -1430,8 +1431,8 @@ config SENSORS_INA2XX tristate "Texas Instruments INA219 and compatibles" depends on I2C help - If you say yes here you get support for INA219, INA220, INA226, and - INA230 power monitor chips. + If you say yes here you get support for INA219, INA220, INA226, + INA230, and INA231 power monitor chips. The INA2xx driver is configured for the default configuration of the part as described in the datasheet. diff --git a/drivers/hwmon/abx500.c b/drivers/hwmon/abx500.c index 13875968c84..6cb89c0ebab 100644 --- a/drivers/hwmon/abx500.c +++ b/drivers/hwmon/abx500.c @@ -221,7 +221,7 @@ static ssize_t show_min(struct device *dev, struct abx500_temp *data = dev_get_drvdata(dev); struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); - return sprintf(buf, "%ld\n", data->min[attr->index]); + return sprintf(buf, "%lu\n", data->min[attr->index]); } static ssize_t show_max(struct device *dev, @@ -230,7 +230,7 @@ static ssize_t show_max(struct device *dev, struct abx500_temp *data = dev_get_drvdata(dev); struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); - return sprintf(buf, "%ld\n", data->max[attr->index]); + return sprintf(buf, "%lu\n", data->max[attr->index]); } static ssize_t show_max_hyst(struct device *dev, @@ -239,7 +239,7 @@ static ssize_t show_max_hyst(struct device *dev, struct abx500_temp *data = dev_get_drvdata(dev); struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); - return sprintf(buf, "%ld\n", data->max_hyst[attr->index]); + return sprintf(buf, "%lu\n", data->max_hyst[attr->index]); } static ssize_t show_min_alarm(struct device *dev, diff --git a/drivers/hwmon/ad7314.c b/drivers/hwmon/ad7314.c index f4f9b219bf1..11955467fc0 100644 --- a/drivers/hwmon/ad7314.c +++ b/drivers/hwmon/ad7314.c @@ -16,6 +16,7 @@ #include <linux/err.h> #include <linux/hwmon.h> #include <linux/hwmon-sysfs.h> +#include <linux/bitops.h> /* * AD7314 temperature masks @@ -67,7 +68,7 @@ static ssize_t ad7314_show_temperature(struct device *dev, switch (spi_get_device_id(chip->spi_dev)->driver_data) { case ad7314: data = (ret & AD7314_TEMP_MASK) >> AD7314_TEMP_SHIFT; - data = (data << 6) >> 6; + data = sign_extend32(data, 9); return sprintf(buf, "%d\n", 250 * data); case adt7301: @@ -78,7 +79,7 @@ static ssize_t ad7314_show_temperature(struct device *dev, * register. 1lsb - 31.25 milli degrees centigrade */ data = ret & ADT7301_TEMP_MASK; - data = (data << 2) >> 2; + data = sign_extend32(data, 13); return sprintf(buf, "%d\n", DIV_ROUND_CLOSEST(data * 3125, 100)); diff --git a/drivers/hwmon/adc128d818.c b/drivers/hwmon/adc128d818.c index 0625e50d7a6..ad2b47e4034 100644 --- a/drivers/hwmon/adc128d818.c +++ b/drivers/hwmon/adc128d818.c @@ -27,6 +27,7 @@ #include <linux/err.h> #include <linux/regulator/consumer.h> #include <linux/mutex.h> +#include <linux/bitops.h> /* Addresses to scan * The chip also supports addresses 0x35..0x37. Don't scan those addresses @@ -189,7 +190,7 @@ static ssize_t adc128_show_temp(struct device *dev, if (IS_ERR(data)) return PTR_ERR(data); - temp = (data->temp[index] << 7) >> 7; /* sign extend */ + temp = sign_extend32(data->temp[index], 8); return sprintf(buf, "%d\n", temp * 500);/* 0.5 degrees C resolution */ } diff --git a/drivers/hwmon/ads7828.c b/drivers/hwmon/ads7828.c index a622d40eec1..bce4e9ff21b 100644 --- a/drivers/hwmon/ads7828.c +++ b/drivers/hwmon/ads7828.c @@ -30,14 +30,12 @@ #include <linux/hwmon-sysfs.h> #include <linux/i2c.h> #include <linux/init.h> -#include <linux/jiffies.h> #include <linux/module.h> -#include <linux/mutex.h> #include <linux/platform_data/ads7828.h> +#include <linux/regmap.h> #include <linux/slab.h> /* The ADS7828 registers */ -#define ADS7828_NCH 8 /* 8 channels supported */ #define ADS7828_CMD_SD_SE 0x80 /* Single ended inputs */ #define ADS7828_CMD_PD1 0x04 /* Internal vref OFF && A/D ON */ #define ADS7828_CMD_PD3 0x0C /* Internal vref ON && A/D ON */ @@ -50,17 +48,9 @@ enum ads7828_chips { ads7828, ads7830 }; /* Client specific data */ struct ads7828_data { - struct i2c_client *client; - struct mutex update_lock; /* Mutex protecting updates */ - unsigned long last_updated; /* Last updated time (in jiffies) */ - u16 adc_input[ADS7828_NCH]; /* ADS7828_NCH samples */ - bool valid; /* Validity flag */ - bool diff_input; /* Differential input */ - bool ext_vref; /* External voltage reference */ - unsigned int vref_mv; /* voltage reference value */ + struct regmap *regmap; u8 cmd_byte; /* Command byte without channel bits */ unsigned int lsb_resol; /* Resolution of the ADC sample LSB */ - s32 (*read_channel)(const struct i2c_client *client, u8 command); }; /* Command byte C2,C1,C0 - see datasheet */ @@ -69,42 +59,22 @@ static inline u8 ads7828_cmd_byte(u8 cmd, int ch) return cmd | (((ch >> 1) | (ch & 0x01) << 2) << 4); } -/* Update data for the device (all 8 channels) */ -static struct ads7828_data *ads7828_update_device(struct device *dev) -{ - struct ads7828_data *data = dev_get_drvdata(dev); - struct i2c_client *client = data->client; - - mutex_lock(&data->update_lock); - - if (time_after(jiffies, data->last_updated + HZ + HZ / 2) - || !data->valid) { - unsigned int ch; - dev_dbg(&client->dev, "Starting ads7828 update\n"); - - for (ch = 0; ch < ADS7828_NCH; ch++) { - u8 cmd = ads7828_cmd_byte(data->cmd_byte, ch); - data->adc_input[ch] = data->read_channel(client, cmd); - } - data->last_updated = jiffies; - data->valid = true; - } - - mutex_unlock(&data->update_lock); - - return data; -} - /* sysfs callback function */ static ssize_t ads7828_show_in(struct device *dev, struct device_attribute *da, char *buf) { struct sensor_device_attribute *attr = to_sensor_dev_attr(da); - struct ads7828_data *data = ads7828_update_device(dev); - unsigned int value = DIV_ROUND_CLOSEST(data->adc_input[attr->index] * - data->lsb_resol, 1000); + struct ads7828_data *data = dev_get_drvdata(dev); + u8 cmd = ads7828_cmd_byte(data->cmd_byte, attr->index); + unsigned int regval; + int err; - return sprintf(buf, "%d\n", value); + err = regmap_read(data->regmap, cmd, ®val); + if (err < 0) + return err; + + return sprintf(buf, "%d\n", + DIV_ROUND_CLOSEST(regval * data->lsb_resol, 1000)); } static SENSOR_DEVICE_ATTR(in0_input, S_IRUGO, ads7828_show_in, NULL, 0); @@ -130,6 +100,16 @@ static struct attribute *ads7828_attrs[] = { ATTRIBUTE_GROUPS(ads7828); +static const struct regmap_config ads2828_regmap_config = { + .reg_bits = 8, + .val_bits = 16, +}; + +static const struct regmap_config ads2830_regmap_config = { + .reg_bits = 8, + .val_bits = 8, +}; + static int ads7828_probe(struct i2c_client *client, const struct i2c_device_id *id) { @@ -137,42 +117,40 @@ static int ads7828_probe(struct i2c_client *client, struct ads7828_platform_data *pdata = dev_get_platdata(dev); struct ads7828_data *data; struct device *hwmon_dev; + unsigned int vref_mv = ADS7828_INT_VREF_MV; + bool diff_input = false; + bool ext_vref = false; data = devm_kzalloc(dev, sizeof(struct ads7828_data), GFP_KERNEL); if (!data) return -ENOMEM; if (pdata) { - data->diff_input = pdata->diff_input; - data->ext_vref = pdata->ext_vref; - if (data->ext_vref) - data->vref_mv = pdata->vref_mv; + diff_input = pdata->diff_input; + ext_vref = pdata->ext_vref; + if (ext_vref && pdata->vref_mv) + vref_mv = pdata->vref_mv; } - /* Bound Vref with min/max values if it was provided */ - if (data->vref_mv) - data->vref_mv = clamp_val(data->vref_mv, - ADS7828_EXT_VREF_MV_MIN, - ADS7828_EXT_VREF_MV_MAX); - else - data->vref_mv = ADS7828_INT_VREF_MV; + /* Bound Vref with min/max values */ + vref_mv = clamp_val(vref_mv, ADS7828_EXT_VREF_MV_MIN, + ADS7828_EXT_VREF_MV_MAX); /* ADS7828 uses 12-bit samples, while ADS7830 is 8-bit */ if (id->driver_data == ads7828) { - data->lsb_resol = DIV_ROUND_CLOSEST(data->vref_mv * 1000, 4096); - data->read_channel = i2c_smbus_read_word_swapped; + data->lsb_resol = DIV_ROUND_CLOSEST(vref_mv * 1000, 4096); + data->regmap = devm_regmap_init_i2c(client, + &ads2828_regmap_config); } else { - data->lsb_resol = DIV_ROUND_CLOSEST(data->vref_mv * 1000, 256); - data->read_channel = i2c_smbus_read_byte_data; + data->lsb_resol = DIV_ROUND_CLOSEST(vref_mv * 1000, 256); + data->regmap = devm_regmap_init_i2c(client, + &ads2830_regmap_config); } - data->cmd_byte = data->ext_vref ? ADS7828_CMD_PD1 : ADS7828_CMD_PD3; - if (!data->diff_input) + data->cmd_byte = ext_vref ? ADS7828_CMD_PD1 : ADS7828_CMD_PD3; + if (!diff_input) data->cmd_byte |= ADS7828_CMD_SD_SE; - data->client = client; - mutex_init(&data->update_lock); - hwmon_dev = devm_hwmon_device_register_with_groups(dev, client->name, data, ads7828_groups); diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c index e01feba909c..d1542b7d4bc 100644 --- a/drivers/hwmon/ina2xx.c +++ b/drivers/hwmon/ina2xx.c @@ -35,6 +35,7 @@ #include <linux/hwmon-sysfs.h> #include <linux/jiffies.h> #include <linux/of.h> +#include <linux/delay.h> #include <linux/platform_data/ina2xx.h> @@ -51,7 +52,6 @@ #define INA226_ALERT_LIMIT 0x07 #define INA226_DIE_ID 0xFF - /* register count */ #define INA219_REGISTERS 6 #define INA226_REGISTERS 8 @@ -64,6 +64,24 @@ /* worst case is 68.10 ms (~14.6Hz, ina219) */ #define INA2XX_CONVERSION_RATE 15 +#define INA2XX_MAX_DELAY 69 /* worst case delay in ms */ + +#define INA2XX_RSHUNT_DEFAULT 10000 + +/* bit mask for reading the averaging setting in the configuration register */ +#define INA226_AVG_RD_MASK 0x0E00 + +#define INA226_READ_AVG(reg) (((reg) & INA226_AVG_RD_MASK) >> 9) +#define INA226_SHIFT_AVG(val) ((val) << 9) + +/* common attrs, ina226 attrs and NULL */ +#define INA2XX_MAX_ATTRIBUTE_GROUPS 3 + +/* + * Both bus voltage and shunt voltage conversion times for ina226 are set + * to 0b0100 on POR, which translates to 2200 microseconds in total. + */ +#define INA226_TOTAL_CONV_TIME_DEFAULT 2200 enum ina2xx_ids { ina219, ina226 }; @@ -81,11 +99,16 @@ struct ina2xx_data { struct i2c_client *client; const struct ina2xx_config *config; + long rshunt; + u16 curr_config; + struct mutex update_lock; bool valid; unsigned long last_updated; + int update_interval; /* in jiffies */ int kind; + const struct attribute_group *groups[INA2XX_MAX_ATTRIBUTE_GROUPS]; u16 regs[INA2XX_MAX_REGISTERS]; }; @@ -110,34 +133,156 @@ static const struct ina2xx_config ina2xx_config[] = { }, }; -static struct ina2xx_data *ina2xx_update_device(struct device *dev) +/* + * Available averaging rates for ina226. The indices correspond with + * the bit values expected by the chip (according to the ina226 datasheet, + * table 3 AVG bit settings, found at + * http://www.ti.com/lit/ds/symlink/ina226.pdf. + */ +static const int ina226_avg_tab[] = { 1, 4, 16, 64, 128, 256, 512, 1024 }; + +static int ina226_avg_bits(int avg) +{ + int i; + + /* Get the closest average from the tab. */ + for (i = 0; i < ARRAY_SIZE(ina226_avg_tab) - 1; i++) { + if (avg <= (ina226_avg_tab[i] + ina226_avg_tab[i + 1]) / 2) + break; + } + + return i; /* Return 0b0111 for values greater than 1024. */ +} + +static int ina226_reg_to_interval(u16 config) +{ + int avg = ina226_avg_tab[INA226_READ_AVG(config)]; + + /* + * Multiply the total conversion time by the number of averages. + * Return the result in milliseconds. + */ + return DIV_ROUND_CLOSEST(avg * INA226_TOTAL_CONV_TIME_DEFAULT, 1000); +} + +static u16 ina226_interval_to_reg(int interval, u16 config) +{ + int avg, avg_bits; + + avg = DIV_ROUND_CLOSEST(interval * 1000, + INA226_TOTAL_CONV_TIME_DEFAULT); + avg_bits = ina226_avg_bits(avg); + + return (config & ~INA226_AVG_RD_MASK) | INA226_SHIFT_AVG(avg_bits); +} + +static void ina226_set_update_interval(struct ina2xx_data *data) +{ + int ms; + + ms = ina226_reg_to_interval(data->curr_config); + data->update_interval = msecs_to_jiffies(ms); +} + +static int ina2xx_calibrate(struct ina2xx_data *data) +{ + u16 val = DIV_ROUND_CLOSEST(data->config->calibration_factor, + data->rshunt); + + return i2c_smbus_write_word_swapped(data->client, + INA2XX_CALIBRATION, val); +} + +/* + * Initialize the configuration and calibration registers. + */ +static int ina2xx_init(struct ina2xx_data *data) { - struct ina2xx_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; - struct ina2xx_data *ret = data; + int ret; - mutex_lock(&data->update_lock); + /* device configuration */ + ret = i2c_smbus_write_word_swapped(client, INA2XX_CONFIG, + data->curr_config); + if (ret < 0) + return ret; - if (time_after(jiffies, data->last_updated + - HZ / INA2XX_CONVERSION_RATE) || !data->valid) { + /* + * Set current LSB to 1mA, shunt is in uOhms + * (equation 13 in datasheet). + */ + return ina2xx_calibrate(data); +} - int i; +static int ina2xx_do_update(struct device *dev) +{ + struct ina2xx_data *data = dev_get_drvdata(dev); + struct i2c_client *client = data->client; + int i, rv, retry; - dev_dbg(&client->dev, "Starting ina2xx update\n"); + dev_dbg(&client->dev, "Starting ina2xx update\n"); + for (retry = 5; retry; retry--) { /* Read all registers */ for (i = 0; i < data->config->registers; i++) { - int rv = i2c_smbus_read_word_swapped(client, i); - if (rv < 0) { - ret = ERR_PTR(rv); - goto abort; - } + rv = i2c_smbus_read_word_swapped(client, i); + if (rv < 0) + return rv; data->regs[i] = rv; } + + /* + * If the current value in the calibration register is 0, the + * power and current registers will also remain at 0. In case + * the chip has been reset let's check the calibration + * register and reinitialize if needed. + */ + if (data->regs[INA2XX_CALIBRATION] == 0) { + dev_warn(dev, "chip not calibrated, reinitializing\n"); + + rv = ina2xx_init(data); + if (rv < 0) + return rv; + + /* + * Let's make sure the power and current registers + * have been updated before trying again. + */ + msleep(INA2XX_MAX_DELAY); + continue; + } + data->last_updated = jiffies; data->valid = 1; + + return 0; } -abort: + + /* + * If we're here then although all write operations succeeded, the + * chip still returns 0 in the calibration register. Nothing more we + * can do here. + */ + dev_err(dev, "unable to reinitialize the chip\n"); + return -ENODEV; +} + +static struct ina2xx_data *ina2xx_update_device(struct device *dev) +{ + struct ina2xx_data *data = dev_get_drvdata(dev); + struct ina2xx_data *ret = data; + unsigned long after; + int rv; + + mutex_lock(&data->update_lock); + + after = data->last_updated + data->update_interval; + if (time_after(jiffies, after) || !data->valid) { + rv = ina2xx_do_update(dev); + if (rv < 0) + ret = ERR_PTR(rv); + } + mutex_unlock(&data->update_lock); return ret; } @@ -164,6 +309,10 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg) /* signed register, LSB=1mA (selected), in mA */ val = (s16)data->regs[reg]; break; + case INA2XX_CALIBRATION: + val = DIV_ROUND_CLOSEST(data->config->calibration_factor, + data->regs[reg]); + break; default: /* programmer goofed */ WARN_ON_ONCE(1); @@ -187,6 +336,85 @@ static ssize_t ina2xx_show_value(struct device *dev, ina2xx_get_value(data, attr->index)); } +static ssize_t ina2xx_set_shunt(struct device *dev, + struct device_attribute *da, + const char *buf, size_t count) +{ + struct ina2xx_data *data = ina2xx_update_device(dev); + unsigned long val; + int status; + + if (IS_ERR(data)) + return PTR_ERR(data); + + status = kstrtoul(buf, 10, &val); + if (status < 0) + return status; + + if (val == 0 || + /* Values greater than the calibration factor make no sense. */ + val > data->config->calibration_factor) + return -EINVAL; + + mutex_lock(&data->update_lock); + data->rshunt = val; + status = ina2xx_calibrate(data); + mutex_unlock(&data->update_lock); + if (status < 0) + return status; + + return count; +} + +static ssize_t ina226_set_interval(struct device *dev, + struct device_attribute *da, + const char *buf, size_t count) +{ + struct ina2xx_data *data = dev_get_drvdata(dev); + unsigned long val; + int status; + + status = kstrtoul(buf, 10, &val); + if (status < 0) + return status; + + if (val > INT_MAX || val == 0) + return -EINVAL; + + mutex_lock(&data->update_lock); + data->curr_config = ina226_interval_to_reg(val, + data->regs[INA2XX_CONFIG]); + status = i2c_smbus_write_word_swapped(data->client, + INA2XX_CONFIG, + data->curr_config); + + ina226_set_update_interval(data); + /* Make sure the next access re-reads all registers. */ + data->valid = 0; + mutex_unlock(&data->update_lock); + if (status < 0) + return status; + + return count; +} + +static ssize_t ina226_show_interval(struct device *dev, + struct device_attribute *da, char *buf) +{ + struct ina2xx_data *data = ina2xx_update_device(dev); + + if (IS_ERR(data)) + return PTR_ERR(data); + + /* + * We don't use data->update_interval here as we want to display + * the actual interval used by the chip and jiffies_to_msecs() + * doesn't seem to be accurate enough. + */ + return snprintf(buf, PAGE_SIZE, "%d\n", + ina226_reg_to_interval(data->regs[INA2XX_CONFIG])); +} + /* shunt voltage */ static SENSOR_DEVICE_ATTR(in0_input, S_IRUGO, ina2xx_show_value, NULL, INA2XX_SHUNT_VOLTAGE); @@ -203,15 +431,37 @@ static SENSOR_DEVICE_ATTR(curr1_input, S_IRUGO, ina2xx_show_value, NULL, static SENSOR_DEVICE_ATTR(power1_input, S_IRUGO, ina2xx_show_value, NULL, INA2XX_POWER); +/* shunt resistance */ +static SENSOR_DEVICE_ATTR(shunt_resistor, S_IRUGO | S_IWUSR, + ina2xx_show_value, ina2xx_set_shunt, + INA2XX_CALIBRATION); + +/* update interval (ina226 only) */ +static SENSOR_DEVICE_ATTR(update_interval, S_IRUGO | S_IWUSR, + ina226_show_interval, ina226_set_interval, 0); + /* pointers to created device attributes */ static struct attribute *ina2xx_attrs[] = { &sensor_dev_attr_in0_input.dev_attr.attr, &sensor_dev_attr_in1_input.dev_attr.attr, &sensor_dev_attr_curr1_input.dev_attr.attr, &sensor_dev_attr_power1_input.dev_attr.attr, + &sensor_dev_attr_shunt_resistor.dev_attr.attr, NULL, }; -ATTRIBUTE_GROUPS(ina2xx); + +static const struct attribute_group ina2xx_group = { + .attrs = ina2xx_attrs, +}; + +static struct attribute *ina226_attrs[] = { + &sensor_dev_attr_update_interval.dev_attr.attr, + NULL, +}; + +static const struct attribute_group ina226_group = { + .attrs = ina226_attrs, +}; static int ina2xx_probe(struct i2c_client *client, const struct i2c_device_id *id) @@ -221,9 +471,8 @@ static int ina2xx_probe(struct i2c_client *client, struct device *dev = &client->dev; struct ina2xx_data *data; struct device *hwmon_dev; - long shunt = 10000; /* default shunt value 10mOhms */ u32 val; - int ret; + int ret, group = 0; if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_WORD_DATA)) return -ENODEV; @@ -234,50 +483,52 @@ static int ina2xx_probe(struct i2c_client *client, if (dev_get_platdata(dev)) { pdata = dev_get_platdata(dev); - shunt = pdata->shunt_uohms; + data->rshunt = pdata->shunt_uohms; } else if (!of_property_read_u32(dev->of_node, "shunt-resistor", &val)) { - shunt = val; + data->rshunt = val; + } else { + data->rshunt = INA2XX_RSHUNT_DEFAULT; } - if (shunt <= 0) - return -ENODEV; - /* set the device type */ data->kind = id->driver_data; data->config = &ina2xx_config[data->kind]; - - /* device configuration */ - ret = i2c_smbus_write_word_swapped(client, INA2XX_CONFIG, - data->config->config_default); - if (ret < 0) { - dev_err(dev, - "error writing to the config register: %d", ret); - return -ENODEV; - } + data->curr_config = data->config->config_default; + data->client = client; /* - * Set current LSB to 1mA, shunt is in uOhms - * (equation 13 in datasheet). + * Ina226 has a variable update_interval. For ina219 we + * use a constant value. */ - ret = i2c_smbus_write_word_swapped(client, INA2XX_CALIBRATION, - data->config->calibration_factor / shunt); + if (data->kind == ina226) + ina226_set_update_interval(data); + else + data->update_interval = HZ / INA2XX_CONVERSION_RATE; + + if (data->rshunt <= 0 || + data->rshunt > data->config->calibration_factor) + return -ENODEV; + + ret = ina2xx_init(data); if (ret < 0) { - dev_err(dev, - "error writing to the calibration register: %d", ret); + dev_err(dev, "error configuring the device: %d\n", ret); return -ENODEV; } - data->client = client; mutex_init(&data->update_lock); + data->groups[group++] = &ina2xx_group; + if (data->kind == ina226) + data->groups[group++] = &ina226_group; + hwmon_dev = devm_hwmon_device_register_with_groups(dev, client->name, - data, ina2xx_groups); + data, data->groups); if (IS_ERR(hwmon_dev)) return PTR_ERR(hwmon_dev); dev_info(dev, "power monitor %s (Rshunt = %li uOhm)\n", - id->name, shunt); + id->name, data->rshunt); return 0; } @@ -287,6 +538,7 @@ static const struct i2c_device_id ina2xx_id[] = { { "ina220", ina219 }, { "ina226", ina226 }, { "ina230", ina226 }, + { "ina231", ina226 }, { } }; MODULE_DEVICE_TABLE(i2c, ina2xx_id); diff --git a/drivers/hwmon/jc42.c b/drivers/hwmon/jc42.c index 388f8bcd898..996bdfd5cf2 100644 --- a/drivers/hwmon/jc42.c +++ b/drivers/hwmon/jc42.c @@ -201,7 +201,7 @@ struct jc42_data { #define JC42_TEMP_MIN 0 #define JC42_TEMP_MAX 125000 -static u16 jc42_temp_to_reg(int temp, bool extended) +static u16 jc42_temp_to_reg(long temp, bool extended) { int ntemp = clamp_val(temp, extended ? JC42_TEMP_MIN_EXTENDED : @@ -213,11 +213,7 @@ static u16 jc42_temp_to_reg(int temp, bool extended) static int jc42_temp_from_reg(s16 reg) { - reg &= 0x1fff; - - /* sign extend register */ - if (reg & 0x1000) - reg |= 0xf000; + reg = sign_extend32(reg, 12); /* convert from 0.0625 to 0.001 resolution */ return reg * 125 / 2; @@ -308,15 +304,18 @@ static ssize_t set_temp_crit_hyst(struct device *dev, const char *buf, size_t count) { struct jc42_data *data = dev_get_drvdata(dev); - unsigned long val; + long val; int diff, hyst; int err; int ret = count; - if (kstrtoul(buf, 10, &val) < 0) + if (kstrtol(buf, 10, &val) < 0) return -EINVAL; + val = clamp_val(val, (data->extended ? JC42_TEMP_MIN_EXTENDED : + JC42_TEMP_MIN) - 6000, JC42_TEMP_MAX); diff = jc42_temp_from_reg(data->temp[t_crit]) - val; + hyst = 0; if (diff > 0) { if (diff < 2250) diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c index ec5678289e4..55765790907 100644 --- a/drivers/hwmon/nct7802.c +++ b/drivers/hwmon/nct7802.c @@ -779,7 +779,7 @@ static bool nct7802_regmap_is_volatile(struct device *dev, unsigned int reg) return reg != REG_BANK && reg <= 0x20; } -static struct regmap_config nct7802_regmap_config = { +static const struct regmap_config nct7802_regmap_config = { .reg_bits = 8, .val_bits = 8, .cache_type = REGCACHE_RBTREE, diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c index ba9f478f64e..9da2735f142 100644 --- a/drivers/hwmon/tmp102.c +++ b/drivers/hwmon/tmp102.c @@ -253,7 +253,7 @@ static int tmp102_remove(struct i2c_client *client) return 0; } -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static int tmp102_suspend(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); @@ -279,17 +279,10 @@ static int tmp102_resume(struct device *dev) config &= ~TMP102_CONF_SD; return i2c_smbus_write_word_swapped(client, TMP102_CONF_REG, config); } - -static const struct dev_pm_ops tmp102_dev_pm_ops = { - .suspend = tmp102_suspend, - .resume = tmp102_resume, -}; - -#define TMP102_DEV_PM_OPS (&tmp102_dev_pm_ops) -#else -#define TMP102_DEV_PM_OPS NULL #endif /* CONFIG_PM */ +static SIMPLE_DEV_PM_OPS(tmp102_dev_pm_ops, tmp102_suspend, tmp102_resume); + static const struct i2c_device_id tmp102_id[] = { { "tmp102", 0 }, { } @@ -298,7 +291,7 @@ MODULE_DEVICE_TABLE(i2c, tmp102_id); static struct i2c_driver tmp102_driver = { .driver.name = DRIVER_NAME, - .driver.pm = TMP102_DEV_PM_OPS, + .driver.pm = &tmp102_dev_pm_ops, .probe = tmp102_probe, .remove = tmp102_remove, .id_table = tmp102_id, diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h index b716b081564..643c08a025a 100644 --- a/drivers/infiniband/core/uverbs.h +++ b/drivers/infiniband/core/uverbs.h @@ -258,6 +258,5 @@ IB_UVERBS_DECLARE_CMD(close_xrcd); IB_UVERBS_DECLARE_EX_CMD(create_flow); IB_UVERBS_DECLARE_EX_CMD(destroy_flow); -IB_UVERBS_DECLARE_EX_CMD(query_device); #endif /* UVERBS_H */ diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 532d8eba8b0..b7943ff16ed 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -400,52 +400,6 @@ err: return ret; } -static void copy_query_dev_fields(struct ib_uverbs_file *file, - struct ib_uverbs_query_device_resp *resp, - struct ib_device_attr *attr) -{ - resp->fw_ver = attr->fw_ver; - resp->node_guid = file->device->ib_dev->node_guid; - resp->sys_image_guid = attr->sys_image_guid; - resp->max_mr_size = attr->max_mr_size; - resp->page_size_cap = attr->page_size_cap; - resp->vendor_id = attr->vendor_id; - resp->vendor_part_id = attr->vendor_part_id; - resp->hw_ver = attr->hw_ver; - resp->max_qp = attr->max_qp; - resp->max_qp_wr = attr->max_qp_wr; - resp->device_cap_flags = attr->device_cap_flags; - resp->max_sge = attr->max_sge; - resp->max_sge_rd = attr->max_sge_rd; - resp->max_cq = attr->max_cq; - resp->max_cqe = attr->max_cqe; - resp->max_mr = attr->max_mr; - resp->max_pd = attr->max_pd; - resp->max_qp_rd_atom = attr->max_qp_rd_atom; - resp->max_ee_rd_atom = attr->max_ee_rd_atom; - resp->max_res_rd_atom = attr->max_res_rd_atom; - resp->max_qp_init_rd_atom = attr->max_qp_init_rd_atom; - resp->max_ee_init_rd_atom = attr->max_ee_init_rd_atom; - resp->atomic_cap = attr->atomic_cap; - resp->max_ee = attr->max_ee; - resp->max_rdd = attr->max_rdd; - resp->max_mw = attr->max_mw; - resp->max_raw_ipv6_qp = attr->max_raw_ipv6_qp; - resp->max_raw_ethy_qp = attr->max_raw_ethy_qp; - resp->max_mcast_grp = attr->max_mcast_grp; - resp->max_mcast_qp_attach = attr->max_mcast_qp_attach; - resp->max_total_mcast_qp_attach = attr->max_total_mcast_qp_attach; - resp->max_ah = attr->max_ah; - resp->max_fmr = attr->max_fmr; - resp->max_map_per_fmr = attr->max_map_per_fmr; - resp->max_srq = attr->max_srq; - resp->max_srq_wr = attr->max_srq_wr; - resp->max_srq_sge = attr->max_srq_sge; - resp->max_pkeys = attr->max_pkeys; - resp->local_ca_ack_delay = attr->local_ca_ack_delay; - resp->phys_port_cnt = file->device->ib_dev->phys_port_cnt; -} - ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file, const char __user *buf, int in_len, int out_len) @@ -466,7 +420,47 @@ ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file, return ret; memset(&resp, 0, sizeof resp); - copy_query_dev_fields(file, &resp, &attr); + + resp.fw_ver = attr.fw_ver; + resp.node_guid = file->device->ib_dev->node_guid; + resp.sys_image_guid = attr.sys_image_guid; + resp.max_mr_size = attr.max_mr_size; + resp.page_size_cap = attr.page_size_cap; + resp.vendor_id = attr.vendor_id; + resp.vendor_part_id = attr.vendor_part_id; + resp.hw_ver = attr.hw_ver; + resp.max_qp = attr.max_qp; + resp.max_qp_wr = attr.max_qp_wr; + resp.device_cap_flags = attr.device_cap_flags; + resp.max_sge = attr.max_sge; + resp.max_sge_rd = attr.max_sge_rd; + resp.max_cq = attr.max_cq; + resp.max_cqe = attr.max_cqe; + resp.max_mr = attr.max_mr; + resp.max_pd = attr.max_pd; + resp.max_qp_rd_atom = attr.max_qp_rd_atom; + resp.max_ee_rd_atom = attr.max_ee_rd_atom; + resp.max_res_rd_atom = attr.max_res_rd_atom; + resp.max_qp_init_rd_atom = attr.max_qp_init_rd_atom; + resp.max_ee_init_rd_atom = attr.max_ee_init_rd_atom; + resp.atomic_cap = attr.atomic_cap; + resp.max_ee = attr.max_ee; + resp.max_rdd = attr.max_rdd; + resp.max_mw = attr.max_mw; + resp.max_raw_ipv6_qp = attr.max_raw_ipv6_qp; + resp.max_raw_ethy_qp = attr.max_raw_ethy_qp; + resp.max_mcast_grp = attr.max_mcast_grp; + resp.max_mcast_qp_attach = attr.max_mcast_qp_attach; + resp.max_total_mcast_qp_attach = attr.max_total_mcast_qp_attach; + resp.max_ah = attr.max_ah; + resp.max_fmr = attr.max_fmr; + resp.max_map_per_fmr = attr.max_map_per_fmr; + resp.max_srq = attr.max_srq; + resp.max_srq_wr = attr.max_srq_wr; + resp.max_srq_sge = attr.max_srq_sge; + resp.max_pkeys = attr.max_pkeys; + resp.local_ca_ack_delay = attr.local_ca_ack_delay; + resp.phys_port_cnt = file->device->ib_dev->phys_port_cnt; if (copy_to_user((void __user *) (unsigned long) cmd.response, &resp, sizeof resp)) @@ -3293,52 +3287,3 @@ ssize_t ib_uverbs_destroy_srq(struct ib_uverbs_file *file, return ret ? ret : in_len; } - -int ib_uverbs_ex_query_device(struct ib_uverbs_file *file, - struct ib_udata *ucore, - struct ib_udata *uhw) -{ - struct ib_uverbs_ex_query_device_resp resp; - struct ib_uverbs_ex_query_device cmd; - struct ib_device_attr attr; - struct ib_device *device; - int err; - - device = file->device->ib_dev; - if (ucore->inlen < sizeof(cmd)) - return -EINVAL; - - err = ib_copy_from_udata(&cmd, ucore, sizeof(cmd)); - if (err) - return err; - - if (cmd.reserved) - return -EINVAL; - - err = device->query_device(device, &attr); - if (err) - return err; - - memset(&resp, 0, sizeof(resp)); - copy_query_dev_fields(file, &resp.base, &attr); - resp.comp_mask = 0; - -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - if (cmd.comp_mask & IB_USER_VERBS_EX_QUERY_DEVICE_ODP) { - resp.odp_caps.general_caps = attr.odp_caps.general_caps; - resp.odp_caps.per_transport_caps.rc_odp_caps = - attr.odp_caps.per_transport_caps.rc_odp_caps; - resp.odp_caps.per_transport_caps.uc_odp_caps = - attr.odp_caps.per_transport_caps.uc_odp_caps; - resp.odp_caps.per_transport_caps.ud_odp_caps = - attr.odp_caps.per_transport_caps.ud_odp_caps; - resp.comp_mask |= IB_USER_VERBS_EX_QUERY_DEVICE_ODP; - } -#endif - - err = ib_copy_to_udata(ucore, &resp, sizeof(resp)); - if (err) - return err; - - return 0; -} diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 8a87404e9c7..03bf81211a5 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1331,8 +1331,6 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) (1ull << IB_USER_VERBS_CMD_DESTROY_SRQ) | (1ull << IB_USER_VERBS_CMD_CREATE_XSRQ) | (1ull << IB_USER_VERBS_CMD_OPEN_QP); - dev->ib_dev.uverbs_ex_cmd_mask = - (1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE); dev->ib_dev.query_device = mlx5_ib_query_device; dev->ib_dev.query_port = mlx5_ib_query_port; diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 98024856df0..59de6364a91 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -4284,7 +4284,6 @@ static int alloc_hpet_msi(unsigned int irq, unsigned int id) } struct irq_remap_ops amd_iommu_irq_ops = { - .supported = amd_iommu_supported, .prepare = amd_iommu_prepare, .enable = amd_iommu_enable, .disable = amd_iommu_disable, diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index b0522f15730..9a20248e706 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -2014,9 +2014,6 @@ static bool detect_ivrs(void) /* Make sure ACS will be enabled during PCI probe */ pci_request_acs(); - if (!disable_irq_remap) - amd_iommu_irq_remap = true; - return true; } @@ -2123,12 +2120,14 @@ static int __init iommu_go_to_state(enum iommu_init_state state) #ifdef CONFIG_IRQ_REMAP int __init amd_iommu_prepare(void) { - return iommu_go_to_state(IOMMU_ACPI_FINISHED); -} + int ret; -int __init amd_iommu_supported(void) -{ - return amd_iommu_irq_remap ? 1 : 0; + amd_iommu_irq_remap = true; + + ret = iommu_go_to_state(IOMMU_ACPI_FINISHED); + if (ret) + return ret; + return amd_iommu_irq_remap ? 0 : -ENODEV; } int __init amd_iommu_enable(void) diff --git a/drivers/iommu/amd_iommu_proto.h b/drivers/iommu/amd_iommu_proto.h index 95ed6deae47..861af9d8338 100644 --- a/drivers/iommu/amd_iommu_proto.h +++ b/drivers/iommu/amd_iommu_proto.h @@ -33,7 +33,6 @@ extern void amd_iommu_init_notifier(void); extern void amd_iommu_init_api(void); /* Needed for interrupt remapping */ -extern int amd_iommu_supported(void); extern int amd_iommu_prepare(void); extern int amd_iommu_enable(void); extern void amd_iommu_disable(void); diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index a55b207b942..14de1ab223c 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -32,8 +32,9 @@ struct hpet_scope { }; #define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0) -#define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8) +#define IRTE_DEST(dest) ((eim_mode) ? dest : dest << 8) +static int __read_mostly eim_mode; static struct ioapic_scope ir_ioapic[MAX_IO_APICS]; static struct hpet_scope ir_hpet[MAX_HPET_TBS]; @@ -481,11 +482,11 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) if (iommu->ir_table) return 0; - ir_table = kzalloc(sizeof(struct ir_table), GFP_ATOMIC); + ir_table = kzalloc(sizeof(struct ir_table), GFP_KERNEL); if (!ir_table) return -ENOMEM; - pages = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO, + pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO, INTR_REMAP_PAGE_ORDER); if (!pages) { @@ -566,13 +567,27 @@ static int __init dmar_x2apic_optout(void) return dmar->flags & DMAR_X2APIC_OPT_OUT; } -static int __init intel_irq_remapping_supported(void) +static void __init intel_cleanup_irq_remapping(void) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu; + + for_each_iommu(iommu, drhd) { + if (ecap_ir_support(iommu->ecap)) { + iommu_disable_irq_remapping(iommu); + intel_teardown_irq_remapping(iommu); + } + } + + if (x2apic_supported()) + pr_warn("Failed to enable irq remapping. You are vulnerable to irq-injection attacks.\n"); +} + +static int __init intel_prepare_irq_remapping(void) { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; - if (disable_irq_remap) - return 0; if (irq_remap_broken) { printk(KERN_WARNING "This system BIOS has enabled interrupt remapping\n" @@ -581,38 +596,45 @@ static int __init intel_irq_remapping_supported(void) "interrupt remapping is being disabled. Please\n" "contact your BIOS vendor for an update\n"); add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); - disable_irq_remap = 1; - return 0; + return -ENODEV; } + if (dmar_table_init() < 0) + return -ENODEV; + if (!dmar_ir_support()) - return 0; + return -ENODEV; + + if (parse_ioapics_under_ir() != 1) { + printk(KERN_INFO "Not enabling interrupt remapping\n"); + goto error; + } + /* First make sure all IOMMUs support IRQ remapping */ for_each_iommu(iommu, drhd) if (!ecap_ir_support(iommu->ecap)) - return 0; + goto error; - return 1; + /* Do the allocations early */ + for_each_iommu(iommu, drhd) + if (intel_setup_irq_remapping(iommu)) + goto error; + + return 0; + +error: + intel_cleanup_irq_remapping(); + return -ENODEV; } static int __init intel_enable_irq_remapping(void) { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; - bool x2apic_present; int setup = 0; int eim = 0; - x2apic_present = x2apic_supported(); - - if (parse_ioapics_under_ir() != 1) { - printk(KERN_INFO "Not enable interrupt remapping\n"); - goto error; - } - - if (x2apic_present) { - pr_info("Queued invalidation will be enabled to support x2apic and Intr-remapping.\n"); - + if (x2apic_supported()) { eim = !dmar_x2apic_optout(); if (!eim) printk(KERN_WARNING @@ -646,16 +668,15 @@ static int __init intel_enable_irq_remapping(void) /* * check for the Interrupt-remapping support */ - for_each_iommu(iommu, drhd) { - if (!ecap_ir_support(iommu->ecap)) - continue; - + for_each_iommu(iommu, drhd) if (eim && !ecap_eim_support(iommu->ecap)) { printk(KERN_INFO "DRHD %Lx: EIM not supported by DRHD, " " ecap %Lx\n", drhd->reg_base_addr, iommu->ecap); - goto error; + eim = 0; } - } + eim_mode = eim; + if (eim) + pr_info("Queued invalidation will be enabled to support x2apic and Intr-remapping.\n"); /* * Enable queued invalidation for all the DRHD's. @@ -675,12 +696,6 @@ static int __init intel_enable_irq_remapping(void) * Setup Interrupt-remapping for all the DRHD's now. */ for_each_iommu(iommu, drhd) { - if (!ecap_ir_support(iommu->ecap)) - continue; - - if (intel_setup_irq_remapping(iommu)) - goto error; - iommu_set_irq_remapping(iommu, eim); setup = 1; } @@ -702,15 +717,7 @@ static int __init intel_enable_irq_remapping(void) return eim ? IRQ_REMAP_X2APIC_MODE : IRQ_REMAP_XAPIC_MODE; error: - for_each_iommu(iommu, drhd) - if (ecap_ir_support(iommu->ecap)) { - iommu_disable_irq_remapping(iommu); - intel_teardown_irq_remapping(iommu); - } - - if (x2apic_present) - pr_warn("Failed to enable irq remapping. You are vulnerable to irq-injection attacks.\n"); - + intel_cleanup_irq_remapping(); return -1; } @@ -1199,8 +1206,7 @@ static int intel_alloc_hpet_msi(unsigned int irq, unsigned int id) } struct irq_remap_ops intel_irq_remap_ops = { - .supported = intel_irq_remapping_supported, - .prepare = dmar_table_init, + .prepare = intel_prepare_irq_remapping, .enable = intel_enable_irq_remapping, .disable = disable_irq_remapping, .reenable = reenable_irq_remapping, diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index 89c4846683b..390079ee135 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -17,12 +17,11 @@ #include "irq_remapping.h" int irq_remapping_enabled; - -int disable_irq_remap; int irq_remap_broken; int disable_sourceid_checking; int no_x2apic_optout; +static int disable_irq_remap; static struct irq_remap_ops *remap_ops; static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec); @@ -194,45 +193,32 @@ static __init int setup_irqremap(char *str) } early_param("intremap", setup_irqremap); -void __init setup_irq_remapping_ops(void) -{ - remap_ops = &intel_irq_remap_ops; - -#ifdef CONFIG_AMD_IOMMU - if (amd_iommu_irq_ops.prepare() == 0) - remap_ops = &amd_iommu_irq_ops; -#endif -} - void set_irq_remapping_broken(void) { irq_remap_broken = 1; } -int irq_remapping_supported(void) +int __init irq_remapping_prepare(void) { if (disable_irq_remap) - return 0; - - if (!remap_ops || !remap_ops->supported) - return 0; - - return remap_ops->supported(); -} + return -ENOSYS; -int __init irq_remapping_prepare(void) -{ - if (!remap_ops || !remap_ops->prepare) - return -ENODEV; + if (intel_irq_remap_ops.prepare() == 0) + remap_ops = &intel_irq_remap_ops; + else if (IS_ENABLED(CONFIG_AMD_IOMMU) && + amd_iommu_irq_ops.prepare() == 0) + remap_ops = &amd_iommu_irq_ops; + else + return -ENOSYS; - return remap_ops->prepare(); + return 0; } int __init irq_remapping_enable(void) { int ret; - if (!remap_ops || !remap_ops->enable) + if (!remap_ops->enable) return -ENODEV; ret = remap_ops->enable(); @@ -245,22 +231,16 @@ int __init irq_remapping_enable(void) void irq_remapping_disable(void) { - if (!irq_remapping_enabled || - !remap_ops || - !remap_ops->disable) - return; - - remap_ops->disable(); + if (irq_remapping_enabled && remap_ops->disable) + remap_ops->disable(); } int irq_remapping_reenable(int mode) { - if (!irq_remapping_enabled || - !remap_ops || - !remap_ops->reenable) - return 0; + if (irq_remapping_enabled && remap_ops->reenable) + return remap_ops->reenable(mode); - return remap_ops->reenable(mode); + return 0; } int __init irq_remap_enable_fault_handling(void) @@ -268,7 +248,7 @@ int __init irq_remap_enable_fault_handling(void) if (!irq_remapping_enabled) return 0; - if (!remap_ops || !remap_ops->enable_faulting) + if (!remap_ops->enable_faulting) return -ENODEV; return remap_ops->enable_faulting(); @@ -279,7 +259,7 @@ int setup_ioapic_remapped_entry(int irq, unsigned int destination, int vector, struct io_apic_irq_attr *attr) { - if (!remap_ops || !remap_ops->setup_ioapic_entry) + if (!remap_ops->setup_ioapic_entry) return -ENODEV; return remap_ops->setup_ioapic_entry(irq, entry, destination, @@ -289,8 +269,7 @@ int setup_ioapic_remapped_entry(int irq, static int set_remapped_irq_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { - if (!config_enabled(CONFIG_SMP) || !remap_ops || - !remap_ops->set_affinity) + if (!config_enabled(CONFIG_SMP) || !remap_ops->set_affinity) return 0; return remap_ops->set_affinity(data, mask, force); @@ -300,10 +279,7 @@ void free_remapped_irq(int irq) { struct irq_cfg *cfg = irq_cfg(irq); - if (!remap_ops || !remap_ops->free_irq) - return; - - if (irq_remapped(cfg)) + if (irq_remapped(cfg) && remap_ops->free_irq) remap_ops->free_irq(irq); } @@ -315,13 +291,13 @@ void compose_remapped_msi_msg(struct pci_dev *pdev, if (!irq_remapped(cfg)) native_compose_msi_msg(pdev, irq, dest, msg, hpet_id); - else if (remap_ops && remap_ops->compose_msi_msg) + else if (remap_ops->compose_msi_msg) remap_ops->compose_msi_msg(pdev, irq, dest, msg, hpet_id); } static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec) { - if (!remap_ops || !remap_ops->msi_alloc_irq) + if (!remap_ops->msi_alloc_irq) return -ENODEV; return remap_ops->msi_alloc_irq(pdev, irq, nvec); @@ -330,7 +306,7 @@ static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec) static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq, int index, int sub_handle) { - if (!remap_ops || !remap_ops->msi_setup_irq) + if (!remap_ops->msi_setup_irq) return -ENODEV; return remap_ops->msi_setup_irq(pdev, irq, index, sub_handle); @@ -340,7 +316,7 @@ int setup_hpet_msi_remapped(unsigned int irq, unsigned int id) { int ret; - if (!remap_ops || !remap_ops->alloc_hpet_msi) + if (!remap_ops->alloc_hpet_msi) return -ENODEV; ret = remap_ops->alloc_hpet_msi(irq, id); diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h index fde250f86e6..c448eb48340 100644 --- a/drivers/iommu/irq_remapping.h +++ b/drivers/iommu/irq_remapping.h @@ -31,16 +31,12 @@ struct cpumask; struct pci_dev; struct msi_msg; -extern int disable_irq_remap; extern int irq_remap_broken; extern int disable_sourceid_checking; extern int no_x2apic_optout; extern int irq_remapping_enabled; struct irq_remap_ops { - /* Check whether Interrupt Remapping is supported */ - int (*supported)(void); - /* Initializes hardware and makes it ready for remapping interrupts */ int (*prepare)(void); @@ -89,7 +85,6 @@ extern struct irq_remap_ops amd_iommu_irq_ops; #else /* CONFIG_IRQ_REMAP */ #define irq_remapping_enabled 0 -#define disable_irq_remap 1 #define irq_remap_broken 0 #endif /* CONFIG_IRQ_REMAP */ diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 2b0468e3df6..56b96c63dc4 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -37,6 +37,7 @@ static struct irq_domain *gic_irq_domain; static int gic_shared_intrs; static int gic_vpes; static unsigned int gic_cpu_pin; +static unsigned int timer_cpu_pin; static struct irq_chip gic_level_irq_controller, gic_edge_irq_controller; static void __gic_irq_dispatch(void); @@ -616,6 +617,8 @@ static int gic_local_irq_domain_map(struct irq_domain *d, unsigned int virq, gic_write(GIC_REG(VPE_OTHER, GIC_VPE_COMPARE_MAP), val); break; case GIC_LOCAL_INT_TIMER: + /* CONFIG_MIPS_CMP workaround (see __gic_init) */ + val = GIC_MAP_TO_PIN_MSK | timer_cpu_pin; gic_write(GIC_REG(VPE_OTHER, GIC_VPE_TIMER_MAP), val); break; case GIC_LOCAL_INT_PERFCTR: @@ -713,12 +716,36 @@ static void __init __gic_init(unsigned long gic_base_addr, if (cpu_has_veic) { /* Always use vector 1 in EIC mode */ gic_cpu_pin = 0; + timer_cpu_pin = gic_cpu_pin; set_vi_handler(gic_cpu_pin + GIC_PIN_TO_VEC_OFFSET, __gic_irq_dispatch); } else { gic_cpu_pin = cpu_vec - GIC_CPU_PIN_OFFSET; irq_set_chained_handler(MIPS_CPU_IRQ_BASE + cpu_vec, gic_irq_dispatch); + /* + * With the CMP implementation of SMP (deprecated), other CPUs + * are started by the bootloader and put into a timer based + * waiting poll loop. We must not re-route those CPU's local + * timer interrupts as the wait instruction will never finish, + * so just handle whatever CPU interrupt it is routed to by + * default. + * + * This workaround should be removed when CMP support is + * dropped. + */ + if (IS_ENABLED(CONFIG_MIPS_CMP) && + gic_local_irq_is_routable(GIC_LOCAL_INT_TIMER)) { + timer_cpu_pin = gic_read(GIC_REG(VPE_LOCAL, + GIC_VPE_TIMER_MAP)) & + GIC_MAP_MSK; + irq_set_chained_handler(MIPS_CPU_IRQ_BASE + + GIC_CPU_PIN_OFFSET + + timer_cpu_pin, + gic_irq_dispatch); + } else { + timer_cpu_pin = gic_cpu_pin; + } } gic_irq_domain = irq_domain_add_simple(node, GIC_NUM_LOCAL_INTRS + diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c index 6dbf6fcbdfa..e8902f8dddf 100644 --- a/drivers/mailbox/pcc.c +++ b/drivers/mailbox/pcc.c @@ -386,7 +386,7 @@ static int __init pcc_init(void) ret = acpi_pcc_probe(); if (ret) { - pr_err("ACPI PCC probe failed.\n"); + pr_debug("ACPI PCC probe failed.\n"); return -ENODEV; } @@ -394,7 +394,7 @@ static int __init pcc_init(void) pcc_mbox_probe, NULL, 0, NULL, 0); if (!pcc_pdev) { - pr_err("Err creating PCC platform bundle\n"); + pr_debug("Err creating PCC platform bundle\n"); return -ENODEV; } diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 5bdedf6df15..c355a226a02 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -5,6 +5,7 @@ menuconfig MD bool "Multiple devices driver support (RAID and LVM)" depends on BLOCK + select SRCU help Support multiple physical spindles through a single logical device. Required for RAID and logical volume management. diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index d6607ee9c85..84673ebcf42 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -197,6 +197,7 @@ config NETCONSOLE_DYNAMIC config NETPOLL def_bool NETCONSOLE + select SRCU config NET_POLL_CONTROLLER def_bool NETPOLL diff --git a/drivers/net/ethernet/amd/atarilance.c b/drivers/net/ethernet/amd/atarilance.c index e07ce5ff2d4..b10964e8cb5 100644 --- a/drivers/net/ethernet/amd/atarilance.c +++ b/drivers/net/ethernet/amd/atarilance.c @@ -553,8 +553,8 @@ static unsigned long __init lance_probe1( struct net_device *dev, if (lp->cardtype == PAM_CARD || memaddr == (unsigned short *)0xffe00000) { /* PAMs card and Riebl on ST use level 5 autovector */ - if (request_irq(IRQ_AUTO_5, lance_interrupt, IRQ_TYPE_PRIO, - "PAM,Riebl-ST Ethernet", dev)) { + if (request_irq(IRQ_AUTO_5, lance_interrupt, 0, + "PAM,Riebl-ST Ethernet", dev)) { printk( "Lance: request for irq %d failed\n", IRQ_AUTO_5 ); return 0; } @@ -567,8 +567,8 @@ static unsigned long __init lance_probe1( struct net_device *dev, printk( "Lance: request for VME interrupt failed\n" ); return 0; } - if (request_irq(irq, lance_interrupt, IRQ_TYPE_PRIO, - "Riebl-VME Ethernet", dev)) { + if (request_irq(irq, lance_interrupt, 0, "Riebl-VME Ethernet", + dev)) { printk( "Lance: request for irq %u failed\n", irq ); return 0; } diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index cd286b0356a..ad0020af219 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4915,7 +4915,7 @@ static void r8168c_hw_jumbo_enable(struct rtl8169_private *tp) RTL_W8(Config3, RTL_R8(Config3) | Jumbo_En0); RTL_W8(Config4, RTL_R8(Config4) | Jumbo_En1); - rtl_tx_performance_tweak(tp->pci_dev, 0x2 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp->pci_dev, PCI_EXP_DEVCTL_READRQ_512B); } static void r8168c_hw_jumbo_disable(struct rtl8169_private *tp) @@ -4948,7 +4948,7 @@ static void r8168e_hw_jumbo_enable(struct rtl8169_private *tp) RTL_W8(MaxTxPacketSize, 0x3f); RTL_W8(Config3, RTL_R8(Config3) | Jumbo_En0); RTL_W8(Config4, RTL_R8(Config4) | 0x01); - rtl_tx_performance_tweak(tp->pci_dev, 0x2 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp->pci_dev, PCI_EXP_DEVCTL_READRQ_512B); } static void r8168e_hw_jumbo_disable(struct rtl8169_private *tp) @@ -4964,7 +4964,7 @@ static void r8168e_hw_jumbo_disable(struct rtl8169_private *tp) static void r8168b_0_hw_jumbo_enable(struct rtl8169_private *tp) { rtl_tx_performance_tweak(tp->pci_dev, - (0x2 << MAX_READ_REQUEST_SHIFT) | PCI_EXP_DEVCTL_NOSNOOP_EN); + PCI_EXP_DEVCTL_READRQ_512B | PCI_EXP_DEVCTL_NOSNOOP_EN); } static void r8168b_0_hw_jumbo_disable(struct rtl8169_private *tp) diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 2b2484b4cc2..f38227afe09 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -483,9 +483,8 @@ int xenvif_init_queue(struct xenvif_queue *queue) * better enable it. The long term solution would be to use just a * bunch of valid page descriptors, without dependency on ballooning */ - err = alloc_xenballooned_pages(MAX_PENDING_REQS, - queue->mmap_pages, - false); + err = gnttab_alloc_pages(MAX_PENDING_REQS, + queue->mmap_pages); if (err) { netdev_err(queue->vif->dev, "Could not reserve mmap_pages\n"); return -ENOMEM; @@ -664,7 +663,7 @@ void xenvif_disconnect(struct xenvif *vif) */ void xenvif_deinit_queue(struct xenvif_queue *queue) { - free_xenballooned_pages(MAX_PENDING_REQS, queue->mmap_pages); + gnttab_free_pages(MAX_PENDING_REQS, queue->mmap_pages); } void xenvif_free(struct xenvif *vif) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 13899d5099e..f7a31d2cb3f 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -269,9 +269,7 @@ static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif_queue *queue, static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb, struct netrx_pending_operations *npo, struct page *page, unsigned long size, - unsigned long offset, int *head, - struct xenvif_queue *foreign_queue, - grant_ref_t foreign_gref) + unsigned long offset, int *head) { struct gnttab_copy *copy_gop; struct xenvif_rx_meta *meta; @@ -288,6 +286,8 @@ static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb offset &= ~PAGE_MASK; while (size > 0) { + struct xen_page_foreign *foreign; + BUG_ON(offset >= PAGE_SIZE); BUG_ON(npo->copy_off > MAX_BUFFER_OFFSET); @@ -305,9 +305,10 @@ static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb copy_gop->flags = GNTCOPY_dest_gref; copy_gop->len = bytes; - if (foreign_queue) { - copy_gop->source.domid = foreign_queue->vif->domid; - copy_gop->source.u.ref = foreign_gref; + foreign = xen_page_foreign(page); + if (foreign) { + copy_gop->source.domid = foreign->domid; + copy_gop->source.u.ref = foreign->gref; copy_gop->flags |= GNTCOPY_source_gref; } else { copy_gop->source.domid = DOMID_SELF; @@ -350,35 +351,6 @@ static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb } /* - * Find the grant ref for a given frag in a chain of struct ubuf_info's - * skb: the skb itself - * i: the frag's number - * ubuf: a pointer to an element in the chain. It should not be NULL - * - * Returns a pointer to the element in the chain where the page were found. If - * not found, returns NULL. - * See the definition of callback_struct in common.h for more details about - * the chain. - */ -static const struct ubuf_info *xenvif_find_gref(const struct sk_buff *const skb, - const int i, - const struct ubuf_info *ubuf) -{ - struct xenvif_queue *foreign_queue = ubuf_to_queue(ubuf); - - do { - u16 pending_idx = ubuf->desc; - - if (skb_shinfo(skb)->frags[i].page.p == - foreign_queue->mmap_pages[pending_idx]) - break; - ubuf = (struct ubuf_info *) ubuf->ctx; - } while (ubuf); - - return ubuf; -} - -/* * Prepare an SKB to be transmitted to the frontend. * * This function is responsible for allocating grant operations, meta @@ -403,8 +375,6 @@ static int xenvif_gop_skb(struct sk_buff *skb, int head = 1; int old_meta_prod; int gso_type; - const struct ubuf_info *ubuf = skb_shinfo(skb)->destructor_arg; - const struct ubuf_info *const head_ubuf = ubuf; old_meta_prod = npo->meta_prod; @@ -451,68 +421,16 @@ static int xenvif_gop_skb(struct sk_buff *skb, len = skb_tail_pointer(skb) - data; xenvif_gop_frag_copy(queue, skb, npo, - virt_to_page(data), len, offset, &head, - NULL, - 0); + virt_to_page(data), len, offset, &head); data += len; } for (i = 0; i < nr_frags; i++) { - /* This variable also signals whether foreign_gref has a real - * value or not. - */ - struct xenvif_queue *foreign_queue = NULL; - grant_ref_t foreign_gref; - - if ((skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) && - (ubuf->callback == &xenvif_zerocopy_callback)) { - const struct ubuf_info *const startpoint = ubuf; - - /* Ideally ubuf points to the chain element which - * belongs to this frag. Or if frags were removed from - * the beginning, then shortly before it. - */ - ubuf = xenvif_find_gref(skb, i, ubuf); - - /* Try again from the beginning of the list, if we - * haven't tried from there. This only makes sense in - * the unlikely event of reordering the original frags. - * For injected local pages it's an unnecessary second - * run. - */ - if (unlikely(!ubuf) && startpoint != head_ubuf) - ubuf = xenvif_find_gref(skb, i, head_ubuf); - - if (likely(ubuf)) { - u16 pending_idx = ubuf->desc; - - foreign_queue = ubuf_to_queue(ubuf); - foreign_gref = - foreign_queue->pending_tx_info[pending_idx].req.gref; - /* Just a safety measure. If this was the last - * element on the list, the for loop will - * iterate again if a local page were added to - * the end. Using head_ubuf here prevents the - * second search on the chain. Or the original - * frags changed order, but that's less likely. - * In any way, ubuf shouldn't be NULL. - */ - ubuf = ubuf->ctx ? - (struct ubuf_info *) ubuf->ctx : - head_ubuf; - } else - /* This frag was a local page, added to the - * array after the skb left netback. - */ - ubuf = head_ubuf; - } xenvif_gop_frag_copy(queue, skb, npo, skb_frag_page(&skb_shinfo(skb)->frags[i]), skb_frag_size(&skb_shinfo(skb)->frags[i]), skb_shinfo(skb)->frags[i].page_offset, - &head, - foreign_queue, - foreign_queue ? foreign_gref : UINT_MAX); + &head); } return npo->meta_prod - old_meta_prod; @@ -1140,12 +1058,6 @@ static void xenvif_fill_frags(struct xenvif_queue *queue, struct sk_buff *skb) /* Take an extra reference to offset network stack's put_page */ get_page(queue->mmap_pages[pending_idx]); } - /* FIXME: __skb_fill_page_desc set this to true because page->pfmemalloc - * overlaps with "index", and "mapping" is not set. I think mapping - * should be set. If delivered to local stack, it would drop this - * skb in sk_filter unless the socket has the right to use it. - */ - skb->pfmemalloc = false; } static int xenvif_get_extras(struct xenvif_queue *queue, diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c index 88471d3d98c..110fece2ff5 100644 --- a/drivers/of/of_pci.c +++ b/drivers/of/of_pci.c @@ -140,6 +140,7 @@ int of_pci_get_host_bridge_resources(struct device_node *dev, unsigned char busno, unsigned char bus_max, struct list_head *resources, resource_size_t *io_base) { + struct resource_entry *window; struct resource *res; struct resource *bus_range; struct of_pci_range range; @@ -225,7 +226,10 @@ int of_pci_get_host_bridge_resources(struct device_node *dev, conversion_failed: kfree(res); parse_failed: + resource_list_for_each_entry(window, resources) + kfree(window->res); pci_free_resource_list(resources); + kfree(bus_range); return err; } EXPORT_SYMBOL_GPL(of_pci_get_host_bridge_resources); diff --git a/drivers/parport/parport_atari.c b/drivers/parport/parport_atari.c index 7ad59ac68cf..a81cd2a2747 100644 --- a/drivers/parport/parport_atari.c +++ b/drivers/parport/parport_atari.c @@ -192,8 +192,8 @@ static int __init parport_atari_init(void) &parport_atari_ops); if (!p) return -ENODEV; - if (request_irq(IRQ_MFP_BUSY, parport_irq_handler, - IRQ_TYPE_SLOW, p->name, p)) { + if (request_irq(IRQ_MFP_BUSY, parport_irq_handler, 0, p->name, + p)) { parport_put_port (p); return -ENODEV; } diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 49dd766852b..d9b64a17599 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -67,6 +67,93 @@ EXPORT_SYMBOL(pci_bus_write_config_byte); EXPORT_SYMBOL(pci_bus_write_config_word); EXPORT_SYMBOL(pci_bus_write_config_dword); +int pci_generic_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + void __iomem *addr; + + addr = bus->ops->map_bus(bus, devfn, where); + if (!addr) { + *val = ~0; + return PCIBIOS_DEVICE_NOT_FOUND; + } + + if (size == 1) + *val = readb(addr); + else if (size == 2) + *val = readw(addr); + else + *val = readl(addr); + + return PCIBIOS_SUCCESSFUL; +} +EXPORT_SYMBOL_GPL(pci_generic_config_read); + +int pci_generic_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + void __iomem *addr; + + addr = bus->ops->map_bus(bus, devfn, where); + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (size == 1) + writeb(val, addr); + else if (size == 2) + writew(val, addr); + else + writel(val, addr); + + return PCIBIOS_SUCCESSFUL; +} +EXPORT_SYMBOL_GPL(pci_generic_config_write); + +int pci_generic_config_read32(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + void __iomem *addr; + + addr = bus->ops->map_bus(bus, devfn, where & ~0x3); + if (!addr) { + *val = ~0; + return PCIBIOS_DEVICE_NOT_FOUND; + } + + *val = readl(addr); + + if (size <= 2) + *val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1); + + return PCIBIOS_SUCCESSFUL; +} +EXPORT_SYMBOL_GPL(pci_generic_config_read32); + +int pci_generic_config_write32(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + void __iomem *addr; + u32 mask, tmp; + + addr = bus->ops->map_bus(bus, devfn, where & ~0x3); + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (size == 4) { + writel(val, addr); + return PCIBIOS_SUCCESSFUL; + } else { + mask = ~(((1 << (size * 8)) - 1) << ((where & 0x3) * 8)); + } + + tmp = readl(addr) & mask; + tmp |= val << ((where & 0x3) * 8); + writel(tmp, addr); + + return PCIBIOS_SUCCESSFUL; +} +EXPORT_SYMBOL_GPL(pci_generic_config_write32); + /** * pci_bus_set_ops - Set raw operations of pci bus * @bus: pci bus struct diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 8fb16188cd8..90fa3a78fb7 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -20,17 +20,16 @@ void pci_add_resource_offset(struct list_head *resources, struct resource *res, resource_size_t offset) { - struct pci_host_bridge_window *window; + struct resource_entry *entry; - window = kzalloc(sizeof(struct pci_host_bridge_window), GFP_KERNEL); - if (!window) { + entry = resource_list_create_entry(res, 0); + if (!entry) { printk(KERN_ERR "PCI: can't add host bridge window %pR\n", res); return; } - window->res = res; - window->offset = offset; - list_add_tail(&window->list, resources); + entry->offset = offset; + resource_list_add_tail(entry, resources); } EXPORT_SYMBOL(pci_add_resource_offset); @@ -42,12 +41,7 @@ EXPORT_SYMBOL(pci_add_resource); void pci_free_resource_list(struct list_head *resources) { - struct pci_host_bridge_window *window, *tmp; - - list_for_each_entry_safe(window, tmp, resources, list) { - list_del(&window->list); - kfree(window); - } + resource_list_free(resources); } EXPORT_SYMBOL(pci_free_resource_list); diff --git a/drivers/pci/host-bridge.c b/drivers/pci/host-bridge.c index 0e5f3c95af5..39b2dbe585a 100644 --- a/drivers/pci/host-bridge.c +++ b/drivers/pci/host-bridge.c @@ -35,10 +35,10 @@ void pcibios_resource_to_bus(struct pci_bus *bus, struct pci_bus_region *region, struct resource *res) { struct pci_host_bridge *bridge = find_pci_host_bridge(bus); - struct pci_host_bridge_window *window; + struct resource_entry *window; resource_size_t offset = 0; - list_for_each_entry(window, &bridge->windows, list) { + resource_list_for_each_entry(window, &bridge->windows) { if (resource_contains(window->res, res)) { offset = window->offset; break; @@ -60,10 +60,10 @@ void pcibios_bus_to_resource(struct pci_bus *bus, struct resource *res, struct pci_bus_region *region) { struct pci_host_bridge *bridge = find_pci_host_bridge(bus); - struct pci_host_bridge_window *window; + struct resource_entry *window; resource_size_t offset = 0; - list_for_each_entry(window, &bridge->windows, list) { + resource_list_for_each_entry(window, &bridge->windows) { struct pci_bus_region bus_region; if (resource_type(res) != resource_type(window->res)) diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig index c4b6568e486..7b892a9cc4f 100644 --- a/drivers/pci/host/Kconfig +++ b/drivers/pci/host/Kconfig @@ -102,4 +102,8 @@ config PCI_LAYERSCAPE help Say Y here if you want PCIe controller support on Layerscape SoCs. +config PCI_VERSATILE + bool "ARM Versatile PB PCI controller" + depends on ARCH_VERSATILE + endmenu diff --git a/drivers/pci/host/Makefile b/drivers/pci/host/Makefile index 44c26998027..e61d91c92bf 100644 --- a/drivers/pci/host/Makefile +++ b/drivers/pci/host/Makefile @@ -12,3 +12,4 @@ obj-$(CONFIG_PCI_KEYSTONE) += pci-keystone-dw.o pci-keystone.o obj-$(CONFIG_PCIE_XILINX) += pcie-xilinx.o obj-$(CONFIG_PCI_XGENE) += pci-xgene.o obj-$(CONFIG_PCI_LAYERSCAPE) += pci-layerscape.o +obj-$(CONFIG_PCI_VERSATILE) += pci-versatile.o diff --git a/drivers/pci/host/pci-host-generic.c b/drivers/pci/host/pci-host-generic.c index 6eb1aa75bd3..ba46e581db9 100644 --- a/drivers/pci/host/pci-host-generic.c +++ b/drivers/pci/host/pci-host-generic.c @@ -76,55 +76,9 @@ static struct gen_pci_cfg_bus_ops gen_pci_cfg_ecam_bus_ops = { .map_bus = gen_pci_map_cfg_bus_ecam, }; -static int gen_pci_config_read(struct pci_bus *bus, unsigned int devfn, - int where, int size, u32 *val) -{ - void __iomem *addr; - struct pci_sys_data *sys = bus->sysdata; - struct gen_pci *pci = sys->private_data; - - addr = pci->cfg.ops->map_bus(bus, devfn, where); - - switch (size) { - case 1: - *val = readb(addr); - break; - case 2: - *val = readw(addr); - break; - default: - *val = readl(addr); - } - - return PCIBIOS_SUCCESSFUL; -} - -static int gen_pci_config_write(struct pci_bus *bus, unsigned int devfn, - int where, int size, u32 val) -{ - void __iomem *addr; - struct pci_sys_data *sys = bus->sysdata; - struct gen_pci *pci = sys->private_data; - - addr = pci->cfg.ops->map_bus(bus, devfn, where); - - switch (size) { - case 1: - writeb(val, addr); - break; - case 2: - writew(val, addr); - break; - default: - writel(val, addr); - } - - return PCIBIOS_SUCCESSFUL; -} - static struct pci_ops gen_pci_ops = { - .read = gen_pci_config_read, - .write = gen_pci_config_write, + .read = pci_generic_config_read, + .write = pci_generic_config_write, }; static const struct of_device_id gen_pci_of_match[] = { @@ -149,14 +103,14 @@ static int gen_pci_parse_request_of_pci_ranges(struct gen_pci *pci) struct device *dev = pci->host.dev.parent; struct device_node *np = dev->of_node; resource_size_t iobase; - struct pci_host_bridge_window *win; + struct resource_entry *win; err = of_pci_get_host_bridge_resources(np, 0, 0xff, &pci->resources, &iobase); if (err) return err; - list_for_each_entry(win, &pci->resources, list) { + resource_list_for_each_entry(win, &pci->resources) { struct resource *parent, *res = win->res; switch (resource_type(res)) { @@ -287,6 +241,7 @@ static int gen_pci_probe(struct platform_device *pdev) of_id = of_match_node(gen_pci_of_match, np); pci->cfg.ops = of_id->data; + gen_pci_ops.map_bus = pci->cfg.ops->map_bus; pci->host.dev.parent = dev; INIT_LIST_HEAD(&pci->host.windows); INIT_LIST_HEAD(&pci->resources); diff --git a/drivers/pci/host/pci-keystone.c b/drivers/pci/host/pci-keystone.c index 78f79e31ac5..75333b0c4f0 100644 --- a/drivers/pci/host/pci-keystone.c +++ b/drivers/pci/host/pci-keystone.c @@ -119,7 +119,7 @@ static void ks_pcie_msi_irq_handler(unsigned int irq, struct irq_desc *desc) struct pcie_port *pp = &ks_pcie->pp; struct irq_chip *chip = irq_desc_get_chip(desc); - dev_dbg(pp->dev, "ks_pci_msi_irq_handler, irq %d\n", irq); + dev_dbg(pp->dev, "%s, irq %d\n", __func__, irq); /* * The chained irq handler installation would have replaced normal @@ -197,7 +197,7 @@ static int ks_pcie_get_irq_controller_info(struct keystone_pcie *ks_pcie, */ for (temp = 0; temp < max_host_irqs; temp++) { host_irqs[temp] = irq_of_parse_and_map(*np_temp, temp); - if (host_irqs[temp] < 0) + if (!host_irqs[temp]) break; } if (temp) { diff --git a/drivers/pci/host/pci-layerscape.c b/drivers/pci/host/pci-layerscape.c index 6697b1a4d4f..68c9e5e9b0a 100644 --- a/drivers/pci/host/pci-layerscape.c +++ b/drivers/pci/host/pci-layerscape.c @@ -167,7 +167,6 @@ MODULE_DEVICE_TABLE(of, ls_pcie_of_match); static struct platform_driver ls_pcie_driver = { .driver = { .name = "layerscape-pcie", - .owner = THIS_MODULE, .of_match_table = ls_pcie_of_match, }, }; diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c index 1dd759596b0..1309cfbaa71 100644 --- a/drivers/pci/host/pci-mvebu.c +++ b/drivers/pci/host/pci-mvebu.c @@ -101,9 +101,7 @@ struct mvebu_pcie { struct mvebu_pcie_port *ports; struct msi_controller *msi; struct resource io; - char io_name[30]; struct resource realio; - char mem_name[30]; struct resource mem; struct resource busn; int nports; @@ -723,18 +721,9 @@ static int mvebu_pcie_setup(int nr, struct pci_sys_data *sys) { struct mvebu_pcie *pcie = sys_to_pcie(sys); int i; - int domain = 0; -#ifdef CONFIG_PCI_DOMAINS - domain = sys->domain; -#endif - - snprintf(pcie->mem_name, sizeof(pcie->mem_name), "PCI MEM %04x", - domain); - pcie->mem.name = pcie->mem_name; - - snprintf(pcie->io_name, sizeof(pcie->io_name), "PCI I/O %04x", domain); - pcie->realio.name = pcie->io_name; + pcie->mem.name = "PCI MEM"; + pcie->realio.name = "PCI I/O"; if (request_resource(&iomem_resource, &pcie->mem)) return 0; diff --git a/drivers/pci/host/pci-rcar-gen2.c b/drivers/pci/host/pci-rcar-gen2.c index d9c042febb1..dd6b84e6206 100644 --- a/drivers/pci/host/pci-rcar-gen2.c +++ b/drivers/pci/host/pci-rcar-gen2.c @@ -131,52 +131,6 @@ static void __iomem *rcar_pci_cfg_base(struct pci_bus *bus, unsigned int devfn, return priv->reg + (slot >> 1) * 0x100 + where; } -static int rcar_pci_read_config(struct pci_bus *bus, unsigned int devfn, - int where, int size, u32 *val) -{ - void __iomem *reg = rcar_pci_cfg_base(bus, devfn, where); - - if (!reg) - return PCIBIOS_DEVICE_NOT_FOUND; - - switch (size) { - case 1: - *val = ioread8(reg); - break; - case 2: - *val = ioread16(reg); - break; - default: - *val = ioread32(reg); - break; - } - - return PCIBIOS_SUCCESSFUL; -} - -static int rcar_pci_write_config(struct pci_bus *bus, unsigned int devfn, - int where, int size, u32 val) -{ - void __iomem *reg = rcar_pci_cfg_base(bus, devfn, where); - - if (!reg) - return PCIBIOS_DEVICE_NOT_FOUND; - - switch (size) { - case 1: - iowrite8(val, reg); - break; - case 2: - iowrite16(val, reg); - break; - default: - iowrite32(val, reg); - break; - } - - return PCIBIOS_SUCCESSFUL; -} - /* PCI interrupt mapping */ static int rcar_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { @@ -325,8 +279,9 @@ static int rcar_pci_setup(int nr, struct pci_sys_data *sys) } static struct pci_ops rcar_pci_ops = { - .read = rcar_pci_read_config, - .write = rcar_pci_write_config, + .map_bus = rcar_pci_cfg_base, + .read = pci_generic_config_read, + .write = pci_generic_config_write, }; static int rcar_pci_probe(struct platform_device *pdev) diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c index a800ae91639..00e92720d7f 100644 --- a/drivers/pci/host/pci-tegra.c +++ b/drivers/pci/host/pci-tegra.c @@ -480,59 +480,10 @@ static void __iomem *tegra_pcie_conf_address(struct pci_bus *bus, return addr; } -static int tegra_pcie_read_conf(struct pci_bus *bus, unsigned int devfn, - int where, int size, u32 *value) -{ - void __iomem *addr; - - addr = tegra_pcie_conf_address(bus, devfn, where); - if (!addr) { - *value = 0xffffffff; - return PCIBIOS_DEVICE_NOT_FOUND; - } - - *value = readl(addr); - - if (size == 1) - *value = (*value >> (8 * (where & 3))) & 0xff; - else if (size == 2) - *value = (*value >> (8 * (where & 3))) & 0xffff; - - return PCIBIOS_SUCCESSFUL; -} - -static int tegra_pcie_write_conf(struct pci_bus *bus, unsigned int devfn, - int where, int size, u32 value) -{ - void __iomem *addr; - u32 mask, tmp; - - addr = tegra_pcie_conf_address(bus, devfn, where); - if (!addr) - return PCIBIOS_DEVICE_NOT_FOUND; - - if (size == 4) { - writel(value, addr); - return PCIBIOS_SUCCESSFUL; - } - - if (size == 2) - mask = ~(0xffff << ((where & 0x3) * 8)); - else if (size == 1) - mask = ~(0xff << ((where & 0x3) * 8)); - else - return PCIBIOS_BAD_REGISTER_NUMBER; - - tmp = readl(addr) & mask; - tmp |= value << ((where & 0x3) * 8); - writel(tmp, addr); - - return PCIBIOS_SUCCESSFUL; -} - static struct pci_ops tegra_pcie_ops = { - .read = tegra_pcie_read_conf, - .write = tegra_pcie_write_conf, + .map_bus = tegra_pcie_conf_address, + .read = pci_generic_config_read32, + .write = pci_generic_config_write32, }; static unsigned long tegra_pcie_port_get_pex_ctrl(struct tegra_pcie_port *port) @@ -625,19 +576,6 @@ static void tegra_pcie_port_free(struct tegra_pcie_port *port) devm_kfree(pcie->dev, port); } -static void tegra_pcie_fixup_bridge(struct pci_dev *dev) -{ - u16 reg; - - if ((dev->class >> 16) == PCI_BASE_CLASS_BRIDGE) { - pci_read_config_word(dev, PCI_COMMAND, ®); - reg |= (PCI_COMMAND_IO | PCI_COMMAND_MEMORY | - PCI_COMMAND_MASTER | PCI_COMMAND_SERR); - pci_write_config_word(dev, PCI_COMMAND, reg); - } -} -DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, tegra_pcie_fixup_bridge); - /* Tegra PCIE root complex wrongly reports device class */ static void tegra_pcie_fixup_class(struct pci_dev *dev) { diff --git a/drivers/pci/host/pci-versatile.c b/drivers/pci/host/pci-versatile.c new file mode 100644 index 00000000000..1ec694a5237 --- /dev/null +++ b/drivers/pci/host/pci-versatile.c @@ -0,0 +1,237 @@ +/* + * Copyright 2004 Koninklijke Philips Electronics NV + * + * Conversion to platform driver and DT: + * Copyright 2014 Linaro Ltd. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * 14/04/2005 Initial version, colin.king@philips.com + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/platform_device.h> + +static void __iomem *versatile_pci_base; +static void __iomem *versatile_cfg_base[2]; + +#define PCI_IMAP(m) (versatile_pci_base + ((m) * 4)) +#define PCI_SMAP(m) (versatile_pci_base + 0x14 + ((m) * 4)) +#define PCI_SELFID (versatile_pci_base + 0xc) + +#define VP_PCI_DEVICE_ID 0x030010ee +#define VP_PCI_CLASS_ID 0x0b400000 + +static u32 pci_slot_ignore; + +static int __init versatile_pci_slot_ignore(char *str) +{ + int retval; + int slot; + + while ((retval = get_option(&str, &slot))) { + if ((slot < 0) || (slot > 31)) + pr_err("Illegal slot value: %d\n", slot); + else + pci_slot_ignore |= (1 << slot); + } + return 1; +} +__setup("pci_slot_ignore=", versatile_pci_slot_ignore); + + +static void __iomem *versatile_map_bus(struct pci_bus *bus, + unsigned int devfn, int offset) +{ + unsigned int busnr = bus->number; + + if (pci_slot_ignore & (1 << PCI_SLOT(devfn))) + return NULL; + + return versatile_cfg_base[1] + ((busnr << 16) | (devfn << 8) | offset); +} + +static struct pci_ops pci_versatile_ops = { + .map_bus = versatile_map_bus, + .read = pci_generic_config_read32, + .write = pci_generic_config_write, +}; + +static int versatile_pci_parse_request_of_pci_ranges(struct device *dev, + struct list_head *res) +{ + int err, mem = 1, res_valid = 0; + struct device_node *np = dev->of_node; + resource_size_t iobase; + struct resource_entry *win; + + err = of_pci_get_host_bridge_resources(np, 0, 0xff, res, &iobase); + if (err) + return err; + + resource_list_for_each_entry(win, res, list) { + struct resource *parent, *res = win->res; + + switch (resource_type(res)) { + case IORESOURCE_IO: + parent = &ioport_resource; + err = pci_remap_iospace(res, iobase); + if (err) { + dev_warn(dev, "error %d: failed to map resource %pR\n", + err, res); + continue; + } + break; + case IORESOURCE_MEM: + parent = &iomem_resource; + res_valid |= !(res->flags & IORESOURCE_PREFETCH); + + writel(res->start >> 28, PCI_IMAP(mem)); + writel(PHYS_OFFSET >> 28, PCI_SMAP(mem)); + mem++; + + break; + case IORESOURCE_BUS: + default: + continue; + } + + err = devm_request_resource(dev, parent, res); + if (err) + goto out_release_res; + } + + if (!res_valid) { + dev_err(dev, "non-prefetchable memory resource required\n"); + err = -EINVAL; + goto out_release_res; + } + + return 0; + +out_release_res: + pci_free_resource_list(res); + return err; +} + +/* Unused, temporary to satisfy ARM arch code */ +struct pci_sys_data sys; + +static int versatile_pci_probe(struct platform_device *pdev) +{ + struct resource *res; + int ret, i, myslot = -1; + u32 val; + void __iomem *local_pci_cfg_base; + struct pci_bus *bus; + LIST_HEAD(pci_res); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return -ENODEV; + versatile_pci_base = devm_ioremap_resource(&pdev->dev, res); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (!res) + return -ENODEV; + versatile_cfg_base[0] = devm_ioremap_resource(&pdev->dev, res); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 2); + if (!res) + return -ENODEV; + versatile_cfg_base[1] = devm_ioremap_resource(&pdev->dev, res); + + ret = versatile_pci_parse_request_of_pci_ranges(&pdev->dev, &pci_res); + if (ret) + return ret; + + /* + * We need to discover the PCI core first to configure itself + * before the main PCI probing is performed + */ + for (i = 0; i < 32; i++) { + if ((readl(versatile_cfg_base[0] + (i << 11) + PCI_VENDOR_ID) == VP_PCI_DEVICE_ID) && + (readl(versatile_cfg_base[0] + (i << 11) + PCI_CLASS_REVISION) == VP_PCI_CLASS_ID)) { + myslot = i; + break; + } + } + if (myslot == -1) { + dev_err(&pdev->dev, "Cannot find PCI core!\n"); + return -EIO; + } + /* + * Do not to map Versatile FPGA PCI device into memory space + */ + pci_slot_ignore |= (1 << myslot); + + dev_info(&pdev->dev, "PCI core found (slot %d)\n", myslot); + + writel(myslot, PCI_SELFID); + local_pci_cfg_base = versatile_cfg_base[1] + (myslot << 11); + + val = readl(local_pci_cfg_base + PCI_COMMAND); + val |= PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER | PCI_COMMAND_INVALIDATE; + writel(val, local_pci_cfg_base + PCI_COMMAND); + + /* + * Configure the PCI inbound memory windows to be 1:1 mapped to SDRAM + */ + writel(PHYS_OFFSET, local_pci_cfg_base + PCI_BASE_ADDRESS_0); + writel(PHYS_OFFSET, local_pci_cfg_base + PCI_BASE_ADDRESS_1); + writel(PHYS_OFFSET, local_pci_cfg_base + PCI_BASE_ADDRESS_2); + + /* + * For many years the kernel and QEMU were symbiotically buggy + * in that they both assumed the same broken IRQ mapping. + * QEMU therefore attempts to auto-detect old broken kernels + * so that they still work on newer QEMU as they did on old + * QEMU. Since we now use the correct (ie matching-hardware) + * IRQ mapping we write a definitely different value to a + * PCI_INTERRUPT_LINE register to tell QEMU that we expect + * real hardware behaviour and it need not be backwards + * compatible for us. This write is harmless on real hardware. + */ + writel(0, versatile_cfg_base[0] + PCI_INTERRUPT_LINE); + + pci_add_flags(PCI_ENABLE_PROC_DOMAINS); + pci_add_flags(PCI_REASSIGN_ALL_BUS | PCI_REASSIGN_ALL_RSRC); + + bus = pci_scan_root_bus(&pdev->dev, 0, &pci_versatile_ops, &sys, &pci_res); + if (!bus) + return -ENOMEM; + + pci_fixup_irqs(pci_common_swizzle, of_irq_parse_and_map_pci); + pci_assign_unassigned_bus_resources(bus); + + return 0; +} + +static const struct of_device_id versatile_pci_of_match[] = { + { .compatible = "arm,versatile-pci", }, + { }, +}; +MODULE_DEVICE_TABLE(of, versatile_pci_of_match); + +static struct platform_driver versatile_pci_driver = { + .driver = { + .name = "versatile-pci", + .of_match_table = versatile_pci_of_match, + }, + .probe = versatile_pci_probe, +}; +module_platform_driver(versatile_pci_driver); + +MODULE_DESCRIPTION("Versatile PCI driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/host/pci-xgene.c b/drivers/pci/host/pci-xgene.c index b1d0596457c..aab55474dd0 100644 --- a/drivers/pci/host/pci-xgene.c +++ b/drivers/pci/host/pci-xgene.c @@ -16,7 +16,7 @@ * GNU General Public License for more details. * */ -#include <linux/clk-private.h> +#include <linux/clk.h> #include <linux/delay.h> #include <linux/io.h> #include <linux/jiffies.h> @@ -74,92 +74,6 @@ static inline u32 pcie_bar_low_val(u32 addr, u32 flags) return (addr & PCI_BASE_ADDRESS_MEM_MASK) | flags; } -/* PCIe Configuration Out/In */ -static inline void xgene_pcie_cfg_out32(void __iomem *addr, int offset, u32 val) -{ - writel(val, addr + offset); -} - -static inline void xgene_pcie_cfg_out16(void __iomem *addr, int offset, u16 val) -{ - u32 val32 = readl(addr + (offset & ~0x3)); - - switch (offset & 0x3) { - case 2: - val32 &= ~0xFFFF0000; - val32 |= (u32)val << 16; - break; - case 0: - default: - val32 &= ~0xFFFF; - val32 |= val; - break; - } - writel(val32, addr + (offset & ~0x3)); -} - -static inline void xgene_pcie_cfg_out8(void __iomem *addr, int offset, u8 val) -{ - u32 val32 = readl(addr + (offset & ~0x3)); - - switch (offset & 0x3) { - case 0: - val32 &= ~0xFF; - val32 |= val; - break; - case 1: - val32 &= ~0xFF00; - val32 |= (u32)val << 8; - break; - case 2: - val32 &= ~0xFF0000; - val32 |= (u32)val << 16; - break; - case 3: - default: - val32 &= ~0xFF000000; - val32 |= (u32)val << 24; - break; - } - writel(val32, addr + (offset & ~0x3)); -} - -static inline void xgene_pcie_cfg_in32(void __iomem *addr, int offset, u32 *val) -{ - *val = readl(addr + offset); -} - -static inline void xgene_pcie_cfg_in16(void __iomem *addr, int offset, u32 *val) -{ - *val = readl(addr + (offset & ~0x3)); - - switch (offset & 0x3) { - case 2: - *val >>= 16; - break; - } - - *val &= 0xFFFF; -} - -static inline void xgene_pcie_cfg_in8(void __iomem *addr, int offset, u32 *val) -{ - *val = readl(addr + (offset & ~0x3)); - - switch (offset & 0x3) { - case 3: - *val = *val >> 24; - break; - case 2: - *val = *val >> 16; - break; - case 1: - *val = *val >> 8; - break; - } - *val &= 0xFF; -} - /* * When the address bit [17:16] is 2'b01, the Configuration access will be * treated as Type 1 and it will be forwarded to external PCIe device. @@ -213,69 +127,23 @@ static bool xgene_pcie_hide_rc_bars(struct pci_bus *bus, int offset) return false; } -static int xgene_pcie_read_config(struct pci_bus *bus, unsigned int devfn, - int offset, int len, u32 *val) -{ - struct xgene_pcie_port *port = bus->sysdata; - void __iomem *addr; - - if ((pci_is_root_bus(bus) && devfn != 0) || !port->link_up) - return PCIBIOS_DEVICE_NOT_FOUND; - - if (xgene_pcie_hide_rc_bars(bus, offset)) { - *val = 0; - return PCIBIOS_SUCCESSFUL; - } - - xgene_pcie_set_rtdid_reg(bus, devfn); - addr = xgene_pcie_get_cfg_base(bus); - switch (len) { - case 1: - xgene_pcie_cfg_in8(addr, offset, val); - break; - case 2: - xgene_pcie_cfg_in16(addr, offset, val); - break; - default: - xgene_pcie_cfg_in32(addr, offset, val); - break; - } - - return PCIBIOS_SUCCESSFUL; -} - -static int xgene_pcie_write_config(struct pci_bus *bus, unsigned int devfn, - int offset, int len, u32 val) +static int xgene_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, + int offset) { struct xgene_pcie_port *port = bus->sysdata; - void __iomem *addr; - if ((pci_is_root_bus(bus) && devfn != 0) || !port->link_up) - return PCIBIOS_DEVICE_NOT_FOUND; - - if (xgene_pcie_hide_rc_bars(bus, offset)) - return PCIBIOS_SUCCESSFUL; + if ((pci_is_root_bus(bus) && devfn != 0) || !port->link_up || + xgene_pcie_hide_rc_bars(bus, offset)) + return NULL; xgene_pcie_set_rtdid_reg(bus, devfn); - addr = xgene_pcie_get_cfg_base(bus); - switch (len) { - case 1: - xgene_pcie_cfg_out8(addr, offset, (u8)val); - break; - case 2: - xgene_pcie_cfg_out16(addr, offset, (u16)val); - break; - default: - xgene_pcie_cfg_out32(addr, offset, val); - break; - } - - return PCIBIOS_SUCCESSFUL; + return xgene_pcie_get_cfg_base(bus); } static struct pci_ops xgene_pcie_ops = { - .read = xgene_pcie_read_config, - .write = xgene_pcie_write_config + .map_bus = xgene_pcie_map_bus, + .read = pci_generic_config_read32, + .write = pci_generic_config_write32, }; static u64 xgene_pcie_set_ib_mask(void __iomem *csr_base, u32 addr, @@ -401,11 +269,11 @@ static int xgene_pcie_map_ranges(struct xgene_pcie_port *port, struct list_head *res, resource_size_t io_base) { - struct pci_host_bridge_window *window; + struct resource_entry *window; struct device *dev = port->dev; int ret; - list_for_each_entry(window, res, list) { + resource_list_for_each_entry(window, res) { struct resource *res = window->res; u64 restype = resource_type(res); diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c index 17ca98657a2..1f4ea6f2d91 100644 --- a/drivers/pci/host/pcie-designware.c +++ b/drivers/pci/host/pcie-designware.c @@ -511,9 +511,6 @@ int __init dw_pcie_host_init(struct pcie_port *pp) dw_pci.private_data = (void **)&pp; pci_common_init_dev(pp->dev, &dw_pci); -#ifdef CONFIG_PCI_DOMAINS - dw_pci.domain++; -#endif return 0; } diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c index 748786c402f..c57bd0ac39a 100644 --- a/drivers/pci/host/pcie-rcar.c +++ b/drivers/pci/host/pcie-rcar.c @@ -397,9 +397,6 @@ static void rcar_pcie_enable(struct rcar_pcie *pcie) #endif pci_common_init_dev(&pdev->dev, &rcar_pci); -#ifdef CONFIG_PCI_DOMAINS - rcar_pci.domain++; -#endif } static int phy_wait_for_ack(struct rcar_pcie *pcie) @@ -757,7 +754,7 @@ static int rcar_pcie_get_resources(struct platform_device *pdev, goto err_map_reg; i = irq_of_parse_and_map(pdev->dev.of_node, 0); - if (i < 0) { + if (!i) { dev_err(pcie->dev, "cannot get platform resources for msi interrupt\n"); err = -ENOENT; goto err_map_reg; @@ -765,7 +762,7 @@ static int rcar_pcie_get_resources(struct platform_device *pdev, pcie->msi.irq1 = i; i = irq_of_parse_and_map(pdev->dev.of_node, 1); - if (i < 0) { + if (!i) { dev_err(pcie->dev, "cannot get platform resources for msi interrupt\n"); err = -ENOENT; goto err_map_reg; diff --git a/drivers/pci/host/pcie-xilinx.c b/drivers/pci/host/pcie-xilinx.c index ef3ebaf9a73..f1a06a091cc 100644 --- a/drivers/pci/host/pcie-xilinx.c +++ b/drivers/pci/host/pcie-xilinx.c @@ -148,10 +148,10 @@ static inline bool xilinx_pcie_link_is_up(struct xilinx_pcie_port *port) */ static void xilinx_pcie_clear_err_interrupts(struct xilinx_pcie_port *port) { - u32 val = pcie_read(port, XILINX_PCIE_REG_RPEFR); + unsigned long val = pcie_read(port, XILINX_PCIE_REG_RPEFR); if (val & XILINX_PCIE_RPEFR_ERR_VALID) { - dev_dbg(port->dev, "Requester ID %d\n", + dev_dbg(port->dev, "Requester ID %lu\n", val & XILINX_PCIE_RPEFR_REQ_ID); pcie_write(port, XILINX_PCIE_RPEFR_ALL_MASK, XILINX_PCIE_REG_RPEFR); @@ -189,7 +189,7 @@ static bool xilinx_pcie_valid_device(struct pci_bus *bus, unsigned int devfn) } /** - * xilinx_pcie_config_base - Get configuration base + * xilinx_pcie_map_bus - Get configuration base * @bus: PCI Bus structure * @devfn: Device/function * @where: Offset from base @@ -197,96 +197,26 @@ static bool xilinx_pcie_valid_device(struct pci_bus *bus, unsigned int devfn) * Return: Base address of the configuration space needed to be * accessed. */ -static void __iomem *xilinx_pcie_config_base(struct pci_bus *bus, - unsigned int devfn, int where) +static void __iomem *xilinx_pcie_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) { struct xilinx_pcie_port *port = sys_to_pcie(bus->sysdata); int relbus; + if (!xilinx_pcie_valid_device(bus, devfn)) + return NULL; + relbus = (bus->number << ECAM_BUS_NUM_SHIFT) | (devfn << ECAM_DEV_NUM_SHIFT); return port->reg_base + relbus + where; } -/** - * xilinx_pcie_read_config - Read configuration space - * @bus: PCI Bus structure - * @devfn: Device/function - * @where: Offset from base - * @size: Byte/word/dword - * @val: Value to be read - * - * Return: PCIBIOS_SUCCESSFUL on success - * PCIBIOS_DEVICE_NOT_FOUND on failure - */ -static int xilinx_pcie_read_config(struct pci_bus *bus, unsigned int devfn, - int where, int size, u32 *val) -{ - void __iomem *addr; - - if (!xilinx_pcie_valid_device(bus, devfn)) { - *val = 0xFFFFFFFF; - return PCIBIOS_DEVICE_NOT_FOUND; - } - - addr = xilinx_pcie_config_base(bus, devfn, where); - - switch (size) { - case 1: - *val = readb(addr); - break; - case 2: - *val = readw(addr); - break; - default: - *val = readl(addr); - break; - } - - return PCIBIOS_SUCCESSFUL; -} - -/** - * xilinx_pcie_write_config - Write configuration space - * @bus: PCI Bus structure - * @devfn: Device/function - * @where: Offset from base - * @size: Byte/word/dword - * @val: Value to be written to device - * - * Return: PCIBIOS_SUCCESSFUL on success - * PCIBIOS_DEVICE_NOT_FOUND on failure - */ -static int xilinx_pcie_write_config(struct pci_bus *bus, unsigned int devfn, - int where, int size, u32 val) -{ - void __iomem *addr; - - if (!xilinx_pcie_valid_device(bus, devfn)) - return PCIBIOS_DEVICE_NOT_FOUND; - - addr = xilinx_pcie_config_base(bus, devfn, where); - - switch (size) { - case 1: - writeb(val, addr); - break; - case 2: - writew(val, addr); - break; - default: - writel(val, addr); - break; - } - - return PCIBIOS_SUCCESSFUL; -} - /* PCIe operations */ static struct pci_ops xilinx_pcie_ops = { - .read = xilinx_pcie_read_config, - .write = xilinx_pcie_write_config, + .map_bus = xilinx_pcie_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, }; /* MSI functions */ @@ -737,7 +667,7 @@ static int xilinx_pcie_parse_and_add_res(struct xilinx_pcie_port *port) resource_size_t offset; struct of_pci_range_parser parser; struct of_pci_range range; - struct pci_host_bridge_window *win; + struct resource_entry *win; int err = 0, mem_resno = 0; /* Get the ranges */ @@ -807,7 +737,7 @@ static int xilinx_pcie_parse_and_add_res(struct xilinx_pcie_port *port) free_resources: release_child_resources(&iomem_resource); - list_for_each_entry(win, &port->resources, list) + resource_list_for_each_entry(win, &port->resources) devm_kfree(dev, win->res); pci_free_resource_list(&port->resources); diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c index a5a7fd8332a..46db29395a6 100644 --- a/drivers/pci/hotplug/cpci_hotplug_core.c +++ b/drivers/pci/hotplug/cpci_hotplug_core.c @@ -214,8 +214,7 @@ static void release_slot(struct hotplug_slot *hotplug_slot) kfree(slot->hotplug_slot->info); kfree(slot->hotplug_slot); - if (slot->dev) - pci_dev_put(slot->dev); + pci_dev_put(slot->dev); kfree(slot); } diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index ff32e85e1de..f052e951b23 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -532,8 +532,6 @@ static void interrupt_event_handler(struct work_struct *work) pciehp_green_led_off(p_slot); break; case INT_PRESENCE_ON: - if (!HP_SUPR_RM(ctrl)) - break; ctrl_dbg(ctrl, "Surprise Insertion\n"); handle_surprise_event(p_slot); break; diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c index bada2099987..c32fb786d48 100644 --- a/drivers/pci/hotplug/sgi_hotplug.c +++ b/drivers/pci/hotplug/sgi_hotplug.c @@ -475,7 +475,7 @@ static int disable_slot(struct hotplug_slot *bss_hotplug_slot) struct slot *slot = bss_hotplug_slot->private; struct pci_dev *dev, *temp; int rc; - acpi_owner_id ssdt_id = 0; + acpi_handle ssdt_hdl = NULL; /* Acquire update access to the bus */ mutex_lock(&sn_hotplug_mutex); @@ -522,7 +522,7 @@ static int disable_slot(struct hotplug_slot *bss_hotplug_slot) if (ACPI_SUCCESS(ret) && (adr>>16) == (slot->device_num + 1)) { /* retain the owner id */ - acpi_get_id(chandle, &ssdt_id); + ssdt_hdl = chandle; ret = acpi_bus_get_device(chandle, &device); @@ -547,12 +547,13 @@ static int disable_slot(struct hotplug_slot *bss_hotplug_slot) pci_unlock_rescan_remove(); /* Remove the SSDT for the slot from the ACPI namespace */ - if (SN_ACPI_BASE_SUPPORT() && ssdt_id) { + if (SN_ACPI_BASE_SUPPORT() && ssdt_hdl) { acpi_status ret; - ret = acpi_unload_table_id(ssdt_id); + ret = acpi_unload_parent_table(ssdt_hdl); if (ACPI_FAILURE(ret)) { - printk(KERN_ERR "%s: acpi_unload_table_id failed (0x%x) for id %d\n", - __func__, ret, ssdt_id); + acpi_handle_err(ssdt_hdl, + "%s: acpi_unload_parent_table failed (0x%x)\n", + __func__, ret); /* try to continue on */ } } diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index fd60806d3fd..c3e7dfcf9ff 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -694,11 +694,16 @@ static void __iomem *msix_map_region(struct pci_dev *dev, unsigned nr_entries) { resource_size_t phys_addr; u32 table_offset; + unsigned long flags; u8 bir; pci_read_config_dword(dev, dev->msix_cap + PCI_MSIX_TABLE, &table_offset); bir = (u8)(table_offset & PCI_MSIX_TABLE_BIR); + flags = pci_resource_flags(dev, bir); + if (!flags || (flags & IORESOURCE_UNSET)) + return NULL; + table_offset &= PCI_MSIX_TABLE_OFFSET; phys_addr = pci_resource_start(dev, bir) + table_offset; diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 3542150fc8a..48906398732 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -501,12 +501,29 @@ static int acpi_pci_run_wake(struct pci_dev *dev, bool enable) return 0; } +static bool acpi_pci_need_resume(struct pci_dev *dev) +{ + struct acpi_device *adev = ACPI_COMPANION(&dev->dev); + + if (!adev || !acpi_device_power_manageable(adev)) + return false; + + if (device_may_wakeup(&dev->dev) != !!adev->wakeup.prepare_count) + return true; + + if (acpi_target_system_state() == ACPI_STATE_S0) + return false; + + return !!adev->power.flags.dsw_present; +} + static struct pci_platform_pm_ops acpi_pci_platform_pm = { .is_manageable = acpi_pci_power_manageable, .set_state = acpi_pci_set_power_state, .choose_state = acpi_pci_choose_state, .sleep_wake = acpi_pci_sleep_wake, .run_wake = acpi_pci_run_wake, + .need_resume = acpi_pci_need_resume, }; void acpi_pci_add_bus(struct pci_bus *bus) diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 887e6bd95af..3cb2210de55 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -653,7 +653,6 @@ static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev) static int pci_pm_prepare(struct device *dev) { struct device_driver *drv = dev->driver; - int error = 0; /* * Devices having power.ignore_children set may still be necessary for @@ -662,10 +661,12 @@ static int pci_pm_prepare(struct device *dev) if (dev->power.ignore_children) pm_runtime_resume(dev); - if (drv && drv->pm && drv->pm->prepare) - error = drv->pm->prepare(dev); - - return error; + if (drv && drv->pm && drv->pm->prepare) { + int error = drv->pm->prepare(dev); + if (error) + return error; + } + return pci_dev_keep_suspended(to_pci_dev(dev)); } @@ -1383,7 +1384,7 @@ static int pci_uevent(struct device *dev, struct kobj_uevent_env *env) if (add_uevent_var(env, "PCI_SLOT_NAME=%s", pci_name(pdev))) return -ENOMEM; - if (add_uevent_var(env, "MODALIAS=pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x", + if (add_uevent_var(env, "MODALIAS=pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02X", pdev->vendor, pdev->device, pdev->subsystem_vendor, pdev->subsystem_device, (u8)(pdev->class >> 16), (u8)(pdev->class >> 8), diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e9d4fd861ba..81f06e8dcc0 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -10,6 +10,8 @@ #include <linux/kernel.h> #include <linux/delay.h> #include <linux/init.h> +#include <linux/of.h> +#include <linux/of_pci.h> #include <linux/pci.h> #include <linux/pm.h> #include <linux/slab.h> @@ -521,6 +523,11 @@ static inline int platform_pci_run_wake(struct pci_dev *dev, bool enable) pci_platform_pm->run_wake(dev, enable) : -ENODEV; } +static inline bool platform_pci_need_resume(struct pci_dev *dev) +{ + return pci_platform_pm ? pci_platform_pm->need_resume(dev) : false; +} + /** * pci_raw_set_power_state - Use PCI PM registers to set the power state of * given PCI device @@ -1999,6 +2006,27 @@ bool pci_dev_run_wake(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_dev_run_wake); +/** + * pci_dev_keep_suspended - Check if the device can stay in the suspended state. + * @pci_dev: Device to check. + * + * Return 'true' if the device is runtime-suspended, it doesn't have to be + * reconfigured due to wakeup settings difference between system and runtime + * suspend and the current power state of it is suitable for the upcoming + * (system) transition. + */ +bool pci_dev_keep_suspended(struct pci_dev *pci_dev) +{ + struct device *dev = &pci_dev->dev; + + if (!pm_runtime_suspended(dev) + || (device_can_wakeup(dev) && !device_may_wakeup(dev)) + || platform_pci_need_resume(pci_dev)) + return false; + + return pci_target_state(pci_dev) == pci_dev->current_state; +} + void pci_config_pm_runtime_get(struct pci_dev *pdev) { struct device *dev = &pdev->dev; @@ -3197,7 +3225,7 @@ static int pci_pm_reset(struct pci_dev *dev, int probe) { u16 csr; - if (!dev->pm_cap) + if (!dev->pm_cap || dev->dev_flags & PCI_DEV_FLAGS_NO_PM_RESET) return -ENOTTY; pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &csr); @@ -4471,6 +4499,53 @@ int pci_get_new_domain_nr(void) { return atomic_inc_return(&__domain_nr); } + +#ifdef CONFIG_PCI_DOMAINS_GENERIC +void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent) +{ + static int use_dt_domains = -1; + int domain = of_get_pci_domain_nr(parent->of_node); + + /* + * Check DT domain and use_dt_domains values. + * + * If DT domain property is valid (domain >= 0) and + * use_dt_domains != 0, the DT assignment is valid since this means + * we have not previously allocated a domain number by using + * pci_get_new_domain_nr(); we should also update use_dt_domains to + * 1, to indicate that we have just assigned a domain number from + * DT. + * + * If DT domain property value is not valid (ie domain < 0), and we + * have not previously assigned a domain number from DT + * (use_dt_domains != 1) we should assign a domain number by + * using the: + * + * pci_get_new_domain_nr() + * + * API and update the use_dt_domains value to keep track of method we + * are using to assign domain numbers (use_dt_domains = 0). + * + * All other combinations imply we have a platform that is trying + * to mix domain numbers obtained from DT and pci_get_new_domain_nr(), + * which is a recipe for domain mishandling and it is prevented by + * invalidating the domain value (domain = -1) and printing a + * corresponding error. + */ + if (domain >= 0 && use_dt_domains) { + use_dt_domains = 1; + } else if (domain < 0 && use_dt_domains != 1) { + use_dt_domains = 0; + domain = pci_get_new_domain_nr(); + } else { + dev_err(parent, "Node %s has inconsistent \"linux,pci-domain\" property in DT\n", + parent->of_node->full_name); + domain = -1; + } + + bus->domain_nr = domain; +} +#endif #endif /** diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index d54632a1db4..4091f82239c 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -50,6 +50,10 @@ int pci_probe_reset_function(struct pci_dev *dev); * for given device (the device's wake-up capability has to be * enabled by @sleep_wake for this feature to work) * + * @need_resume: returns 'true' if the given device (which is currently + * suspended) needs to be resumed to be configured for system + * wakeup. + * * If given platform is generally capable of power managing PCI devices, all of * these callbacks are mandatory. */ @@ -59,6 +63,7 @@ struct pci_platform_pm_ops { pci_power_t (*choose_state)(struct pci_dev *dev); int (*sleep_wake)(struct pci_dev *dev, bool enable); int (*run_wake)(struct pci_dev *dev, bool enable); + bool (*need_resume)(struct pci_dev *dev); }; int pci_set_platform_pm(struct pci_platform_pm_ops *ops); @@ -67,6 +72,7 @@ void pci_power_up(struct pci_dev *dev); void pci_disable_enabled_device(struct pci_dev *dev); int pci_finish_runtime_suspend(struct pci_dev *dev); int __pci_pme_wakeup(struct pci_dev *dev, void *ign); +bool pci_dev_keep_suspended(struct pci_dev *dev); void pci_config_pm_runtime_get(struct pci_dev *dev); void pci_config_pm_runtime_put(struct pci_dev *dev); void pci_pm_init(struct pci_dev *dev); diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index e1e7026b838..820740a22e9 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -859,7 +859,10 @@ static ssize_t link_state_store(struct device *dev, { struct pci_dev *pdev = to_pci_dev(dev); struct pcie_link_state *link, *root = pdev->link_state->root; - u32 val = buf[0] - '0', state = 0; + u32 val, state = 0; + + if (kstrtouint(buf, 10, &val)) + return -EINVAL; if (aspm_disabled) return -EPERM; @@ -900,15 +903,14 @@ static ssize_t clk_ctl_store(struct device *dev, size_t n) { struct pci_dev *pdev = to_pci_dev(dev); - int state; + bool state; - if (n < 1) + if (strtobool(buf, &state)) return -EINVAL; - state = buf[0]-'0'; down_read(&pci_bus_sem); mutex_lock(&aspm_lock); - pcie_set_clkpm_nocheck(pdev->link_state, !!state); + pcie_set_clkpm_nocheck(pdev->link_state, state); mutex_unlock(&aspm_lock); up_read(&pci_bus_sem); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 23212f8ae09..8d2f400e96c 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1895,7 +1895,7 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus, int error; struct pci_host_bridge *bridge; struct pci_bus *b, *b2; - struct pci_host_bridge_window *window, *n; + struct resource_entry *window, *n; struct resource *res; resource_size_t offset; char bus_addr[64]; @@ -1959,8 +1959,8 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus, printk(KERN_INFO "PCI host bridge to bus %s\n", dev_name(&b->dev)); /* Add initial resources to the bus */ - list_for_each_entry_safe(window, n, resources, list) { - list_move_tail(&window->list, &bridge->windows); + resource_list_for_each_entry_safe(window, n, resources) { + list_move_tail(&window->node, &bridge->windows); res = window->res; offset = window->offset; if (res->flags & IORESOURCE_BUS) @@ -2060,12 +2060,12 @@ void pci_bus_release_busn_res(struct pci_bus *b) struct pci_bus *pci_scan_root_bus(struct device *parent, int bus, struct pci_ops *ops, void *sysdata, struct list_head *resources) { - struct pci_host_bridge_window *window; + struct resource_entry *window; bool found = false; struct pci_bus *b; int max; - list_for_each_entry(window, resources, list) + resource_list_for_each_entry(window, resources) if (window->res->flags & IORESOURCE_BUS) { found = true; break; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 903d5078b5e..85f247e28a8 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3076,6 +3076,27 @@ static void quirk_no_bus_reset(struct pci_dev *dev) */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x0030, quirk_no_bus_reset); +static void quirk_no_pm_reset(struct pci_dev *dev) +{ + /* + * We can't do a bus reset on root bus devices, but an ineffective + * PM reset may be better than nothing. + */ + if (!pci_is_root_bus(dev->bus)) + dev->dev_flags |= PCI_DEV_FLAGS_NO_PM_RESET; +} + +/* + * Some AMD/ATI GPUS (HD8570 - Oland) report that a D3hot->D0 transition + * causes a reset (i.e., they advertise NoSoftRst-). This transition seems + * to have no effect on the device: it retains the framebuffer contents and + * monitor sync. Advertising this support makes other layers, like VFIO, + * assume pci_reset_function() is viable for this device. Mark it as + * unavailable to skip it when testing reset methods. + */ +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_ATI, PCI_ANY_ID, + PCI_CLASS_DISPLAY_VGA, 8, quirk_no_pm_reset); + #ifdef CONFIG_ACPI /* * Apple: Shutdown Cactus Ridge Thunderbolt controller. @@ -3576,6 +3597,44 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_JMICRON, quirk_dma_func1_alias); /* + * Some devices DMA with the wrong devfn, not just the wrong function. + * quirk_fixed_dma_alias() uses this table to create fixed aliases, where + * the alias is "fixed" and independent of the device devfn. + * + * For example, the Adaptec 3405 is a PCIe card with an Intel 80333 I/O + * processor. To software, this appears as a PCIe-to-PCI/X bridge with a + * single device on the secondary bus. In reality, the single exposed + * device at 0e.0 is the Address Translation Unit (ATU) of the controller + * that provides a bridge to the internal bus of the I/O processor. The + * controller supports private devices, which can be hidden from PCI config + * space. In the case of the Adaptec 3405, a private device at 01.0 + * appears to be the DMA engine, which therefore needs to become a DMA + * alias for the device. + */ +static const struct pci_device_id fixed_dma_alias_tbl[] = { + { PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x0285, + PCI_VENDOR_ID_ADAPTEC2, 0x02bb), /* Adaptec 3405 */ + .driver_data = PCI_DEVFN(1, 0) }, + { 0 } +}; + +static void quirk_fixed_dma_alias(struct pci_dev *dev) +{ + const struct pci_device_id *id; + + id = pci_match_id(fixed_dma_alias_tbl, dev); + if (id) { + dev->dma_alias_devfn = id->driver_data; + dev->dev_flags |= PCI_DEV_FLAGS_DMA_ALIAS_DEVFN; + dev_info(&dev->dev, "Enabling fixed DMA alias to %02x.%d\n", + PCI_SLOT(dev->dma_alias_devfn), + PCI_FUNC(dev->dma_alias_devfn)); + } +} + +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ADAPTEC2, 0x0285, quirk_fixed_dma_alias); + +/* * A few PCIe-to-PCI bridges fail to expose a PCIe capability, resulting in * using the wrong DMA alias for the device. Some of these devices can be * used as either forward or reverse bridges, so we need to test whether the @@ -3678,6 +3737,9 @@ static const u16 pci_quirk_intel_pch_acs_ids[] = { 0x9c98, 0x9c99, 0x9c9a, 0x9c9b, /* Patsburg (X79) PCH */ 0x1d10, 0x1d12, 0x1d14, 0x1d16, 0x1d18, 0x1d1a, 0x1d1c, 0x1d1e, + /* Wellsburg (X99) PCH */ + 0x8d10, 0x8d11, 0x8d12, 0x8d13, 0x8d14, 0x8d15, 0x8d16, 0x8d17, + 0x8d18, 0x8d19, 0x8d1a, 0x8d1b, 0x8d1c, 0x8d1d, 0x8d1e, }; static bool pci_quirk_intel_pch_acs_match(struct pci_dev *dev) @@ -3761,6 +3823,8 @@ static const struct pci_dev_acs_enabled { { PCI_VENDOR_ID_INTEL, 0x1551, pci_quirk_mf_endpoint_acs }, { PCI_VENDOR_ID_INTEL, 0x1558, pci_quirk_mf_endpoint_acs }, { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_intel_pch_acs }, + { 0x19a2, 0x710, pci_quirk_mf_endpoint_acs }, /* Emulex BE3-R */ + { 0x10df, 0x720, pci_quirk_mf_endpoint_acs }, /* Emulex Skyhawk-R */ { 0 } }; diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c index f955edb9bea..eb0ad530dc4 100644 --- a/drivers/pci/rom.c +++ b/drivers/pci/rom.c @@ -71,6 +71,7 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size) { void __iomem *image; int last_image; + unsigned length; image = rom; do { @@ -93,9 +94,9 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size) if (readb(pds + 3) != 'R') break; last_image = readb(pds + 21) & 0x80; - /* this length is reliable */ - image += readw(pds + 16) * 512; - } while (!last_image); + length = readw(pds + 16); + image += length * 512; + } while (length && !last_image); /* never return a size larger than the PCI resource window */ /* there are known ROMs that get the size wrong */ diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c index 66977ebf13b..ff0356fb378 100644 --- a/drivers/pnp/pnpacpi/rsparser.c +++ b/drivers/pnp/pnpacpi/rsparser.c @@ -180,20 +180,21 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res, struct pnp_dev *dev = data; struct acpi_resource_dma *dma; struct acpi_resource_vendor_typed *vendor_typed; - struct resource r = {0}; + struct resource_win win = {{0}, 0}; + struct resource *r = &win.res; int i, flags; - if (acpi_dev_resource_address_space(res, &r) - || acpi_dev_resource_ext_address_space(res, &r)) { - pnp_add_resource(dev, &r); + if (acpi_dev_resource_address_space(res, &win) + || acpi_dev_resource_ext_address_space(res, &win)) { + pnp_add_resource(dev, &win.res); return AE_OK; } - r.flags = 0; - if (acpi_dev_resource_interrupt(res, 0, &r)) { - pnpacpi_add_irqresource(dev, &r); - for (i = 1; acpi_dev_resource_interrupt(res, i, &r); i++) - pnpacpi_add_irqresource(dev, &r); + r->flags = 0; + if (acpi_dev_resource_interrupt(res, 0, r)) { + pnpacpi_add_irqresource(dev, r); + for (i = 1; acpi_dev_resource_interrupt(res, i, r); i++) + pnpacpi_add_irqresource(dev, r); if (i > 1) { /* @@ -209,7 +210,7 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res, } } return AE_OK; - } else if (r.flags & IORESOURCE_DISABLED) { + } else if (r->flags & IORESOURCE_DISABLED) { pnp_add_irq_resource(dev, 0, IORESOURCE_DISABLED); return AE_OK; } @@ -218,13 +219,13 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res, case ACPI_RESOURCE_TYPE_MEMORY24: case ACPI_RESOURCE_TYPE_MEMORY32: case ACPI_RESOURCE_TYPE_FIXED_MEMORY32: - if (acpi_dev_resource_memory(res, &r)) - pnp_add_resource(dev, &r); + if (acpi_dev_resource_memory(res, r)) + pnp_add_resource(dev, r); break; case ACPI_RESOURCE_TYPE_IO: case ACPI_RESOURCE_TYPE_FIXED_IO: - if (acpi_dev_resource_io(res, &r)) - pnp_add_resource(dev, &r); + if (acpi_dev_resource_io(res, r)) + pnp_add_resource(dev, r); break; case ACPI_RESOURCE_TYPE_DMA: dma = &res->data.dma; @@ -410,12 +411,12 @@ static __init void pnpacpi_parse_address_option(struct pnp_dev *dev, if (p->resource_type == ACPI_MEMORY_RANGE) { if (p->info.mem.write_protect == ACPI_READ_WRITE_MEMORY) flags = IORESOURCE_MEM_WRITEABLE; - pnp_register_mem_resource(dev, option_flags, p->minimum, - p->minimum, 0, p->address_length, + pnp_register_mem_resource(dev, option_flags, p->address.minimum, + p->address.minimum, 0, p->address.address_length, flags); } else if (p->resource_type == ACPI_IO_RANGE) - pnp_register_port_resource(dev, option_flags, p->minimum, - p->minimum, 0, p->address_length, + pnp_register_port_resource(dev, option_flags, p->address.minimum, + p->address.minimum, 0, p->address.address_length, IORESOURCE_IO_FIXED); } @@ -429,12 +430,12 @@ static __init void pnpacpi_parse_ext_address_option(struct pnp_dev *dev, if (p->resource_type == ACPI_MEMORY_RANGE) { if (p->info.mem.write_protect == ACPI_READ_WRITE_MEMORY) flags = IORESOURCE_MEM_WRITEABLE; - pnp_register_mem_resource(dev, option_flags, p->minimum, - p->minimum, 0, p->address_length, + pnp_register_mem_resource(dev, option_flags, p->address.minimum, + p->address.minimum, 0, p->address.address_length, flags); } else if (p->resource_type == ACPI_IO_RANGE) - pnp_register_port_resource(dev, option_flags, p->minimum, - p->minimum, 0, p->address_length, + pnp_register_port_resource(dev, option_flags, p->address.minimum, + p->address.minimum, 0, p->address.address_length, IORESOURCE_IO_FIXED); } diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c index 8bcfecd6628..eeca70ddbf6 100644 --- a/drivers/rapidio/devices/tsi721.c +++ b/drivers/rapidio/devices/tsi721.c @@ -2430,7 +2430,7 @@ static int tsi721_probe(struct pci_dev *pdev, pcie_capability_clear_and_set_word(pdev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_READRQ | PCI_EXP_DEVCTL_RELAX_EN | PCI_EXP_DEVCTL_NOSNOOP_EN, - 0x2 << MAX_READ_REQUEST_SZ_SHIFT); + PCI_EXP_DEVCTL_READRQ_512B); /* Adjust PCIe completion timeout. */ pcie_capability_clear_and_set_word(pdev, PCI_EXP_DEVCTL2, 0xf, 0x2); diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h index a7b42680a06..9d2502543ef 100644 --- a/drivers/rapidio/devices/tsi721.h +++ b/drivers/rapidio/devices/tsi721.h @@ -72,8 +72,6 @@ #define TSI721_MSIXPBA_OFFSET 0x2a000 #define TSI721_PCIECFG_EPCTL 0x400 -#define MAX_READ_REQUEST_SZ_SHIFT 12 - /* * Event Management Registers */ diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index c3a60b57a86..a6f116aa523 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -414,6 +414,14 @@ config REGULATOR_MAX77802 Exynos5420/Exynos5800 SoCs to control various voltages. It includes support for control of voltage and ramp speed. +config REGULATOR_MAX77843 + tristate "Maxim 77843 regulator" + depends on MFD_MAX77843 + help + This driver controls a Maxim 77843 regulator. + The regulator include two 'SAFEOUT' for USB(Universal Serial Bus) + This is suitable for Exynos5433 SoC chips. + config REGULATOR_MC13XXX_CORE tristate @@ -433,6 +441,15 @@ config REGULATOR_MC13892 Say y here to support the regulators found on the Freescale MC13892 PMIC. +config REGULATOR_MT6397 + tristate "MediaTek MT6397 PMIC" + depends on MFD_MT6397 + help + Say y here to select this option to enable the power regulator of + MediaTek MT6397 PMIC. + This driver supports the control of different power rails of device + through regulator interface. + config REGULATOR_PALMAS tristate "TI Palmas PMIC Regulators" depends on MFD_PALMAS diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile index 1f28ebfc6f3..2c4da15e154 100644 --- a/drivers/regulator/Makefile +++ b/drivers/regulator/Makefile @@ -55,9 +55,11 @@ obj-$(CONFIG_REGULATOR_MAX8998) += max8998.o obj-$(CONFIG_REGULATOR_MAX77686) += max77686.o obj-$(CONFIG_REGULATOR_MAX77693) += max77693.o obj-$(CONFIG_REGULATOR_MAX77802) += max77802.o +obj-$(CONFIG_REGULATOR_MAX77843) += max77843.o obj-$(CONFIG_REGULATOR_MC13783) += mc13783-regulator.o obj-$(CONFIG_REGULATOR_MC13892) += mc13892-regulator.o obj-$(CONFIG_REGULATOR_MC13XXX_CORE) += mc13xxx-regulator-core.o +obj-$(CONFIG_REGULATOR_MT6397) += mt6397-regulator.o obj-$(CONFIG_REGULATOR_QCOM_RPM) += qcom_rpm-regulator.o obj-$(CONFIG_REGULATOR_PALMAS) += palmas-regulator.o obj-$(CONFIG_REGULATOR_PFUZE100) += pfuze100-regulator.o diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index f23d7e1f2ee..e4331f5e5d7 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -32,11 +32,13 @@ #define AXP20X_FREQ_DCDC_MASK 0x0f -#define AXP20X_DESC_IO(_id, _supply, _min, _max, _step, _vreg, _vmask, _ereg, \ - _emask, _enable_val, _disable_val) \ +#define AXP20X_DESC_IO(_id, _match, _supply, _min, _max, _step, _vreg, _vmask, \ + _ereg, _emask, _enable_val, _disable_val) \ [AXP20X_##_id] = { \ .name = #_id, \ .supply_name = (_supply), \ + .of_match = of_match_ptr(_match), \ + .regulators_node = of_match_ptr("regulators"), \ .type = REGULATOR_VOLTAGE, \ .id = AXP20X_##_id, \ .n_voltages = (((_max) - (_min)) / (_step) + 1), \ @@ -52,11 +54,13 @@ .ops = &axp20x_ops, \ } -#define AXP20X_DESC(_id, _supply, _min, _max, _step, _vreg, _vmask, _ereg, \ - _emask) \ +#define AXP20X_DESC(_id, _match, _supply, _min, _max, _step, _vreg, _vmask, \ + _ereg, _emask) \ [AXP20X_##_id] = { \ .name = #_id, \ .supply_name = (_supply), \ + .of_match = of_match_ptr(_match), \ + .regulators_node = of_match_ptr("regulators"), \ .type = REGULATOR_VOLTAGE, \ .id = AXP20X_##_id, \ .n_voltages = (((_max) - (_min)) / (_step) + 1), \ @@ -70,10 +74,12 @@ .ops = &axp20x_ops, \ } -#define AXP20X_DESC_FIXED(_id, _supply, _volt) \ +#define AXP20X_DESC_FIXED(_id, _match, _supply, _volt) \ [AXP20X_##_id] = { \ .name = #_id, \ .supply_name = (_supply), \ + .of_match = of_match_ptr(_match), \ + .regulators_node = of_match_ptr("regulators"), \ .type = REGULATOR_VOLTAGE, \ .id = AXP20X_##_id, \ .n_voltages = 1, \ @@ -82,10 +88,13 @@ .ops = &axp20x_ops_fixed \ } -#define AXP20X_DESC_TABLE(_id, _supply, _table, _vreg, _vmask, _ereg, _emask) \ +#define AXP20X_DESC_TABLE(_id, _match, _supply, _table, _vreg, _vmask, _ereg, \ + _emask) \ [AXP20X_##_id] = { \ .name = #_id, \ .supply_name = (_supply), \ + .of_match = of_match_ptr(_match), \ + .regulators_node = of_match_ptr("regulators"), \ .type = REGULATOR_VOLTAGE, \ .id = AXP20X_##_id, \ .n_voltages = ARRAY_SIZE(_table), \ @@ -127,36 +136,20 @@ static struct regulator_ops axp20x_ops = { }; static const struct regulator_desc axp20x_regulators[] = { - AXP20X_DESC(DCDC2, "vin2", 700, 2275, 25, AXP20X_DCDC2_V_OUT, 0x3f, - AXP20X_PWR_OUT_CTRL, 0x10), - AXP20X_DESC(DCDC3, "vin3", 700, 3500, 25, AXP20X_DCDC3_V_OUT, 0x7f, - AXP20X_PWR_OUT_CTRL, 0x02), - AXP20X_DESC_FIXED(LDO1, "acin", 1300), - AXP20X_DESC(LDO2, "ldo24in", 1800, 3300, 100, AXP20X_LDO24_V_OUT, 0xf0, - AXP20X_PWR_OUT_CTRL, 0x04), - AXP20X_DESC(LDO3, "ldo3in", 700, 3500, 25, AXP20X_LDO3_V_OUT, 0x7f, - AXP20X_PWR_OUT_CTRL, 0x40), - AXP20X_DESC_TABLE(LDO4, "ldo24in", axp20x_ldo4_data, AXP20X_LDO24_V_OUT, 0x0f, - AXP20X_PWR_OUT_CTRL, 0x08), - AXP20X_DESC_IO(LDO5, "ldo5in", 1800, 3300, 100, AXP20X_LDO5_V_OUT, 0xf0, - AXP20X_GPIO0_CTRL, 0x07, AXP20X_IO_ENABLED, - AXP20X_IO_DISABLED), -}; - -#define AXP_MATCH(_name, _id) \ - [AXP20X_##_id] = { \ - .name = #_name, \ - .driver_data = (void *) &axp20x_regulators[AXP20X_##_id], \ - } - -static struct of_regulator_match axp20x_matches[] = { - AXP_MATCH(dcdc2, DCDC2), - AXP_MATCH(dcdc3, DCDC3), - AXP_MATCH(ldo1, LDO1), - AXP_MATCH(ldo2, LDO2), - AXP_MATCH(ldo3, LDO3), - AXP_MATCH(ldo4, LDO4), - AXP_MATCH(ldo5, LDO5), + AXP20X_DESC(DCDC2, "dcdc2", "vin2", 700, 2275, 25, AXP20X_DCDC2_V_OUT, + 0x3f, AXP20X_PWR_OUT_CTRL, 0x10), + AXP20X_DESC(DCDC3, "dcdc3", "vin3", 700, 3500, 25, AXP20X_DCDC3_V_OUT, + 0x7f, AXP20X_PWR_OUT_CTRL, 0x02), + AXP20X_DESC_FIXED(LDO1, "ldo1", "acin", 1300), + AXP20X_DESC(LDO2, "ldo2", "ldo24in", 1800, 3300, 100, + AXP20X_LDO24_V_OUT, 0xf0, AXP20X_PWR_OUT_CTRL, 0x04), + AXP20X_DESC(LDO3, "ldo3", "ldo3in", 700, 3500, 25, AXP20X_LDO3_V_OUT, + 0x7f, AXP20X_PWR_OUT_CTRL, 0x40), + AXP20X_DESC_TABLE(LDO4, "ldo4", "ldo24in", axp20x_ldo4_data, + AXP20X_LDO24_V_OUT, 0x0f, AXP20X_PWR_OUT_CTRL, 0x08), + AXP20X_DESC_IO(LDO5, "ldo5", "ldo5in", 1800, 3300, 100, + AXP20X_LDO5_V_OUT, 0xf0, AXP20X_GPIO0_CTRL, 0x07, + AXP20X_IO_ENABLED, AXP20X_IO_DISABLED), }; static int axp20x_set_dcdc_freq(struct platform_device *pdev, u32 dcdcfreq) @@ -193,13 +186,6 @@ static int axp20x_regulator_parse_dt(struct platform_device *pdev) if (!regulators) { dev_warn(&pdev->dev, "regulators node not found\n"); } else { - ret = of_regulator_match(&pdev->dev, regulators, axp20x_matches, - ARRAY_SIZE(axp20x_matches)); - if (ret < 0) { - dev_err(&pdev->dev, "Error parsing regulator init data: %d\n", ret); - return ret; - } - dcdcfreq = 1500; of_property_read_u32(regulators, "x-powers,dcdc-freq", &dcdcfreq); ret = axp20x_set_dcdc_freq(pdev, dcdcfreq); @@ -233,23 +219,17 @@ static int axp20x_regulator_probe(struct platform_device *pdev) { struct regulator_dev *rdev; struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent); - struct regulator_config config = { }; - struct regulator_init_data *init_data; + struct regulator_config config = { + .dev = pdev->dev.parent, + .regmap = axp20x->regmap, + }; int ret, i; u32 workmode; - ret = axp20x_regulator_parse_dt(pdev); - if (ret) - return ret; + /* This only sets the dcdc freq. Ignore any errors */ + axp20x_regulator_parse_dt(pdev); for (i = 0; i < AXP20X_REG_ID_MAX; i++) { - init_data = axp20x_matches[i].init_data; - - config.dev = pdev->dev.parent; - config.init_data = init_data; - config.regmap = axp20x->regmap; - config.of_node = axp20x_matches[i].of_node; - rdev = devm_regulator_register(&pdev->dev, &axp20x_regulators[i], &config); if (IS_ERR(rdev)) { @@ -259,7 +239,8 @@ static int axp20x_regulator_probe(struct platform_device *pdev) return PTR_ERR(rdev); } - ret = of_property_read_u32(axp20x_matches[i].of_node, "x-powers,dcdc-workmode", + ret = of_property_read_u32(rdev->dev.of_node, + "x-powers,dcdc-workmode", &workmode); if (!ret) { if (axp20x_set_dcdc_workmode(rdev, i, workmode)) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 9c48fb32f66..b899947d839 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -632,49 +632,34 @@ static ssize_t regulator_bypass_show(struct device *dev, static DEVICE_ATTR(bypass, 0444, regulator_bypass_show, NULL); -/* - * These are the only attributes are present for all regulators. - * Other attributes are a function of regulator functionality. - */ -static struct attribute *regulator_dev_attrs[] = { - &dev_attr_name.attr, - &dev_attr_num_users.attr, - &dev_attr_type.attr, - NULL, -}; -ATTRIBUTE_GROUPS(regulator_dev); - -static void regulator_dev_release(struct device *dev) -{ - struct regulator_dev *rdev = dev_get_drvdata(dev); - kfree(rdev); -} - -static struct class regulator_class = { - .name = "regulator", - .dev_release = regulator_dev_release, - .dev_groups = regulator_dev_groups, -}; - /* Calculate the new optimum regulator operating mode based on the new total * consumer load. All locks held by caller */ -static void drms_uA_update(struct regulator_dev *rdev) +static int drms_uA_update(struct regulator_dev *rdev) { struct regulator *sibling; int current_uA = 0, output_uV, input_uV, err; unsigned int mode; + /* + * first check to see if we can set modes at all, otherwise just + * tell the consumer everything is OK. + */ err = regulator_check_drms(rdev); - if (err < 0 || !rdev->desc->ops->get_optimum_mode || - (!rdev->desc->ops->get_voltage && - !rdev->desc->ops->get_voltage_sel) || - !rdev->desc->ops->set_mode) - return; + if (err < 0) + return 0; + + if (!rdev->desc->ops->get_optimum_mode) + return 0; + + if (!rdev->desc->ops->set_mode) + return -EINVAL; /* get output voltage */ output_uV = _regulator_get_voltage(rdev); - if (output_uV <= 0) - return; + if (output_uV <= 0) { + rdev_err(rdev, "invalid output voltage found\n"); + return -EINVAL; + } /* get input voltage */ input_uV = 0; @@ -682,8 +667,10 @@ static void drms_uA_update(struct regulator_dev *rdev) input_uV = regulator_get_voltage(rdev->supply); if (input_uV <= 0) input_uV = rdev->constraints->input_uV; - if (input_uV <= 0) - return; + if (input_uV <= 0) { + rdev_err(rdev, "invalid input voltage found\n"); + return -EINVAL; + } /* calc total requested load */ list_for_each_entry(sibling, &rdev->consumer_list, list) @@ -695,8 +682,17 @@ static void drms_uA_update(struct regulator_dev *rdev) /* check the new mode is allowed */ err = regulator_mode_constrain(rdev, &mode); - if (err == 0) - rdev->desc->ops->set_mode(rdev, mode); + if (err < 0) { + rdev_err(rdev, "failed to get optimum mode @ %d uA %d -> %d uV\n", + current_uA, input_uV, output_uV); + return err; + } + + err = rdev->desc->ops->set_mode(rdev, mode); + if (err < 0) + rdev_err(rdev, "failed to set optimum mode %x\n", mode); + + return err; } static int suspend_set_state(struct regulator_dev *rdev, @@ -3026,75 +3022,13 @@ EXPORT_SYMBOL_GPL(regulator_get_mode); int regulator_set_optimum_mode(struct regulator *regulator, int uA_load) { struct regulator_dev *rdev = regulator->rdev; - struct regulator *consumer; - int ret, output_uV, input_uV = 0, total_uA_load = 0; - unsigned int mode; - - if (rdev->supply) - input_uV = regulator_get_voltage(rdev->supply); + int ret; mutex_lock(&rdev->mutex); - - /* - * first check to see if we can set modes at all, otherwise just - * tell the consumer everything is OK. - */ regulator->uA_load = uA_load; - ret = regulator_check_drms(rdev); - if (ret < 0) { - ret = 0; - goto out; - } - - if (!rdev->desc->ops->get_optimum_mode) - goto out; - - /* - * we can actually do this so any errors are indicators of - * potential real failure. - */ - ret = -EINVAL; - - if (!rdev->desc->ops->set_mode) - goto out; - - /* get output voltage */ - output_uV = _regulator_get_voltage(rdev); - if (output_uV <= 0) { - rdev_err(rdev, "invalid output voltage found\n"); - goto out; - } - - /* No supply? Use constraint voltage */ - if (input_uV <= 0) - input_uV = rdev->constraints->input_uV; - if (input_uV <= 0) { - rdev_err(rdev, "invalid input voltage found\n"); - goto out; - } - - /* calc total requested load for this regulator */ - list_for_each_entry(consumer, &rdev->consumer_list, list) - total_uA_load += consumer->uA_load; - - mode = rdev->desc->ops->get_optimum_mode(rdev, - input_uV, output_uV, - total_uA_load); - ret = regulator_mode_constrain(rdev, &mode); - if (ret < 0) { - rdev_err(rdev, "failed to get optimum mode @ %d uA %d -> %d uV\n", - total_uA_load, input_uV, output_uV); - goto out; - } - - ret = rdev->desc->ops->set_mode(rdev, mode); - if (ret < 0) { - rdev_err(rdev, "failed to set optimum mode %x\n", mode); - goto out; - } - ret = mode; -out: + ret = drms_uA_update(rdev); mutex_unlock(&rdev->mutex); + return ret; } EXPORT_SYMBOL_GPL(regulator_set_optimum_mode); @@ -3436,126 +3370,136 @@ int regulator_mode_to_status(unsigned int mode) } EXPORT_SYMBOL_GPL(regulator_mode_to_status); +static struct attribute *regulator_dev_attrs[] = { + &dev_attr_name.attr, + &dev_attr_num_users.attr, + &dev_attr_type.attr, + &dev_attr_microvolts.attr, + &dev_attr_microamps.attr, + &dev_attr_opmode.attr, + &dev_attr_state.attr, + &dev_attr_status.attr, + &dev_attr_bypass.attr, + &dev_attr_requested_microamps.attr, + &dev_attr_min_microvolts.attr, + &dev_attr_max_microvolts.attr, + &dev_attr_min_microamps.attr, + &dev_attr_max_microamps.attr, + &dev_attr_suspend_standby_state.attr, + &dev_attr_suspend_mem_state.attr, + &dev_attr_suspend_disk_state.attr, + &dev_attr_suspend_standby_microvolts.attr, + &dev_attr_suspend_mem_microvolts.attr, + &dev_attr_suspend_disk_microvolts.attr, + &dev_attr_suspend_standby_mode.attr, + &dev_attr_suspend_mem_mode.attr, + &dev_attr_suspend_disk_mode.attr, + NULL +}; + /* * To avoid cluttering sysfs (and memory) with useless state, only * create attributes that can be meaningfully displayed. */ -static int add_regulator_attributes(struct regulator_dev *rdev) +static umode_t regulator_attr_is_visible(struct kobject *kobj, + struct attribute *attr, int idx) { - struct device *dev = &rdev->dev; + struct device *dev = kobj_to_dev(kobj); + struct regulator_dev *rdev = container_of(dev, struct regulator_dev, dev); const struct regulator_ops *ops = rdev->desc->ops; - int status = 0; + umode_t mode = attr->mode; + + /* these three are always present */ + if (attr == &dev_attr_name.attr || + attr == &dev_attr_num_users.attr || + attr == &dev_attr_type.attr) + return mode; /* some attributes need specific methods to be displayed */ - if ((ops->get_voltage && ops->get_voltage(rdev) >= 0) || - (ops->get_voltage_sel && ops->get_voltage_sel(rdev) >= 0) || - (ops->list_voltage && ops->list_voltage(rdev, 0) >= 0) || - (rdev->desc->fixed_uV && (rdev->desc->n_voltages == 1))) { - status = device_create_file(dev, &dev_attr_microvolts); - if (status < 0) - return status; - } - if (ops->get_current_limit) { - status = device_create_file(dev, &dev_attr_microamps); - if (status < 0) - return status; - } - if (ops->get_mode) { - status = device_create_file(dev, &dev_attr_opmode); - if (status < 0) - return status; - } - if (rdev->ena_pin || ops->is_enabled) { - status = device_create_file(dev, &dev_attr_state); - if (status < 0) - return status; - } - if (ops->get_status) { - status = device_create_file(dev, &dev_attr_status); - if (status < 0) - return status; - } - if (ops->get_bypass) { - status = device_create_file(dev, &dev_attr_bypass); - if (status < 0) - return status; + if (attr == &dev_attr_microvolts.attr) { + if ((ops->get_voltage && ops->get_voltage(rdev) >= 0) || + (ops->get_voltage_sel && ops->get_voltage_sel(rdev) >= 0) || + (ops->list_voltage && ops->list_voltage(rdev, 0) >= 0) || + (rdev->desc->fixed_uV && rdev->desc->n_voltages == 1)) + return mode; + return 0; } + if (attr == &dev_attr_microamps.attr) + return ops->get_current_limit ? mode : 0; + + if (attr == &dev_attr_opmode.attr) + return ops->get_mode ? mode : 0; + + if (attr == &dev_attr_state.attr) + return (rdev->ena_pin || ops->is_enabled) ? mode : 0; + + if (attr == &dev_attr_status.attr) + return ops->get_status ? mode : 0; + + if (attr == &dev_attr_bypass.attr) + return ops->get_bypass ? mode : 0; + /* some attributes are type-specific */ - if (rdev->desc->type == REGULATOR_CURRENT) { - status = device_create_file(dev, &dev_attr_requested_microamps); - if (status < 0) - return status; - } + if (attr == &dev_attr_requested_microamps.attr) + return rdev->desc->type == REGULATOR_CURRENT ? mode : 0; /* all the other attributes exist to support constraints; * don't show them if there are no constraints, or if the * relevant supporting methods are missing. */ if (!rdev->constraints) - return status; + return 0; /* constraints need specific supporting methods */ - if (ops->set_voltage || ops->set_voltage_sel) { - status = device_create_file(dev, &dev_attr_min_microvolts); - if (status < 0) - return status; - status = device_create_file(dev, &dev_attr_max_microvolts); - if (status < 0) - return status; - } - if (ops->set_current_limit) { - status = device_create_file(dev, &dev_attr_min_microamps); - if (status < 0) - return status; - status = device_create_file(dev, &dev_attr_max_microamps); - if (status < 0) - return status; - } - - status = device_create_file(dev, &dev_attr_suspend_standby_state); - if (status < 0) - return status; - status = device_create_file(dev, &dev_attr_suspend_mem_state); - if (status < 0) - return status; - status = device_create_file(dev, &dev_attr_suspend_disk_state); - if (status < 0) - return status; + if (attr == &dev_attr_min_microvolts.attr || + attr == &dev_attr_max_microvolts.attr) + return (ops->set_voltage || ops->set_voltage_sel) ? mode : 0; + + if (attr == &dev_attr_min_microamps.attr || + attr == &dev_attr_max_microamps.attr) + return ops->set_current_limit ? mode : 0; - if (ops->set_suspend_voltage) { - status = device_create_file(dev, - &dev_attr_suspend_standby_microvolts); - if (status < 0) - return status; - status = device_create_file(dev, - &dev_attr_suspend_mem_microvolts); - if (status < 0) - return status; - status = device_create_file(dev, - &dev_attr_suspend_disk_microvolts); - if (status < 0) - return status; - } - - if (ops->set_suspend_mode) { - status = device_create_file(dev, - &dev_attr_suspend_standby_mode); - if (status < 0) - return status; - status = device_create_file(dev, - &dev_attr_suspend_mem_mode); - if (status < 0) - return status; - status = device_create_file(dev, - &dev_attr_suspend_disk_mode); - if (status < 0) - return status; - } - - return status; + if (attr == &dev_attr_suspend_standby_state.attr || + attr == &dev_attr_suspend_mem_state.attr || + attr == &dev_attr_suspend_disk_state.attr) + return mode; + + if (attr == &dev_attr_suspend_standby_microvolts.attr || + attr == &dev_attr_suspend_mem_microvolts.attr || + attr == &dev_attr_suspend_disk_microvolts.attr) + return ops->set_suspend_voltage ? mode : 0; + + if (attr == &dev_attr_suspend_standby_mode.attr || + attr == &dev_attr_suspend_mem_mode.attr || + attr == &dev_attr_suspend_disk_mode.attr) + return ops->set_suspend_mode ? mode : 0; + + return mode; } +static const struct attribute_group regulator_dev_group = { + .attrs = regulator_dev_attrs, + .is_visible = regulator_attr_is_visible, +}; + +static const struct attribute_group *regulator_dev_groups[] = { + ®ulator_dev_group, + NULL +}; + +static void regulator_dev_release(struct device *dev) +{ + struct regulator_dev *rdev = dev_get_drvdata(dev); + kfree(rdev); +} + +static struct class regulator_class = { + .name = "regulator", + .dev_release = regulator_dev_release, + .dev_groups = regulator_dev_groups, +}; + static void rdev_init_debugfs(struct regulator_dev *rdev) { rdev->debugfs = debugfs_create_dir(rdev_get_name(rdev), debugfs_root); @@ -3575,7 +3519,7 @@ static void rdev_init_debugfs(struct regulator_dev *rdev) /** * regulator_register - register regulator * @regulator_desc: regulator to register - * @config: runtime configuration for regulator + * @cfg: runtime configuration for regulator * * Called by regulator drivers to register a regulator. * Returns a valid pointer to struct regulator_dev on success @@ -3583,20 +3527,21 @@ static void rdev_init_debugfs(struct regulator_dev *rdev) */ struct regulator_dev * regulator_register(const struct regulator_desc *regulator_desc, - const struct regulator_config *config) + const struct regulator_config *cfg) { const struct regulation_constraints *constraints = NULL; const struct regulator_init_data *init_data; - static atomic_t regulator_no = ATOMIC_INIT(0); + struct regulator_config *config = NULL; + static atomic_t regulator_no = ATOMIC_INIT(-1); struct regulator_dev *rdev; struct device *dev; int ret, i; const char *supply = NULL; - if (regulator_desc == NULL || config == NULL) + if (regulator_desc == NULL || cfg == NULL) return ERR_PTR(-EINVAL); - dev = config->dev; + dev = cfg->dev; WARN_ON(!dev); if (regulator_desc->name == NULL || regulator_desc->ops == NULL) @@ -3626,7 +3571,17 @@ regulator_register(const struct regulator_desc *regulator_desc, if (rdev == NULL) return ERR_PTR(-ENOMEM); - init_data = regulator_of_get_init_data(dev, regulator_desc, + /* + * Duplicate the config so the driver could override it after + * parsing init data. + */ + config = kmemdup(cfg, sizeof(*cfg), GFP_KERNEL); + if (config == NULL) { + kfree(rdev); + return ERR_PTR(-ENOMEM); + } + + init_data = regulator_of_get_init_data(dev, regulator_desc, config, &rdev->dev.of_node); if (!init_data) { init_data = config->init_data; @@ -3660,8 +3615,8 @@ regulator_register(const struct regulator_desc *regulator_desc, /* register with sysfs */ rdev->dev.class = ®ulator_class; rdev->dev.parent = dev; - dev_set_name(&rdev->dev, "regulator.%d", - atomic_inc_return(®ulator_no) - 1); + dev_set_name(&rdev->dev, "regulator.%lu", + (unsigned long) atomic_inc_return(®ulator_no)); ret = device_register(&rdev->dev); if (ret != 0) { put_device(&rdev->dev); @@ -3694,11 +3649,6 @@ regulator_register(const struct regulator_desc *regulator_desc, if (ret < 0) goto scrub; - /* add attributes supported by this regulator */ - ret = add_regulator_attributes(rdev); - if (ret < 0) - goto scrub; - if (init_data && init_data->supply_regulator) supply = init_data->supply_regulator; else if (regulator_desc->supply_name) @@ -3754,6 +3704,7 @@ add_dev: rdev_init_debugfs(rdev); out: mutex_unlock(®ulator_list_mutex); + kfree(config); return rdev; unset_supplies: diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c index c78d2106d6c..01343419555 100644 --- a/drivers/regulator/da9211-regulator.c +++ b/drivers/regulator/da9211-regulator.c @@ -24,6 +24,7 @@ #include <linux/regmap.h> #include <linux/irq.h> #include <linux/interrupt.h> +#include <linux/of_gpio.h> #include <linux/regulator/of_regulator.h> #include <linux/regulator/da9211.h> #include "da9211-regulator.h" @@ -276,7 +277,10 @@ static struct da9211_pdata *da9211_parse_regulators_dt( continue; pdata->init_data[n] = da9211_matches[i].init_data; - + pdata->reg_node[n] = da9211_matches[i].of_node; + pdata->gpio_ren[n] = + of_get_named_gpio(da9211_matches[i].of_node, + "enable-gpios", 0); n++; } @@ -364,7 +368,15 @@ static int da9211_regulator_init(struct da9211 *chip) config.dev = chip->dev; config.driver_data = chip; config.regmap = chip->regmap; - config.of_node = chip->dev->of_node; + config.of_node = chip->pdata->reg_node[i]; + + if (gpio_is_valid(chip->pdata->gpio_ren[i])) { + config.ena_gpio = chip->pdata->gpio_ren[i]; + config.ena_gpio_initialized = true; + } else { + config.ena_gpio = -EINVAL; + config.ena_gpio_initialized = false; + } chip->rdev[i] = devm_regulator_register(chip->dev, &da9211_regulators[i], &config); diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c index 6c43ab2d512..3c25db89a02 100644 --- a/drivers/regulator/fan53555.c +++ b/drivers/regulator/fan53555.c @@ -147,7 +147,7 @@ static unsigned int fan53555_get_mode(struct regulator_dev *rdev) return REGULATOR_MODE_NORMAL; } -static int slew_rates[] = { +static const int slew_rates[] = { 64000, 32000, 16000, @@ -296,7 +296,7 @@ static int fan53555_regulator_register(struct fan53555_device_info *di, return PTR_ERR_OR_ZERO(di->rdev); } -static struct regmap_config fan53555_regmap_config = { +static const struct regmap_config fan53555_regmap_config = { .reg_bits = 8, .val_bits = 8, }; diff --git a/drivers/regulator/internal.h b/drivers/regulator/internal.h index 80ba2a35a04..c74ac873402 100644 --- a/drivers/regulator/internal.h +++ b/drivers/regulator/internal.h @@ -38,11 +38,13 @@ struct regulator { #ifdef CONFIG_OF struct regulator_init_data *regulator_of_get_init_data(struct device *dev, const struct regulator_desc *desc, + struct regulator_config *config, struct device_node **node); #else static inline struct regulator_init_data * regulator_of_get_init_data(struct device *dev, const struct regulator_desc *desc, + struct regulator_config *config, struct device_node **node) { return NULL; diff --git a/drivers/regulator/isl9305.c b/drivers/regulator/isl9305.c index 92fefd98da5..6e3a15fe00f 100644 --- a/drivers/regulator/isl9305.c +++ b/drivers/regulator/isl9305.c @@ -177,8 +177,10 @@ static int isl9305_i2c_probe(struct i2c_client *i2c, #ifdef CONFIG_OF static const struct of_device_id isl9305_dt_ids[] = { - { .compatible = "isl,isl9305" }, - { .compatible = "isl,isl9305h" }, + { .compatible = "isl,isl9305" }, /* for backward compat., don't use */ + { .compatible = "isil,isl9305" }, + { .compatible = "isl,isl9305h" }, /* for backward compat., don't use */ + { .compatible = "isil,isl9305h" }, {}, }; #endif diff --git a/drivers/regulator/lp872x.c b/drivers/regulator/lp872x.c index 021d64d856b..3de328ab41f 100644 --- a/drivers/regulator/lp872x.c +++ b/drivers/regulator/lp872x.c @@ -106,7 +106,6 @@ struct lp872x { struct device *dev; enum lp872x_id chipid; struct lp872x_platform_data *pdata; - struct regulator_dev **regulators; int num_regulators; enum lp872x_dvs_state dvs_pin; int dvs_gpio; @@ -801,8 +800,6 @@ static int lp872x_regulator_register(struct lp872x *lp) dev_err(lp->dev, "regulator register err"); return PTR_ERR(rdev); } - - *(lp->regulators + i) = rdev; } return 0; @@ -906,7 +903,7 @@ static struct lp872x_platform_data static int lp872x_probe(struct i2c_client *cl, const struct i2c_device_id *id) { struct lp872x *lp; - int ret, size, num_regulators; + int ret; const int lp872x_num_regulators[] = { [LP8720] = LP8720_NUM_REGULATORS, [LP8725] = LP8725_NUM_REGULATORS, @@ -918,38 +915,27 @@ static int lp872x_probe(struct i2c_client *cl, const struct i2c_device_id *id) lp = devm_kzalloc(&cl->dev, sizeof(struct lp872x), GFP_KERNEL); if (!lp) - goto err_mem; - - num_regulators = lp872x_num_regulators[id->driver_data]; - size = sizeof(struct regulator_dev *) * num_regulators; + return -ENOMEM; - lp->regulators = devm_kzalloc(&cl->dev, size, GFP_KERNEL); - if (!lp->regulators) - goto err_mem; + lp->num_regulators = lp872x_num_regulators[id->driver_data]; lp->regmap = devm_regmap_init_i2c(cl, &lp872x_regmap_config); if (IS_ERR(lp->regmap)) { ret = PTR_ERR(lp->regmap); dev_err(&cl->dev, "regmap init i2c err: %d\n", ret); - goto err_dev; + return ret; } lp->dev = &cl->dev; lp->pdata = dev_get_platdata(&cl->dev); lp->chipid = id->driver_data; - lp->num_regulators = num_regulators; i2c_set_clientdata(cl, lp); ret = lp872x_config(lp); if (ret) - goto err_dev; + return ret; return lp872x_regulator_register(lp); - -err_mem: - return -ENOMEM; -err_dev: - return ret; } static const struct of_device_id lp872x_dt_ids[] = { diff --git a/drivers/regulator/max14577.c b/drivers/regulator/max14577.c index bf9a44c5fdd..b3678d28961 100644 --- a/drivers/regulator/max14577.c +++ b/drivers/regulator/max14577.c @@ -103,6 +103,8 @@ static struct regulator_ops max14577_charger_ops = { static const struct regulator_desc max14577_supported_regulators[] = { [MAX14577_SAFEOUT] = { .name = "SAFEOUT", + .of_match = of_match_ptr("SAFEOUT"), + .regulators_node = of_match_ptr("regulators"), .id = MAX14577_SAFEOUT, .ops = &max14577_safeout_ops, .type = REGULATOR_VOLTAGE, @@ -114,6 +116,8 @@ static const struct regulator_desc max14577_supported_regulators[] = { }, [MAX14577_CHARGER] = { .name = "CHARGER", + .of_match = of_match_ptr("CHARGER"), + .regulators_node = of_match_ptr("regulators"), .id = MAX14577_CHARGER, .ops = &max14577_charger_ops, .type = REGULATOR_CURRENT, @@ -137,6 +141,8 @@ static struct regulator_ops max77836_ldo_ops = { static const struct regulator_desc max77836_supported_regulators[] = { [MAX14577_SAFEOUT] = { .name = "SAFEOUT", + .of_match = of_match_ptr("SAFEOUT"), + .regulators_node = of_match_ptr("regulators"), .id = MAX14577_SAFEOUT, .ops = &max14577_safeout_ops, .type = REGULATOR_VOLTAGE, @@ -148,6 +154,8 @@ static const struct regulator_desc max77836_supported_regulators[] = { }, [MAX14577_CHARGER] = { .name = "CHARGER", + .of_match = of_match_ptr("CHARGER"), + .regulators_node = of_match_ptr("regulators"), .id = MAX14577_CHARGER, .ops = &max14577_charger_ops, .type = REGULATOR_CURRENT, @@ -157,6 +165,8 @@ static const struct regulator_desc max77836_supported_regulators[] = { }, [MAX77836_LDO1] = { .name = "LDO1", + .of_match = of_match_ptr("LDO1"), + .regulators_node = of_match_ptr("regulators"), .id = MAX77836_LDO1, .ops = &max77836_ldo_ops, .type = REGULATOR_VOLTAGE, @@ -171,6 +181,8 @@ static const struct regulator_desc max77836_supported_regulators[] = { }, [MAX77836_LDO2] = { .name = "LDO2", + .of_match = of_match_ptr("LDO2"), + .regulators_node = of_match_ptr("regulators"), .id = MAX77836_LDO2, .ops = &max77836_ldo_ops, .type = REGULATOR_VOLTAGE, @@ -198,43 +210,6 @@ static struct of_regulator_match max77836_regulator_matches[] = { { .name = "LDO2", }, }; -static int max14577_regulator_dt_parse_pdata(struct platform_device *pdev, - enum maxim_device_type dev_type) -{ - int ret; - struct device_node *np; - struct of_regulator_match *regulator_matches; - unsigned int regulator_matches_size; - - np = of_get_child_by_name(pdev->dev.parent->of_node, "regulators"); - if (!np) { - dev_err(&pdev->dev, "Failed to get child OF node for regulators\n"); - return -EINVAL; - } - - switch (dev_type) { - case MAXIM_DEVICE_TYPE_MAX77836: - regulator_matches = max77836_regulator_matches; - regulator_matches_size = ARRAY_SIZE(max77836_regulator_matches); - break; - case MAXIM_DEVICE_TYPE_MAX14577: - default: - regulator_matches = max14577_regulator_matches; - regulator_matches_size = ARRAY_SIZE(max14577_regulator_matches); - } - - ret = of_regulator_match(&pdev->dev, np, regulator_matches, - regulator_matches_size); - if (ret < 0) - dev_err(&pdev->dev, "Error parsing regulator init data: %d\n", ret); - else - ret = 0; - - of_node_put(np); - - return ret; -} - static inline struct regulator_init_data *match_init_data(int index, enum maxim_device_type dev_type) { @@ -261,11 +236,6 @@ static inline struct device_node *match_of_node(int index, } } #else /* CONFIG_OF */ -static int max14577_regulator_dt_parse_pdata(struct platform_device *pdev, - enum maxim_device_type dev_type) -{ - return 0; -} static inline struct regulator_init_data *match_init_data(int index, enum maxim_device_type dev_type) { @@ -308,16 +278,12 @@ static int max14577_regulator_probe(struct platform_device *pdev) { struct max14577 *max14577 = dev_get_drvdata(pdev->dev.parent); struct max14577_platform_data *pdata = dev_get_platdata(max14577->dev); - int i, ret; + int i, ret = 0; struct regulator_config config = {}; const struct regulator_desc *supported_regulators; unsigned int supported_regulators_size; enum maxim_device_type dev_type = max14577->dev_type; - ret = max14577_regulator_dt_parse_pdata(pdev, dev_type); - if (ret) - return ret; - switch (dev_type) { case MAXIM_DEVICE_TYPE_MAX77836: supported_regulators = max77836_supported_regulators; @@ -329,7 +295,7 @@ static int max14577_regulator_probe(struct platform_device *pdev) supported_regulators_size = ARRAY_SIZE(max14577_supported_regulators); } - config.dev = &pdev->dev; + config.dev = max14577->dev; config.driver_data = max14577; for (i = 0; i < supported_regulators_size; i++) { diff --git a/drivers/regulator/max77686.c b/drivers/regulator/max77686.c index 10d206266ac..15fb1416bfb 100644 --- a/drivers/regulator/max77686.c +++ b/drivers/regulator/max77686.c @@ -26,6 +26,7 @@ #include <linux/bug.h> #include <linux/err.h> #include <linux/gpio.h> +#include <linux/of_gpio.h> #include <linux/slab.h> #include <linux/platform_device.h> #include <linux/regulator/driver.h> @@ -46,6 +47,11 @@ #define MAX77686_DVS_UVSTEP 12500 /* + * Value for configuring buck[89] and LDO{20,21,22} as GPIO control. + * It is the same as 'off' for other regulators. + */ +#define MAX77686_GPIO_CONTROL 0x0 +/* * Values used for configuring LDOs and bucks. * Forcing low power mode: LDO1, 3-5, 9, 13, 17-26 */ @@ -82,6 +88,8 @@ enum max77686_ramp_rate { }; struct max77686_data { + u64 gpio_enabled:MAX77686_REGULATORS; + /* Array indexed by regulator id */ unsigned int opmode[MAX77686_REGULATORS]; }; @@ -100,6 +108,26 @@ static unsigned int max77686_get_opmode_shift(int id) } } +/* + * When regulator is configured for GPIO control then it + * replaces "normal" mode. Any change from low power mode to normal + * should actually change to GPIO control. + * Map normal mode to proper value for such regulators. + */ +static unsigned int max77686_map_normal_mode(struct max77686_data *max77686, + int id) +{ + switch (id) { + case MAX77686_BUCK8: + case MAX77686_BUCK9: + case MAX77686_LDO20 ... MAX77686_LDO22: + if (max77686->gpio_enabled & (1 << id)) + return MAX77686_GPIO_CONTROL; + } + + return MAX77686_NORMAL; +} + /* Some BUCKs and LDOs supports Normal[ON/OFF] mode during suspend */ static int max77686_set_suspend_disable(struct regulator_dev *rdev) { @@ -136,7 +164,7 @@ static int max77686_set_suspend_mode(struct regulator_dev *rdev, val = MAX77686_LDO_LOWPOWER_PWRREQ; break; case REGULATOR_MODE_NORMAL: /* ON in Normal Mode */ - val = MAX77686_NORMAL; + val = max77686_map_normal_mode(max77686, id); break; default: pr_warn("%s: regulator_suspend_mode : 0x%x not supported\n", @@ -160,7 +188,7 @@ static int max77686_ldo_set_suspend_mode(struct regulator_dev *rdev, { unsigned int val; struct max77686_data *max77686 = rdev_get_drvdata(rdev); - int ret; + int ret, id = rdev_get_id(rdev); switch (mode) { case REGULATOR_MODE_STANDBY: /* switch off */ @@ -170,7 +198,7 @@ static int max77686_ldo_set_suspend_mode(struct regulator_dev *rdev, val = MAX77686_LDO_LOWPOWER_PWRREQ; break; case REGULATOR_MODE_NORMAL: /* ON in Normal Mode */ - val = MAX77686_NORMAL; + val = max77686_map_normal_mode(max77686, id); break; default: pr_warn("%s: regulator_suspend_mode : 0x%x not supported\n", @@ -184,7 +212,7 @@ static int max77686_ldo_set_suspend_mode(struct regulator_dev *rdev, if (ret) return ret; - max77686->opmode[rdev_get_id(rdev)] = val; + max77686->opmode[id] = val; return 0; } @@ -197,7 +225,7 @@ static int max77686_enable(struct regulator_dev *rdev) shift = max77686_get_opmode_shift(id); if (max77686->opmode[id] == MAX77686_OFF_PWRREQ) - max77686->opmode[id] = MAX77686_NORMAL; + max77686->opmode[id] = max77686_map_normal_mode(max77686, id); return regmap_update_bits(rdev->regmap, rdev->desc->enable_reg, rdev->desc->enable_mask, @@ -229,6 +257,36 @@ static int max77686_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay) MAX77686_RAMP_RATE_MASK, ramp_value << 6); } +static int max77686_of_parse_cb(struct device_node *np, + const struct regulator_desc *desc, + struct regulator_config *config) +{ + struct max77686_data *max77686 = config->driver_data; + + switch (desc->id) { + case MAX77686_BUCK8: + case MAX77686_BUCK9: + case MAX77686_LDO20 ... MAX77686_LDO22: + config->ena_gpio = of_get_named_gpio(np, + "maxim,ena-gpios", 0); + config->ena_gpio_flags = GPIOF_OUT_INIT_HIGH; + config->ena_gpio_initialized = true; + break; + default: + return 0; + } + + if (gpio_is_valid(config->ena_gpio)) { + max77686->gpio_enabled |= (1 << desc->id); + + return regmap_update_bits(config->regmap, desc->enable_reg, + desc->enable_mask, + MAX77686_GPIO_CONTROL); + } + + return 0; +} + static struct regulator_ops max77686_ops = { .list_voltage = regulator_list_voltage_linear, .map_voltage = regulator_map_voltage_linear, @@ -283,6 +341,7 @@ static struct regulator_ops max77686_buck_dvs_ops = { .name = "LDO"#num, \ .of_match = of_match_ptr("LDO"#num), \ .regulators_node = of_match_ptr("voltage-regulators"), \ + .of_parse_cb = max77686_of_parse_cb, \ .id = MAX77686_LDO##num, \ .ops = &max77686_ops, \ .type = REGULATOR_VOLTAGE, \ @@ -355,6 +414,7 @@ static struct regulator_ops max77686_buck_dvs_ops = { .name = "BUCK"#num, \ .of_match = of_match_ptr("BUCK"#num), \ .regulators_node = of_match_ptr("voltage-regulators"), \ + .of_parse_cb = max77686_of_parse_cb, \ .id = MAX77686_BUCK##num, \ .ops = &max77686_ops, \ .type = REGULATOR_VOLTAGE, \ diff --git a/drivers/regulator/max77843.c b/drivers/regulator/max77843.c new file mode 100644 index 00000000000..c132ef527cd --- /dev/null +++ b/drivers/regulator/max77843.c @@ -0,0 +1,227 @@ +/* + * max77843.c - Regulator driver for the Maxim MAX77843 + * + * Copyright (C) 2015 Samsung Electronics + * Author: Jaewon Kim <jaewon02.kim@samsung.com> + * Author: Beomho Seo <beomho.seo@samsung.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/machine.h> +#include <linux/mfd/max77843-private.h> +#include <linux/regulator/of_regulator.h> + +enum max77843_regulator_type { + MAX77843_SAFEOUT1 = 0, + MAX77843_SAFEOUT2, + MAX77843_CHARGER, + + MAX77843_NUM, +}; + +static const unsigned int max77843_safeout_voltage_table[] = { + 4850000, + 4900000, + 4950000, + 3300000, +}; + +static int max77843_reg_is_enabled(struct regulator_dev *rdev) +{ + struct regmap *regmap = rdev->regmap; + int ret; + unsigned int reg; + + ret = regmap_read(regmap, rdev->desc->enable_reg, ®); + if (ret) { + dev_err(&rdev->dev, "Fialed to read charger register\n"); + return ret; + } + + return (reg & rdev->desc->enable_mask) == rdev->desc->enable_mask; +} + +static int max77843_reg_get_current_limit(struct regulator_dev *rdev) +{ + struct regmap *regmap = rdev->regmap; + unsigned int chg_min_uA = rdev->constraints->min_uA; + unsigned int chg_max_uA = rdev->constraints->max_uA; + unsigned int val; + int ret; + unsigned int reg, sel; + + ret = regmap_read(regmap, MAX77843_CHG_REG_CHG_CNFG_02, ®); + if (ret) { + dev_err(&rdev->dev, "Failed to read charger register\n"); + return ret; + } + + sel = reg & MAX77843_CHG_FAST_CHG_CURRENT_MASK; + + if (sel < 0x03) + sel = 0; + else + sel -= 2; + + val = chg_min_uA + MAX77843_CHG_FAST_CHG_CURRENT_STEP * sel; + if (val > chg_max_uA) + return -EINVAL; + + return val; +} + +static int max77843_reg_set_current_limit(struct regulator_dev *rdev, + int min_uA, int max_uA) +{ + struct regmap *regmap = rdev->regmap; + unsigned int chg_min_uA = rdev->constraints->min_uA; + int sel = 0; + + while (chg_min_uA + MAX77843_CHG_FAST_CHG_CURRENT_STEP * sel < min_uA) + sel++; + + if (chg_min_uA + MAX77843_CHG_FAST_CHG_CURRENT_STEP * sel > max_uA) + return -EINVAL; + + sel += 2; + + return regmap_write(regmap, MAX77843_CHG_REG_CHG_CNFG_02, sel); +} + +static struct regulator_ops max77843_charger_ops = { + .is_enabled = max77843_reg_is_enabled, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .get_current_limit = max77843_reg_get_current_limit, + .set_current_limit = max77843_reg_set_current_limit, +}; + +static struct regulator_ops max77843_regulator_ops = { + .is_enabled = regulator_is_enabled_regmap, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .list_voltage = regulator_list_voltage_table, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, +}; + +static const struct regulator_desc max77843_supported_regulators[] = { + [MAX77843_SAFEOUT1] = { + .name = "SAFEOUT1", + .id = MAX77843_SAFEOUT1, + .ops = &max77843_regulator_ops, + .of_match = of_match_ptr("SAFEOUT1"), + .regulators_node = of_match_ptr("regulators"), + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .n_voltages = ARRAY_SIZE(max77843_safeout_voltage_table), + .volt_table = max77843_safeout_voltage_table, + .enable_reg = MAX77843_SYS_REG_SAFEOUTCTRL, + .enable_mask = MAX77843_REG_SAFEOUTCTRL_ENSAFEOUT1, + .vsel_reg = MAX77843_SYS_REG_SAFEOUTCTRL, + .vsel_mask = MAX77843_REG_SAFEOUTCTRL_SAFEOUT1_MASK, + }, + [MAX77843_SAFEOUT2] = { + .name = "SAFEOUT2", + .id = MAX77843_SAFEOUT2, + .ops = &max77843_regulator_ops, + .of_match = of_match_ptr("SAFEOUT2"), + .regulators_node = of_match_ptr("regulators"), + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .n_voltages = ARRAY_SIZE(max77843_safeout_voltage_table), + .volt_table = max77843_safeout_voltage_table, + .enable_reg = MAX77843_SYS_REG_SAFEOUTCTRL, + .enable_mask = MAX77843_REG_SAFEOUTCTRL_ENSAFEOUT2, + .vsel_reg = MAX77843_SYS_REG_SAFEOUTCTRL, + .vsel_mask = MAX77843_REG_SAFEOUTCTRL_SAFEOUT2_MASK, + }, + [MAX77843_CHARGER] = { + .name = "CHARGER", + .id = MAX77843_CHARGER, + .ops = &max77843_charger_ops, + .of_match = of_match_ptr("CHARGER"), + .regulators_node = of_match_ptr("regulators"), + .type = REGULATOR_CURRENT, + .owner = THIS_MODULE, + .enable_reg = MAX77843_CHG_REG_CHG_CNFG_00, + .enable_mask = MAX77843_CHG_MASK, + }, +}; + +static struct regmap *max77843_get_regmap(struct max77843 *max77843, int reg_id) +{ + switch (reg_id) { + case MAX77843_SAFEOUT1: + case MAX77843_SAFEOUT2: + return max77843->regmap; + case MAX77843_CHARGER: + return max77843->regmap_chg; + default: + return max77843->regmap; + } +} + +static int max77843_regulator_probe(struct platform_device *pdev) +{ + struct max77843 *max77843 = dev_get_drvdata(pdev->dev.parent); + struct regulator_config config = {}; + int i; + + config.dev = max77843->dev; + config.driver_data = max77843; + + for (i = 0; i < ARRAY_SIZE(max77843_supported_regulators); i++) { + struct regulator_dev *regulator; + + config.regmap = max77843_get_regmap(max77843, + max77843_supported_regulators[i].id); + + regulator = devm_regulator_register(&pdev->dev, + &max77843_supported_regulators[i], &config); + if (IS_ERR(regulator)) { + dev_err(&pdev->dev, + "Failed to regiser regulator-%d\n", i); + return PTR_ERR(regulator); + } + } + + return 0; +} + +static const struct platform_device_id max77843_regulator_id[] = { + { "max77843-regulator", }, + { /* sentinel */ }, +}; + +static struct platform_driver max77843_regulator_driver = { + .driver = { + .name = "max77843-regulator", + }, + .probe = max77843_regulator_probe, + .id_table = max77843_regulator_id, +}; + +static int __init max77843_regulator_init(void) +{ + return platform_driver_register(&max77843_regulator_driver); +} +subsys_initcall(max77843_regulator_init); + +static void __exit max77843_regulator_exit(void) +{ + platform_driver_unregister(&max77843_regulator_driver); +} +module_exit(max77843_regulator_exit); + +MODULE_AUTHOR("Jaewon Kim <jaewon02.kim@samsung.com>"); +MODULE_AUTHOR("Beomho Seo <beomho.seo@samsung.com>"); +MODULE_DESCRIPTION("Maxim MAX77843 regulator driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/regulator/max8649.c b/drivers/regulator/max8649.c index c8bddcc8f91..81229579ece 100644 --- a/drivers/regulator/max8649.c +++ b/drivers/regulator/max8649.c @@ -115,7 +115,7 @@ static unsigned int max8649_get_mode(struct regulator_dev *rdev) return REGULATOR_MODE_NORMAL; } -static struct regulator_ops max8649_dcdc_ops = { +static const struct regulator_ops max8649_dcdc_ops = { .set_voltage_sel = regulator_set_voltage_sel_regmap, .get_voltage_sel = regulator_get_voltage_sel_regmap, .list_voltage = regulator_list_voltage_linear, @@ -143,7 +143,7 @@ static struct regulator_desc dcdc_desc = { .enable_is_inverted = true, }; -static struct regmap_config max8649_regmap_config = { +static const struct regmap_config max8649_regmap_config = { .reg_bits = 8, .val_bits = 8, }; diff --git a/drivers/regulator/mt6397-regulator.c b/drivers/regulator/mt6397-regulator.c new file mode 100644 index 00000000000..a5b2f476267 --- /dev/null +++ b/drivers/regulator/mt6397-regulator.c @@ -0,0 +1,332 @@ +/* + * Copyright (c) 2014 MediaTek Inc. + * Author: Flora Fu <flora.fu@mediatek.com> + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/mfd/mt6397/core.h> +#include <linux/mfd/mt6397/registers.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/machine.h> +#include <linux/regulator/mt6397-regulator.h> +#include <linux/regulator/of_regulator.h> + +/* + * MT6397 regulators' information + * + * @desc: standard fields of regulator description. + * @qi: Mask for query enable signal status of regulators + * @vselon_reg: Register sections for hardware control mode of bucks + * @vselctrl_reg: Register for controlling the buck control mode. + * @vselctrl_mask: Mask for query buck's voltage control mode. + */ +struct mt6397_regulator_info { + struct regulator_desc desc; + u32 qi; + u32 vselon_reg; + u32 vselctrl_reg; + u32 vselctrl_mask; +}; + +#define MT6397_BUCK(match, vreg, min, max, step, volt_ranges, enreg, \ + vosel, vosel_mask, voselon, vosel_ctrl) \ +[MT6397_ID_##vreg] = { \ + .desc = { \ + .name = #vreg, \ + .of_match = of_match_ptr(match), \ + .ops = &mt6397_volt_range_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = MT6397_ID_##vreg, \ + .owner = THIS_MODULE, \ + .n_voltages = (max - min)/step + 1, \ + .linear_ranges = volt_ranges, \ + .n_linear_ranges = ARRAY_SIZE(volt_ranges), \ + .vsel_reg = vosel, \ + .vsel_mask = vosel_mask, \ + .enable_reg = enreg, \ + .enable_mask = BIT(0), \ + }, \ + .qi = BIT(13), \ + .vselon_reg = voselon, \ + .vselctrl_reg = vosel_ctrl, \ + .vselctrl_mask = BIT(1), \ +} + +#define MT6397_LDO(match, vreg, ldo_volt_table, enreg, enbit, vosel, \ + vosel_mask) \ +[MT6397_ID_##vreg] = { \ + .desc = { \ + .name = #vreg, \ + .of_match = of_match_ptr(match), \ + .ops = &mt6397_volt_table_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = MT6397_ID_##vreg, \ + .owner = THIS_MODULE, \ + .n_voltages = ARRAY_SIZE(ldo_volt_table), \ + .volt_table = ldo_volt_table, \ + .vsel_reg = vosel, \ + .vsel_mask = vosel_mask, \ + .enable_reg = enreg, \ + .enable_mask = BIT(enbit), \ + }, \ + .qi = BIT(15), \ +} + +#define MT6397_REG_FIXED(match, vreg, enreg, enbit, volt) \ +[MT6397_ID_##vreg] = { \ + .desc = { \ + .name = #vreg, \ + .of_match = of_match_ptr(match), \ + .ops = &mt6397_volt_fixed_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = MT6397_ID_##vreg, \ + .owner = THIS_MODULE, \ + .n_voltages = 1, \ + .enable_reg = enreg, \ + .enable_mask = BIT(enbit), \ + .min_uV = volt, \ + }, \ + .qi = BIT(15), \ +} + +static const struct regulator_linear_range buck_volt_range1[] = { + REGULATOR_LINEAR_RANGE(700000, 0, 0x7f, 6250), +}; + +static const struct regulator_linear_range buck_volt_range2[] = { + REGULATOR_LINEAR_RANGE(800000, 0, 0x7f, 6250), +}; + +static const struct regulator_linear_range buck_volt_range3[] = { + REGULATOR_LINEAR_RANGE(1500000, 0, 0x1f, 20000), +}; + +static const u32 ldo_volt_table1[] = { + 1500000, 1800000, 2500000, 2800000, +}; + +static const u32 ldo_volt_table2[] = { + 1800000, 3300000, +}; + +static const u32 ldo_volt_table3[] = { + 3000000, 3300000, +}; + +static const u32 ldo_volt_table4[] = { + 1220000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000, +}; + +static const u32 ldo_volt_table5[] = { + 1200000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000, +}; + +static const u32 ldo_volt_table5_v2[] = { + 1200000, 1000000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000, +}; + +static const u32 ldo_volt_table6[] = { + 1200000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 2000000, +}; + +static const u32 ldo_volt_table7[] = { + 1300000, 1500000, 1800000, 2000000, 2500000, 2800000, 3000000, 3300000, +}; + +static int mt6397_get_status(struct regulator_dev *rdev) +{ + int ret; + u32 regval; + struct mt6397_regulator_info *info = rdev_get_drvdata(rdev); + + ret = regmap_read(rdev->regmap, info->desc.enable_reg, ®val); + if (ret != 0) { + dev_err(&rdev->dev, "Failed to get enable reg: %d\n", ret); + return ret; + } + + return (regval & info->qi) ? REGULATOR_STATUS_ON : REGULATOR_STATUS_OFF; +} + +static struct regulator_ops mt6397_volt_range_ops = { + .list_voltage = regulator_list_voltage_linear_range, + .map_voltage = regulator_map_voltage_linear_range, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_time_sel = regulator_set_voltage_time_sel, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .get_status = mt6397_get_status, +}; + +static struct regulator_ops mt6397_volt_table_ops = { + .list_voltage = regulator_list_voltage_table, + .map_voltage = regulator_map_voltage_iterate, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_time_sel = regulator_set_voltage_time_sel, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .get_status = mt6397_get_status, +}; + +static struct regulator_ops mt6397_volt_fixed_ops = { + .list_voltage = regulator_list_voltage_linear, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .get_status = mt6397_get_status, +}; + +/* The array is indexed by id(MT6397_ID_XXX) */ +static struct mt6397_regulator_info mt6397_regulators[] = { + MT6397_BUCK("buck_vpca15", VPCA15, 700000, 1493750, 6250, + buck_volt_range1, MT6397_VCA15_CON7, MT6397_VCA15_CON9, 0x7f, + MT6397_VCA15_CON10, MT6397_VCA15_CON5), + MT6397_BUCK("buck_vpca7", VPCA7, 700000, 1493750, 6250, + buck_volt_range1, MT6397_VPCA7_CON7, MT6397_VPCA7_CON9, 0x7f, + MT6397_VPCA7_CON10, MT6397_VPCA7_CON5), + MT6397_BUCK("buck_vsramca15", VSRAMCA15, 700000, 1493750, 6250, + buck_volt_range1, MT6397_VSRMCA15_CON7, MT6397_VSRMCA15_CON9, + 0x7f, MT6397_VSRMCA15_CON10, MT6397_VSRMCA15_CON5), + MT6397_BUCK("buck_vsramca7", VSRAMCA7, 700000, 1493750, 6250, + buck_volt_range1, MT6397_VSRMCA7_CON7, MT6397_VSRMCA7_CON9, + 0x7f, MT6397_VSRMCA7_CON10, MT6397_VSRMCA7_CON5), + MT6397_BUCK("buck_vcore", VCORE, 700000, 1493750, 6250, + buck_volt_range1, MT6397_VCORE_CON7, MT6397_VCORE_CON9, 0x7f, + MT6397_VCORE_CON10, MT6397_VCORE_CON5), + MT6397_BUCK("buck_vgpu", VGPU, 700000, 1493750, 6250, buck_volt_range1, + MT6397_VGPU_CON7, MT6397_VGPU_CON9, 0x7f, + MT6397_VGPU_CON10, MT6397_VGPU_CON5), + MT6397_BUCK("buck_vdrm", VDRM, 800000, 1593750, 6250, buck_volt_range2, + MT6397_VDRM_CON7, MT6397_VDRM_CON9, 0x7f, + MT6397_VDRM_CON10, MT6397_VDRM_CON5), + MT6397_BUCK("buck_vio18", VIO18, 1500000, 2120000, 20000, + buck_volt_range3, MT6397_VIO18_CON7, MT6397_VIO18_CON9, 0x1f, + MT6397_VIO18_CON10, MT6397_VIO18_CON5), + MT6397_REG_FIXED("ldo_vtcxo", VTCXO, MT6397_ANALDO_CON0, 10, 2800000), + MT6397_REG_FIXED("ldo_va28", VA28, MT6397_ANALDO_CON1, 14, 2800000), + MT6397_LDO("ldo_vcama", VCAMA, ldo_volt_table1, + MT6397_ANALDO_CON2, 15, MT6397_ANALDO_CON6, 0xC0), + MT6397_REG_FIXED("ldo_vio28", VIO28, MT6397_DIGLDO_CON0, 14, 2800000), + MT6397_REG_FIXED("ldo_vusb", VUSB, MT6397_DIGLDO_CON1, 14, 3300000), + MT6397_LDO("ldo_vmc", VMC, ldo_volt_table2, + MT6397_DIGLDO_CON2, 12, MT6397_DIGLDO_CON29, 0x10), + MT6397_LDO("ldo_vmch", VMCH, ldo_volt_table3, + MT6397_DIGLDO_CON3, 14, MT6397_DIGLDO_CON17, 0x80), + MT6397_LDO("ldo_vemc3v3", VEMC3V3, ldo_volt_table3, + MT6397_DIGLDO_CON4, 14, MT6397_DIGLDO_CON18, 0x10), + MT6397_LDO("ldo_vgp1", VGP1, ldo_volt_table4, + MT6397_DIGLDO_CON5, 15, MT6397_DIGLDO_CON19, 0xE0), + MT6397_LDO("ldo_vgp2", VGP2, ldo_volt_table5, + MT6397_DIGLDO_CON6, 15, MT6397_DIGLDO_CON20, 0xE0), + MT6397_LDO("ldo_vgp3", VGP3, ldo_volt_table5, + MT6397_DIGLDO_CON7, 15, MT6397_DIGLDO_CON21, 0xE0), + MT6397_LDO("ldo_vgp4", VGP4, ldo_volt_table5, + MT6397_DIGLDO_CON8, 15, MT6397_DIGLDO_CON22, 0xE0), + MT6397_LDO("ldo_vgp5", VGP5, ldo_volt_table6, + MT6397_DIGLDO_CON9, 15, MT6397_DIGLDO_CON23, 0xE0), + MT6397_LDO("ldo_vgp6", VGP6, ldo_volt_table5, + MT6397_DIGLDO_CON10, 15, MT6397_DIGLDO_CON33, 0xE0), + MT6397_LDO("ldo_vibr", VIBR, ldo_volt_table7, + MT6397_DIGLDO_CON24, 15, MT6397_DIGLDO_CON25, 0xE00), +}; + +static int mt6397_set_buck_vosel_reg(struct platform_device *pdev) +{ + struct mt6397_chip *mt6397 = dev_get_drvdata(pdev->dev.parent); + int i; + u32 regval; + + for (i = 0; i < MT6397_MAX_REGULATOR; i++) { + if (mt6397_regulators[i].vselctrl_reg) { + if (regmap_read(mt6397->regmap, + mt6397_regulators[i].vselctrl_reg, + ®val) < 0) { + dev_err(&pdev->dev, + "Failed to read buck ctrl\n"); + return -EIO; + } + + if (regval & mt6397_regulators[i].vselctrl_mask) { + mt6397_regulators[i].desc.vsel_reg = + mt6397_regulators[i].vselon_reg; + } + } + } + + return 0; +} + +static int mt6397_regulator_probe(struct platform_device *pdev) +{ + struct mt6397_chip *mt6397 = dev_get_drvdata(pdev->dev.parent); + struct regulator_config config = {}; + struct regulator_dev *rdev; + int i; + u32 reg_value, version; + + /* Query buck controller to select activated voltage register part */ + if (mt6397_set_buck_vosel_reg(pdev)) + return -EIO; + + /* Read PMIC chip revision to update constraints and voltage table */ + if (regmap_read(mt6397->regmap, MT6397_CID, ®_value) < 0) { + dev_err(&pdev->dev, "Failed to read Chip ID\n"); + return -EIO; + } + dev_info(&pdev->dev, "Chip ID = 0x%x\n", reg_value); + + version = (reg_value & 0xFF); + switch (version) { + case MT6397_REGULATOR_ID91: + mt6397_regulators[MT6397_ID_VGP2].desc.volt_table = + ldo_volt_table5_v2; + break; + default: + break; + } + + for (i = 0; i < MT6397_MAX_REGULATOR; i++) { + config.dev = &pdev->dev; + config.driver_data = &mt6397_regulators[i]; + config.regmap = mt6397->regmap; + rdev = devm_regulator_register(&pdev->dev, + &mt6397_regulators[i].desc, &config); + if (IS_ERR(rdev)) { + dev_err(&pdev->dev, "failed to register %s\n", + mt6397_regulators[i].desc.name); + return PTR_ERR(rdev); + } + } + + return 0; +} + +static struct platform_driver mt6397_regulator_driver = { + .driver = { + .name = "mt6397-regulator", + }, + .probe = mt6397_regulator_probe, +}; + +module_platform_driver(mt6397_regulator_driver); + +MODULE_AUTHOR("Flora Fu <flora.fu@mediatek.com>"); +MODULE_DESCRIPTION("Regulator Driver for MediaTek MT6397 PMIC"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:mt6397-regulator"); diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index 91eaaf01052..24e812c48d9 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -270,6 +270,7 @@ EXPORT_SYMBOL_GPL(of_regulator_match); struct regulator_init_data *regulator_of_get_init_data(struct device *dev, const struct regulator_desc *desc, + struct regulator_config *config, struct device_node **node) { struct device_node *search, *child; @@ -307,6 +308,16 @@ struct regulator_init_data *regulator_of_get_init_data(struct device *dev, break; } + if (desc->of_parse_cb) { + if (desc->of_parse_cb(child, desc, config)) { + dev_err(dev, + "driver callback failed to parse DT for regulator %s\n", + child->name); + init_data = NULL; + break; + } + } + of_node_get(child); *node = child; break; diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c index c879dff597e..8cc8d1877c4 100644 --- a/drivers/regulator/pfuze100-regulator.c +++ b/drivers/regulator/pfuze100-regulator.c @@ -56,7 +56,7 @@ #define PFUZE100_VGEN5VOL 0x70 #define PFUZE100_VGEN6VOL 0x71 -enum chips { PFUZE100, PFUZE200 }; +enum chips { PFUZE100, PFUZE200, PFUZE3000 = 3 }; struct pfuze_regulator { struct regulator_desc desc; @@ -80,9 +80,18 @@ static const int pfuze100_vsnvs[] = { 1000000, 1100000, 1200000, 1300000, 1500000, 1800000, 3000000, }; +static const int pfuze3000_sw2lo[] = { + 1500000, 1550000, 1600000, 1650000, 1700000, 1750000, 1800000, 1850000, +}; + +static const int pfuze3000_sw2hi[] = { + 2500000, 2800000, 2850000, 3000000, 3100000, 3150000, 3200000, 3300000, +}; + static const struct i2c_device_id pfuze_device_id[] = { {.name = "pfuze100", .driver_data = PFUZE100}, {.name = "pfuze200", .driver_data = PFUZE200}, + {.name = "pfuze3000", .driver_data = PFUZE3000}, { } }; MODULE_DEVICE_TABLE(i2c, pfuze_device_id); @@ -90,6 +99,7 @@ MODULE_DEVICE_TABLE(i2c, pfuze_device_id); static const struct of_device_id pfuze_dt_ids[] = { { .compatible = "fsl,pfuze100", .data = (void *)PFUZE100}, { .compatible = "fsl,pfuze200", .data = (void *)PFUZE200}, + { .compatible = "fsl,pfuze3000", .data = (void *)PFUZE3000}, { } }; MODULE_DEVICE_TABLE(of, pfuze_dt_ids); @@ -219,6 +229,60 @@ static struct regulator_ops pfuze100_swb_regulator_ops = { .stby_mask = 0x20, \ } +#define PFUZE3000_VCC_REG(_chip, _name, base, min, max, step) { \ + .desc = { \ + .name = #_name, \ + .n_voltages = ((max) - (min)) / (step) + 1, \ + .ops = &pfuze100_ldo_regulator_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = _chip ## _ ## _name, \ + .owner = THIS_MODULE, \ + .min_uV = (min), \ + .uV_step = (step), \ + .vsel_reg = (base), \ + .vsel_mask = 0x3, \ + .enable_reg = (base), \ + .enable_mask = 0x10, \ + }, \ + .stby_reg = (base), \ + .stby_mask = 0x20, \ +} + + +#define PFUZE3000_SW2_REG(_chip, _name, base, min, max, step) { \ + .desc = { \ + .name = #_name,\ + .n_voltages = ((max) - (min)) / (step) + 1, \ + .ops = &pfuze100_sw_regulator_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = _chip ## _ ## _name, \ + .owner = THIS_MODULE, \ + .min_uV = (min), \ + .uV_step = (step), \ + .vsel_reg = (base) + PFUZE100_VOL_OFFSET, \ + .vsel_mask = 0x7, \ + }, \ + .stby_reg = (base) + PFUZE100_STANDBY_OFFSET, \ + .stby_mask = 0x7, \ +} + +#define PFUZE3000_SW3_REG(_chip, _name, base, min, max, step) { \ + .desc = { \ + .name = #_name,\ + .n_voltages = ((max) - (min)) / (step) + 1, \ + .ops = &pfuze100_sw_regulator_ops, \ + .type = REGULATOR_VOLTAGE, \ + .id = _chip ## _ ## _name, \ + .owner = THIS_MODULE, \ + .min_uV = (min), \ + .uV_step = (step), \ + .vsel_reg = (base) + PFUZE100_VOL_OFFSET, \ + .vsel_mask = 0xf, \ + }, \ + .stby_reg = (base) + PFUZE100_STANDBY_OFFSET, \ + .stby_mask = 0xf, \ +} + /* PFUZE100 */ static struct pfuze_regulator pfuze100_regulators[] = { PFUZE100_SW_REG(PFUZE100, SW1AB, PFUZE100_SW1ABVOL, 300000, 1875000, 25000), @@ -254,6 +318,22 @@ static struct pfuze_regulator pfuze200_regulators[] = { PFUZE100_VGEN_REG(PFUZE200, VGEN6, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000), }; +static struct pfuze_regulator pfuze3000_regulators[] = { + PFUZE100_SW_REG(PFUZE3000, SW1A, PFUZE100_SW1ABVOL, 700000, 1475000, 25000), + PFUZE100_SW_REG(PFUZE3000, SW1B, PFUZE100_SW1CVOL, 700000, 1475000, 25000), + PFUZE100_SWB_REG(PFUZE3000, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo), + PFUZE3000_SW3_REG(PFUZE3000, SW3, PFUZE100_SW3AVOL, 900000, 1650000, 50000), + PFUZE100_SWB_REG(PFUZE3000, SWBST, PFUZE100_SWBSTCON1, 0x3, pfuze100_swbst), + PFUZE100_SWB_REG(PFUZE3000, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs), + PFUZE100_FIXED_REG(PFUZE3000, VREFDDR, PFUZE100_VREFDDRCON, 750000), + PFUZE100_VGEN_REG(PFUZE3000, VLDO1, PFUZE100_VGEN1VOL, 1800000, 3300000, 100000), + PFUZE100_VGEN_REG(PFUZE3000, VLDO2, PFUZE100_VGEN2VOL, 800000, 1550000, 50000), + PFUZE3000_VCC_REG(PFUZE3000, VCCSD, PFUZE100_VGEN3VOL, 2850000, 3300000, 150000), + PFUZE3000_VCC_REG(PFUZE3000, V33, PFUZE100_VGEN4VOL, 2850000, 3300000, 150000), + PFUZE100_VGEN_REG(PFUZE3000, VLDO3, PFUZE100_VGEN5VOL, 1800000, 3300000, 100000), + PFUZE100_VGEN_REG(PFUZE3000, VLDO4, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000), +}; + static struct pfuze_regulator *pfuze_regulators; #ifdef CONFIG_OF @@ -294,6 +374,24 @@ static struct of_regulator_match pfuze200_matches[] = { { .name = "vgen6", }, }; +/* PFUZE3000 */ +static struct of_regulator_match pfuze3000_matches[] = { + + { .name = "sw1a", }, + { .name = "sw1b", }, + { .name = "sw2", }, + { .name = "sw3", }, + { .name = "swbst", }, + { .name = "vsnvs", }, + { .name = "vrefddr", }, + { .name = "vldo1", }, + { .name = "vldo2", }, + { .name = "vccsd", }, + { .name = "v33", }, + { .name = "vldo3", }, + { .name = "vldo4", }, +}; + static struct of_regulator_match *pfuze_matches; static int pfuze_parse_regulators_dt(struct pfuze_chip *chip) @@ -313,6 +411,11 @@ static int pfuze_parse_regulators_dt(struct pfuze_chip *chip) } switch (chip->chip_id) { + case PFUZE3000: + pfuze_matches = pfuze3000_matches; + ret = of_regulator_match(dev, parent, pfuze3000_matches, + ARRAY_SIZE(pfuze3000_matches)); + break; case PFUZE200: pfuze_matches = pfuze200_matches; ret = of_regulator_match(dev, parent, pfuze200_matches, @@ -378,7 +481,8 @@ static int pfuze_identify(struct pfuze_chip *pfuze_chip) * as ID=8 in PFUZE100 */ dev_info(pfuze_chip->dev, "Assuming misprogrammed ID=0x8"); - } else if ((value & 0x0f) != pfuze_chip->chip_id) { + } else if ((value & 0x0f) != pfuze_chip->chip_id && + (value & 0xf0) >> 4 != pfuze_chip->chip_id) { /* device id NOT match with your setting */ dev_warn(pfuze_chip->dev, "Illegal ID: %x\n", value); return -ENODEV; @@ -417,7 +521,7 @@ static int pfuze100_regulator_probe(struct i2c_client *client, int i, ret; const struct of_device_id *match; u32 regulator_num; - u32 sw_check_start, sw_check_end; + u32 sw_check_start, sw_check_end, sw_hi = 0x40; pfuze_chip = devm_kzalloc(&client->dev, sizeof(*pfuze_chip), GFP_KERNEL); @@ -458,13 +562,19 @@ static int pfuze100_regulator_probe(struct i2c_client *client, /* use the right regulators after identify the right device */ switch (pfuze_chip->chip_id) { + case PFUZE3000: + pfuze_regulators = pfuze3000_regulators; + regulator_num = ARRAY_SIZE(pfuze3000_regulators); + sw_check_start = PFUZE3000_SW2; + sw_check_end = PFUZE3000_SW2; + sw_hi = 1 << 3; + break; case PFUZE200: pfuze_regulators = pfuze200_regulators; regulator_num = ARRAY_SIZE(pfuze200_regulators); sw_check_start = PFUZE200_SW2; sw_check_end = PFUZE200_SW3B; break; - case PFUZE100: default: pfuze_regulators = pfuze100_regulators; @@ -474,7 +584,8 @@ static int pfuze100_regulator_probe(struct i2c_client *client, break; } dev_info(&client->dev, "pfuze%s found.\n", - (pfuze_chip->chip_id == PFUZE100) ? "100" : "200"); + (pfuze_chip->chip_id == PFUZE100) ? "100" : + ((pfuze_chip->chip_id == PFUZE200) ? "200" : "3000")); memcpy(pfuze_chip->regulator_descs, pfuze_regulators, sizeof(pfuze_chip->regulator_descs)); @@ -498,10 +609,15 @@ static int pfuze100_regulator_probe(struct i2c_client *client, /* SW2~SW4 high bit check and modify the voltage value table */ if (i >= sw_check_start && i <= sw_check_end) { regmap_read(pfuze_chip->regmap, desc->vsel_reg, &val); - if (val & 0x40) { - desc->min_uV = 800000; - desc->uV_step = 50000; - desc->n_voltages = 51; + if (val & sw_hi) { + if (pfuze_chip->chip_id == PFUZE3000) { + desc->volt_table = pfuze3000_sw2hi; + desc->n_voltages = ARRAY_SIZE(pfuze3000_sw2hi); + } else { + desc->min_uV = 800000; + desc->uV_step = 50000; + desc->n_voltages = 51; + } } } diff --git a/drivers/regulator/qcom_rpm-regulator.c b/drivers/regulator/qcom_rpm-regulator.c index 8364ff331a8..e8647f7cf25 100644 --- a/drivers/regulator/qcom_rpm-regulator.c +++ b/drivers/regulator/qcom_rpm-regulator.c @@ -227,9 +227,11 @@ static int rpm_reg_set_mV_sel(struct regulator_dev *rdev, return uV; mutex_lock(&vreg->lock); - vreg->uV = uV; if (vreg->is_enabled) - ret = rpm_reg_write(vreg, req, vreg->uV / 1000); + ret = rpm_reg_write(vreg, req, uV / 1000); + + if (!ret) + vreg->uV = uV; mutex_unlock(&vreg->lock); return ret; @@ -252,9 +254,11 @@ static int rpm_reg_set_uV_sel(struct regulator_dev *rdev, return uV; mutex_lock(&vreg->lock); - vreg->uV = uV; if (vreg->is_enabled) - ret = rpm_reg_write(vreg, req, vreg->uV); + ret = rpm_reg_write(vreg, req, uV); + + if (!ret) + vreg->uV = uV; mutex_unlock(&vreg->lock); return ret; @@ -674,6 +678,7 @@ static int rpm_reg_probe(struct platform_device *pdev) vreg->desc.owner = THIS_MODULE; vreg->desc.type = REGULATOR_VOLTAGE; vreg->desc.name = pdev->dev.of_node->name; + vreg->desc.supply_name = "vin"; vreg->rpm = dev_get_drvdata(pdev->dev.parent); if (!vreg->rpm) { @@ -768,7 +773,7 @@ static int rpm_reg_probe(struct platform_device *pdev) break; } - if (force_mode < 0) { + if (force_mode == -1) { dev_err(&pdev->dev, "invalid force mode\n"); return -EINVAL; } diff --git a/drivers/regulator/rk808-regulator.c b/drivers/regulator/rk808-regulator.c index c94a3e0f3b9..1f93b752a81 100644 --- a/drivers/regulator/rk808-regulator.c +++ b/drivers/regulator/rk808-regulator.c @@ -97,7 +97,7 @@ static int rk808_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay) RK808_RAMP_RATE_MASK, ramp_value); } -int rk808_set_suspend_voltage(struct regulator_dev *rdev, int uv) +static int rk808_set_suspend_voltage(struct regulator_dev *rdev, int uv) { unsigned int reg; int sel = regulator_map_voltage_linear_range(rdev, uv, uv); @@ -112,7 +112,7 @@ int rk808_set_suspend_voltage(struct regulator_dev *rdev, int uv) sel); } -int rk808_set_suspend_enable(struct regulator_dev *rdev) +static int rk808_set_suspend_enable(struct regulator_dev *rdev) { unsigned int reg; @@ -123,7 +123,7 @@ int rk808_set_suspend_enable(struct regulator_dev *rdev) 0); } -int rk808_set_suspend_disable(struct regulator_dev *rdev) +static int rk808_set_suspend_disable(struct regulator_dev *rdev) { unsigned int reg; diff --git a/drivers/regulator/rt5033-regulator.c b/drivers/regulator/rt5033-regulator.c index 870cc49438d..96d2c18e051 100644 --- a/drivers/regulator/rt5033-regulator.c +++ b/drivers/regulator/rt5033-regulator.c @@ -36,6 +36,8 @@ static struct regulator_ops rt5033_buck_ops = { static const struct regulator_desc rt5033_supported_regulators[] = { [RT5033_BUCK] = { .name = "BUCK", + .of_match = of_match_ptr("BUCK"), + .regulators_node = of_match_ptr("regulators"), .id = RT5033_BUCK, .ops = &rt5033_buck_ops, .type = REGULATOR_VOLTAGE, @@ -50,6 +52,8 @@ static const struct regulator_desc rt5033_supported_regulators[] = { }, [RT5033_LDO] = { .name = "LDO", + .of_match = of_match_ptr("LDO"), + .regulators_node = of_match_ptr("regulators"), .id = RT5033_LDO, .ops = &rt5033_buck_ops, .type = REGULATOR_VOLTAGE, @@ -64,6 +68,8 @@ static const struct regulator_desc rt5033_supported_regulators[] = { }, [RT5033_SAFE_LDO] = { .name = "SAFE_LDO", + .of_match = of_match_ptr("SAFE_LDO"), + .regulators_node = of_match_ptr("regulators"), .id = RT5033_SAFE_LDO, .ops = &rt5033_safe_ldo_ops, .type = REGULATOR_VOLTAGE, @@ -81,7 +87,7 @@ static int rt5033_regulator_probe(struct platform_device *pdev) int ret, i; struct regulator_config config = {}; - config.dev = &pdev->dev; + config.dev = rt5033->dev; config.driver_data = rt5033; for (i = 0; i < ARRAY_SIZE(rt5033_supported_regulators); i++) { diff --git a/drivers/regulator/tps65023-regulator.c b/drivers/regulator/tps65023-regulator.c index 7380af8bd50..b941e564b3f 100644 --- a/drivers/regulator/tps65023-regulator.c +++ b/drivers/regulator/tps65023-regulator.c @@ -173,7 +173,7 @@ static int tps65023_dcdc_set_voltage_sel(struct regulator_dev *dev, } /* Operations permitted on VDCDCx */ -static struct regulator_ops tps65023_dcdc_ops = { +static const struct regulator_ops tps65023_dcdc_ops = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, @@ -184,7 +184,7 @@ static struct regulator_ops tps65023_dcdc_ops = { }; /* Operations permitted on LDOx */ -static struct regulator_ops tps65023_ldo_ops = { +static const struct regulator_ops tps65023_ldo_ops = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, @@ -194,7 +194,7 @@ static struct regulator_ops tps65023_ldo_ops = { .map_voltage = regulator_map_voltage_ascend, }; -static struct regmap_config tps65023_regmap_config = { +static const struct regmap_config tps65023_regmap_config = { .reg_bits = 8, .val_bits = 8, }; diff --git a/drivers/rtc/hctosys.c b/drivers/rtc/hctosys.c index 4aa60d74004..6c719f23520 100644 --- a/drivers/rtc/hctosys.c +++ b/drivers/rtc/hctosys.c @@ -26,7 +26,7 @@ static int __init rtc_hctosys(void) { int err = -ENODEV; struct rtc_time tm; - struct timespec tv = { + struct timespec64 tv64 = { .tv_nsec = NSEC_PER_SEC >> 1, }; struct rtc_device *rtc = rtc_class_open(CONFIG_RTC_HCTOSYS_DEVICE); @@ -45,25 +45,17 @@ static int __init rtc_hctosys(void) } - err = rtc_valid_tm(&tm); - if (err) { - dev_err(rtc->dev.parent, - "hctosys: invalid date/time\n"); - goto err_invalid; - } - - rtc_tm_to_time(&tm, &tv.tv_sec); + tv64.tv_sec = rtc_tm_to_time64(&tm); - err = do_settimeofday(&tv); + err = do_settimeofday64(&tv64); dev_info(rtc->dev.parent, "setting system clock to " - "%d-%02d-%02d %02d:%02d:%02d UTC (%u)\n", + "%d-%02d-%02d %02d:%02d:%02d UTC (%lld)\n", tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec, - (unsigned int) tv.tv_sec); + (long long) tv64.tv_sec); -err_invalid: err_read: rtc_class_close(rtc); diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 45bfc28ee3a..37215cf983e 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -73,10 +73,8 @@ int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm) else if (rtc->ops->set_time) err = rtc->ops->set_time(rtc->dev.parent, tm); else if (rtc->ops->set_mmss) { - unsigned long secs; - err = rtc_tm_to_time(tm, &secs); - if (err == 0) - err = rtc->ops->set_mmss(rtc->dev.parent, secs); + time64_t secs64 = rtc_tm_to_time64(tm); + err = rtc->ops->set_mmss(rtc->dev.parent, secs64); } else err = -EINVAL; @@ -105,7 +103,7 @@ int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs) err = rtc->ops->read_time(rtc->dev.parent, &old); if (err == 0) { - rtc_time_to_tm(secs, &new); + rtc_time64_to_tm(secs, &new); /* * avoid writing when we're going to change the day of @@ -157,7 +155,7 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) int err; struct rtc_time before, now; int first_time = 1; - unsigned long t_now, t_alm; + time64_t t_now, t_alm; enum { none, day, month, year } missing = none; unsigned days; @@ -258,8 +256,8 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) } /* with luck, no rollover is needed */ - rtc_tm_to_time(&now, &t_now); - rtc_tm_to_time(&alarm->time, &t_alm); + t_now = rtc_tm_to_time64(&now); + t_alm = rtc_tm_to_time64(&alarm->time); if (t_now < t_alm) goto done; @@ -273,7 +271,7 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) case day: dev_dbg(&rtc->dev, "alarm rollover: %s\n", "day"); t_alm += 24 * 60 * 60; - rtc_time_to_tm(t_alm, &alarm->time); + rtc_time64_to_tm(t_alm, &alarm->time); break; /* Month rollover ... if it's the 31th, an alarm on the 3rd will @@ -346,19 +344,19 @@ EXPORT_SYMBOL_GPL(rtc_read_alarm); static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) { struct rtc_time tm; - long now, scheduled; + time64_t now, scheduled; int err; err = rtc_valid_tm(&alarm->time); if (err) return err; - rtc_tm_to_time(&alarm->time, &scheduled); + scheduled = rtc_tm_to_time64(&alarm->time); /* Make sure we're not setting alarms in the past */ err = __rtc_read_time(rtc, &tm); if (err) return err; - rtc_tm_to_time(&tm, &now); + now = rtc_tm_to_time64(&tm); if (scheduled <= now) return -ETIME; /* diff --git a/drivers/rtc/rtc-dev.c b/drivers/rtc/rtc-dev.c index d0493936925..799c34bcb26 100644 --- a/drivers/rtc/rtc-dev.c +++ b/drivers/rtc/rtc-dev.c @@ -304,12 +304,12 @@ static long rtc_dev_ioctl(struct file *file, * Not supported here. */ { - unsigned long now, then; + time64_t now, then; err = rtc_read_time(rtc, &tm); if (err < 0) return err; - rtc_tm_to_time(&tm, &now); + now = rtc_tm_to_time64(&tm); alarm.time.tm_mday = tm.tm_mday; alarm.time.tm_mon = tm.tm_mon; @@ -317,11 +317,11 @@ static long rtc_dev_ioctl(struct file *file, err = rtc_valid_tm(&alarm.time); if (err < 0) return err; - rtc_tm_to_time(&alarm.time, &then); + then = rtc_tm_to_time64(&alarm.time); /* alarm may need to wrap into tomorrow */ if (then < now) { - rtc_time_to_tm(now + 24 * 60 * 60, &tm); + rtc_time64_to_tm(now + 24 * 60 * 60, &tm); alarm.time.tm_mday = tm.tm_mday; alarm.time.tm_mon = tm.tm_mon; alarm.time.tm_year = tm.tm_year; diff --git a/drivers/rtc/rtc-efi.c b/drivers/rtc/rtc-efi.c index b37b0c80bd5..cb989cd00b1 100644 --- a/drivers/rtc/rtc-efi.c +++ b/drivers/rtc/rtc-efi.c @@ -218,6 +218,7 @@ static int __init efi_rtc_probe(struct platform_device *dev) if (IS_ERR(rtc)) return PTR_ERR(rtc); + rtc->uie_unsupported = 1; platform_set_drvdata(dev, rtc); return 0; diff --git a/drivers/rtc/systohc.c b/drivers/rtc/systohc.c index bf3e242ccc5..eb71872d036 100644 --- a/drivers/rtc/systohc.c +++ b/drivers/rtc/systohc.c @@ -20,16 +20,16 @@ * * If temporary failure is indicated the caller should try again 'soon' */ -int rtc_set_ntp_time(struct timespec now) +int rtc_set_ntp_time(struct timespec64 now) { struct rtc_device *rtc; struct rtc_time tm; int err = -ENODEV; if (now.tv_nsec < (NSEC_PER_SEC >> 1)) - rtc_time_to_tm(now.tv_sec, &tm); + rtc_time64_to_tm(now.tv_sec, &tm); else - rtc_time_to_tm(now.tv_sec + 1, &tm); + rtc_time64_to_tm(now.tv_sec + 1, &tm); rtc = rtc_class_open(CONFIG_RTC_HCTOSYS_DEVICE); if (rtc) { diff --git a/drivers/scsi/aic7xxx/aic79xx_core.c b/drivers/scsi/aic7xxx/aic79xx_core.c index 0bcacf71aef..97f2accd3db 100644 --- a/drivers/scsi/aic7xxx/aic79xx_core.c +++ b/drivers/scsi/aic7xxx/aic79xx_core.c @@ -1298,7 +1298,7 @@ rescan_fifos: /* * Wait for any inprogress DMA to complete and clear DMA state - * if this if for an SCB in the qinfifo. + * if this is for an SCB in the qinfifo. */ while (((ccscbctl = ahd_inb(ahd, CCSCBCTL)) & (CCARREN|CCSCBEN)) != 0) { diff --git a/drivers/scsi/esas2r/esas2r_init.c b/drivers/scsi/esas2r/esas2r_init.c index 6776931e25d..78ce4d61a69 100644 --- a/drivers/scsi/esas2r/esas2r_init.c +++ b/drivers/scsi/esas2r/esas2r_init.c @@ -813,12 +813,13 @@ static void esas2r_init_pci_cfg_space(struct esas2r_adapter *a) pci_read_config_word(a->pcid, pcie_cap_reg + PCI_EXP_DEVCTL, &devcontrol); - if ((devcontrol & PCI_EXP_DEVCTL_READRQ) > 0x2000) { + if ((devcontrol & PCI_EXP_DEVCTL_READRQ) > + PCI_EXP_DEVCTL_READRQ_512B) { esas2r_log(ESAS2R_LOG_INFO, "max read request size > 512B"); devcontrol &= ~PCI_EXP_DEVCTL_READRQ; - devcontrol |= 0x2000; + devcontrol |= PCI_EXP_DEVCTL_READRQ_512B; pci_write_config_word(a->pcid, pcie_cap_reg + PCI_EXP_DEVCTL, devcontrol); diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index cf222f46eac..ed31d8cc626 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -4217,7 +4217,7 @@ static ssize_t pmcraid_show_adapter_id( static struct device_attribute pmcraid_adapter_id_attr = { .attr = { .name = "adapter_id", - .mode = S_IRUGO | S_IWUSR, + .mode = S_IRUGO, }, .show = pmcraid_show_adapter_id, }; diff --git a/drivers/sfi/sfi_core.c b/drivers/sfi/sfi_core.c index 1e824fb1649..296db7a69c2 100644 --- a/drivers/sfi/sfi_core.c +++ b/drivers/sfi/sfi_core.c @@ -161,7 +161,7 @@ static int sfi_verify_table(struct sfi_table_header *table) * Check for common case that we can re-use mapping to SYST, * which requires syst_pa, syst_va to be initialized. */ -struct sfi_table_header *sfi_map_table(u64 pa) +static struct sfi_table_header *sfi_map_table(u64 pa) { struct sfi_table_header *th; u32 length; @@ -189,7 +189,7 @@ struct sfi_table_header *sfi_map_table(u64 pa) * Undoes effect of sfi_map_table() by unmapping table * if it did not completely fit on same page as SYST. */ -void sfi_unmap_table(struct sfi_table_header *th) +static void sfi_unmap_table(struct sfi_table_header *th) { if (!TABLE_ON_PAGE(syst_va, th, th->len)) sfi_unmap_memory(th, TABLE_ON_PAGE(th, th, th->len) ? diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index 99829985c1a..95ccedabba4 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -185,6 +185,16 @@ config SPI_DAVINCI help SPI master controller for DaVinci/DA8x/OMAP-L/AM1x SPI modules. +config SPI_DLN2 + tristate "Diolan DLN-2 USB SPI adapter" + depends on MFD_DLN2 + help + If you say yes to this option, support will be included for Diolan + DLN2, a USB to SPI interface. + + This driver can also be built as a module. If so, the module + will be called spi-dln2. + config SPI_EFM32 tristate "EFM32 SPI controller" depends on OF && ARM && (ARCH_EFM32 || COMPILE_TEST) @@ -279,7 +289,7 @@ config SPI_FSL_CPM depends on FSL_SOC config SPI_FSL_SPI - bool "Freescale SPI controller and Aeroflex Gaisler GRLIB SPI controller" + tristate "Freescale SPI controller and Aeroflex Gaisler GRLIB SPI controller" depends on OF select SPI_FSL_LIB select SPI_FSL_CPM if FSL_SOC @@ -292,7 +302,6 @@ config SPI_FSL_SPI config SPI_FSL_DSPI tristate "Freescale DSPI controller" - select SPI_BITBANG select REGMAP_MMIO depends on SOC_VF610 || COMPILE_TEST help @@ -300,7 +309,7 @@ config SPI_FSL_DSPI mode. VF610 platform uses the controller. config SPI_FSL_ESPI - bool "Freescale eSPI controller" + tristate "Freescale eSPI controller" depends on FSL_SOC select SPI_FSL_LIB help @@ -460,7 +469,6 @@ config SPI_S3C24XX_FIQ config SPI_S3C64XX tristate "Samsung S3C64XX series type SPI" depends on (PLAT_SAMSUNG || ARCH_EXYNOS) - select S3C64XX_PL080 if ARCH_S3C64XX help SPI driver for Samsung S3C64XX and newer SoCs. @@ -503,6 +511,13 @@ config SPI_SIRF help SPI driver for CSR SiRFprimaII SoCs +config SPI_ST_SSC4 + tristate "STMicroelectronics SPI SSC-based driver" + depends on ARCH_STI + help + STMicroelectronics SoCs support for SPI. If you say yes to + this option, support will be included for the SSC driven SPI. + config SPI_SUN4I tristate "Allwinner A10 SoCs SPI controller" depends on ARCH_SUNXI || COMPILE_TEST @@ -595,7 +610,6 @@ config SPI_XTENSA_XTFPGA 16 bit words in SPI mode 0, automatically asserting CS on transfer start and deasserting on end. - config SPI_NUC900 tristate "Nuvoton NUC900 series SPI" depends on ARCH_W90X900 diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile index 6b9d2ac629c..d8cbf654976 100644 --- a/drivers/spi/Makefile +++ b/drivers/spi/Makefile @@ -27,6 +27,7 @@ obj-$(CONFIG_SPI_CADENCE) += spi-cadence.o obj-$(CONFIG_SPI_CLPS711X) += spi-clps711x.o obj-$(CONFIG_SPI_COLDFIRE_QSPI) += spi-coldfire-qspi.o obj-$(CONFIG_SPI_DAVINCI) += spi-davinci.o +obj-$(CONFIG_SPI_DLN2) += spi-dln2.o obj-$(CONFIG_SPI_DESIGNWARE) += spi-dw.o obj-$(CONFIG_SPI_DW_MMIO) += spi-dw-mmio.o obj-$(CONFIG_SPI_DW_PCI) += spi-dw-midpci.o @@ -76,6 +77,7 @@ obj-$(CONFIG_SPI_SH_HSPI) += spi-sh-hspi.o obj-$(CONFIG_SPI_SH_MSIOF) += spi-sh-msiof.o obj-$(CONFIG_SPI_SH_SCI) += spi-sh-sci.o obj-$(CONFIG_SPI_SIRF) += spi-sirf.o +obj-$(CONFIG_SPI_ST_SSC4) += spi-st-ssc4.o obj-$(CONFIG_SPI_SUN4I) += spi-sun4i.o obj-$(CONFIG_SPI_SUN6I) += spi-sun6i.o obj-$(CONFIG_SPI_TEGRA114) += spi-tegra114.o diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c index 23d8f5f5657..9af7841f2e8 100644 --- a/drivers/spi/spi-atmel.c +++ b/drivers/spi/spi-atmel.c @@ -1046,6 +1046,7 @@ static int atmel_spi_one_transfer(struct spi_master *master, struct atmel_spi_device *asd; int timeout; int ret; + unsigned long dma_timeout; as = spi_master_get_devdata(master); @@ -1103,15 +1104,12 @@ static int atmel_spi_one_transfer(struct spi_master *master, /* interrupts are disabled, so free the lock for schedule */ atmel_spi_unlock(as); - ret = wait_for_completion_timeout(&as->xfer_completion, - SPI_DMA_TIMEOUT); + dma_timeout = wait_for_completion_timeout(&as->xfer_completion, + SPI_DMA_TIMEOUT); atmel_spi_lock(as); - if (WARN_ON(ret == 0)) { - dev_err(&spi->dev, - "spi trasfer timeout, err %d\n", ret); + if (WARN_ON(dma_timeout == 0)) { + dev_err(&spi->dev, "spi transfer timeout\n"); as->done_status = -EIO; - } else { - ret = 0; } if (as->done_status) diff --git a/drivers/spi/spi-au1550.c b/drivers/spi/spi-au1550.c index 326f4797368..f45e085c01a 100644 --- a/drivers/spi/spi-au1550.c +++ b/drivers/spi/spi-au1550.c @@ -15,10 +15,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/init.h> diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index 98aab457b24..419a782ab6d 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -17,10 +17,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ #include <linux/clk.h> diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c index c20530982e2..e73e2b052c9 100644 --- a/drivers/spi/spi-bcm63xx.c +++ b/drivers/spi/spi-bcm63xx.c @@ -13,10 +13,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, */ #include <linux/kernel.h> diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c index dc7d2c2d643..5ef6638d5e8 100644 --- a/drivers/spi/spi-bitbang.c +++ b/drivers/spi/spi-bitbang.c @@ -10,10 +10,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/spinlock.h> diff --git a/drivers/spi/spi-butterfly.c b/drivers/spi/spi-butterfly.c index ee4f91ccd8f..9a95862986c 100644 --- a/drivers/spi/spi-butterfly.c +++ b/drivers/spi/spi-butterfly.c @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/kernel.h> #include <linux/init.h> diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c index 41b5dc4445f..688956ff509 100644 --- a/drivers/spi/spi-coldfire-qspi.c +++ b/drivers/spi/spi-coldfire-qspi.c @@ -12,11 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA - * */ #include <linux/kernel.h> diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c index b3707badb1e..5e991065f5b 100644 --- a/drivers/spi/spi-davinci.c +++ b/drivers/spi/spi-davinci.c @@ -11,10 +11,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/interrupt.h> diff --git a/drivers/spi/spi-dln2.c b/drivers/spi/spi-dln2.c new file mode 100644 index 00000000000..3b7d91d94fe --- /dev/null +++ b/drivers/spi/spi-dln2.c @@ -0,0 +1,881 @@ +/* + * Driver for the Diolan DLN-2 USB-SPI adapter + * + * Copyright (c) 2014 Intel Corporation + * + * 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. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/mfd/dln2.h> +#include <linux/spi/spi.h> +#include <linux/pm_runtime.h> +#include <asm/unaligned.h> + +#define DLN2_SPI_MODULE_ID 0x02 +#define DLN2_SPI_CMD(cmd) DLN2_CMD(cmd, DLN2_SPI_MODULE_ID) + +/* SPI commands */ +#define DLN2_SPI_GET_PORT_COUNT DLN2_SPI_CMD(0x00) +#define DLN2_SPI_ENABLE DLN2_SPI_CMD(0x11) +#define DLN2_SPI_DISABLE DLN2_SPI_CMD(0x12) +#define DLN2_SPI_IS_ENABLED DLN2_SPI_CMD(0x13) +#define DLN2_SPI_SET_MODE DLN2_SPI_CMD(0x14) +#define DLN2_SPI_GET_MODE DLN2_SPI_CMD(0x15) +#define DLN2_SPI_SET_FRAME_SIZE DLN2_SPI_CMD(0x16) +#define DLN2_SPI_GET_FRAME_SIZE DLN2_SPI_CMD(0x17) +#define DLN2_SPI_SET_FREQUENCY DLN2_SPI_CMD(0x18) +#define DLN2_SPI_GET_FREQUENCY DLN2_SPI_CMD(0x19) +#define DLN2_SPI_READ_WRITE DLN2_SPI_CMD(0x1A) +#define DLN2_SPI_READ DLN2_SPI_CMD(0x1B) +#define DLN2_SPI_WRITE DLN2_SPI_CMD(0x1C) +#define DLN2_SPI_SET_DELAY_BETWEEN_SS DLN2_SPI_CMD(0x20) +#define DLN2_SPI_GET_DELAY_BETWEEN_SS DLN2_SPI_CMD(0x21) +#define DLN2_SPI_SET_DELAY_AFTER_SS DLN2_SPI_CMD(0x22) +#define DLN2_SPI_GET_DELAY_AFTER_SS DLN2_SPI_CMD(0x23) +#define DLN2_SPI_SET_DELAY_BETWEEN_FRAMES DLN2_SPI_CMD(0x24) +#define DLN2_SPI_GET_DELAY_BETWEEN_FRAMES DLN2_SPI_CMD(0x25) +#define DLN2_SPI_SET_SS DLN2_SPI_CMD(0x26) +#define DLN2_SPI_GET_SS DLN2_SPI_CMD(0x27) +#define DLN2_SPI_RELEASE_SS DLN2_SPI_CMD(0x28) +#define DLN2_SPI_SS_VARIABLE_ENABLE DLN2_SPI_CMD(0x2B) +#define DLN2_SPI_SS_VARIABLE_DISABLE DLN2_SPI_CMD(0x2C) +#define DLN2_SPI_SS_VARIABLE_IS_ENABLED DLN2_SPI_CMD(0x2D) +#define DLN2_SPI_SS_AAT_ENABLE DLN2_SPI_CMD(0x2E) +#define DLN2_SPI_SS_AAT_DISABLE DLN2_SPI_CMD(0x2F) +#define DLN2_SPI_SS_AAT_IS_ENABLED DLN2_SPI_CMD(0x30) +#define DLN2_SPI_SS_BETWEEN_FRAMES_ENABLE DLN2_SPI_CMD(0x31) +#define DLN2_SPI_SS_BETWEEN_FRAMES_DISABLE DLN2_SPI_CMD(0x32) +#define DLN2_SPI_SS_BETWEEN_FRAMES_IS_ENABLED DLN2_SPI_CMD(0x33) +#define DLN2_SPI_SET_CPHA DLN2_SPI_CMD(0x34) +#define DLN2_SPI_GET_CPHA DLN2_SPI_CMD(0x35) +#define DLN2_SPI_SET_CPOL DLN2_SPI_CMD(0x36) +#define DLN2_SPI_GET_CPOL DLN2_SPI_CMD(0x37) +#define DLN2_SPI_SS_MULTI_ENABLE DLN2_SPI_CMD(0x38) +#define DLN2_SPI_SS_MULTI_DISABLE DLN2_SPI_CMD(0x39) +#define DLN2_SPI_SS_MULTI_IS_ENABLED DLN2_SPI_CMD(0x3A) +#define DLN2_SPI_GET_SUPPORTED_MODES DLN2_SPI_CMD(0x40) +#define DLN2_SPI_GET_SUPPORTED_CPHA_VALUES DLN2_SPI_CMD(0x41) +#define DLN2_SPI_GET_SUPPORTED_CPOL_VALUES DLN2_SPI_CMD(0x42) +#define DLN2_SPI_GET_SUPPORTED_FRAME_SIZES DLN2_SPI_CMD(0x43) +#define DLN2_SPI_GET_SS_COUNT DLN2_SPI_CMD(0x44) +#define DLN2_SPI_GET_MIN_FREQUENCY DLN2_SPI_CMD(0x45) +#define DLN2_SPI_GET_MAX_FREQUENCY DLN2_SPI_CMD(0x46) +#define DLN2_SPI_GET_MIN_DELAY_BETWEEN_SS DLN2_SPI_CMD(0x47) +#define DLN2_SPI_GET_MAX_DELAY_BETWEEN_SS DLN2_SPI_CMD(0x48) +#define DLN2_SPI_GET_MIN_DELAY_AFTER_SS DLN2_SPI_CMD(0x49) +#define DLN2_SPI_GET_MAX_DELAY_AFTER_SS DLN2_SPI_CMD(0x4A) +#define DLN2_SPI_GET_MIN_DELAY_BETWEEN_FRAMES DLN2_SPI_CMD(0x4B) +#define DLN2_SPI_GET_MAX_DELAY_BETWEEN_FRAMES DLN2_SPI_CMD(0x4C) + +#define DLN2_SPI_MAX_XFER_SIZE 256 +#define DLN2_SPI_BUF_SIZE (DLN2_SPI_MAX_XFER_SIZE + 16) +#define DLN2_SPI_ATTR_LEAVE_SS_LOW BIT(0) +#define DLN2_TRANSFERS_WAIT_COMPLETE 1 +#define DLN2_TRANSFERS_CANCEL 0 +#define DLN2_RPM_AUTOSUSPEND_TIMEOUT 2000 + +struct dln2_spi { + struct platform_device *pdev; + struct spi_master *master; + u8 port; + + /* + * This buffer will be used mainly for read/write operations. Since + * they're quite large, we cannot use the stack. Protection is not + * needed because all SPI communication is serialized by the SPI core. + */ + void *buf; + + u8 bpw; + u32 speed; + u16 mode; + u8 cs; +}; + +/* + * Enable/Disable SPI module. The disable command will wait for transfers to + * complete first. + */ +static int dln2_spi_enable(struct dln2_spi *dln2, bool enable) +{ + u16 cmd; + struct { + u8 port; + u8 wait_for_completion; + } tx; + unsigned len = sizeof(tx); + + tx.port = dln2->port; + + if (enable) { + cmd = DLN2_SPI_ENABLE; + len -= sizeof(tx.wait_for_completion); + } else { + tx.wait_for_completion = DLN2_TRANSFERS_WAIT_COMPLETE; + cmd = DLN2_SPI_DISABLE; + } + + return dln2_transfer_tx(dln2->pdev, cmd, &tx, len); +} + +/* + * Select/unselect multiple CS lines. The selected lines will be automatically + * toggled LOW/HIGH by the board firmware during transfers, provided they're + * enabled first. + * + * Ex: cs_mask = 0x03 -> CS0 & CS1 will be selected and the next WR/RD operation + * will toggle the lines LOW/HIGH automatically. + */ +static int dln2_spi_cs_set(struct dln2_spi *dln2, u8 cs_mask) +{ + struct { + u8 port; + u8 cs; + } tx; + + tx.port = dln2->port; + + /* + * According to Diolan docs, "a slave device can be selected by changing + * the corresponding bit value to 0". The rest must be set to 1. Hence + * the bitwise NOT in front. + */ + tx.cs = ~cs_mask; + + return dln2_transfer_tx(dln2->pdev, DLN2_SPI_SET_SS, &tx, sizeof(tx)); +} + +/* + * Select one CS line. The other lines will be un-selected. + */ +static int dln2_spi_cs_set_one(struct dln2_spi *dln2, u8 cs) +{ + return dln2_spi_cs_set(dln2, BIT(cs)); +} + +/* + * Enable/disable CS lines for usage. The module has to be disabled first. + */ +static int dln2_spi_cs_enable(struct dln2_spi *dln2, u8 cs_mask, bool enable) +{ + struct { + u8 port; + u8 cs; + } tx; + u16 cmd; + + tx.port = dln2->port; + tx.cs = cs_mask; + cmd = enable ? DLN2_SPI_SS_MULTI_ENABLE : DLN2_SPI_SS_MULTI_DISABLE; + + return dln2_transfer_tx(dln2->pdev, cmd, &tx, sizeof(tx)); +} + +static int dln2_spi_cs_enable_all(struct dln2_spi *dln2, bool enable) +{ + u8 cs_mask = GENMASK(dln2->master->num_chipselect - 1, 0); + + return dln2_spi_cs_enable(dln2, cs_mask, enable); +} + +static int dln2_spi_get_cs_num(struct dln2_spi *dln2, u16 *cs_num) +{ + int ret; + struct { + u8 port; + } tx; + struct { + __le16 cs_count; + } rx; + unsigned rx_len = sizeof(rx); + + tx.port = dln2->port; + ret = dln2_transfer(dln2->pdev, DLN2_SPI_GET_SS_COUNT, &tx, sizeof(tx), + &rx, &rx_len); + if (ret < 0) + return ret; + if (rx_len < sizeof(rx)) + return -EPROTO; + + *cs_num = le16_to_cpu(rx.cs_count); + + dev_dbg(&dln2->pdev->dev, "cs_num = %d\n", *cs_num); + + return 0; +} + +static int dln2_spi_get_speed(struct dln2_spi *dln2, u16 cmd, u32 *freq) +{ + int ret; + struct { + u8 port; + } tx; + struct { + __le32 speed; + } rx; + unsigned rx_len = sizeof(rx); + + tx.port = dln2->port; + + ret = dln2_transfer(dln2->pdev, cmd, &tx, sizeof(tx), &rx, &rx_len); + if (ret < 0) + return ret; + if (rx_len < sizeof(rx)) + return -EPROTO; + + *freq = le32_to_cpu(rx.speed); + + return 0; +} + +/* + * Get bus min/max frequencies. + */ +static int dln2_spi_get_speed_range(struct dln2_spi *dln2, u32 *fmin, u32 *fmax) +{ + int ret; + + ret = dln2_spi_get_speed(dln2, DLN2_SPI_GET_MIN_FREQUENCY, fmin); + if (ret < 0) + return ret; + + ret = dln2_spi_get_speed(dln2, DLN2_SPI_GET_MAX_FREQUENCY, fmax); + if (ret < 0) + return ret; + + dev_dbg(&dln2->pdev->dev, "freq_min = %d, freq_max = %d\n", + *fmin, *fmax); + + return 0; +} + +/* + * Set the bus speed. The module will automatically round down to the closest + * available frequency and returns it. The module has to be disabled first. + */ +static int dln2_spi_set_speed(struct dln2_spi *dln2, u32 speed) +{ + int ret; + struct { + u8 port; + __le32 speed; + } __packed tx; + struct { + __le32 speed; + } rx; + int rx_len = sizeof(rx); + + tx.port = dln2->port; + tx.speed = cpu_to_le32(speed); + + ret = dln2_transfer(dln2->pdev, DLN2_SPI_SET_FREQUENCY, &tx, sizeof(tx), + &rx, &rx_len); + if (ret < 0) + return ret; + if (rx_len < sizeof(rx)) + return -EPROTO; + + return 0; +} + +/* + * Change CPOL & CPHA. The module has to be disabled first. + */ +static int dln2_spi_set_mode(struct dln2_spi *dln2, u8 mode) +{ + struct { + u8 port; + u8 mode; + } tx; + + tx.port = dln2->port; + tx.mode = mode; + + return dln2_transfer_tx(dln2->pdev, DLN2_SPI_SET_MODE, &tx, sizeof(tx)); +} + +/* + * Change frame size. The module has to be disabled first. + */ +static int dln2_spi_set_bpw(struct dln2_spi *dln2, u8 bpw) +{ + struct { + u8 port; + u8 bpw; + } tx; + + tx.port = dln2->port; + tx.bpw = bpw; + + return dln2_transfer_tx(dln2->pdev, DLN2_SPI_SET_FRAME_SIZE, + &tx, sizeof(tx)); +} + +static int dln2_spi_get_supported_frame_sizes(struct dln2_spi *dln2, + u32 *bpw_mask) +{ + int ret; + struct { + u8 port; + } tx; + struct { + u8 count; + u8 frame_sizes[36]; + } *rx = dln2->buf; + unsigned rx_len = sizeof(*rx); + int i; + + tx.port = dln2->port; + + ret = dln2_transfer(dln2->pdev, DLN2_SPI_GET_SUPPORTED_FRAME_SIZES, + &tx, sizeof(tx), rx, &rx_len); + if (ret < 0) + return ret; + if (rx_len < sizeof(*rx)) + return -EPROTO; + if (rx->count > ARRAY_SIZE(rx->frame_sizes)) + return -EPROTO; + + *bpw_mask = 0; + for (i = 0; i < rx->count; i++) + *bpw_mask |= BIT(rx->frame_sizes[i] - 1); + + dev_dbg(&dln2->pdev->dev, "bpw_mask = 0x%X\n", *bpw_mask); + + return 0; +} + +/* + * Copy the data to DLN2 buffer and change the byte order to LE, requested by + * DLN2 module. SPI core makes sure that the data length is a multiple of word + * size. + */ +static int dln2_spi_copy_to_buf(u8 *dln2_buf, const u8 *src, u16 len, u8 bpw) +{ +#ifdef __LITTLE_ENDIAN + memcpy(dln2_buf, src, len); +#else + if (bpw <= 8) { + memcpy(dln2_buf, src, len); + } else if (bpw <= 16) { + __le16 *d = (__le16 *)dln2_buf; + u16 *s = (u16 *)src; + + len = len / 2; + while (len--) + *d++ = cpu_to_le16p(s++); + } else { + __le32 *d = (__le32 *)dln2_buf; + u32 *s = (u32 *)src; + + len = len / 4; + while (len--) + *d++ = cpu_to_le32p(s++); + } +#endif + + return 0; +} + +/* + * Copy the data from DLN2 buffer and convert to CPU byte order since the DLN2 + * buffer is LE ordered. SPI core makes sure that the data length is a multiple + * of word size. The RX dln2_buf is 2 byte aligned so, for BE, we have to make + * sure we avoid unaligned accesses for 32 bit case. + */ +static int dln2_spi_copy_from_buf(u8 *dest, const u8 *dln2_buf, u16 len, u8 bpw) +{ +#ifdef __LITTLE_ENDIAN + memcpy(dest, dln2_buf, len); +#else + if (bpw <= 8) { + memcpy(dest, dln2_buf, len); + } else if (bpw <= 16) { + u16 *d = (u16 *)dest; + __le16 *s = (__le16 *)dln2_buf; + + len = len / 2; + while (len--) + *d++ = le16_to_cpup(s++); + } else { + u32 *d = (u32 *)dest; + __le32 *s = (__le32 *)dln2_buf; + + len = len / 4; + while (len--) + *d++ = get_unaligned_le32(s++); + } +#endif + + return 0; +} + +/* + * Perform one write operation. + */ +static int dln2_spi_write_one(struct dln2_spi *dln2, const u8 *data, + u16 data_len, u8 attr) +{ + struct { + u8 port; + __le16 size; + u8 attr; + u8 buf[DLN2_SPI_MAX_XFER_SIZE]; + } __packed *tx = dln2->buf; + unsigned tx_len; + + BUILD_BUG_ON(sizeof(*tx) > DLN2_SPI_BUF_SIZE); + + if (data_len > DLN2_SPI_MAX_XFER_SIZE) + return -EINVAL; + + tx->port = dln2->port; + tx->size = cpu_to_le16(data_len); + tx->attr = attr; + + dln2_spi_copy_to_buf(tx->buf, data, data_len, dln2->bpw); + + tx_len = sizeof(*tx) + data_len - DLN2_SPI_MAX_XFER_SIZE; + return dln2_transfer_tx(dln2->pdev, DLN2_SPI_WRITE, tx, tx_len); +} + +/* + * Perform one read operation. + */ +static int dln2_spi_read_one(struct dln2_spi *dln2, u8 *data, + u16 data_len, u8 attr) +{ + int ret; + struct { + u8 port; + __le16 size; + u8 attr; + } __packed tx; + struct { + __le16 size; + u8 buf[DLN2_SPI_MAX_XFER_SIZE]; + } __packed *rx = dln2->buf; + unsigned rx_len = sizeof(*rx); + + BUILD_BUG_ON(sizeof(*rx) > DLN2_SPI_BUF_SIZE); + + if (data_len > DLN2_SPI_MAX_XFER_SIZE) + return -EINVAL; + + tx.port = dln2->port; + tx.size = cpu_to_le16(data_len); + tx.attr = attr; + + ret = dln2_transfer(dln2->pdev, DLN2_SPI_READ, &tx, sizeof(tx), + rx, &rx_len); + if (ret < 0) + return ret; + if (rx_len < sizeof(rx->size) + data_len) + return -EPROTO; + if (le16_to_cpu(rx->size) != data_len) + return -EPROTO; + + dln2_spi_copy_from_buf(data, rx->buf, data_len, dln2->bpw); + + return 0; +} + +/* + * Perform one write & read operation. + */ +static int dln2_spi_read_write_one(struct dln2_spi *dln2, const u8 *tx_data, + u8 *rx_data, u16 data_len, u8 attr) +{ + int ret; + struct { + u8 port; + __le16 size; + u8 attr; + u8 buf[DLN2_SPI_MAX_XFER_SIZE]; + } __packed *tx; + struct { + __le16 size; + u8 buf[DLN2_SPI_MAX_XFER_SIZE]; + } __packed *rx; + unsigned tx_len, rx_len; + + BUILD_BUG_ON(sizeof(*tx) > DLN2_SPI_BUF_SIZE || + sizeof(*rx) > DLN2_SPI_BUF_SIZE); + + if (data_len > DLN2_SPI_MAX_XFER_SIZE) + return -EINVAL; + + /* + * Since this is a pseudo full-duplex communication, we're perfectly + * safe to use the same buffer for both tx and rx. When DLN2 sends the + * response back, with the rx data, we don't need the tx buffer anymore. + */ + tx = dln2->buf; + rx = dln2->buf; + + tx->port = dln2->port; + tx->size = cpu_to_le16(data_len); + tx->attr = attr; + + dln2_spi_copy_to_buf(tx->buf, tx_data, data_len, dln2->bpw); + + tx_len = sizeof(*tx) + data_len - DLN2_SPI_MAX_XFER_SIZE; + rx_len = sizeof(*rx); + + ret = dln2_transfer(dln2->pdev, DLN2_SPI_READ_WRITE, tx, tx_len, + rx, &rx_len); + if (ret < 0) + return ret; + if (rx_len < sizeof(rx->size) + data_len) + return -EPROTO; + if (le16_to_cpu(rx->size) != data_len) + return -EPROTO; + + dln2_spi_copy_from_buf(rx_data, rx->buf, data_len, dln2->bpw); + + return 0; +} + +/* + * Read/Write wrapper. It will automatically split an operation into multiple + * single ones due to device buffer constraints. + */ +static int dln2_spi_rdwr(struct dln2_spi *dln2, const u8 *tx_data, + u8 *rx_data, u16 data_len, u8 attr) { + int ret; + u16 len; + u8 temp_attr; + u16 remaining = data_len; + u16 offset; + + do { + if (remaining > DLN2_SPI_MAX_XFER_SIZE) { + len = DLN2_SPI_MAX_XFER_SIZE; + temp_attr = DLN2_SPI_ATTR_LEAVE_SS_LOW; + } else { + len = remaining; + temp_attr = attr; + } + + offset = data_len - remaining; + + if (tx_data && rx_data) { + ret = dln2_spi_read_write_one(dln2, + tx_data + offset, + rx_data + offset, + len, temp_attr); + } else if (tx_data) { + ret = dln2_spi_write_one(dln2, + tx_data + offset, + len, temp_attr); + } else if (rx_data) { + ret = dln2_spi_read_one(dln2, + rx_data + offset, + len, temp_attr); + } else { + return -EINVAL; + } + + if (ret < 0) + return ret; + + remaining -= len; + } while (remaining); + + return 0; +} + +static int dln2_spi_prepare_message(struct spi_master *master, + struct spi_message *message) +{ + int ret; + struct dln2_spi *dln2 = spi_master_get_devdata(master); + struct spi_device *spi = message->spi; + + if (dln2->cs != spi->chip_select) { + ret = dln2_spi_cs_set_one(dln2, spi->chip_select); + if (ret < 0) + return ret; + + dln2->cs = spi->chip_select; + } + + return 0; +} + +static int dln2_spi_transfer_setup(struct dln2_spi *dln2, u32 speed, + u8 bpw, u8 mode) +{ + int ret; + bool bus_setup_change; + + bus_setup_change = dln2->speed != speed || dln2->mode != mode || + dln2->bpw != bpw; + + if (!bus_setup_change) + return 0; + + ret = dln2_spi_enable(dln2, false); + if (ret < 0) + return ret; + + if (dln2->speed != speed) { + ret = dln2_spi_set_speed(dln2, speed); + if (ret < 0) + return ret; + + dln2->speed = speed; + } + + if (dln2->mode != mode) { + ret = dln2_spi_set_mode(dln2, mode & 0x3); + if (ret < 0) + return ret; + + dln2->mode = mode; + } + + if (dln2->bpw != bpw) { + ret = dln2_spi_set_bpw(dln2, bpw); + if (ret < 0) + return ret; + + dln2->bpw = bpw; + } + + return dln2_spi_enable(dln2, true); +} + +static int dln2_spi_transfer_one(struct spi_master *master, + struct spi_device *spi, + struct spi_transfer *xfer) +{ + struct dln2_spi *dln2 = spi_master_get_devdata(master); + int status; + u8 attr = 0; + + status = dln2_spi_transfer_setup(dln2, xfer->speed_hz, + xfer->bits_per_word, + spi->mode); + if (status < 0) { + dev_err(&dln2->pdev->dev, "Cannot setup transfer\n"); + return status; + } + + if (!xfer->cs_change && !spi_transfer_is_last(master, xfer)) + attr = DLN2_SPI_ATTR_LEAVE_SS_LOW; + + status = dln2_spi_rdwr(dln2, xfer->tx_buf, xfer->rx_buf, + xfer->len, attr); + if (status < 0) + dev_err(&dln2->pdev->dev, "write/read failed!\n"); + + return status; +} + +static int dln2_spi_probe(struct platform_device *pdev) +{ + struct spi_master *master; + struct dln2_spi *dln2; + struct dln2_platform_data *pdata = dev_get_platdata(&pdev->dev); + int ret; + + master = spi_alloc_master(&pdev->dev, sizeof(*dln2)); + if (!master) + return -ENOMEM; + + platform_set_drvdata(pdev, master); + + dln2 = spi_master_get_devdata(master); + + dln2->buf = devm_kmalloc(&pdev->dev, DLN2_SPI_BUF_SIZE, GFP_KERNEL); + if (!dln2->buf) { + ret = -ENOMEM; + goto exit_free_master; + } + + dln2->master = master; + dln2->pdev = pdev; + dln2->port = pdata->port; + /* cs/mode can never be 0xff, so the first transfer will set them */ + dln2->cs = 0xff; + dln2->mode = 0xff; + + /* disable SPI module before continuing with the setup */ + ret = dln2_spi_enable(dln2, false); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to disable SPI module\n"); + goto exit_free_master; + } + + ret = dln2_spi_get_cs_num(dln2, &master->num_chipselect); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to get number of CS pins\n"); + goto exit_free_master; + } + + ret = dln2_spi_get_speed_range(dln2, + &master->min_speed_hz, + &master->max_speed_hz); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to read bus min/max freqs\n"); + goto exit_free_master; + } + + ret = dln2_spi_get_supported_frame_sizes(dln2, + &master->bits_per_word_mask); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to read supported frame sizes\n"); + goto exit_free_master; + } + + ret = dln2_spi_cs_enable_all(dln2, true); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to enable CS pins\n"); + goto exit_free_master; + } + + master->bus_num = -1; + master->mode_bits = SPI_CPOL | SPI_CPHA; + master->prepare_message = dln2_spi_prepare_message; + master->transfer_one = dln2_spi_transfer_one; + master->auto_runtime_pm = true; + + /* enable SPI module, we're good to go */ + ret = dln2_spi_enable(dln2, true); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to enable SPI module\n"); + goto exit_free_master; + } + + pm_runtime_set_autosuspend_delay(&pdev->dev, + DLN2_RPM_AUTOSUSPEND_TIMEOUT); + pm_runtime_use_autosuspend(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + ret = devm_spi_register_master(&pdev->dev, master); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to register master\n"); + goto exit_register; + } + + return ret; + +exit_register: + pm_runtime_disable(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); + + if (dln2_spi_enable(dln2, false) < 0) + dev_err(&pdev->dev, "Failed to disable SPI module\n"); +exit_free_master: + spi_master_put(master); + + return ret; +} + +static int dln2_spi_remove(struct platform_device *pdev) +{ + struct spi_master *master = spi_master_get(platform_get_drvdata(pdev)); + struct dln2_spi *dln2 = spi_master_get_devdata(master); + + pm_runtime_disable(&pdev->dev); + + if (dln2_spi_enable(dln2, false) < 0) + dev_err(&pdev->dev, "Failed to disable SPI module\n"); + + return 0; +} + +#ifdef CONFIG_PM_SLEEP +static int dln2_spi_suspend(struct device *dev) +{ + int ret; + struct spi_master *master = dev_get_drvdata(dev); + struct dln2_spi *dln2 = spi_master_get_devdata(master); + + ret = spi_master_suspend(master); + if (ret < 0) + return ret; + + if (!pm_runtime_suspended(dev)) { + ret = dln2_spi_enable(dln2, false); + if (ret < 0) + return ret; + } + + /* + * USB power may be cut off during sleep. Resetting the following + * parameters will force the board to be set up before first transfer. + */ + dln2->cs = 0xff; + dln2->speed = 0; + dln2->bpw = 0; + dln2->mode = 0xff; + + return 0; +} + +static int dln2_spi_resume(struct device *dev) +{ + int ret; + struct spi_master *master = dev_get_drvdata(dev); + struct dln2_spi *dln2 = spi_master_get_devdata(master); + + if (!pm_runtime_suspended(dev)) { + ret = dln2_spi_cs_enable_all(dln2, true); + if (ret < 0) + return ret; + + ret = dln2_spi_enable(dln2, true); + if (ret < 0) + return ret; + } + + return spi_master_resume(master); +} +#endif /* CONFIG_PM_SLEEP */ + +#ifdef CONFIG_PM +static int dln2_spi_runtime_suspend(struct device *dev) +{ + struct spi_master *master = dev_get_drvdata(dev); + struct dln2_spi *dln2 = spi_master_get_devdata(master); + + return dln2_spi_enable(dln2, false); +} + +static int dln2_spi_runtime_resume(struct device *dev) +{ + struct spi_master *master = dev_get_drvdata(dev); + struct dln2_spi *dln2 = spi_master_get_devdata(master); + + return dln2_spi_enable(dln2, true); +} +#endif /* CONFIG_PM */ + +static const struct dev_pm_ops dln2_spi_pm = { + SET_SYSTEM_SLEEP_PM_OPS(dln2_spi_suspend, dln2_spi_resume) + SET_RUNTIME_PM_OPS(dln2_spi_runtime_suspend, + dln2_spi_runtime_resume, NULL) +}; + +static struct platform_driver spi_dln2_driver = { + .driver = { + .name = "dln2-spi", + .pm = &dln2_spi_pm, + }, + .probe = dln2_spi_probe, + .remove = dln2_spi_remove, +}; +module_platform_driver(spi_dln2_driver); + +MODULE_DESCRIPTION("Driver for the Diolan DLN2 SPI master interface"); +MODULE_AUTHOR("Laurentiu Palcu <laurentiu.palcu@intel.com>"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:dln2-spi"); diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c index a67d37c7e3c..a0197fd4e95 100644 --- a/drivers/spi/spi-dw-mid.c +++ b/drivers/spi/spi-dw-mid.c @@ -247,9 +247,9 @@ static struct dw_spi_dma_ops mid_dma_ops = { /* Some specific info for SPI0 controller on Intel MID */ -/* HW info for MRST CLk Control Unit, one 32b reg */ +/* HW info for MRST Clk Control Unit, 32b reg per controller */ #define MRST_SPI_CLK_BASE 100000000 /* 100m */ -#define MRST_CLK_SPI0_REG 0xff11d86c +#define MRST_CLK_SPI_REG 0xff11d86c #define CLK_SPI_BDIV_OFFSET 0 #define CLK_SPI_BDIV_MASK 0x00000007 #define CLK_SPI_CDIV_OFFSET 9 @@ -261,16 +261,17 @@ int dw_spi_mid_init(struct dw_spi *dws) void __iomem *clk_reg; u32 clk_cdiv; - clk_reg = ioremap_nocache(MRST_CLK_SPI0_REG, 16); + clk_reg = ioremap_nocache(MRST_CLK_SPI_REG, 16); if (!clk_reg) return -ENOMEM; - /* get SPI controller operating freq info */ - clk_cdiv = (readl(clk_reg) & CLK_SPI_CDIV_MASK) >> CLK_SPI_CDIV_OFFSET; + /* Get SPI controller operating freq info */ + clk_cdiv = readl(clk_reg + dws->bus_num * sizeof(u32)); + clk_cdiv &= CLK_SPI_CDIV_MASK; + clk_cdiv >>= CLK_SPI_CDIV_OFFSET; dws->max_freq = MRST_SPI_CLK_BASE / (clk_cdiv + 1); - iounmap(clk_reg); - dws->num_cs = 16; + iounmap(clk_reg); #ifdef CONFIG_SPI_DW_MID_DMA dws->dma_priv = kzalloc(sizeof(struct mid_dma), GFP_KERNEL); diff --git a/drivers/spi/spi-dw-pci.c b/drivers/spi/spi-dw-pci.c index ba68da12cdf..5ba331047cb 100644 --- a/drivers/spi/spi-dw-pci.c +++ b/drivers/spi/spi-dw-pci.c @@ -30,10 +30,20 @@ struct dw_spi_pci { struct spi_pci_desc { int (*setup)(struct dw_spi *); + u16 num_cs; + u16 bus_num; }; -static struct spi_pci_desc spi_pci_mid_desc = { +static struct spi_pci_desc spi_pci_mid_desc_1 = { .setup = dw_spi_mid_init, + .num_cs = 32, + .bus_num = 0, +}; + +static struct spi_pci_desc spi_pci_mid_desc_2 = { + .setup = dw_spi_mid_init, + .num_cs = 4, + .bus_num = 1, }; static int spi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) @@ -65,18 +75,23 @@ static int spi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dws->regs = pcim_iomap_table(pdev)[pci_bar]; - dws->bus_num = 0; - dws->num_cs = 4; dws->irq = pdev->irq; /* * Specific handling for paltforms, like dma setup, * clock rate, FIFO depth. */ - if (desc && desc->setup) { - ret = desc->setup(dws); - if (ret) - return ret; + if (desc) { + dws->num_cs = desc->num_cs; + dws->bus_num = desc->bus_num; + + if (desc->setup) { + ret = desc->setup(dws); + if (ret) + return ret; + } + } else { + return -ENODEV; } ret = dw_spi_add_host(&pdev->dev, dws); @@ -121,7 +136,14 @@ static SIMPLE_DEV_PM_OPS(dw_spi_pm_ops, spi_suspend, spi_resume); static const struct pci_device_id pci_ids[] = { /* Intel MID platform SPI controller 0 */ - { PCI_VDEVICE(INTEL, 0x0800), (kernel_ulong_t)&spi_pci_mid_desc}, + /* + * The access to the device 8086:0801 is disabled by HW, since it's + * exclusively used by SCU to communicate with MSIC. + */ + /* Intel MID platform SPI controller 1 */ + { PCI_VDEVICE(INTEL, 0x0800), (kernel_ulong_t)&spi_pci_mid_desc_1}, + /* Intel MID platform SPI controller 2 */ + { PCI_VDEVICE(INTEL, 0x0812), (kernel_ulong_t)&spi_pci_mid_desc_2}, {}, }; diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c index 8edcd1b8456..5a97a62b298 100644 --- a/drivers/spi/spi-dw.c +++ b/drivers/spi/spi-dw.c @@ -608,7 +608,7 @@ static void dw_spi_cleanup(struct spi_device *spi) } /* Restart the controller, disable all interrupts, clean rx fifo */ -static void spi_hw_init(struct dw_spi *dws) +static void spi_hw_init(struct device *dev, struct dw_spi *dws) { spi_enable_chip(dws, 0); spi_mask_intr(dws, 0xff); @@ -626,9 +626,10 @@ static void spi_hw_init(struct dw_spi *dws) if (fifo != dw_readw(dws, DW_SPI_TXFLTR)) break; } + dw_writew(dws, DW_SPI_TXFLTR, 0); dws->fifo_len = (fifo == 2) ? 0 : fifo - 1; - dw_writew(dws, DW_SPI_TXFLTR, 0); + dev_dbg(dev, "Detected FIFO size: %u bytes\n", dws->fifo_len); } } @@ -668,7 +669,7 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws) master->dev.of_node = dev->of_node; /* Basic HW init */ - spi_hw_init(dws); + spi_hw_init(dev, dws); if (dws->dma_ops && dws->dma_ops->dma_init) { ret = dws->dma_ops->dma_init(dws); @@ -731,7 +732,7 @@ int dw_spi_resume_host(struct dw_spi *dws) { int ret; - spi_hw_init(dws); + spi_hw_init(&dws->master->dev, dws); ret = spi_master_resume(dws->master); if (ret) dev_err(&dws->master->dev, "fail to start queue (%d)\n", ret); diff --git a/drivers/spi/spi-falcon.c b/drivers/spi/spi-falcon.c index 912b9037e9c..286b2c81fc6 100644 --- a/drivers/spi/spi-falcon.c +++ b/drivers/spi/spi-falcon.c @@ -353,16 +353,6 @@ static int falcon_sflash_setup(struct spi_device *spi) return 0; } -static int falcon_sflash_prepare_xfer(struct spi_master *master) -{ - return 0; -} - -static int falcon_sflash_unprepare_xfer(struct spi_master *master) -{ - return 0; -} - static int falcon_sflash_xfer_one(struct spi_master *master, struct spi_message *m) { @@ -420,9 +410,7 @@ static int falcon_sflash_probe(struct platform_device *pdev) master->mode_bits = SPI_MODE_3; master->flags = SPI_MASTER_HALF_DUPLEX; master->setup = falcon_sflash_setup; - master->prepare_transfer_hardware = falcon_sflash_prepare_xfer; master->transfer_one_message = falcon_sflash_xfer_one; - master->unprepare_transfer_hardware = falcon_sflash_unprepare_xfer; master->dev.of_node = pdev->dev.of_node; ret = devm_spi_register_master(&pdev->dev, master); diff --git a/drivers/spi/spi-fsl-cpm.c b/drivers/spi/spi-fsl-cpm.c index e85ab1cb17a..9c46a305874 100644 --- a/drivers/spi/spi-fsl-cpm.c +++ b/drivers/spi/spi-fsl-cpm.c @@ -20,6 +20,7 @@ #include <linux/dma-mapping.h> #include <linux/fsl_devices.h> #include <linux/kernel.h> +#include <linux/module.h> #include <linux/of_address.h> #include <linux/spi/spi.h> #include <linux/types.h> @@ -68,6 +69,7 @@ void fsl_spi_cpm_reinit_txrx(struct mpc8xxx_spi *mspi) } } } +EXPORT_SYMBOL_GPL(fsl_spi_cpm_reinit_txrx); static void fsl_spi_cpm_bufs_start(struct mpc8xxx_spi *mspi) { @@ -162,6 +164,7 @@ err_rx_dma: dma_unmap_single(dev, mspi->tx_dma, t->len, DMA_TO_DEVICE); return -ENOMEM; } +EXPORT_SYMBOL_GPL(fsl_spi_cpm_bufs); void fsl_spi_cpm_bufs_complete(struct mpc8xxx_spi *mspi) { @@ -174,6 +177,7 @@ void fsl_spi_cpm_bufs_complete(struct mpc8xxx_spi *mspi) dma_unmap_single(dev, mspi->rx_dma, t->len, DMA_FROM_DEVICE); mspi->xfer_in_progress = NULL; } +EXPORT_SYMBOL_GPL(fsl_spi_cpm_bufs_complete); void fsl_spi_cpm_irq(struct mpc8xxx_spi *mspi, u32 events) { @@ -198,6 +202,7 @@ void fsl_spi_cpm_irq(struct mpc8xxx_spi *mspi, u32 events) else complete(&mspi->done); } +EXPORT_SYMBOL_GPL(fsl_spi_cpm_irq); static void *fsl_spi_alloc_dummy_rx(void) { @@ -375,6 +380,7 @@ err_pram: fsl_spi_free_dummy_rx(); return -ENOMEM; } +EXPORT_SYMBOL_GPL(fsl_spi_cpm_init); void fsl_spi_cpm_free(struct mpc8xxx_spi *mspi) { @@ -389,3 +395,6 @@ void fsl_spi_cpm_free(struct mpc8xxx_spi *mspi) cpm_muram_free(cpm_muram_offset(mspi->pram)); fsl_spi_free_dummy_rx(); } +EXPORT_SYMBOL_GPL(fsl_spi_cpm_free); + +MODULE_LICENSE("GPL"); diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 9b80d54d4dd..d1a39249704 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -106,7 +106,7 @@ struct chip_data { }; struct fsl_dspi { - struct spi_bitbang bitbang; + struct spi_master *master; struct platform_device *pdev; struct regmap *regmap; @@ -114,6 +114,7 @@ struct fsl_dspi { struct clk *clk; struct spi_transfer *cur_transfer; + struct spi_message *cur_msg; struct chip_data *cur_chip; size_t len; void *tx; @@ -123,6 +124,7 @@ struct fsl_dspi { char dataflags; u8 cs; u16 void_write_data; + u32 cs_change; wait_queue_head_t waitq; u32 waitflags; @@ -225,6 +227,8 @@ static int dspi_transfer_write(struct fsl_dspi *dspi) if (dspi->len == 0 || tx_count == DSPI_FIFO_SIZE - 1) { /* last transfer in the transfer */ dspi_pushr |= SPI_PUSHR_EOQ; + if ((dspi->cs_change) && (!dspi->len)) + dspi_pushr &= ~SPI_PUSHR_CONT; } else if (tx_word && (dspi->len == 1)) dspi_pushr |= SPI_PUSHR_EOQ; @@ -246,6 +250,7 @@ static int dspi_transfer_read(struct fsl_dspi *dspi) int rx_count = 0; int rx_word = is_double_byte_mode(dspi); u16 d; + while ((dspi->rx < dspi->rx_end) && (rx_count < DSPI_FIFO_SIZE)) { if (rx_word) { @@ -276,69 +281,79 @@ static int dspi_transfer_read(struct fsl_dspi *dspi) return rx_count; } -static int dspi_txrx_transfer(struct spi_device *spi, struct spi_transfer *t) +static int dspi_transfer_one_message(struct spi_master *master, + struct spi_message *message) { - struct fsl_dspi *dspi = spi_master_get_devdata(spi->master); - dspi->cur_transfer = t; - dspi->cur_chip = spi_get_ctldata(spi); - dspi->cs = spi->chip_select; - dspi->void_write_data = dspi->cur_chip->void_write_data; - - dspi->dataflags = 0; - dspi->tx = (void *)t->tx_buf; - dspi->tx_end = dspi->tx + t->len; - dspi->rx = t->rx_buf; - dspi->rx_end = dspi->rx + t->len; - dspi->len = t->len; - - if (!dspi->rx) - dspi->dataflags |= TRAN_STATE_RX_VOID; - - if (!dspi->tx) - dspi->dataflags |= TRAN_STATE_TX_VOID; - - regmap_write(dspi->regmap, SPI_MCR, dspi->cur_chip->mcr_val); - regmap_write(dspi->regmap, SPI_CTAR(dspi->cs), dspi->cur_chip->ctar_val); - regmap_write(dspi->regmap, SPI_RSER, SPI_RSER_EOQFE); - - if (t->speed_hz) + struct fsl_dspi *dspi = spi_master_get_devdata(master); + struct spi_device *spi = message->spi; + struct spi_transfer *transfer; + int status = 0; + message->actual_length = 0; + + list_for_each_entry(transfer, &message->transfers, transfer_list) { + dspi->cur_transfer = transfer; + dspi->cur_msg = message; + dspi->cur_chip = spi_get_ctldata(spi); + dspi->cs = spi->chip_select; + if (dspi->cur_transfer->transfer_list.next + == &dspi->cur_msg->transfers) + transfer->cs_change = 1; + dspi->cs_change = transfer->cs_change; + dspi->void_write_data = dspi->cur_chip->void_write_data; + + dspi->dataflags = 0; + dspi->tx = (void *)transfer->tx_buf; + dspi->tx_end = dspi->tx + transfer->len; + dspi->rx = transfer->rx_buf; + dspi->rx_end = dspi->rx + transfer->len; + dspi->len = transfer->len; + + if (!dspi->rx) + dspi->dataflags |= TRAN_STATE_RX_VOID; + + if (!dspi->tx) + dspi->dataflags |= TRAN_STATE_TX_VOID; + + regmap_write(dspi->regmap, SPI_MCR, dspi->cur_chip->mcr_val); + regmap_update_bits(dspi->regmap, SPI_MCR, + SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF, + SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF); regmap_write(dspi->regmap, SPI_CTAR(dspi->cs), dspi->cur_chip->ctar_val); + if (transfer->speed_hz) + regmap_write(dspi->regmap, SPI_CTAR(dspi->cs), + dspi->cur_chip->ctar_val); - dspi_transfer_write(dspi); - - if (wait_event_interruptible(dspi->waitq, dspi->waitflags)) - dev_err(&dspi->pdev->dev, "wait transfer complete fail!\n"); - dspi->waitflags = 0; - - return t->len - dspi->len; -} + regmap_write(dspi->regmap, SPI_RSER, SPI_RSER_EOQFE); + message->actual_length += dspi_transfer_write(dspi); -static void dspi_chipselect(struct spi_device *spi, int value) -{ - struct fsl_dspi *dspi = spi_master_get_devdata(spi->master); - unsigned int pushr; + if (wait_event_interruptible(dspi->waitq, dspi->waitflags)) + dev_err(&dspi->pdev->dev, "wait transfer complete fail!\n"); + dspi->waitflags = 0; - regmap_read(dspi->regmap, SPI_PUSHR, &pushr); - - switch (value) { - case BITBANG_CS_ACTIVE: - pushr |= SPI_PUSHR_CONT; - break; - case BITBANG_CS_INACTIVE: - pushr &= ~SPI_PUSHR_CONT; - break; + if (transfer->delay_usecs) + udelay(transfer->delay_usecs); } - regmap_write(dspi->regmap, SPI_PUSHR, pushr); + message->status = status; + spi_finalize_current_message(master); + + return status; } -static int dspi_setup_transfer(struct spi_device *spi, struct spi_transfer *t) +static int dspi_setup(struct spi_device *spi) { struct chip_data *chip; struct fsl_dspi *dspi = spi_master_get_devdata(spi->master); unsigned char br = 0, pbr = 0, fmsz = 0; + if ((spi->bits_per_word >= 4) && (spi->bits_per_word <= 16)) { + fmsz = spi->bits_per_word - 1; + } else { + pr_err("Invalid wordsize\n"); + return -ENODEV; + } + /* Only alloc on first setup */ chip = spi_get_ctldata(spi); if (chip == NULL) { @@ -349,12 +364,6 @@ static int dspi_setup_transfer(struct spi_device *spi, struct spi_transfer *t) chip->mcr_val = SPI_MCR_MASTER | SPI_MCR_PCSIS | SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF; - if ((spi->bits_per_word >= 4) && (spi->bits_per_word <= 16)) { - fmsz = spi->bits_per_word - 1; - } else { - pr_err("Invalid wordsize\n"); - return -ENODEV; - } chip->void_write_data = 0; @@ -373,14 +382,6 @@ static int dspi_setup_transfer(struct spi_device *spi, struct spi_transfer *t) return 0; } -static int dspi_setup(struct spi_device *spi) -{ - if (!spi->max_speed_hz) - return -EINVAL; - - return dspi_setup_transfer(spi, NULL); -} - static void dspi_cleanup(struct spi_device *spi) { struct chip_data *chip = spi_get_ctldata((struct spi_device *)spi); @@ -395,22 +396,20 @@ static irqreturn_t dspi_interrupt(int irq, void *dev_id) { struct fsl_dspi *dspi = (struct fsl_dspi *)dev_id; - regmap_write(dspi->regmap, SPI_SR, SPI_SR_EOQF); + struct spi_message *msg = dspi->cur_msg; + regmap_write(dspi->regmap, SPI_SR, SPI_SR_EOQF); dspi_transfer_read(dspi); if (!dspi->len) { if (dspi->dataflags & TRAN_STATE_WORD_ODD_NUM) regmap_update_bits(dspi->regmap, SPI_CTAR(dspi->cs), - SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(16)); + SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(16)); dspi->waitflags = 1; wake_up_interruptible(&dspi->waitq); - } else { - dspi_transfer_write(dspi); - - return IRQ_HANDLED; - } + } else + msg->actual_length += dspi_transfer_write(dspi); return IRQ_HANDLED; } @@ -469,12 +468,12 @@ static int dspi_probe(struct platform_device *pdev) dspi = spi_master_get_devdata(master); dspi->pdev = pdev; - dspi->bitbang.master = master; - dspi->bitbang.chipselect = dspi_chipselect; - dspi->bitbang.setup_transfer = dspi_setup_transfer; - dspi->bitbang.txrx_bufs = dspi_txrx_transfer; - dspi->bitbang.master->setup = dspi_setup; - dspi->bitbang.master->dev.of_node = pdev->dev.of_node; + dspi->master = master; + + master->transfer = NULL; + master->setup = dspi_setup; + master->transfer_one_message = dspi_transfer_one_message; + master->dev.of_node = pdev->dev.of_node; master->cleanup = dspi_cleanup; master->mode_bits = SPI_CPOL | SPI_CPHA; @@ -535,7 +534,7 @@ static int dspi_probe(struct platform_device *pdev) init_waitqueue_head(&dspi->waitq); platform_set_drvdata(pdev, master); - ret = spi_bitbang_start(&dspi->bitbang); + ret = spi_register_master(master); if (ret != 0) { dev_err(&pdev->dev, "Problem registering DSPI master\n"); goto out_clk_put; @@ -557,9 +556,9 @@ static int dspi_remove(struct platform_device *pdev) struct fsl_dspi *dspi = spi_master_get_devdata(master); /* Disconnect from the SPI framework */ - spi_bitbang_stop(&dspi->bitbang); clk_disable_unprepare(dspi->clk); - spi_master_put(dspi->bitbang.master); + spi_unregister_master(dspi->master); + spi_master_put(dspi->master); return 0; } diff --git a/drivers/spi/spi-fsl-lib.c b/drivers/spi/spi-fsl-lib.c index 446b737e153..cb35d2f0d0e 100644 --- a/drivers/spi/spi-fsl-lib.c +++ b/drivers/spi/spi-fsl-lib.c @@ -21,6 +21,7 @@ #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/module.h> #include <linux/of_platform.h> #include <linux/spi/spi.h> #ifdef CONFIG_FSL_SOC @@ -35,7 +36,8 @@ void mpc8xxx_spi_rx_buf_##type(u32 data, struct mpc8xxx_spi *mpc8xxx_spi) \ type *rx = mpc8xxx_spi->rx; \ *rx++ = (type)(data >> mpc8xxx_spi->rx_shift); \ mpc8xxx_spi->rx = rx; \ -} +} \ +EXPORT_SYMBOL_GPL(mpc8xxx_spi_rx_buf_##type); #define MPC8XXX_SPI_TX_BUF(type) \ u32 mpc8xxx_spi_tx_buf_##type(struct mpc8xxx_spi *mpc8xxx_spi) \ @@ -47,7 +49,8 @@ u32 mpc8xxx_spi_tx_buf_##type(struct mpc8xxx_spi *mpc8xxx_spi) \ data = *tx++ << mpc8xxx_spi->tx_shift; \ mpc8xxx_spi->tx = tx; \ return data; \ -} +} \ +EXPORT_SYMBOL_GPL(mpc8xxx_spi_tx_buf_##type); MPC8XXX_SPI_RX_BUF(u8) MPC8XXX_SPI_RX_BUF(u16) @@ -60,6 +63,7 @@ struct mpc8xxx_spi_probe_info *to_of_pinfo(struct fsl_spi_platform_data *pdata) { return container_of(pdata, struct mpc8xxx_spi_probe_info, pdata); } +EXPORT_SYMBOL_GPL(to_of_pinfo); const char *mpc8xxx_spi_strmode(unsigned int flags) { @@ -75,6 +79,7 @@ const char *mpc8xxx_spi_strmode(unsigned int flags) } return "CPU"; } +EXPORT_SYMBOL_GPL(mpc8xxx_spi_strmode); void mpc8xxx_spi_probe(struct device *dev, struct resource *mem, unsigned int irq) @@ -102,13 +107,12 @@ void mpc8xxx_spi_probe(struct device *dev, struct resource *mem, mpc8xxx_spi->rx_shift = 0; mpc8xxx_spi->tx_shift = 0; - init_completion(&mpc8xxx_spi->done); - master->bus_num = pdata->bus_num; master->num_chipselect = pdata->max_chipselect; init_completion(&mpc8xxx_spi->done); } +EXPORT_SYMBOL_GPL(mpc8xxx_spi_probe); int mpc8xxx_spi_remove(struct device *dev) { @@ -127,6 +131,7 @@ int mpc8xxx_spi_remove(struct device *dev) return 0; } +EXPORT_SYMBOL_GPL(mpc8xxx_spi_remove); int of_mpc8xxx_spi_probe(struct platform_device *ofdev) { @@ -173,3 +178,6 @@ int of_mpc8xxx_spi_probe(struct platform_device *ofdev) return 0; } +EXPORT_SYMBOL_GPL(of_mpc8xxx_spi_probe); + +MODULE_LICENSE("GPL"); diff --git a/drivers/spi/spi-fsl-lib.h b/drivers/spi/spi-fsl-lib.h index b4ed04e8862..1326a392adc 100644 --- a/drivers/spi/spi-fsl-lib.h +++ b/drivers/spi/spi-fsl-lib.h @@ -28,7 +28,7 @@ struct mpc8xxx_spi { /* rx & tx bufs from the spi_transfer */ const void *tx; void *rx; -#ifdef CONFIG_SPI_FSL_ESPI +#if IS_ENABLED(CONFIG_SPI_FSL_ESPI) int len; #endif @@ -68,7 +68,7 @@ struct mpc8xxx_spi { unsigned int flags; -#ifdef CONFIG_SPI_FSL_SPI +#if IS_ENABLED(CONFIG_SPI_FSL_SPI) int type; int native_chipselects; u8 max_bits_per_word; diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c index aee4e758956..1c34c9314c8 100644 --- a/drivers/spi/spi-gpio.c +++ b/drivers/spi/spi-gpio.c @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/kernel.h> #include <linux/module.h> @@ -92,7 +88,7 @@ struct spi_gpio { /*----------------------------------------------------------------------*/ -static inline struct spi_gpio * __pure +static inline struct spi_gpio *__pure spi_to_spi_gpio(const struct spi_device *spi) { const struct spi_bitbang *bang; @@ -103,7 +99,7 @@ spi_to_spi_gpio(const struct spi_device *spi) return spi_gpio; } -static inline struct spi_gpio_platform_data * __pure +static inline struct spi_gpio_platform_data *__pure spi_to_pdata(const struct spi_device *spi) { return &spi_to_spi_gpio(spi)->pdata; diff --git a/drivers/spi/spi-img-spfi.c b/drivers/spi/spi-img-spfi.c index aad6683db81..c01567d5358 100644 --- a/drivers/spi/spi-img-spfi.c +++ b/drivers/spi/spi-img-spfi.c @@ -160,16 +160,16 @@ static unsigned int spfi_pio_write32(struct img_spfi *spfi, const u32 *buf, unsigned int count = 0; u32 status; - while (count < max) { + while (count < max / 4) { spfi_writel(spfi, SPFI_INTERRUPT_SDFUL, SPFI_INTERRUPT_CLEAR); status = spfi_readl(spfi, SPFI_INTERRUPT_STATUS); if (status & SPFI_INTERRUPT_SDFUL) break; - spfi_writel(spfi, buf[count / 4], SPFI_TX_32BIT_VALID_DATA); - count += 4; + spfi_writel(spfi, buf[count], SPFI_TX_32BIT_VALID_DATA); + count++; } - return count; + return count * 4; } static unsigned int spfi_pio_write8(struct img_spfi *spfi, const u8 *buf, @@ -196,17 +196,17 @@ static unsigned int spfi_pio_read32(struct img_spfi *spfi, u32 *buf, unsigned int count = 0; u32 status; - while (count < max) { + while (count < max / 4) { spfi_writel(spfi, SPFI_INTERRUPT_GDEX32BIT, SPFI_INTERRUPT_CLEAR); status = spfi_readl(spfi, SPFI_INTERRUPT_STATUS); if (!(status & SPFI_INTERRUPT_GDEX32BIT)) break; - buf[count / 4] = spfi_readl(spfi, SPFI_RX_32BIT_VALID_DATA); - count += 4; + buf[count] = spfi_readl(spfi, SPFI_RX_32BIT_VALID_DATA); + count++; } - return count; + return count * 4; } static unsigned int spfi_pio_read8(struct img_spfi *spfi, u8 *buf, @@ -251,17 +251,15 @@ static int img_spfi_start_pio(struct spi_master *master, time_before(jiffies, timeout)) { unsigned int tx_count, rx_count; - switch (xfer->bits_per_word) { - case 32: + if (tx_bytes >= 4) tx_count = spfi_pio_write32(spfi, tx_buf, tx_bytes); - rx_count = spfi_pio_read32(spfi, rx_buf, rx_bytes); - break; - case 8: - default: + else tx_count = spfi_pio_write8(spfi, tx_buf, tx_bytes); + + if (rx_bytes >= 4) + rx_count = spfi_pio_read32(spfi, rx_buf, rx_bytes); + else rx_count = spfi_pio_read8(spfi, rx_buf, rx_bytes); - break; - } tx_buf += tx_count; rx_buf += rx_count; @@ -331,14 +329,11 @@ static int img_spfi_start_dma(struct spi_master *master, if (xfer->rx_buf) { rxconf.direction = DMA_DEV_TO_MEM; - switch (xfer->bits_per_word) { - case 32: + if (xfer->len % 4 == 0) { rxconf.src_addr = spfi->phys + SPFI_RX_32BIT_VALID_DATA; rxconf.src_addr_width = 4; rxconf.src_maxburst = 4; - break; - case 8: - default: + } else { rxconf.src_addr = spfi->phys + SPFI_RX_8BIT_VALID_DATA; rxconf.src_addr_width = 1; rxconf.src_maxburst = 4; @@ -358,18 +353,14 @@ static int img_spfi_start_dma(struct spi_master *master, if (xfer->tx_buf) { txconf.direction = DMA_MEM_TO_DEV; - switch (xfer->bits_per_word) { - case 32: + if (xfer->len % 4 == 0) { txconf.dst_addr = spfi->phys + SPFI_TX_32BIT_VALID_DATA; txconf.dst_addr_width = 4; txconf.dst_maxburst = 4; - break; - case 8: - default: + } else { txconf.dst_addr = spfi->phys + SPFI_TX_8BIT_VALID_DATA; txconf.dst_addr_width = 1; txconf.dst_maxburst = 4; - break; } dmaengine_slave_config(spfi->tx_ch, &txconf); @@ -508,9 +499,7 @@ static void img_spfi_set_cs(struct spi_device *spi, bool enable) static bool img_spfi_can_dma(struct spi_master *master, struct spi_device *spi, struct spi_transfer *xfer) { - if (xfer->bits_per_word == 8 && xfer->len > SPFI_8BIT_FIFO_SIZE) - return true; - if (xfer->bits_per_word == 32 && xfer->len > SPFI_32BIT_FIFO_SIZE) + if (xfer->len > SPFI_32BIT_FIFO_SIZE) return true; return false; } diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index fe1b7699fab..6fea4af51c4 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -89,7 +89,6 @@ struct spi_imx_data { struct completion xfer_done; void __iomem *base; - int irq; struct clk *clk_per; struct clk *clk_ipg; unsigned long spi_clk; @@ -896,6 +895,7 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, { struct dma_async_tx_descriptor *desc_tx = NULL, *desc_rx = NULL; int ret; + unsigned long timeout; u32 dma; int left; struct spi_master *master = spi_imx->bitbang.master; @@ -943,17 +943,17 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, dma_async_issue_pending(master->dma_tx); dma_async_issue_pending(master->dma_rx); /* Wait SDMA to finish the data transfer.*/ - ret = wait_for_completion_timeout(&spi_imx->dma_tx_completion, + timeout = wait_for_completion_timeout(&spi_imx->dma_tx_completion, IMX_DMA_TIMEOUT); - if (!ret) { + if (!timeout) { pr_warn("%s %s: I/O Error in DMA TX\n", dev_driver_string(&master->dev), dev_name(&master->dev)); dmaengine_terminate_all(master->dma_tx); } else { - ret = wait_for_completion_timeout(&spi_imx->dma_rx_completion, - IMX_DMA_TIMEOUT); - if (!ret) { + timeout = wait_for_completion_timeout( + &spi_imx->dma_rx_completion, IMX_DMA_TIMEOUT); + if (!timeout) { pr_warn("%s %s: I/O Error in DMA RX\n", dev_driver_string(&master->dev), dev_name(&master->dev)); @@ -968,9 +968,9 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, spi_imx->dma_finished = 1; spi_imx->devtype_data->trigger(spi_imx); - if (!ret) + if (!timeout) ret = -ETIMEDOUT; - else if (ret > 0) + else ret = transfer->len; return ret; @@ -1080,7 +1080,7 @@ static int spi_imx_probe(struct platform_device *pdev) struct spi_master *master; struct spi_imx_data *spi_imx; struct resource *res; - int i, ret, num_cs; + int i, ret, num_cs, irq; if (!np && !mxc_platform_info) { dev_err(&pdev->dev, "can't get the platform data\n"); @@ -1147,16 +1147,16 @@ static int spi_imx_probe(struct platform_device *pdev) goto out_master_put; } - spi_imx->irq = platform_get_irq(pdev, 0); - if (spi_imx->irq < 0) { - ret = spi_imx->irq; + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + ret = irq; goto out_master_put; } - ret = devm_request_irq(&pdev->dev, spi_imx->irq, spi_imx_isr, 0, + ret = devm_request_irq(&pdev->dev, irq, spi_imx_isr, 0, dev_name(&pdev->dev), spi_imx); if (ret) { - dev_err(&pdev->dev, "can't get irq%d: %d\n", spi_imx->irq, ret); + dev_err(&pdev->dev, "can't get irq%d: %d\n", irq, ret); goto out_master_put; } diff --git a/drivers/spi/spi-lm70llp.c b/drivers/spi/spi-lm70llp.c index 41c5765be74..ba72347cb99 100644 --- a/drivers/spi/spi-lm70llp.c +++ b/drivers/spi/spi-lm70llp.c @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/init.h> diff --git a/drivers/spi/spi-meson-spifc.c b/drivers/spi/spi-meson-spifc.c index 1bbac0378bf..5468fc70dbf 100644 --- a/drivers/spi/spi-meson-spifc.c +++ b/drivers/spi/spi-meson-spifc.c @@ -85,7 +85,7 @@ struct meson_spifc { struct device *dev; }; -static struct regmap_config spifc_regmap_config = { +static const struct regmap_config spifc_regmap_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, diff --git a/drivers/spi/spi-mxs.c b/drivers/spi/spi-mxs.c index 4045a1e580e..5b0e9a3e83f 100644 --- a/drivers/spi/spi-mxs.c +++ b/drivers/spi/spi-mxs.c @@ -282,9 +282,8 @@ static int mxs_spi_txrx_dma(struct mxs_spi *spi, dmaengine_submit(desc); dma_async_issue_pending(ssp->dmach); - ret = wait_for_completion_timeout(&spi->c, - msecs_to_jiffies(SSP_TIMEOUT)); - if (!ret) { + if (!wait_for_completion_timeout(&spi->c, + msecs_to_jiffies(SSP_TIMEOUT))) { dev_err(ssp->dev, "DMA transfer timeout\n"); ret = -ETIMEDOUT; dmaengine_terminate_all(ssp->dmach); diff --git a/drivers/spi/spi-omap-100k.c b/drivers/spi/spi-omap-100k.c index 79399ae9c84..d890d309dff 100644 --- a/drivers/spi/spi-omap-100k.c +++ b/drivers/spi/spi-omap-100k.c @@ -16,11 +16,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * */ #include <linux/kernel.h> #include <linux/init.h> diff --git a/drivers/spi/spi-omap-uwire.c b/drivers/spi/spi-omap-uwire.c index daf1ada5cd1..3c0844457c0 100644 --- a/drivers/spi/spi-omap-uwire.c +++ b/drivers/spi/spi-omap-uwire.c @@ -28,10 +28,6 @@ * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/kernel.h> #include <linux/init.h> diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index 3bc3cbabbbc..4df8942058d 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -14,11 +14,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * */ #include <linux/kernel.h> diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c index 3dec9e0b99b..86166477667 100644 --- a/drivers/spi/spi-orion.c +++ b/drivers/spi/spi-orion.c @@ -28,7 +28,12 @@ /* Runtime PM autosuspend timeout: PM is fairly light on this driver */ #define SPI_AUTOSUSPEND_TIMEOUT 200 -#define ORION_NUM_CHIPSELECTS 1 /* only one slave is supported*/ +/* Some SoCs using this driver support up to 8 chip selects. + * It is up to the implementer to only use the chip selects + * that are available. + */ +#define ORION_NUM_CHIPSELECTS 8 + #define ORION_SPI_WAIT_RDY_MAX_LOOP 2000 /* in usec */ #define ORION_SPI_IF_CTRL_REG 0x00 @@ -44,6 +49,10 @@ #define ARMADA_SPI_CLK_PRESCALE_MASK 0xDF #define ORION_SPI_MODE_MASK (ORION_SPI_MODE_CPOL | \ ORION_SPI_MODE_CPHA) +#define ORION_SPI_CS_MASK 0x1C +#define ORION_SPI_CS_SHIFT 2 +#define ORION_SPI_CS(cs) ((cs << ORION_SPI_CS_SHIFT) & \ + ORION_SPI_CS_MASK) enum orion_spi_type { ORION_SPI, @@ -215,9 +224,18 @@ orion_spi_setup_transfer(struct spi_device *spi, struct spi_transfer *t) return 0; } -static void orion_spi_set_cs(struct orion_spi *orion_spi, int enable) +static void orion_spi_set_cs(struct spi_device *spi, bool enable) { - if (enable) + struct orion_spi *orion_spi; + + orion_spi = spi_master_get_devdata(spi->master); + + orion_spi_clrbits(orion_spi, ORION_SPI_IF_CTRL_REG, ORION_SPI_CS_MASK); + orion_spi_setbits(orion_spi, ORION_SPI_IF_CTRL_REG, + ORION_SPI_CS(spi->chip_select)); + + /* Chip select logic is inverted from spi_set_cs */ + if (!enable) orion_spi_setbits(orion_spi, ORION_SPI_IF_CTRL_REG, 0x1); else orion_spi_clrbits(orion_spi, ORION_SPI_IF_CTRL_REG, 0x1); @@ -332,64 +350,31 @@ out: return xfer->len - count; } -static int orion_spi_transfer_one_message(struct spi_master *master, - struct spi_message *m) +static int orion_spi_transfer_one(struct spi_master *master, + struct spi_device *spi, + struct spi_transfer *t) { - struct orion_spi *orion_spi = spi_master_get_devdata(master); - struct spi_device *spi = m->spi; - struct spi_transfer *t = NULL; - int par_override = 0; int status = 0; - int cs_active = 0; - - /* Load defaults */ - status = orion_spi_setup_transfer(spi, NULL); + status = orion_spi_setup_transfer(spi, t); if (status < 0) - goto msg_done; - - list_for_each_entry(t, &m->transfers, transfer_list) { - if (par_override || t->speed_hz || t->bits_per_word) { - par_override = 1; - status = orion_spi_setup_transfer(spi, t); - if (status < 0) - break; - if (!t->speed_hz && !t->bits_per_word) - par_override = 0; - } - - if (!cs_active) { - orion_spi_set_cs(orion_spi, 1); - cs_active = 1; - } + return status; - if (t->len) - m->actual_length += orion_spi_write_read(spi, t); + if (t->len) + orion_spi_write_read(spi, t); - if (t->delay_usecs) - udelay(t->delay_usecs); - - if (t->cs_change) { - orion_spi_set_cs(orion_spi, 0); - cs_active = 0; - } - } - -msg_done: - if (cs_active) - orion_spi_set_cs(orion_spi, 0); - - m->status = status; - spi_finalize_current_message(master); + return status; +} - return 0; +static int orion_spi_setup(struct spi_device *spi) +{ + return orion_spi_setup_transfer(spi, NULL); } static int orion_spi_reset(struct orion_spi *orion_spi) { /* Verify that the CS is deasserted */ - orion_spi_set_cs(orion_spi, 0); - + orion_spi_clrbits(orion_spi, ORION_SPI_IF_CTRL_REG, 0x1); return 0; } @@ -442,9 +427,10 @@ static int orion_spi_probe(struct platform_device *pdev) /* we support only mode 0, and no options */ master->mode_bits = SPI_CPHA | SPI_CPOL; - - master->transfer_one_message = orion_spi_transfer_one_message; + master->set_cs = orion_spi_set_cs; + master->transfer_one = orion_spi_transfer_one; master->num_chipselect = ORION_NUM_CHIPSELECTS; + master->setup = orion_spi_setup; master->bits_per_word_mask = SPI_BPW_MASK(8) | SPI_BPW_MASK(16); master->auto_runtime_pm = true; diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c index 62a9297e96a..66a173939be 100644 --- a/drivers/spi/spi-pxa2xx-dma.c +++ b/drivers/spi/spi-pxa2xx-dma.c @@ -111,23 +111,24 @@ static void pxa2xx_spi_dma_transfer_complete(struct driver_data *drv_data, * by using ->dma_running. */ if (atomic_dec_and_test(&drv_data->dma_running)) { - void __iomem *reg = drv_data->ioaddr; - /* * If the other CPU is still handling the ROR interrupt we * might not know about the error yet. So we re-check the * ROR bit here before we clear the status register. */ if (!error) { - u32 status = read_SSSR(reg) & drv_data->mask_sr; + u32 status = pxa2xx_spi_read(drv_data, SSSR) + & drv_data->mask_sr; error = status & SSSR_ROR; } /* Clear status & disable interrupts */ - write_SSCR1(read_SSCR1(reg) & ~drv_data->dma_cr1, reg); + pxa2xx_spi_write(drv_data, SSCR1, + pxa2xx_spi_read(drv_data, SSCR1) + & ~drv_data->dma_cr1); write_SSSR_CS(drv_data, drv_data->clear_sr); if (!pxa25x_ssp_comp(drv_data)) - write_SSTO(0, reg); + pxa2xx_spi_write(drv_data, SSTO, 0); if (!error) { pxa2xx_spi_unmap_dma_buffers(drv_data); @@ -139,7 +140,9 @@ static void pxa2xx_spi_dma_transfer_complete(struct driver_data *drv_data, msg->state = pxa2xx_spi_next_transfer(drv_data); } else { /* In case we got an error we disable the SSP now */ - write_SSCR0(read_SSCR0(reg) & ~SSCR0_SSE, reg); + pxa2xx_spi_write(drv_data, SSCR0, + pxa2xx_spi_read(drv_data, SSCR0) + & ~SSCR0_SSE); msg->state = ERROR_STATE; } @@ -247,7 +250,7 @@ irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data) { u32 status; - status = read_SSSR(drv_data->ioaddr) & drv_data->mask_sr; + status = pxa2xx_spi_read(drv_data, SSSR) & drv_data->mask_sr; if (status & SSSR_ROR) { dev_err(&drv_data->pdev->dev, "FIFO overrun\n"); diff --git a/drivers/spi/spi-pxa2xx-pxadma.c b/drivers/spi/spi-pxa2xx-pxadma.c index e8a26f25d5c..2e0796a0003 100644 --- a/drivers/spi/spi-pxa2xx-pxadma.c +++ b/drivers/spi/spi-pxa2xx-pxadma.c @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/delay.h> @@ -25,6 +21,7 @@ #include <linux/spi/spi.h> #include <linux/spi/pxa2xx_spi.h> +#include <mach/dma.h> #include "spi-pxa2xx.h" #define DMA_INT_MASK (DCSR_ENDINTR | DCSR_STARTINTR | DCSR_BUSERR) @@ -118,11 +115,11 @@ static void pxa2xx_spi_unmap_dma_buffers(struct driver_data *drv_data) drv_data->dma_mapped = 0; } -static int wait_ssp_rx_stall(void const __iomem *ioaddr) +static int wait_ssp_rx_stall(struct driver_data *drv_data) { unsigned long limit = loops_per_jiffy << 1; - while ((read_SSSR(ioaddr) & SSSR_BSY) && --limit) + while ((pxa2xx_spi_read(drv_data, SSSR) & SSSR_BSY) && --limit) cpu_relax(); return limit; @@ -141,17 +138,18 @@ static int wait_dma_channel_stop(int channel) static void pxa2xx_spi_dma_error_stop(struct driver_data *drv_data, const char *msg) { - void __iomem *reg = drv_data->ioaddr; - /* Stop and reset */ DCSR(drv_data->rx_channel) = RESET_DMA_CHANNEL; DCSR(drv_data->tx_channel) = RESET_DMA_CHANNEL; write_SSSR_CS(drv_data, drv_data->clear_sr); - write_SSCR1(read_SSCR1(reg) & ~drv_data->dma_cr1, reg); + pxa2xx_spi_write(drv_data, SSCR1, + pxa2xx_spi_read(drv_data, SSCR1) + & ~drv_data->dma_cr1); if (!pxa25x_ssp_comp(drv_data)) - write_SSTO(0, reg); + pxa2xx_spi_write(drv_data, SSTO, 0); pxa2xx_spi_flush(drv_data); - write_SSCR0(read_SSCR0(reg) & ~SSCR0_SSE, reg); + pxa2xx_spi_write(drv_data, SSCR0, + pxa2xx_spi_read(drv_data, SSCR0) & ~SSCR0_SSE); pxa2xx_spi_unmap_dma_buffers(drv_data); @@ -163,11 +161,12 @@ static void pxa2xx_spi_dma_error_stop(struct driver_data *drv_data, static void pxa2xx_spi_dma_transfer_complete(struct driver_data *drv_data) { - void __iomem *reg = drv_data->ioaddr; struct spi_message *msg = drv_data->cur_msg; /* Clear and disable interrupts on SSP and DMA channels*/ - write_SSCR1(read_SSCR1(reg) & ~drv_data->dma_cr1, reg); + pxa2xx_spi_write(drv_data, SSCR1, + pxa2xx_spi_read(drv_data, SSCR1) + & ~drv_data->dma_cr1); write_SSSR_CS(drv_data, drv_data->clear_sr); DCSR(drv_data->tx_channel) = RESET_DMA_CHANNEL; DCSR(drv_data->rx_channel) = RESET_DMA_CHANNEL; @@ -228,7 +227,7 @@ void pxa2xx_spi_dma_handler(int channel, void *data) && (drv_data->ssp_type == PXA25x_SSP)) { /* Wait for rx to stall */ - if (wait_ssp_rx_stall(drv_data->ioaddr) == 0) + if (wait_ssp_rx_stall(drv_data) == 0) dev_err(&drv_data->pdev->dev, "dma_handler: ssp rx stall failed\n"); @@ -240,9 +239,8 @@ void pxa2xx_spi_dma_handler(int channel, void *data) irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data) { u32 irq_status; - void __iomem *reg = drv_data->ioaddr; - irq_status = read_SSSR(reg) & drv_data->mask_sr; + irq_status = pxa2xx_spi_read(drv_data, SSSR) & drv_data->mask_sr; if (irq_status & SSSR_ROR) { pxa2xx_spi_dma_error_stop(drv_data, "dma_transfer: fifo overrun"); @@ -252,7 +250,7 @@ irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data) /* Check for false positive timeout */ if ((irq_status & SSSR_TINT) && (DCSR(drv_data->tx_channel) & DCSR_RUN)) { - write_SSSR(SSSR_TINT, reg); + pxa2xx_spi_write(drv_data, SSSR, SSSR_TINT); return IRQ_HANDLED; } @@ -261,7 +259,7 @@ irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data) /* Clear and disable timeout interrupt, do the rest in * dma_transfer_complete */ if (!pxa25x_ssp_comp(drv_data)) - write_SSTO(0, reg); + pxa2xx_spi_write(drv_data, SSTO, 0); /* finish this transfer, start the next */ pxa2xx_spi_dma_transfer_complete(drv_data); diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index 23822e7df6c..6f72ad01e04 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -11,10 +11,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/init.h> @@ -45,8 +41,6 @@ MODULE_DESCRIPTION("PXA2xx SSP SPI Controller"); MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:pxa2xx-spi"); -#define MAX_BUSES 3 - #define TIMOUT_DFLT 1000 /* @@ -162,7 +156,6 @@ pxa2xx_spi_get_rx_default_thre(const struct driver_data *drv_data) static bool pxa2xx_spi_txfifo_full(const struct driver_data *drv_data) { - void __iomem *reg = drv_data->ioaddr; u32 mask; switch (drv_data->ssp_type) { @@ -174,7 +167,7 @@ static bool pxa2xx_spi_txfifo_full(const struct driver_data *drv_data) break; } - return (read_SSSR(reg) & mask) == mask; + return (pxa2xx_spi_read(drv_data, SSSR) & mask) == mask; } static void pxa2xx_spi_clear_rx_thre(const struct driver_data *drv_data, @@ -253,9 +246,6 @@ static void lpss_ssp_setup(struct driver_data *drv_data) unsigned offset = 0x400; u32 value, orig; - if (!is_lpss_ssp(drv_data)) - return; - /* * Perform auto-detection of the LPSS SSP private registers. They * can be either at 1k or 2k offset from the base address. @@ -304,9 +294,6 @@ static void lpss_ssp_cs_control(struct driver_data *drv_data, bool enable) { u32 value; - if (!is_lpss_ssp(drv_data)) - return; - value = __lpss_ssp_read_priv(drv_data, SPI_CS_CONTROL); if (enable) value &= ~SPI_CS_CONTROL_CS_HIGH; @@ -320,7 +307,7 @@ static void cs_assert(struct driver_data *drv_data) struct chip_data *chip = drv_data->cur_chip; if (drv_data->ssp_type == CE4100_SSP) { - write_SSSR(drv_data->cur_chip->frm, drv_data->ioaddr); + pxa2xx_spi_write(drv_data, SSSR, drv_data->cur_chip->frm); return; } @@ -334,7 +321,8 @@ static void cs_assert(struct driver_data *drv_data) return; } - lpss_ssp_cs_control(drv_data, true); + if (is_lpss_ssp(drv_data)) + lpss_ssp_cs_control(drv_data, true); } static void cs_deassert(struct driver_data *drv_data) @@ -354,20 +342,18 @@ static void cs_deassert(struct driver_data *drv_data) return; } - lpss_ssp_cs_control(drv_data, false); + if (is_lpss_ssp(drv_data)) + lpss_ssp_cs_control(drv_data, false); } int pxa2xx_spi_flush(struct driver_data *drv_data) { unsigned long limit = loops_per_jiffy << 1; - void __iomem *reg = drv_data->ioaddr; - do { - while (read_SSSR(reg) & SSSR_RNE) { - read_SSDR(reg); - } - } while ((read_SSSR(reg) & SSSR_BSY) && --limit); + while (pxa2xx_spi_read(drv_data, SSSR) & SSSR_RNE) + pxa2xx_spi_read(drv_data, SSDR); + } while ((pxa2xx_spi_read(drv_data, SSSR) & SSSR_BSY) && --limit); write_SSSR_CS(drv_data, SSSR_ROR); return limit; @@ -375,14 +361,13 @@ int pxa2xx_spi_flush(struct driver_data *drv_data) static int null_writer(struct driver_data *drv_data) { - void __iomem *reg = drv_data->ioaddr; u8 n_bytes = drv_data->n_bytes; if (pxa2xx_spi_txfifo_full(drv_data) || (drv_data->tx == drv_data->tx_end)) return 0; - write_SSDR(0, reg); + pxa2xx_spi_write(drv_data, SSDR, 0); drv_data->tx += n_bytes; return 1; @@ -390,12 +375,11 @@ static int null_writer(struct driver_data *drv_data) static int null_reader(struct driver_data *drv_data) { - void __iomem *reg = drv_data->ioaddr; u8 n_bytes = drv_data->n_bytes; - while ((read_SSSR(reg) & SSSR_RNE) - && (drv_data->rx < drv_data->rx_end)) { - read_SSDR(reg); + while ((pxa2xx_spi_read(drv_data, SSSR) & SSSR_RNE) + && (drv_data->rx < drv_data->rx_end)) { + pxa2xx_spi_read(drv_data, SSDR); drv_data->rx += n_bytes; } @@ -404,13 +388,11 @@ static int null_reader(struct driver_data *drv_data) static int u8_writer(struct driver_data *drv_data) { - void __iomem *reg = drv_data->ioaddr; - if (pxa2xx_spi_txfifo_full(drv_data) || (drv_data->tx == drv_data->tx_end)) return 0; - write_SSDR(*(u8 *)(drv_data->tx), reg); + pxa2xx_spi_write(drv_data, SSDR, *(u8 *)(drv_data->tx)); ++drv_data->tx; return 1; @@ -418,11 +400,9 @@ static int u8_writer(struct driver_data *drv_data) static int u8_reader(struct driver_data *drv_data) { - void __iomem *reg = drv_data->ioaddr; - - while ((read_SSSR(reg) & SSSR_RNE) - && (drv_data->rx < drv_data->rx_end)) { - *(u8 *)(drv_data->rx) = read_SSDR(reg); + while ((pxa2xx_spi_read(drv_data, SSSR) & SSSR_RNE) + && (drv_data->rx < drv_data->rx_end)) { + *(u8 *)(drv_data->rx) = pxa2xx_spi_read(drv_data, SSDR); ++drv_data->rx; } @@ -431,13 +411,11 @@ static int u8_reader(struct driver_data *drv_data) static int u16_writer(struct driver_data *drv_data) { - void __iomem *reg = drv_data->ioaddr; - if (pxa2xx_spi_txfifo_full(drv_data) || (drv_data->tx == drv_data->tx_end)) return 0; - write_SSDR(*(u16 *)(drv_data->tx), reg); + pxa2xx_spi_write(drv_data, SSDR, *(u16 *)(drv_data->tx)); drv_data->tx += 2; return 1; @@ -445,11 +423,9 @@ static int u16_writer(struct driver_data *drv_data) static int u16_reader(struct driver_data *drv_data) { - void __iomem *reg = drv_data->ioaddr; - - while ((read_SSSR(reg) & SSSR_RNE) - && (drv_data->rx < drv_data->rx_end)) { - *(u16 *)(drv_data->rx) = read_SSDR(reg); + while ((pxa2xx_spi_read(drv_data, SSSR) & SSSR_RNE) + && (drv_data->rx < drv_data->rx_end)) { + *(u16 *)(drv_data->rx) = pxa2xx_spi_read(drv_data, SSDR); drv_data->rx += 2; } @@ -458,13 +434,11 @@ static int u16_reader(struct driver_data *drv_data) static int u32_writer(struct driver_data *drv_data) { - void __iomem *reg = drv_data->ioaddr; - if (pxa2xx_spi_txfifo_full(drv_data) || (drv_data->tx == drv_data->tx_end)) return 0; - write_SSDR(*(u32 *)(drv_data->tx), reg); + pxa2xx_spi_write(drv_data, SSDR, *(u32 *)(drv_data->tx)); drv_data->tx += 4; return 1; @@ -472,11 +446,9 @@ static int u32_writer(struct driver_data *drv_data) static int u32_reader(struct driver_data *drv_data) { - void __iomem *reg = drv_data->ioaddr; - - while ((read_SSSR(reg) & SSSR_RNE) - && (drv_data->rx < drv_data->rx_end)) { - *(u32 *)(drv_data->rx) = read_SSDR(reg); + while ((pxa2xx_spi_read(drv_data, SSSR) & SSSR_RNE) + && (drv_data->rx < drv_data->rx_end)) { + *(u32 *)(drv_data->rx) = pxa2xx_spi_read(drv_data, SSDR); drv_data->rx += 4; } @@ -552,27 +524,25 @@ static void giveback(struct driver_data *drv_data) static void reset_sccr1(struct driver_data *drv_data) { - void __iomem *reg = drv_data->ioaddr; struct chip_data *chip = drv_data->cur_chip; u32 sccr1_reg; - sccr1_reg = read_SSCR1(reg) & ~drv_data->int_cr1; + sccr1_reg = pxa2xx_spi_read(drv_data, SSCR1) & ~drv_data->int_cr1; sccr1_reg &= ~SSCR1_RFT; sccr1_reg |= chip->threshold; - write_SSCR1(sccr1_reg, reg); + pxa2xx_spi_write(drv_data, SSCR1, sccr1_reg); } static void int_error_stop(struct driver_data *drv_data, const char* msg) { - void __iomem *reg = drv_data->ioaddr; - /* Stop and reset SSP */ write_SSSR_CS(drv_data, drv_data->clear_sr); reset_sccr1(drv_data); if (!pxa25x_ssp_comp(drv_data)) - write_SSTO(0, reg); + pxa2xx_spi_write(drv_data, SSTO, 0); pxa2xx_spi_flush(drv_data); - write_SSCR0(read_SSCR0(reg) & ~SSCR0_SSE, reg); + pxa2xx_spi_write(drv_data, SSCR0, + pxa2xx_spi_read(drv_data, SSCR0) & ~SSCR0_SSE); dev_err(&drv_data->pdev->dev, "%s\n", msg); @@ -582,13 +552,11 @@ static void int_error_stop(struct driver_data *drv_data, const char* msg) static void int_transfer_complete(struct driver_data *drv_data) { - void __iomem *reg = drv_data->ioaddr; - /* Stop SSP */ write_SSSR_CS(drv_data, drv_data->clear_sr); reset_sccr1(drv_data); if (!pxa25x_ssp_comp(drv_data)) - write_SSTO(0, reg); + pxa2xx_spi_write(drv_data, SSTO, 0); /* Update total byte transferred return count actual bytes read */ drv_data->cur_msg->actual_length += drv_data->len - @@ -607,12 +575,10 @@ static void int_transfer_complete(struct driver_data *drv_data) static irqreturn_t interrupt_transfer(struct driver_data *drv_data) { - void __iomem *reg = drv_data->ioaddr; + u32 irq_mask = (pxa2xx_spi_read(drv_data, SSCR1) & SSCR1_TIE) ? + drv_data->mask_sr : drv_data->mask_sr & ~SSSR_TFS; - u32 irq_mask = (read_SSCR1(reg) & SSCR1_TIE) ? - drv_data->mask_sr : drv_data->mask_sr & ~SSSR_TFS; - - u32 irq_status = read_SSSR(reg) & irq_mask; + u32 irq_status = pxa2xx_spi_read(drv_data, SSSR) & irq_mask; if (irq_status & SSSR_ROR) { int_error_stop(drv_data, "interrupt_transfer: fifo overrun"); @@ -620,7 +586,7 @@ static irqreturn_t interrupt_transfer(struct driver_data *drv_data) } if (irq_status & SSSR_TINT) { - write_SSSR(SSSR_TINT, reg); + pxa2xx_spi_write(drv_data, SSSR, SSSR_TINT); if (drv_data->read(drv_data)) { int_transfer_complete(drv_data); return IRQ_HANDLED; @@ -644,7 +610,7 @@ static irqreturn_t interrupt_transfer(struct driver_data *drv_data) u32 bytes_left; u32 sccr1_reg; - sccr1_reg = read_SSCR1(reg); + sccr1_reg = pxa2xx_spi_read(drv_data, SSCR1); sccr1_reg &= ~SSCR1_TIE; /* @@ -670,7 +636,7 @@ static irqreturn_t interrupt_transfer(struct driver_data *drv_data) pxa2xx_spi_set_rx_thre(drv_data, &sccr1_reg, rx_thre); } - write_SSCR1(sccr1_reg, reg); + pxa2xx_spi_write(drv_data, SSCR1, sccr1_reg); } /* We did something */ @@ -680,7 +646,6 @@ static irqreturn_t interrupt_transfer(struct driver_data *drv_data) static irqreturn_t ssp_int(int irq, void *dev_id) { struct driver_data *drv_data = dev_id; - void __iomem *reg = drv_data->ioaddr; u32 sccr1_reg; u32 mask = drv_data->mask_sr; u32 status; @@ -700,11 +665,11 @@ static irqreturn_t ssp_int(int irq, void *dev_id) * are all set to one. That means that the device is already * powered off. */ - status = read_SSSR(reg); + status = pxa2xx_spi_read(drv_data, SSSR); if (status == ~0) return IRQ_NONE; - sccr1_reg = read_SSCR1(reg); + sccr1_reg = pxa2xx_spi_read(drv_data, SSCR1); /* Ignore possible writes if we don't need to write */ if (!(sccr1_reg & SSCR1_TIE)) @@ -715,10 +680,14 @@ static irqreturn_t ssp_int(int irq, void *dev_id) if (!drv_data->cur_msg) { - write_SSCR0(read_SSCR0(reg) & ~SSCR0_SSE, reg); - write_SSCR1(read_SSCR1(reg) & ~drv_data->int_cr1, reg); + pxa2xx_spi_write(drv_data, SSCR0, + pxa2xx_spi_read(drv_data, SSCR0) + & ~SSCR0_SSE); + pxa2xx_spi_write(drv_data, SSCR1, + pxa2xx_spi_read(drv_data, SSCR1) + & ~drv_data->int_cr1); if (!pxa25x_ssp_comp(drv_data)) - write_SSTO(0, reg); + pxa2xx_spi_write(drv_data, SSTO, 0); write_SSSR_CS(drv_data, drv_data->clear_sr); dev_err(&drv_data->pdev->dev, @@ -787,7 +756,6 @@ static void pump_transfers(unsigned long data) struct spi_transfer *transfer = NULL; struct spi_transfer *previous = NULL; struct chip_data *chip = NULL; - void __iomem *reg = drv_data->ioaddr; u32 clk_div = 0; u8 bits = 0; u32 speed = 0; @@ -931,7 +899,7 @@ static void pump_transfers(unsigned long data) /* Clear status and start DMA engine */ cr1 = chip->cr1 | dma_thresh | drv_data->dma_cr1; - write_SSSR(drv_data->clear_sr, reg); + pxa2xx_spi_write(drv_data, SSSR, drv_data->clear_sr); pxa2xx_spi_dma_start(drv_data); } else { @@ -944,39 +912,43 @@ static void pump_transfers(unsigned long data) } if (is_lpss_ssp(drv_data)) { - if ((read_SSIRF(reg) & 0xff) != chip->lpss_rx_threshold) - write_SSIRF(chip->lpss_rx_threshold, reg); - if ((read_SSITF(reg) & 0xffff) != chip->lpss_tx_threshold) - write_SSITF(chip->lpss_tx_threshold, reg); + if ((pxa2xx_spi_read(drv_data, SSIRF) & 0xff) + != chip->lpss_rx_threshold) + pxa2xx_spi_write(drv_data, SSIRF, + chip->lpss_rx_threshold); + if ((pxa2xx_spi_read(drv_data, SSITF) & 0xffff) + != chip->lpss_tx_threshold) + pxa2xx_spi_write(drv_data, SSITF, + chip->lpss_tx_threshold); } if (is_quark_x1000_ssp(drv_data) && - (read_DDS_RATE(reg) != chip->dds_rate)) - write_DDS_RATE(chip->dds_rate, reg); + (pxa2xx_spi_read(drv_data, DDS_RATE) != chip->dds_rate)) + pxa2xx_spi_write(drv_data, DDS_RATE, chip->dds_rate); /* see if we need to reload the config registers */ - if ((read_SSCR0(reg) != cr0) || - (read_SSCR1(reg) & change_mask) != (cr1 & change_mask)) { - + if ((pxa2xx_spi_read(drv_data, SSCR0) != cr0) + || (pxa2xx_spi_read(drv_data, SSCR1) & change_mask) + != (cr1 & change_mask)) { /* stop the SSP, and update the other bits */ - write_SSCR0(cr0 & ~SSCR0_SSE, reg); + pxa2xx_spi_write(drv_data, SSCR0, cr0 & ~SSCR0_SSE); if (!pxa25x_ssp_comp(drv_data)) - write_SSTO(chip->timeout, reg); + pxa2xx_spi_write(drv_data, SSTO, chip->timeout); /* first set CR1 without interrupt and service enables */ - write_SSCR1(cr1 & change_mask, reg); + pxa2xx_spi_write(drv_data, SSCR1, cr1 & change_mask); /* restart the SSP */ - write_SSCR0(cr0, reg); + pxa2xx_spi_write(drv_data, SSCR0, cr0); } else { if (!pxa25x_ssp_comp(drv_data)) - write_SSTO(chip->timeout, reg); + pxa2xx_spi_write(drv_data, SSTO, chip->timeout); } cs_assert(drv_data); /* after chip select, release the data by enabling service * requests and interrupts, without changing any mode bits */ - write_SSCR1(cr1, reg); + pxa2xx_spi_write(drv_data, SSCR1, cr1); } static int pxa2xx_spi_transfer_one_message(struct spi_master *master, @@ -1005,8 +977,8 @@ static int pxa2xx_spi_unprepare_transfer(struct spi_master *master) struct driver_data *drv_data = spi_master_get_devdata(master); /* Disable the SSP now */ - write_SSCR0(read_SSCR0(drv_data->ioaddr) & ~SSCR0_SSE, - drv_data->ioaddr); + pxa2xx_spi_write(drv_data, SSCR0, + pxa2xx_spi_read(drv_data, SSCR0) & ~SSCR0_SSE); return 0; } @@ -1289,6 +1261,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) struct driver_data *drv_data; struct ssp_device *ssp; int status; + u32 tmp; platform_info = dev_get_platdata(dev); if (!platform_info) { @@ -1386,38 +1359,35 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) drv_data->max_clk_rate = clk_get_rate(ssp->clk); /* Load default SSP configuration */ - write_SSCR0(0, drv_data->ioaddr); + pxa2xx_spi_write(drv_data, SSCR0, 0); switch (drv_data->ssp_type) { case QUARK_X1000_SSP: - write_SSCR1(QUARK_X1000_SSCR1_RxTresh( - RX_THRESH_QUARK_X1000_DFLT) | - QUARK_X1000_SSCR1_TxTresh( - TX_THRESH_QUARK_X1000_DFLT), - drv_data->ioaddr); + tmp = QUARK_X1000_SSCR1_RxTresh(RX_THRESH_QUARK_X1000_DFLT) + | QUARK_X1000_SSCR1_TxTresh(TX_THRESH_QUARK_X1000_DFLT); + pxa2xx_spi_write(drv_data, SSCR1, tmp); /* using the Motorola SPI protocol and use 8 bit frame */ - write_SSCR0(QUARK_X1000_SSCR0_Motorola - | QUARK_X1000_SSCR0_DataSize(8), - drv_data->ioaddr); + pxa2xx_spi_write(drv_data, SSCR0, + QUARK_X1000_SSCR0_Motorola + | QUARK_X1000_SSCR0_DataSize(8)); break; default: - write_SSCR1(SSCR1_RxTresh(RX_THRESH_DFLT) | - SSCR1_TxTresh(TX_THRESH_DFLT), - drv_data->ioaddr); - write_SSCR0(SSCR0_SCR(2) - | SSCR0_Motorola - | SSCR0_DataSize(8), - drv_data->ioaddr); + tmp = SSCR1_RxTresh(RX_THRESH_DFLT) | + SSCR1_TxTresh(TX_THRESH_DFLT); + pxa2xx_spi_write(drv_data, SSCR1, tmp); + tmp = SSCR0_SCR(2) | SSCR0_Motorola | SSCR0_DataSize(8); + pxa2xx_spi_write(drv_data, SSCR0, tmp); break; } if (!pxa25x_ssp_comp(drv_data)) - write_SSTO(0, drv_data->ioaddr); + pxa2xx_spi_write(drv_data, SSTO, 0); if (!is_quark_x1000_ssp(drv_data)) - write_SSPSP(0, drv_data->ioaddr); + pxa2xx_spi_write(drv_data, SSPSP, 0); - lpss_ssp_setup(drv_data); + if (is_lpss_ssp(drv_data)) + lpss_ssp_setup(drv_data); tasklet_init(&drv_data->pump_transfers, pump_transfers, (unsigned long)drv_data); @@ -1460,7 +1430,7 @@ static int pxa2xx_spi_remove(struct platform_device *pdev) pm_runtime_get_sync(&pdev->dev); /* Disable the SSP at the peripheral and SOC level */ - write_SSCR0(0, drv_data->ioaddr); + pxa2xx_spi_write(drv_data, SSCR0, 0); clk_disable_unprepare(ssp->clk); /* Release DMA */ @@ -1497,7 +1467,7 @@ static int pxa2xx_spi_suspend(struct device *dev) status = spi_master_suspend(drv_data->master); if (status != 0) return status; - write_SSCR0(0, drv_data->ioaddr); + pxa2xx_spi_write(drv_data, SSCR0, 0); if (!pm_runtime_suspended(dev)) clk_disable_unprepare(ssp->clk); @@ -1518,7 +1488,8 @@ static int pxa2xx_spi_resume(struct device *dev) clk_prepare_enable(ssp->clk); /* Restore LPSS private register bits */ - lpss_ssp_setup(drv_data); + if (is_lpss_ssp(drv_data)) + lpss_ssp_setup(drv_data); /* Start the queue running */ status = spi_master_resume(drv_data->master); diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h index 6bec59c90cd..85a58c90686 100644 --- a/drivers/spi/spi-pxa2xx.h +++ b/drivers/spi/spi-pxa2xx.h @@ -115,23 +115,17 @@ struct chip_data { void (*cs_control)(u32 command); }; -#define DEFINE_SSP_REG(reg, off) \ -static inline u32 read_##reg(void const __iomem *p) \ -{ return __raw_readl(p + (off)); } \ -\ -static inline void write_##reg(u32 v, void __iomem *p) \ -{ __raw_writel(v, p + (off)); } - -DEFINE_SSP_REG(SSCR0, 0x00) -DEFINE_SSP_REG(SSCR1, 0x04) -DEFINE_SSP_REG(SSSR, 0x08) -DEFINE_SSP_REG(SSITR, 0x0c) -DEFINE_SSP_REG(SSDR, 0x10) -DEFINE_SSP_REG(DDS_RATE, 0x28) /* DDS Clock Rate */ -DEFINE_SSP_REG(SSTO, 0x28) -DEFINE_SSP_REG(SSPSP, 0x2c) -DEFINE_SSP_REG(SSITF, SSITF) -DEFINE_SSP_REG(SSIRF, SSIRF) +static inline u32 pxa2xx_spi_read(const struct driver_data *drv_data, + unsigned reg) +{ + return __raw_readl(drv_data->ioaddr + reg); +} + +static inline void pxa2xx_spi_write(const struct driver_data *drv_data, + unsigned reg, u32 val) +{ + __raw_writel(val, drv_data->ioaddr + reg); +} #define START_STATE ((void *)0) #define RUNNING_STATE ((void *)1) @@ -155,13 +149,11 @@ static inline int pxa25x_ssp_comp(struct driver_data *drv_data) static inline void write_SSSR_CS(struct driver_data *drv_data, u32 val) { - void __iomem *reg = drv_data->ioaddr; - if (drv_data->ssp_type == CE4100_SSP || drv_data->ssp_type == QUARK_X1000_SSP) - val |= read_SSSR(reg) & SSSR_ALT_FRM_MASK; + val |= pxa2xx_spi_read(drv_data, SSSR) & SSSR_ALT_FRM_MASK; - write_SSSR(val, reg); + pxa2xx_spi_write(drv_data, SSSR, val); } extern int pxa2xx_spi_flush(struct driver_data *drv_data); diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c index e7fb5a0d2e8..ff9cdbdb667 100644 --- a/drivers/spi/spi-qup.c +++ b/drivers/spi/spi-qup.c @@ -337,7 +337,7 @@ static irqreturn_t spi_qup_qup_irq(int irq, void *dev_id) static int spi_qup_io_config(struct spi_device *spi, struct spi_transfer *xfer) { struct spi_qup *controller = spi_master_get_devdata(spi->master); - u32 config, iomode, mode; + u32 config, iomode, mode, control; int ret, n_words, w_size; if (spi->mode & SPI_LOOP && xfer->len > controller->in_fifo_sz) { @@ -392,6 +392,15 @@ static int spi_qup_io_config(struct spi_device *spi, struct spi_transfer *xfer) writel_relaxed(iomode, controller->base + QUP_IO_M_MODES); + control = readl_relaxed(controller->base + SPI_IO_CONTROL); + + if (spi->mode & SPI_CPOL) + control |= SPI_IO_C_CLK_IDLE_HIGH; + else + control &= ~SPI_IO_C_CLK_IDLE_HIGH; + + writel_relaxed(control, controller->base + SPI_IO_CONTROL); + config = readl_relaxed(controller->base + SPI_CONFIG); if (spi->mode & SPI_LOOP) diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index daabbabd26b..1a777dc261d 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -437,6 +437,7 @@ static void rockchip_spi_prepare_dma(struct rockchip_spi *rs) rs->state &= ~TXBUSY; spin_unlock_irqrestore(&rs->lock, flags); + rxdesc = NULL; if (rs->rx) { rxconf.direction = rs->dma_rx.direction; rxconf.src_addr = rs->dma_rx.addr; @@ -453,6 +454,7 @@ static void rockchip_spi_prepare_dma(struct rockchip_spi *rs) rxdesc->callback_param = rs; } + txdesc = NULL; if (rs->tx) { txconf.direction = rs->dma_tx.direction; txconf.dst_addr = rs->dma_tx.addr; @@ -470,7 +472,7 @@ static void rockchip_spi_prepare_dma(struct rockchip_spi *rs) } /* rx must be started before tx due to spi instinct */ - if (rs->rx) { + if (rxdesc) { spin_lock_irqsave(&rs->lock, flags); rs->state |= RXBUSY; spin_unlock_irqrestore(&rs->lock, flags); @@ -478,7 +480,7 @@ static void rockchip_spi_prepare_dma(struct rockchip_spi *rs) dma_async_issue_pending(rs->dma_rx.ch); } - if (rs->tx) { + if (txdesc) { spin_lock_irqsave(&rs->lock, flags); rs->state |= TXBUSY; spin_unlock_irqrestore(&rs->lock, flags); diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c index 2071f788c6f..46ce47076e6 100644 --- a/drivers/spi/spi-rspi.c +++ b/drivers/spi/spi-rspi.c @@ -15,11 +15,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * */ #include <linux/module.h> diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c index 37b19836f5c..9231c34b5a5 100644 --- a/drivers/spi/spi-s3c64xx.c +++ b/drivers/spi/spi-s3c64xx.c @@ -11,10 +11,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/init.h> diff --git a/drivers/spi/spi-sc18is602.c b/drivers/spi/spi-sc18is602.c index 237f2e7a717..5a56acf8a43 100644 --- a/drivers/spi/spi-sc18is602.c +++ b/drivers/spi/spi-sc18is602.c @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/kernel.h> diff --git a/drivers/spi/spi-sh-hspi.c b/drivers/spi/spi-sh-hspi.c index fc29233d065..20e800e7044 100644 --- a/drivers/spi/spi-sh-hspi.c +++ b/drivers/spi/spi-sh-hspi.c @@ -16,11 +16,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * */ #include <linux/clk.h> diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c index 3ab7a21445f..e57eec0b2f4 100644 --- a/drivers/spi/spi-sh-msiof.c +++ b/drivers/spi/spi-sh-msiof.c @@ -82,6 +82,8 @@ struct sh_msiof_spi_priv { #define MDR1_SYNCMD_LR 0x30000000 /* L/R mode */ #define MDR1_SYNCAC_SHIFT 25 /* Sync Polarity (1 = Active-low) */ #define MDR1_BITLSB_SHIFT 24 /* MSB/LSB First (1 = LSB first) */ +#define MDR1_DTDL_SHIFT 20 /* Data Pin Bit Delay for MSIOF_SYNC */ +#define MDR1_SYNCDL_SHIFT 16 /* Frame Sync Signal Timing Delay */ #define MDR1_FLD_MASK 0x0000000c /* Frame Sync Signal Interval (0-3) */ #define MDR1_FLD_SHIFT 2 #define MDR1_XXSTP 0x00000001 /* Transmission/Reception Stop on FIFO */ @@ -241,42 +243,80 @@ static irqreturn_t sh_msiof_spi_irq(int irq, void *data) static struct { unsigned short div; - unsigned short scr; -} const sh_msiof_spi_clk_table[] = { - { 1, SCR_BRPS( 1) | SCR_BRDV_DIV_1 }, - { 2, SCR_BRPS( 1) | SCR_BRDV_DIV_2 }, - { 4, SCR_BRPS( 1) | SCR_BRDV_DIV_4 }, - { 8, SCR_BRPS( 1) | SCR_BRDV_DIV_8 }, - { 16, SCR_BRPS( 1) | SCR_BRDV_DIV_16 }, - { 32, SCR_BRPS( 1) | SCR_BRDV_DIV_32 }, - { 64, SCR_BRPS(32) | SCR_BRDV_DIV_2 }, - { 128, SCR_BRPS(32) | SCR_BRDV_DIV_4 }, - { 256, SCR_BRPS(32) | SCR_BRDV_DIV_8 }, - { 512, SCR_BRPS(32) | SCR_BRDV_DIV_16 }, - { 1024, SCR_BRPS(32) | SCR_BRDV_DIV_32 }, + unsigned short brdv; +} const sh_msiof_spi_div_table[] = { + { 1, SCR_BRDV_DIV_1 }, + { 2, SCR_BRDV_DIV_2 }, + { 4, SCR_BRDV_DIV_4 }, + { 8, SCR_BRDV_DIV_8 }, + { 16, SCR_BRDV_DIV_16 }, + { 32, SCR_BRDV_DIV_32 }, }; static void sh_msiof_spi_set_clk_regs(struct sh_msiof_spi_priv *p, unsigned long parent_rate, u32 spi_hz) { unsigned long div = 1024; + u32 brps, scr; size_t k; if (!WARN_ON(!spi_hz || !parent_rate)) div = DIV_ROUND_UP(parent_rate, spi_hz); - /* TODO: make more fine grained */ - - for (k = 0; k < ARRAY_SIZE(sh_msiof_spi_clk_table); k++) { - if (sh_msiof_spi_clk_table[k].div >= div) + for (k = 0; k < ARRAY_SIZE(sh_msiof_spi_div_table); k++) { + brps = DIV_ROUND_UP(div, sh_msiof_spi_div_table[k].div); + if (brps <= 32) /* max of brdv is 32 */ break; } - k = min_t(int, k, ARRAY_SIZE(sh_msiof_spi_clk_table) - 1); + k = min_t(int, k, ARRAY_SIZE(sh_msiof_spi_div_table) - 1); - sh_msiof_write(p, TSCR, sh_msiof_spi_clk_table[k].scr); + scr = sh_msiof_spi_div_table[k].brdv | SCR_BRPS(brps); + sh_msiof_write(p, TSCR, scr); if (!(p->chipdata->master_flags & SPI_MASTER_MUST_TX)) - sh_msiof_write(p, RSCR, sh_msiof_spi_clk_table[k].scr); + sh_msiof_write(p, RSCR, scr); +} + +static u32 sh_msiof_get_delay_bit(u32 dtdl_or_syncdl) +{ + /* + * DTDL/SYNCDL bit : p->info->dtdl or p->info->syncdl + * b'000 : 0 + * b'001 : 100 + * b'010 : 200 + * b'011 (SYNCDL only) : 300 + * b'101 : 50 + * b'110 : 150 + */ + if (dtdl_or_syncdl % 100) + return dtdl_or_syncdl / 100 + 5; + else + return dtdl_or_syncdl / 100; +} + +static u32 sh_msiof_spi_get_dtdl_and_syncdl(struct sh_msiof_spi_priv *p) +{ + u32 val; + + if (!p->info) + return 0; + + /* check if DTDL and SYNCDL is allowed value */ + if (p->info->dtdl > 200 || p->info->syncdl > 300) { + dev_warn(&p->pdev->dev, "DTDL or SYNCDL is too large\n"); + return 0; + } + + /* check if the sum of DTDL and SYNCDL becomes an integer value */ + if ((p->info->dtdl + p->info->syncdl) % 100) { + dev_warn(&p->pdev->dev, "the sum of DTDL/SYNCDL is not good\n"); + return 0; + } + + val = sh_msiof_get_delay_bit(p->info->dtdl) << MDR1_DTDL_SHIFT; + val |= sh_msiof_get_delay_bit(p->info->syncdl) << MDR1_SYNCDL_SHIFT; + + return val; } static void sh_msiof_spi_set_pin_regs(struct sh_msiof_spi_priv *p, @@ -296,6 +336,7 @@ static void sh_msiof_spi_set_pin_regs(struct sh_msiof_spi_priv *p, tmp = MDR1_SYNCMD_SPI | 1 << MDR1_FLD_SHIFT | MDR1_XXSTP; tmp |= !cs_high << MDR1_SYNCAC_SHIFT; tmp |= lsb_first << MDR1_BITLSB_SHIFT; + tmp |= sh_msiof_spi_get_dtdl_and_syncdl(p); sh_msiof_write(p, TMDR1, tmp | MDR1_TRMD | TMDR1_PCON); if (p->chipdata->master_flags & SPI_MASTER_MUST_TX) { /* These bits are reserved if RX needs TX */ @@ -501,7 +542,7 @@ static int sh_msiof_spi_setup(struct spi_device *spi) gpio_set_value(spi->cs_gpio, !(spi->mode & SPI_CS_HIGH)); - pm_runtime_put_sync(&p->pdev->dev); + pm_runtime_put(&p->pdev->dev); return 0; } @@ -595,8 +636,7 @@ static int sh_msiof_spi_txrx_once(struct sh_msiof_spi_priv *p, } /* wait for tx fifo to be emptied / rx fifo to be filled */ - ret = wait_for_completion_timeout(&p->done, HZ); - if (!ret) { + if (!wait_for_completion_timeout(&p->done, HZ)) { dev_err(&p->pdev->dev, "PIO timeout\n"); ret = -ETIMEDOUT; goto stop_reset; @@ -706,8 +746,7 @@ static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx, } /* wait for tx fifo to be emptied / rx fifo to be filled */ - ret = wait_for_completion_timeout(&p->done, HZ); - if (!ret) { + if (!wait_for_completion_timeout(&p->done, HZ)) { dev_err(&p->pdev->dev, "DMA timeout\n"); ret = -ETIMEDOUT; goto stop_reset; @@ -957,6 +996,8 @@ static struct sh_msiof_spi_info *sh_msiof_spi_parse_dt(struct device *dev) &info->tx_fifo_override); of_property_read_u32(np, "renesas,rx-fifo-size", &info->rx_fifo_override); + of_property_read_u32(np, "renesas,dtdl", &info->dtdl); + of_property_read_u32(np, "renesas,syncdl", &info->syncdl); info->num_chipselect = num_cs; diff --git a/drivers/spi/spi-sh.c b/drivers/spi/spi-sh.c index 1cfc906dd17..502501187c9 100644 --- a/drivers/spi/spi-sh.c +++ b/drivers/spi/spi-sh.c @@ -14,11 +14,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * */ #include <linux/module.h> diff --git a/drivers/spi/spi-sirf.c b/drivers/spi/spi-sirf.c index d075191476f..f5715c9f68b 100644 --- a/drivers/spi/spi-sirf.c +++ b/drivers/spi/spi-sirf.c @@ -818,7 +818,6 @@ static SIMPLE_DEV_PM_OPS(spi_sirfsoc_pm_ops, spi_sirfsoc_suspend, static const struct of_device_id spi_sirfsoc_of_match[] = { { .compatible = "sirf,prima2-spi", }, - { .compatible = "sirf,marco-spi", }, {} }; MODULE_DEVICE_TABLE(of, spi_sirfsoc_of_match); diff --git a/drivers/spi/spi-st-ssc4.c b/drivers/spi/spi-st-ssc4.c new file mode 100644 index 00000000000..2faeaa7b57a --- /dev/null +++ b/drivers/spi/spi-st-ssc4.c @@ -0,0 +1,504 @@ +/* + * Copyright (c) 2008-2014 STMicroelectronics Limited + * + * Author: Angus Clark <Angus.Clark@st.com> + * Patrice Chotard <patrice.chotard@st.com> + * Lee Jones <lee.jones@linaro.org> + * + * SPI master mode controller driver, used in STMicroelectronics devices. + * + * May be copied or modified under the terms of the GNU General Public + * License Version 2.0 only. See linux/COPYING for more information. + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/pinctrl/consumer.h> +#include <linux/platform_device.h> +#include <linux/of.h> +#include <linux/of_gpio.h> +#include <linux/of_irq.h> +#include <linux/pm_runtime.h> +#include <linux/spi/spi.h> +#include <linux/spi/spi_bitbang.h> + +/* SSC registers */ +#define SSC_BRG 0x000 +#define SSC_TBUF 0x004 +#define SSC_RBUF 0x008 +#define SSC_CTL 0x00C +#define SSC_IEN 0x010 +#define SSC_I2C 0x018 + +/* SSC Control */ +#define SSC_CTL_DATA_WIDTH_9 0x8 +#define SSC_CTL_DATA_WIDTH_MSK 0xf +#define SSC_CTL_BM 0xf +#define SSC_CTL_HB BIT(4) +#define SSC_CTL_PH BIT(5) +#define SSC_CTL_PO BIT(6) +#define SSC_CTL_SR BIT(7) +#define SSC_CTL_MS BIT(8) +#define SSC_CTL_EN BIT(9) +#define SSC_CTL_LPB BIT(10) +#define SSC_CTL_EN_TX_FIFO BIT(11) +#define SSC_CTL_EN_RX_FIFO BIT(12) +#define SSC_CTL_EN_CLST_RX BIT(13) + +/* SSC Interrupt Enable */ +#define SSC_IEN_TEEN BIT(2) + +#define FIFO_SIZE 8 + +struct spi_st { + /* SSC SPI Controller */ + void __iomem *base; + struct clk *clk; + struct device *dev; + + /* SSC SPI current transaction */ + const u8 *tx_ptr; + u8 *rx_ptr; + u16 bytes_per_word; + unsigned int words_remaining; + unsigned int baud; + struct completion done; +}; + +static int spi_st_clk_enable(struct spi_st *spi_st) +{ + /* + * Current platforms use one of the core clocks for SPI and I2C. + * If we attempt to disable the clock, the system will hang. + * + * TODO: Remove this when platform supports power domains. + */ + return 0; + + return clk_prepare_enable(spi_st->clk); +} + +static void spi_st_clk_disable(struct spi_st *spi_st) +{ + /* + * Current platforms use one of the core clocks for SPI and I2C. + * If we attempt to disable the clock, the system will hang. + * + * TODO: Remove this when platform supports power domains. + */ + return; + + clk_disable_unprepare(spi_st->clk); +} + +/* Load the TX FIFO */ +static void ssc_write_tx_fifo(struct spi_st *spi_st) +{ + unsigned int count, i; + uint32_t word = 0; + + if (spi_st->words_remaining > FIFO_SIZE) + count = FIFO_SIZE; + else + count = spi_st->words_remaining; + + for (i = 0; i < count; i++) { + if (spi_st->tx_ptr) { + if (spi_st->bytes_per_word == 1) { + word = *spi_st->tx_ptr++; + } else { + word = *spi_st->tx_ptr++; + word = *spi_st->tx_ptr++ | (word << 8); + } + } + writel_relaxed(word, spi_st->base + SSC_TBUF); + } +} + +/* Read the RX FIFO */ +static void ssc_read_rx_fifo(struct spi_st *spi_st) +{ + unsigned int count, i; + uint32_t word = 0; + + if (spi_st->words_remaining > FIFO_SIZE) + count = FIFO_SIZE; + else + count = spi_st->words_remaining; + + for (i = 0; i < count; i++) { + word = readl_relaxed(spi_st->base + SSC_RBUF); + + if (spi_st->rx_ptr) { + if (spi_st->bytes_per_word == 1) { + *spi_st->rx_ptr++ = (uint8_t)word; + } else { + *spi_st->rx_ptr++ = (word >> 8); + *spi_st->rx_ptr++ = word & 0xff; + } + } + } + spi_st->words_remaining -= count; +} + +static int spi_st_transfer_one(struct spi_master *master, + struct spi_device *spi, struct spi_transfer *t) +{ + struct spi_st *spi_st = spi_master_get_devdata(master); + uint32_t ctl = 0; + + /* Setup transfer */ + spi_st->tx_ptr = t->tx_buf; + spi_st->rx_ptr = t->rx_buf; + + if (spi->bits_per_word > 8) { + /* + * Anything greater than 8 bits-per-word requires 2 + * bytes-per-word in the RX/TX buffers + */ + spi_st->bytes_per_word = 2; + spi_st->words_remaining = t->len / 2; + + } else if (spi->bits_per_word == 8 && !(t->len & 0x1)) { + /* + * If transfer is even-length, and 8 bits-per-word, then + * implement as half-length 16 bits-per-word transfer + */ + spi_st->bytes_per_word = 2; + spi_st->words_remaining = t->len / 2; + + /* Set SSC_CTL to 16 bits-per-word */ + ctl = readl_relaxed(spi_st->base + SSC_CTL); + writel_relaxed((ctl | 0xf), spi_st->base + SSC_CTL); + + readl_relaxed(spi_st->base + SSC_RBUF); + + } else { + spi_st->bytes_per_word = 1; + spi_st->words_remaining = t->len; + } + + reinit_completion(&spi_st->done); + + /* Start transfer by writing to the TX FIFO */ + ssc_write_tx_fifo(spi_st); + writel_relaxed(SSC_IEN_TEEN, spi_st->base + SSC_IEN); + + /* Wait for transfer to complete */ + wait_for_completion(&spi_st->done); + + /* Restore SSC_CTL if necessary */ + if (ctl) + writel_relaxed(ctl, spi_st->base + SSC_CTL); + + spi_finalize_current_transfer(spi->master); + + return t->len; +} + +static void spi_st_cleanup(struct spi_device *spi) +{ + int cs = spi->cs_gpio; + + if (gpio_is_valid(cs)) + devm_gpio_free(&spi->dev, cs); +} + +/* the spi->mode bits understood by this driver: */ +#define MODEBITS (SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST | SPI_LOOP | SPI_CS_HIGH) +static int spi_st_setup(struct spi_device *spi) +{ + struct spi_st *spi_st = spi_master_get_devdata(spi->master); + u32 spi_st_clk, sscbrg, var; + u32 hz = spi->max_speed_hz; + int cs = spi->cs_gpio; + int ret; + + if (!hz) { + dev_err(&spi->dev, "max_speed_hz unspecified\n"); + return -EINVAL; + } + + if (!gpio_is_valid(cs)) { + dev_err(&spi->dev, "%d is not a valid gpio\n", cs); + return -EINVAL; + } + + if (devm_gpio_request(&spi->dev, cs, dev_name(&spi->dev))) { + dev_err(&spi->dev, "could not request gpio:%d\n", cs); + return -EINVAL; + } + + ret = gpio_direction_output(cs, spi->mode & SPI_CS_HIGH); + if (ret) + return ret; + + spi_st_clk = clk_get_rate(spi_st->clk); + + /* Set SSC_BRF */ + sscbrg = spi_st_clk / (2 * hz); + if (sscbrg < 0x07 || sscbrg > BIT(16)) { + dev_err(&spi->dev, + "baudrate %d outside valid range %d\n", sscbrg, hz); + return -EINVAL; + } + + spi_st->baud = spi_st_clk / (2 * sscbrg); + if (sscbrg == BIT(16)) /* 16-bit counter wraps */ + sscbrg = 0x0; + + writel_relaxed(sscbrg, spi_st->base + SSC_BRG); + + dev_dbg(&spi->dev, + "setting baudrate:target= %u hz, actual= %u hz, sscbrg= %u\n", + hz, spi_st->baud, sscbrg); + + /* Set SSC_CTL and enable SSC */ + var = readl_relaxed(spi_st->base + SSC_CTL); + var |= SSC_CTL_MS; + + if (spi->mode & SPI_CPOL) + var |= SSC_CTL_PO; + else + var &= ~SSC_CTL_PO; + + if (spi->mode & SPI_CPHA) + var |= SSC_CTL_PH; + else + var &= ~SSC_CTL_PH; + + if ((spi->mode & SPI_LSB_FIRST) == 0) + var |= SSC_CTL_HB; + else + var &= ~SSC_CTL_HB; + + if (spi->mode & SPI_LOOP) + var |= SSC_CTL_LPB; + else + var &= ~SSC_CTL_LPB; + + var &= ~SSC_CTL_DATA_WIDTH_MSK; + var |= (spi->bits_per_word - 1); + + var |= SSC_CTL_EN_TX_FIFO | SSC_CTL_EN_RX_FIFO; + var |= SSC_CTL_EN; + + writel_relaxed(var, spi_st->base + SSC_CTL); + + /* Clear the status register */ + readl_relaxed(spi_st->base + SSC_RBUF); + + return 0; +} + +/* Interrupt fired when TX shift register becomes empty */ +static irqreturn_t spi_st_irq(int irq, void *dev_id) +{ + struct spi_st *spi_st = (struct spi_st *)dev_id; + + /* Read RX FIFO */ + ssc_read_rx_fifo(spi_st); + + /* Fill TX FIFO */ + if (spi_st->words_remaining) { + ssc_write_tx_fifo(spi_st); + } else { + /* TX/RX complete */ + writel_relaxed(0x0, spi_st->base + SSC_IEN); + /* + * read SSC_IEN to ensure that this bit is set + * before re-enabling interrupt + */ + readl(spi_st->base + SSC_IEN); + complete(&spi_st->done); + } + + return IRQ_HANDLED; +} + +static int spi_st_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + struct spi_master *master; + struct resource *res; + struct spi_st *spi_st; + int irq, ret = 0; + u32 var; + + master = spi_alloc_master(&pdev->dev, sizeof(*spi_st)); + if (!master) + return -ENOMEM; + + master->dev.of_node = np; + master->mode_bits = MODEBITS; + master->setup = spi_st_setup; + master->cleanup = spi_st_cleanup; + master->transfer_one = spi_st_transfer_one; + master->bits_per_word_mask = SPI_BPW_MASK(8) | SPI_BPW_MASK(16); + master->auto_runtime_pm = true; + master->bus_num = pdev->id; + spi_st = spi_master_get_devdata(master); + + spi_st->clk = devm_clk_get(&pdev->dev, "ssc"); + if (IS_ERR(spi_st->clk)) { + dev_err(&pdev->dev, "Unable to request clock\n"); + return PTR_ERR(spi_st->clk); + } + + ret = spi_st_clk_enable(spi_st); + if (ret) + return ret; + + init_completion(&spi_st->done); + + /* Get resources */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + spi_st->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(spi_st->base)) { + ret = PTR_ERR(spi_st->base); + goto clk_disable; + } + + /* Disable I2C and Reset SSC */ + writel_relaxed(0x0, spi_st->base + SSC_I2C); + var = readw_relaxed(spi_st->base + SSC_CTL); + var |= SSC_CTL_SR; + writel_relaxed(var, spi_st->base + SSC_CTL); + + udelay(1); + var = readl_relaxed(spi_st->base + SSC_CTL); + var &= ~SSC_CTL_SR; + writel_relaxed(var, spi_st->base + SSC_CTL); + + /* Set SSC into slave mode before reconfiguring PIO pins */ + var = readl_relaxed(spi_st->base + SSC_CTL); + var &= ~SSC_CTL_MS; + writel_relaxed(var, spi_st->base + SSC_CTL); + + irq = irq_of_parse_and_map(np, 0); + if (!irq) { + dev_err(&pdev->dev, "IRQ missing or invalid\n"); + ret = -EINVAL; + goto clk_disable; + } + + ret = devm_request_irq(&pdev->dev, irq, spi_st_irq, 0, + pdev->name, spi_st); + if (ret) { + dev_err(&pdev->dev, "Failed to request irq %d\n", irq); + goto clk_disable; + } + + /* by default the device is on */ + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + platform_set_drvdata(pdev, master); + + ret = devm_spi_register_master(&pdev->dev, master); + if (ret) { + dev_err(&pdev->dev, "Failed to register master\n"); + goto clk_disable; + } + + return 0; + +clk_disable: + spi_st_clk_disable(spi_st); + + return ret; +} + +static int spi_st_remove(struct platform_device *pdev) +{ + struct spi_master *master = platform_get_drvdata(pdev); + struct spi_st *spi_st = spi_master_get_devdata(master); + + spi_st_clk_disable(spi_st); + + pinctrl_pm_select_sleep_state(&pdev->dev); + + return 0; +} + +#ifdef CONFIG_PM +static int spi_st_runtime_suspend(struct device *dev) +{ + struct spi_master *master = dev_get_drvdata(dev); + struct spi_st *spi_st = spi_master_get_devdata(master); + + writel_relaxed(0, spi_st->base + SSC_IEN); + pinctrl_pm_select_sleep_state(dev); + + spi_st_clk_disable(spi_st); + + return 0; +} + +static int spi_st_runtime_resume(struct device *dev) +{ + struct spi_master *master = dev_get_drvdata(dev); + struct spi_st *spi_st = spi_master_get_devdata(master); + int ret; + + ret = spi_st_clk_enable(spi_st); + pinctrl_pm_select_default_state(dev); + + return ret; +} +#endif + +#ifdef CONFIG_PM_SLEEP +static int spi_st_suspend(struct device *dev) +{ + struct spi_master *master = dev_get_drvdata(dev); + int ret; + + ret = spi_master_suspend(master); + if (ret) + return ret; + + return pm_runtime_force_suspend(dev); +} + +static int spi_st_resume(struct device *dev) +{ + struct spi_master *master = dev_get_drvdata(dev); + int ret; + + ret = spi_master_resume(master); + if (ret) + return ret; + + return pm_runtime_force_resume(dev); +} +#endif + +static const struct dev_pm_ops spi_st_pm = { + SET_SYSTEM_SLEEP_PM_OPS(spi_st_suspend, spi_st_resume) + SET_RUNTIME_PM_OPS(spi_st_runtime_suspend, spi_st_runtime_resume, NULL) +}; + +static struct of_device_id stm_spi_match[] = { + { .compatible = "st,comms-ssc4-spi", }, + {}, +}; +MODULE_DEVICE_TABLE(of, stm_spi_match); + +static struct platform_driver spi_st_driver = { + .driver = { + .name = "spi-st", + .pm = &spi_st_pm, + .of_match_table = of_match_ptr(stm_spi_match), + }, + .probe = spi_st_probe, + .remove = spi_st_remove, +}; +module_platform_driver(spi_st_driver); + +MODULE_AUTHOR("Patrice Chotard <patrice.chotard@st.com>"); +MODULE_DESCRIPTION("STM SSC SPI driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c index 6146c4cd658..884a716e50c 100644 --- a/drivers/spi/spi-ti-qspi.c +++ b/drivers/spi/spi-ti-qspi.c @@ -201,7 +201,7 @@ static void ti_qspi_restore_ctx(struct ti_qspi *qspi) static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t) { - int wlen, count, ret; + int wlen, count; unsigned int cmd; const u8 *txbuf; @@ -230,9 +230,8 @@ static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t) } ti_qspi_write(qspi, cmd, QSPI_SPI_CMD_REG); - ret = wait_for_completion_timeout(&qspi->transfer_complete, - QSPI_COMPLETION_TIMEOUT); - if (ret == 0) { + if (!wait_for_completion_timeout(&qspi->transfer_complete, + QSPI_COMPLETION_TIMEOUT)) { dev_err(qspi->dev, "write timed out\n"); return -ETIMEDOUT; } @@ -245,7 +244,7 @@ static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t) static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t) { - int wlen, count, ret; + int wlen, count; unsigned int cmd; u8 *rxbuf; @@ -268,9 +267,8 @@ static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t) while (count) { dev_dbg(qspi->dev, "rx cmd %08x dc %08x\n", cmd, qspi->dc); ti_qspi_write(qspi, cmd, QSPI_SPI_CMD_REG); - ret = wait_for_completion_timeout(&qspi->transfer_complete, - QSPI_COMPLETION_TIMEOUT); - if (ret == 0) { + if (!wait_for_completion_timeout(&qspi->transfer_complete, + QSPI_COMPLETION_TIMEOUT)) { dev_err(qspi->dev, "read timed out\n"); return -ETIMEDOUT; } diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c index be692ad5044..93dfcee0f98 100644 --- a/drivers/spi/spi-topcliff-pch.c +++ b/drivers/spi/spi-topcliff-pch.c @@ -11,10 +11,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA. */ #include <linux/delay.h> diff --git a/drivers/spi/spi-xilinx.c b/drivers/spi/spi-xilinx.c index 79bd84f4343..133f53a9c1d 100644 --- a/drivers/spi/spi-xilinx.c +++ b/drivers/spi/spi-xilinx.c @@ -22,6 +22,8 @@ #include <linux/spi/xilinx_spi.h> #include <linux/io.h> +#define XILINX_SPI_MAX_CS 32 + #define XILINX_SPI_NAME "xilinx_spi" /* Register definitions as per "OPB Serial Peripheral Interface (SPI) (v1.00e) @@ -34,7 +36,8 @@ #define XSPI_CR_MASTER_MODE 0x04 #define XSPI_CR_CPOL 0x08 #define XSPI_CR_CPHA 0x10 -#define XSPI_CR_MODE_MASK (XSPI_CR_CPHA | XSPI_CR_CPOL) +#define XSPI_CR_MODE_MASK (XSPI_CR_CPHA | XSPI_CR_CPOL | \ + XSPI_CR_LSB_FIRST | XSPI_CR_LOOP) #define XSPI_CR_TXFIFO_RESET 0x20 #define XSPI_CR_RXFIFO_RESET 0x40 #define XSPI_CR_MANUAL_SSELECT 0x80 @@ -85,12 +88,11 @@ struct xilinx_spi { u8 *rx_ptr; /* pointer in the Tx buffer */ const u8 *tx_ptr; /* pointer in the Rx buffer */ - int remaining_bytes; /* the number of bytes left to transfer */ - u8 bits_per_word; + u8 bytes_per_word; + int buffer_size; /* buffer size in words */ + u32 cs_inactive; /* Level of the CS pins when inactive*/ unsigned int (*read_fn)(void __iomem *); void (*write_fn)(u32, void __iomem *); - void (*tx_fn)(struct xilinx_spi *); - void (*rx_fn)(struct xilinx_spi *); }; static void xspi_write32(u32 val, void __iomem *addr) @@ -113,49 +115,51 @@ static unsigned int xspi_read32_be(void __iomem *addr) return ioread32be(addr); } -static void xspi_tx8(struct xilinx_spi *xspi) +static void xilinx_spi_tx(struct xilinx_spi *xspi) { - xspi->write_fn(*xspi->tx_ptr, xspi->regs + XSPI_TXD_OFFSET); - xspi->tx_ptr++; -} - -static void xspi_tx16(struct xilinx_spi *xspi) -{ - xspi->write_fn(*(u16 *)(xspi->tx_ptr), xspi->regs + XSPI_TXD_OFFSET); - xspi->tx_ptr += 2; -} + u32 data = 0; -static void xspi_tx32(struct xilinx_spi *xspi) -{ - xspi->write_fn(*(u32 *)(xspi->tx_ptr), xspi->regs + XSPI_TXD_OFFSET); - xspi->tx_ptr += 4; -} - -static void xspi_rx8(struct xilinx_spi *xspi) -{ - u32 data = xspi->read_fn(xspi->regs + XSPI_RXD_OFFSET); - if (xspi->rx_ptr) { - *xspi->rx_ptr = data & 0xff; - xspi->rx_ptr++; + if (!xspi->tx_ptr) { + xspi->write_fn(0, xspi->regs + XSPI_TXD_OFFSET); + return; } -} -static void xspi_rx16(struct xilinx_spi *xspi) -{ - u32 data = xspi->read_fn(xspi->regs + XSPI_RXD_OFFSET); - if (xspi->rx_ptr) { - *(u16 *)(xspi->rx_ptr) = data & 0xffff; - xspi->rx_ptr += 2; + switch (xspi->bytes_per_word) { + case 1: + data = *(u8 *)(xspi->tx_ptr); + break; + case 2: + data = *(u16 *)(xspi->tx_ptr); + break; + case 4: + data = *(u32 *)(xspi->tx_ptr); + break; } + + xspi->write_fn(data, xspi->regs + XSPI_TXD_OFFSET); + xspi->tx_ptr += xspi->bytes_per_word; } -static void xspi_rx32(struct xilinx_spi *xspi) +static void xilinx_spi_rx(struct xilinx_spi *xspi) { u32 data = xspi->read_fn(xspi->regs + XSPI_RXD_OFFSET); - if (xspi->rx_ptr) { + + if (!xspi->rx_ptr) + return; + + switch (xspi->bytes_per_word) { + case 1: + *(u8 *)(xspi->rx_ptr) = data; + break; + case 2: + *(u16 *)(xspi->rx_ptr) = data; + break; + case 4: *(u32 *)(xspi->rx_ptr) = data; - xspi->rx_ptr += 4; + break; } + + xspi->rx_ptr += xspi->bytes_per_word; } static void xspi_init_hw(struct xilinx_spi *xspi) @@ -165,46 +169,56 @@ static void xspi_init_hw(struct xilinx_spi *xspi) /* Reset the SPI device */ xspi->write_fn(XIPIF_V123B_RESET_MASK, regs_base + XIPIF_V123B_RESETR_OFFSET); - /* Disable all the interrupts just in case */ - xspi->write_fn(0, regs_base + XIPIF_V123B_IIER_OFFSET); - /* Enable the global IPIF interrupt */ - xspi->write_fn(XIPIF_V123B_GINTR_ENABLE, - regs_base + XIPIF_V123B_DGIER_OFFSET); + /* Enable the transmit empty interrupt, which we use to determine + * progress on the transmission. + */ + xspi->write_fn(XSPI_INTR_TX_EMPTY, + regs_base + XIPIF_V123B_IIER_OFFSET); + /* Disable the global IPIF interrupt */ + xspi->write_fn(0, regs_base + XIPIF_V123B_DGIER_OFFSET); /* Deselect the slave on the SPI bus */ xspi->write_fn(0xffff, regs_base + XSPI_SSR_OFFSET); /* Disable the transmitter, enable Manual Slave Select Assertion, * put SPI controller into master mode, and enable it */ - xspi->write_fn(XSPI_CR_TRANS_INHIBIT | XSPI_CR_MANUAL_SSELECT | - XSPI_CR_MASTER_MODE | XSPI_CR_ENABLE | XSPI_CR_TXFIFO_RESET | - XSPI_CR_RXFIFO_RESET, regs_base + XSPI_CR_OFFSET); + xspi->write_fn(XSPI_CR_MANUAL_SSELECT | XSPI_CR_MASTER_MODE | + XSPI_CR_ENABLE | XSPI_CR_TXFIFO_RESET | XSPI_CR_RXFIFO_RESET, + regs_base + XSPI_CR_OFFSET); } static void xilinx_spi_chipselect(struct spi_device *spi, int is_on) { struct xilinx_spi *xspi = spi_master_get_devdata(spi->master); + u16 cr; + u32 cs; if (is_on == BITBANG_CS_INACTIVE) { /* Deselect the slave on the SPI bus */ - xspi->write_fn(0xffff, xspi->regs + XSPI_SSR_OFFSET); - } else if (is_on == BITBANG_CS_ACTIVE) { - /* Set the SPI clock phase and polarity */ - u16 cr = xspi->read_fn(xspi->regs + XSPI_CR_OFFSET) - & ~XSPI_CR_MODE_MASK; - if (spi->mode & SPI_CPHA) - cr |= XSPI_CR_CPHA; - if (spi->mode & SPI_CPOL) - cr |= XSPI_CR_CPOL; - xspi->write_fn(cr, xspi->regs + XSPI_CR_OFFSET); - - /* We do not check spi->max_speed_hz here as the SPI clock - * frequency is not software programmable (the IP block design - * parameter) - */ - - /* Activate the chip select */ - xspi->write_fn(~(0x0001 << spi->chip_select), - xspi->regs + XSPI_SSR_OFFSET); + xspi->write_fn(xspi->cs_inactive, xspi->regs + XSPI_SSR_OFFSET); + return; } + + /* Set the SPI clock phase and polarity */ + cr = xspi->read_fn(xspi->regs + XSPI_CR_OFFSET) & ~XSPI_CR_MODE_MASK; + if (spi->mode & SPI_CPHA) + cr |= XSPI_CR_CPHA; + if (spi->mode & SPI_CPOL) + cr |= XSPI_CR_CPOL; + if (spi->mode & SPI_LSB_FIRST) + cr |= XSPI_CR_LSB_FIRST; + if (spi->mode & SPI_LOOP) + cr |= XSPI_CR_LOOP; + xspi->write_fn(cr, xspi->regs + XSPI_CR_OFFSET); + + /* We do not check spi->max_speed_hz here as the SPI clock + * frequency is not software programmable (the IP block design + * parameter) + */ + + cs = xspi->cs_inactive; + cs ^= BIT(spi->chip_select); + + /* Activate the chip select */ + xspi->write_fn(cs, xspi->regs + XSPI_SSR_OFFSET); } /* spi_bitbang requires custom setup_transfer() to be defined if there is a @@ -213,85 +227,85 @@ static void xilinx_spi_chipselect(struct spi_device *spi, int is_on) static int xilinx_spi_setup_transfer(struct spi_device *spi, struct spi_transfer *t) { - return 0; -} + struct xilinx_spi *xspi = spi_master_get_devdata(spi->master); -static void xilinx_spi_fill_tx_fifo(struct xilinx_spi *xspi) -{ - u8 sr; + if (spi->mode & SPI_CS_HIGH) + xspi->cs_inactive &= ~BIT(spi->chip_select); + else + xspi->cs_inactive |= BIT(spi->chip_select); - /* Fill the Tx FIFO with as many bytes as possible */ - sr = xspi->read_fn(xspi->regs + XSPI_SR_OFFSET); - while ((sr & XSPI_SR_TX_FULL_MASK) == 0 && xspi->remaining_bytes > 0) { - if (xspi->tx_ptr) - xspi->tx_fn(xspi); - else - xspi->write_fn(0, xspi->regs + XSPI_TXD_OFFSET); - xspi->remaining_bytes -= xspi->bits_per_word / 8; - sr = xspi->read_fn(xspi->regs + XSPI_SR_OFFSET); - } + return 0; } static int xilinx_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t) { struct xilinx_spi *xspi = spi_master_get_devdata(spi->master); - u32 ipif_ier; + int remaining_words; /* the number of words left to transfer */ + bool use_irq = false; + u16 cr = 0; /* We get here with transmitter inhibited */ xspi->tx_ptr = t->tx_buf; xspi->rx_ptr = t->rx_buf; - xspi->remaining_bytes = t->len; + remaining_words = t->len / xspi->bytes_per_word; reinit_completion(&xspi->done); + if (xspi->irq >= 0 && remaining_words > xspi->buffer_size) { + use_irq = true; + xspi->write_fn(XSPI_INTR_TX_EMPTY, + xspi->regs + XIPIF_V123B_IISR_OFFSET); + /* Enable the global IPIF interrupt */ + xspi->write_fn(XIPIF_V123B_GINTR_ENABLE, + xspi->regs + XIPIF_V123B_DGIER_OFFSET); + /* Inhibit irq to avoid spurious irqs on tx_empty*/ + cr = xspi->read_fn(xspi->regs + XSPI_CR_OFFSET); + xspi->write_fn(cr | XSPI_CR_TRANS_INHIBIT, + xspi->regs + XSPI_CR_OFFSET); + } - /* Enable the transmit empty interrupt, which we use to determine - * progress on the transmission. - */ - ipif_ier = xspi->read_fn(xspi->regs + XIPIF_V123B_IIER_OFFSET); - xspi->write_fn(ipif_ier | XSPI_INTR_TX_EMPTY, - xspi->regs + XIPIF_V123B_IIER_OFFSET); + while (remaining_words) { + int n_words, tx_words, rx_words; - for (;;) { - u16 cr; - u8 sr; + n_words = min(remaining_words, xspi->buffer_size); - xilinx_spi_fill_tx_fifo(xspi); + tx_words = n_words; + while (tx_words--) + xilinx_spi_tx(xspi); /* Start the transfer by not inhibiting the transmitter any * longer */ - cr = xspi->read_fn(xspi->regs + XSPI_CR_OFFSET) & - ~XSPI_CR_TRANS_INHIBIT; - xspi->write_fn(cr, xspi->regs + XSPI_CR_OFFSET); - wait_for_completion(&xspi->done); + if (use_irq) { + xspi->write_fn(cr, xspi->regs + XSPI_CR_OFFSET); + wait_for_completion(&xspi->done); + } else + while (!(xspi->read_fn(xspi->regs + XSPI_SR_OFFSET) & + XSPI_SR_TX_EMPTY_MASK)) + ; /* A transmit has just completed. Process received data and * check for more data to transmit. Always inhibit the * transmitter while the Isr refills the transmit register/FIFO, * or make sure it is stopped if we're done. */ - cr = xspi->read_fn(xspi->regs + XSPI_CR_OFFSET); - xspi->write_fn(cr | XSPI_CR_TRANS_INHIBIT, + if (use_irq) + xspi->write_fn(cr | XSPI_CR_TRANS_INHIBIT, xspi->regs + XSPI_CR_OFFSET); /* Read out all the data from the Rx FIFO */ - sr = xspi->read_fn(xspi->regs + XSPI_SR_OFFSET); - while ((sr & XSPI_SR_RX_EMPTY_MASK) == 0) { - xspi->rx_fn(xspi); - sr = xspi->read_fn(xspi->regs + XSPI_SR_OFFSET); - } - - /* See if there is more data to send */ - if (xspi->remaining_bytes <= 0) - break; + rx_words = n_words; + while (rx_words--) + xilinx_spi_rx(xspi); + + remaining_words -= n_words; } - /* Disable the transmit empty interrupt */ - xspi->write_fn(ipif_ier, xspi->regs + XIPIF_V123B_IIER_OFFSET); + if (use_irq) + xspi->write_fn(0, xspi->regs + XIPIF_V123B_DGIER_OFFSET); - return t->len - xspi->remaining_bytes; + return t->len; } @@ -316,6 +330,28 @@ static irqreturn_t xilinx_spi_irq(int irq, void *dev_id) return IRQ_HANDLED; } +static int xilinx_spi_find_buffer_size(struct xilinx_spi *xspi) +{ + u8 sr; + int n_words = 0; + + /* + * Before the buffer_size detection we reset the core + * to make sure we start with a clean state. + */ + xspi->write_fn(XIPIF_V123B_RESET_MASK, + xspi->regs + XIPIF_V123B_RESETR_OFFSET); + + /* Fill the Tx FIFO with as many words as possible */ + do { + xspi->write_fn(0, xspi->regs + XSPI_TXD_OFFSET); + sr = xspi->read_fn(xspi->regs + XSPI_SR_OFFSET); + n_words++; + } while (!(sr & XSPI_SR_TX_FULL_MASK)); + + return n_words; +} + static const struct of_device_id xilinx_spi_of_match[] = { { .compatible = "xlnx,xps-spi-2.00.a", }, { .compatible = "xlnx,xps-spi-2.00.b", }, @@ -348,14 +384,21 @@ static int xilinx_spi_probe(struct platform_device *pdev) return -EINVAL; } + if (num_cs > XILINX_SPI_MAX_CS) { + dev_err(&pdev->dev, "Invalid number of spi slaves\n"); + return -EINVAL; + } + master = spi_alloc_master(&pdev->dev, sizeof(struct xilinx_spi)); if (!master) return -ENODEV; /* the spi->mode bits understood by this driver: */ - master->mode_bits = SPI_CPOL | SPI_CPHA; + master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST | SPI_LOOP | + SPI_CS_HIGH; xspi = spi_master_get_devdata(master); + xspi->cs_inactive = 0xffffffff; xspi->bitbang.master = master; xspi->bitbang.chipselect = xilinx_spi_chipselect; xspi->bitbang.setup_transfer = xilinx_spi_setup_transfer; @@ -392,35 +435,20 @@ static int xilinx_spi_probe(struct platform_device *pdev) } master->bits_per_word_mask = SPI_BPW_MASK(bits_per_word); - xspi->bits_per_word = bits_per_word; - if (xspi->bits_per_word == 8) { - xspi->tx_fn = xspi_tx8; - xspi->rx_fn = xspi_rx8; - } else if (xspi->bits_per_word == 16) { - xspi->tx_fn = xspi_tx16; - xspi->rx_fn = xspi_rx16; - } else if (xspi->bits_per_word == 32) { - xspi->tx_fn = xspi_tx32; - xspi->rx_fn = xspi_rx32; - } else { - ret = -EINVAL; - goto put_master; - } - - /* SPI controller initializations */ - xspi_init_hw(xspi); + xspi->bytes_per_word = bits_per_word / 8; + xspi->buffer_size = xilinx_spi_find_buffer_size(xspi); xspi->irq = platform_get_irq(pdev, 0); - if (xspi->irq < 0) { - ret = xspi->irq; - goto put_master; + if (xspi->irq >= 0) { + /* Register for SPI Interrupt */ + ret = devm_request_irq(&pdev->dev, xspi->irq, xilinx_spi_irq, 0, + dev_name(&pdev->dev), xspi); + if (ret) + goto put_master; } - /* Register for SPI Interrupt */ - ret = devm_request_irq(&pdev->dev, xspi->irq, xilinx_spi_irq, 0, - dev_name(&pdev->dev), xspi); - if (ret) - goto put_master; + /* SPI controller initializations */ + xspi_init_hw(xspi); ret = spi_bitbang_start(&xspi->bitbang); if (ret) { diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 66a70e9bc74..c64a3e59fce 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -13,10 +13,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/kernel.h> @@ -788,7 +784,7 @@ static int spi_transfer_one_message(struct spi_master *master, struct spi_transfer *xfer; bool keep_cs = false; int ret = 0; - int ms = 1; + unsigned long ms = 1; spi_set_cs(msg->spi, true); @@ -875,31 +871,59 @@ void spi_finalize_current_transfer(struct spi_master *master) EXPORT_SYMBOL_GPL(spi_finalize_current_transfer); /** - * spi_pump_messages - kthread work function which processes spi message queue - * @work: pointer to kthread work struct contained in the master struct + * __spi_pump_messages - function which processes spi message queue + * @master: master to process queue for + * @in_kthread: true if we are in the context of the message pump thread * * This function checks if there is any spi message in the queue that * needs processing and if so call out to the driver to initialize hardware * and transfer each message. * + * Note that it is called both from the kthread itself and also from + * inside spi_sync(); the queue extraction handling at the top of the + * function should deal with this safely. */ -static void spi_pump_messages(struct kthread_work *work) +static void __spi_pump_messages(struct spi_master *master, bool in_kthread) { - struct spi_master *master = - container_of(work, struct spi_master, pump_messages); unsigned long flags; bool was_busy = false; int ret; - /* Lock queue and check for queue work */ + /* Lock queue */ spin_lock_irqsave(&master->queue_lock, flags); + + /* Make sure we are not already running a message */ + if (master->cur_msg) { + spin_unlock_irqrestore(&master->queue_lock, flags); + return; + } + + /* If another context is idling the device then defer */ + if (master->idling) { + queue_kthread_work(&master->kworker, &master->pump_messages); + spin_unlock_irqrestore(&master->queue_lock, flags); + return; + } + + /* Check if the queue is idle */ if (list_empty(&master->queue) || !master->running) { if (!master->busy) { spin_unlock_irqrestore(&master->queue_lock, flags); return; } + + /* Only do teardown in the thread */ + if (!in_kthread) { + queue_kthread_work(&master->kworker, + &master->pump_messages); + spin_unlock_irqrestore(&master->queue_lock, flags); + return; + } + master->busy = false; + master->idling = true; spin_unlock_irqrestore(&master->queue_lock, flags); + kfree(master->dummy_rx); master->dummy_rx = NULL; kfree(master->dummy_tx); @@ -913,14 +937,13 @@ static void spi_pump_messages(struct kthread_work *work) pm_runtime_put_autosuspend(master->dev.parent); } trace_spi_master_idle(master); - return; - } - /* Make sure we are not already running a message */ - if (master->cur_msg) { + spin_lock_irqsave(&master->queue_lock, flags); + master->idling = false; spin_unlock_irqrestore(&master->queue_lock, flags); return; } + /* Extract head of queue */ master->cur_msg = list_first_entry(&master->queue, struct spi_message, queue); @@ -985,13 +1008,22 @@ static void spi_pump_messages(struct kthread_work *work) } } +/** + * spi_pump_messages - kthread work function which processes spi message queue + * @work: pointer to kthread work struct contained in the master struct + */ +static void spi_pump_messages(struct kthread_work *work) +{ + struct spi_master *master = + container_of(work, struct spi_master, pump_messages); + + __spi_pump_messages(master, true); +} + static int spi_init_queue(struct spi_master *master) { struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; - INIT_LIST_HEAD(&master->queue); - spin_lock_init(&master->queue_lock); - master->running = false; master->busy = false; @@ -1161,12 +1193,9 @@ static int spi_destroy_queue(struct spi_master *master) return 0; } -/** - * spi_queued_transfer - transfer function for queued transfers - * @spi: spi device which is requesting transfer - * @msg: spi message which is to handled is queued to driver queue - */ -static int spi_queued_transfer(struct spi_device *spi, struct spi_message *msg) +static int __spi_queued_transfer(struct spi_device *spi, + struct spi_message *msg, + bool need_pump) { struct spi_master *master = spi->master; unsigned long flags; @@ -1181,13 +1210,23 @@ static int spi_queued_transfer(struct spi_device *spi, struct spi_message *msg) msg->status = -EINPROGRESS; list_add_tail(&msg->queue, &master->queue); - if (!master->busy) + if (!master->busy && need_pump) queue_kthread_work(&master->kworker, &master->pump_messages); spin_unlock_irqrestore(&master->queue_lock, flags); return 0; } +/** + * spi_queued_transfer - transfer function for queued transfers + * @spi: spi device which is requesting transfer + * @msg: spi message which is to handled is queued to driver queue + */ +static int spi_queued_transfer(struct spi_device *spi, struct spi_message *msg) +{ + return __spi_queued_transfer(spi, msg, true); +} + static int spi_master_initialize_queue(struct spi_master *master) { int ret; @@ -1609,6 +1648,8 @@ int spi_register_master(struct spi_master *master) dynamic = 1; } + INIT_LIST_HEAD(&master->queue); + spin_lock_init(&master->queue_lock); spin_lock_init(&master->bus_lock_spinlock); mutex_init(&master->bus_lock_mutex); master->bus_lock_flag = 0; @@ -2114,19 +2155,46 @@ static int __spi_sync(struct spi_device *spi, struct spi_message *message, DECLARE_COMPLETION_ONSTACK(done); int status; struct spi_master *master = spi->master; + unsigned long flags; + + status = __spi_validate(spi, message); + if (status != 0) + return status; message->complete = spi_complete; message->context = &done; + message->spi = spi; if (!bus_locked) mutex_lock(&master->bus_lock_mutex); - status = spi_async_locked(spi, message); + /* If we're not using the legacy transfer method then we will + * try to transfer in the calling context so special case. + * This code would be less tricky if we could remove the + * support for driver implemented message queues. + */ + if (master->transfer == spi_queued_transfer) { + spin_lock_irqsave(&master->bus_lock_spinlock, flags); + + trace_spi_message_submit(message); + + status = __spi_queued_transfer(spi, message, false); + + spin_unlock_irqrestore(&master->bus_lock_spinlock, flags); + } else { + status = spi_async_locked(spi, message); + } if (!bus_locked) mutex_unlock(&master->bus_lock_mutex); if (status == 0) { + /* Push out the messages in the calling context if we + * can. + */ + if (master->transfer == spi_queued_transfer) + __spi_pump_messages(master, false); + wait_for_completion(&done); status = message->status; } diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 6941e04afb8..4eb7a980e67 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -14,10 +14,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/init.h> @@ -317,6 +313,37 @@ done: return status; } +static struct spi_ioc_transfer * +spidev_get_ioc_message(unsigned int cmd, struct spi_ioc_transfer __user *u_ioc, + unsigned *n_ioc) +{ + struct spi_ioc_transfer *ioc; + u32 tmp; + + /* Check type, command number and direction */ + if (_IOC_TYPE(cmd) != SPI_IOC_MAGIC + || _IOC_NR(cmd) != _IOC_NR(SPI_IOC_MESSAGE(0)) + || _IOC_DIR(cmd) != _IOC_WRITE) + return ERR_PTR(-ENOTTY); + + tmp = _IOC_SIZE(cmd); + if ((tmp % sizeof(struct spi_ioc_transfer)) != 0) + return ERR_PTR(-EINVAL); + *n_ioc = tmp / sizeof(struct spi_ioc_transfer); + if (*n_ioc == 0) + return NULL; + + /* copy into scratch area */ + ioc = kmalloc(tmp, GFP_KERNEL); + if (!ioc) + return ERR_PTR(-ENOMEM); + if (__copy_from_user(ioc, u_ioc, tmp)) { + kfree(ioc); + return ERR_PTR(-EFAULT); + } + return ioc; +} + static long spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { @@ -456,32 +483,15 @@ spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) default: /* segmented and/or full-duplex I/O request */ - if (_IOC_NR(cmd) != _IOC_NR(SPI_IOC_MESSAGE(0)) - || _IOC_DIR(cmd) != _IOC_WRITE) { - retval = -ENOTTY; - break; - } - - tmp = _IOC_SIZE(cmd); - if ((tmp % sizeof(struct spi_ioc_transfer)) != 0) { - retval = -EINVAL; - break; - } - n_ioc = tmp / sizeof(struct spi_ioc_transfer); - if (n_ioc == 0) - break; - - /* copy into scratch area */ - ioc = kmalloc(tmp, GFP_KERNEL); - if (!ioc) { - retval = -ENOMEM; - break; - } - if (__copy_from_user(ioc, (void __user *)arg, tmp)) { - kfree(ioc); - retval = -EFAULT; + /* Check message and copy into scratch area */ + ioc = spidev_get_ioc_message(cmd, + (struct spi_ioc_transfer __user *)arg, &n_ioc); + if (IS_ERR(ioc)) { + retval = PTR_ERR(ioc); break; } + if (!ioc) + break; /* n_ioc is also 0 */ /* translate to spi_message, execute */ retval = spidev_message(spidev, ioc, n_ioc); @@ -496,8 +506,67 @@ spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) #ifdef CONFIG_COMPAT static long +spidev_compat_ioc_message(struct file *filp, unsigned int cmd, + unsigned long arg) +{ + struct spi_ioc_transfer __user *u_ioc; + int retval = 0; + struct spidev_data *spidev; + struct spi_device *spi; + unsigned n_ioc, n; + struct spi_ioc_transfer *ioc; + + u_ioc = (struct spi_ioc_transfer __user *) compat_ptr(arg); + if (!access_ok(VERIFY_READ, u_ioc, _IOC_SIZE(cmd))) + return -EFAULT; + + /* guard against device removal before, or while, + * we issue this ioctl. + */ + spidev = filp->private_data; + spin_lock_irq(&spidev->spi_lock); + spi = spi_dev_get(spidev->spi); + spin_unlock_irq(&spidev->spi_lock); + + if (spi == NULL) + return -ESHUTDOWN; + + /* SPI_IOC_MESSAGE needs the buffer locked "normally" */ + mutex_lock(&spidev->buf_lock); + + /* Check message and copy into scratch area */ + ioc = spidev_get_ioc_message(cmd, u_ioc, &n_ioc); + if (IS_ERR(ioc)) { + retval = PTR_ERR(ioc); + goto done; + } + if (!ioc) + goto done; /* n_ioc is also 0 */ + + /* Convert buffer pointers */ + for (n = 0; n < n_ioc; n++) { + ioc[n].rx_buf = (uintptr_t) compat_ptr(ioc[n].rx_buf); + ioc[n].tx_buf = (uintptr_t) compat_ptr(ioc[n].tx_buf); + } + + /* translate to spi_message, execute */ + retval = spidev_message(spidev, ioc, n_ioc); + kfree(ioc); + +done: + mutex_unlock(&spidev->buf_lock); + spi_dev_put(spi); + return retval; +} + +static long spidev_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { + if (_IOC_TYPE(cmd) == SPI_IOC_MAGIC + && _IOC_NR(cmd) == _IOC_NR(SPI_IOC_MESSAGE(0)) + && _IOC_DIR(cmd) == _IOC_WRITE) + return spidev_compat_ioc_message(filp, cmd, arg); + return spidev_ioctl(filp, cmd, (unsigned long)compat_ptr(arg)); } #else diff --git a/drivers/staging/speakup/speakup_dtlk.c b/drivers/staging/speakup/speakup_dtlk.c index 4e059ea78d4..89592c0b915 100644 --- a/drivers/staging/speakup/speakup_dtlk.c +++ b/drivers/staging/speakup/speakup_dtlk.c @@ -325,7 +325,7 @@ static struct synth_settings *synth_interrogate(struct spk_synth *synth) static int synth_probe(struct spk_synth *synth) { - unsigned int port_val = 0; + unsigned int port_val = 0; int i = 0; struct synth_settings *sp; @@ -361,7 +361,8 @@ static int synth_probe(struct spk_synth *synth) port_val &= 0xfbff; if (port_val != 0x107f) { pr_info("DoubleTalk PC: not found\n"); - synth_release_region(synth_lpc, SYNTH_IO_EXTENT); + if (synth_lpc) + synth_release_region(synth_lpc, SYNTH_IO_EXTENT); return -ENODEV; } while (inw_p(synth_lpc) != 0x147f) @@ -369,7 +370,7 @@ static int synth_probe(struct spk_synth *synth) sp = synth_interrogate(synth); pr_info("%s: %03x-%03x, ROM ver %s, s/n %u, driver: %s\n", synth->long_name, synth_lpc, synth_lpc+SYNTH_IO_EXTENT - 1, - sp->rom_version, sp->serial_number, synth->version); + sp->rom_version, sp->serial_number, synth->version); synth->alive = 1; return 0; } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index aeb50bb6ba9..eaffb0248de 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -3452,8 +3452,6 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg) return status; } -#ifdef CONFIG_PM - int usb_remote_wakeup(struct usb_device *udev) { int status = 0; @@ -3512,16 +3510,6 @@ static int hub_handle_remote_wakeup(struct usb_hub *hub, unsigned int port, return connect_change; } -#else - -static int hub_handle_remote_wakeup(struct usb_hub *hub, unsigned int port, - u16 portstatus, u16 portchange) -{ - return 0; -} - -#endif - static int check_ports_changed(struct usb_hub *hub) { int port1; diff --git a/drivers/video/fbdev/atafb.c b/drivers/video/fbdev/atafb.c index 4953b657635..cb9ee255685 100644 --- a/drivers/video/fbdev/atafb.c +++ b/drivers/video/fbdev/atafb.c @@ -3118,8 +3118,7 @@ int __init atafb_init(void) printk("atafb_init: initializing Falcon hw\n"); fbhw = &falcon_switch; atafb_ops.fb_setcolreg = &falcon_setcolreg; - error = request_irq(IRQ_AUTO_4, falcon_vbl_switcher, - IRQ_TYPE_PRIO, + error = request_irq(IRQ_AUTO_4, falcon_vbl_switcher, 0, "framebuffer:modeswitch", falcon_vbl_switcher); if (error) diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 3860d02729d..0b52d92cb2e 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -92,7 +92,6 @@ EXPORT_SYMBOL_GPL(balloon_stats); /* We increase/decrease in batches which fit in a page */ static xen_pfn_t frame_list[PAGE_SIZE / sizeof(unsigned long)]; -static DEFINE_PER_CPU(struct page *, balloon_scratch_page); /* List of ballooned pages, threaded through the mem_map array. */ @@ -423,22 +422,12 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) page = pfn_to_page(pfn); #ifdef CONFIG_XEN_HAVE_PVMMU - /* - * Ballooned out frames are effectively replaced with - * a scratch frame. Ensure direct mappings and the - * p2m are consistent. - */ if (!xen_feature(XENFEAT_auto_translated_physmap)) { if (!PageHighMem(page)) { - struct page *scratch_page = get_balloon_scratch_page(); - ret = HYPERVISOR_update_va_mapping( (unsigned long)__va(pfn << PAGE_SHIFT), - pfn_pte(page_to_pfn(scratch_page), - PAGE_KERNEL_RO), 0); + __pte_ma(0), 0); BUG_ON(ret); - - put_balloon_scratch_page(); } __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } @@ -500,18 +489,6 @@ static void balloon_process(struct work_struct *work) mutex_unlock(&balloon_mutex); } -struct page *get_balloon_scratch_page(void) -{ - struct page *ret = get_cpu_var(balloon_scratch_page); - BUG_ON(ret == NULL); - return ret; -} - -void put_balloon_scratch_page(void) -{ - put_cpu_var(balloon_scratch_page); -} - /* Resets the Xen limit, sets new target, and kicks off processing. */ void balloon_set_new_target(unsigned long target) { @@ -605,61 +582,13 @@ static void __init balloon_add_region(unsigned long start_pfn, } } -static int alloc_balloon_scratch_page(int cpu) -{ - if (per_cpu(balloon_scratch_page, cpu) != NULL) - return 0; - - per_cpu(balloon_scratch_page, cpu) = alloc_page(GFP_KERNEL); - if (per_cpu(balloon_scratch_page, cpu) == NULL) { - pr_warn("Failed to allocate balloon_scratch_page for cpu %d\n", cpu); - return -ENOMEM; - } - - return 0; -} - - -static int balloon_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - int cpu = (long)hcpu; - switch (action) { - case CPU_UP_PREPARE: - if (alloc_balloon_scratch_page(cpu)) - return NOTIFY_BAD; - break; - default: - break; - } - return NOTIFY_OK; -} - -static struct notifier_block balloon_cpu_notifier = { - .notifier_call = balloon_cpu_notify, -}; - static int __init balloon_init(void) { - int i, cpu; + int i; if (!xen_domain()) return -ENODEV; - if (!xen_feature(XENFEAT_auto_translated_physmap)) { - register_cpu_notifier(&balloon_cpu_notifier); - - get_online_cpus(); - for_each_online_cpu(cpu) { - if (alloc_balloon_scratch_page(cpu)) { - put_online_cpus(); - unregister_cpu_notifier(&balloon_cpu_notifier); - return -ENOMEM; - } - } - put_online_cpus(); - } - pr_info("Initialising balloon driver\n"); balloon_stats.current_pages = xen_pv_domain() @@ -696,15 +625,4 @@ static int __init balloon_init(void) subsys_initcall(balloon_init); -static int __init balloon_clear(void) -{ - int cpu; - - for_each_possible_cpu(cpu) - per_cpu(balloon_scratch_page, cpu) = NULL; - - return 0; -} -early_initcall(balloon_clear); - MODULE_LICENSE("GPL"); diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 073b4a19a8b..d5bb1a33d0a 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -67,7 +67,7 @@ struct gntdev_priv { * Only populated if populate_freeable_maps == 1 */ struct list_head freeable_maps; /* lock protects maps and freeable_maps */ - spinlock_t lock; + struct mutex lock; struct mm_struct *mm; struct mmu_notifier mn; }; @@ -91,7 +91,9 @@ struct grant_map { struct gnttab_map_grant_ref *map_ops; struct gnttab_unmap_grant_ref *unmap_ops; struct gnttab_map_grant_ref *kmap_ops; + struct gnttab_unmap_grant_ref *kunmap_ops; struct page **pages; + unsigned long pages_vm_start; }; static int unmap_grant_pages(struct grant_map *map, int offset, int pages); @@ -118,12 +120,13 @@ static void gntdev_free_map(struct grant_map *map) return; if (map->pages) - free_xenballooned_pages(map->count, map->pages); + gnttab_free_pages(map->count, map->pages); kfree(map->pages); kfree(map->grants); kfree(map->map_ops); kfree(map->unmap_ops); kfree(map->kmap_ops); + kfree(map->kunmap_ops); kfree(map); } @@ -140,21 +143,24 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count) add->map_ops = kcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL); add->unmap_ops = kcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL); add->kmap_ops = kcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL); + add->kunmap_ops = kcalloc(count, sizeof(add->kunmap_ops[0]), GFP_KERNEL); add->pages = kcalloc(count, sizeof(add->pages[0]), GFP_KERNEL); if (NULL == add->grants || NULL == add->map_ops || NULL == add->unmap_ops || NULL == add->kmap_ops || + NULL == add->kunmap_ops || NULL == add->pages) goto err; - if (alloc_xenballooned_pages(count, add->pages, false /* lowmem */)) + if (gnttab_alloc_pages(count, add->pages)) goto err; for (i = 0; i < count; i++) { add->map_ops[i].handle = -1; add->unmap_ops[i].handle = -1; add->kmap_ops[i].handle = -1; + add->kunmap_ops[i].handle = -1; } add->index = 0; @@ -216,9 +222,9 @@ static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map) } if (populate_freeable_maps && priv) { - spin_lock(&priv->lock); + mutex_lock(&priv->lock); list_del(&map->next); - spin_unlock(&priv->lock); + mutex_unlock(&priv->lock); } if (map->pages && !use_ptemod) @@ -239,6 +245,14 @@ static int find_grant_ptes(pte_t *pte, pgtable_t token, BUG_ON(pgnr >= map->count); pte_maddr = arbitrary_virt_to_machine(pte).maddr; + /* + * Set the PTE as special to force get_user_pages_fast() fall + * back to the slow path. If this is not supported as part of + * the grant map, it will be done afterwards. + */ + if (xen_feature(XENFEAT_gnttab_map_avail_bits)) + flags |= (1 << _GNTMAP_guest_avail0); + gnttab_set_map_op(&map->map_ops[pgnr], pte_maddr, flags, map->grants[pgnr].ref, map->grants[pgnr].domid); @@ -247,6 +261,15 @@ static int find_grant_ptes(pte_t *pte, pgtable_t token, return 0; } +#ifdef CONFIG_X86 +static int set_grant_ptes_as_special(pte_t *pte, pgtable_t token, + unsigned long addr, void *data) +{ + set_pte_at(current->mm, addr, pte, pte_mkspecial(*pte)); + return 0; +} +#endif + static int map_grant_pages(struct grant_map *map) { int i, err = 0; @@ -280,6 +303,8 @@ static int map_grant_pages(struct grant_map *map) map->flags | GNTMAP_host_map, map->grants[i].ref, map->grants[i].domid); + gnttab_set_unmap_op(&map->kunmap_ops[i], address, + map->flags | GNTMAP_host_map, -1); } } @@ -290,20 +315,42 @@ static int map_grant_pages(struct grant_map *map) return err; for (i = 0; i < map->count; i++) { - if (map->map_ops[i].status) + if (map->map_ops[i].status) { err = -EINVAL; - else { - BUG_ON(map->map_ops[i].handle == -1); - map->unmap_ops[i].handle = map->map_ops[i].handle; - pr_debug("map handle=%d\n", map->map_ops[i].handle); + continue; } + + map->unmap_ops[i].handle = map->map_ops[i].handle; + if (use_ptemod) + map->kunmap_ops[i].handle = map->kmap_ops[i].handle; } return err; } +struct unmap_grant_pages_callback_data +{ + struct completion completion; + int result; +}; + +static void unmap_grant_callback(int result, + struct gntab_unmap_queue_data *data) +{ + struct unmap_grant_pages_callback_data* d = data->data; + + d->result = result; + complete(&d->completion); +} + static int __unmap_grant_pages(struct grant_map *map, int offset, int pages) { int i, err = 0; + struct gntab_unmap_queue_data unmap_data; + struct unmap_grant_pages_callback_data data; + + init_completion(&data.completion); + unmap_data.data = &data; + unmap_data.done= &unmap_grant_callback; if (map->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) { int pgno = (map->notify.addr >> PAGE_SHIFT); @@ -315,11 +362,16 @@ static int __unmap_grant_pages(struct grant_map *map, int offset, int pages) } } - err = gnttab_unmap_refs(map->unmap_ops + offset, - use_ptemod ? map->kmap_ops + offset : NULL, map->pages + offset, - pages); - if (err) - return err; + unmap_data.unmap_ops = map->unmap_ops + offset; + unmap_data.kunmap_ops = use_ptemod ? map->kunmap_ops + offset : NULL; + unmap_data.pages = map->pages + offset; + unmap_data.count = pages; + + gnttab_unmap_refs_async(&unmap_data); + + wait_for_completion(&data.completion); + if (data.result) + return data.result; for (i = 0; i < pages; i++) { if (map->unmap_ops[offset+i].status) @@ -387,17 +439,26 @@ static void gntdev_vma_close(struct vm_area_struct *vma) * not do any unmapping, since that has been done prior to * closing the vma, but it may still iterate the unmap_ops list. */ - spin_lock(&priv->lock); + mutex_lock(&priv->lock); map->vma = NULL; - spin_unlock(&priv->lock); + mutex_unlock(&priv->lock); } vma->vm_private_data = NULL; gntdev_put_map(priv, map); } +static struct page *gntdev_vma_find_special_page(struct vm_area_struct *vma, + unsigned long addr) +{ + struct grant_map *map = vma->vm_private_data; + + return map->pages[(addr - map->pages_vm_start) >> PAGE_SHIFT]; +} + static struct vm_operations_struct gntdev_vmops = { .open = gntdev_vma_open, .close = gntdev_vma_close, + .find_special_page = gntdev_vma_find_special_page, }; /* ------------------------------------------------------------------ */ @@ -433,14 +494,14 @@ static void mn_invl_range_start(struct mmu_notifier *mn, struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn); struct grant_map *map; - spin_lock(&priv->lock); + mutex_lock(&priv->lock); list_for_each_entry(map, &priv->maps, next) { unmap_if_in_range(map, start, end); } list_for_each_entry(map, &priv->freeable_maps, next) { unmap_if_in_range(map, start, end); } - spin_unlock(&priv->lock); + mutex_unlock(&priv->lock); } static void mn_invl_page(struct mmu_notifier *mn, @@ -457,7 +518,7 @@ static void mn_release(struct mmu_notifier *mn, struct grant_map *map; int err; - spin_lock(&priv->lock); + mutex_lock(&priv->lock); list_for_each_entry(map, &priv->maps, next) { if (!map->vma) continue; @@ -476,7 +537,7 @@ static void mn_release(struct mmu_notifier *mn, err = unmap_grant_pages(map, /* offset */ 0, map->count); WARN_ON(err); } - spin_unlock(&priv->lock); + mutex_unlock(&priv->lock); } static struct mmu_notifier_ops gntdev_mmu_ops = { @@ -498,7 +559,7 @@ static int gntdev_open(struct inode *inode, struct file *flip) INIT_LIST_HEAD(&priv->maps); INIT_LIST_HEAD(&priv->freeable_maps); - spin_lock_init(&priv->lock); + mutex_init(&priv->lock); if (use_ptemod) { priv->mm = get_task_mm(current); @@ -572,10 +633,10 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv, return -EFAULT; } - spin_lock(&priv->lock); + mutex_lock(&priv->lock); gntdev_add_map(priv, map); op.index = map->index << PAGE_SHIFT; - spin_unlock(&priv->lock); + mutex_unlock(&priv->lock); if (copy_to_user(u, &op, sizeof(op)) != 0) return -EFAULT; @@ -594,7 +655,7 @@ static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv, return -EFAULT; pr_debug("priv %p, del %d+%d\n", priv, (int)op.index, (int)op.count); - spin_lock(&priv->lock); + mutex_lock(&priv->lock); map = gntdev_find_map_index(priv, op.index >> PAGE_SHIFT, op.count); if (map) { list_del(&map->next); @@ -602,7 +663,7 @@ static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv, list_add_tail(&map->next, &priv->freeable_maps); err = 0; } - spin_unlock(&priv->lock); + mutex_unlock(&priv->lock); if (map) gntdev_put_map(priv, map); return err; @@ -670,7 +731,7 @@ static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u) out_flags = op.action; out_event = op.event_channel_port; - spin_lock(&priv->lock); + mutex_lock(&priv->lock); list_for_each_entry(map, &priv->maps, next) { uint64_t begin = map->index << PAGE_SHIFT; @@ -698,7 +759,7 @@ static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u) rc = 0; unlock_out: - spin_unlock(&priv->lock); + mutex_unlock(&priv->lock); /* Drop the reference to the event channel we did not save in the map */ if (out_flags & UNMAP_NOTIFY_SEND_EVENT) @@ -748,7 +809,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) pr_debug("map %d+%d at %lx (pgoff %lx)\n", index, count, vma->vm_start, vma->vm_pgoff); - spin_lock(&priv->lock); + mutex_lock(&priv->lock); map = gntdev_find_map_index(priv, index, count); if (!map) goto unlock_out; @@ -783,7 +844,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) map->flags |= GNTMAP_readonly; } - spin_unlock(&priv->lock); + mutex_unlock(&priv->lock); if (use_ptemod) { err = apply_to_page_range(vma->vm_mm, vma->vm_start, @@ -806,16 +867,34 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) if (err) goto out_put_map; } + } else { +#ifdef CONFIG_X86 + /* + * If the PTEs were not made special by the grant map + * hypercall, do so here. + * + * This is racy since the mapping is already visible + * to userspace but userspace should be well-behaved + * enough to not touch it until the mmap() call + * returns. + */ + if (!xen_feature(XENFEAT_gnttab_map_avail_bits)) { + apply_to_page_range(vma->vm_mm, vma->vm_start, + vma->vm_end - vma->vm_start, + set_grant_ptes_as_special, NULL); + } +#endif + map->pages_vm_start = vma->vm_start; } return 0; unlock_out: - spin_unlock(&priv->lock); + mutex_unlock(&priv->lock); return err; out_unlock_put: - spin_unlock(&priv->lock); + mutex_unlock(&priv->lock); out_put_map: if (use_ptemod) map->vma = NULL; diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 7786291ba22..17972fbacdd 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -42,6 +42,7 @@ #include <linux/io.h> #include <linux/delay.h> #include <linux/hardirq.h> +#include <linux/workqueue.h> #include <xen/xen.h> #include <xen/interface/xen.h> @@ -50,6 +51,7 @@ #include <xen/interface/memory.h> #include <xen/hvc-console.h> #include <xen/swiotlb-xen.h> +#include <xen/balloon.h> #include <asm/xen/hypercall.h> #include <asm/xen/interface.h> @@ -671,6 +673,59 @@ void gnttab_free_auto_xlat_frames(void) } EXPORT_SYMBOL_GPL(gnttab_free_auto_xlat_frames); +/** + * gnttab_alloc_pages - alloc pages suitable for grant mapping into + * @nr_pages: number of pages to alloc + * @pages: returns the pages + */ +int gnttab_alloc_pages(int nr_pages, struct page **pages) +{ + int i; + int ret; + + ret = alloc_xenballooned_pages(nr_pages, pages, false); + if (ret < 0) + return ret; + + for (i = 0; i < nr_pages; i++) { +#if BITS_PER_LONG < 64 + struct xen_page_foreign *foreign; + + foreign = kzalloc(sizeof(*foreign), GFP_KERNEL); + if (!foreign) { + gnttab_free_pages(nr_pages, pages); + return -ENOMEM; + } + set_page_private(pages[i], (unsigned long)foreign); +#endif + SetPagePrivate(pages[i]); + } + + return 0; +} +EXPORT_SYMBOL(gnttab_alloc_pages); + +/** + * gnttab_free_pages - free pages allocated by gnttab_alloc_pages() + * @nr_pages; number of pages to free + * @pages: the pages + */ +void gnttab_free_pages(int nr_pages, struct page **pages) +{ + int i; + + for (i = 0; i < nr_pages; i++) { + if (PagePrivate(pages[i])) { +#if BITS_PER_LONG < 64 + kfree((void *)page_private(pages[i])); +#endif + ClearPagePrivate(pages[i]); + } + } + free_xenballooned_pages(nr_pages, pages); +} +EXPORT_SYMBOL(gnttab_free_pages); + /* Handling of paged out grant targets (GNTST_eagain) */ #define MAX_DELAY 256 static inline void @@ -727,30 +782,87 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, if (ret) return ret; - /* Retry eagain maps */ - for (i = 0; i < count; i++) + for (i = 0; i < count; i++) { + /* Retry eagain maps */ if (map_ops[i].status == GNTST_eagain) gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, map_ops + i, &map_ops[i].status, __func__); + if (map_ops[i].status == GNTST_okay) { + struct xen_page_foreign *foreign; + + SetPageForeign(pages[i]); + foreign = xen_page_foreign(pages[i]); + foreign->domid = map_ops[i].dom; + foreign->gref = map_ops[i].ref; + } + } + return set_foreign_p2m_mapping(map_ops, kmap_ops, pages, count); } EXPORT_SYMBOL_GPL(gnttab_map_refs); int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, - struct gnttab_map_grant_ref *kmap_ops, + struct gnttab_unmap_grant_ref *kunmap_ops, struct page **pages, unsigned int count) { + unsigned int i; int ret; ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap_ops, count); if (ret) return ret; - return clear_foreign_p2m_mapping(unmap_ops, kmap_ops, pages, count); + for (i = 0; i < count; i++) + ClearPageForeign(pages[i]); + + return clear_foreign_p2m_mapping(unmap_ops, kunmap_ops, pages, count); } EXPORT_SYMBOL_GPL(gnttab_unmap_refs); +#define GNTTAB_UNMAP_REFS_DELAY 5 + +static void __gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item); + +static void gnttab_unmap_work(struct work_struct *work) +{ + struct gntab_unmap_queue_data + *unmap_data = container_of(work, + struct gntab_unmap_queue_data, + gnttab_work.work); + if (unmap_data->age != UINT_MAX) + unmap_data->age++; + __gnttab_unmap_refs_async(unmap_data); +} + +static void __gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item) +{ + int ret; + int pc; + + for (pc = 0; pc < item->count; pc++) { + if (page_count(item->pages[pc]) > 1) { + unsigned long delay = GNTTAB_UNMAP_REFS_DELAY * (item->age + 1); + schedule_delayed_work(&item->gnttab_work, + msecs_to_jiffies(delay)); + return; + } + } + + ret = gnttab_unmap_refs(item->unmap_ops, item->kunmap_ops, + item->pages, item->count); + item->done(ret, item); +} + +void gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item) +{ + INIT_DELAYED_WORK(&item->gnttab_work, gnttab_unmap_work); + item->age = 0; + + __gnttab_unmap_refs_async(item); +} +EXPORT_SYMBOL_GPL(gnttab_unmap_refs_async); + static int gnttab_map_frames_v1(xen_pfn_t *frames, unsigned int nr_gframes) { int rc; diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index f8bb36f9d9c..bf194070642 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -105,10 +105,16 @@ static void do_suspend(void) err = freeze_processes(); if (err) { - pr_err("%s: freeze failed %d\n", __func__, err); + pr_err("%s: freeze processes failed %d\n", __func__, err); goto out; } + err = freeze_kernel_threads(); + if (err) { + pr_err("%s: freeze kernel threads failed %d\n", __func__, err); + goto out_thaw; + } + err = dpm_suspend_start(PMSG_FREEZE); if (err) { pr_err("%s: dpm_suspend_start %d\n", __func__, err); diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c index 83b5c53bec6..8a65423bc69 100644 --- a/drivers/xen/tmem.c +++ b/drivers/xen/tmem.c @@ -374,7 +374,7 @@ static struct frontswap_ops tmem_frontswap_ops = { }; #endif -static int xen_tmem_init(void) +static int __init xen_tmem_init(void) { if (!xen_domain()) return 0; diff --git a/drivers/xen/xen-acpi-memhotplug.c b/drivers/xen/xen-acpi-memhotplug.c index 34e40b733f9..4fc886cd558 100644 --- a/drivers/xen/xen-acpi-memhotplug.c +++ b/drivers/xen/xen-acpi-memhotplug.c @@ -117,8 +117,8 @@ acpi_memory_get_resource(struct acpi_resource *resource, void *context) list_for_each_entry(info, &mem_device->res_list, list) { if ((info->caching == address64.info.mem.caching) && (info->write_protect == address64.info.mem.write_protect) && - (info->start_addr + info->length == address64.minimum)) { - info->length += address64.address_length; + (info->start_addr + info->length == address64.address.minimum)) { + info->length += address64.address.address_length; return AE_OK; } } @@ -130,8 +130,8 @@ acpi_memory_get_resource(struct acpi_resource *resource, void *context) INIT_LIST_HEAD(&new->list); new->caching = address64.info.mem.caching; new->write_protect = address64.info.mem.write_protect; - new->start_addr = address64.minimum; - new->length = address64.address_length; + new->start_addr = address64.address.minimum; + new->length = address64.address.address_length; list_add_tail(&new->list, &mem_device->res_list); return AE_OK; diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index e999496eda3..ecd540a7a56 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -227,7 +227,7 @@ static void put_free_pages(struct page **page, int num) return; if (i > scsiback_max_buffer_pages) { n = min(num, i - scsiback_max_buffer_pages); - free_xenballooned_pages(n, page + num - n); + gnttab_free_pages(n, page + num - n); n = num - n; } spin_lock_irqsave(&free_pages_lock, flags); @@ -244,7 +244,7 @@ static int get_free_page(struct page **page) spin_lock_irqsave(&free_pages_lock, flags); if (list_empty(&scsiback_free_pages)) { spin_unlock_irqrestore(&free_pages_lock, flags); - return alloc_xenballooned_pages(1, page, false); + return gnttab_alloc_pages(1, page); } page[0] = list_first_entry(&scsiback_free_pages, struct page, lru); list_del(&page[0]->lru); @@ -2106,7 +2106,7 @@ static void __exit scsiback_exit(void) while (free_pages_num) { if (get_free_page(&page)) BUG(); - free_xenballooned_pages(1, &page); + gnttab_free_pages(1, &page); } scsiback_deregister_configfs(); xenbus_unregister_driver(&scsiback_driver); diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 85534ea6355..9433e46518c 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -326,10 +326,13 @@ static int xenbus_write_transaction(unsigned msg_type, } if (msg_type == XS_TRANSACTION_START) { - trans->handle.id = simple_strtoul(reply, NULL, 0); - - list_add(&trans->list, &u->transactions); - } else if (msg_type == XS_TRANSACTION_END) { + if (u->u.msg.type == XS_ERROR) + kfree(trans); + else { + trans->handle.id = simple_strtoul(reply, NULL, 0); + list_add(&trans->list, &u->transactions); + } + } else if (u->u.msg.type == XS_TRANSACTION_END) { list_for_each_entry(trans, &u->transactions, list) if (trans->handle.id == u->u.msg.tx_id) break; diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 5594505e6e7..b40133796b8 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -831,7 +831,6 @@ static const struct vm_operations_struct v9fs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = v9fs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static const struct vm_operations_struct v9fs_mmap_file_vm_ops = { @@ -839,7 +838,6 @@ static const struct vm_operations_struct v9fs_mmap_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = v9fs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; diff --git a/fs/Kconfig b/fs/Kconfig index 664991afe0c..a6bb530b1ec 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -165,6 +165,7 @@ config HUGETLB_PAGE def_bool HUGETLBFS source "fs/configfs/Kconfig" +source "fs/efivarfs/Kconfig" endmenu @@ -209,7 +210,6 @@ source "fs/sysv/Kconfig" source "fs/ufs/Kconfig" source "fs/exofs/Kconfig" source "fs/f2fs/Kconfig" -source "fs/efivarfs/Kconfig" endif # MISC_FILESYSTEMS @@ -1140,6 +1140,13 @@ static long aio_read_events_ring(struct kioctx *ctx, long ret = 0; int copy_ret; + /* + * The mutex can block and wake us up and that will cause + * wait_event_interruptible_hrtimeout() to schedule without sleeping + * and repeat. This should be rare enough that it doesn't cause + * peformance issues. See the comment in read_events() for more detail. + */ + sched_annotate_sleep(); mutex_lock(&ctx->ring_lock); /* Access to ->ring_pages here is protected by ctx->ring_lock. */ diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index a66768ebc8d..80e9c18ea64 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -8,6 +8,7 @@ config BTRFS_FS select LZO_DECOMPRESS select RAID6_PQ select XOR_BLOCKS + select SRCU help Btrfs is a general purpose copy-on-write filesystem with extents, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index e4090259569..a606ab55129 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2081,7 +2081,6 @@ static const struct vm_operations_struct btrfs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = btrfs_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 9a02da16f2b..1a9585d4380 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2591,6 +2591,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, } if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) { + blk_finish_plug(&plug); mutex_unlock(&log_root_tree->log_mutex); ret = root_log_ctx.log_ret; goto out; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index c81c0e00458..24be059fd1f 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1569,7 +1569,6 @@ out: static struct vm_operations_struct ceph_vmops = { .fault = ceph_filemap_fault, .page_mkwrite = ceph_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; int ceph_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index c35c5c614e3..06ea5cd05cd 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -239,23 +239,21 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) return err; } -/** - * Must be called with lock_flocks() already held. Fills in the passed - * counter variables, so you can prepare pagelist metadata before calling - * ceph_encode_locks. +/* + * Fills in the passed counter variables, so you can prepare pagelist metadata + * before calling ceph_encode_locks. */ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) { - struct file_lock *lock; + struct file_lock_context *ctx; *fcntl_count = 0; *flock_count = 0; - for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { - if (lock->fl_flags & FL_POSIX) - ++(*fcntl_count); - else if (lock->fl_flags & FL_FLOCK) - ++(*flock_count); + ctx = inode->i_flctx; + if (ctx) { + *fcntl_count = ctx->flc_posix_cnt; + *flock_count = ctx->flc_flock_cnt; } dout("counted %d flock locks and %d fcntl locks", *flock_count, *fcntl_count); @@ -271,6 +269,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode, int num_fcntl_locks, int num_flock_locks) { struct file_lock *lock; + struct file_lock_context *ctx = inode->i_flctx; int err = 0; int seen_fcntl = 0; int seen_flock = 0; @@ -279,33 +278,34 @@ int ceph_encode_locks_to_buffer(struct inode *inode, dout("encoding %d flock and %d fcntl locks", num_flock_locks, num_fcntl_locks); - for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { - if (lock->fl_flags & FL_POSIX) { - ++seen_fcntl; - if (seen_fcntl > num_fcntl_locks) { - err = -ENOSPC; - goto fail; - } - err = lock_to_ceph_filelock(lock, &flocks[l]); - if (err) - goto fail; - ++l; + if (!ctx) + return 0; + + spin_lock(&ctx->flc_lock); + list_for_each_entry(lock, &ctx->flc_flock, fl_list) { + ++seen_fcntl; + if (seen_fcntl > num_fcntl_locks) { + err = -ENOSPC; + goto fail; } + err = lock_to_ceph_filelock(lock, &flocks[l]); + if (err) + goto fail; + ++l; } - for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { - if (lock->fl_flags & FL_FLOCK) { - ++seen_flock; - if (seen_flock > num_flock_locks) { - err = -ENOSPC; - goto fail; - } - err = lock_to_ceph_filelock(lock, &flocks[l]); - if (err) - goto fail; - ++l; + list_for_each_entry(lock, &ctx->flc_flock, fl_list) { + ++seen_flock; + if (seen_flock > num_flock_locks) { + err = -ENOSPC; + goto fail; } + err = lock_to_ceph_filelock(lock, &flocks[l]); + if (err) + goto fail; + ++l; } fail: + spin_unlock(&ctx->flc_lock); return err; } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index d2171f4a698..5f62fb7a5d0 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2700,20 +2700,16 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, struct ceph_filelock *flocks; encode_again: - spin_lock(&inode->i_lock); ceph_count_locks(inode, &num_fcntl_locks, &num_flock_locks); - spin_unlock(&inode->i_lock); flocks = kmalloc((num_fcntl_locks+num_flock_locks) * sizeof(struct ceph_filelock), GFP_NOFS); if (!flocks) { err = -ENOMEM; goto out_free; } - spin_lock(&inode->i_lock); err = ceph_encode_locks_to_buffer(inode, flocks, num_fcntl_locks, num_flock_locks); - spin_unlock(&inode->i_lock); if (err) { kfree(flocks); if (err == -ENOSPC) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 74f12877493..8fe1f7a21b3 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1113,11 +1113,6 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) return rc; } -/* copied from fs/locks.c with a name change */ -#define cifs_for_each_lock(inode, lockp) \ - for (lockp = &inode->i_flock; *lockp != NULL; \ - lockp = &(*lockp)->fl_next) - struct lock_to_push { struct list_head llist; __u64 offset; @@ -1132,8 +1127,9 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) { struct inode *inode = cfile->dentry->d_inode; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); - struct file_lock *flock, **before; - unsigned int count = 0, i = 0; + struct file_lock *flock; + struct file_lock_context *flctx = inode->i_flctx; + unsigned int i; int rc = 0, xid, type; struct list_head locks_to_send, *el; struct lock_to_push *lck, *tmp; @@ -1141,21 +1137,17 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) xid = get_xid(); - spin_lock(&inode->i_lock); - cifs_for_each_lock(inode, before) { - if ((*before)->fl_flags & FL_POSIX) - count++; - } - spin_unlock(&inode->i_lock); + if (!flctx) + goto out; INIT_LIST_HEAD(&locks_to_send); /* - * Allocating count locks is enough because no FL_POSIX locks can be - * added to the list while we are holding cinode->lock_sem that + * Allocating flc_posix_cnt locks is enough because no FL_POSIX locks + * can be added to the list while we are holding cinode->lock_sem that * protects locking operations of this inode. */ - for (; i < count; i++) { + for (i = 0; i < flctx->flc_posix_cnt; i++) { lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL); if (!lck) { rc = -ENOMEM; @@ -1165,11 +1157,8 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) } el = locks_to_send.next; - spin_lock(&inode->i_lock); - cifs_for_each_lock(inode, before) { - flock = *before; - if ((flock->fl_flags & FL_POSIX) == 0) - continue; + spin_lock(&flctx->flc_lock); + list_for_each_entry(flock, &flctx->flc_posix, fl_list) { if (el == &locks_to_send) { /* * The list ended. We don't have enough allocated @@ -1189,9 +1178,8 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) lck->length = length; lck->type = type; lck->offset = flock->fl_start; - el = el->next; } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) { int stored_rc; @@ -3248,7 +3236,6 @@ static struct vm_operations_struct cifs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = cifs_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/efivarfs/Kconfig b/fs/efivarfs/Kconfig index 367bbb10c54..c2499ef174a 100644 --- a/fs/efivarfs/Kconfig +++ b/fs/efivarfs/Kconfig @@ -1,6 +1,7 @@ config EFIVAR_FS tristate "EFI Variable filesystem" depends on EFI + default m help efivarfs is a replacement filesystem for the old EFI variable support via sysfs, as it doesn't suffer from the diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 6dad1176ec5..ddbce42548c 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -140,7 +140,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, name[len] = '-'; - efi_guid_unparse(&entry->var.VendorGuid, name + len + 1); + efi_guid_to_str(&entry->var.VendorGuid, name + len + 1); name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 9b4e7d750d4..d4dbf3c259b 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -466,6 +466,8 @@ static void ext3_put_super (struct super_block * sb) } sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); + mutex_destroy(&sbi->s_orphan_lock); + mutex_destroy(&sbi->s_resize_lock); kfree(sbi); } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 8131be8c0af..7cb59238612 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -195,7 +195,6 @@ static const struct vm_operations_struct ext4_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = ext4_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 74c5f53595f..ac64edbe501 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1046,10 +1046,7 @@ static int ext4_mark_dquot_dirty(struct dquot *dquot); static int ext4_write_info(struct super_block *sb, int type); static int ext4_quota_on(struct super_block *sb, int type, int format_id, struct path *path); -static int ext4_quota_on_sysfile(struct super_block *sb, int type, - int format_id); static int ext4_quota_off(struct super_block *sb, int type); -static int ext4_quota_off_sysfile(struct super_block *sb, int type); static int ext4_quota_on_mount(struct super_block *sb, int type); static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); @@ -1084,16 +1081,6 @@ static const struct quotactl_ops ext4_qctl_operations = { .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk }; - -static const struct quotactl_ops ext4_qctl_sysfile_operations = { - .quota_on_meta = ext4_quota_on_sysfile, - .quota_off = ext4_quota_off_sysfile, - .quota_sync = dquot_quota_sync, - .get_info = dquot_get_dqinfo, - .set_info = dquot_set_dqinfo, - .get_dqblk = dquot_get_dqblk, - .set_dqblk = dquot_set_dqblk -}; #endif static const struct super_operations ext4_sops = { @@ -3935,7 +3922,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_QUOTA sb->dq_op = &ext4_quota_operations; if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) - sb->s_qcop = &ext4_qctl_sysfile_operations; + sb->s_qcop = &dquot_quotactl_sysfile_ops; else sb->s_qcop = &ext4_qctl_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; @@ -5288,21 +5275,6 @@ static int ext4_enable_quotas(struct super_block *sb) return 0; } -/* - * quota_on function that is used when QUOTA feature is set. - */ -static int ext4_quota_on_sysfile(struct super_block *sb, int type, - int format_id) -{ - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) - return -EINVAL; - - /* - * USAGE was enabled at mount time. Only need to enable LIMITS now. - */ - return ext4_quota_enable(sb, type, format_id, DQUOT_LIMITS_ENABLED); -} - static int ext4_quota_off(struct super_block *sb, int type) { struct inode *inode = sb_dqopt(sb)->files[type]; @@ -5329,18 +5301,6 @@ out: return dquot_quota_off(sb, type); } -/* - * quota_off function that is used when QUOTA feature is set. - */ -static int ext4_quota_off_sysfile(struct super_block *sb, int type) -{ - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) - return -EINVAL; - - /* Disable only the limits. */ - return dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); -} - /* Read data from quotafile - avoid pagecache and such because we cannot afford * acquiring the locks... As quota files are never truncated and quota code * itself serializes the operations (and no one else should touch the files) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 3c27e0ecb3b..5674ba13102 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -92,7 +92,6 @@ static const struct vm_operations_struct f2fs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = f2fs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int get_parent_ino(struct inode *inode, nid_t *pino) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 760b2c55219..d769e594855 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2062,7 +2062,6 @@ static const struct vm_operations_struct fuse_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = fuse_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 3088e2a38e3..7b3143064af 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -73,7 +73,7 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) BUG_ON(name == NULL); - if (acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode))) + if (acl && acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode))) return -E2BIG; if (type == ACL_TYPE_ACCESS) { diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index c5a34f09e22..6371192961e 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -1896,7 +1896,8 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, ht = kzalloc(size, GFP_NOFS | __GFP_NOWARN); if (ht == NULL) - ht = vzalloc(size); + ht = __vmalloc(size, GFP_NOFS | __GFP_NOWARN | __GFP_ZERO, + PAGE_KERNEL); if (!ht) return -ENOMEM; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 6e600abf694..ec9c2d33477 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -498,7 +498,6 @@ static const struct vm_operations_struct gfs2_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = gfs2_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; /** diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index a23524aa3ea..aeb7bc958a1 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -173,19 +173,14 @@ void gfs2_glock_add_to_lru(struct gfs2_glock *gl) spin_unlock(&lru_lock); } -static void __gfs2_glock_remove_from_lru(struct gfs2_glock *gl) +static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl) { + spin_lock(&lru_lock); if (!list_empty(&gl->gl_lru)) { list_del_init(&gl->gl_lru); atomic_dec(&lru_count); clear_bit(GLF_LRU, &gl->gl_flags); } -} - -static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl) -{ - spin_lock(&lru_lock); - __gfs2_glock_remove_from_lru(gl); spin_unlock(&lru_lock); } @@ -205,9 +200,7 @@ void gfs2_glock_put(struct gfs2_glock *gl) lockref_mark_dead(&gl->gl_lockref); - spin_lock(&lru_lock); - __gfs2_glock_remove_from_lru(gl); - spin_unlock(&lru_lock); + gfs2_glock_remove_from_lru(gl); spin_unlock(&gl->gl_lockref.lock); spin_lock_bucket(gl->gl_hash); hlist_bl_del_rcu(&gl->gl_list); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 9054002ebe7..73c72253faa 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -543,10 +543,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name, } error = gfs2_dir_add(&dip->i_inode, name, ip, da); - if (error) - goto fail_end_trans; -fail_end_trans: gfs2_trans_end(sdp); fail_ipreserv: gfs2_inplace_release(dip); diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 573bd3b758f..1b645773c98 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -439,7 +439,7 @@ static void gfs2_recovery_done(struct gfs2_sbd *sdp, unsigned int jid, ls->ls_recover_jid_done = jid; ls->ls_recover_jid_status = message; - sprintf(env_jid, "JID=%d", jid); + sprintf(env_jid, "JID=%u", jid); sprintf(env_status, "RECOVERY=%s", message == LM_RD_SUCCESS ? "Done" : "Failed"); kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp); diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 3ab566ba569..ae8e8811f0e 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -96,7 +96,7 @@ static ssize_t freeze_show(struct gfs2_sbd *sdp, char *buf) struct super_block *sb = sdp->sd_vfs; int frozen = (sb->s_writers.frozen == SB_UNFROZEN) ? 0 : 1; - return snprintf(buf, PAGE_SIZE, "%u\n", frozen); + return snprintf(buf, PAGE_SIZE, "%d\n", frozen); } static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len) diff --git a/fs/inode.c b/fs/inode.c index aa149e7262a..3a53b1da3fb 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -194,7 +194,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) #ifdef CONFIG_FSNOTIFY inode->i_fsnotify_mask = 0; #endif - + inode->i_flctx = NULL; this_cpu_inc(nr_inodes); return 0; @@ -237,6 +237,7 @@ void __destroy_inode(struct inode *inode) BUG_ON(inode_has_buffers(inode)); security_inode_free(inode); fsnotify_inode_delete(inode); + locks_free_lock_context(inode->i_flctx); if (!inode->i_nlink) { WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); atomic_long_dec(&inode->i_sb->s_remove_count); @@ -355,7 +356,6 @@ void address_space_init_once(struct address_space *mapping) INIT_LIST_HEAD(&mapping->private_list); spin_lock_init(&mapping->private_lock); mapping->i_mmap = RB_ROOT; - INIT_LIST_HEAD(&mapping->i_mmap_nonlinear); } EXPORT_SYMBOL(address_space_init_once); diff --git a/fs/ioctl.c b/fs/ioctl.c index 214c3c11fbc..5d01d2638ca 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -379,6 +379,11 @@ int __generic_block_fiemap(struct inode *inode, past_eof = true; } cond_resched(); + if (fatal_signal_pending(current)) { + ret = -EINTR; + break; + } + } while (1); /* If ret is 1 then we just hit the end of the extent array */ diff --git a/fs/isofs/util.c b/fs/isofs/util.c index 01e1ee7a998..005a15cfd30 100644 --- a/fs/isofs/util.c +++ b/fs/isofs/util.c @@ -2,6 +2,7 @@ * linux/fs/isofs/util.c */ +#include <linux/time.h> #include "isofs.h" /* @@ -17,9 +18,9 @@ int iso_date(char * p, int flag) { int year, month, day, hour, minute, second, tz; - int crtime, days, i; + int crtime; - year = p[0] - 70; + year = p[0]; month = p[1]; day = p[2]; hour = p[3]; @@ -31,18 +32,7 @@ int iso_date(char * p, int flag) if (year < 0) { crtime = 0; } else { - int monlen[12] = {31,28,31,30,31,30,31,31,30,31,30,31}; - - days = year * 365; - if (year > 2) - days += (year+1) / 4; - for (i = 1; i < month; i++) - days += monlen[i-1]; - if (((year+2) % 4) == 0 && month > 2) - days++; - days += day - 1; - crtime = ((((days * 24) + hour) * 60 + minute) * 60) - + second; + crtime = mktime64(year+1900, month, day, hour, minute, second); /* sign extend */ if (tz & 0x80) diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index d12ff4e2dbe..665ef5a0518 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -164,12 +164,15 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file, { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; + struct file_lock_context *flctx = inode->i_flctx; struct nlm_host *lockhost; + if (!flctx || list_empty_careful(&flctx->flc_posix)) + return 0; again: file->f_locks = 0; - spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl; fl = fl->fl_next) { + spin_lock(&flctx->flc_lock); + list_for_each_entry(fl, &flctx->flc_posix, fl_list) { if (fl->fl_lmops != &nlmsvc_lock_operations) continue; @@ -180,7 +183,7 @@ again: if (match(lockhost, host)) { struct file_lock lock = *fl; - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); lock.fl_type = F_UNLCK; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; @@ -192,7 +195,7 @@ again: goto again; } } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); return 0; } @@ -223,18 +226,21 @@ nlm_file_inuse(struct nlm_file *file) { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; + struct file_lock_context *flctx = inode->i_flctx; if (file->f_count || !list_empty(&file->f_blocks) || file->f_shares) return 1; - spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl; fl = fl->fl_next) { - if (fl->fl_lmops == &nlmsvc_lock_operations) { - spin_unlock(&inode->i_lock); - return 1; + if (flctx && !list_empty_careful(&flctx->flc_posix)) { + spin_lock(&flctx->flc_lock); + list_for_each_entry(fl, &flctx->flc_posix, fl_list) { + if (fl->fl_lmops == &nlmsvc_lock_operations) { + spin_unlock(&flctx->flc_lock); + return 1; + } } + spin_unlock(&flctx->flc_lock); } - spin_unlock(&inode->i_lock); file->f_locks = 0; return 0; } diff --git a/fs/locks.c b/fs/locks.c index 59e2f905e4f..4d0d41163a5 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -157,14 +157,11 @@ static int target_leasetype(struct file_lock *fl) int leases_enable = 1; int lease_break_time = 45; -#define for_each_lock(inode, lockp) \ - for (lockp = &inode->i_flock; *lockp != NULL; lockp = &(*lockp)->fl_next) - /* * The global file_lock_list is only used for displaying /proc/locks, so we * keep a list on each CPU, with each list protected by its own spinlock via * the file_lock_lglock. Note that alterations to the list also require that - * the relevant i_lock is held. + * the relevant flc_lock is held. */ DEFINE_STATIC_LGLOCK(file_lock_lglock); static DEFINE_PER_CPU(struct hlist_head, file_lock_list); @@ -192,21 +189,68 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS); * contrast to those that are acting as records of acquired locks). * * Note that when we acquire this lock in order to change the above fields, - * we often hold the i_lock as well. In certain cases, when reading the fields + * we often hold the flc_lock as well. In certain cases, when reading the fields * protected by this lock, we can skip acquiring it iff we already hold the - * i_lock. + * flc_lock. * * In particular, adding an entry to the fl_block list requires that you hold - * both the i_lock and the blocked_lock_lock (acquired in that order). Deleting - * an entry from the list however only requires the file_lock_lock. + * both the flc_lock and the blocked_lock_lock (acquired in that order). + * Deleting an entry from the list however only requires the file_lock_lock. */ static DEFINE_SPINLOCK(blocked_lock_lock); +static struct kmem_cache *flctx_cache __read_mostly; static struct kmem_cache *filelock_cache __read_mostly; +static struct file_lock_context * +locks_get_lock_context(struct inode *inode) +{ + struct file_lock_context *new; + + if (likely(inode->i_flctx)) + goto out; + + new = kmem_cache_alloc(flctx_cache, GFP_KERNEL); + if (!new) + goto out; + + spin_lock_init(&new->flc_lock); + INIT_LIST_HEAD(&new->flc_flock); + INIT_LIST_HEAD(&new->flc_posix); + INIT_LIST_HEAD(&new->flc_lease); + + /* + * Assign the pointer if it's not already assigned. If it is, then + * free the context we just allocated. + */ + spin_lock(&inode->i_lock); + if (likely(!inode->i_flctx)) { + inode->i_flctx = new; + new = NULL; + } + spin_unlock(&inode->i_lock); + + if (new) + kmem_cache_free(flctx_cache, new); +out: + return inode->i_flctx; +} + +void +locks_free_lock_context(struct file_lock_context *ctx) +{ + if (ctx) { + WARN_ON_ONCE(!list_empty(&ctx->flc_flock)); + WARN_ON_ONCE(!list_empty(&ctx->flc_posix)); + WARN_ON_ONCE(!list_empty(&ctx->flc_lease)); + kmem_cache_free(flctx_cache, ctx); + } +} + static void locks_init_lock_heads(struct file_lock *fl) { INIT_HLIST_NODE(&fl->fl_link); + INIT_LIST_HEAD(&fl->fl_list); INIT_LIST_HEAD(&fl->fl_block); init_waitqueue_head(&fl->fl_wait); } @@ -243,6 +287,7 @@ EXPORT_SYMBOL_GPL(locks_release_private); void locks_free_lock(struct file_lock *fl) { BUG_ON(waitqueue_active(&fl->fl_wait)); + BUG_ON(!list_empty(&fl->fl_list)); BUG_ON(!list_empty(&fl->fl_block)); BUG_ON(!hlist_unhashed(&fl->fl_link)); @@ -257,8 +302,8 @@ locks_dispose_list(struct list_head *dispose) struct file_lock *fl; while (!list_empty(dispose)) { - fl = list_first_entry(dispose, struct file_lock, fl_block); - list_del_init(&fl->fl_block); + fl = list_first_entry(dispose, struct file_lock, fl_list); + list_del_init(&fl->fl_list); locks_free_lock(fl); } } @@ -513,7 +558,7 @@ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2) return fl1->fl_owner == fl2->fl_owner; } -/* Must be called with the i_lock held! */ +/* Must be called with the flc_lock held! */ static void locks_insert_global_locks(struct file_lock *fl) { lg_local_lock(&file_lock_lglock); @@ -522,12 +567,12 @@ static void locks_insert_global_locks(struct file_lock *fl) lg_local_unlock(&file_lock_lglock); } -/* Must be called with the i_lock held! */ +/* Must be called with the flc_lock held! */ static void locks_delete_global_locks(struct file_lock *fl) { /* * Avoid taking lock if already unhashed. This is safe since this check - * is done while holding the i_lock, and new insertions into the list + * is done while holding the flc_lock, and new insertions into the list * also require that it be held. */ if (hlist_unhashed(&fl->fl_link)) @@ -579,10 +624,10 @@ static void locks_delete_block(struct file_lock *waiter) * the order they blocked. The documentation doesn't require this but * it seems like the reasonable thing to do. * - * Must be called with both the i_lock and blocked_lock_lock held. The fl_block - * list itself is protected by the blocked_lock_lock, but by ensuring that the - * i_lock is also held on insertions we can avoid taking the blocked_lock_lock - * in some cases when we see that the fl_block list is empty. + * Must be called with both the flc_lock and blocked_lock_lock held. The + * fl_block list itself is protected by the blocked_lock_lock, but by ensuring + * that the flc_lock is also held on insertions we can avoid taking the + * blocked_lock_lock in some cases when we see that the fl_block list is empty. */ static void __locks_insert_block(struct file_lock *blocker, struct file_lock *waiter) @@ -594,7 +639,7 @@ static void __locks_insert_block(struct file_lock *blocker, locks_insert_global_blocked(waiter); } -/* Must be called with i_lock held. */ +/* Must be called with flc_lock held. */ static void locks_insert_block(struct file_lock *blocker, struct file_lock *waiter) { @@ -606,15 +651,15 @@ static void locks_insert_block(struct file_lock *blocker, /* * Wake up processes blocked waiting for blocker. * - * Must be called with the inode->i_lock held! + * Must be called with the inode->flc_lock held! */ static void locks_wake_up_blocks(struct file_lock *blocker) { /* * Avoid taking global lock if list is empty. This is safe since new - * blocked requests are only added to the list under the i_lock, and - * the i_lock is always held here. Note that removal from the fl_block - * list does not require the i_lock, so we must recheck list_empty() + * blocked requests are only added to the list under the flc_lock, and + * the flc_lock is always held here. Note that removal from the fl_block + * list does not require the flc_lock, so we must recheck list_empty() * after acquiring the blocked_lock_lock. */ if (list_empty(&blocker->fl_block)) @@ -635,63 +680,36 @@ static void locks_wake_up_blocks(struct file_lock *blocker) spin_unlock(&blocked_lock_lock); } -/* Insert file lock fl into an inode's lock list at the position indicated - * by pos. At the same time add the lock to the global file lock list. - * - * Must be called with the i_lock held! - */ -static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl) +static void +locks_insert_lock_ctx(struct file_lock *fl, int *counter, + struct list_head *before) { fl->fl_nspid = get_pid(task_tgid(current)); - - /* insert into file's list */ - fl->fl_next = *pos; - *pos = fl; - + list_add_tail(&fl->fl_list, before); + ++*counter; locks_insert_global_locks(fl); } -/** - * locks_delete_lock - Delete a lock and then free it. - * @thisfl_p: pointer that points to the fl_next field of the previous - * inode->i_flock list entry - * - * Unlink a lock from all lists and free the namespace reference, but don't - * free it yet. Wake up processes that are blocked waiting for this lock and - * notify the FS that the lock has been cleared. - * - * Must be called with the i_lock held! - */ -static void locks_unlink_lock(struct file_lock **thisfl_p) +static void +locks_unlink_lock_ctx(struct file_lock *fl, int *counter) { - struct file_lock *fl = *thisfl_p; - locks_delete_global_locks(fl); - - *thisfl_p = fl->fl_next; - fl->fl_next = NULL; - + list_del_init(&fl->fl_list); + --*counter; if (fl->fl_nspid) { put_pid(fl->fl_nspid); fl->fl_nspid = NULL; } - locks_wake_up_blocks(fl); } -/* - * Unlink a lock from all lists and free it. - * - * Must be called with i_lock held! - */ -static void locks_delete_lock(struct file_lock **thisfl_p, - struct list_head *dispose) +static void +locks_delete_lock_ctx(struct file_lock *fl, int *counter, + struct list_head *dispose) { - struct file_lock *fl = *thisfl_p; - - locks_unlink_lock(thisfl_p); + locks_unlink_lock_ctx(fl, counter); if (dispose) - list_add(&fl->fl_block, dispose); + list_add(&fl->fl_list, dispose); else locks_free_lock(fl); } @@ -746,22 +764,27 @@ void posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; + struct file_lock_context *ctx; struct inode *inode = file_inode(filp); - spin_lock(&inode->i_lock); - for (cfl = file_inode(filp)->i_flock; cfl; cfl = cfl->fl_next) { - if (!IS_POSIX(cfl)) - continue; - if (posix_locks_conflict(fl, cfl)) - break; - } - if (cfl) { - locks_copy_conflock(fl, cfl); - if (cfl->fl_nspid) - fl->fl_pid = pid_vnr(cfl->fl_nspid); - } else + ctx = inode->i_flctx; + if (!ctx || list_empty_careful(&ctx->flc_posix)) { fl->fl_type = F_UNLCK; - spin_unlock(&inode->i_lock); + return; + } + + spin_lock(&ctx->flc_lock); + list_for_each_entry(cfl, &ctx->flc_posix, fl_list) { + if (posix_locks_conflict(fl, cfl)) { + locks_copy_conflock(fl, cfl); + if (cfl->fl_nspid) + fl->fl_pid = pid_vnr(cfl->fl_nspid); + goto out; + } + } + fl->fl_type = F_UNLCK; +out: + spin_unlock(&ctx->flc_lock); return; } EXPORT_SYMBOL(posix_test_lock); @@ -845,34 +868,34 @@ static int posix_locks_deadlock(struct file_lock *caller_fl, static int flock_lock_file(struct file *filp, struct file_lock *request) { struct file_lock *new_fl = NULL; - struct file_lock **before; - struct inode * inode = file_inode(filp); + struct file_lock *fl; + struct file_lock_context *ctx; + struct inode *inode = file_inode(filp); int error = 0; - int found = 0; + bool found = false; LIST_HEAD(dispose); + ctx = locks_get_lock_context(inode); + if (!ctx) + return -ENOMEM; + if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) { new_fl = locks_alloc_lock(); if (!new_fl) return -ENOMEM; } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); if (request->fl_flags & FL_ACCESS) goto find_conflict; - for_each_lock(inode, before) { - struct file_lock *fl = *before; - if (IS_POSIX(fl)) - break; - if (IS_LEASE(fl)) - continue; + list_for_each_entry(fl, &ctx->flc_flock, fl_list) { if (filp != fl->fl_file) continue; if (request->fl_type == fl->fl_type) goto out; - found = 1; - locks_delete_lock(before, &dispose); + found = true; + locks_delete_lock_ctx(fl, &ctx->flc_flock_cnt, &dispose); break; } @@ -887,18 +910,13 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) * give it the opportunity to lock the file. */ if (found) { - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); cond_resched(); - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); } find_conflict: - for_each_lock(inode, before) { - struct file_lock *fl = *before; - if (IS_POSIX(fl)) - break; - if (IS_LEASE(fl)) - continue; + list_for_each_entry(fl, &ctx->flc_flock, fl_list) { if (!flock_locks_conflict(request, fl)) continue; error = -EAGAIN; @@ -911,12 +929,12 @@ find_conflict: if (request->fl_flags & FL_ACCESS) goto out; locks_copy_lock(new_fl, request); - locks_insert_lock(before, new_fl); + locks_insert_lock_ctx(new_fl, &ctx->flc_flock_cnt, &ctx->flc_flock); new_fl = NULL; error = 0; out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); @@ -925,16 +943,20 @@ out: static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock) { - struct file_lock *fl; + struct file_lock *fl, *tmp; struct file_lock *new_fl = NULL; struct file_lock *new_fl2 = NULL; struct file_lock *left = NULL; struct file_lock *right = NULL; - struct file_lock **before; + struct file_lock_context *ctx; int error; bool added = false; LIST_HEAD(dispose); + ctx = locks_get_lock_context(inode); + if (!ctx) + return -ENOMEM; + /* * We may need two file_lock structures for this operation, * so we get them in advance to avoid races. @@ -948,15 +970,14 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str new_fl2 = locks_alloc_lock(); } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); /* * New lock request. Walk all POSIX locks and look for conflicts. If * there are any, either return error or put the request on the * blocker's list of waiters and the global blocked_hash. */ if (request->fl_type != F_UNLCK) { - for_each_lock(inode, before) { - fl = *before; + list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (!IS_POSIX(fl)) continue; if (!posix_locks_conflict(request, fl)) @@ -986,29 +1007,25 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str if (request->fl_flags & FL_ACCESS) goto out; - /* - * Find the first old lock with the same owner as the new lock. - */ - - before = &inode->i_flock; - - /* First skip locks owned by other processes. */ - while ((fl = *before) && (!IS_POSIX(fl) || - !posix_same_owner(request, fl))) { - before = &fl->fl_next; + /* Find the first old lock with the same owner as the new lock */ + list_for_each_entry(fl, &ctx->flc_posix, fl_list) { + if (posix_same_owner(request, fl)) + break; } /* Process locks with this owner. */ - while ((fl = *before) && posix_same_owner(request, fl)) { - /* Detect adjacent or overlapping regions (if same lock type) - */ + list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, fl_list) { + if (!posix_same_owner(request, fl)) + break; + + /* Detect adjacent or overlapping regions (if same lock type) */ if (request->fl_type == fl->fl_type) { /* In all comparisons of start vs end, use * "start - 1" rather than "end + 1". If end * is OFFSET_MAX, end + 1 will become negative. */ if (fl->fl_end < request->fl_start - 1) - goto next_lock; + continue; /* If the next lock in the list has entirely bigger * addresses than the new one, insert the lock here. */ @@ -1029,18 +1046,18 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str else request->fl_end = fl->fl_end; if (added) { - locks_delete_lock(before, &dispose); + locks_delete_lock_ctx(fl, &ctx->flc_posix_cnt, + &dispose); continue; } request = fl; added = true; - } - else { + } else { /* Processing for different lock types is a bit * more complex. */ if (fl->fl_end < request->fl_start) - goto next_lock; + continue; if (fl->fl_start > request->fl_end) break; if (request->fl_type == F_UNLCK) @@ -1059,7 +1076,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str * one (This may happen several times). */ if (added) { - locks_delete_lock(before, &dispose); + locks_delete_lock_ctx(fl, + &ctx->flc_posix_cnt, &dispose); continue; } /* @@ -1075,15 +1093,13 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str locks_copy_lock(new_fl, request); request = new_fl; new_fl = NULL; - locks_delete_lock(before, &dispose); - locks_insert_lock(before, request); + locks_insert_lock_ctx(request, + &ctx->flc_posix_cnt, &fl->fl_list); + locks_delete_lock_ctx(fl, + &ctx->flc_posix_cnt, &dispose); added = true; } } - /* Go on to next lock. - */ - next_lock: - before = &fl->fl_next; } /* @@ -1108,7 +1124,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str goto out; } locks_copy_lock(new_fl, request); - locks_insert_lock(before, new_fl); + locks_insert_lock_ctx(new_fl, &ctx->flc_posix_cnt, + &fl->fl_list); new_fl = NULL; } if (right) { @@ -1119,7 +1136,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str left = new_fl2; new_fl2 = NULL; locks_copy_lock(left, right); - locks_insert_lock(before, left); + locks_insert_lock_ctx(left, &ctx->flc_posix_cnt, + &fl->fl_list); } right->fl_start = request->fl_end + 1; locks_wake_up_blocks(right); @@ -1129,7 +1147,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str locks_wake_up_blocks(left); } out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); /* * Free any unused locks. */ @@ -1199,22 +1217,29 @@ EXPORT_SYMBOL(posix_lock_file_wait); */ int locks_mandatory_locked(struct file *file) { + int ret; struct inode *inode = file_inode(file); + struct file_lock_context *ctx; struct file_lock *fl; + ctx = inode->i_flctx; + if (!ctx || list_empty_careful(&ctx->flc_posix)) + return 0; + /* * Search the lock list for this inode for any POSIX locks. */ - spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { - if (!IS_POSIX(fl)) - continue; + spin_lock(&ctx->flc_lock); + ret = 0; + list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (fl->fl_owner != current->files && - fl->fl_owner != file) + fl->fl_owner != file) { + ret = -EAGAIN; break; + } } - spin_unlock(&inode->i_lock); - return fl ? -EAGAIN : 0; + spin_unlock(&ctx->flc_lock); + return ret; } /** @@ -1294,9 +1319,9 @@ static void lease_clear_pending(struct file_lock *fl, int arg) } /* We already had a lease on this file; just change its type */ -int lease_modify(struct file_lock **before, int arg, struct list_head *dispose) +int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { - struct file_lock *fl = *before; + struct file_lock_context *flctx; int error = assign_type(fl, arg); if (error) @@ -1306,6 +1331,7 @@ int lease_modify(struct file_lock **before, int arg, struct list_head *dispose) if (arg == F_UNLCK) { struct file *filp = fl->fl_file; + flctx = file_inode(filp)->i_flctx; f_delown(filp); filp->f_owner.signum = 0; fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync); @@ -1313,7 +1339,7 @@ int lease_modify(struct file_lock **before, int arg, struct list_head *dispose) printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); fl->fl_fasync = NULL; } - locks_delete_lock(before, dispose); + locks_delete_lock_ctx(fl, &flctx->flc_lease_cnt, dispose); } return 0; } @@ -1329,20 +1355,17 @@ static bool past_time(unsigned long then) static void time_out_leases(struct inode *inode, struct list_head *dispose) { - struct file_lock **before; - struct file_lock *fl; + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl, *tmp; - lockdep_assert_held(&inode->i_lock); + lockdep_assert_held(&ctx->flc_lock); - before = &inode->i_flock; - while ((fl = *before) && IS_LEASE(fl) && lease_breaking(fl)) { + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { trace_time_out_leases(inode, fl); if (past_time(fl->fl_downgrade_time)) - lease_modify(before, F_RDLCK, dispose); + lease_modify(fl, F_RDLCK, dispose); if (past_time(fl->fl_break_time)) - lease_modify(before, F_UNLCK, dispose); - if (fl == *before) /* lease_modify may have freed fl */ - before = &fl->fl_next; + lease_modify(fl, F_UNLCK, dispose); } } @@ -1356,11 +1379,12 @@ static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker) static bool any_leases_conflict(struct inode *inode, struct file_lock *breaker) { + struct file_lock_context *ctx = inode->i_flctx; struct file_lock *fl; - lockdep_assert_held(&inode->i_lock); + lockdep_assert_held(&ctx->flc_lock); - for (fl = inode->i_flock ; fl && IS_LEASE(fl); fl = fl->fl_next) { + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (leases_conflict(fl, breaker)) return true; } @@ -1384,7 +1408,8 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { int error = 0; struct file_lock *new_fl; - struct file_lock *fl, **before; + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl; unsigned long break_time; int want_write = (mode & O_ACCMODE) != O_RDONLY; LIST_HEAD(dispose); @@ -1394,7 +1419,13 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) return PTR_ERR(new_fl); new_fl->fl_flags = type; - spin_lock(&inode->i_lock); + /* typically we will check that ctx is non-NULL before calling */ + if (!ctx) { + WARN_ON_ONCE(1); + return error; + } + + spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); @@ -1408,9 +1439,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) break_time++; /* so that 0 means no break time */ } - for (before = &inode->i_flock; - ((fl = *before) != NULL) && IS_LEASE(fl); - before = &fl->fl_next) { + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (!leases_conflict(fl, new_fl)) continue; if (want_write) { @@ -1419,17 +1448,17 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) fl->fl_flags |= FL_UNLOCK_PENDING; fl->fl_break_time = break_time; } else { - if (lease_breaking(inode->i_flock)) + if (lease_breaking(fl)) continue; fl->fl_flags |= FL_DOWNGRADE_PENDING; fl->fl_downgrade_time = break_time; } if (fl->fl_lmops->lm_break(fl)) - locks_delete_lock(before, &dispose); + locks_delete_lock_ctx(fl, &ctx->flc_lease_cnt, + &dispose); } - fl = inode->i_flock; - if (!fl || !IS_LEASE(fl)) + if (list_empty(&ctx->flc_lease)) goto out; if (mode & O_NONBLOCK) { @@ -1439,18 +1468,19 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) } restart: - break_time = inode->i_flock->fl_break_time; + fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list); + break_time = fl->fl_break_time; if (break_time != 0) break_time -= jiffies; if (break_time == 0) break_time++; - locks_insert_block(inode->i_flock, new_fl); + locks_insert_block(fl, new_fl); trace_break_lease_block(inode, new_fl); - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->fl_wait, !new_fl->fl_next, break_time); - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); locks_delete_block(new_fl); if (error >= 0) { @@ -1462,12 +1492,10 @@ restart: time_out_leases(inode, &dispose); if (any_leases_conflict(inode, new_fl)) goto restart; - error = 0; } - out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); locks_free_lock(new_fl); return error; @@ -1487,14 +1515,18 @@ EXPORT_SYMBOL(__break_lease); void lease_get_mtime(struct inode *inode, struct timespec *time) { bool has_lease = false; - struct file_lock *flock; + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl; - if (inode->i_flock) { - spin_lock(&inode->i_lock); - flock = inode->i_flock; - if (flock && IS_LEASE(flock) && (flock->fl_type == F_WRLCK)) - has_lease = true; - spin_unlock(&inode->i_lock); + if (ctx && !list_empty_careful(&ctx->flc_lease)) { + spin_lock(&ctx->flc_lock); + if (!list_empty(&ctx->flc_lease)) { + fl = list_first_entry(&ctx->flc_lease, + struct file_lock, fl_list); + if (fl->fl_type == F_WRLCK) + has_lease = true; + } + spin_unlock(&ctx->flc_lock); } if (has_lease) @@ -1532,20 +1564,22 @@ int fcntl_getlease(struct file *filp) { struct file_lock *fl; struct inode *inode = file_inode(filp); + struct file_lock_context *ctx = inode->i_flctx; int type = F_UNLCK; LIST_HEAD(dispose); - spin_lock(&inode->i_lock); - time_out_leases(file_inode(filp), &dispose); - for (fl = file_inode(filp)->i_flock; fl && IS_LEASE(fl); - fl = fl->fl_next) { - if (fl->fl_file == filp) { + if (ctx && !list_empty_careful(&ctx->flc_lease)) { + spin_lock(&ctx->flc_lock); + time_out_leases(file_inode(filp), &dispose); + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { + if (fl->fl_file != filp) + continue; type = target_leasetype(fl); break; } + spin_unlock(&ctx->flc_lock); + locks_dispose_list(&dispose); } - spin_unlock(&inode->i_lock); - locks_dispose_list(&dispose); return type; } @@ -1578,9 +1612,10 @@ check_conflicting_open(const struct dentry *dentry, const long arg) static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv) { - struct file_lock *fl, **before, **my_before = NULL, *lease; + struct file_lock *fl, *my_fl = NULL, *lease; struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; + struct file_lock_context *ctx; bool is_deleg = (*flp)->fl_flags & FL_DELEG; int error; LIST_HEAD(dispose); @@ -1588,6 +1623,10 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr lease = *flp; trace_generic_add_lease(inode, lease); + ctx = locks_get_lock_context(inode); + if (!ctx) + return -ENOMEM; + /* * In the delegation case we need mutual exclusion with * a number of operations that take the i_mutex. We trylock @@ -1606,7 +1645,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr return -EINVAL; } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); error = check_conflicting_open(dentry, arg); if (error) @@ -1621,13 +1660,12 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr * except for this filp. */ error = -EAGAIN; - for (before = &inode->i_flock; - ((fl = *before) != NULL) && IS_LEASE(fl); - before = &fl->fl_next) { + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp) { - my_before = before; + my_fl = fl; continue; } + /* * No exclusive leases if someone else has a lease on * this file: @@ -1642,9 +1680,8 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr goto out; } - if (my_before != NULL) { - lease = *my_before; - error = lease->fl_lmops->lm_change(my_before, arg, &dispose); + if (my_fl != NULL) { + error = lease->fl_lmops->lm_change(my_fl, arg, &dispose); if (error) goto out; goto out_setup; @@ -1654,7 +1691,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr if (!leases_enable) goto out; - locks_insert_lock(before, lease); + locks_insert_lock_ctx(lease, &ctx->flc_lease_cnt, &ctx->flc_lease); /* * The check in break_lease() is lockless. It's possible for another * open to race in after we did the earlier check for a conflicting @@ -1666,45 +1703,49 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr */ smp_mb(); error = check_conflicting_open(dentry, arg); - if (error) - goto out_unlink; + if (error) { + locks_unlink_lock_ctx(lease, &ctx->flc_lease_cnt); + goto out; + } out_setup: if (lease->fl_lmops->lm_setup) lease->fl_lmops->lm_setup(lease, priv); out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); if (is_deleg) mutex_unlock(&inode->i_mutex); - if (!error && !my_before) + if (!error && !my_fl) *flp = NULL; return error; -out_unlink: - locks_unlink_lock(before); - goto out; } static int generic_delete_lease(struct file *filp) { int error = -EAGAIN; - struct file_lock *fl, **before; + struct file_lock *fl, *victim = NULL; struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; + struct file_lock_context *ctx = inode->i_flctx; LIST_HEAD(dispose); - spin_lock(&inode->i_lock); - time_out_leases(inode, &dispose); - for (before = &inode->i_flock; - ((fl = *before) != NULL) && IS_LEASE(fl); - before = &fl->fl_next) { - if (fl->fl_file == filp) + if (!ctx) { + trace_generic_delete_lease(inode, NULL); + return error; + } + + spin_lock(&ctx->flc_lock); + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { + if (fl->fl_file == filp) { + victim = fl; break; + } } trace_generic_delete_lease(inode, fl); - if (fl && IS_LEASE(fl)) - error = fl->fl_lmops->lm_change(before, F_UNLCK, &dispose); - spin_unlock(&inode->i_lock); + if (victim) + error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); return error; } @@ -2171,7 +2212,7 @@ again: */ /* * we need that spin_lock here - it prevents reordering between - * update of inode->i_flock and check for it done in close(). + * update of i_flctx->flc_posix and check for it done in close(). * rcu_read_lock() wouldn't do. */ spin_lock(¤t->files->file_lock); @@ -2331,13 +2372,14 @@ out: void locks_remove_posix(struct file *filp, fl_owner_t owner) { struct file_lock lock; + struct file_lock_context *ctx = file_inode(filp)->i_flctx; /* * If there are no locks held on this file, we don't need to call * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ - if (!file_inode(filp)->i_flock) + if (!ctx || list_empty(&ctx->flc_posix)) return; lock.fl_type = F_UNLCK; @@ -2358,67 +2400,67 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner) EXPORT_SYMBOL(locks_remove_posix); +/* The i_flctx must be valid when calling into here */ +static void +locks_remove_flock(struct file *filp) +{ + struct file_lock fl = { + .fl_owner = filp, + .fl_pid = current->tgid, + .fl_file = filp, + .fl_flags = FL_FLOCK, + .fl_type = F_UNLCK, + .fl_end = OFFSET_MAX, + }; + struct file_lock_context *flctx = file_inode(filp)->i_flctx; + + if (list_empty(&flctx->flc_flock)) + return; + + if (filp->f_op->flock) + filp->f_op->flock(filp, F_SETLKW, &fl); + else + flock_lock_file(filp, &fl); + + if (fl.fl_ops && fl.fl_ops->fl_release_private) + fl.fl_ops->fl_release_private(&fl); +} + +/* The i_flctx must be valid when calling into here */ +static void +locks_remove_lease(struct file *filp) +{ + struct inode *inode = file_inode(filp); + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl, *tmp; + LIST_HEAD(dispose); + + if (list_empty(&ctx->flc_lease)) + return; + + spin_lock(&ctx->flc_lock); + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) + lease_modify(fl, F_UNLCK, &dispose); + spin_unlock(&ctx->flc_lock); + locks_dispose_list(&dispose); +} + /* * This function is called on the last close of an open file. */ void locks_remove_file(struct file *filp) { - struct inode * inode = file_inode(filp); - struct file_lock *fl; - struct file_lock **before; - LIST_HEAD(dispose); - - if (!inode->i_flock) + if (!file_inode(filp)->i_flctx) return; + /* remove any OFD locks */ locks_remove_posix(filp, filp); - if (filp->f_op->flock) { - struct file_lock fl = { - .fl_owner = filp, - .fl_pid = current->tgid, - .fl_file = filp, - .fl_flags = FL_FLOCK, - .fl_type = F_UNLCK, - .fl_end = OFFSET_MAX, - }; - filp->f_op->flock(filp, F_SETLKW, &fl); - if (fl.fl_ops && fl.fl_ops->fl_release_private) - fl.fl_ops->fl_release_private(&fl); - } - - spin_lock(&inode->i_lock); - before = &inode->i_flock; - - while ((fl = *before) != NULL) { - if (fl->fl_file == filp) { - if (IS_LEASE(fl)) { - lease_modify(before, F_UNLCK, &dispose); - continue; - } - - /* - * There's a leftover lock on the list of a type that - * we didn't expect to see. Most likely a classic - * POSIX lock that ended up not getting released - * properly, or that raced onto the list somehow. Log - * some info about it and then just remove it from - * the list. - */ - WARN(!IS_FLOCK(fl), - "leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n", - MAJOR(inode->i_sb->s_dev), - MINOR(inode->i_sb->s_dev), inode->i_ino, - fl->fl_type, fl->fl_flags, - fl->fl_start, fl->fl_end); + /* remove flock locks */ + locks_remove_flock(filp); - locks_delete_lock(before, &dispose); - continue; - } - before = &fl->fl_next; - } - spin_unlock(&inode->i_lock); - locks_dispose_list(&dispose); + /* remove any leases */ + locks_remove_lease(filp); } /** @@ -2621,6 +2663,9 @@ static int __init filelock_init(void) { int i; + flctx_cache = kmem_cache_create("file_lock_ctx", + sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL); + filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL); diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 7f3f6064134..8cdb2b28a10 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -85,25 +85,30 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ { struct inode *inode = state->inode; struct file_lock *fl; + struct file_lock_context *flctx = inode->i_flctx; + struct list_head *list; int status = 0; - if (inode->i_flock == NULL) + if (flctx == NULL) goto out; - /* Protect inode->i_flock using the i_lock */ - spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { - if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK))) - continue; + list = &flctx->flc_posix; + spin_lock(&flctx->flc_lock); +restart: + list_for_each_entry(fl, list, fl_list) { if (nfs_file_open_context(fl->fl_file) != ctx) continue; - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); status = nfs4_lock_delegation_recall(fl, state, stateid); if (status < 0) goto out; - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); } - spin_unlock(&inode->i_lock); + if (list == &flctx->flc_posix) { + list = &flctx->flc_flock; + goto restart; + } + spin_unlock(&flctx->flc_lock); out: return status; } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 2ab6f00dba5..94712fc781f 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -646,7 +646,6 @@ static const struct vm_operations_struct nfs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = nfs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int nfs_need_sync_write(struct file *filp, struct inode *inode) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 5194933ed41..a3bb22ab68c 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1366,49 +1366,55 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ struct nfs_inode *nfsi = NFS_I(inode); struct file_lock *fl; int status = 0; + struct file_lock_context *flctx = inode->i_flctx; + struct list_head *list; - if (inode->i_flock == NULL) + if (flctx == NULL) return 0; + list = &flctx->flc_posix; + /* Guard against delegation returns and new lock/unlock calls */ down_write(&nfsi->rwsem); - /* Protect inode->i_flock using the BKL */ - spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { - if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK))) - continue; + spin_lock(&flctx->flc_lock); +restart: + list_for_each_entry(fl, list, fl_list) { if (nfs_file_open_context(fl->fl_file)->state != state) continue; - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); status = ops->recover_lock(state, fl); switch (status) { - case 0: - break; - case -ESTALE: - case -NFS4ERR_ADMIN_REVOKED: - case -NFS4ERR_STALE_STATEID: - case -NFS4ERR_BAD_STATEID: - case -NFS4ERR_EXPIRED: - case -NFS4ERR_NO_GRACE: - case -NFS4ERR_STALE_CLIENTID: - case -NFS4ERR_BADSESSION: - case -NFS4ERR_BADSLOT: - case -NFS4ERR_BAD_HIGH_SLOT: - case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: - goto out; - default: - printk(KERN_ERR "NFS: %s: unhandled error %d\n", - __func__, status); - case -ENOMEM: - case -NFS4ERR_DENIED: - case -NFS4ERR_RECLAIM_BAD: - case -NFS4ERR_RECLAIM_CONFLICT: - /* kill_proc(fl->fl_pid, SIGLOST, 1); */ - status = 0; + case 0: + break; + case -ESTALE: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_EXPIRED: + case -NFS4ERR_NO_GRACE: + case -NFS4ERR_STALE_CLIENTID: + case -NFS4ERR_BADSESSION: + case -NFS4ERR_BADSLOT: + case -NFS4ERR_BAD_HIGH_SLOT: + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + goto out; + default: + pr_err("NFS: %s: unhandled error %d\n", + __func__, status); + case -ENOMEM: + case -NFS4ERR_DENIED: + case -NFS4ERR_RECLAIM_BAD: + case -NFS4ERR_RECLAIM_CONFLICT: + /* kill_proc(fl->fl_pid, SIGLOST, 1); */ + status = 0; } - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); } - spin_unlock(&inode->i_lock); + if (list == &flctx->flc_posix) { + list = &flctx->flc_flock; + goto restart; + } + spin_unlock(&flctx->flc_lock); out: up_write(&nfsi->rwsem); return status; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 2b5e769beb1..29c7f33c9cf 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -826,11 +826,15 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev, struct nfs_pageio_descriptor *pgio) { size_t size; + struct file_lock_context *flctx; if (prev) { if (!nfs_match_open_context(req->wb_context, prev->wb_context)) return false; - if (req->wb_context->dentry->d_inode->i_flock != NULL && + flctx = req->wb_context->dentry->d_inode->i_flctx; + if (flctx != NULL && + !(list_empty_careful(&flctx->flc_posix) && + list_empty_careful(&flctx->flc_flock)) && !nfs_match_lock_context(req->wb_lock_context, prev->wb_lock_context)) return false; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index af3af685a9e..4ae66f416eb 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1091,6 +1091,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page) { struct nfs_open_context *ctx = nfs_file_open_context(file); struct nfs_lock_context *l_ctx; + struct file_lock_context *flctx = file_inode(file)->i_flctx; struct nfs_page *req; int do_flush, status; /* @@ -1109,7 +1110,9 @@ int nfs_flush_incompatible(struct file *file, struct page *page) do_flush = req->wb_page != page || req->wb_context != ctx; /* for now, flush if more than 1 request in page_group */ do_flush |= req->wb_this_page != req; - if (l_ctx && ctx->dentry->d_inode->i_flock != NULL) { + if (l_ctx && flctx && + !(list_empty_careful(&flctx->flc_posix) && + list_empty_careful(&flctx->flc_flock))) { do_flush |= l_ctx->lockowner.l_owner != current->files || l_ctx->lockowner.l_pid != current->tgid; } @@ -1170,6 +1173,13 @@ out: return PageUptodate(page) != 0; } +static bool +is_whole_file_wrlock(struct file_lock *fl) +{ + return fl->fl_start == 0 && fl->fl_end == OFFSET_MAX && + fl->fl_type == F_WRLCK; +} + /* If we know the page is up to date, and we're not using byte range locks (or * if we have the whole file locked for writing), it may be more efficient to * extend the write to cover the entire page in order to avoid fragmentation @@ -1180,17 +1190,36 @@ out: */ static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode) { + int ret; + struct file_lock_context *flctx = inode->i_flctx; + struct file_lock *fl; + if (file->f_flags & O_DSYNC) return 0; if (!nfs_write_pageuptodate(page, inode)) return 0; if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) return 1; - if (inode->i_flock == NULL || (inode->i_flock->fl_start == 0 && - inode->i_flock->fl_end == OFFSET_MAX && - inode->i_flock->fl_type != F_RDLCK)) - return 1; - return 0; + if (!flctx || (list_empty_careful(&flctx->flc_flock) && + list_empty_careful(&flctx->flc_posix))) + return 0; + + /* Check to see if there are whole file write locks */ + ret = 0; + spin_lock(&flctx->flc_lock); + if (!list_empty(&flctx->flc_posix)) { + fl = list_first_entry(&flctx->flc_posix, struct file_lock, + fl_list); + if (is_whole_file_wrlock(fl)) + ret = 1; + } else if (!list_empty(&flctx->flc_flock)) { + fl = list_first_entry(&flctx->flc_flock, struct file_lock, + fl_list); + if (fl->fl_type == F_WRLCK) + ret = 1; + } + spin_unlock(&flctx->flc_lock); + return ret; } /* diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c06a1ba80d7..532a60cca2f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3477,7 +3477,8 @@ nfsd_break_deleg_cb(struct file_lock *fl) } static int -nfsd_change_deleg_cb(struct file_lock **onlist, int arg, struct list_head *dispose) +nfsd_change_deleg_cb(struct file_lock *onlist, int arg, + struct list_head *dispose) { if (arg & F_UNLCK) return lease_modify(onlist, arg, dispose); @@ -5556,10 +5557,11 @@ out_nfserr: static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) { - struct file_lock **flpp; + struct file_lock *fl; int status = false; struct file *filp = find_any_file(fp); struct inode *inode; + struct file_lock_context *flctx; if (!filp) { /* Any valid lock stateid should have some sort of access */ @@ -5568,15 +5570,18 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) } inode = file_inode(filp); + flctx = inode->i_flctx; - spin_lock(&inode->i_lock); - for (flpp = &inode->i_flock; *flpp != NULL; flpp = &(*flpp)->fl_next) { - if ((*flpp)->fl_owner == (fl_owner_t)lowner) { - status = true; - break; + if (flctx && !list_empty_careful(&flctx->flc_posix)) { + spin_lock(&flctx->flc_lock); + list_for_each_entry(fl, &flctx->flc_posix, fl_list) { + if (fl->fl_owner == (fl_owner_t)lowner) { + status = true; + break; + } } + spin_unlock(&flctx->flc_lock); } - spin_unlock(&inode->i_lock); fput(filp); return status; } diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 3a03e0aea1f..a8c728acb7a 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -128,7 +128,6 @@ static const struct vm_operations_struct nilfs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = nilfs_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 91093cd74f0..38570402757 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -141,7 +141,6 @@ enum { * @ti_save: Backup of journal_info field of task_struct * @ti_flags: Flags * @ti_count: Nest level - * @ti_garbage: List of inode to be put when releasing semaphore */ struct nilfs_transaction_info { u32 ti_magic; @@ -150,7 +149,6 @@ struct nilfs_transaction_info { one of other filesystems has a bug. */ unsigned short ti_flags; unsigned short ti_count; - struct list_head ti_garbage; }; /* ti_magic */ diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 7ef18fc656c..469086b9f99 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -305,7 +305,6 @@ static void nilfs_transaction_lock(struct super_block *sb, ti->ti_count = 0; ti->ti_save = cur_ti; ti->ti_magic = NILFS_TI_MAGIC; - INIT_LIST_HEAD(&ti->ti_garbage); current->journal_info = ti; for (;;) { @@ -332,8 +331,6 @@ static void nilfs_transaction_unlock(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); current->journal_info = ti->ti_save; - if (!list_empty(&ti->ti_garbage)) - nilfs_dispose_list(nilfs, &ti->ti_garbage, 0); } static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci, @@ -746,6 +743,15 @@ static void nilfs_dispose_list(struct the_nilfs *nilfs, } } +static void nilfs_iput_work_func(struct work_struct *work) +{ + struct nilfs_sc_info *sci = container_of(work, struct nilfs_sc_info, + sc_iput_work); + struct the_nilfs *nilfs = sci->sc_super->s_fs_info; + + nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 0); +} + static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs, struct nilfs_root *root) { @@ -1900,8 +1906,8 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci, static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, struct the_nilfs *nilfs) { - struct nilfs_transaction_info *ti = current->journal_info; struct nilfs_inode_info *ii, *n; + int defer_iput = false; spin_lock(&nilfs->ns_inode_lock); list_for_each_entry_safe(ii, n, &sci->sc_dirty_files, i_dirty) { @@ -1912,9 +1918,24 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, clear_bit(NILFS_I_BUSY, &ii->i_state); brelse(ii->i_bh); ii->i_bh = NULL; - list_move_tail(&ii->i_dirty, &ti->ti_garbage); + list_del_init(&ii->i_dirty); + if (!ii->vfs_inode.i_nlink) { + /* + * Defer calling iput() to avoid a deadlock + * over I_SYNC flag for inodes with i_nlink == 0 + */ + list_add_tail(&ii->i_dirty, &sci->sc_iput_queue); + defer_iput = true; + } else { + spin_unlock(&nilfs->ns_inode_lock); + iput(&ii->vfs_inode); + spin_lock(&nilfs->ns_inode_lock); + } } spin_unlock(&nilfs->ns_inode_lock); + + if (defer_iput) + schedule_work(&sci->sc_iput_work); } /* @@ -2583,6 +2604,8 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb, INIT_LIST_HEAD(&sci->sc_segbufs); INIT_LIST_HEAD(&sci->sc_write_logs); INIT_LIST_HEAD(&sci->sc_gc_inodes); + INIT_LIST_HEAD(&sci->sc_iput_queue); + INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func); init_timer(&sci->sc_timer); sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT; @@ -2609,6 +2632,8 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci) ret = nilfs_segctor_construct(sci, SC_LSEG_SR); nilfs_transaction_unlock(sci->sc_super); + flush_work(&sci->sc_iput_work); + } while (ret && retrycount-- > 0); } @@ -2633,6 +2658,9 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) || sci->sc_seq_request != sci->sc_seq_done); spin_unlock(&sci->sc_state_lock); + if (flush_work(&sci->sc_iput_work)) + flag = true; + if (flag || !nilfs_segctor_confirm(sci)) nilfs_segctor_write_out(sci); @@ -2642,6 +2670,12 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1); } + if (!list_empty(&sci->sc_iput_queue)) { + nilfs_warning(sci->sc_super, __func__, + "iput queue is not empty\n"); + nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1); + } + WARN_ON(!list_empty(&sci->sc_segbufs)); WARN_ON(!list_empty(&sci->sc_write_logs)); diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index 38a1d001331..a48d6de1e02 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -26,6 +26,7 @@ #include <linux/types.h> #include <linux/fs.h> #include <linux/buffer_head.h> +#include <linux/workqueue.h> #include <linux/nilfs2_fs.h> #include "nilfs.h" @@ -92,6 +93,8 @@ struct nilfs_segsum_pointer { * @sc_nblk_inc: Block count of current generation * @sc_dirty_files: List of files to be written * @sc_gc_inodes: List of GC inodes having blocks to be written + * @sc_iput_queue: list of inodes for which iput should be done + * @sc_iput_work: work struct to defer iput call * @sc_freesegs: array of segment numbers to be freed * @sc_nfreesegs: number of segments on @sc_freesegs * @sc_dsync_inode: inode whose data pages are written for a sync operation @@ -135,6 +138,8 @@ struct nilfs_sc_info { struct list_head sc_dirty_files; struct list_head sc_gc_inodes; + struct list_head sc_iput_queue; + struct work_struct sc_iput_work; __u64 *sc_freesegs; size_t sc_nfreesegs; diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig index 22c629eedd8..2a24249b30a 100644 --- a/fs/notify/Kconfig +++ b/fs/notify/Kconfig @@ -1,5 +1,6 @@ config FSNOTIFY def_bool n + select SRCU source "fs/notify/dnotify/Kconfig" source "fs/notify/inotify/Kconfig" diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 30d3addfad7..51ceb810728 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -140,7 +140,7 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark, } if (S_ISDIR(path->dentry->d_inode->i_mode) && - (marks_ignored_mask & FS_ISDIR)) + !(marks_mask & FS_ISDIR & ~marks_ignored_mask)) return false; if (event_mask & marks_mask & ~marks_ignored_mask) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index bff8567aa42..cf275500a66 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -487,20 +487,27 @@ static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark, unsigned int flags, int *destroy) { - __u32 oldmask; + __u32 oldmask = 0; spin_lock(&fsn_mark->lock); if (!(flags & FAN_MARK_IGNORED_MASK)) { + __u32 tmask = fsn_mark->mask & ~mask; + + if (flags & FAN_MARK_ONDIR) + tmask &= ~FAN_ONDIR; + oldmask = fsn_mark->mask; - fsnotify_set_mark_mask_locked(fsn_mark, (oldmask & ~mask)); + fsnotify_set_mark_mask_locked(fsn_mark, tmask); } else { - oldmask = fsn_mark->ignored_mask; - fsnotify_set_mark_ignored_mask_locked(fsn_mark, (oldmask & ~mask)); + __u32 tmask = fsn_mark->ignored_mask & ~mask; + if (flags & FAN_MARK_ONDIR) + tmask &= ~FAN_ONDIR; + + fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask); } + *destroy = !(fsn_mark->mask | fsn_mark->ignored_mask); spin_unlock(&fsn_mark->lock); - *destroy = !(oldmask & ~mask); - return mask & oldmask; } @@ -569,20 +576,22 @@ static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark, spin_lock(&fsn_mark->lock); if (!(flags & FAN_MARK_IGNORED_MASK)) { + __u32 tmask = fsn_mark->mask | mask; + + if (flags & FAN_MARK_ONDIR) + tmask |= FAN_ONDIR; + oldmask = fsn_mark->mask; - fsnotify_set_mark_mask_locked(fsn_mark, (oldmask | mask)); + fsnotify_set_mark_mask_locked(fsn_mark, tmask); } else { __u32 tmask = fsn_mark->ignored_mask | mask; + if (flags & FAN_MARK_ONDIR) + tmask |= FAN_ONDIR; + fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask); if (flags & FAN_MARK_IGNORED_SURV_MODIFY) fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY; } - - if (!(flags & FAN_MARK_ONDIR)) { - __u32 tmask = fsn_mark->ignored_mask | FAN_ONDIR; - fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask); - } - spin_unlock(&fsn_mark->lock); return mask & ~oldmask; diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 7e8282dcea2..c58a1bcfda0 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -245,16 +245,14 @@ int ocfs2_set_acl(handle_t *handle, ret = posix_acl_equiv_mode(acl, &mode); if (ret < 0) return ret; - else { - if (ret == 0) - acl = NULL; - ret = ocfs2_acl_set_mode(inode, di_bh, - handle, mode); - if (ret) - return ret; + if (ret == 0) + acl = NULL; - } + ret = ocfs2_acl_set_mode(inode, di_bh, + handle, mode); + if (ret) + return ret; } break; case ACL_TYPE_DEFAULT: diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index fcae9ef1a32..044158bd22b 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -6873,7 +6873,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); - goto out_unlock; + goto out; } ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh, @@ -6931,7 +6931,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, if (ret) { mlog_errno(ret); need_free = 1; - goto out_commit; + goto out_unlock; } page_end = PAGE_CACHE_SIZE; @@ -6964,12 +6964,16 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, if (ret) { mlog_errno(ret); need_free = 1; - goto out_commit; + goto out_unlock; } inode->i_blocks = ocfs2_inode_sector_count(inode); } +out_unlock: + if (pages) + ocfs2_unlock_and_free_pages(pages, num_pages); + out_commit: if (ret < 0 && did_quota) dquot_free_space_nodirty(inode, @@ -6989,15 +6993,11 @@ out_commit: ocfs2_commit_trans(osb, handle); -out_unlock: +out: if (data_ac) ocfs2_free_alloc_context(data_ac); - -out: - if (pages) { - ocfs2_unlock_and_free_pages(pages, num_pages); + if (pages) kfree(pages); - } return ret; } diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 2e355e0f833..56c403a563b 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1016,7 +1016,8 @@ void o2net_fill_node_map(unsigned long *map, unsigned bytes) memset(map, 0, bytes); for (node = 0; node < O2NM_MAX_NODES; ++node) { - o2net_tx_can_proceed(o2net_nn_from_num(node), &sc, &ret); + if (!o2net_tx_can_proceed(o2net_nn_from_num(node), &sc, &ret)) + continue; if (!ret) { set_bit(node, map); sc_put(sc); diff --git a/fs/ocfs2/cluster/tcp_internal.h b/fs/ocfs2/cluster/tcp_internal.h index dc024367110..b95e7df5b76 100644 --- a/fs/ocfs2/cluster/tcp_internal.h +++ b/fs/ocfs2/cluster/tcp_internal.h @@ -107,12 +107,12 @@ struct o2net_node { struct list_head nn_status_list; /* connects are attempted from when heartbeat comes up until either hb - * goes down, the node is unconfigured, no connect attempts succeed - * before O2NET_CONN_IDLE_DELAY, or a connect succeeds. connect_work - * is queued from set_nn_state both from hb up and from itself if a - * connect attempt fails and so can be self-arming. shutdown is - * careful to first mark the nn such that no connects will be attempted - * before canceling delayed connect work and flushing the queue. */ + * goes down, the node is unconfigured, or a connect succeeds. + * connect_work is queued from set_nn_state both from hb up and from + * itself if a connect attempt fails and so can be self-arming. + * shutdown is careful to first mark the nn such that no connects will + * be attempted before canceling delayed connect work and flushing the + * queue. */ struct delayed_work nn_connect_work; unsigned long nn_last_connect_attempt; diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 319e786175a..b08050bd3f2 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -3456,10 +3456,8 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name, int blocksize = dir->i_sb->s_blocksize; status = ocfs2_read_dir_block(dir, 0, &bh, 0); - if (status) { - mlog_errno(status); + if (status) goto bail; - } rec_len = OCFS2_DIR_REC_LEN(namelen); offset = 0; @@ -3480,10 +3478,9 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name, status = ocfs2_read_dir_block(dir, offset >> sb->s_blocksize_bits, &bh, 0); - if (status) { - mlog_errno(status); + if (status) goto bail; - } + /* move to next block */ de = (struct ocfs2_dir_entry *) bh->b_data; } @@ -3513,7 +3510,6 @@ next: de = (struct ocfs2_dir_entry *)((char *) de + le16_to_cpu(de->rec_len)); } - status = 0; bail: brelse(bh); if (status) diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c index b46278f9ae4..fd6bbbbd7d7 100644 --- a/fs/ocfs2/dlm/dlmast.c +++ b/fs/ocfs2/dlm/dlmast.c @@ -385,8 +385,12 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data, head = &res->granted; list_for_each_entry(lock, head, list) { - if (lock->ml.cookie == cookie) + /* if lock is found but unlock is pending ignore the bast */ + if (lock->ml.cookie == cookie) { + if (lock->unlock_pending) + break; goto do_ast; + } } mlog(0, "Got %sast for unknown lock! cookie=%u:%llu, name=%.*s, " diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index 149eb556b8c..825136070d2 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -406,7 +406,7 @@ static int debug_purgelist_print(struct dlm_ctxt *dlm, char *buf, int len) } spin_unlock(&dlm->spinlock); - out += snprintf(buf + out, len - out, "Total on list: %ld\n", total); + out += snprintf(buf + out, len - out, "Total on list: %lu\n", total); return out; } @@ -464,7 +464,7 @@ static int debug_mle_print(struct dlm_ctxt *dlm, char *buf, int len) spin_unlock(&dlm->master_lock); out += snprintf(buf + out, len - out, - "Total: %ld, Longest: %ld\n", total, longest); + "Total: %lu, Longest: %lu\n", total, longest); return out; } diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 50a59d2337b..7df88a6dd62 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -674,20 +674,6 @@ static void dlm_leave_domain(struct dlm_ctxt *dlm) spin_unlock(&dlm->spinlock); } -int dlm_joined(struct dlm_ctxt *dlm) -{ - int ret = 0; - - spin_lock(&dlm_domain_lock); - - if (dlm->dlm_state == DLM_CTXT_JOINED) - ret = 1; - - spin_unlock(&dlm_domain_lock); - - return ret; -} - int dlm_shutting_down(struct dlm_ctxt *dlm) { int ret = 0; diff --git a/fs/ocfs2/dlm/dlmdomain.h b/fs/ocfs2/dlm/dlmdomain.h index 2f7f60bfeb3..fd6122a38db 100644 --- a/fs/ocfs2/dlm/dlmdomain.h +++ b/fs/ocfs2/dlm/dlmdomain.h @@ -28,7 +28,6 @@ extern spinlock_t dlm_domain_lock; extern struct list_head dlm_domains; -int dlm_joined(struct dlm_ctxt *dlm); int dlm_shutting_down(struct dlm_ctxt *dlm); void dlm_fire_domain_eviction_callbacks(struct dlm_ctxt *dlm, int node_num); diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index cecd875653e..ce12e0b1a31 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1070,6 +1070,9 @@ static void dlm_move_reco_locks_to_list(struct dlm_ctxt *dlm, dead_node, dlm->name); list_del_init(&lock->list); dlm_lock_put(lock); + /* Can't schedule DLM_UNLOCK_FREE_LOCK + * - do manually */ + dlm_lock_put(lock); break; } } @@ -2346,6 +2349,10 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) dead_node, dlm->name); list_del_init(&lock->list); dlm_lock_put(lock); + /* Can't schedule + * DLM_UNLOCK_FREE_LOCK + * - do manually */ + dlm_lock_put(lock); break; } } diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 1c423af04c6..11849a44dc5 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3750,6 +3750,9 @@ static int ocfs2_dentry_convert_worker(struct ocfs2_lock_res *lockres, break; spin_unlock(&dentry_attach_lock); + if (S_ISDIR(dl->dl_inode->i_mode)) + shrink_dcache_parent(dentry); + mlog(0, "d_delete(%pd);\n", dentry); /* diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 3950693dd0f..245db4f504d 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -569,7 +569,7 @@ static int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start, handle_t *handle = NULL; struct ocfs2_alloc_context *data_ac = NULL; struct ocfs2_alloc_context *meta_ac = NULL; - enum ocfs2_alloc_restarted why; + enum ocfs2_alloc_restarted why = RESTART_NONE; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_extent_tree et; int did_quota = 0; diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 4f502382180..d10860fde16 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1447,7 +1447,6 @@ bail: * requires that we call do_exit(). And it isn't exported, but * complete_and_exit() seems to be a minimal wrapper around it. */ complete_and_exit(NULL, status); - return status; } void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num) diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 10d66c75cec..9581d190f6e 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -173,7 +173,6 @@ out: static const struct vm_operations_struct ocfs2_file_vm_ops = { .fault = ocfs2_fault, .page_mkwrite = ocfs2_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; int ocfs2_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 7d6b7d09045..fdbcbfed529 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -279,6 +279,8 @@ enum ocfs2_mount_options writes */ OCFS2_MOUNT_HB_NONE = 1 << 13, /* No heartbeat */ OCFS2_MOUNT_HB_GLOBAL = 1 << 14, /* Global heartbeat */ + + OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15, /* Journal Async Commit */ }; #define OCFS2_OSB_SOFT_RO 0x0001 diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h index 1eae330193a..b6d51333ad0 100644 --- a/fs/ocfs2/quota.h +++ b/fs/ocfs2/quota.h @@ -48,6 +48,7 @@ struct ocfs2_quota_recovery { /* In-memory structure with quota header information */ struct ocfs2_mem_dqinfo { unsigned int dqi_type; /* Quota type this structure describes */ + unsigned int dqi_flags; /* Flags OLQF_* */ unsigned int dqi_chunks; /* Number of chunks in local quota file */ unsigned int dqi_blocks; /* Number of blocks allocated for local quota file */ unsigned int dqi_syncms; /* How often should we sync with other nodes */ diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 10b653930ee..3d0b63d3422 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -73,12 +73,6 @@ static loff_t ol_dqblk_off(struct super_block *sb, int c, int off) ol_dqblk_block_off(sb, c, off); } -/* Compute block number from given offset */ -static inline unsigned int ol_dqblk_file_block(struct super_block *sb, loff_t off) -{ - return off >> sb->s_blocksize_bits; -} - static inline unsigned int ol_dqblk_block_offset(struct super_block *sb, loff_t off) { return off & ((1 << sb->s_blocksize_bits) - 1); @@ -292,7 +286,7 @@ static void olq_update_info(struct buffer_head *bh, void *private) ldinfo = (struct ocfs2_local_disk_dqinfo *)(bh->b_data + OCFS2_LOCAL_INFO_OFF); spin_lock(&dq_data_lock); - ldinfo->dqi_flags = cpu_to_le32(info->dqi_flags & DQF_MASK); + ldinfo->dqi_flags = cpu_to_le32(oinfo->dqi_flags); ldinfo->dqi_chunks = cpu_to_le32(oinfo->dqi_chunks); ldinfo->dqi_blocks = cpu_to_le32(oinfo->dqi_blocks); spin_unlock(&dq_data_lock); @@ -701,8 +695,8 @@ static int ocfs2_local_read_info(struct super_block *sb, int type) /* We don't need the lock and we have to acquire quota file locks * which will later depend on this lock */ mutex_unlock(&sb_dqopt(sb)->dqio_mutex); - info->dqi_maxblimit = 0x7fffffffffffffffLL; - info->dqi_maxilimit = 0x7fffffffffffffffLL; + info->dqi_max_spc_limit = 0x7fffffffffffffffLL; + info->dqi_max_ino_limit = 0x7fffffffffffffffLL; oinfo = kmalloc(sizeof(struct ocfs2_mem_dqinfo), GFP_NOFS); if (!oinfo) { mlog(ML_ERROR, "failed to allocate memory for ocfs2 quota" @@ -737,13 +731,13 @@ static int ocfs2_local_read_info(struct super_block *sb, int type) } ldinfo = (struct ocfs2_local_disk_dqinfo *)(bh->b_data + OCFS2_LOCAL_INFO_OFF); - info->dqi_flags = le32_to_cpu(ldinfo->dqi_flags); + oinfo->dqi_flags = le32_to_cpu(ldinfo->dqi_flags); oinfo->dqi_chunks = le32_to_cpu(ldinfo->dqi_chunks); oinfo->dqi_blocks = le32_to_cpu(ldinfo->dqi_blocks); oinfo->dqi_libh = bh; /* We crashed when using local quota file? */ - if (!(info->dqi_flags & OLQF_CLEAN)) { + if (!(oinfo->dqi_flags & OLQF_CLEAN)) { rec = OCFS2_SB(sb)->quota_rec; if (!rec) { rec = ocfs2_alloc_quota_recovery(); @@ -772,7 +766,7 @@ static int ocfs2_local_read_info(struct super_block *sb, int type) } /* Now mark quota file as used */ - info->dqi_flags &= ~OLQF_CLEAN; + oinfo->dqi_flags &= ~OLQF_CLEAN; status = ocfs2_modify_bh(lqinode, bh, olq_update_info, info); if (status < 0) { mlog_errno(status); @@ -857,7 +851,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type) goto out; /* Mark local file as clean */ - info->dqi_flags |= OLQF_CLEAN; + oinfo->dqi_flags |= OLQF_CLEAN; status = ocfs2_modify_bh(sb_dqopt(sb)->files[type], oinfo->dqi_libh, olq_update_info, diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index d81f6e2a97f..ee541f92dab 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -2428,8 +2428,6 @@ static int ocfs2_calc_refcount_meta_credits(struct super_block *sb, get_bh(prev_bh); } - rb = (struct ocfs2_refcount_block *)ref_leaf_bh->b_data; - trace_ocfs2_calc_refcount_meta_credits_iterate( recs_add, (unsigned long long)cpos, clusters, (unsigned long long)le64_to_cpu(rec.r_cpos), diff --git a/fs/ocfs2/reservations.c b/fs/ocfs2/reservations.c index 41ffd36c689..6a348b0294a 100644 --- a/fs/ocfs2/reservations.c +++ b/fs/ocfs2/reservations.c @@ -39,7 +39,7 @@ #define OCFS2_CHECK_RESERVATIONS #endif -DEFINE_SPINLOCK(resv_lock); +static DEFINE_SPINLOCK(resv_lock); #define OCFS2_MIN_RESV_WINDOW_BITS 8 #define OCFS2_MAX_RESV_WINDOW_BITS 1024 diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 83723179e1e..87a1f7679d9 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -191,6 +191,7 @@ enum { Opt_coherency_full, Opt_resv_level, Opt_dir_resv_level, + Opt_journal_async_commit, Opt_err, }; @@ -222,6 +223,7 @@ static const match_table_t tokens = { {Opt_coherency_full, "coherency=full"}, {Opt_resv_level, "resv_level=%u"}, {Opt_dir_resv_level, "dir_resv_level=%u"}, + {Opt_journal_async_commit, "journal_async_commit"}, {Opt_err, NULL} }; @@ -1000,36 +1002,6 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb) } } -/* Handle quota on quotactl */ -static int ocfs2_quota_on(struct super_block *sb, int type, int format_id) -{ - unsigned int feature[OCFS2_MAXQUOTAS] = { - OCFS2_FEATURE_RO_COMPAT_USRQUOTA, - OCFS2_FEATURE_RO_COMPAT_GRPQUOTA}; - - if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, feature[type])) - return -EINVAL; - - return dquot_enable(sb_dqopt(sb)->files[type], type, - format_id, DQUOT_LIMITS_ENABLED); -} - -/* Handle quota off quotactl */ -static int ocfs2_quota_off(struct super_block *sb, int type) -{ - return dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); -} - -static const struct quotactl_ops ocfs2_quotactl_ops = { - .quota_on_meta = ocfs2_quota_on, - .quota_off = ocfs2_quota_off, - .quota_sync = dquot_quota_sync, - .get_info = dquot_get_dqinfo, - .set_info = dquot_set_dqinfo, - .get_dqblk = dquot_get_dqblk, - .set_dqblk = dquot_set_dqblk, -}; - static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) { struct dentry *root; @@ -1500,6 +1472,9 @@ static int ocfs2_parse_options(struct super_block *sb, option < OCFS2_MAX_RESV_LEVEL) mopt->dir_resv_level = option; break; + case Opt_journal_async_commit: + mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT; + break; default: mlog(ML_ERROR, "Unrecognized mount option \"%s\" " @@ -1606,6 +1581,9 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root) if (osb->osb_dir_resv_level != osb->osb_resv_level) seq_printf(s, ",dir_resv_level=%d", osb->osb_resv_level); + if (opts & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT) + seq_printf(s, ",journal_async_commit"); + return 0; } @@ -2079,7 +2057,7 @@ static int ocfs2_initialize_super(struct super_block *sb, sb->s_op = &ocfs2_sops; sb->s_d_op = &ocfs2_dentry_ops; sb->s_export_op = &ocfs2_export_ops; - sb->s_qcop = &ocfs2_quotactl_ops; + sb->s_qcop = &dquot_quotactl_sysfile_ops; sb->dq_op = &ocfs2_quota_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; sb->s_xattr = ocfs2_xattr_handlers; @@ -2475,6 +2453,15 @@ static int ocfs2_check_volume(struct ocfs2_super *osb) goto finally; } + if (osb->s_mount_opt & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT) + jbd2_journal_set_features(osb->journal->j_journal, + JBD2_FEATURE_COMPAT_CHECKSUM, 0, + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); + else + jbd2_journal_clear_features(osb->journal->j_journal, + JBD2_FEATURE_COMPAT_CHECKSUM, 0, + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); + if (dirty) { /* recover my local alloc if we didn't unmount cleanly. */ status = ocfs2_begin_local_alloc_recovery(osb, diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 662f8dee149..85b190dc132 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -5334,16 +5334,6 @@ out: return ret; } -static inline char *ocfs2_xattr_bucket_get_val(struct inode *inode, - struct ocfs2_xattr_bucket *bucket, - int offs) -{ - int block_off = offs >> inode->i_sb->s_blocksize_bits; - - offs = offs % inode->i_sb->s_blocksize; - return bucket_block(bucket, block_off) + offs; -} - /* * Truncate the specified xe_off entry in xattr bucket. * bucket is indicated by header_bh and len is the new length. diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 246eae84b13..6396f88c668 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -443,7 +443,6 @@ struct mem_size_stats { unsigned long anonymous; unsigned long anonymous_thp; unsigned long swap; - unsigned long nonlinear; u64 pss; }; @@ -484,7 +483,6 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = mss->vma; - pgoff_t pgoff = linear_page_index(vma, addr); struct page *page = NULL; if (pte_present(*pte)) { @@ -496,17 +494,10 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, mss->swap += PAGE_SIZE; else if (is_migration_entry(swpent)) page = migration_entry_to_page(swpent); - } else if (pte_file(*pte)) { - if (pte_to_pgoff(*pte) != pgoff) - mss->nonlinear += PAGE_SIZE; } if (!page) return; - - if (page->index != pgoff) - mss->nonlinear += PAGE_SIZE; - smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte)); } @@ -596,7 +587,6 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_ACCOUNT)] = "ac", [ilog2(VM_NORESERVE)] = "nr", [ilog2(VM_HUGETLB)] = "ht", - [ilog2(VM_NONLINEAR)] = "nl", [ilog2(VM_ARCH_1)] = "ar", [ilog2(VM_DONTDUMP)] = "dd", #ifdef CONFIG_MEM_SOFT_DIRTY @@ -668,10 +658,6 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) (vma->vm_flags & VM_LOCKED) ? (unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0); - if (vma->vm_flags & VM_NONLINEAR) - seq_printf(m, "Nonlinear: %8lu kB\n", - mss.nonlinear >> 10); - show_smap_vma_flags(m, vma); m_cache_vma(m, vma); return 0; @@ -772,8 +758,6 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY); } else if (is_swap_pte(ptent)) { ptent = pte_swp_clear_soft_dirty(ptent); - } else if (pte_file(ptent)) { - ptent = pte_file_clear_soft_dirty(ptent); } set_pte_at(vma->vm_mm, addr, pte, ptent); diff --git a/fs/quota/Kconfig b/fs/quota/Kconfig index c51df1dd237..4a09975aac9 100644 --- a/fs/quota/Kconfig +++ b/fs/quota/Kconfig @@ -5,6 +5,7 @@ config QUOTA bool "Quota support" select QUOTACTL + select SRCU help If you say Y here, you will be able to set per user limits for disk usage (also called disk quotas). Currently, it works for the diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 69df5b23984..0ccd4ba3a24 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1248,7 +1248,7 @@ static int ignore_hardlimit(struct dquot *dquot) return capable(CAP_SYS_RESOURCE) && (info->dqi_format->qf_fmt_id != QFMT_VFS_OLD || - !(info->dqi_flags & V1_DQF_RSQUASH)); + !(info->dqi_flags & DQF_ROOT_SQUASH)); } /* needs dq_data_lock */ @@ -2385,14 +2385,84 @@ out: } EXPORT_SYMBOL(dquot_quota_on_mount); -static inline qsize_t qbtos(qsize_t blocks) +static int dquot_quota_enable(struct super_block *sb, unsigned int flags) { - return blocks << QIF_DQBLKSIZE_BITS; + int ret; + int type; + struct quota_info *dqopt = sb_dqopt(sb); + + if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) + return -ENOSYS; + /* Accounting cannot be turned on while fs is mounted */ + flags &= ~(FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT); + if (!flags) + return -EINVAL; + for (type = 0; type < MAXQUOTAS; type++) { + if (!(flags & qtype_enforce_flag(type))) + continue; + /* Can't enforce without accounting */ + if (!sb_has_quota_usage_enabled(sb, type)) + return -EINVAL; + ret = dquot_enable(dqopt->files[type], type, + dqopt->info[type].dqi_fmt_id, + DQUOT_LIMITS_ENABLED); + if (ret < 0) + goto out_err; + } + return 0; +out_err: + /* Backout enforcement enablement we already did */ + for (type--; type >= 0; type--) { + if (flags & qtype_enforce_flag(type)) + dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); + } + /* Error code translation for better compatibility with XFS */ + if (ret == -EBUSY) + ret = -EEXIST; + return ret; } -static inline qsize_t stoqb(qsize_t space) +static int dquot_quota_disable(struct super_block *sb, unsigned int flags) { - return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS; + int ret; + int type; + struct quota_info *dqopt = sb_dqopt(sb); + + if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) + return -ENOSYS; + /* + * We don't support turning off accounting via quotactl. In principle + * quota infrastructure can do this but filesystems don't expect + * userspace to be able to do it. + */ + if (flags & + (FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT)) + return -EOPNOTSUPP; + + /* Filter out limits not enabled */ + for (type = 0; type < MAXQUOTAS; type++) + if (!sb_has_quota_limits_enabled(sb, type)) + flags &= ~qtype_enforce_flag(type); + /* Nothing left? */ + if (!flags) + return -EEXIST; + for (type = 0; type < MAXQUOTAS; type++) { + if (flags & qtype_enforce_flag(type)) { + ret = dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); + if (ret < 0) + goto out_err; + } + } + return 0; +out_err: + /* Backout enforcement disabling we already did */ + for (type--; type >= 0; type--) { + if (flags & qtype_enforce_flag(type)) + dquot_enable(dqopt->files[type], type, + dqopt->info[type].dqi_fmt_id, + DQUOT_LIMITS_ENABLED); + } + return ret; } /* Generic routine for getting common part of quota structure */ @@ -2444,13 +2514,13 @@ static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di) return -EINVAL; if (((di->d_fieldmask & QC_SPC_SOFT) && - stoqb(di->d_spc_softlimit) > dqi->dqi_maxblimit) || + di->d_spc_softlimit > dqi->dqi_max_spc_limit) || ((di->d_fieldmask & QC_SPC_HARD) && - stoqb(di->d_spc_hardlimit) > dqi->dqi_maxblimit) || + di->d_spc_hardlimit > dqi->dqi_max_spc_limit) || ((di->d_fieldmask & QC_INO_SOFT) && - (di->d_ino_softlimit > dqi->dqi_maxilimit)) || + (di->d_ino_softlimit > dqi->dqi_max_ino_limit)) || ((di->d_fieldmask & QC_INO_HARD) && - (di->d_ino_hardlimit > dqi->dqi_maxilimit))) + (di->d_ino_hardlimit > dqi->dqi_max_ino_limit))) return -ERANGE; spin_lock(&dq_data_lock); @@ -2577,6 +2647,14 @@ int dquot_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii) goto out; } mi = sb_dqopt(sb)->info + type; + if (ii->dqi_valid & IIF_FLAGS) { + if (ii->dqi_flags & ~DQF_SETINFO_MASK || + (ii->dqi_flags & DQF_ROOT_SQUASH && + mi->dqi_format->qf_fmt_id != QFMT_VFS_OLD)) { + err = -EINVAL; + goto out; + } + } spin_lock(&dq_data_lock); if (ii->dqi_valid & IIF_BGRACE) mi->dqi_bgrace = ii->dqi_bgrace; @@ -2606,6 +2684,17 @@ const struct quotactl_ops dquot_quotactl_ops = { }; EXPORT_SYMBOL(dquot_quotactl_ops); +const struct quotactl_ops dquot_quotactl_sysfile_ops = { + .quota_enable = dquot_quota_enable, + .quota_disable = dquot_quota_disable, + .quota_sync = dquot_quota_sync, + .get_info = dquot_get_dqinfo, + .set_info = dquot_set_dqinfo, + .get_dqblk = dquot_get_dqblk, + .set_dqblk = dquot_set_dqblk +}; +EXPORT_SYMBOL(dquot_quotactl_sysfile_ops); + static int do_proc_dqstats(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 6f3856328ee..d14a799c778 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -66,18 +66,40 @@ static int quota_sync_all(int type) return ret; } +unsigned int qtype_enforce_flag(int type) +{ + switch (type) { + case USRQUOTA: + return FS_QUOTA_UDQ_ENFD; + case GRPQUOTA: + return FS_QUOTA_GDQ_ENFD; + case PRJQUOTA: + return FS_QUOTA_PDQ_ENFD; + } + return 0; +} + static int quota_quotaon(struct super_block *sb, int type, int cmd, qid_t id, struct path *path) { - if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_on_meta) + if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_enable) return -ENOSYS; - if (sb->s_qcop->quota_on_meta) - return sb->s_qcop->quota_on_meta(sb, type, id); + if (sb->s_qcop->quota_enable) + return sb->s_qcop->quota_enable(sb, qtype_enforce_flag(type)); if (IS_ERR(path)) return PTR_ERR(path); return sb->s_qcop->quota_on(sb, type, id, path); } +static int quota_quotaoff(struct super_block *sb, int type) +{ + if (!sb->s_qcop->quota_off && !sb->s_qcop->quota_disable) + return -ENOSYS; + if (sb->s_qcop->quota_disable) + return sb->s_qcop->quota_disable(sb, qtype_enforce_flag(type)); + return sb->s_qcop->quota_off(sb, type); +} + static int quota_getfmt(struct super_block *sb, int type, void __user *addr) { __u32 fmt; @@ -208,15 +230,26 @@ static int quota_setquota(struct super_block *sb, int type, qid_t id, return sb->s_qcop->set_dqblk(sb, qid, &fdq); } -static int quota_setxstate(struct super_block *sb, int cmd, void __user *addr) +static int quota_enable(struct super_block *sb, void __user *addr) { __u32 flags; if (copy_from_user(&flags, addr, sizeof(flags))) return -EFAULT; - if (!sb->s_qcop->set_xstate) + if (!sb->s_qcop->quota_enable) return -ENOSYS; - return sb->s_qcop->set_xstate(sb, flags, cmd); + return sb->s_qcop->quota_enable(sb, flags); +} + +static int quota_disable(struct super_block *sb, void __user *addr) +{ + __u32 flags; + + if (copy_from_user(&flags, addr, sizeof(flags))) + return -EFAULT; + if (!sb->s_qcop->quota_disable) + return -ENOSYS; + return sb->s_qcop->quota_disable(sb, flags); } static int quota_getxstate(struct super_block *sb, void __user *addr) @@ -429,9 +462,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, case Q_QUOTAON: return quota_quotaon(sb, type, cmd, id, path); case Q_QUOTAOFF: - if (!sb->s_qcop->quota_off) - return -ENOSYS; - return sb->s_qcop->quota_off(sb, type); + return quota_quotaoff(sb, type); case Q_GETFMT: return quota_getfmt(sb, type, addr); case Q_GETINFO: @@ -447,8 +478,9 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, return -ENOSYS; return sb->s_qcop->quota_sync(sb, type); case Q_XQUOTAON: + return quota_enable(sb, addr); case Q_XQUOTAOFF: - return quota_setxstate(sb, cmd, addr); + return quota_disable(sb, addr); case Q_XQUOTARM: return quota_rmxquota(sb, addr); case Q_XGETQSTAT: diff --git a/fs/quota/quota_v1.c b/fs/quota/quota_v1.c index 469c6848b32..8fe79beced5 100644 --- a/fs/quota/quota_v1.c +++ b/fs/quota/quota_v1.c @@ -169,8 +169,8 @@ static int v1_read_file_info(struct super_block *sb, int type) } ret = 0; /* limits are stored as unsigned 32-bit data */ - dqopt->info[type].dqi_maxblimit = 0xffffffff; - dqopt->info[type].dqi_maxilimit = 0xffffffff; + dqopt->info[type].dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS; + dqopt->info[type].dqi_max_ino_limit = 0xffffffff; dqopt->info[type].dqi_igrace = dqblk.dqb_itime ? dqblk.dqb_itime : MAX_IQ_TIME; dqopt->info[type].dqi_bgrace = diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index 02751ec695c..9cb10d7197f 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -117,16 +117,17 @@ static int v2_read_file_info(struct super_block *sb, int type) qinfo = info->dqi_priv; if (version == 0) { /* limits are stored as unsigned 32-bit data */ - info->dqi_maxblimit = 0xffffffff; - info->dqi_maxilimit = 0xffffffff; + info->dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS; + info->dqi_max_ino_limit = 0xffffffff; } else { - /* used space is stored as unsigned 64-bit value */ - info->dqi_maxblimit = 0xffffffffffffffffULL; /* 2^64-1 */ - info->dqi_maxilimit = 0xffffffffffffffffULL; + /* used space is stored as unsigned 64-bit value in bytes */ + info->dqi_max_spc_limit = 0xffffffffffffffffULL; /* 2^64-1 */ + info->dqi_max_ino_limit = 0xffffffffffffffffULL; } info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace); info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace); - info->dqi_flags = le32_to_cpu(dinfo.dqi_flags); + /* No flags currently supported */ + info->dqi_flags = 0; qinfo->dqi_sb = sb; qinfo->dqi_type = type; qinfo->dqi_blocks = le32_to_cpu(dinfo.dqi_blocks); @@ -157,7 +158,8 @@ static int v2_write_file_info(struct super_block *sb, int type) info->dqi_flags &= ~DQF_INFO_DIRTY; dinfo.dqi_bgrace = cpu_to_le32(info->dqi_bgrace); dinfo.dqi_igrace = cpu_to_le32(info->dqi_igrace); - dinfo.dqi_flags = cpu_to_le32(info->dqi_flags & DQF_MASK); + /* No flags currently supported */ + dinfo.dqi_flags = cpu_to_le32(0); spin_unlock(&dq_data_lock); dinfo.dqi_blocks = cpu_to_le32(qinfo->dqi_blocks); dinfo.dqi_free_blk = cpu_to_le32(qinfo->dqi_free_blk); diff --git a/fs/read_write.c b/fs/read_write.c index c0805c93b6f..4060691e78f 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -358,7 +358,7 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t return retval; } - if (unlikely(inode->i_flock && mandatory_lock(inode))) { + if (unlikely(inode->i_flctx && mandatory_lock(inode))) { retval = locks_mandatory_area( read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE, inode, file, pos, count); diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 538519ee37d..035e5101144 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1536,7 +1536,6 @@ static const struct vm_operations_struct ubifs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = ubifs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/udf/Kconfig b/fs/udf/Kconfig index 0e0e99bd6bc..c6e17a744c3 100644 --- a/fs/udf/Kconfig +++ b/fs/udf/Kconfig @@ -2,10 +2,12 @@ config UDF_FS tristate "UDF file system support" select CRC_ITU_T help - This is the new file system used on some CD-ROMs and DVDs. Say Y if - you intend to mount DVD discs or CDRW's written in packet mode, or - if written to by other UDF utilities, such as DirectCD. - Please read <file:Documentation/filesystems/udf.txt>. + This is a file system used on some CD-ROMs and DVDs. Since the + file system is supported by multiple operating systems and is more + compatible with standard unix file systems, it is also suitable for + removable USB disks. Say Y if you intend to mount DVD discs or CDRW's + written in packet mode, or if you want to use UDF for removable USB + disks. Please read <file:Documentation/filesystems/udf.txt>. To compile this file system support as a module, choose M here: the module will be called udf. diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 5bc71d9a674..a445d599098 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -750,7 +750,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, /* Are we beyond EOF? */ if (etype == -1) { int ret; - isBeyondEOF = 1; + isBeyondEOF = true; if (count) { if (c) laarr[0] = laarr[1]; @@ -792,7 +792,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, endnum = c + 1; lastblock = 1; } else { - isBeyondEOF = 0; + isBeyondEOF = false; endnum = startnum = ((count > 2) ? 2 : count); /* if the current extent is in position 0, @@ -1288,6 +1288,7 @@ static int udf_read_inode(struct inode *inode, bool hidden_inode) struct kernel_lb_addr *iloc = &iinfo->i_location; unsigned int link_count; unsigned int indirections = 0; + int bs = inode->i_sb->s_blocksize; int ret = -EIO; reread: @@ -1374,38 +1375,35 @@ reread: if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_EFE)) { iinfo->i_efe = 1; iinfo->i_use = 0; - ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize - + ret = udf_alloc_i_data(inode, bs - sizeof(struct extendedFileEntry)); if (ret) goto out; memcpy(iinfo->i_ext.i_data, bh->b_data + sizeof(struct extendedFileEntry), - inode->i_sb->s_blocksize - - sizeof(struct extendedFileEntry)); + bs - sizeof(struct extendedFileEntry)); } else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_FE)) { iinfo->i_efe = 0; iinfo->i_use = 0; - ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize - - sizeof(struct fileEntry)); + ret = udf_alloc_i_data(inode, bs - sizeof(struct fileEntry)); if (ret) goto out; memcpy(iinfo->i_ext.i_data, bh->b_data + sizeof(struct fileEntry), - inode->i_sb->s_blocksize - sizeof(struct fileEntry)); + bs - sizeof(struct fileEntry)); } else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_USE)) { iinfo->i_efe = 0; iinfo->i_use = 1; iinfo->i_lenAlloc = le32_to_cpu( ((struct unallocSpaceEntry *)bh->b_data)-> lengthAllocDescs); - ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize - + ret = udf_alloc_i_data(inode, bs - sizeof(struct unallocSpaceEntry)); if (ret) goto out; memcpy(iinfo->i_ext.i_data, bh->b_data + sizeof(struct unallocSpaceEntry), - inode->i_sb->s_blocksize - - sizeof(struct unallocSpaceEntry)); + bs - sizeof(struct unallocSpaceEntry)); return 0; } @@ -1489,6 +1487,15 @@ reread: } inode->i_generation = iinfo->i_unique; + /* + * Sanity check length of allocation descriptors and extended attrs to + * avoid integer overflows + */ + if (iinfo->i_lenEAttr > bs || iinfo->i_lenAlloc > bs) + goto out; + /* Now do exact checks */ + if (udf_file_entry_alloc_offset(inode) + iinfo->i_lenAlloc > bs) + goto out; /* Sanity checks for files in ICB so that we don't get confused later */ if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { /* @@ -1498,8 +1505,7 @@ reread: if (iinfo->i_lenAlloc != inode->i_size) goto out; /* File in ICB has to fit in there... */ - if (inode->i_size > inode->i_sb->s_blocksize - - udf_file_entry_alloc_offset(inode)) + if (inode->i_size > bs - udf_file_entry_alloc_offset(inode)) goto out; } diff --git a/fs/udf/super.c b/fs/udf/super.c index 3ccb2f11fc7..f169411c4ea 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1599,7 +1599,7 @@ static noinline int udf_process_sequence( struct udf_vds_record *curr; struct generic_desc *gd; struct volDescPtr *vdp; - int done = 0; + bool done = false; uint32_t vdsn; uint16_t ident; long next_s = 0, next_e = 0; @@ -1680,7 +1680,7 @@ static noinline int udf_process_sequence( lastblock = next_e; next_s = next_e = 0; } else - done = 1; + done = true; break; } brelse(bh); @@ -2300,6 +2300,7 @@ static void udf_put_super(struct super_block *sb) udf_close_lvid(sb); brelse(sbi->s_lvid_bh); udf_sb_free_partitions(sb); + mutex_destroy(&sbi->s_alloc_mutex); kfree(sb->s_fs_info); sb->s_fs_info = NULL; } diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index 53e95b2a136..a7a3a63bb36 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -91,16 +91,6 @@ kmem_zalloc_large(size_t size, xfs_km_flags_t flags) return ptr; } -void -kmem_free(const void *ptr) -{ - if (!is_vmalloc_addr(ptr)) { - kfree(ptr); - } else { - vfree(ptr); - } -} - void * kmem_realloc(const void *ptr, size_t newsize, size_t oldsize, xfs_km_flags_t flags) diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index 64db0e53ede..cc6b768fc06 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -63,7 +63,10 @@ kmem_flags_convert(xfs_km_flags_t flags) extern void *kmem_alloc(size_t, xfs_km_flags_t); extern void *kmem_zalloc_large(size_t size, xfs_km_flags_t); extern void *kmem_realloc(const void *, size_t, size_t, xfs_km_flags_t); -extern void kmem_free(const void *); +static inline void kmem_free(const void *ptr) +{ + kvfree(ptr); +} extern void *kmem_zalloc_greedy(size_t *, size_t, size_t); diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 5d38e8b8a91..15105dbc9e2 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -403,7 +403,7 @@ xfs_sbversion_add_attr2(xfs_mount_t *mp, xfs_trans_t *tp) if (!xfs_sb_version_hasattr2(&mp->m_sb)) { xfs_sb_version_addattr2(&mp->m_sb); spin_unlock(&mp->m_sb_lock); - xfs_mod_sb(tp, XFS_SB_VERSIONNUM | XFS_SB_FEATURES2); + xfs_log_sb(tp); } else spin_unlock(&mp->m_sb_lock); } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index b5eb4743f75..61ec015dca1 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -973,7 +973,11 @@ xfs_bmap_local_to_extents( *firstblock = args.fsbno; bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0); - /* initialise the block and copy the data */ + /* + * Initialise the block and copy the data + * + * Note: init_fn must set the buffer log item type correctly! + */ init_fn(tp, bp, ip, ifp); /* account for the change in fork size and log everything */ @@ -1221,22 +1225,20 @@ xfs_bmap_add_attrfork( goto bmap_cancel; if (!xfs_sb_version_hasattr(&mp->m_sb) || (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) { - __int64_t sbfields = 0; + bool log_sb = false; spin_lock(&mp->m_sb_lock); if (!xfs_sb_version_hasattr(&mp->m_sb)) { xfs_sb_version_addattr(&mp->m_sb); - sbfields |= XFS_SB_VERSIONNUM; + log_sb = true; } if (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2) { xfs_sb_version_addattr2(&mp->m_sb); - sbfields |= (XFS_SB_VERSIONNUM | XFS_SB_FEATURES2); + log_sb = true; } - if (sbfields) { - spin_unlock(&mp->m_sb_lock); - xfs_mod_sb(tp, sbfields); - } else - spin_unlock(&mp->m_sb_lock); + spin_unlock(&mp->m_sb_lock); + if (log_sb) + xfs_log_sb(tp); } error = xfs_bmap_finish(&tp, &flist, &committed); diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 44db6db8640..b9d8a499d2c 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -28,6 +28,37 @@ struct xfs_trans; extern kmem_zone_t *xfs_bmap_free_item_zone; /* + * Argument structure for xfs_bmap_alloc. + */ +struct xfs_bmalloca { + xfs_fsblock_t *firstblock; /* i/o first block allocated */ + struct xfs_bmap_free *flist; /* bmap freelist */ + struct xfs_trans *tp; /* transaction pointer */ + struct xfs_inode *ip; /* incore inode pointer */ + struct xfs_bmbt_irec prev; /* extent before the new one */ + struct xfs_bmbt_irec got; /* extent after, or delayed */ + + xfs_fileoff_t offset; /* offset in file filling in */ + xfs_extlen_t length; /* i/o length asked/allocated */ + xfs_fsblock_t blkno; /* starting block of new extent */ + + struct xfs_btree_cur *cur; /* btree cursor */ + xfs_extnum_t idx; /* current extent index */ + int nallocs;/* number of extents alloc'd */ + int logflags;/* flags for transaction logging */ + + xfs_extlen_t total; /* total blocks needed for xaction */ + xfs_extlen_t minlen; /* minimum allocation size (blocks) */ + xfs_extlen_t minleft; /* amount must be left after alloc */ + bool eof; /* set if allocating past last extent */ + bool wasdel; /* replacing a delayed allocation */ + bool userdata;/* set if is user data */ + bool aeof; /* allocated space at eof */ + bool conv; /* overwriting unwritten extents */ + int flags; +}; + +/* * List of extents to be free "later". * The list is kept sorted on xbf_startblock. */ @@ -149,6 +180,8 @@ void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork); void xfs_bmap_add_free(xfs_fsblock_t bno, xfs_filblks_t len, struct xfs_bmap_free *flist, struct xfs_mount *mp); void xfs_bmap_cancel(struct xfs_bmap_free *flist); +int xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist, + int *committed); void xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork); int xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip, xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork); diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index fbd6da26357..8eb71897938 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -151,10 +151,13 @@ typedef struct xfs_sb { __uint32_t sb_features2; /* additional feature bits */ /* - * bad features2 field as a result of failing to pad the sb - * structure to 64 bits. Some machines will be using this field - * for features2 bits. Easiest just to mark it bad and not use - * it for anything else. + * bad features2 field as a result of failing to pad the sb structure to + * 64 bits. Some machines will be using this field for features2 bits. + * Easiest just to mark it bad and not use it for anything else. + * + * This is not kept up to date in memory; it is always overwritten by + * the value in sb_features2 when formatting the incore superblock to + * the disk buffer. */ __uint32_t sb_bad_features2; @@ -304,8 +307,8 @@ typedef enum { #define XFS_SB_ICOUNT XFS_SB_MVAL(ICOUNT) #define XFS_SB_IFREE XFS_SB_MVAL(IFREE) #define XFS_SB_FDBLOCKS XFS_SB_MVAL(FDBLOCKS) -#define XFS_SB_FEATURES2 XFS_SB_MVAL(FEATURES2) -#define XFS_SB_BAD_FEATURES2 XFS_SB_MVAL(BAD_FEATURES2) +#define XFS_SB_FEATURES2 (XFS_SB_MVAL(FEATURES2) | \ + XFS_SB_MVAL(BAD_FEATURES2)) #define XFS_SB_FEATURES_COMPAT XFS_SB_MVAL(FEATURES_COMPAT) #define XFS_SB_FEATURES_RO_COMPAT XFS_SB_MVAL(FEATURES_RO_COMPAT) #define XFS_SB_FEATURES_INCOMPAT XFS_SB_MVAL(FEATURES_INCOMPAT) @@ -319,9 +322,9 @@ typedef enum { XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO | XFS_SB_GQUOTINO | \ XFS_SB_QFLAGS | XFS_SB_SHARED_VN | XFS_SB_UNIT | XFS_SB_WIDTH | \ XFS_SB_ICOUNT | XFS_SB_IFREE | XFS_SB_FDBLOCKS | XFS_SB_FEATURES2 | \ - XFS_SB_BAD_FEATURES2 | XFS_SB_FEATURES_COMPAT | \ - XFS_SB_FEATURES_RO_COMPAT | XFS_SB_FEATURES_INCOMPAT | \ - XFS_SB_FEATURES_LOG_INCOMPAT | XFS_SB_PQUOTINO) + XFS_SB_FEATURES_COMPAT | XFS_SB_FEATURES_RO_COMPAT | \ + XFS_SB_FEATURES_INCOMPAT | XFS_SB_FEATURES_LOG_INCOMPAT | \ + XFS_SB_PQUOTINO) /* @@ -453,13 +456,11 @@ static inline void xfs_sb_version_addattr2(struct xfs_sb *sbp) { sbp->sb_versionnum |= XFS_SB_VERSION_MOREBITSBIT; sbp->sb_features2 |= XFS_SB_VERSION2_ATTR2BIT; - sbp->sb_bad_features2 |= XFS_SB_VERSION2_ATTR2BIT; } static inline void xfs_sb_version_removeattr2(struct xfs_sb *sbp) { sbp->sb_features2 &= ~XFS_SB_VERSION2_ATTR2BIT; - sbp->sb_bad_features2 &= ~XFS_SB_VERSION2_ATTR2BIT; if (!sbp->sb_features2) sbp->sb_versionnum &= ~XFS_SB_VERSION_MOREBITSBIT; } @@ -475,7 +476,6 @@ static inline void xfs_sb_version_addprojid32bit(struct xfs_sb *sbp) { sbp->sb_versionnum |= XFS_SB_VERSION_MOREBITSBIT; sbp->sb_features2 |= XFS_SB_VERSION2_PROJID32BIT; - sbp->sb_bad_features2 |= XFS_SB_VERSION2_PROJID32BIT; } /* diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index 18dc721ca19..18dc721ca19 100644 --- a/fs/xfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 752915fa775..b0a5fe95a3e 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -40,69 +40,6 @@ * Physical superblock buffer manipulations. Shared with libxfs in userspace. */ -static const struct { - short offset; - short type; /* 0 = integer - * 1 = binary / string (no translation) - */ -} xfs_sb_info[] = { - { offsetof(xfs_sb_t, sb_magicnum), 0 }, - { offsetof(xfs_sb_t, sb_blocksize), 0 }, - { offsetof(xfs_sb_t, sb_dblocks), 0 }, - { offsetof(xfs_sb_t, sb_rblocks), 0 }, - { offsetof(xfs_sb_t, sb_rextents), 0 }, - { offsetof(xfs_sb_t, sb_uuid), 1 }, - { offsetof(xfs_sb_t, sb_logstart), 0 }, - { offsetof(xfs_sb_t, sb_rootino), 0 }, - { offsetof(xfs_sb_t, sb_rbmino), 0 }, - { offsetof(xfs_sb_t, sb_rsumino), 0 }, - { offsetof(xfs_sb_t, sb_rextsize), 0 }, - { offsetof(xfs_sb_t, sb_agblocks), 0 }, - { offsetof(xfs_sb_t, sb_agcount), 0 }, - { offsetof(xfs_sb_t, sb_rbmblocks), 0 }, - { offsetof(xfs_sb_t, sb_logblocks), 0 }, - { offsetof(xfs_sb_t, sb_versionnum), 0 }, - { offsetof(xfs_sb_t, sb_sectsize), 0 }, - { offsetof(xfs_sb_t, sb_inodesize), 0 }, - { offsetof(xfs_sb_t, sb_inopblock), 0 }, - { offsetof(xfs_sb_t, sb_fname[0]), 1 }, - { offsetof(xfs_sb_t, sb_blocklog), 0 }, - { offsetof(xfs_sb_t, sb_sectlog), 0 }, - { offsetof(xfs_sb_t, sb_inodelog), 0 }, - { offsetof(xfs_sb_t, sb_inopblog), 0 }, - { offsetof(xfs_sb_t, sb_agblklog), 0 }, - { offsetof(xfs_sb_t, sb_rextslog), 0 }, - { offsetof(xfs_sb_t, sb_inprogress), 0 }, - { offsetof(xfs_sb_t, sb_imax_pct), 0 }, - { offsetof(xfs_sb_t, sb_icount), 0 }, - { offsetof(xfs_sb_t, sb_ifree), 0 }, - { offsetof(xfs_sb_t, sb_fdblocks), 0 }, - { offsetof(xfs_sb_t, sb_frextents), 0 }, - { offsetof(xfs_sb_t, sb_uquotino), 0 }, - { offsetof(xfs_sb_t, sb_gquotino), 0 }, - { offsetof(xfs_sb_t, sb_qflags), 0 }, - { offsetof(xfs_sb_t, sb_flags), 0 }, - { offsetof(xfs_sb_t, sb_shared_vn), 0 }, - { offsetof(xfs_sb_t, sb_inoalignmt), 0 }, - { offsetof(xfs_sb_t, sb_unit), 0 }, - { offsetof(xfs_sb_t, sb_width), 0 }, - { offsetof(xfs_sb_t, sb_dirblklog), 0 }, - { offsetof(xfs_sb_t, sb_logsectlog), 0 }, - { offsetof(xfs_sb_t, sb_logsectsize), 0 }, - { offsetof(xfs_sb_t, sb_logsunit), 0 }, - { offsetof(xfs_sb_t, sb_features2), 0 }, - { offsetof(xfs_sb_t, sb_bad_features2), 0 }, - { offsetof(xfs_sb_t, sb_features_compat), 0 }, - { offsetof(xfs_sb_t, sb_features_ro_compat), 0 }, - { offsetof(xfs_sb_t, sb_features_incompat), 0 }, - { offsetof(xfs_sb_t, sb_features_log_incompat), 0 }, - { offsetof(xfs_sb_t, sb_crc), 0 }, - { offsetof(xfs_sb_t, sb_pad), 0 }, - { offsetof(xfs_sb_t, sb_pquotino), 0 }, - { offsetof(xfs_sb_t, sb_lsn), 0 }, - { sizeof(xfs_sb_t), 0 } -}; - /* * Reference counting access wrappers to the perag structures. * Because we never free per-ag structures, the only thing we @@ -461,58 +398,49 @@ xfs_sb_from_disk( __xfs_sb_from_disk(to, from, true); } -static inline void +static void xfs_sb_quota_to_disk( - xfs_dsb_t *to, - xfs_sb_t *from, - __int64_t *fields) + struct xfs_dsb *to, + struct xfs_sb *from) { __uint16_t qflags = from->sb_qflags; + to->sb_uquotino = cpu_to_be64(from->sb_uquotino); + if (xfs_sb_version_has_pquotino(from)) { + to->sb_qflags = cpu_to_be16(from->sb_qflags); + to->sb_gquotino = cpu_to_be64(from->sb_gquotino); + to->sb_pquotino = cpu_to_be64(from->sb_pquotino); + return; + } + /* - * We need to do these manipilations only if we are working - * with an older version of on-disk superblock. + * The in-core version of sb_qflags do not have XFS_OQUOTA_* + * flags, whereas the on-disk version does. So, convert incore + * XFS_{PG}QUOTA_* flags to on-disk XFS_OQUOTA_* flags. */ - if (xfs_sb_version_has_pquotino(from)) - return; + qflags &= ~(XFS_PQUOTA_ENFD | XFS_PQUOTA_CHKD | + XFS_GQUOTA_ENFD | XFS_GQUOTA_CHKD); - if (*fields & XFS_SB_QFLAGS) { - /* - * The in-core version of sb_qflags do not have - * XFS_OQUOTA_* flags, whereas the on-disk version - * does. So, convert incore XFS_{PG}QUOTA_* flags - * to on-disk XFS_OQUOTA_* flags. - */ - qflags &= ~(XFS_PQUOTA_ENFD | XFS_PQUOTA_CHKD | - XFS_GQUOTA_ENFD | XFS_GQUOTA_CHKD); - - if (from->sb_qflags & - (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD)) - qflags |= XFS_OQUOTA_ENFD; - if (from->sb_qflags & - (XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) - qflags |= XFS_OQUOTA_CHKD; - to->sb_qflags = cpu_to_be16(qflags); - *fields &= ~XFS_SB_QFLAGS; - } + if (from->sb_qflags & + (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD)) + qflags |= XFS_OQUOTA_ENFD; + if (from->sb_qflags & + (XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) + qflags |= XFS_OQUOTA_CHKD; + to->sb_qflags = cpu_to_be16(qflags); /* - * GQUOTINO and PQUOTINO cannot be used together in versions of - * superblock that do not have pquotino. from->sb_flags tells us which - * quota is active and should be copied to disk. If neither are active, - * make sure we write NULLFSINO to the sb_gquotino field as a quota - * inode value of "0" is invalid when the XFS_SB_VERSION_QUOTA feature - * bit is set. + * GQUOTINO and PQUOTINO cannot be used together in versions + * of superblock that do not have pquotino. from->sb_flags + * tells us which quota is active and should be copied to + * disk. If neither are active, we should NULL the inode. * - * Note that we don't need to handle the sb_uquotino or sb_pquotino here - * as they do not require any translation. Hence the main sb field loop - * will write them appropriately from the in-core superblock. + * In all cases, the separate pquotino must remain 0 because it + * it beyond the "end" of the valid non-pquotino superblock. */ - if ((*fields & XFS_SB_GQUOTINO) && - (from->sb_qflags & XFS_GQUOTA_ACCT)) + if (from->sb_qflags & XFS_GQUOTA_ACCT) to->sb_gquotino = cpu_to_be64(from->sb_gquotino); - else if ((*fields & XFS_SB_PQUOTINO) && - (from->sb_qflags & XFS_PQUOTA_ACCT)) + else if (from->sb_qflags & XFS_PQUOTA_ACCT) to->sb_gquotino = cpu_to_be64(from->sb_pquotino); else { /* @@ -526,63 +454,78 @@ xfs_sb_quota_to_disk( to->sb_gquotino = cpu_to_be64(NULLFSINO); } - *fields &= ~(XFS_SB_PQUOTINO | XFS_SB_GQUOTINO); + to->sb_pquotino = 0; } -/* - * Copy in core superblock to ondisk one. - * - * The fields argument is mask of superblock fields to copy. - */ void xfs_sb_to_disk( - xfs_dsb_t *to, - xfs_sb_t *from, - __int64_t fields) + struct xfs_dsb *to, + struct xfs_sb *from) { - xfs_caddr_t to_ptr = (xfs_caddr_t)to; - xfs_caddr_t from_ptr = (xfs_caddr_t)from; - xfs_sb_field_t f; - int first; - int size; - - ASSERT(fields); - if (!fields) - return; + xfs_sb_quota_to_disk(to, from); - /* We should never write the crc here, it's updated in the IO path */ - fields &= ~XFS_SB_CRC; - - xfs_sb_quota_to_disk(to, from, &fields); - while (fields) { - f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields); - first = xfs_sb_info[f].offset; - size = xfs_sb_info[f + 1].offset - first; - - ASSERT(xfs_sb_info[f].type == 0 || xfs_sb_info[f].type == 1); - - if (size == 1 || xfs_sb_info[f].type == 1) { - memcpy(to_ptr + first, from_ptr + first, size); - } else { - switch (size) { - case 2: - *(__be16 *)(to_ptr + first) = - cpu_to_be16(*(__u16 *)(from_ptr + first)); - break; - case 4: - *(__be32 *)(to_ptr + first) = - cpu_to_be32(*(__u32 *)(from_ptr + first)); - break; - case 8: - *(__be64 *)(to_ptr + first) = - cpu_to_be64(*(__u64 *)(from_ptr + first)); - break; - default: - ASSERT(0); - } - } + to->sb_magicnum = cpu_to_be32(from->sb_magicnum); + to->sb_blocksize = cpu_to_be32(from->sb_blocksize); + to->sb_dblocks = cpu_to_be64(from->sb_dblocks); + to->sb_rblocks = cpu_to_be64(from->sb_rblocks); + to->sb_rextents = cpu_to_be64(from->sb_rextents); + memcpy(&to->sb_uuid, &from->sb_uuid, sizeof(to->sb_uuid)); + to->sb_logstart = cpu_to_be64(from->sb_logstart); + to->sb_rootino = cpu_to_be64(from->sb_rootino); + to->sb_rbmino = cpu_to_be64(from->sb_rbmino); + to->sb_rsumino = cpu_to_be64(from->sb_rsumino); + to->sb_rextsize = cpu_to_be32(from->sb_rextsize); + to->sb_agblocks = cpu_to_be32(from->sb_agblocks); + to->sb_agcount = cpu_to_be32(from->sb_agcount); + to->sb_rbmblocks = cpu_to_be32(from->sb_rbmblocks); + to->sb_logblocks = cpu_to_be32(from->sb_logblocks); + to->sb_versionnum = cpu_to_be16(from->sb_versionnum); + to->sb_sectsize = cpu_to_be16(from->sb_sectsize); + to->sb_inodesize = cpu_to_be16(from->sb_inodesize); + to->sb_inopblock = cpu_to_be16(from->sb_inopblock); + memcpy(&to->sb_fname, &from->sb_fname, sizeof(to->sb_fname)); + to->sb_blocklog = from->sb_blocklog; + to->sb_sectlog = from->sb_sectlog; + to->sb_inodelog = from->sb_inodelog; + to->sb_inopblog = from->sb_inopblog; + to->sb_agblklog = from->sb_agblklog; + to->sb_rextslog = from->sb_rextslog; + to->sb_inprogress = from->sb_inprogress; + to->sb_imax_pct = from->sb_imax_pct; + to->sb_icount = cpu_to_be64(from->sb_icount); + to->sb_ifree = cpu_to_be64(from->sb_ifree); + to->sb_fdblocks = cpu_to_be64(from->sb_fdblocks); + to->sb_frextents = cpu_to_be64(from->sb_frextents); - fields &= ~(1LL << f); + to->sb_flags = from->sb_flags; + to->sb_shared_vn = from->sb_shared_vn; + to->sb_inoalignmt = cpu_to_be32(from->sb_inoalignmt); + to->sb_unit = cpu_to_be32(from->sb_unit); + to->sb_width = cpu_to_be32(from->sb_width); + to->sb_dirblklog = from->sb_dirblklog; + to->sb_logsectlog = from->sb_logsectlog; + to->sb_logsectsize = cpu_to_be16(from->sb_logsectsize); + to->sb_logsunit = cpu_to_be32(from->sb_logsunit); + + /* + * We need to ensure that bad_features2 always matches features2. + * Hence we enforce that here rather than having to remember to do it + * everywhere else that updates features2. + */ + from->sb_bad_features2 = from->sb_features2; + to->sb_features2 = cpu_to_be32(from->sb_features2); + to->sb_bad_features2 = cpu_to_be32(from->sb_bad_features2); + + if (xfs_sb_version_hascrc(from)) { + to->sb_features_compat = cpu_to_be32(from->sb_features_compat); + to->sb_features_ro_compat = + cpu_to_be32(from->sb_features_ro_compat); + to->sb_features_incompat = + cpu_to_be32(from->sb_features_incompat); + to->sb_features_log_incompat = + cpu_to_be32(from->sb_features_log_incompat); + to->sb_pad = 0; + to->sb_lsn = cpu_to_be64(from->sb_lsn); } } @@ -816,42 +759,51 @@ xfs_initialize_perag_data( } /* - * xfs_mod_sb() can be used to copy arbitrary changes to the - * in-core superblock into the superblock buffer to be logged. - * It does not provide the higher level of locking that is - * needed to protect the in-core superblock from concurrent - * access. + * xfs_log_sb() can be used to copy arbitrary changes to the in-core superblock + * into the superblock buffer to be logged. It does not provide the higher + * level of locking that is needed to protect the in-core superblock from + * concurrent access. */ void -xfs_mod_sb(xfs_trans_t *tp, __int64_t fields) +xfs_log_sb( + struct xfs_trans *tp) { - xfs_buf_t *bp; - int first; - int last; - xfs_mount_t *mp; - xfs_sb_field_t f; - - ASSERT(fields); - if (!fields) - return; - mp = tp->t_mountp; - bp = xfs_trans_getsb(tp, mp, 0); - first = sizeof(xfs_sb_t); - last = 0; - - /* translate/copy */ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_buf *bp = xfs_trans_getsb(tp, mp, 0); - xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb, fields); + xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb); + xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); + xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb)); +} - /* find modified range */ - f = (xfs_sb_field_t)xfs_highbit64((__uint64_t)fields); - ASSERT((1LL << f) & XFS_SB_MOD_BITS); - last = xfs_sb_info[f + 1].offset - 1; +/* + * xfs_sync_sb + * + * Sync the superblock to disk. + * + * Note that the caller is responsible for checking the frozen state of the + * filesystem. This procedure uses the non-blocking transaction allocator and + * thus will allow modifications to a frozen fs. This is required because this + * code can be called during the process of freezing where use of the high-level + * allocator would deadlock. + */ +int +xfs_sync_sb( + struct xfs_mount *mp, + bool wait) +{ + struct xfs_trans *tp; + int error; - f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields); - ASSERT((1LL << f) & XFS_SB_MOD_BITS); - first = xfs_sb_info[f].offset; + tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_CHANGE, KM_SLEEP); + error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0); + if (error) { + xfs_trans_cancel(tp, 0); + return error; + } - xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); - xfs_trans_log_buf(tp, bp, first, last); + xfs_log_sb(tp); + if (wait) + xfs_trans_set_sync(tp); + return xfs_trans_commit(tp, 0); } diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h index 8eb1c54bafb..b25bb9a343f 100644 --- a/fs/xfs/libxfs/xfs_sb.h +++ b/fs/xfs/libxfs/xfs_sb.h @@ -27,11 +27,12 @@ extern struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *, xfs_agnumber_t, extern void xfs_perag_put(struct xfs_perag *pag); extern int xfs_initialize_perag_data(struct xfs_mount *, xfs_agnumber_t); -extern void xfs_sb_calc_crc(struct xfs_buf *); -extern void xfs_mod_sb(struct xfs_trans *, __int64_t); -extern void xfs_sb_mount_common(struct xfs_mount *, struct xfs_sb *); -extern void xfs_sb_from_disk(struct xfs_sb *, struct xfs_dsb *); -extern void xfs_sb_to_disk(struct xfs_dsb *, struct xfs_sb *, __int64_t); +extern void xfs_sb_calc_crc(struct xfs_buf *bp); +extern void xfs_log_sb(struct xfs_trans *tp); +extern int xfs_sync_sb(struct xfs_mount *mp, bool wait); +extern void xfs_sb_mount_common(struct xfs_mount *mp, struct xfs_sb *sbp); +extern void xfs_sb_from_disk(struct xfs_sb *to, struct xfs_dsb *from); +extern void xfs_sb_to_disk(struct xfs_dsb *to, struct xfs_sb *from); extern void xfs_sb_quota_from_disk(struct xfs_sb *sbp); #endif /* __XFS_SB_H__ */ diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h index 82404da2ca6..8dda4b32134 100644 --- a/fs/xfs/libxfs/xfs_shared.h +++ b/fs/xfs/libxfs/xfs_shared.h @@ -82,7 +82,7 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops; #define XFS_TRANS_ATTR_RM 23 #define XFS_TRANS_ATTR_FLAG 24 #define XFS_TRANS_CLEAR_AGI_BUCKET 25 -#define XFS_TRANS_QM_SBCHANGE 26 +#define XFS_TRANS_SB_CHANGE 26 /* * Dummy entries since we use the transaction type to index into the * trans_type[] in xlog_recover_print_trans_head() @@ -95,17 +95,15 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops; #define XFS_TRANS_QM_DQCLUSTER 32 #define XFS_TRANS_QM_QINOCREATE 33 #define XFS_TRANS_QM_QUOTAOFF_END 34 -#define XFS_TRANS_SB_UNIT 35 -#define XFS_TRANS_FSYNC_TS 36 -#define XFS_TRANS_GROWFSRT_ALLOC 37 -#define XFS_TRANS_GROWFSRT_ZERO 38 -#define XFS_TRANS_GROWFSRT_FREE 39 -#define XFS_TRANS_SWAPEXT 40 -#define XFS_TRANS_SB_COUNT 41 -#define XFS_TRANS_CHECKPOINT 42 -#define XFS_TRANS_ICREATE 43 -#define XFS_TRANS_CREATE_TMPFILE 44 -#define XFS_TRANS_TYPE_MAX 44 +#define XFS_TRANS_FSYNC_TS 35 +#define XFS_TRANS_GROWFSRT_ALLOC 36 +#define XFS_TRANS_GROWFSRT_ZERO 37 +#define XFS_TRANS_GROWFSRT_FREE 38 +#define XFS_TRANS_SWAPEXT 39 +#define XFS_TRANS_CHECKPOINT 40 +#define XFS_TRANS_ICREATE 41 +#define XFS_TRANS_CREATE_TMPFILE 42 +#define XFS_TRANS_TYPE_MAX 43 /* new transaction types need to be reflected in xfs_logprint(8) */ #define XFS_TRANS_TYPES \ @@ -113,7 +111,6 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops; { XFS_TRANS_SETATTR_SIZE, "SETATTR_SIZE" }, \ { XFS_TRANS_INACTIVE, "INACTIVE" }, \ { XFS_TRANS_CREATE, "CREATE" }, \ - { XFS_TRANS_CREATE_TMPFILE, "CREATE_TMPFILE" }, \ { XFS_TRANS_CREATE_TRUNC, "CREATE_TRUNC" }, \ { XFS_TRANS_TRUNCATE_FILE, "TRUNCATE_FILE" }, \ { XFS_TRANS_REMOVE, "REMOVE" }, \ @@ -134,23 +131,23 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops; { XFS_TRANS_ATTR_RM, "ATTR_RM" }, \ { XFS_TRANS_ATTR_FLAG, "ATTR_FLAG" }, \ { XFS_TRANS_CLEAR_AGI_BUCKET, "CLEAR_AGI_BUCKET" }, \ - { XFS_TRANS_QM_SBCHANGE, "QM_SBCHANGE" }, \ + { XFS_TRANS_SB_CHANGE, "SBCHANGE" }, \ + { XFS_TRANS_DUMMY1, "DUMMY1" }, \ + { XFS_TRANS_DUMMY2, "DUMMY2" }, \ { XFS_TRANS_QM_QUOTAOFF, "QM_QUOTAOFF" }, \ { XFS_TRANS_QM_DQALLOC, "QM_DQALLOC" }, \ { XFS_TRANS_QM_SETQLIM, "QM_SETQLIM" }, \ { XFS_TRANS_QM_DQCLUSTER, "QM_DQCLUSTER" }, \ { XFS_TRANS_QM_QINOCREATE, "QM_QINOCREATE" }, \ { XFS_TRANS_QM_QUOTAOFF_END, "QM_QOFF_END" }, \ - { XFS_TRANS_SB_UNIT, "SB_UNIT" }, \ { XFS_TRANS_FSYNC_TS, "FSYNC_TS" }, \ { XFS_TRANS_GROWFSRT_ALLOC, "GROWFSRT_ALLOC" }, \ { XFS_TRANS_GROWFSRT_ZERO, "GROWFSRT_ZERO" }, \ { XFS_TRANS_GROWFSRT_FREE, "GROWFSRT_FREE" }, \ { XFS_TRANS_SWAPEXT, "SWAPEXT" }, \ - { XFS_TRANS_SB_COUNT, "SB_COUNT" }, \ { XFS_TRANS_CHECKPOINT, "CHECKPOINT" }, \ - { XFS_TRANS_DUMMY1, "DUMMY1" }, \ - { XFS_TRANS_DUMMY2, "DUMMY2" }, \ + { XFS_TRANS_ICREATE, "ICREATE" }, \ + { XFS_TRANS_CREATE_TMPFILE, "CREATE_TMPFILE" }, \ { XLOG_UNMOUNT_REC_TYPE, "UNMOUNT" } /* diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c index c80c5236c3d..e7e26bd6468 100644 --- a/fs/xfs/libxfs/xfs_symlink_remote.c +++ b/fs/xfs/libxfs/xfs_symlink_remote.c @@ -178,6 +178,8 @@ xfs_symlink_local_to_remote( struct xfs_mount *mp = ip->i_mount; char *buf; + xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF); + if (!xfs_sb_version_hascrc(&mp->m_sb)) { bp->b_ops = NULL; memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes); diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index 6c1330f2905..68cb1e7bf2b 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -716,17 +716,6 @@ xfs_calc_clear_agi_bucket_reservation( } /* - * Clearing the quotaflags in the superblock. - * the super block for changing quota flags: sector size - */ -STATIC uint -xfs_calc_qm_sbchange_reservation( - struct xfs_mount *mp) -{ - return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize); -} - -/* * Adjusting quota limits. * the xfs_disk_dquot_t: sizeof(struct xfs_disk_dquot) */ @@ -864,9 +853,6 @@ xfs_trans_resv_calc( * The following transactions are logged in logical format with * a default log count. */ - resp->tr_qm_sbchange.tr_logres = xfs_calc_qm_sbchange_reservation(mp); - resp->tr_qm_sbchange.tr_logcount = XFS_DEFAULT_LOG_COUNT; - resp->tr_qm_setqlim.tr_logres = xfs_calc_qm_setqlim_reservation(mp); resp->tr_qm_setqlim.tr_logcount = XFS_DEFAULT_LOG_COUNT; diff --git a/fs/xfs/libxfs/xfs_trans_resv.h b/fs/xfs/libxfs/xfs_trans_resv.h index 1097d14cd58..2d5bdfce6d8 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.h +++ b/fs/xfs/libxfs/xfs_trans_resv.h @@ -56,7 +56,6 @@ struct xfs_trans_resv { struct xfs_trans_res tr_growrtalloc; /* grow realtime allocations */ struct xfs_trans_res tr_growrtzero; /* grow realtime zeroing */ struct xfs_trans_res tr_growrtfree; /* grow realtime freeing */ - struct xfs_trans_res tr_qm_sbchange; /* change quota flags */ struct xfs_trans_res tr_qm_setqlim; /* adjust quota limits */ struct xfs_trans_res tr_qm_dqalloc; /* allocate quota on disk */ struct xfs_trans_res tr_qm_quotaoff; /* turn quota off */ diff --git a/fs/xfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index b79dc66b2ec..b79dc66b2ec 100644 --- a/fs/xfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 18e2f3bbae5..3a9b7a1b870 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -135,30 +135,22 @@ xfs_setfilesize_trans_alloc( */ STATIC int xfs_setfilesize( - struct xfs_ioend *ioend) + struct xfs_inode *ip, + struct xfs_trans *tp, + xfs_off_t offset, + size_t size) { - struct xfs_inode *ip = XFS_I(ioend->io_inode); - struct xfs_trans *tp = ioend->io_append_trans; xfs_fsize_t isize; - /* - * The transaction may have been allocated in the I/O submission thread, - * thus we need to mark ourselves as beeing in a transaction manually. - * Similarly for freeze protection. - */ - current_set_flags_nested(&tp->t_pflags, PF_FSTRANS); - rwsem_acquire_read(&VFS_I(ip)->i_sb->s_writers.lock_map[SB_FREEZE_FS-1], - 0, 1, _THIS_IP_); - xfs_ilock(ip, XFS_ILOCK_EXCL); - isize = xfs_new_eof(ip, ioend->io_offset + ioend->io_size); + isize = xfs_new_eof(ip, offset + size); if (!isize) { xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_trans_cancel(tp, 0); return 0; } - trace_xfs_setfilesize(ip, ioend->io_offset, ioend->io_size); + trace_xfs_setfilesize(ip, offset, size); ip->i_d.di_size = isize; xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); @@ -167,6 +159,25 @@ xfs_setfilesize( return xfs_trans_commit(tp, 0); } +STATIC int +xfs_setfilesize_ioend( + struct xfs_ioend *ioend) +{ + struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_trans *tp = ioend->io_append_trans; + + /* + * The transaction may have been allocated in the I/O submission thread, + * thus we need to mark ourselves as being in a transaction manually. + * Similarly for freeze protection. + */ + current_set_flags_nested(&tp->t_pflags, PF_FSTRANS); + rwsem_acquire_read(&VFS_I(ip)->i_sb->s_writers.lock_map[SB_FREEZE_FS-1], + 0, 1, _THIS_IP_); + + return xfs_setfilesize(ip, tp, ioend->io_offset, ioend->io_size); +} + /* * Schedule IO completion handling on the final put of an ioend. * @@ -182,8 +193,7 @@ xfs_finish_ioend( if (ioend->io_type == XFS_IO_UNWRITTEN) queue_work(mp->m_unwritten_workqueue, &ioend->io_work); - else if (ioend->io_append_trans || - (ioend->io_isdirect && xfs_ioend_is_append(ioend))) + else if (ioend->io_append_trans) queue_work(mp->m_data_workqueue, &ioend->io_work); else xfs_destroy_ioend(ioend); @@ -215,22 +225,8 @@ xfs_end_io( if (ioend->io_type == XFS_IO_UNWRITTEN) { error = xfs_iomap_write_unwritten(ip, ioend->io_offset, ioend->io_size); - } else if (ioend->io_isdirect && xfs_ioend_is_append(ioend)) { - /* - * For direct I/O we do not know if we need to allocate blocks - * or not so we can't preallocate an append transaction as that - * results in nested reservations and log space deadlocks. Hence - * allocate the transaction here. While this is sub-optimal and - * can block IO completion for some time, we're stuck with doing - * it this way until we can pass the ioend to the direct IO - * allocation callbacks and avoid nesting that way. - */ - error = xfs_setfilesize_trans_alloc(ioend); - if (error) - goto done; - error = xfs_setfilesize(ioend); } else if (ioend->io_append_trans) { - error = xfs_setfilesize(ioend); + error = xfs_setfilesize_ioend(ioend); } else { ASSERT(!xfs_ioend_is_append(ioend)); } @@ -242,17 +238,6 @@ done: } /* - * Call IO completion handling in caller context on the final put of an ioend. - */ -STATIC void -xfs_finish_ioend_sync( - struct xfs_ioend *ioend) -{ - if (atomic_dec_and_test(&ioend->io_remaining)) - xfs_end_io(&ioend->io_work); -} - -/* * Allocate and initialise an IO completion structure. * We need to track unwritten extent write completion here initially. * We'll need to extend this for updating the ondisk inode size later @@ -273,7 +258,6 @@ xfs_alloc_ioend( * all the I/O from calling the completion routine too early. */ atomic_set(&ioend->io_remaining, 1); - ioend->io_isdirect = 0; ioend->io_error = 0; ioend->io_list = NULL; ioend->io_type = type; @@ -1459,11 +1443,7 @@ xfs_get_blocks_direct( * * If the private argument is non-NULL __xfs_get_blocks signals us that we * need to issue a transaction to convert the range from unwritten to written - * extents. In case this is regular synchronous I/O we just call xfs_end_io - * to do this and we are done. But in case this was a successful AIO - * request this handler is called from interrupt context, from which we - * can't start transactions. In that case offload the I/O completion to - * the workqueues we also use for buffered I/O completion. + * extents. */ STATIC void xfs_end_io_direct_write( @@ -1472,7 +1452,12 @@ xfs_end_io_direct_write( ssize_t size, void *private) { - struct xfs_ioend *ioend = iocb->private; + struct inode *inode = file_inode(iocb->ki_filp); + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + + if (XFS_FORCED_SHUTDOWN(mp)) + return; /* * While the generic direct I/O code updates the inode size, it does @@ -1480,22 +1465,33 @@ xfs_end_io_direct_write( * end_io handler thinks the on-disk size is outside the in-core * size. To prevent this just update it a little bit earlier here. */ - if (offset + size > i_size_read(ioend->io_inode)) - i_size_write(ioend->io_inode, offset + size); + if (offset + size > i_size_read(inode)) + i_size_write(inode, offset + size); /* - * blockdev_direct_IO can return an error even after the I/O - * completion handler was called. Thus we need to protect - * against double-freeing. + * For direct I/O we do not know if we need to allocate blocks or not, + * so we can't preallocate an append transaction, as that results in + * nested reservations and log space deadlocks. Hence allocate the + * transaction here. While this is sub-optimal and can block IO + * completion for some time, we're stuck with doing it this way until + * we can pass the ioend to the direct IO allocation callbacks and + * avoid nesting that way. */ - iocb->private = NULL; - - ioend->io_offset = offset; - ioend->io_size = size; - if (private && size > 0) - ioend->io_type = XFS_IO_UNWRITTEN; + if (private && size > 0) { + xfs_iomap_write_unwritten(ip, offset, size); + } else if (offset + size > ip->i_d.di_size) { + struct xfs_trans *tp; + int error; + + tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS); + error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0); + if (error) { + xfs_trans_cancel(tp, 0); + return; + } - xfs_finish_ioend_sync(ioend); + xfs_setfilesize(ip, tp, offset, size); + } } STATIC ssize_t @@ -1507,39 +1503,16 @@ xfs_vm_direct_IO( { struct inode *inode = iocb->ki_filp->f_mapping->host; struct block_device *bdev = xfs_find_bdev_for_inode(inode); - struct xfs_ioend *ioend = NULL; - ssize_t ret; if (rw & WRITE) { - size_t size = iov_iter_count(iter); - - /* - * We cannot preallocate a size update transaction here as we - * don't know whether allocation is necessary or not. Hence we - * can only tell IO completion that one is necessary if we are - * not doing unwritten extent conversion. - */ - iocb->private = ioend = xfs_alloc_ioend(inode, XFS_IO_DIRECT); - if (offset + size > XFS_I(inode)->i_d.di_size) - ioend->io_isdirect = 1; - - ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter, + return __blockdev_direct_IO(rw, iocb, inode, bdev, iter, offset, xfs_get_blocks_direct, xfs_end_io_direct_write, NULL, DIO_ASYNC_EXTEND); - if (ret != -EIOCBQUEUED && iocb->private) - goto out_destroy_ioend; - } else { - ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter, - offset, xfs_get_blocks_direct, - NULL, NULL, 0); } - - return ret; - -out_destroy_ioend: - xfs_destroy_ioend(ioend); - return ret; + return __blockdev_direct_IO(rw, iocb, inode, bdev, iter, + offset, xfs_get_blocks_direct, + NULL, NULL, 0); } /* diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index f94dd459dff..ac644e0137a 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -24,14 +24,12 @@ extern mempool_t *xfs_ioend_pool; * Types of I/O for bmap clustering and I/O completion tracking. */ enum { - XFS_IO_DIRECT = 0, /* special case for direct I/O ioends */ XFS_IO_DELALLOC, /* covers delalloc region */ XFS_IO_UNWRITTEN, /* covers allocated but uninitialized data */ XFS_IO_OVERWRITE, /* covers already allocated extent */ }; #define XFS_IO_TYPES \ - { 0, "" }, \ { XFS_IO_DELALLOC, "delalloc" }, \ { XFS_IO_UNWRITTEN, "unwritten" }, \ { XFS_IO_OVERWRITE, "overwrite" } @@ -45,7 +43,6 @@ typedef struct xfs_ioend { unsigned int io_type; /* delalloc / unwritten */ int io_error; /* I/O error code */ atomic_t io_remaining; /* hold count */ - unsigned int io_isdirect : 1;/* direct I/O */ struct inode *io_inode; /* file being written to */ struct buffer_head *io_buffer_head;/* buffer linked list head */ struct buffer_head *io_buffer_tail;/* buffer linked list tail */ diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 2fdb72d2c90..736429a72a1 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -26,43 +26,8 @@ struct xfs_ifork; struct xfs_inode; struct xfs_mount; struct xfs_trans; +struct xfs_bmalloca; -/* - * Argument structure for xfs_bmap_alloc. - */ -struct xfs_bmalloca { - xfs_fsblock_t *firstblock; /* i/o first block allocated */ - struct xfs_bmap_free *flist; /* bmap freelist */ - struct xfs_trans *tp; /* transaction pointer */ - struct xfs_inode *ip; /* incore inode pointer */ - struct xfs_bmbt_irec prev; /* extent before the new one */ - struct xfs_bmbt_irec got; /* extent after, or delayed */ - - xfs_fileoff_t offset; /* offset in file filling in */ - xfs_extlen_t length; /* i/o length asked/allocated */ - xfs_fsblock_t blkno; /* starting block of new extent */ - - struct xfs_btree_cur *cur; /* btree cursor */ - xfs_extnum_t idx; /* current extent index */ - int nallocs;/* number of extents alloc'd */ - int logflags;/* flags for transaction logging */ - - xfs_extlen_t total; /* total blocks needed for xaction */ - xfs_extlen_t minlen; /* minimum allocation size (blocks) */ - xfs_extlen_t minleft; /* amount must be left after alloc */ - bool eof; /* set if allocating past last extent */ - bool wasdel; /* replacing a delayed allocation */ - bool userdata;/* set if is user data */ - bool aeof; /* allocated space at eof */ - bool conv; /* overwriting unwritten extents */ - int flags; - struct completion *done; - struct work_struct work; - int result; -}; - -int xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist, - int *committed); int xfs_bmap_rtalloc(struct xfs_bmalloca *ap); int xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff, int whichfork, int *eof); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 3f9bd58edec..507d96a57ac 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -319,6 +319,10 @@ xfs_buf_item_format( ASSERT(atomic_read(&bip->bli_refcount) > 0); ASSERT((bip->bli_flags & XFS_BLI_LOGGED) || (bip->bli_flags & XFS_BLI_STALE)); + ASSERT((bip->bli_flags & XFS_BLI_STALE) || + (xfs_blft_from_flags(&bip->__bli_format) > XFS_BLFT_UNKNOWN_BUF + && xfs_blft_from_flags(&bip->__bli_format) < XFS_BLFT_MAX_BUF)); + /* * If it is an inode buffer, transfer the in-memory state to the @@ -535,7 +539,7 @@ xfs_buf_item_push( if ((bp->b_flags & XBF_WRITE_FAIL) && ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) { xfs_warn(bp->b_target->bt_mount, -"Detected failing async write on buffer block 0x%llx. Retrying async write.\n", +"Detected failing async write on buffer block 0x%llx. Retrying async write.", (long long)bp->b_bn); } diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h index c24c67e22a2..2f536f33cd2 100644 --- a/fs/xfs/xfs_dquot.h +++ b/fs/xfs/xfs_dquot.h @@ -86,7 +86,7 @@ static inline void xfs_dqflock(xfs_dquot_t *dqp) wait_for_completion(&dqp->q_flush); } -static inline int xfs_dqflock_nowait(xfs_dquot_t *dqp) +static inline bool xfs_dqflock_nowait(xfs_dquot_t *dqp) { return try_wait_for_completion(&dqp->q_flush); } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 13e974e6a88..f2d05a19d68 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -127,6 +127,42 @@ xfs_iozero( return (-status); } +int +xfs_update_prealloc_flags( + struct xfs_inode *ip, + enum xfs_prealloc_flags flags) +{ + struct xfs_trans *tp; + int error; + + tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_WRITEID); + error = xfs_trans_reserve(tp, &M_RES(ip->i_mount)->tr_writeid, 0, 0); + if (error) { + xfs_trans_cancel(tp, 0); + return error; + } + + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + + if (!(flags & XFS_PREALLOC_INVISIBLE)) { + ip->i_d.di_mode &= ~S_ISUID; + if (ip->i_d.di_mode & S_IXGRP) + ip->i_d.di_mode &= ~S_ISGID; + xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + } + + if (flags & XFS_PREALLOC_SET) + ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC; + if (flags & XFS_PREALLOC_CLEAR) + ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC; + + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + if (flags & XFS_PREALLOC_SYNC) + xfs_trans_set_sync(tp); + return xfs_trans_commit(tp, 0); +} + /* * Fsync operations on directories are much simpler than on regular files, * as there is no file data to flush, and thus also no need for explicit @@ -784,8 +820,8 @@ xfs_file_fallocate( { struct inode *inode = file_inode(file); struct xfs_inode *ip = XFS_I(inode); - struct xfs_trans *tp; long error; + enum xfs_prealloc_flags flags = 0; loff_t new_size = 0; if (!S_ISREG(inode->i_mode)) @@ -822,6 +858,8 @@ xfs_file_fallocate( if (error) goto out_unlock; } else { + flags |= XFS_PREALLOC_SET; + if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > i_size_read(inode)) { new_size = offset + len; @@ -839,28 +877,10 @@ xfs_file_fallocate( goto out_unlock; } - tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_WRITEID); - error = xfs_trans_reserve(tp, &M_RES(ip->i_mount)->tr_writeid, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - goto out_unlock; - } - - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); - ip->i_d.di_mode &= ~S_ISUID; - if (ip->i_d.di_mode & S_IXGRP) - ip->i_d.di_mode &= ~S_ISGID; - - if (!(mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE))) - ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC; - - xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - if (file->f_flags & O_DSYNC) - xfs_trans_set_sync(tp); - error = xfs_trans_commit(tp, 0); + flags |= XFS_PREALLOC_SYNC; + + error = xfs_update_prealloc_flags(ip, flags); if (error) goto out_unlock; @@ -1384,5 +1404,4 @@ static const struct vm_operations_struct xfs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = xfs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index fdc64220fcb..fba6532efba 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -488,6 +488,7 @@ xfs_growfs_data_private( xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, nfree); if (dpct) xfs_trans_mod_sb(tp, XFS_TRANS_SB_IMAXPCT, dpct); + xfs_trans_set_sync(tp); error = xfs_trans_commit(tp, 0); if (error) return error; @@ -541,7 +542,7 @@ xfs_growfs_data_private( saved_error = error; continue; } - xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb, XFS_SB_ALL_BITS); + xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb); error = xfs_bwrite(bp); xfs_buf_relse(bp); @@ -756,37 +757,6 @@ out: return 0; } -/* - * Dump a transaction into the log that contains no real change. This is needed - * to be able to make the log dirty or stamp the current tail LSN into the log - * during the covering operation. - * - * We cannot use an inode here for this - that will push dirty state back up - * into the VFS and then periodic inode flushing will prevent log covering from - * making progress. Hence we log a field in the superblock instead and use a - * synchronous transaction to ensure the superblock is immediately unpinned - * and can be written back. - */ -int -xfs_fs_log_dummy( - xfs_mount_t *mp) -{ - xfs_trans_t *tp; - int error; - - tp = _xfs_trans_alloc(mp, XFS_TRANS_DUMMY1, KM_SLEEP); - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - return error; - } - - /* log the UUID because it is an unchanging field */ - xfs_mod_sb(tp, XFS_SB_UUID); - xfs_trans_set_sync(tp); - return xfs_trans_commit(tp, 0); -} - int xfs_fs_goingdown( xfs_mount_t *mp, diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 41f804e740d..daafa1f6d26 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1995,6 +1995,7 @@ xfs_iunlink( agi->agi_unlinked[bucket_index] = cpu_to_be32(agino); offset = offsetof(xfs_agi_t, agi_unlinked) + (sizeof(xfs_agino_t) * bucket_index); + xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF); xfs_trans_log_buf(tp, agibp, offset, (offset + sizeof(xfs_agino_t) - 1)); return 0; @@ -2086,6 +2087,7 @@ xfs_iunlink_remove( agi->agi_unlinked[bucket_index] = cpu_to_be32(next_agino); offset = offsetof(xfs_agi_t, agi_unlinked) + (sizeof(xfs_agino_t) * bucket_index); + xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF); xfs_trans_log_buf(tp, agibp, offset, (offset + sizeof(xfs_agino_t) - 1)); } else { @@ -2656,6 +2658,124 @@ xfs_sort_for_rename( } /* + * xfs_cross_rename() + * + * responsible for handling RENAME_EXCHANGE flag in renameat2() sytemcall + */ +STATIC int +xfs_cross_rename( + struct xfs_trans *tp, + struct xfs_inode *dp1, + struct xfs_name *name1, + struct xfs_inode *ip1, + struct xfs_inode *dp2, + struct xfs_name *name2, + struct xfs_inode *ip2, + struct xfs_bmap_free *free_list, + xfs_fsblock_t *first_block, + int spaceres) +{ + int error = 0; + int ip1_flags = 0; + int ip2_flags = 0; + int dp2_flags = 0; + + /* Swap inode number for dirent in first parent */ + error = xfs_dir_replace(tp, dp1, name1, + ip2->i_ino, + first_block, free_list, spaceres); + if (error) + goto out; + + /* Swap inode number for dirent in second parent */ + error = xfs_dir_replace(tp, dp2, name2, + ip1->i_ino, + first_block, free_list, spaceres); + if (error) + goto out; + + /* + * If we're renaming one or more directories across different parents, + * update the respective ".." entries (and link counts) to match the new + * parents. + */ + if (dp1 != dp2) { + dp2_flags = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; + + if (S_ISDIR(ip2->i_d.di_mode)) { + error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot, + dp1->i_ino, first_block, + free_list, spaceres); + if (error) + goto out; + + /* transfer ip2 ".." reference to dp1 */ + if (!S_ISDIR(ip1->i_d.di_mode)) { + error = xfs_droplink(tp, dp2); + if (error) + goto out; + error = xfs_bumplink(tp, dp1); + if (error) + goto out; + } + + /* + * Although ip1 isn't changed here, userspace needs + * to be warned about the change, so that applications + * relying on it (like backup ones), will properly + * notify the change + */ + ip1_flags |= XFS_ICHGTIME_CHG; + ip2_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; + } + + if (S_ISDIR(ip1->i_d.di_mode)) { + error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot, + dp2->i_ino, first_block, + free_list, spaceres); + if (error) + goto out; + + /* transfer ip1 ".." reference to dp2 */ + if (!S_ISDIR(ip2->i_d.di_mode)) { + error = xfs_droplink(tp, dp1); + if (error) + goto out; + error = xfs_bumplink(tp, dp2); + if (error) + goto out; + } + + /* + * Although ip2 isn't changed here, userspace needs + * to be warned about the change, so that applications + * relying on it (like backup ones), will properly + * notify the change + */ + ip1_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; + ip2_flags |= XFS_ICHGTIME_CHG; + } + } + + if (ip1_flags) { + xfs_trans_ichgtime(tp, ip1, ip1_flags); + xfs_trans_log_inode(tp, ip1, XFS_ILOG_CORE); + } + if (ip2_flags) { + xfs_trans_ichgtime(tp, ip2, ip2_flags); + xfs_trans_log_inode(tp, ip2, XFS_ILOG_CORE); + } + if (dp2_flags) { + xfs_trans_ichgtime(tp, dp2, dp2_flags); + xfs_trans_log_inode(tp, dp2, XFS_ILOG_CORE); + } + xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE); +out: + return error; +} + +/* * xfs_rename */ int @@ -2665,7 +2785,8 @@ xfs_rename( xfs_inode_t *src_ip, xfs_inode_t *target_dp, struct xfs_name *target_name, - xfs_inode_t *target_ip) + xfs_inode_t *target_ip, + unsigned int flags) { xfs_trans_t *tp = NULL; xfs_mount_t *mp = src_dp->i_mount; @@ -2743,6 +2864,18 @@ xfs_rename( } /* + * Handle RENAME_EXCHANGE flags + */ + if (flags & RENAME_EXCHANGE) { + error = xfs_cross_rename(tp, src_dp, src_name, src_ip, + target_dp, target_name, target_ip, + &free_list, &first_block, spaceres); + if (error) + goto abort_return; + goto finish_rename; + } + + /* * Set up the target. */ if (target_ip == NULL) { @@ -2881,6 +3014,7 @@ xfs_rename( if (new_parent) xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE); +finish_rename: /* * If this is a synchronous mount, make sure that the * rename transaction goes to disk before returning to diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 4ed2ba9342d..86cd6b39bed 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -338,7 +338,7 @@ int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip, int xfs_rename(struct xfs_inode *src_dp, struct xfs_name *src_name, struct xfs_inode *src_ip, struct xfs_inode *target_dp, struct xfs_name *target_name, - struct xfs_inode *target_ip); + struct xfs_inode *target_ip, unsigned int flags); void xfs_ilock(xfs_inode_t *, uint); int xfs_ilock_nowait(xfs_inode_t *, uint); @@ -377,6 +377,15 @@ int xfs_droplink(struct xfs_trans *, struct xfs_inode *); int xfs_bumplink(struct xfs_trans *, struct xfs_inode *); /* from xfs_file.c */ +enum xfs_prealloc_flags { + XFS_PREALLOC_SET = (1 << 1), + XFS_PREALLOC_CLEAR = (1 << 2), + XFS_PREALLOC_SYNC = (1 << 3), + XFS_PREALLOC_INVISIBLE = (1 << 4), +}; + +int xfs_update_prealloc_flags(struct xfs_inode *, + enum xfs_prealloc_flags); int xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t); int xfs_iozero(struct xfs_inode *, loff_t, size_t); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index a1831980a68..f7afb86c914 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -606,11 +606,8 @@ xfs_ioc_space( unsigned int cmd, xfs_flock64_t *bf) { - struct xfs_mount *mp = ip->i_mount; - struct xfs_trans *tp; struct iattr iattr; - bool setprealloc = false; - bool clrprealloc = false; + enum xfs_prealloc_flags flags = 0; int error; /* @@ -630,6 +627,11 @@ xfs_ioc_space( if (!S_ISREG(inode->i_mode)) return -EINVAL; + if (filp->f_flags & O_DSYNC) + flags |= XFS_PREALLOC_SYNC; + if (ioflags & XFS_IO_INVIS) + flags |= XFS_PREALLOC_INVISIBLE; + error = mnt_want_write_file(filp); if (error) return error; @@ -673,25 +675,23 @@ xfs_ioc_space( } if (bf->l_start < 0 || - bf->l_start > mp->m_super->s_maxbytes || + bf->l_start > inode->i_sb->s_maxbytes || bf->l_start + bf->l_len < 0 || - bf->l_start + bf->l_len >= mp->m_super->s_maxbytes) { + bf->l_start + bf->l_len >= inode->i_sb->s_maxbytes) { error = -EINVAL; goto out_unlock; } switch (cmd) { case XFS_IOC_ZERO_RANGE: + flags |= XFS_PREALLOC_SET; error = xfs_zero_file_space(ip, bf->l_start, bf->l_len); - if (!error) - setprealloc = true; break; case XFS_IOC_RESVSP: case XFS_IOC_RESVSP64: + flags |= XFS_PREALLOC_SET; error = xfs_alloc_file_space(ip, bf->l_start, bf->l_len, XFS_BMAPI_PREALLOC); - if (!error) - setprealloc = true; break; case XFS_IOC_UNRESVSP: case XFS_IOC_UNRESVSP64: @@ -701,6 +701,7 @@ xfs_ioc_space( case XFS_IOC_ALLOCSP64: case XFS_IOC_FREESP: case XFS_IOC_FREESP64: + flags |= XFS_PREALLOC_CLEAR; if (bf->l_start > XFS_ISIZE(ip)) { error = xfs_alloc_file_space(ip, XFS_ISIZE(ip), bf->l_start - XFS_ISIZE(ip), 0); @@ -712,8 +713,6 @@ xfs_ioc_space( iattr.ia_size = bf->l_start; error = xfs_setattr_size(ip, &iattr); - if (!error) - clrprealloc = true; break; default: ASSERT(0); @@ -723,32 +722,7 @@ xfs_ioc_space( if (error) goto out_unlock; - tp = xfs_trans_alloc(mp, XFS_TRANS_WRITEID); - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_writeid, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - goto out_unlock; - } - - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); - - if (!(ioflags & XFS_IO_INVIS)) { - ip->i_d.di_mode &= ~S_ISUID; - if (ip->i_d.di_mode & S_IXGRP) - ip->i_d.di_mode &= ~S_ISGID; - xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); - } - - if (setprealloc) - ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC; - else if (clrprealloc) - ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC; - - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - if (filp->f_flags & O_DSYNC) - xfs_trans_set_sync(tp); - error = xfs_trans_commit(tp, 0); + error = xfs_update_prealloc_flags(ip, flags); out_unlock: xfs_iunlock(ip, XFS_IOLOCK_EXCL); @@ -1013,20 +987,182 @@ xfs_diflags_to_linux( inode->i_flags &= ~S_NOATIME; } -#define FSX_PROJID 1 -#define FSX_EXTSIZE 2 -#define FSX_XFLAGS 4 -#define FSX_NONBLOCK 8 +static int +xfs_ioctl_setattr_xflags( + struct xfs_trans *tp, + struct xfs_inode *ip, + struct fsxattr *fa) +{ + struct xfs_mount *mp = ip->i_mount; + + /* Can't change realtime flag if any extents are allocated. */ + if ((ip->i_d.di_nextents || ip->i_delayed_blks) && + XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & XFS_XFLAG_REALTIME)) + return -EINVAL; + + /* If realtime flag is set then must have realtime device */ + if (fa->fsx_xflags & XFS_XFLAG_REALTIME) { + if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 || + (ip->i_d.di_extsize % mp->m_sb.sb_rextsize)) + return -EINVAL; + } + + /* + * Can't modify an immutable/append-only file unless + * we have appropriate permission. + */ + if (((ip->i_d.di_flags & (XFS_DIFLAG_IMMUTABLE | XFS_DIFLAG_APPEND)) || + (fa->fsx_xflags & (XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) && + !capable(CAP_LINUX_IMMUTABLE)) + return -EPERM; + + xfs_set_diflags(ip, fa->fsx_xflags); + xfs_diflags_to_linux(ip); + xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + XFS_STATS_INC(xs_ig_attrchg); + return 0; +} + +/* + * Set up the transaction structure for the setattr operation, checking that we + * have permission to do so. On success, return a clean transaction and the + * inode locked exclusively ready for further operation specific checks. On + * failure, return an error without modifying or locking the inode. + */ +static struct xfs_trans * +xfs_ioctl_setattr_get_trans( + struct xfs_inode *ip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_trans *tp; + int error; + + if (mp->m_flags & XFS_MOUNT_RDONLY) + return ERR_PTR(-EROFS); + if (XFS_FORCED_SHUTDOWN(mp)) + return ERR_PTR(-EIO); + + tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE); + error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0); + if (error) + goto out_cancel; + + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + + /* + * CAP_FOWNER overrides the following restrictions: + * + * The user ID of the calling process must be equal to the file owner + * ID, except in cases where the CAP_FSETID capability is applicable. + */ + if (!inode_owner_or_capable(VFS_I(ip))) { + error = -EPERM; + goto out_cancel; + } + + if (mp->m_flags & XFS_MOUNT_WSYNC) + xfs_trans_set_sync(tp); + + return tp; + +out_cancel: + xfs_trans_cancel(tp, 0); + return ERR_PTR(error); +} + +/* + * extent size hint validation is somewhat cumbersome. Rules are: + * + * 1. extent size hint is only valid for directories and regular files + * 2. XFS_XFLAG_EXTSIZE is only valid for regular files + * 3. XFS_XFLAG_EXTSZINHERIT is only valid for directories. + * 4. can only be changed on regular files if no extents are allocated + * 5. can be changed on directories at any time + * 6. extsize hint of 0 turns off hints, clears inode flags. + * 7. Extent size must be a multiple of the appropriate block size. + * 8. for non-realtime files, the extent size hint must be limited + * to half the AG size to avoid alignment extending the extent beyond the + * limits of the AG. + */ +static int +xfs_ioctl_setattr_check_extsize( + struct xfs_inode *ip, + struct fsxattr *fa) +{ + struct xfs_mount *mp = ip->i_mount; + + if ((fa->fsx_xflags & XFS_XFLAG_EXTSIZE) && !S_ISREG(ip->i_d.di_mode)) + return -EINVAL; + + if ((fa->fsx_xflags & XFS_XFLAG_EXTSZINHERIT) && + !S_ISDIR(ip->i_d.di_mode)) + return -EINVAL; + + if (S_ISREG(ip->i_d.di_mode) && ip->i_d.di_nextents && + ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize)) + return -EINVAL; + + if (fa->fsx_extsize != 0) { + xfs_extlen_t size; + xfs_fsblock_t extsize_fsb; + + extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize); + if (extsize_fsb > MAXEXTLEN) + return -EINVAL; + + if (XFS_IS_REALTIME_INODE(ip) || + (fa->fsx_xflags & XFS_XFLAG_REALTIME)) { + size = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog; + } else { + size = mp->m_sb.sb_blocksize; + if (extsize_fsb > mp->m_sb.sb_agblocks / 2) + return -EINVAL; + } + + if (fa->fsx_extsize % size) + return -EINVAL; + } else + fa->fsx_xflags &= ~(XFS_XFLAG_EXTSIZE | XFS_XFLAG_EXTSZINHERIT); + + return 0; +} + +static int +xfs_ioctl_setattr_check_projid( + struct xfs_inode *ip, + struct fsxattr *fa) +{ + /* Disallow 32bit project ids if projid32bit feature is not enabled. */ + if (fa->fsx_projid > (__uint16_t)-1 && + !xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb)) + return -EINVAL; + + /* + * Project Quota ID state is only allowed to change from within the init + * namespace. Enforce that restriction only if we are trying to change + * the quota ID state. Everything else is allowed in user namespaces. + */ + if (current_user_ns() == &init_user_ns) + return 0; + + if (xfs_get_projid(ip) != fa->fsx_projid) + return -EINVAL; + if ((fa->fsx_xflags & XFS_XFLAG_PROJINHERIT) != + (ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)) + return -EINVAL; + + return 0; +} STATIC int xfs_ioctl_setattr( xfs_inode_t *ip, - struct fsxattr *fa, - int mask) + struct fsxattr *fa) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; - unsigned int lock_flags = 0; struct xfs_dquot *udqp = NULL; struct xfs_dquot *pdqp = NULL; struct xfs_dquot *olddquot = NULL; @@ -1034,17 +1170,9 @@ xfs_ioctl_setattr( trace_xfs_ioctl_setattr(ip); - if (mp->m_flags & XFS_MOUNT_RDONLY) - return -EROFS; - if (XFS_FORCED_SHUTDOWN(mp)) - return -EIO; - - /* - * Disallow 32bit project ids when projid32bit feature is not enabled. - */ - if ((mask & FSX_PROJID) && (fa->fsx_projid > (__uint16_t)-1) && - !xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb)) - return -EINVAL; + code = xfs_ioctl_setattr_check_projid(ip, fa); + if (code) + return code; /* * If disk quotas is on, we make sure that the dquots do exist on disk, @@ -1054,7 +1182,7 @@ xfs_ioctl_setattr( * If the IDs do change before we take the ilock, we're covered * because the i_*dquot fields will get updated anyway. */ - if (XFS_IS_QUOTA_ON(mp) && (mask & FSX_PROJID)) { + if (XFS_IS_QUOTA_ON(mp)) { code = xfs_qm_vop_dqalloc(ip, ip->i_d.di_uid, ip->i_d.di_gid, fa->fsx_projid, XFS_QMOPT_PQUOTA, &udqp, NULL, &pdqp); @@ -1062,175 +1190,49 @@ xfs_ioctl_setattr( return code; } - /* - * For the other attributes, we acquire the inode lock and - * first do an error checking pass. - */ - tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE); - code = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0); - if (code) - goto error_return; - - lock_flags = XFS_ILOCK_EXCL; - xfs_ilock(ip, lock_flags); - - /* - * CAP_FOWNER overrides the following restrictions: - * - * The user ID of the calling process must be equal - * to the file owner ID, except in cases where the - * CAP_FSETID capability is applicable. - */ - if (!inode_owner_or_capable(VFS_I(ip))) { - code = -EPERM; - goto error_return; - } - - /* - * Do a quota reservation only if projid is actually going to change. - * Only allow changing of projid from init_user_ns since it is a - * non user namespace aware identifier. - */ - if (mask & FSX_PROJID) { - if (current_user_ns() != &init_user_ns) { - code = -EINVAL; - goto error_return; - } - - if (XFS_IS_QUOTA_RUNNING(mp) && - XFS_IS_PQUOTA_ON(mp) && - xfs_get_projid(ip) != fa->fsx_projid) { - ASSERT(tp); - code = xfs_qm_vop_chown_reserve(tp, ip, udqp, NULL, - pdqp, capable(CAP_FOWNER) ? - XFS_QMOPT_FORCE_RES : 0); - if (code) /* out of quota */ - goto error_return; - } + tp = xfs_ioctl_setattr_get_trans(ip); + if (IS_ERR(tp)) { + code = PTR_ERR(tp); + goto error_free_dquots; } - if (mask & FSX_EXTSIZE) { - /* - * Can't change extent size if any extents are allocated. - */ - if (ip->i_d.di_nextents && - ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != - fa->fsx_extsize)) { - code = -EINVAL; /* EFBIG? */ - goto error_return; - } - /* - * Extent size must be a multiple of the appropriate block - * size, if set at all. It must also be smaller than the - * maximum extent size supported by the filesystem. - * - * Also, for non-realtime files, limit the extent size hint to - * half the size of the AGs in the filesystem so alignment - * doesn't result in extents larger than an AG. - */ - if (fa->fsx_extsize != 0) { - xfs_extlen_t size; - xfs_fsblock_t extsize_fsb; - - extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize); - if (extsize_fsb > MAXEXTLEN) { - code = -EINVAL; - goto error_return; - } - - if (XFS_IS_REALTIME_INODE(ip) || - ((mask & FSX_XFLAGS) && - (fa->fsx_xflags & XFS_XFLAG_REALTIME))) { - size = mp->m_sb.sb_rextsize << - mp->m_sb.sb_blocklog; - } else { - size = mp->m_sb.sb_blocksize; - if (extsize_fsb > mp->m_sb.sb_agblocks / 2) { - code = -EINVAL; - goto error_return; - } - } - - if (fa->fsx_extsize % size) { - code = -EINVAL; - goto error_return; - } - } + if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp) && + xfs_get_projid(ip) != fa->fsx_projid) { + code = xfs_qm_vop_chown_reserve(tp, ip, udqp, NULL, pdqp, + capable(CAP_FOWNER) ? XFS_QMOPT_FORCE_RES : 0); + if (code) /* out of quota */ + goto error_trans_cancel; } + code = xfs_ioctl_setattr_check_extsize(ip, fa); + if (code) + goto error_trans_cancel; - if (mask & FSX_XFLAGS) { - /* - * Can't change realtime flag if any extents are allocated. - */ - if ((ip->i_d.di_nextents || ip->i_delayed_blks) && - (XFS_IS_REALTIME_INODE(ip)) != - (fa->fsx_xflags & XFS_XFLAG_REALTIME)) { - code = -EINVAL; /* EFBIG? */ - goto error_return; - } - - /* - * If realtime flag is set then must have realtime data. - */ - if ((fa->fsx_xflags & XFS_XFLAG_REALTIME)) { - if ((mp->m_sb.sb_rblocks == 0) || - (mp->m_sb.sb_rextsize == 0) || - (ip->i_d.di_extsize % mp->m_sb.sb_rextsize)) { - code = -EINVAL; - goto error_return; - } - } - - /* - * Can't modify an immutable/append-only file unless - * we have appropriate permission. - */ - if ((ip->i_d.di_flags & - (XFS_DIFLAG_IMMUTABLE|XFS_DIFLAG_APPEND) || - (fa->fsx_xflags & - (XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) && - !capable(CAP_LINUX_IMMUTABLE)) { - code = -EPERM; - goto error_return; - } - } - - xfs_trans_ijoin(tp, ip, 0); + code = xfs_ioctl_setattr_xflags(tp, ip, fa); + if (code) + goto error_trans_cancel; /* - * Change file ownership. Must be the owner or privileged. + * Change file ownership. Must be the owner or privileged. CAP_FSETID + * overrides the following restrictions: + * + * The set-user-ID and set-group-ID bits of a file will be cleared upon + * successful return from chown() */ - if (mask & FSX_PROJID) { - /* - * CAP_FSETID overrides the following restrictions: - * - * The set-user-ID and set-group-ID bits of a file will be - * cleared upon successful return from chown() - */ - if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) && - !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID)) - ip->i_d.di_mode &= ~(S_ISUID|S_ISGID); - - /* - * Change the ownerships and register quota modifications - * in the transaction. - */ - if (xfs_get_projid(ip) != fa->fsx_projid) { - if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) { - olddquot = xfs_qm_vop_chown(tp, ip, - &ip->i_pdquot, pdqp); - } - ASSERT(ip->i_d.di_version > 1); - xfs_set_projid(ip, fa->fsx_projid); - } - } + if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) && + !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID)) + ip->i_d.di_mode &= ~(S_ISUID|S_ISGID); - if (mask & FSX_XFLAGS) { - xfs_set_diflags(ip, fa->fsx_xflags); - xfs_diflags_to_linux(ip); + /* Change the ownerships and register project quota modifications */ + if (xfs_get_projid(ip) != fa->fsx_projid) { + if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) { + olddquot = xfs_qm_vop_chown(tp, ip, + &ip->i_pdquot, pdqp); + } + ASSERT(ip->i_d.di_version > 1); + xfs_set_projid(ip, fa->fsx_projid); } /* @@ -1238,34 +1240,12 @@ xfs_ioctl_setattr( * extent size hint should be set on the inode. If no extent size flags * are set on the inode then unconditionally clear the extent size hint. */ - if (mask & FSX_EXTSIZE) { - int extsize = 0; - - if (ip->i_d.di_flags & - (XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT)) - extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog; - ip->i_d.di_extsize = extsize; - } - - xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - - XFS_STATS_INC(xs_ig_attrchg); + if (ip->i_d.di_flags & (XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT)) + ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog; + else + ip->i_d.di_extsize = 0; - /* - * If this is a synchronous mount, make sure that the - * transaction goes to disk before returning to the user. - * This is slightly sub-optimal in that truncates require - * two sync transactions instead of one for wsync filesystems. - * One for the truncate and one for the timestamps since we - * don't want to change the timestamps unless we're sure the - * truncate worked. Truncates are less than 1% of the laddis - * mix so this probably isn't worth the trouble to optimize. - */ - if (mp->m_flags & XFS_MOUNT_WSYNC) - xfs_trans_set_sync(tp); code = xfs_trans_commit(tp, 0); - xfs_iunlock(ip, lock_flags); /* * Release any dquot(s) the inode had kept before chown. @@ -1276,12 +1256,11 @@ xfs_ioctl_setattr( return code; - error_return: +error_trans_cancel: + xfs_trans_cancel(tp, 0); +error_free_dquots: xfs_qm_dqrele(udqp); xfs_qm_dqrele(pdqp); - xfs_trans_cancel(tp, 0); - if (lock_flags) - xfs_iunlock(ip, lock_flags); return code; } @@ -1292,20 +1271,15 @@ xfs_ioc_fssetxattr( void __user *arg) { struct fsxattr fa; - unsigned int mask; int error; if (copy_from_user(&fa, arg, sizeof(fa))) return -EFAULT; - mask = FSX_XFLAGS | FSX_EXTSIZE | FSX_PROJID; - if (filp->f_flags & (O_NDELAY|O_NONBLOCK)) - mask |= FSX_NONBLOCK; - error = mnt_want_write_file(filp); if (error) return error; - error = xfs_ioctl_setattr(ip, &fa, mask); + error = xfs_ioctl_setattr(ip, &fa); mnt_drop_write_file(filp); return error; } @@ -1325,14 +1299,14 @@ xfs_ioc_getxflags( STATIC int xfs_ioc_setxflags( - xfs_inode_t *ip, + struct xfs_inode *ip, struct file *filp, void __user *arg) { + struct xfs_trans *tp; struct fsxattr fa; unsigned int flags; - unsigned int mask; - int error; + int error; if (copy_from_user(&flags, arg, sizeof(flags))) return -EFAULT; @@ -1342,15 +1316,26 @@ xfs_ioc_setxflags( FS_SYNC_FL)) return -EOPNOTSUPP; - mask = FSX_XFLAGS; - if (filp->f_flags & (O_NDELAY|O_NONBLOCK)) - mask |= FSX_NONBLOCK; fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip)); error = mnt_want_write_file(filp); if (error) return error; - error = xfs_ioctl_setattr(ip, &fa, mask); + + tp = xfs_ioctl_setattr_get_trans(ip); + if (IS_ERR(tp)) { + error = PTR_ERR(tp); + goto out_drop_write; + } + + error = xfs_ioctl_setattr_xflags(tp, ip, &fa); + if (error) { + xfs_trans_cancel(tp, 0); + goto out_drop_write; + } + + error = xfs_trans_commit(tp, 0); +out_drop_write: mnt_drop_write_file(filp); return error; } diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index ec6772866f3..bfc7c7c8a0c 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -423,7 +423,7 @@ xfs_compat_attrmulti_by_handle( ops = memdup_user(compat_ptr(am_hreq.ops), size); if (IS_ERR(ops)) { - error = -PTR_ERR(ops); + error = PTR_ERR(ops); goto out_dput; } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index c980e2a5086..ccb1dd0d509 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -802,7 +802,7 @@ int xfs_iomap_write_unwritten( xfs_inode_t *ip, xfs_off_t offset, - size_t count) + xfs_off_t count) { xfs_mount_t *mp = ip->i_mount; xfs_fileoff_t offset_fsb; diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 411fbb8919e..8688e663d74 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -27,6 +27,6 @@ int xfs_iomap_write_delay(struct xfs_inode *, xfs_off_t, size_t, struct xfs_bmbt_irec *); int xfs_iomap_write_allocate(struct xfs_inode *, xfs_off_t, struct xfs_bmbt_irec *); -int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, size_t); +int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t); #endif /* __XFS_IOMAP_H__*/ diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index c50311cae1b..ce80eeb8faa 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -380,18 +380,27 @@ xfs_vn_rename( struct inode *odir, struct dentry *odentry, struct inode *ndir, - struct dentry *ndentry) + struct dentry *ndentry, + unsigned int flags) { struct inode *new_inode = ndentry->d_inode; + int omode = 0; struct xfs_name oname; struct xfs_name nname; - xfs_dentry_to_name(&oname, odentry, 0); + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + return -EINVAL; + + /* if we are exchanging files, we need to set i_mode of both files */ + if (flags & RENAME_EXCHANGE) + omode = ndentry->d_inode->i_mode; + + xfs_dentry_to_name(&oname, odentry, omode); xfs_dentry_to_name(&nname, ndentry, odentry->d_inode->i_mode); return xfs_rename(XFS_I(odir), &oname, XFS_I(odentry->d_inode), - XFS_I(ndir), &nname, new_inode ? - XFS_I(new_inode) : NULL); + XFS_I(ndir), &nname, + new_inode ? XFS_I(new_inode) : NULL, flags); } /* @@ -1144,7 +1153,7 @@ static const struct inode_operations xfs_dir_inode_operations = { */ .rmdir = xfs_vn_unlink, .mknod = xfs_vn_mknod, - .rename = xfs_vn_rename, + .rename2 = xfs_vn_rename, .get_acl = xfs_get_acl, .set_acl = xfs_set_acl, .getattr = xfs_vn_getattr, @@ -1172,7 +1181,7 @@ static const struct inode_operations xfs_dir_ci_inode_operations = { */ .rmdir = xfs_vn_unlink, .mknod = xfs_vn_mknod, - .rename = xfs_vn_rename, + .rename2 = xfs_vn_rename, .get_acl = xfs_get_acl, .set_acl = xfs_set_acl, .getattr = xfs_vn_getattr, diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index e408bf5a3ff..bcc7cfabb78 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -33,6 +33,7 @@ #include "xfs_fsops.h" #include "xfs_cksum.h" #include "xfs_sysfs.h" +#include "xfs_sb.h" kmem_zone_t *xfs_log_ticket_zone; @@ -1290,9 +1291,20 @@ xfs_log_worker( struct xfs_mount *mp = log->l_mp; /* dgc: errors ignored - not fatal and nowhere to report them */ - if (xfs_log_need_covered(mp)) - xfs_fs_log_dummy(mp); - else + if (xfs_log_need_covered(mp)) { + /* + * Dump a transaction into the log that contains no real change. + * This is needed to stamp the current tail LSN into the log + * during the covering operation. + * + * We cannot use an inode here for this - that will push dirty + * state back up into the VFS and then periodic inode flushing + * will prevent log covering from making progress. Hence we + * synchronously log the superblock instead to ensure the + * superblock is immediately unpinned and can be written back. + */ + xfs_sync_sb(mp, true); + } else xfs_log_force(mp, 0); /* start pushing all the metadata that is currently dirty */ @@ -1395,6 +1407,8 @@ xlog_alloc_log( ASSERT(xfs_buf_islocked(bp)); xfs_buf_unlock(bp); + /* use high priority wq for log I/O completion */ + bp->b_ioend_wq = mp->m_log_workqueue; bp->b_iodone = xlog_iodone; log->l_xbuf = bp; @@ -1427,6 +1441,8 @@ xlog_alloc_log( ASSERT(xfs_buf_islocked(bp)); xfs_buf_unlock(bp); + /* use high priority wq for log I/O completion */ + bp->b_ioend_wq = mp->m_log_workqueue; bp->b_iodone = xlog_iodone; iclog->ic_bp = bp; iclog->ic_data = bp->b_addr; @@ -1806,8 +1822,6 @@ xlog_sync( XFS_BUF_ZEROFLAGS(bp); XFS_BUF_ASYNC(bp); bp->b_flags |= XBF_SYNCIO; - /* use high priority completion wq */ - bp->b_ioend_wq = log->l_mp->m_log_workqueue; if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) { bp->b_flags |= XBF_FUA; @@ -1856,8 +1870,6 @@ xlog_sync( bp->b_flags |= XBF_SYNCIO; if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) bp->b_flags |= XBF_FUA; - /* use high priority completion wq */ - bp->b_ioend_wq = log->l_mp->m_log_workqueue; ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1); ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize); @@ -2027,7 +2039,7 @@ xlog_print_tic_res( " total reg = %u bytes (o/flow = %u bytes)\n" " ophdrs = %u (ophdr space = %u bytes)\n" " ophdr + reg = %u bytes\n" - " num regions = %u\n", + " num regions = %u", ((ticket->t_trans_type <= 0 || ticket->t_trans_type > XFS_TRANS_TYPE_MAX) ? "bad-trans-type" : trans_type_str[ticket->t_trans_type-1]), diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index d3d38836f87..4fa80e63eea 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -408,11 +408,11 @@ xfs_update_alignment(xfs_mount_t *mp) if (xfs_sb_version_hasdalign(sbp)) { if (sbp->sb_unit != mp->m_dalign) { sbp->sb_unit = mp->m_dalign; - mp->m_update_flags |= XFS_SB_UNIT; + mp->m_update_sb = true; } if (sbp->sb_width != mp->m_swidth) { sbp->sb_width = mp->m_swidth; - mp->m_update_flags |= XFS_SB_WIDTH; + mp->m_update_sb = true; } } else { xfs_warn(mp, @@ -583,38 +583,19 @@ int xfs_mount_reset_sbqflags( struct xfs_mount *mp) { - int error; - struct xfs_trans *tp; - mp->m_qflags = 0; - /* - * It is OK to look at sb_qflags here in mount path, - * without m_sb_lock. - */ + /* It is OK to look at sb_qflags in the mount path without m_sb_lock. */ if (mp->m_sb.sb_qflags == 0) return 0; spin_lock(&mp->m_sb_lock); mp->m_sb.sb_qflags = 0; spin_unlock(&mp->m_sb_lock); - /* - * If the fs is readonly, let the incore superblock run - * with quotas off but don't flush the update out to disk - */ - if (mp->m_flags & XFS_MOUNT_RDONLY) + if (!xfs_fs_writable(mp, SB_FREEZE_WRITE)) return 0; - tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE); - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_sbchange, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - xfs_alert(mp, "%s: Superblock update failed!", __func__); - return error; - } - - xfs_mod_sb(tp, XFS_SB_QFLAGS); - return xfs_trans_commit(tp, 0); + return xfs_sync_sb(mp, false); } __uint64_t @@ -659,26 +640,25 @@ xfs_mountfs( xfs_sb_mount_common(mp, sbp); /* - * Check for a mismatched features2 values. Older kernels - * read & wrote into the wrong sb offset for sb_features2 - * on some platforms due to xfs_sb_t not being 64bit size aligned - * when sb_features2 was added, which made older superblock - * reading/writing routines swap it as a 64-bit value. + * Check for a mismatched features2 values. Older kernels read & wrote + * into the wrong sb offset for sb_features2 on some platforms due to + * xfs_sb_t not being 64bit size aligned when sb_features2 was added, + * which made older superblock reading/writing routines swap it as a + * 64-bit value. * * For backwards compatibility, we make both slots equal. * - * If we detect a mismatched field, we OR the set bits into the - * existing features2 field in case it has already been modified; we - * don't want to lose any features. We then update the bad location - * with the ORed value so that older kernels will see any features2 - * flags, and mark the two fields as needing updates once the - * transaction subsystem is online. + * If we detect a mismatched field, we OR the set bits into the existing + * features2 field in case it has already been modified; we don't want + * to lose any features. We then update the bad location with the ORed + * value so that older kernels will see any features2 flags. The + * superblock writeback code ensures the new sb_features2 is copied to + * sb_bad_features2 before it is logged or written to disk. */ if (xfs_sb_has_mismatched_features2(sbp)) { xfs_warn(mp, "correcting sb_features alignment problem"); sbp->sb_features2 |= sbp->sb_bad_features2; - sbp->sb_bad_features2 = sbp->sb_features2; - mp->m_update_flags |= XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2; + mp->m_update_sb = true; /* * Re-check for ATTR2 in case it was found in bad_features2 @@ -692,17 +672,17 @@ xfs_mountfs( if (xfs_sb_version_hasattr2(&mp->m_sb) && (mp->m_flags & XFS_MOUNT_NOATTR2)) { xfs_sb_version_removeattr2(&mp->m_sb); - mp->m_update_flags |= XFS_SB_FEATURES2; + mp->m_update_sb = true; /* update sb_versionnum for the clearing of the morebits */ if (!sbp->sb_features2) - mp->m_update_flags |= XFS_SB_VERSIONNUM; + mp->m_update_sb = true; } /* always use v2 inodes by default now */ if (!(mp->m_sb.sb_versionnum & XFS_SB_VERSION_NLINKBIT)) { mp->m_sb.sb_versionnum |= XFS_SB_VERSION_NLINKBIT; - mp->m_update_flags |= XFS_SB_VERSIONNUM; + mp->m_update_sb = true; } /* @@ -895,8 +875,8 @@ xfs_mountfs( * the next remount into writeable mode. Otherwise we would never * perform the update e.g. for the root filesystem. */ - if (mp->m_update_flags && !(mp->m_flags & XFS_MOUNT_RDONLY)) { - error = xfs_mount_log_sb(mp, mp->m_update_flags); + if (mp->m_update_sb && !(mp->m_flags & XFS_MOUNT_RDONLY)) { + error = xfs_sync_sb(mp, false); if (error) { xfs_warn(mp, "failed to write sb changes"); goto out_rtunmount; @@ -1103,9 +1083,6 @@ xfs_fs_writable( int xfs_log_sbcount(xfs_mount_t *mp) { - xfs_trans_t *tp; - int error; - /* allow this to proceed during the freeze sequence... */ if (!xfs_fs_writable(mp, SB_FREEZE_COMPLETE)) return 0; @@ -1119,17 +1096,7 @@ xfs_log_sbcount(xfs_mount_t *mp) if (!xfs_sb_version_haslazysbcount(&mp->m_sb)) return 0; - tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT, KM_SLEEP); - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - return error; - } - - xfs_mod_sb(tp, XFS_SB_IFREE | XFS_SB_ICOUNT | XFS_SB_FDBLOCKS); - xfs_trans_set_sync(tp); - error = xfs_trans_commit(tp, 0); - return error; + return xfs_sync_sb(mp, true); } /* @@ -1423,34 +1390,6 @@ xfs_freesb( } /* - * Used to log changes to the superblock unit and width fields which could - * be altered by the mount options, as well as any potential sb_features2 - * fixup. Only the first superblock is updated. - */ -int -xfs_mount_log_sb( - xfs_mount_t *mp, - __int64_t fields) -{ - xfs_trans_t *tp; - int error; - - ASSERT(fields & (XFS_SB_UNIT | XFS_SB_WIDTH | XFS_SB_UUID | - XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2 | - XFS_SB_VERSIONNUM)); - - tp = xfs_trans_alloc(mp, XFS_TRANS_SB_UNIT); - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - return error; - } - xfs_mod_sb(tp, fields); - error = xfs_trans_commit(tp, 0); - return error; -} - -/* * If the underlying (data/log/rt) device is readonly, there are some * operations that cannot proceed. */ diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 22ccf69d4d3..a5b2ff82265 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -162,8 +162,7 @@ typedef struct xfs_mount { struct delayed_work m_reclaim_work; /* background inode reclaim */ struct delayed_work m_eofblocks_work; /* background eof blocks trimming */ - __int64_t m_update_flags; /* sb flags we need to update - on the next remount,rw */ + bool m_update_sb; /* sb needs update in mount */ int64_t m_low_space[XFS_LOWSP_MAX]; /* low free space thresholds */ struct xfs_kobj m_kobj; @@ -378,7 +377,7 @@ extern void xfs_unmountfs(xfs_mount_t *); extern int xfs_mod_incore_sb(xfs_mount_t *, xfs_sb_field_t, int64_t, int); extern int xfs_mod_incore_sb_batch(xfs_mount_t *, xfs_mod_sb_t *, uint, int); -extern int xfs_mount_log_sb(xfs_mount_t *, __int64_t); +extern int xfs_mount_log_sb(xfs_mount_t *); extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int); extern int xfs_readsb(xfs_mount_t *, int); extern void xfs_freesb(xfs_mount_t *); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 79fb19dd9c8..3e818627954 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -714,7 +714,6 @@ STATIC int xfs_qm_qino_alloc( xfs_mount_t *mp, xfs_inode_t **ip, - __int64_t sbfields, uint flags) { xfs_trans_t *tp; @@ -777,11 +776,6 @@ xfs_qm_qino_alloc( spin_lock(&mp->m_sb_lock); if (flags & XFS_QMOPT_SBVERSION) { ASSERT(!xfs_sb_version_hasquota(&mp->m_sb)); - ASSERT((sbfields & (XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO | - XFS_SB_GQUOTINO | XFS_SB_PQUOTINO | XFS_SB_QFLAGS)) == - (XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO | - XFS_SB_GQUOTINO | XFS_SB_PQUOTINO | - XFS_SB_QFLAGS)); xfs_sb_version_addquota(&mp->m_sb); mp->m_sb.sb_uquotino = NULLFSINO; @@ -798,7 +792,7 @@ xfs_qm_qino_alloc( else mp->m_sb.sb_pquotino = (*ip)->i_ino; spin_unlock(&mp->m_sb_lock); - xfs_mod_sb(tp, sbfields); + xfs_log_sb(tp); if ((error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES))) { xfs_alert(mp, "%s failed (error %d)!", __func__, error); @@ -1451,7 +1445,7 @@ xfs_qm_mount_quotas( spin_unlock(&mp->m_sb_lock); if (sbf != (mp->m_qflags & XFS_MOUNT_QUOTA_ALL)) { - if (xfs_qm_write_sb_changes(mp, XFS_SB_QFLAGS)) { + if (xfs_sync_sb(mp, false)) { /* * We could only have been turning quotas off. * We aren't in very good shape actually because @@ -1482,7 +1476,6 @@ xfs_qm_init_quotainos( struct xfs_inode *gip = NULL; struct xfs_inode *pip = NULL; int error; - __int64_t sbflags = 0; uint flags = 0; ASSERT(mp->m_quotainfo); @@ -1517,9 +1510,6 @@ xfs_qm_init_quotainos( } } else { flags |= XFS_QMOPT_SBVERSION; - sbflags |= (XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO | - XFS_SB_GQUOTINO | XFS_SB_PQUOTINO | - XFS_SB_QFLAGS); } /* @@ -1530,7 +1520,6 @@ xfs_qm_init_quotainos( */ if (XFS_IS_UQUOTA_ON(mp) && uip == NULL) { error = xfs_qm_qino_alloc(mp, &uip, - sbflags | XFS_SB_UQUOTINO, flags | XFS_QMOPT_UQUOTA); if (error) goto error_rele; @@ -1539,7 +1528,6 @@ xfs_qm_init_quotainos( } if (XFS_IS_GQUOTA_ON(mp) && gip == NULL) { error = xfs_qm_qino_alloc(mp, &gip, - sbflags | XFS_SB_GQUOTINO, flags | XFS_QMOPT_GQUOTA); if (error) goto error_rele; @@ -1548,7 +1536,6 @@ xfs_qm_init_quotainos( } if (XFS_IS_PQUOTA_ON(mp) && pip == NULL) { error = xfs_qm_qino_alloc(mp, &pip, - sbflags | XFS_SB_PQUOTINO, flags | XFS_QMOPT_PQUOTA); if (error) goto error_rele; @@ -1587,32 +1574,6 @@ xfs_qm_dqfree_one( xfs_qm_dqdestroy(dqp); } -/* - * Start a transaction and write the incore superblock changes to - * disk. flags parameter indicates which fields have changed. - */ -int -xfs_qm_write_sb_changes( - xfs_mount_t *mp, - __int64_t flags) -{ - xfs_trans_t *tp; - int error; - - tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE); - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_sbchange, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - return error; - } - - xfs_mod_sb(tp, flags); - error = xfs_trans_commit(tp, 0); - - return error; -} - - /* --------------- utility functions for vnodeops ---------------- */ diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index 41f6c0b9d51..0d4d3590cf8 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -157,7 +157,6 @@ struct xfs_dquot_acct { #define XFS_QM_RTBWARNLIMIT 5 extern void xfs_qm_destroy_quotainfo(struct xfs_mount *); -extern int xfs_qm_write_sb_changes(struct xfs_mount *, __int64_t); /* dquot stuff */ extern void xfs_qm_dqpurge_all(struct xfs_mount *, uint); diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index cb6168ec92c..9b965db4580 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -91,8 +91,7 @@ xfs_qm_scall_quotaoff( mutex_unlock(&q->qi_quotaofflock); /* XXX what to do if error ? Revert back to old vals incore ? */ - error = xfs_qm_write_sb_changes(mp, XFS_SB_QFLAGS); - return error; + return xfs_sync_sb(mp, false); } dqtype = 0; @@ -313,7 +312,6 @@ xfs_qm_scall_quotaon( { int error; uint qf; - __int64_t sbflags; flags &= (XFS_ALL_QUOTA_ACCT | XFS_ALL_QUOTA_ENFD); /* @@ -321,30 +319,22 @@ xfs_qm_scall_quotaon( */ flags &= ~(XFS_ALL_QUOTA_ACCT); - sbflags = 0; - if (flags == 0) { xfs_debug(mp, "%s: zero flags, m_qflags=%x", __func__, mp->m_qflags); return -EINVAL; } - /* No fs can turn on quotas with a delayed effect */ - ASSERT((flags & XFS_ALL_QUOTA_ACCT) == 0); - /* * Can't enforce without accounting. We check the superblock * qflags here instead of m_qflags because rootfs can have * quota acct on ondisk without m_qflags' knowing. */ - if (((flags & XFS_UQUOTA_ACCT) == 0 && - (mp->m_sb.sb_qflags & XFS_UQUOTA_ACCT) == 0 && + if (((mp->m_sb.sb_qflags & XFS_UQUOTA_ACCT) == 0 && (flags & XFS_UQUOTA_ENFD)) || - ((flags & XFS_GQUOTA_ACCT) == 0 && - (mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) == 0 && + ((mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) == 0 && (flags & XFS_GQUOTA_ENFD)) || - ((flags & XFS_PQUOTA_ACCT) == 0 && - (mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) == 0 && + ((mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) == 0 && (flags & XFS_PQUOTA_ENFD))) { xfs_debug(mp, "%s: Can't enforce without acct, flags=%x sbflags=%x", @@ -369,11 +359,11 @@ xfs_qm_scall_quotaon( /* * There's nothing to change if it's the same. */ - if ((qf & flags) == flags && sbflags == 0) + if ((qf & flags) == flags) return -EEXIST; - sbflags |= XFS_SB_QFLAGS; - if ((error = xfs_qm_write_sb_changes(mp, sbflags))) + error = xfs_sync_sb(mp, false); + if (error) return error; /* * If we aren't trying to switch on quota enforcement, we are done. @@ -383,8 +373,7 @@ xfs_qm_scall_quotaon( ((mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) != (mp->m_qflags & XFS_PQUOTA_ACCT)) || ((mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) != - (mp->m_qflags & XFS_GQUOTA_ACCT)) || - (flags & XFS_ALL_QUOTA_ENFD) == 0) + (mp->m_qflags & XFS_GQUOTA_ACCT))) return 0; if (! XFS_IS_QUOTA_RUNNING(mp)) @@ -421,20 +410,12 @@ xfs_qm_scall_getqstat( memset(out, 0, sizeof(fs_quota_stat_t)); out->qs_version = FS_QSTAT_VERSION; - if (!xfs_sb_version_hasquota(&mp->m_sb)) { - out->qs_uquota.qfs_ino = NULLFSINO; - out->qs_gquota.qfs_ino = NULLFSINO; - return 0; - } - out->qs_flags = (__uint16_t) xfs_qm_export_flags(mp->m_qflags & (XFS_ALL_QUOTA_ACCT| XFS_ALL_QUOTA_ENFD)); - if (q) { - uip = q->qi_uquotaip; - gip = q->qi_gquotaip; - pip = q->qi_pquotaip; - } + uip = q->qi_uquotaip; + gip = q->qi_gquotaip; + pip = q->qi_pquotaip; if (!uip && mp->m_sb.sb_uquotino != NULLFSINO) { if (xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, 0, 0, &uip) == 0) @@ -480,14 +461,13 @@ xfs_qm_scall_getqstat( if (temppqip) IRELE(pip); } - if (q) { - out->qs_incoredqs = q->qi_dquots; - out->qs_btimelimit = q->qi_btimelimit; - out->qs_itimelimit = q->qi_itimelimit; - out->qs_rtbtimelimit = q->qi_rtbtimelimit; - out->qs_bwarnlimit = q->qi_bwarnlimit; - out->qs_iwarnlimit = q->qi_iwarnlimit; - } + out->qs_incoredqs = q->qi_dquots; + out->qs_btimelimit = q->qi_btimelimit; + out->qs_itimelimit = q->qi_itimelimit; + out->qs_rtbtimelimit = q->qi_rtbtimelimit; + out->qs_bwarnlimit = q->qi_bwarnlimit; + out->qs_iwarnlimit = q->qi_iwarnlimit; + return 0; } @@ -508,13 +488,6 @@ xfs_qm_scall_getqstatv( bool tempgqip = false; bool temppqip = false; - if (!xfs_sb_version_hasquota(&mp->m_sb)) { - out->qs_uquota.qfs_ino = NULLFSINO; - out->qs_gquota.qfs_ino = NULLFSINO; - out->qs_pquota.qfs_ino = NULLFSINO; - return 0; - } - out->qs_flags = (__uint16_t) xfs_qm_export_flags(mp->m_qflags & (XFS_ALL_QUOTA_ACCT| XFS_ALL_QUOTA_ENFD)); @@ -522,11 +495,9 @@ xfs_qm_scall_getqstatv( out->qs_gquota.qfs_ino = mp->m_sb.sb_gquotino; out->qs_pquota.qfs_ino = mp->m_sb.sb_pquotino; - if (q) { - uip = q->qi_uquotaip; - gip = q->qi_gquotaip; - pip = q->qi_pquotaip; - } + uip = q->qi_uquotaip; + gip = q->qi_gquotaip; + pip = q->qi_pquotaip; if (!uip && mp->m_sb.sb_uquotino != NULLFSINO) { if (xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, 0, 0, &uip) == 0) @@ -561,14 +532,13 @@ xfs_qm_scall_getqstatv( if (temppqip) IRELE(pip); } - if (q) { - out->qs_incoredqs = q->qi_dquots; - out->qs_btimelimit = q->qi_btimelimit; - out->qs_itimelimit = q->qi_itimelimit; - out->qs_rtbtimelimit = q->qi_rtbtimelimit; - out->qs_bwarnlimit = q->qi_bwarnlimit; - out->qs_iwarnlimit = q->qi_iwarnlimit; - } + out->qs_incoredqs = q->qi_dquots; + out->qs_btimelimit = q->qi_btimelimit; + out->qs_itimelimit = q->qi_itimelimit; + out->qs_rtbtimelimit = q->qi_rtbtimelimit; + out->qs_bwarnlimit = q->qi_bwarnlimit; + out->qs_iwarnlimit = q->qi_iwarnlimit; + return 0; } @@ -800,7 +770,7 @@ xfs_qm_log_quotaoff( mp->m_sb.sb_qflags = (mp->m_qflags & ~(flags)) & XFS_MOUNT_QUOTA_ALL; spin_unlock(&mp->m_sb_lock); - xfs_mod_sb(tp, XFS_SB_QFLAGS); + xfs_log_sb(tp); /* * We have to make sure that the transaction is secure on disk before we diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c index 801a84c1cdc..6923905ab33 100644 --- a/fs/xfs/xfs_quotaops.c +++ b/fs/xfs/xfs_quotaops.c @@ -64,19 +64,10 @@ xfs_fs_get_xstatev( return xfs_qm_scall_getqstatv(mp, fqs); } -STATIC int -xfs_fs_set_xstate( - struct super_block *sb, - unsigned int uflags, - int op) +static unsigned int +xfs_quota_flags(unsigned int uflags) { - struct xfs_mount *mp = XFS_M(sb); - unsigned int flags = 0; - - if (sb->s_flags & MS_RDONLY) - return -EROFS; - if (op != Q_XQUOTARM && !XFS_IS_QUOTA_RUNNING(mp)) - return -ENOSYS; + unsigned int flags = 0; if (uflags & FS_QUOTA_UDQ_ACCT) flags |= XFS_UQUOTA_ACCT; @@ -91,16 +82,39 @@ xfs_fs_set_xstate( if (uflags & FS_QUOTA_PDQ_ENFD) flags |= XFS_PQUOTA_ENFD; - switch (op) { - case Q_XQUOTAON: - return xfs_qm_scall_quotaon(mp, flags); - case Q_XQUOTAOFF: - if (!XFS_IS_QUOTA_ON(mp)) - return -EINVAL; - return xfs_qm_scall_quotaoff(mp, flags); - } + return flags; +} + +STATIC int +xfs_quota_enable( + struct super_block *sb, + unsigned int uflags) +{ + struct xfs_mount *mp = XFS_M(sb); + + if (sb->s_flags & MS_RDONLY) + return -EROFS; + if (!XFS_IS_QUOTA_RUNNING(mp)) + return -ENOSYS; + + return xfs_qm_scall_quotaon(mp, xfs_quota_flags(uflags)); +} + +STATIC int +xfs_quota_disable( + struct super_block *sb, + unsigned int uflags) +{ + struct xfs_mount *mp = XFS_M(sb); + + if (sb->s_flags & MS_RDONLY) + return -EROFS; + if (!XFS_IS_QUOTA_RUNNING(mp)) + return -ENOSYS; + if (!XFS_IS_QUOTA_ON(mp)) + return -EINVAL; - return -EINVAL; + return xfs_qm_scall_quotaoff(mp, xfs_quota_flags(uflags)); } STATIC int @@ -166,7 +180,8 @@ xfs_fs_set_dqblk( const struct quotactl_ops xfs_quotactl_operations = { .get_xstatev = xfs_fs_get_xstatev, .get_xstate = xfs_fs_get_xstate, - .set_xstate = xfs_fs_set_xstate, + .quota_enable = xfs_quota_enable, + .quota_disable = xfs_quota_disable, .rm_xquota = xfs_fs_rm_xquota, .get_dqblk = xfs_fs_get_dqblk, .set_dqblk = xfs_fs_set_dqblk, diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 19cbda19636..f2449fd8692 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -685,7 +685,7 @@ xfs_blkdev_get( mp); if (IS_ERR(*bdevp)) { error = PTR_ERR(*bdevp); - xfs_warn(mp, "Invalid device [%s], error=%d\n", name, error); + xfs_warn(mp, "Invalid device [%s], error=%d", name, error); } return error; @@ -1111,6 +1111,11 @@ xfs_fs_statfs( statp->f_files, mp->m_maxicount); + /* If sb_icount overshot maxicount, report actual allocation */ + statp->f_files = max_t(typeof(statp->f_files), + statp->f_files, + sbp->sb_icount); + /* make sure statp->f_ffree does not underflow */ ffree = statp->f_files - (sbp->sb_icount - sbp->sb_ifree); statp->f_ffree = max_t(__int64_t, ffree, 0); @@ -1257,13 +1262,13 @@ xfs_fs_remount( * If this is the first remount to writeable state we * might have some superblock changes to update. */ - if (mp->m_update_flags) { - error = xfs_mount_log_sb(mp, mp->m_update_flags); + if (mp->m_update_sb) { + error = xfs_sync_sb(mp, false); if (error) { xfs_warn(mp, "failed to write sb changes"); return error; } - mp->m_update_flags = 0; + mp->m_update_sb = false; } /* @@ -1293,8 +1298,9 @@ xfs_fs_remount( /* * Second stage of a freeze. The data is already frozen so we only - * need to take care of the metadata. Once that's done write a dummy - * record to dirty the log in case of a crash while frozen. + * need to take care of the metadata. Once that's done sync the superblock + * to the log to dirty it in case of a crash while frozen. This ensures that we + * will recover the unlinked inode lists on the next mount. */ STATIC int xfs_fs_freeze( @@ -1304,7 +1310,7 @@ xfs_fs_freeze( xfs_save_resvblks(mp); xfs_quiesce_attr(mp); - return xfs_fs_log_dummy(mp); + return xfs_sync_sb(mp, true); } STATIC int diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c index 1743b9f8e23..a0c8067cea6 100644 --- a/fs/xfs/xfs_sysctl.c +++ b/fs/xfs/xfs_sysctl.c @@ -149,24 +149,6 @@ static struct ctl_table xfs_table[] = { .extra2 = &xfs_params.inherit_noatim.max }, { - .procname = "xfsbufd_centisecs", - .data = &xfs_params.xfs_buf_timer.val, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &xfs_params.xfs_buf_timer.min, - .extra2 = &xfs_params.xfs_buf_timer.max - }, - { - .procname = "age_buffer_centisecs", - .data = &xfs_params.xfs_buf_age.val, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &xfs_params.xfs_buf_age.min, - .extra2 = &xfs_params.xfs_buf_age.max - }, - { .procname = "inherit_nosymlinks", .data = &xfs_params.inherit_nosym.val, .maxlen = sizeof(int), diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index fa3135b9bf0..eb90cd59a0e 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -472,6 +472,7 @@ xfs_trans_apply_sb_deltas( whole = 1; } + xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); if (whole) /* * Log the whole thing, the fields are noncontiguous. diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 0a4d4ab6d9a..75798412859 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -327,9 +327,10 @@ xfs_trans_read_buf_map( return -EIO; } - if (tp) + if (tp) { _xfs_trans_bjoin(tp, bp, 1); - trace_xfs_trans_read_buf(bp->b_fspriv); + trace_xfs_trans_read_buf(bp->b_fspriv); + } *bpp = bp; return 0; diff --git a/include/acpi/acbuffer.h b/include/acpi/acbuffer.h index d5ec6c87810..6b040f4ddfa 100644 --- a/include/acpi/acbuffer.h +++ b/include/acpi/acbuffer.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h index 5a0a3e5daf8..03aacfb3e98 100644 --- a/include/acpi/acconfig.h +++ b/include/acpi/acconfig.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h index 8b06e4c1dd5..11c3a011dcb 100644 --- a/include/acpi/acexcep.h +++ b/include/acpi/acexcep.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h index 7461327e14e..273de709495 100644 --- a/include/acpi/acnames.h +++ b/include/acpi/acnames.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h index 1baae6edda8..9318a87ee39 100644 --- a/include/acpi/acoutput.h +++ b/include/acpi/acoutput.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/acpi.h b/include/acpi/acpi.h index a08e55a263c..b0bb30ebb80 100644 --- a/include/acpi/acpi.h +++ b/include/acpi/acpi.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h index 03b3e6d405f..0bc78df66d4 100644 --- a/include/acpi/acpiosxf.h +++ b/include/acpi/acpiosxf.h @@ -7,7 +7,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 5ba78464c1b..d56f5d72213 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -46,7 +46,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20141107 +#define ACPI_CA_VERSION 0x20150204 #include <acpi/acconfig.h> #include <acpi/actypes.h> @@ -569,6 +569,14 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status address, void *context)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status + acpi_install_gpe_raw_handler(acpi_handle + gpe_device, + u32 gpe_number, + u32 type, + acpi_gpe_handler + address, + void *context)) +ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_remove_gpe_handler(acpi_handle gpe_device, u32 gpe_number, acpi_gpe_handler @@ -891,12 +899,6 @@ ACPI_APP_DEPENDENT_RETURN_VOID(ACPI_PRINTF_LIKE(1) ACPI_GLOBAL(u8, acpi_gbl_permanent_mmap); ACPI_EXTERNAL_RETURN_STATUS(acpi_status - acpi_get_id(acpi_handle object, - acpi_owner_id * out_type)) - -ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_unload_table_id(acpi_owner_id id)) - -ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_get_table_with_size(acpi_string signature, u32 instance, struct acpi_table_header diff --git a/include/acpi/acrestyp.h b/include/acpi/acrestyp.h index eb760ca0b2e..ebe24263859 100644 --- a/include/acpi/acrestyp.h +++ b/include/acpi/acrestyp.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -305,43 +305,51 @@ struct acpi_resource_source { u8 max_address_fixed; \ union acpi_resource_attribute info; -struct acpi_resource_address { -ACPI_RESOURCE_ADDRESS_COMMON}; - -struct acpi_resource_address16 { - ACPI_RESOURCE_ADDRESS_COMMON u16 granularity; +struct acpi_address16_attribute { + u16 granularity; u16 minimum; u16 maximum; u16 translation_offset; u16 address_length; - struct acpi_resource_source resource_source; }; -struct acpi_resource_address32 { - ACPI_RESOURCE_ADDRESS_COMMON u32 granularity; +struct acpi_address32_attribute { + u32 granularity; u32 minimum; u32 maximum; u32 translation_offset; u32 address_length; - struct acpi_resource_source resource_source; }; -struct acpi_resource_address64 { - ACPI_RESOURCE_ADDRESS_COMMON u64 granularity; +struct acpi_address64_attribute { + u64 granularity; u64 minimum; u64 maximum; u64 translation_offset; u64 address_length; +}; + +struct acpi_resource_address { +ACPI_RESOURCE_ADDRESS_COMMON}; + +struct acpi_resource_address16 { + ACPI_RESOURCE_ADDRESS_COMMON struct acpi_address16_attribute address; + struct acpi_resource_source resource_source; +}; + +struct acpi_resource_address32 { + ACPI_RESOURCE_ADDRESS_COMMON struct acpi_address32_attribute address; + struct acpi_resource_source resource_source; +}; + +struct acpi_resource_address64 { + ACPI_RESOURCE_ADDRESS_COMMON struct acpi_address64_attribute address; struct acpi_resource_source resource_source; }; struct acpi_resource_extended_address64 { ACPI_RESOURCE_ADDRESS_COMMON u8 revision_ID; - u64 granularity; - u64 minimum; - u64 maximum; - u64 translation_offset; - u64 address_length; + struct acpi_address64_attribute address; u64 type_specific; }; diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h index bee19d8170c..d4081fef109 100644 --- a/include/acpi/actbl.h +++ b/include/acpi/actbl.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 29e79370641..b80b0e6dabc 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index ecff62405f1..f06d75e5fa5 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h index 5480cb2236b..440ca8104b4 100644 --- a/include/acpi/actbl3.h +++ b/include/acpi/actbl3.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index bbef17368e4..b034f1068df 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -744,7 +744,7 @@ typedef u32 acpi_event_status; /* * GPE info flags - Per GPE * +-------+-+-+---+ - * | 7:4 |3|2|1:0| + * | 7:5 |4|3|2:0| * +-------+-+-+---+ * | | | | * | | | +-- Type of dispatch:to method, handler, notify, or none @@ -756,13 +756,15 @@ typedef u32 acpi_event_status; #define ACPI_GPE_DISPATCH_METHOD (u8) 0x01 #define ACPI_GPE_DISPATCH_HANDLER (u8) 0x02 #define ACPI_GPE_DISPATCH_NOTIFY (u8) 0x03 -#define ACPI_GPE_DISPATCH_MASK (u8) 0x03 +#define ACPI_GPE_DISPATCH_RAW_HANDLER (u8) 0x04 +#define ACPI_GPE_DISPATCH_MASK (u8) 0x07 +#define ACPI_GPE_DISPATCH_TYPE(flags) ((u8) ((flags) & ACPI_GPE_DISPATCH_MASK)) -#define ACPI_GPE_LEVEL_TRIGGERED (u8) 0x04 +#define ACPI_GPE_LEVEL_TRIGGERED (u8) 0x08 #define ACPI_GPE_EDGE_TRIGGERED (u8) 0x00 -#define ACPI_GPE_XRUPT_TYPE_MASK (u8) 0x04 +#define ACPI_GPE_XRUPT_TYPE_MASK (u8) 0x08 -#define ACPI_GPE_CAN_WAKE (u8) 0x08 +#define ACPI_GPE_CAN_WAKE (u8) 0x10 /* * Flags for GPE and Lock interfaces diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h index 5f8cc1fa327..ad74dc51d5b 100644 --- a/include/acpi/platform/acenv.h +++ b/include/acpi/platform/acenv.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/platform/acenvex.h b/include/acpi/platform/acenvex.h index 2b612384c99..71e5ec5b07a 100644 --- a/include/acpi/platform/acenvex.h +++ b/include/acpi/platform/acenvex.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h index 384875da371..f54de0a6355 100644 --- a/include/acpi/platform/acgcc.h +++ b/include/acpi/platform/acgcc.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index 1ba7c190c2c..74ba46c8157 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h index 568d4b88671..acedc3f026d 100644 --- a/include/acpi/platform/aclinuxex.h +++ b/include/acpi/platform/aclinuxex.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 177d5973b13..129de9204d1 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -474,21 +474,6 @@ static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { return pte; } - -static inline pte_t pte_file_clear_soft_dirty(pte_t pte) -{ - return pte; -} - -static inline pte_t pte_file_mksoft_dirty(pte_t pte) -{ - return pte; -} - -static inline int pte_file_soft_dirty(pte_t pte) -{ - return 0; -} #endif #ifndef __HAVE_PFNMAP_TRACKING diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d459cd17b47..24c7aa8b1d2 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -27,6 +27,7 @@ #include <linux/errno.h> #include <linux/ioport.h> /* for struct resource */ +#include <linux/resource_ext.h> #include <linux/device.h> #include <linux/property.h> @@ -151,6 +152,10 @@ int acpi_map_cpu(acpi_handle handle, int physid, int *pcpu); int acpi_unmap_cpu(int cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ +#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC +int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr); +#endif + int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base); int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base); int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base); @@ -288,22 +293,25 @@ extern int pnpacpi_disabled; bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_address_space(struct acpi_resource *ares, - struct resource *res); + struct resource_win *win); bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, - struct resource *res); + struct resource_win *win); unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable); bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res); -struct resource_list_entry { - struct list_head node; - struct resource res; -}; - void acpi_dev_free_resource_list(struct list_head *list); int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, int (*preproc)(struct acpi_resource *, void *), void *preproc_data); +int acpi_dev_filter_resource_type(struct acpi_resource *ares, + unsigned long types); + +static inline int acpi_dev_filter_resource_type_cb(struct acpi_resource *ares, + void *arg) +{ + return acpi_dev_filter_resource_type(ares, (unsigned long)arg); +} int acpi_check_resource_conflict(const struct resource *res); diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 642d6ae4030..a270f25ee7c 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -21,16 +21,20 @@ struct device; struct ata_port_info; struct ahci_host_priv; struct platform_device; +struct scsi_host_template; int ahci_platform_enable_clks(struct ahci_host_priv *hpriv); void ahci_platform_disable_clks(struct ahci_host_priv *hpriv); +int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv); +void ahci_platform_disable_regulators(struct ahci_host_priv *hpriv); int ahci_platform_enable_resources(struct ahci_host_priv *hpriv); void ahci_platform_disable_resources(struct ahci_host_priv *hpriv); struct ahci_host_priv *ahci_platform_get_resources( struct platform_device *pdev); int ahci_platform_init_host(struct platform_device *pdev, struct ahci_host_priv *hpriv, - const struct ata_port_info *pi_template); + const struct ata_port_info *pi_template, + struct scsi_host_template *sht); int ahci_platform_suspend_host(struct device *dev); int ahci_platform_resume_host(struct device *dev); diff --git a/include/linux/ata.h b/include/linux/ata.h index f2f4d8da97c..1648026e06b 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -503,7 +503,7 @@ struct ata_bmdma_prd { #define ata_id_has_dma(id) ((id)[ATA_ID_CAPABILITY] & (1 << 8)) #define ata_id_has_ncq(id) ((id)[ATA_ID_SATA_CAPABILITY] & (1 << 8)) #define ata_id_queue_depth(id) (((id)[ATA_ID_QUEUE_DEPTH] & 0x1f) + 1) -#define ata_id_removeable(id) ((id)[ATA_ID_CONFIG] & (1 << 7)) +#define ata_id_removable(id) ((id)[ATA_ID_CONFIG] & (1 << 7)) #define ata_id_has_atapi_AN(id) \ ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ diff --git a/include/linux/ata_platform.h b/include/linux/ata_platform.h index 5c618a08422..619d9e78e64 100644 --- a/include/linux/ata_platform.h +++ b/include/linux/ata_platform.h @@ -10,12 +10,15 @@ struct pata_platform_info { unsigned int ioport_shift; }; +struct scsi_host_template; + extern int __pata_platform_probe(struct device *dev, struct resource *io_res, struct resource *ctl_res, struct resource *irq_res, unsigned int ioport_shift, - int __pio_mask); + int __pio_mask, + struct scsi_host_template *sht); /* * Marvell SATA private data diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index da0dae0600e..b9cb94c3102 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -943,6 +943,8 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, #else /* !CONFIG_CGROUPS */ +struct cgroup_subsys_state; + static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_fork(struct task_struct *p) {} @@ -955,6 +957,8 @@ static inline int cgroupstats_build(struct cgroupstats *stats, return -EINVAL; } +static inline void css_put(struct cgroup_subsys_state *css) {} + /* No cgroups - nothing to do */ static inline int cgroup_attach_task_all(struct task_struct *from, struct task_struct *t) diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 98c4f9b12b0..e4a96fb1440 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -15,6 +15,10 @@ SUBSYS(cpu) SUBSYS(cpuacct) #endif +#if IS_ENABLED(CONFIG_BLK_CGROUP) +SUBSYS(blkio) +#endif + #if IS_ENABLED(CONFIG_MEMCG) SUBSYS(memory) #endif @@ -31,10 +35,6 @@ SUBSYS(freezer) SUBSYS(net_cls) #endif -#if IS_ENABLED(CONFIG_BLK_CGROUP) -SUBSYS(blkio) -#endif - #if IS_ENABLED(CONFIG_CGROUP_PERF) SUBSYS(perf_event) #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 33063f872ee..176bf816875 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -385,7 +385,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s /* Is this type a native word size -- useful for atomic operations */ #ifndef __native_word -# define __native_word(t) (sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) +# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) #endif /* Compile time object size, -1 for unknown */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 4d078cebafd..2ee4888c1f4 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -66,8 +66,6 @@ struct cpufreq_policy { unsigned int shared_type; /* ACPI: ANY or ALL affected CPUs should set cpufreq */ unsigned int cpu; /* cpu nr of CPU managing this policy */ - unsigned int last_cpu; /* cpu nr of previous CPU that managed - * this policy */ struct clk *clk; struct cpufreq_cpuinfo cpuinfo;/* see above */ @@ -113,6 +111,9 @@ struct cpufreq_policy { wait_queue_head_t transition_wait; struct task_struct *transition_task; /* Task which is doing the transition */ + /* cpufreq-stats */ + struct cpufreq_stats *stats; + /* For cpufreq driver's internal use */ void *driver_data; }; @@ -367,9 +368,8 @@ static inline void cpufreq_resume(void) {} #define CPUFREQ_INCOMPATIBLE (1) #define CPUFREQ_NOTIFY (2) #define CPUFREQ_START (3) -#define CPUFREQ_UPDATE_POLICY_CPU (4) -#define CPUFREQ_CREATE_POLICY (5) -#define CPUFREQ_REMOVE_POLICY (6) +#define CPUFREQ_CREATE_POLICY (4) +#define CPUFREQ_REMOVE_POLICY (5) #ifdef CONFIG_CPU_FREQ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list); diff --git a/include/linux/devfreq-event.h b/include/linux/devfreq-event.h new file mode 100644 index 00000000000..602fbbfcfee --- /dev/null +++ b/include/linux/devfreq-event.h @@ -0,0 +1,196 @@ +/* + * devfreq-event: a framework to provide raw data and events of devfreq devices + * + * Copyright (C) 2014 Samsung Electronics + * Author: Chanwoo Choi <cw00.choi@samsung.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __LINUX_DEVFREQ_EVENT_H__ +#define __LINUX_DEVFREQ_EVENT_H__ + +#include <linux/device.h> + +/** + * struct devfreq_event_dev - the devfreq-event device + * + * @node : Contain the devfreq-event device that have been registered. + * @dev : the device registered by devfreq-event class. dev.parent is + * the device using devfreq-event. + * @lock : a mutex to protect accessing devfreq-event. + * @enable_count: the number of enable function have been called. + * @desc : the description for devfreq-event device. + * + * This structure contains devfreq-event device information. + */ +struct devfreq_event_dev { + struct list_head node; + + struct device dev; + struct mutex lock; + u32 enable_count; + + const struct devfreq_event_desc *desc; +}; + +/** + * struct devfreq_event_data - the devfreq-event data + * + * @load_count : load count of devfreq-event device for the given period. + * @total_count : total count of devfreq-event device for the given period. + * each count may represent a clock cycle, a time unit + * (ns/us/...), or anything the device driver wants. + * Generally, utilization is load_count / total_count. + * + * This structure contains the data of devfreq-event device for polling period. + */ +struct devfreq_event_data { + unsigned long load_count; + unsigned long total_count; +}; + +/** + * struct devfreq_event_ops - the operations of devfreq-event device + * + * @enable : Enable the devfreq-event device. + * @disable : Disable the devfreq-event device. + * @reset : Reset all setting of the devfreq-event device. + * @set_event : Set the specific event type for the devfreq-event device. + * @get_event : Get the result of the devfreq-event devie with specific + * event type. + * + * This structure contains devfreq-event device operations which can be + * implemented by devfreq-event device drivers. + */ +struct devfreq_event_ops { + /* Optional functions */ + int (*enable)(struct devfreq_event_dev *edev); + int (*disable)(struct devfreq_event_dev *edev); + int (*reset)(struct devfreq_event_dev *edev); + + /* Mandatory functions */ + int (*set_event)(struct devfreq_event_dev *edev); + int (*get_event)(struct devfreq_event_dev *edev, + struct devfreq_event_data *edata); +}; + +/** + * struct devfreq_event_desc - the descriptor of devfreq-event device + * + * @name : the name of devfreq-event device. + * @driver_data : the private data for devfreq-event driver. + * @ops : the operation to control devfreq-event device. + * + * Each devfreq-event device is described with a this structure. + * This structure contains the various data for devfreq-event device. + */ +struct devfreq_event_desc { + const char *name; + void *driver_data; + + struct devfreq_event_ops *ops; +}; + +#if defined(CONFIG_PM_DEVFREQ_EVENT) +extern int devfreq_event_enable_edev(struct devfreq_event_dev *edev); +extern int devfreq_event_disable_edev(struct devfreq_event_dev *edev); +extern bool devfreq_event_is_enabled(struct devfreq_event_dev *edev); +extern int devfreq_event_set_event(struct devfreq_event_dev *edev); +extern int devfreq_event_get_event(struct devfreq_event_dev *edev, + struct devfreq_event_data *edata); +extern int devfreq_event_reset_event(struct devfreq_event_dev *edev); +extern struct devfreq_event_dev *devfreq_event_get_edev_by_phandle( + struct device *dev, int index); +extern int devfreq_event_get_edev_count(struct device *dev); +extern struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev, + struct devfreq_event_desc *desc); +extern int devfreq_event_remove_edev(struct devfreq_event_dev *edev); +extern struct devfreq_event_dev *devm_devfreq_event_add_edev(struct device *dev, + struct devfreq_event_desc *desc); +extern void devm_devfreq_event_remove_edev(struct device *dev, + struct devfreq_event_dev *edev); +static inline void *devfreq_event_get_drvdata(struct devfreq_event_dev *edev) +{ + return edev->desc->driver_data; +} +#else +static inline int devfreq_event_enable_edev(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline int devfreq_event_disable_edev(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline bool devfreq_event_is_enabled(struct devfreq_event_dev *edev) +{ + return false; +} + +static inline int devfreq_event_set_event(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline int devfreq_event_get_event(struct devfreq_event_dev *edev, + struct devfreq_event_data *edata) +{ + return -EINVAL; +} + +static inline int devfreq_event_reset_event(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline void *devfreq_event_get_drvdata(struct devfreq_event_dev *edev) +{ + return ERR_PTR(-EINVAL); +} + +static inline struct devfreq_event_dev *devfreq_event_get_edev_by_phandle( + struct device *dev, int index) +{ + return ERR_PTR(-EINVAL); +} + +static inline int devfreq_event_get_edev_count(struct device *dev) +{ + return -EINVAL; +} + +static inline struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev, + struct devfreq_event_desc *desc) +{ + return ERR_PTR(-EINVAL); +} + +static inline int devfreq_event_remove_edev(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline struct devfreq_event_dev *devm_devfreq_event_add_edev( + struct device *dev, + struct devfreq_event_desc *desc) +{ + return ERR_PTR(-EINVAL); +} + +static inline void devm_devfreq_event_remove_edev(struct device *dev, + struct devfreq_event_dev *edev) +{ +} + +static inline void *devfreq_event_get_drvdata(struct devfreq_event_dev *edev) +{ + return NULL; +} +#endif /* CONFIG_PM_DEVFREQ_EVENT */ + +#endif /* __LINUX_DEVFREQ_EVENT_H__ */ diff --git a/include/linux/dqblk_v1.h b/include/linux/dqblk_v1.h index 3713a7232dd..c0d4d1e2a45 100644 --- a/include/linux/dqblk_v1.h +++ b/include/linux/dqblk_v1.h @@ -5,9 +5,6 @@ #ifndef _LINUX_DQBLK_V1_H #define _LINUX_DQBLK_V1_H -/* Root squash turned on */ -#define V1_DQF_RSQUASH 1 - /* Numbers of blocks needed for updates */ #define V1_INIT_ALLOC 1 #define V1_INIT_REWRITE 1 diff --git a/include/linux/efi.h b/include/linux/efi.h index 0238d612750..b674837e2b9 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -848,7 +848,7 @@ efi_guidcmp (efi_guid_t left, efi_guid_t right) } static inline char * -efi_guid_unparse(efi_guid_t *guid, char *out) +efi_guid_to_str(efi_guid_t *guid, char *out) { sprintf(out, "%pUl", guid->b); return out; diff --git a/include/linux/fs.h b/include/linux/fs.h index 42efe13077b..f125b88443b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -401,7 +401,6 @@ struct address_space { spinlock_t tree_lock; /* and lock protecting it */ atomic_t i_mmap_writable;/* count VM_SHARED mappings */ struct rb_root i_mmap; /* tree of private and shared mappings */ - struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */ /* Protected by tree_lock together with the radix tree */ unsigned long nrpages; /* number of total pages */ @@ -493,8 +492,7 @@ static inline void i_mmap_unlock_read(struct address_space *mapping) */ static inline int mapping_mapped(struct address_space *mapping) { - return !RB_EMPTY_ROOT(&mapping->i_mmap) || - !list_empty(&mapping->i_mmap_nonlinear); + return !RB_EMPTY_ROOT(&mapping->i_mmap); } /* @@ -625,7 +623,7 @@ struct inode { atomic_t i_readcount; /* struct files open RO */ #endif const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ - struct file_lock *i_flock; + struct file_lock_context *i_flctx; struct address_space i_data; struct list_head i_devices; union { @@ -885,6 +883,8 @@ static inline struct file *get_file(struct file *f) /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; +struct file_lock; + struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); @@ -898,7 +898,7 @@ struct lock_manager_operations { void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_break)(struct file_lock *); - int (*lm_change)(struct file_lock **, int, struct list_head *); + int (*lm_change)(struct file_lock *, int, struct list_head *); void (*lm_setup)(struct file_lock *, void **); }; @@ -923,17 +923,17 @@ int locks_in_grace(struct net *); * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * - * The i_flock list is ordered by: + * The varous i_flctx lists are ordered by: * - * 1) lock type -- FL_LEASEs first, then FL_FLOCK, and finally FL_POSIX - * 2) lock owner - * 3) lock range start - * 4) lock range end + * 1) lock owner + * 2) lock range start + * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ struct file_lock { struct file_lock *fl_next; /* singly linked list for this inode */ + struct list_head fl_list; /* link into file_lock_context */ struct hlist_node fl_link; /* node in global lists */ struct list_head fl_block; /* circular list of blocked processes */ fl_owner_t fl_owner; @@ -964,6 +964,16 @@ struct file_lock { } fl_u; }; +struct file_lock_context { + spinlock_t flc_lock; + struct list_head flc_flock; + struct list_head flc_posix; + struct list_head flc_lease; + int flc_flock_cnt; + int flc_posix_cnt; + int flc_lease_cnt; +}; + /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define INT_LIMIT(x) (~((x)1 << (sizeof(x)*8 - 1))) @@ -990,6 +1000,7 @@ extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); extern int fcntl_getlease(struct file *filp); /* fs/locks.c */ +void locks_free_lock_context(struct file_lock_context *ctx); void locks_free_lock(struct file_lock *fl); extern void locks_init_lock(struct file_lock *); extern struct file_lock * locks_alloc_lock(void); @@ -1010,7 +1021,7 @@ extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int t extern void lease_get_mtime(struct inode *, struct timespec *time); extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); extern int vfs_setlease(struct file *, long, struct file_lock **, void **); -extern int lease_modify(struct file_lock **, int, struct list_head *); +extern int lease_modify(struct file_lock *, int, struct list_head *); #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) @@ -1047,6 +1058,11 @@ static inline int fcntl_getlease(struct file *filp) return F_UNLCK; } +static inline void +locks_free_lock_context(struct file_lock_context *ctx) +{ +} + static inline void locks_init_lock(struct file_lock *fl) { return; @@ -1137,7 +1153,7 @@ static inline int vfs_setlease(struct file *filp, long arg, return -EINVAL; } -static inline int lease_modify(struct file_lock **before, int arg, +static inline int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { return -EINVAL; @@ -1959,7 +1975,7 @@ static inline int locks_verify_truncate(struct inode *inode, struct file *filp, loff_t size) { - if (inode->i_flock && mandatory_lock(inode)) + if (inode->i_flctx && mandatory_lock(inode)) return locks_mandatory_area( FLOCK_VERIFY_WRITE, inode, filp, size < inode->i_size ? size : inode->i_size, @@ -1973,11 +1989,12 @@ static inline int break_lease(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts - * taken are done before checking inode->i_flock. Otherwise, we could - * end up racing with tasks trying to set a new lease on this file. + * taken are done before checking i_flctx->flc_lease. Otherwise, we + * could end up racing with tasks trying to set a new lease on this + * file. */ smp_mb(); - if (inode->i_flock) + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_LEASE); return 0; } @@ -1986,11 +2003,12 @@ static inline int break_deleg(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts - * taken are done before checking inode->i_flock. Otherwise, we could - * end up racing with tasks trying to set a new lease on this file. + * taken are done before checking i_flctx->flc_lease. Otherwise, we + * could end up racing with tasks trying to set a new lease on this + * file. */ smp_mb(); - if (inode->i_flock) + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_DELEG); return 0; } @@ -2481,8 +2499,6 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); -extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr, - unsigned long size, pgoff_t pgoff); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 1c804b057fb..7ee1774edee 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -101,8 +101,10 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, new_dir_mask |= FS_ISDIR; } - fsnotify(old_dir, old_dir_mask, old_dir, FSNOTIFY_EVENT_INODE, old_name, fs_cookie); - fsnotify(new_dir, new_dir_mask, new_dir, FSNOTIFY_EVENT_INODE, new_name, fs_cookie); + fsnotify(old_dir, old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_name, + fs_cookie); + fsnotify(new_dir, new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_name, + fs_cookie); if (target) fsnotify_link_count(target); diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 0bebb5c348b..d36f68b08ac 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -595,7 +595,7 @@ extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); extern void ftrace_profile_free_filter(struct perf_event *event); extern void *perf_trace_buf_prepare(int size, unsigned short type, - struct pt_regs *regs, int *rctxp); + struct pt_regs **regs, int *rctxp); static inline void perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr, diff --git a/include/linux/hid.h b/include/linux/hid.h index 06c4607744f..efc7787a41a 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -574,7 +574,9 @@ static inline void hid_set_drvdata(struct hid_device *hdev, void *data) #define HID_GLOBAL_STACK_SIZE 4 #define HID_COLLECTION_STACK_SIZE 4 -#define HID_SCAN_FLAG_MT_WIN_8 0x00000001 +#define HID_SCAN_FLAG_MT_WIN_8 BIT(0) +#define HID_SCAN_FLAG_VENDOR_SPECIFIC BIT(1) +#define HID_SCAN_FLAG_GD_POINTER BIT(2) struct hid_parser { struct hid_global global; diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index a036d058a24..05f6df1fdf5 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -170,6 +170,7 @@ enum hrtimer_base_type { * @clock_was_set: Indicates that clock was set from irq context. * @expires_next: absolute time of the next event which was scheduled * via clock_set_next_event() + * @in_hrtirq: hrtimer_interrupt() is currently executing * @hres_active: State of high resolution mode * @hang_detected: The last hrtimer interrupt detected a hang * @nr_events: Total number of hrtimer interrupt events @@ -185,6 +186,7 @@ struct hrtimer_cpu_base { unsigned int clock_was_set; #ifdef CONFIG_HIGH_RES_TIMERS ktime_t expires_next; + int in_hrtirq; int hres_active; int hang_detected; unsigned long nr_events; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 431b7fc605c..7d785635992 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -86,7 +86,7 @@ void free_huge_page(struct page *page); pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); #endif -extern unsigned long hugepages_treat_as_movable; +extern int hugepages_treat_as_movable; extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages; diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 31229e0be90..d32615280be 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -956,15 +956,6 @@ void __log_wait_for_space(journal_t *journal); extern void __journal_drop_transaction(journal_t *, transaction_t *); extern int cleanup_journal_tail(journal_t *); -/* Debugging code only: */ - -#define jbd_ENOSYS() \ -do { \ - printk (KERN_ERR "JBD unimplemented function %s\n", __func__); \ - current->state = TASK_UNINTERRUPTIBLE; \ - schedule(); \ -} while (1) - /* * is_journal_abort * diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 704b9a599b2..20e7f78041c 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1251,15 +1251,6 @@ void __jbd2_log_wait_for_space(journal_t *journal); extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); -/* Debugging code only: */ - -#define jbd_ENOSYS() \ -do { \ - printk (KERN_ERR "JBD unimplemented function %s\n", __func__); \ - current->state = TASK_UNINTERRUPTIBLE; \ - schedule(); \ -} while (1) - /* * is_journal_abort * diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 64ce58bee6f..e42e7dc34c6 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -471,6 +471,7 @@ extern enum system_states { #define TAINT_OOT_MODULE 12 #define TAINT_UNSIGNED_MODULE 13 #define TAINT_SOFTLOCKUP 14 +#define TAINT_LIVEPATCH 15 extern const char hex_asc[]; #define hex_asc_lo(x) hex_asc[((x) & 0x0f)] diff --git a/include/linux/ktime.h b/include/linux/ktime.h index c9d645ad98f..5fc3d108307 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -166,7 +166,17 @@ static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2) } #if BITS_PER_LONG < 64 -extern u64 ktime_divns(const ktime_t kt, s64 div); +extern u64 __ktime_divns(const ktime_t kt, s64 div); +static inline u64 ktime_divns(const ktime_t kt, s64 div) +{ + if (__builtin_constant_p(div) && !(div >> 32)) { + u64 ns = kt.tv64; + do_div(ns, div); + return ns; + } else { + return __ktime_divns(kt, div); + } +} #else /* BITS_PER_LONG < 64 */ # define ktime_divns(kt, div) (u64)((kt).tv64 / (div)) #endif @@ -186,6 +196,11 @@ static inline s64 ktime_us_delta(const ktime_t later, const ktime_t earlier) return ktime_to_us(ktime_sub(later, earlier)); } +static inline s64 ktime_ms_delta(const ktime_t later, const ktime_t earlier) +{ + return ktime_to_ms(ktime_sub(later, earlier)); +} + static inline ktime_t ktime_add_us(const ktime_t kt, const u64 usec) { return ktime_add_ns(kt, usec * NSEC_PER_USEC); diff --git a/include/linux/libata.h b/include/linux/libata.h index 91f705de2c0..61df823ac86 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1340,6 +1340,12 @@ extern const struct ata_port_operations ata_base_port_ops; extern const struct ata_port_operations sata_port_ops; extern struct device_attribute *ata_common_sdev_attrs[]; +/* + * All sht initializers (BASE, PIO, BMDMA, NCQ) must be instantiated + * by the edge drivers. Because the 'module' field of sht must be the + * edge driver's module reference, otherwise the driver can be unloaded + * even if the scsi_device is being accessed. + */ #define ATA_BASE_SHT(drv_name) \ .module = THIS_MODULE, \ .name = drv_name, \ diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h new file mode 100644 index 00000000000..95023fd8b00 --- /dev/null +++ b/include/linux/livepatch.h @@ -0,0 +1,133 @@ +/* + * livepatch.h - Kernel Live Patching Core + * + * Copyright (C) 2014 Seth Jennings <sjenning@redhat.com> + * Copyright (C) 2014 SUSE + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _LINUX_LIVEPATCH_H_ +#define _LINUX_LIVEPATCH_H_ + +#include <linux/module.h> +#include <linux/ftrace.h> + +#if IS_ENABLED(CONFIG_LIVEPATCH) + +#include <asm/livepatch.h> + +enum klp_state { + KLP_DISABLED, + KLP_ENABLED +}; + +/** + * struct klp_func - function structure for live patching + * @old_name: name of the function to be patched + * @new_func: pointer to the patched function code + * @old_addr: a hint conveying at what address the old function + * can be found (optional, vmlinux patches only) + * @kobj: kobject for sysfs resources + * @state: tracks function-level patch application state + * @stack_node: list node for klp_ops func_stack list + */ +struct klp_func { + /* external */ + const char *old_name; + void *new_func; + /* + * The old_addr field is optional and can be used to resolve + * duplicate symbol names in the vmlinux object. If this + * information is not present, the symbol is located by name + * with kallsyms. If the name is not unique and old_addr is + * not provided, the patch application fails as there is no + * way to resolve the ambiguity. + */ + unsigned long old_addr; + + /* internal */ + struct kobject kobj; + enum klp_state state; + struct list_head stack_node; +}; + +/** + * struct klp_reloc - relocation structure for live patching + * @loc: address where the relocation will be written + * @val: address of the referenced symbol (optional, + * vmlinux patches only) + * @type: ELF relocation type + * @name: name of the referenced symbol (for lookup/verification) + * @addend: offset from the referenced symbol + * @external: symbol is either exported or within the live patch module itself + */ +struct klp_reloc { + unsigned long loc; + unsigned long val; + unsigned long type; + const char *name; + int addend; + int external; +}; + +/** + * struct klp_object - kernel object structure for live patching + * @name: module name (or NULL for vmlinux) + * @relocs: relocation entries to be applied at load time + * @funcs: function entries for functions to be patched in the object + * @kobj: kobject for sysfs resources + * @mod: kernel module associated with the patched object + * (NULL for vmlinux) + * @state: tracks object-level patch application state + */ +struct klp_object { + /* external */ + const char *name; + struct klp_reloc *relocs; + struct klp_func *funcs; + + /* internal */ + struct kobject *kobj; + struct module *mod; + enum klp_state state; +}; + +/** + * struct klp_patch - patch structure for live patching + * @mod: reference to the live patch module + * @objs: object entries for kernel objects to be patched + * @list: list node for global list of registered patches + * @kobj: kobject for sysfs resources + * @state: tracks patch-level application state + */ +struct klp_patch { + /* external */ + struct module *mod; + struct klp_object *objs; + + /* internal */ + struct list_head list; + struct kobject kobj; + enum klp_state state; +}; + +extern int klp_register_patch(struct klp_patch *); +extern int klp_unregister_patch(struct klp_patch *); +extern int klp_enable_patch(struct klp_patch *); +extern int klp_disable_patch(struct klp_patch *); + +#endif /* CONFIG_LIVEPATCH */ + +#endif /* _LINUX_LIVEPATCH_H_ */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7c95af8d552..fb212e1d700 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -403,10 +403,9 @@ void memcg_update_array_size(int num_groups); struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep); void __memcg_kmem_put_cache(struct kmem_cache *cachep); -int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order); -void __memcg_uncharge_slab(struct kmem_cache *cachep, int order); - -int __memcg_cleanup_cache_params(struct kmem_cache *s); +int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, + unsigned long nr_pages); +void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages); /** * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed. diff --git a/include/linux/mm.h b/include/linux/mm.h index dd5ea3016fc..65db4aee738 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -138,7 +138,6 @@ extern unsigned int kobjsize(const void *objp); #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ -#define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ #define VM_ARCH_2 0x02000000 #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ @@ -206,21 +205,19 @@ extern unsigned int kobjsize(const void *objp); extern pgprot_t protection_map[16]; #define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */ -#define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */ -#define FAULT_FLAG_MKWRITE 0x04 /* Fault was mkwrite of existing pte */ -#define FAULT_FLAG_ALLOW_RETRY 0x08 /* Retry fault if blocking */ -#define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */ -#define FAULT_FLAG_KILLABLE 0x20 /* The fault task is in SIGKILL killable region */ -#define FAULT_FLAG_TRIED 0x40 /* second try */ -#define FAULT_FLAG_USER 0x80 /* The fault originated in userspace */ +#define FAULT_FLAG_MKWRITE 0x02 /* Fault was mkwrite of existing pte */ +#define FAULT_FLAG_ALLOW_RETRY 0x04 /* Retry fault if blocking */ +#define FAULT_FLAG_RETRY_NOWAIT 0x08 /* Don't drop mmap_sem and wait when retrying */ +#define FAULT_FLAG_KILLABLE 0x10 /* The fault task is in SIGKILL killable region */ +#define FAULT_FLAG_TRIED 0x20 /* Second try */ +#define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */ /* * vm_fault is filled by the the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask * of VM_FAULT_xxx flags that give details about how the fault was handled. * - * pgoff should be used in favour of virtual_address, if possible. If pgoff - * is used, one may implement ->remap_pages to get nonlinear mapping support. + * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { unsigned int flags; /* FAULT_FLAG_xxx flags */ @@ -287,9 +284,13 @@ struct vm_operations_struct { struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr); #endif - /* called by sys_remap_file_pages() to populate non-linear mapping */ - int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr, - unsigned long size, pgoff_t pgoff); + /* + * Called by vm_normal_page() for special PTEs to find the + * page for @addr. This is useful if the default behavior + * (using pte_page()) would not find the correct page. + */ + struct page *(*find_special_page)(struct vm_area_struct *vma, + unsigned long addr); }; struct mmu_gather; @@ -446,6 +447,12 @@ static inline struct page *compound_head_by_tail(struct page *tail) return tail; } +/* + * Since either compound page could be dismantled asynchronously in THP + * or we access asynchronously arbitrary positioned struct page, there + * would be tail flag race. To handle this race, we should call + * smp_rmb() before checking tail flag. compound_head_by_tail() did it. + */ static inline struct page *compound_head(struct page *page) { if (unlikely(PageTail(page))) @@ -454,6 +461,18 @@ static inline struct page *compound_head(struct page *page) } /* + * If we access compound page synchronously such as access to + * allocated page, there is no need to handle tail flag race, so we can + * check tail flag directly without any synchronization primitive. + */ +static inline struct page *compound_head_fast(struct page *page) +{ + if (unlikely(PageTail(page))) + return page->first_page; + return page; +} + +/* * The atomic page->_mapcount, starts from -1: so that transitions * both from it and to it can be tracked, using atomic_inc_and_test * and atomic_add_negative(-1). @@ -531,7 +550,14 @@ static inline void get_page(struct page *page) static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); - return compound_head(page); + + /* + * We don't need to worry about synchronization of tail flag + * when we call virt_to_head_page() since it is only called for + * already allocated page and this page won't be freed until + * this virt_to_head_page() is finished. So use _fast variant. + */ + return compound_head_fast(page); } /* @@ -1121,7 +1147,6 @@ extern void user_shm_unlock(size_t, struct user_struct *); * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { - struct vm_area_struct *nonlinear_vma; /* Check page->index if set */ struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ @@ -1777,12 +1802,6 @@ struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, for (vma = vma_interval_tree_iter_first(root, start, last); \ vma; vma = vma_interval_tree_iter_next(vma, start, last)) -static inline void vma_nonlinear_insert(struct vm_area_struct *vma, - struct list_head *list) -{ - list_add_tail(&vma->shared.nonlinear, list); -} - void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root *root); void anon_vma_interval_tree_remove(struct anon_vma_chain *node, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6d34aa266a8..07c8bd3f7b4 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -273,15 +273,11 @@ struct vm_area_struct { /* * For areas with an address space and backing store, - * linkage into the address_space->i_mmap interval tree, or - * linkage of vma in the address_space->i_mmap_nonlinear list. + * linkage into the address_space->i_mmap interval tree. */ - union { - struct { - struct rb_node rb; - unsigned long rb_subtree_last; - } linear; - struct list_head nonlinear; + struct { + struct rb_node rb; + unsigned long rb_subtree_last; } shared; /* diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h index 90230d5811c..3a6490e81b2 100644 --- a/include/linux/osq_lock.h +++ b/include/linux/osq_lock.h @@ -5,8 +5,11 @@ * An MCS like lock especially tailored for optimistic spinning for sleeping * lock implementations (mutex, rwsem, etc). */ - -#define OSQ_UNLOCKED_VAL (0) +struct optimistic_spin_node { + struct optimistic_spin_node *next, *prev; + int locked; /* 1 if lock acquired */ + int cpu; /* encoded CPU # + 1 value */ +}; struct optimistic_spin_queue { /* @@ -16,6 +19,8 @@ struct optimistic_spin_queue { atomic_t tail; }; +#define OSQ_UNLOCKED_VAL (0) + /* Init macro and function. */ #define OSQ_LOCK_UNLOCKED { ATOMIC_INIT(OSQ_UNLOCKED_VAL) } @@ -24,4 +29,7 @@ static inline void osq_lock_init(struct optimistic_spin_queue *lock) atomic_set(&lock->tail, OSQ_UNLOCKED_VAL); } +extern bool osq_lock(struct optimistic_spin_queue *lock); +extern void osq_unlock(struct optimistic_spin_queue *lock); + #endif diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index e1f5fcd7979..5ed7bdaf22d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -121,8 +121,12 @@ enum pageflags { PG_fscache = PG_private_2, /* page backed by cache */ /* XEN */ + /* Pinned in Xen as a read-only pagetable page. */ PG_pinned = PG_owner_priv_1, + /* Pinned as part of domain save (see xen_mm_pin_all()). */ PG_savepinned = PG_dirty, + /* Has a grant mapping of another (foreign) domain's page. */ + PG_foreign = PG_owner_priv_1, /* SLOB */ PG_slob_free = PG_private, @@ -215,6 +219,7 @@ __PAGEFLAG(Slab, slab) PAGEFLAG(Checked, checked) /* Used by some filesystems */ PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */ PAGEFLAG(SavePinned, savepinned); /* Xen */ +PAGEFLAG(Foreign, foreign); /* Xen */ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked) __SETPAGEFLAG(SwapBacked, swapbacked) diff --git a/include/linux/pci.h b/include/linux/pci.h index 9603094ed59..211e9da8a7d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -29,6 +29,7 @@ #include <linux/atomic.h> #include <linux/device.h> #include <linux/io.h> +#include <linux/resource_ext.h> #include <uapi/linux/pci.h> #include <linux/pci_ids.h> @@ -177,6 +178,8 @@ enum pci_dev_flags { PCI_DEV_FLAG_PCIE_BRIDGE_ALIAS = (__force pci_dev_flags_t) (1 << 5), /* Do not use bus resets for device */ PCI_DEV_FLAGS_NO_BUS_RESET = (__force pci_dev_flags_t) (1 << 6), + /* Do not use PM reset even if device advertises NoSoftRst- */ + PCI_DEV_FLAGS_NO_PM_RESET = (__force pci_dev_flags_t) (1 << 7), }; enum pci_irq_reroute_variant { @@ -397,16 +400,10 @@ static inline int pci_channel_offline(struct pci_dev *pdev) return (pdev->error_state != pci_channel_io_normal); } -struct pci_host_bridge_window { - struct list_head list; - struct resource *res; /* host bridge aperture (CPU address) */ - resource_size_t offset; /* bus address + offset = CPU address */ -}; - struct pci_host_bridge { struct device dev; struct pci_bus *bus; /* root bus */ - struct list_head windows; /* pci_host_bridge_windows */ + struct list_head windows; /* resource_entry */ void (*release_fn)(struct pci_host_bridge *); void *release_data; }; @@ -562,6 +559,7 @@ static inline int pcibios_err_to_errno(int err) /* Low-level architecture-dependent routines */ struct pci_ops { + void __iomem *(*map_bus)(struct pci_bus *bus, unsigned int devfn, int where); int (*read)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val); int (*write)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val); }; @@ -859,6 +857,16 @@ int pci_bus_write_config_word(struct pci_bus *bus, unsigned int devfn, int where, u16 val); int pci_bus_write_config_dword(struct pci_bus *bus, unsigned int devfn, int where, u32 val); + +int pci_generic_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val); +int pci_generic_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val); +int pci_generic_config_read32(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val); +int pci_generic_config_write32(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val); + struct pci_ops *pci_bus_set_ops(struct pci_bus *bus, struct pci_ops *ops); static inline int pci_read_config_byte(const struct pci_dev *dev, int where, u8 *val) @@ -1850,6 +1858,8 @@ static inline void pci_set_of_node(struct pci_dev *dev) { } static inline void pci_release_of_node(struct pci_dev *dev) { } static inline void pci_set_bus_of_node(struct pci_bus *bus) { } static inline void pci_release_bus_of_node(struct pci_bus *bus) { } +static inline struct device_node * +pci_device_to_OF_node(const struct pci_dev *pdev) { return NULL; } #endif /* CONFIG_OF */ #ifdef CONFIG_EEH diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index b4337646388..12c9b485beb 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -128,8 +128,22 @@ static inline void percpu_ref_kill(struct percpu_ref *ref) static inline bool __ref_is_percpu(struct percpu_ref *ref, unsigned long __percpu **percpu_countp) { - /* paired with smp_store_release() in percpu_ref_reinit() */ - unsigned long percpu_ptr = lockless_dereference(ref->percpu_count_ptr); + unsigned long percpu_ptr; + + /* + * The value of @ref->percpu_count_ptr is tested for + * !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then + * used as a pointer. If the compiler generates a separate fetch + * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in + * between contaminating the pointer value, meaning that + * ACCESS_ONCE() is required when fetching it. + * + * Also, we need a data dependency barrier to be paired with + * smp_store_release() in __percpu_ref_switch_to_percpu(). + * + * Use lockless deref which contains both. + */ + percpu_ptr = lockless_dereference(ref->percpu_count_ptr); /* * Theoretically, the following could test just ATOMIC; however, @@ -233,7 +247,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_inc(*percpu_count); ret = true; - } else if (!(ACCESS_ONCE(ref->percpu_count_ptr) & __PERCPU_REF_DEAD)) { + } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { ret = atomic_long_inc_not_zero(&ref->count); } @@ -281,6 +295,20 @@ static inline void percpu_ref_put(struct percpu_ref *ref) } /** + * percpu_ref_is_dying - test whether a percpu refcount is dying or dead + * @ref: percpu_ref to test + * + * Returns %true if @ref is dying or dead. + * + * This function is safe to call as long as @ref is between init and exit + * and the caller is responsible for synchronizing against state changes. + */ +static inline bool percpu_ref_is_dying(struct percpu_ref *ref) +{ + return ref->percpu_count_ptr & __PERCPU_REF_DEAD; +} + +/** * percpu_ref_is_zero - test whether a percpu refcount reached zero * @ref: percpu_ref to test * diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 664de5a4ec4..5cad0e6f355 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -469,6 +469,7 @@ struct perf_event_context { */ struct mutex mutex; + struct list_head active_ctx_list; struct list_head pinned_groups; struct list_head flexible_groups; struct list_head event_list; @@ -519,7 +520,6 @@ struct perf_cpu_context { int exclusive; struct hrtimer hrtimer; ktime_t hrtimer_interval; - struct list_head rotation_list; struct pmu *unique_pmu; struct perf_cgroup *cgrp; }; @@ -659,6 +659,7 @@ static inline int is_software_event(struct perf_event *event) extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; +extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs @@ -683,14 +684,25 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs) static __always_inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { - struct pt_regs hot_regs; + if (static_key_false(&perf_swevent_enabled[event_id])) + __perf_sw_event(event_id, nr, regs, addr); +} + +DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]); +/* + * 'Special' version for the scheduler, it hard assumes no recursion, + * which is guaranteed by us not actually scheduling inside other swevents + * because those disable preemption. + */ +static __always_inline void +perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) +{ if (static_key_false(&perf_swevent_enabled[event_id])) { - if (!regs) { - perf_fetch_caller_regs(&hot_regs); - regs = &hot_regs; - } - __perf_sw_event(event_id, nr, regs, addr); + struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); + + perf_fetch_caller_regs(regs); + ___perf_sw_event(event_id, nr, regs, addr); } } @@ -706,7 +718,7 @@ static inline void perf_event_task_sched_in(struct task_struct *prev, static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { - perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0); + perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); if (static_key_false(&perf_sched_events.key)) __perf_event_task_sched_out(prev, next); @@ -817,6 +829,8 @@ static inline int perf_event_refresh(struct perf_event *event, int refresh) static inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void +perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { } +static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline int perf_register_guest_info_callbacks diff --git a/include/linux/pm.h b/include/linux/pm.h index 8b597636461..e2f1be6dd9d 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -597,7 +597,7 @@ struct dev_pm_info { extern void update_pm_runtime_accounting(struct device *dev); extern int dev_pm_get_subsys_data(struct device *dev); -extern int dev_pm_put_subsys_data(struct device *dev); +extern void dev_pm_put_subsys_data(struct device *dev); /* * Power domains provide callbacks that are executed during system suspend, diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index a9edab2c787..080e778118b 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -113,8 +113,6 @@ struct generic_pm_domain_data { struct pm_domain_data base; struct gpd_timing_data td; struct notifier_block nb; - struct mutex lock; - unsigned int refcount; int need_restore; }; @@ -140,7 +138,6 @@ extern int __pm_genpd_name_add_device(const char *domain_name, extern int pm_genpd_remove_device(struct generic_pm_domain *genpd, struct device *dev); -extern void pm_genpd_dev_need_restore(struct device *dev, bool val); extern int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *new_subdomain); extern int pm_genpd_add_subdomain_names(const char *master_name, @@ -187,7 +184,6 @@ static inline int pm_genpd_remove_device(struct generic_pm_domain *genpd, { return -ENOSYS; } -static inline void pm_genpd_dev_need_restore(struct device *dev, bool val) {} static inline int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *new_sd) { diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 77aed9ea1d2..dab545bb66b 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -37,6 +37,7 @@ #define SSDR (0x10) /* SSP Data Write/Data Read Register */ #define SSTO (0x28) /* SSP Time Out Register */ +#define DDS_RATE (0x28) /* SSP DDS Clock Rate Register (Intel Quark) */ #define SSPSP (0x2C) /* SSP Programmable Serial Protocol */ #define SSTSA (0x30) /* SSP Tx Timeslot Active */ #define SSRSA (0x34) /* SSP Rx Timeslot Active */ diff --git a/include/linux/quota.h b/include/linux/quota.h index 097d7eb2441..d534e8ed308 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -216,19 +216,21 @@ struct mem_dqinfo { unsigned long dqi_flags; unsigned int dqi_bgrace; unsigned int dqi_igrace; - qsize_t dqi_maxblimit; - qsize_t dqi_maxilimit; + qsize_t dqi_max_spc_limit; + qsize_t dqi_max_ino_limit; void *dqi_priv; }; struct super_block; -#define DQF_MASK 0xffff /* Mask for format specific flags */ -#define DQF_GETINFO_MASK 0x1ffff /* Mask for flags passed to userspace */ -#define DQF_SETINFO_MASK 0xffff /* Mask for flags modifiable from userspace */ -#define DQF_SYS_FILE_B 16 -#define DQF_SYS_FILE (1 << DQF_SYS_FILE_B) /* Quota file stored as system file */ -#define DQF_INFO_DIRTY_B 31 +/* Mask for flags passed to userspace */ +#define DQF_GETINFO_MASK (DQF_ROOT_SQUASH | DQF_SYS_FILE) +/* Mask for flags modifiable from userspace */ +#define DQF_SETINFO_MASK DQF_ROOT_SQUASH + +enum { + DQF_INFO_DIRTY_B = DQF_PRIVATE, +}; #define DQF_INFO_DIRTY (1 << DQF_INFO_DIRTY_B) /* Is info dirty? */ extern void mark_info_dirty(struct super_block *sb, int type); @@ -367,15 +369,15 @@ struct qc_dqblk { /* Operations handling requests from userspace */ struct quotactl_ops { int (*quota_on)(struct super_block *, int, int, struct path *); - int (*quota_on_meta)(struct super_block *, int, int); int (*quota_off)(struct super_block *, int); + int (*quota_enable)(struct super_block *, unsigned int); + int (*quota_disable)(struct super_block *, unsigned int); int (*quota_sync)(struct super_block *, int); int (*get_info)(struct super_block *, int, struct if_dqinfo *); int (*set_info)(struct super_block *, int, struct if_dqinfo *); int (*get_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*set_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*get_xstate)(struct super_block *, struct fs_quota_stat *); - int (*set_xstate)(struct super_block *, unsigned int, int); int (*get_xstatev)(struct super_block *, struct fs_quota_statv *); int (*rm_xquota)(struct super_block *, unsigned int); }; diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 29e3455f7d4..df73258cca4 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -166,6 +166,7 @@ static inline bool sb_has_quota_active(struct super_block *sb, int type) */ extern const struct dquot_operations dquot_operations; extern const struct quotactl_ops dquot_quotactl_ops; +extern const struct quotactl_ops dquot_quotactl_sysfile_ops; #else @@ -386,4 +387,6 @@ static inline void dquot_release_reservation_block(struct inode *inode, __dquot_free_space(inode, nr << inode->i_blkbits, DQUOT_SPACE_RESERVE); } +unsigned int qtype_enforce_flag(int type); + #endif /* _LINUX_QUOTAOPS_ */ diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 529bc946f45..a18b16f1dc0 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -524,11 +524,11 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n, * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu(pos, member) \ - for (pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\ - typeof(*(pos)), member); \ + for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member); \ pos; \ - pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\ - typeof(*(pos)), member)) + pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point @@ -536,11 +536,11 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n, * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu_bh(pos, member) \ - for (pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\ - typeof(*(pos)), member); \ + for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member); \ pos; \ - pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\ - typeof(*(pos)), member)) + pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index ed4f5939a45..78097491cd9 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -331,12 +331,13 @@ static inline void rcu_init_nohz(void) extern struct srcu_struct tasks_rcu_exit_srcu; #define rcu_note_voluntary_context_switch(t) \ do { \ + rcu_all_qs(); \ if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \ ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \ } while (0) #else /* #ifdef CONFIG_TASKS_RCU */ #define TASKS_RCU(x) do { } while (0) -#define rcu_note_voluntary_context_switch(t) do { } while (0) +#define rcu_note_voluntary_context_switch(t) rcu_all_qs() #endif /* #else #ifdef CONFIG_TASKS_RCU */ /** @@ -582,11 +583,11 @@ static inline void rcu_preempt_sleep_check(void) }) #define __rcu_dereference_check(p, c, space) \ ({ \ - typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \ + /* Dependency order vs. p above. */ \ + typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \ rcu_lockdep_assert(c, "suspicious rcu_dereference_check() usage"); \ rcu_dereference_sparse(p, space); \ - smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ - ((typeof(*p) __force __kernel *)(_________p1)); \ + ((typeof(*p) __force __kernel *)(________p1)); \ }) #define __rcu_dereference_protected(p, c, space) \ ({ \ @@ -603,10 +604,10 @@ static inline void rcu_preempt_sleep_check(void) }) #define __rcu_dereference_index_check(p, c) \ ({ \ - typeof(p) _________p1 = ACCESS_ONCE(p); \ + /* Dependency order vs. p above. */ \ + typeof(p) _________p1 = lockless_dereference(p); \ rcu_lockdep_assert(c, \ "suspicious rcu_dereference_index_check() usage"); \ - smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ (_________p1); \ }) diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 0e536620015..937edaeb150 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -92,17 +92,49 @@ static inline void rcu_virt_note_context_switch(int cpu) } /* - * Return the number of grace periods. + * Return the number of grace periods started. */ -static inline long rcu_batches_completed(void) +static inline unsigned long rcu_batches_started(void) { return 0; } /* - * Return the number of bottom-half grace periods. + * Return the number of bottom-half grace periods started. */ -static inline long rcu_batches_completed_bh(void) +static inline unsigned long rcu_batches_started_bh(void) +{ + return 0; +} + +/* + * Return the number of sched grace periods started. + */ +static inline unsigned long rcu_batches_started_sched(void) +{ + return 0; +} + +/* + * Return the number of grace periods completed. + */ +static inline unsigned long rcu_batches_completed(void) +{ + return 0; +} + +/* + * Return the number of bottom-half grace periods completed. + */ +static inline unsigned long rcu_batches_completed_bh(void) +{ + return 0; +} + +/* + * Return the number of sched grace periods completed. + */ +static inline unsigned long rcu_batches_completed_sched(void) { return 0; } @@ -154,7 +186,10 @@ static inline bool rcu_is_watching(void) return true; } - #endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */ +static inline void rcu_all_qs(void) +{ +} + #endif /* __LINUX_RCUTINY_H */ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 52953790dcc..d2e583a6aac 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -81,9 +81,12 @@ void cond_synchronize_rcu(unsigned long oldstate); extern unsigned long rcutorture_testseq; extern unsigned long rcutorture_vernum; -long rcu_batches_completed(void); -long rcu_batches_completed_bh(void); -long rcu_batches_completed_sched(void); +unsigned long rcu_batches_started(void); +unsigned long rcu_batches_started_bh(void); +unsigned long rcu_batches_started_sched(void); +unsigned long rcu_batches_completed(void); +unsigned long rcu_batches_completed_bh(void); +unsigned long rcu_batches_completed_sched(void); void show_rcu_gp_kthreads(void); void rcu_force_quiescent_state(void); @@ -97,4 +100,6 @@ extern int rcu_scheduler_active __read_mostly; bool rcu_is_watching(void); +void rcu_all_qs(void); + #endif /* __LINUX_RCUTREE_H */ diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4419b99d8d6..116655d9226 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -468,7 +468,7 @@ bool regmap_reg_in_ranges(unsigned int reg, * * @reg: Offset of the register within the regmap bank * @lsb: lsb of the register field. - * @reg: msb of the register field. + * @msb: msb of the register field. * @id_size: port size if it has some ports * @id_offset: address offset for each ports */ diff --git a/include/linux/regulator/da9211.h b/include/linux/regulator/da9211.h index 5479394fefc..5dd65acc2a6 100644 --- a/include/linux/regulator/da9211.h +++ b/include/linux/regulator/da9211.h @@ -32,6 +32,8 @@ struct da9211_pdata { * 2 : 2 phase 2 buck */ int num_buck; + int gpio_ren[DA9211_MAX_REGULATORS]; + struct device_node *reg_node[DA9211_MAX_REGULATORS]; struct regulator_init_data *init_data[DA9211_MAX_REGULATORS]; }; #endif diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 5f1e9ca4741..d4ad5b5a02b 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -21,6 +21,7 @@ struct regmap; struct regulator_dev; +struct regulator_config; struct regulator_init_data; struct regulator_enable_gpio; @@ -205,6 +206,15 @@ enum regulator_type { * @supply_name: Identifying the regulator supply * @of_match: Name used to identify regulator in DT. * @regulators_node: Name of node containing regulator definitions in DT. + * @of_parse_cb: Optional callback called only if of_match is present. + * Will be called for each regulator parsed from DT, during + * init_data parsing. + * The regulator_config passed as argument to the callback will + * be a copy of config passed to regulator_register, valid only + * for this particular call. Callback may freely change the + * config but it cannot store it for later usage. + * Callback should return 0 on success or negative ERRNO + * indicating failure. * @id: Numerical identifier for the regulator. * @ops: Regulator operations table. * @irq: Interrupt number for the regulator. @@ -251,6 +261,9 @@ struct regulator_desc { const char *supply_name; const char *of_match; const char *regulators_node; + int (*of_parse_cb)(struct device_node *, + const struct regulator_desc *, + struct regulator_config *); int id; bool continuous_voltage_range; unsigned n_voltages; diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 0b08d05d470..b07562e082c 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -191,15 +191,22 @@ struct regulator_init_data { void *driver_data; /* core does not touch this */ }; -int regulator_suspend_prepare(suspend_state_t state); -int regulator_suspend_finish(void); - #ifdef CONFIG_REGULATOR void regulator_has_full_constraints(void); +int regulator_suspend_prepare(suspend_state_t state); +int regulator_suspend_finish(void); #else static inline void regulator_has_full_constraints(void) { } +static inline int regulator_suspend_prepare(suspend_state_t state) +{ + return 0; +} +static inline int regulator_suspend_finish(void) +{ + return 0; +} #endif #endif diff --git a/include/linux/regulator/mt6397-regulator.h b/include/linux/regulator/mt6397-regulator.h new file mode 100644 index 00000000000..30cc5963e26 --- /dev/null +++ b/include/linux/regulator/mt6397-regulator.h @@ -0,0 +1,49 @@ +/* + * Copyright (c) 2014 MediaTek Inc. + * Author: Flora Fu <flora.fu@mediatek.com> + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_REGULATOR_MT6397_H +#define __LINUX_REGULATOR_MT6397_H + +enum { + MT6397_ID_VPCA15 = 0, + MT6397_ID_VPCA7, + MT6397_ID_VSRAMCA15, + MT6397_ID_VSRAMCA7, + MT6397_ID_VCORE, + MT6397_ID_VGPU, + MT6397_ID_VDRM, + MT6397_ID_VIO18 = 7, + MT6397_ID_VTCXO, + MT6397_ID_VA28, + MT6397_ID_VCAMA, + MT6397_ID_VIO28, + MT6397_ID_VUSB, + MT6397_ID_VMC, + MT6397_ID_VMCH, + MT6397_ID_VEMC3V3, + MT6397_ID_VGP1, + MT6397_ID_VGP2, + MT6397_ID_VGP3, + MT6397_ID_VGP4, + MT6397_ID_VGP5, + MT6397_ID_VGP6, + MT6397_ID_VIBR, + MT6397_ID_RG_MAX, +}; + +#define MT6397_MAX_REGULATOR MT6397_ID_RG_MAX +#define MT6397_REGULATOR_ID97 0x97 +#define MT6397_REGULATOR_ID91 0x91 + +#endif /* __LINUX_REGULATOR_MT6397_H */ diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h index 364f7a7c43d..70c6c66c5bc 100644 --- a/include/linux/regulator/pfuze100.h +++ b/include/linux/regulator/pfuze100.h @@ -49,6 +49,20 @@ #define PFUZE200_VGEN5 11 #define PFUZE200_VGEN6 12 +#define PFUZE3000_SW1A 0 +#define PFUZE3000_SW1B 1 +#define PFUZE3000_SW2 2 +#define PFUZE3000_SW3 3 +#define PFUZE3000_SWBST 4 +#define PFUZE3000_VSNVS 5 +#define PFUZE3000_VREFDDR 6 +#define PFUZE3000_VLDO1 7 +#define PFUZE3000_VLDO2 8 +#define PFUZE3000_VCCSD 9 +#define PFUZE3000_V33 10 +#define PFUZE3000_VLDO3 11 +#define PFUZE3000_VLDO4 12 + struct regulator_init_data; struct pfuze_regulator_platform_data { diff --git a/include/linux/resource_ext.h b/include/linux/resource_ext.h new file mode 100644 index 00000000000..e2bf63d881d --- /dev/null +++ b/include/linux/resource_ext.h @@ -0,0 +1,77 @@ +/* + * Copyright (C) 2015, Intel Corporation + * Author: Jiang Liu <jiang.liu@linux.intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ +#ifndef _LINUX_RESOURCE_EXT_H +#define _LINUX_RESOURCE_EXT_H +#include <linux/types.h> +#include <linux/list.h> +#include <linux/ioport.h> +#include <linux/slab.h> + +/* Represent resource window for bridge devices */ +struct resource_win { + struct resource res; /* In master (CPU) address space */ + resource_size_t offset; /* Translation offset for bridge */ +}; + +/* + * Common resource list management data structure and interfaces to support + * ACPI, PNP and PCI host bridge etc. + */ +struct resource_entry { + struct list_head node; + struct resource *res; /* In master (CPU) address space */ + resource_size_t offset; /* Translation offset for bridge */ + struct resource __res; /* Default storage for res */ +}; + +extern struct resource_entry * +resource_list_create_entry(struct resource *res, size_t extra_size); +extern void resource_list_free(struct list_head *head); + +static inline void resource_list_add(struct resource_entry *entry, + struct list_head *head) +{ + list_add(&entry->node, head); +} + +static inline void resource_list_add_tail(struct resource_entry *entry, + struct list_head *head) +{ + list_add_tail(&entry->node, head); +} + +static inline void resource_list_del(struct resource_entry *entry) +{ + list_del(&entry->node); +} + +static inline void resource_list_free_entry(struct resource_entry *entry) +{ + kfree(entry); +} + +static inline void +resource_list_destroy_entry(struct resource_entry *entry) +{ + resource_list_del(entry); + resource_list_free_entry(entry); +} + +#define resource_list_for_each_entry(entry, list) \ + list_for_each_entry((entry), (list), node) + +#define resource_list_for_each_entry_safe(entry, tmp, list) \ + list_for_each_entry_safe((entry), (tmp), (list), node) + +#endif /* _LINUX_RESOURCE_EXT_H */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index d9d7e7e5635..b38f559130d 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -246,7 +246,6 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); * arg: passed to rmap_one() and invalid_vma() * rmap_one: executed on each vma where page is mapped * done: for checking traversing termination condition - * file_nonlinear: for handling file nonlinear mapping * anon_lock: for getting anon_lock by optimized way rather than default * invalid_vma: for skipping uninterested vma */ @@ -255,7 +254,6 @@ struct rmap_walk_control { int (*rmap_one)(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct page *page); - int (*file_nonlinear)(struct page *, struct address_space *, void *arg); struct anon_vma *(*anon_lock)(struct page *page); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 6d6be09a2fe..dcad7ee0d74 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -161,7 +161,7 @@ extern void devm_rtc_device_unregister(struct device *dev, extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs); -extern int rtc_set_ntp_time(struct timespec now); +extern int rtc_set_ntp_time(struct timespec64 now); int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm); extern int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); diff --git a/include/linux/slab.h b/include/linux/slab.h index 9a139b63706..2e3b448cfa2 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -116,9 +116,8 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, unsigned long, void (*)(void *)); #ifdef CONFIG_MEMCG_KMEM -struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *, - struct kmem_cache *, - const char *); +void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *); +void memcg_destroy_kmem_caches(struct mem_cgroup *); #endif void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); @@ -491,7 +490,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) * Child caches will hold extra metadata needed for its operation. Fields are: * * @memcg: pointer to the memcg this cache belongs to - * @list: list_head for the list of all caches in this memcg * @root_cache: pointer to the global, root cache, this cache was derived from */ struct memcg_cache_params { @@ -503,7 +501,6 @@ struct memcg_cache_params { }; struct { struct mem_cgroup *memcg; - struct list_head list; struct kmem_cache *root_cache; }; }; diff --git a/include/linux/smp.h b/include/linux/smp.h index 93dff5fff52..be91db2a701 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -151,6 +151,13 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, static inline void kick_all_cpus_sync(void) { } static inline void wake_up_all_idle_cpus(void) { } +#ifdef CONFIG_UP_LATE_INIT +extern void __init up_late_init(void); +static inline void smp_init(void) { up_late_init(); } +#else +static inline void smp_init(void) { } +#endif + #endif /* !SMP */ /* diff --git a/include/linux/spi/at86rf230.h b/include/linux/spi/at86rf230.h index b2b1afbb320..cd519a11c2c 100644 --- a/include/linux/spi/at86rf230.h +++ b/include/linux/spi/at86rf230.h @@ -12,10 +12,6 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - * * Written by: * Dmitry Eremin-Solenikov <dmitry.baryshkov@siemens.com> */ diff --git a/include/linux/spi/l4f00242t03.h b/include/linux/spi/l4f00242t03.h index bc8677c8eba..e69e9b51b21 100644 --- a/include/linux/spi/l4f00242t03.h +++ b/include/linux/spi/l4f00242t03.h @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _INCLUDE_LINUX_SPI_L4F00242T03_H_ diff --git a/include/linux/spi/lms283gf05.h b/include/linux/spi/lms283gf05.h index 555d254e660..fdd1d1d51da 100644 --- a/include/linux/spi/lms283gf05.h +++ b/include/linux/spi/lms283gf05.h @@ -11,10 +11,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _INCLUDE_LINUX_SPI_LMS283GF05_H_ diff --git a/include/linux/spi/mxs-spi.h b/include/linux/spi/mxs-spi.h index 4835486f58e..381d368b91b 100644 --- a/include/linux/spi/mxs-spi.h +++ b/include/linux/spi/mxs-spi.h @@ -15,10 +15,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. */ #ifndef __LINUX_SPI_MXS_SPI_H__ diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index d5a31655017..6d36dacec4b 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -10,10 +10,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #ifndef __linux_pxa2xx_spi_h #define __linux_pxa2xx_spi_h @@ -57,7 +53,6 @@ struct pxa2xx_spi_chip { #if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP) #include <linux/clk.h> -#include <mach/dma.h> extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_master *info); diff --git a/include/linux/spi/rspi.h b/include/linux/spi/rspi.h index e546b2ceb62..a693188cc08 100644 --- a/include/linux/spi/rspi.h +++ b/include/linux/spi/rspi.h @@ -11,11 +11,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * */ #ifndef __LINUX_SPI_RENESAS_SPI_H__ diff --git a/include/linux/spi/sh_hspi.h b/include/linux/spi/sh_hspi.h index a1121f872ac..aa0d440ab4f 100644 --- a/include/linux/spi/sh_hspi.h +++ b/include/linux/spi/sh_hspi.h @@ -9,10 +9,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #ifndef SH_HSPI_H #define SH_HSPI_H diff --git a/include/linux/spi/sh_msiof.h b/include/linux/spi/sh_msiof.h index 88a14d81c49..b087a85f5f7 100644 --- a/include/linux/spi/sh_msiof.h +++ b/include/linux/spi/sh_msiof.h @@ -7,6 +7,8 @@ struct sh_msiof_spi_info { u16 num_chipselect; unsigned int dma_tx_id; unsigned int dma_rx_id; + u32 dtdl; + u32 syncdl; }; #endif /* __SPI_SH_MSIOF_H__ */ diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a6ef2a8e6de..ed9489d893a 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -10,10 +10,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #ifndef __LINUX_SPI_H @@ -260,6 +256,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @pump_messages: work struct for scheduling work to the message pump * @queue_lock: spinlock to syncronise access to message queue * @queue: message queue + * @idling: the device is entering idle state * @cur_msg: the currently in-flight message * @cur_msg_prepared: spi_prepare_message was called for the currently * in-flight message @@ -425,6 +422,7 @@ struct spi_master { spinlock_t queue_lock; struct list_head queue; struct spi_message *cur_msg; + bool idling; bool busy; bool running; bool rt; diff --git a/include/linux/spi/tle62x0.h b/include/linux/spi/tle62x0.h index 60b59187e59..414c6fddfcf 100644 --- a/include/linux/spi/tle62x0.h +++ b/include/linux/spi/tle62x0.h @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ struct tle62x0_pdata { diff --git a/include/linux/spi/tsc2005.h b/include/linux/spi/tsc2005.h index 8f721e465e0..563b3b1799a 100644 --- a/include/linux/spi/tsc2005.h +++ b/include/linux/spi/tsc2005.h @@ -12,11 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * */ #ifndef _LINUX_SPI_TSC2005_H diff --git a/include/linux/srcu.h b/include/linux/srcu.h index a2783cb5d27..9cfd9623fb0 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -45,7 +45,7 @@ struct rcu_batch { #define RCU_BATCH_INIT(name) { NULL, &(name.head) } struct srcu_struct { - unsigned completed; + unsigned long completed; struct srcu_struct_array __percpu *per_cpu_ref; spinlock_t queue_lock; /* protect ->batch_queue, ->running */ bool running; @@ -102,13 +102,11 @@ void process_srcu(struct work_struct *work); * define and init a srcu struct at build time. * dont't call init_srcu_struct() nor cleanup_srcu_struct() on it. */ -#define DEFINE_SRCU(name) \ +#define __DEFINE_SRCU(name, is_static) \ static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ - struct srcu_struct name = __SRCU_STRUCT_INIT(name); - -#define DEFINE_STATIC_SRCU(name) \ - static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ - static struct srcu_struct name = __SRCU_STRUCT_INIT(name); + is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name) +#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) +#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) /** * call_srcu() - Queue a callback for invocation after an SRCU grace period @@ -135,7 +133,7 @@ int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp); void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); void synchronize_srcu(struct srcu_struct *sp); void synchronize_srcu_expedited(struct srcu_struct *sp); -long srcu_batches_completed(struct srcu_struct *sp); +unsigned long srcu_batches_completed(struct srcu_struct *sp); void srcu_barrier(struct srcu_struct *sp); #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 6adfb7bfbf4..50cbc876be5 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -54,7 +54,7 @@ static inline pgoff_t swp_offset(swp_entry_t entry) /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { - return !pte_none(pte) && !pte_present_nonuma(pte) && !pte_file(pte); + return !pte_none(pte) && !pte_present_nonuma(pte); } #endif @@ -66,7 +66,6 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte) { swp_entry_t arch_entry; - BUG_ON(pte_file(pte)); if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); arch_entry = __pte_to_swp_entry(pte); @@ -82,7 +81,6 @@ static inline pte_t swp_entry_to_pte(swp_entry_t entry) swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); - BUG_ON(pte_file(__swp_entry_to_pte(arch_entry))); return __swp_entry_to_pte(arch_entry); } diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 9b63d13ba82..3eaae475427 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -33,6 +33,7 @@ extern time64_t ktime_get_real_seconds(void); extern int __getnstimeofday64(struct timespec64 *tv); extern void getnstimeofday64(struct timespec64 *tv); +extern void getboottime64(struct timespec64 *ts); #if BITS_PER_LONG == 64 /** @@ -72,6 +73,11 @@ static inline struct timespec get_monotonic_coarse(void) { return get_monotonic_coarse64(); } + +static inline void getboottime(struct timespec *ts) +{ + return getboottime64(ts); +} #else /** * Deprecated. Use do_settimeofday64(). @@ -129,9 +135,15 @@ static inline struct timespec get_monotonic_coarse(void) { return timespec64_to_timespec(get_monotonic_coarse64()); } -#endif -extern void getboottime(struct timespec *ts); +static inline void getboottime(struct timespec *ts) +{ + struct timespec64 ts64; + + getboottime64(&ts64); + *ts = timespec64_to_timespec(ts64); +} +#endif #define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts) #define ktime_get_real_ts64(ts) getnstimeofday64(ts) @@ -217,6 +229,11 @@ static inline void get_monotonic_boottime(struct timespec *ts) *ts = ktime_to_timespec(ktime_get_boottime()); } +static inline void get_monotonic_boottime64(struct timespec64 *ts) +{ + *ts = ktime_to_timespec64(ktime_get_boottime()); +} + static inline void timekeeping_clocktai(struct timespec *ts) { *ts = ktime_to_timespec(ktime_get_clocktai()); diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index e08e21e5f60..c72851328ca 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -173,7 +173,7 @@ extern void syscall_unregfunc(void); TP_PROTO(data_proto), \ TP_ARGS(data_args), \ TP_CONDITION(cond),,); \ - if (IS_ENABLED(CONFIG_LOCKDEP)) { \ + if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ rcu_read_lock_sched_notrace(); \ rcu_dereference_sched(__tracepoint_##name.funcs);\ rcu_read_unlock_sched_notrace(); \ diff --git a/include/linux/wait.h b/include/linux/wait.h index 2232ed16635..537d58eea8a 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -363,7 +363,6 @@ do { \ */ #define wait_event_cmd(wq, condition, cmd1, cmd2) \ do { \ - might_sleep(); \ if (condition) \ break; \ __wait_event_cmd(wq, condition, cmd1, cmd2); \ @@ -991,6 +990,32 @@ wait_on_bit_io(void *word, int bit, unsigned mode) } /** + * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * @timeout: timeout, in jiffies + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared. This is similar to wait_on_bit(), except also takes a + * timeout parameter. + * + * Returned value will be zero if the bit was cleared before the + * @timeout elapsed, or non-zero if the @timeout elapsed or process + * received a signal and the mode permitted wakeup on that signal. + */ +static inline int +wait_on_bit_timeout(void *word, int bit, unsigned mode, unsigned long timeout) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_timeout(word, bit, + bit_wait_timeout, + mode, timeout); +} + +/** * wait_on_bit_action - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index b996e6cde6b..74db135f995 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -220,14 +220,10 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } #endif #define INIT_WORK(_work, _func) \ - do { \ - __INIT_WORK((_work), (_func), 0); \ - } while (0) + __INIT_WORK((_work), (_func), 0) #define INIT_WORK_ONSTACK(_work, _func) \ - do { \ - __INIT_WORK((_work), (_func), 1); \ - } while (0) + __INIT_WORK((_work), (_func), 1) #define __INIT_DELAYED_WORK(_work, _func, _tflags) \ do { \ diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 0d74f1de99a..65994a19e84 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1707,10 +1707,7 @@ static inline int ib_copy_from_udata(void *dest, struct ib_udata *udata, size_t static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len) { - size_t copy_sz; - - copy_sz = min_t(size_t, len, udata->outlen); - return copy_to_user(udata->outbuf, src, copy_sz) ? -EFAULT : 0; + return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0; } /** diff --git a/include/sound/ak4113.h b/include/sound/ak4113.h index 2609048c1d4..3a34f6edc2d 100644 --- a/include/sound/ak4113.h +++ b/include/sound/ak4113.h @@ -286,7 +286,7 @@ struct ak4113 { ak4113_write_t *write; ak4113_read_t *read; void *private_data; - unsigned int init:1; + atomic_t wq_processing; spinlock_t lock; unsigned char regmap[AK4113_WRITABLE_REGS]; struct snd_kcontrol *kctls[AK4113_CONTROLS]; diff --git a/include/sound/ak4114.h b/include/sound/ak4114.h index 52f02a60dba..069299a8891 100644 --- a/include/sound/ak4114.h +++ b/include/sound/ak4114.h @@ -168,7 +168,7 @@ struct ak4114 { ak4114_write_t * write; ak4114_read_t * read; void * private_data; - unsigned int init: 1; + atomic_t wq_processing; spinlock_t lock; unsigned char regmap[6]; unsigned char txcsb[5]; diff --git a/include/sound/soc.h b/include/sound/soc.h index b4fca9aed2a..ac8b333acb4 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -498,6 +498,7 @@ int snd_soc_test_bits(struct snd_soc_codec *codec, unsigned int reg, unsigned int mask, unsigned int value); #ifdef CONFIG_SND_SOC_AC97_BUS +struct snd_ac97 *snd_soc_alloc_ac97_codec(struct snd_soc_codec *codec); struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec); void snd_soc_free_ac97_codec(struct snd_ac97 *ac97); diff --git a/include/trace/events/tlb.h b/include/trace/events/tlb.h index 13391d28810..0e763576515 100644 --- a/include/trace/events/tlb.h +++ b/include/trace/events/tlb.h @@ -13,11 +13,13 @@ { TLB_LOCAL_SHOOTDOWN, "local shootdown" }, \ { TLB_LOCAL_MM_SHOOTDOWN, "local mm shootdown" } -TRACE_EVENT(tlb_flush, +TRACE_EVENT_CONDITION(tlb_flush, TP_PROTO(int reason, unsigned long pages), TP_ARGS(reason, pages), + TP_CONDITION(cpu_online(smp_processor_id())), + TP_STRUCT__entry( __field( int, reason) __field(unsigned long, pages) diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 139b5067345..27609dfcce2 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -763,7 +763,7 @@ perf_trace_##call(void *__data, proto) \ struct ftrace_event_call *event_call = __data; \ struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\ struct ftrace_raw_##call *entry; \ - struct pt_regs __regs; \ + struct pt_regs *__regs; \ u64 __addr = 0, __count = 1; \ struct task_struct *__task = NULL; \ struct hlist_head *head; \ @@ -782,18 +782,19 @@ perf_trace_##call(void *__data, proto) \ sizeof(u64)); \ __entry_size -= sizeof(u32); \ \ - perf_fetch_caller_regs(&__regs); \ entry = perf_trace_buf_prepare(__entry_size, \ event_call->event.type, &__regs, &rctx); \ if (!entry) \ return; \ \ + perf_fetch_caller_regs(__regs); \ + \ tstruct \ \ { assign; } \ \ perf_trace_buf_submit(entry, __entry_size, rctx, __addr, \ - __count, &__regs, head, __task); \ + __count, __regs, head, __task); \ } /* diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index a1d7e931ab7..b0a81307985 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -166,6 +166,7 @@ struct input_keymap_entry { #define INPUT_PROP_SEMI_MT 0x03 /* touch rectangle only */ #define INPUT_PROP_TOPBUTTONPAD 0x04 /* softbuttons at top of pad */ #define INPUT_PROP_POINTING_STICK 0x05 /* is a pointing stick */ +#define INPUT_PROP_ACCELEROMETER 0x06 /* has accelerometer */ #define INPUT_PROP_MAX 0x1f #define INPUT_PROP_CNT (INPUT_PROP_MAX + 1) diff --git a/include/uapi/linux/msdos_fs.h b/include/uapi/linux/msdos_fs.h index e284ff919d6..e956704f5fb 100644 --- a/include/uapi/linux/msdos_fs.h +++ b/include/uapi/linux/msdos_fs.h @@ -134,7 +134,7 @@ struct fat_boot_sector { __u8 vol_id[4]; /* volume ID */ __u8 vol_label[11]; /* volume label */ __u8 fs_type[8]; /* file system type */ - /* other fiealds are not added here */ + /* other fields are not added here */ } fat16; struct { @@ -157,7 +157,7 @@ struct fat_boot_sector { __u8 vol_id[4]; /* volume ID */ __u8 vol_label[11]; /* volume label */ __u8 fs_type[8]; /* file system type */ - /* other fiealds are not added here */ + /* other fields are not added here */ } fat32; }; }; diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 4a1d0cc38ff..efe3443572b 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -451,6 +451,10 @@ #define PCI_EXP_DEVCTL_AUX_PME 0x0400 /* Auxiliary Power PM Enable */ #define PCI_EXP_DEVCTL_NOSNOOP_EN 0x0800 /* Enable No Snoop */ #define PCI_EXP_DEVCTL_READRQ 0x7000 /* Max_Read_Request_Size */ +#define PCI_EXP_DEVCTL_READRQ_128B 0x0000 /* 128 Bytes */ +#define PCI_EXP_DEVCTL_READRQ_256B 0x1000 /* 256 Bytes */ +#define PCI_EXP_DEVCTL_READRQ_512B 0x2000 /* 512 Bytes */ +#define PCI_EXP_DEVCTL_READRQ_1024B 0x3000 /* 1024 Bytes */ #define PCI_EXP_DEVCTL_BCR_FLR 0x8000 /* Bridge Configuration Retry / FLR */ #define PCI_EXP_DEVSTA 10 /* Device Status */ #define PCI_EXP_DEVSTA_CED 0x0001 /* Correctable Error Detected */ diff --git a/include/uapi/linux/quota.h b/include/uapi/linux/quota.h index 3b6cfbeb086..1f49b8341c9 100644 --- a/include/uapi/linux/quota.h +++ b/include/uapi/linux/quota.h @@ -126,10 +126,22 @@ struct if_dqblk { #define IIF_FLAGS 4 #define IIF_ALL (IIF_BGRACE | IIF_IGRACE | IIF_FLAGS) +enum { + DQF_ROOT_SQUASH_B = 0, + DQF_SYS_FILE_B = 16, + /* Kernel internal flags invisible to userspace */ + DQF_PRIVATE +}; + +/* Root squash enabled (for v1 quota format) */ +#define DQF_ROOT_SQUASH (1 << DQF_ROOT_SQUASH_B) +/* Quota stored in a system file */ +#define DQF_SYS_FILE (1 << DQF_SYS_FILE_B) + struct if_dqinfo { __u64 dqi_bgrace; __u64 dqi_igrace; - __u32 dqi_flags; + __u32 dqi_flags; /* DFQ_* */ __u32 dqi_valid; }; diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 4275b961bf6..867cc5084af 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -90,7 +90,6 @@ enum { }; enum { - IB_USER_VERBS_EX_CMD_QUERY_DEVICE = IB_USER_VERBS_CMD_QUERY_DEVICE, IB_USER_VERBS_EX_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD, IB_USER_VERBS_EX_CMD_DESTROY_FLOW, }; @@ -202,32 +201,6 @@ struct ib_uverbs_query_device_resp { __u8 reserved[4]; }; -enum { - IB_USER_VERBS_EX_QUERY_DEVICE_ODP = 1ULL << 0, -}; - -struct ib_uverbs_ex_query_device { - __u32 comp_mask; - __u32 reserved; -}; - -struct ib_uverbs_odp_caps { - __u64 general_caps; - struct { - __u32 rc_odp_caps; - __u32 uc_odp_caps; - __u32 ud_odp_caps; - } per_transport_caps; - __u32 reserved; -}; - -struct ib_uverbs_ex_query_device_resp { - struct ib_uverbs_query_device_resp base; - __u32 comp_mask; - __u32 reserved; - struct ib_uverbs_odp_caps odp_caps; -}; - struct ib_uverbs_query_port { __u64 response; __u8 port_num; diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 3387465b9ca..143ca5ffab7 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -45,6 +45,8 @@ #include <asm/xen/hypervisor.h> #include <xen/features.h> +#include <linux/mm_types.h> +#include <linux/page-flags.h> #define GNTTAB_RESERVED_XENSTORE 1 @@ -58,6 +60,22 @@ struct gnttab_free_callback { u16 count; }; +struct gntab_unmap_queue_data; + +typedef void (*gnttab_unmap_refs_done)(int result, struct gntab_unmap_queue_data *data); + +struct gntab_unmap_queue_data +{ + struct delayed_work gnttab_work; + void *data; + gnttab_unmap_refs_done done; + struct gnttab_unmap_grant_ref *unmap_ops; + struct gnttab_unmap_grant_ref *kunmap_ops; + struct page **pages; + unsigned int count; + unsigned int age; +}; + int gnttab_init(void); int gnttab_suspend(void); int gnttab_resume(void); @@ -163,12 +181,17 @@ void gnttab_free_auto_xlat_frames(void); #define gnttab_map_vaddr(map) ((void *)(map.host_virt_addr)) +int gnttab_alloc_pages(int nr_pages, struct page **pages); +void gnttab_free_pages(int nr_pages, struct page **pages); + int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, struct gnttab_map_grant_ref *kmap_ops, struct page **pages, unsigned int count); int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, - struct gnttab_map_grant_ref *kunmap_ops, + struct gnttab_unmap_grant_ref *kunmap_ops, struct page **pages, unsigned int count); +void gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item); + /* Perform a batch of grant map/copy operations. Retry every batch slot * for which the hypervisor returns GNTST_eagain. This is typically due @@ -182,4 +205,22 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, void gnttab_batch_map(struct gnttab_map_grant_ref *batch, unsigned count); void gnttab_batch_copy(struct gnttab_copy *batch, unsigned count); + +struct xen_page_foreign { + domid_t domid; + grant_ref_t gref; +}; + +static inline struct xen_page_foreign *xen_page_foreign(struct page *page) +{ + if (!PageForeign(page)) + return NULL; +#if BITS_PER_LONG < 64 + return (struct xen_page_foreign *)page->private; +#else + BUILD_BUG_ON(sizeof(struct xen_page_foreign) > BITS_PER_LONG); + return (struct xen_page_foreign *)&page->private; +#endif +} + #endif /* __ASM_GNTTAB_H__ */ diff --git a/include/xen/interface/features.h b/include/xen/interface/features.h index 131a6ccdba2..6ad3d110bb8 100644 --- a/include/xen/interface/features.h +++ b/include/xen/interface/features.h @@ -41,6 +41,12 @@ /* x86: Does this Xen host support the MMU_PT_UPDATE_PRESERVE_AD hypercall? */ #define XENFEAT_mmu_pt_update_preserve_ad 5 +/* + * If set, GNTTABOP_map_grant_ref honors flags to be placed into guest kernel + * available pte bits. + */ +#define XENFEAT_gnttab_map_avail_bits 7 + /* x86: Does this Xen host support the HVM callback vector type? */ #define XENFEAT_hvm_callback_vector 8 diff --git a/include/xen/interface/grant_table.h b/include/xen/interface/grant_table.h index bcce56439d6..56806bc90c2 100644 --- a/include/xen/interface/grant_table.h +++ b/include/xen/interface/grant_table.h @@ -526,6 +526,13 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush); #define GNTMAP_contains_pte (1<<_GNTMAP_contains_pte) /* + * Bits to be placed in guest kernel available PTE bits (architecture + * dependent; only supported when XENFEAT_gnttab_map_avail_bits is set). + */ +#define _GNTMAP_guest_avail0 (16) +#define GNTMAP_guest_avail_mask ((uint32_t)~0 << _GNTMAP_guest_avail0) + +/* * Values for error status returns. All errors are -ve. */ #define GNTST_okay (0) /* Normal return. */ diff --git a/init/Kconfig b/init/Kconfig index 9afb971497f..1354ac09b51 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -470,7 +470,6 @@ choice config TREE_RCU bool "Tree-based hierarchical RCU" depends on !PREEMPT && SMP - select IRQ_WORK help This option selects the RCU implementation that is designed for very large SMP system with hundreds or @@ -480,7 +479,6 @@ config TREE_RCU config PREEMPT_RCU bool "Preemptible tree-based hierarchical RCU" depends on PREEMPT - select IRQ_WORK help This option selects the RCU implementation that is designed for very large SMP systems with hundreds or @@ -501,9 +499,17 @@ config TINY_RCU endchoice +config SRCU + bool + help + This option selects the sleepable version of RCU. This version + permits arbitrary sleeping or blocking within RCU read-side critical + sections. + config TASKS_RCU bool "Task_based RCU implementation using voluntary context switch" default n + select SRCU help This option enables a task-based RCU implementation that uses only voluntary context switch (not preemption!), idle, and @@ -668,9 +674,10 @@ config RCU_BOOST config RCU_KTHREAD_PRIO int "Real-time priority to use for RCU worker threads" - range 1 99 - depends on RCU_BOOST - default 1 + range 1 99 if RCU_BOOST + range 0 99 if !RCU_BOOST + default 1 if RCU_BOOST + default 0 if !RCU_BOOST help This option specifies the SCHED_FIFO priority value that will be assigned to the rcuc/n and rcub/n threads and is also the value @@ -1595,6 +1602,7 @@ config PERF_EVENTS depends on HAVE_PERF_EVENTS select ANON_INODES select IRQ_WORK + select SRCU help Enable kernel support for various performance events provided by software and hardware. diff --git a/init/main.c b/init/main.c index 61b993767db..179ada15d08 100644 --- a/init/main.c +++ b/init/main.c @@ -87,10 +87,6 @@ #include <asm/sections.h> #include <asm/cacheflush.h> -#ifdef CONFIG_X86_LOCAL_APIC -#include <asm/smp.h> -#endif - static int kernel_init(void *); extern void init_IRQ(void); @@ -351,15 +347,6 @@ __setup("rdinit=", rdinit_setup); #ifndef CONFIG_SMP static const unsigned int setup_max_cpus = NR_CPUS; -#ifdef CONFIG_X86_LOCAL_APIC -static void __init smp_init(void) -{ - APIC_init_uniprocessor(); -} -#else -#define smp_init() do { } while (0) -#endif - static inline void setup_nr_cpu_ids(void) { } static inline void smp_prepare_cpus(unsigned int maxcpus) { } #endif diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 76768ee812b..08561f1acd1 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -231,6 +231,10 @@ config RWSEM_SPIN_ON_OWNER def_bool y depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW +config LOCK_SPIN_ON_OWNER + def_bool y + depends on MUTEX_SPIN_ON_OWNER || RWSEM_SPIN_ON_OWNER + config ARCH_USE_QUEUE_RWLOCK bool diff --git a/kernel/Makefile b/kernel/Makefile index a59481a3fa6..616994f0a76 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -26,6 +26,7 @@ obj-y += power/ obj-y += printk/ obj-y += irq/ obj-y += rcu/ +obj-y += livepatch/ obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o obj-$(CONFIG_FREEZER) += freezer.o diff --git a/kernel/cpu.c b/kernel/cpu.c index 5d220234b3c..1972b161c61 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -58,22 +58,23 @@ static int cpu_hotplug_disabled; static struct { struct task_struct *active_writer; - struct mutex lock; /* Synchronizes accesses to refcount, */ + /* wait queue to wake up the active_writer */ + wait_queue_head_t wq; + /* verifies that no writer will get active while readers are active */ + struct mutex lock; /* * Also blocks the new readers during * an ongoing cpu hotplug operation. */ - int refcount; - /* And allows lockless put_online_cpus(). */ - atomic_t puts_pending; + atomic_t refcount; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif } cpu_hotplug = { .active_writer = NULL, + .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq), .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock), - .refcount = 0, #ifdef CONFIG_DEBUG_LOCK_ALLOC .dep_map = {.name = "cpu_hotplug.lock" }, #endif @@ -86,15 +87,6 @@ static struct { #define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map) #define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map) -static void apply_puts_pending(int max) -{ - int delta; - - if (atomic_read(&cpu_hotplug.puts_pending) >= max) { - delta = atomic_xchg(&cpu_hotplug.puts_pending, 0); - cpu_hotplug.refcount -= delta; - } -} void get_online_cpus(void) { @@ -103,8 +95,7 @@ void get_online_cpus(void) return; cpuhp_lock_acquire_read(); mutex_lock(&cpu_hotplug.lock); - apply_puts_pending(65536); - cpu_hotplug.refcount++; + atomic_inc(&cpu_hotplug.refcount); mutex_unlock(&cpu_hotplug.lock); } EXPORT_SYMBOL_GPL(get_online_cpus); @@ -116,8 +107,7 @@ bool try_get_online_cpus(void) if (!mutex_trylock(&cpu_hotplug.lock)) return false; cpuhp_lock_acquire_tryread(); - apply_puts_pending(65536); - cpu_hotplug.refcount++; + atomic_inc(&cpu_hotplug.refcount); mutex_unlock(&cpu_hotplug.lock); return true; } @@ -125,20 +115,18 @@ EXPORT_SYMBOL_GPL(try_get_online_cpus); void put_online_cpus(void) { + int refcount; + if (cpu_hotplug.active_writer == current) return; - if (!mutex_trylock(&cpu_hotplug.lock)) { - atomic_inc(&cpu_hotplug.puts_pending); - cpuhp_lock_release(); - return; - } - if (WARN_ON(!cpu_hotplug.refcount)) - cpu_hotplug.refcount++; /* try to fix things up */ + refcount = atomic_dec_return(&cpu_hotplug.refcount); + if (WARN_ON(refcount < 0)) /* try to fix things up */ + atomic_inc(&cpu_hotplug.refcount); + + if (refcount <= 0 && waitqueue_active(&cpu_hotplug.wq)) + wake_up(&cpu_hotplug.wq); - if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer)) - wake_up_process(cpu_hotplug.active_writer); - mutex_unlock(&cpu_hotplug.lock); cpuhp_lock_release(); } @@ -168,18 +156,20 @@ EXPORT_SYMBOL_GPL(put_online_cpus); */ void cpu_hotplug_begin(void) { - cpu_hotplug.active_writer = current; + DEFINE_WAIT(wait); + cpu_hotplug.active_writer = current; cpuhp_lock_acquire(); + for (;;) { mutex_lock(&cpu_hotplug.lock); - apply_puts_pending(1); - if (likely(!cpu_hotplug.refcount)) - break; - __set_current_state(TASK_UNINTERRUPTIBLE); + prepare_to_wait(&cpu_hotplug.wq, &wait, TASK_UNINTERRUPTIBLE); + if (likely(!atomic_read(&cpu_hotplug.refcount))) + break; mutex_unlock(&cpu_hotplug.lock); schedule(); } + finish_wait(&cpu_hotplug.wq, &wait); } void cpu_hotplug_done(void) diff --git a/kernel/events/core.c b/kernel/events/core.c index 19efcf13375..7f2fbb8b506 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -872,22 +872,32 @@ void perf_pmu_enable(struct pmu *pmu) pmu->pmu_enable(pmu); } -static DEFINE_PER_CPU(struct list_head, rotation_list); +static DEFINE_PER_CPU(struct list_head, active_ctx_list); /* - * perf_pmu_rotate_start() and perf_rotate_context() are fully serialized - * because they're strictly cpu affine and rotate_start is called with IRQs - * disabled, while rotate_context is called from IRQ context. + * perf_event_ctx_activate(), perf_event_ctx_deactivate(), and + * perf_event_task_tick() are fully serialized because they're strictly cpu + * affine and perf_event_ctx{activate,deactivate} are called with IRQs + * disabled, while perf_event_task_tick is called from IRQ context. */ -static void perf_pmu_rotate_start(struct pmu *pmu) +static void perf_event_ctx_activate(struct perf_event_context *ctx) { - struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); - struct list_head *head = this_cpu_ptr(&rotation_list); + struct list_head *head = this_cpu_ptr(&active_ctx_list); WARN_ON(!irqs_disabled()); - if (list_empty(&cpuctx->rotation_list)) - list_add(&cpuctx->rotation_list, head); + WARN_ON(!list_empty(&ctx->active_ctx_list)); + + list_add(&ctx->active_ctx_list, head); +} + +static void perf_event_ctx_deactivate(struct perf_event_context *ctx) +{ + WARN_ON(!irqs_disabled()); + + WARN_ON(list_empty(&ctx->active_ctx_list)); + + list_del_init(&ctx->active_ctx_list); } static void get_ctx(struct perf_event_context *ctx) @@ -907,6 +917,84 @@ static void put_ctx(struct perf_event_context *ctx) } /* + * Because of perf_event::ctx migration in sys_perf_event_open::move_group and + * perf_pmu_migrate_context() we need some magic. + * + * Those places that change perf_event::ctx will hold both + * perf_event_ctx::mutex of the 'old' and 'new' ctx value. + * + * Lock ordering is by mutex address. There is one other site where + * perf_event_context::mutex nests and that is put_event(). But remember that + * that is a parent<->child context relation, and migration does not affect + * children, therefore these two orderings should not interact. + * + * The change in perf_event::ctx does not affect children (as claimed above) + * because the sys_perf_event_open() case will install a new event and break + * the ctx parent<->child relation, and perf_pmu_migrate_context() is only + * concerned with cpuctx and that doesn't have children. + * + * The places that change perf_event::ctx will issue: + * + * perf_remove_from_context(); + * synchronize_rcu(); + * perf_install_in_context(); + * + * to affect the change. The remove_from_context() + synchronize_rcu() should + * quiesce the event, after which we can install it in the new location. This + * means that only external vectors (perf_fops, prctl) can perturb the event + * while in transit. Therefore all such accessors should also acquire + * perf_event_context::mutex to serialize against this. + * + * However; because event->ctx can change while we're waiting to acquire + * ctx->mutex we must be careful and use the below perf_event_ctx_lock() + * function. + * + * Lock order: + * task_struct::perf_event_mutex + * perf_event_context::mutex + * perf_event_context::lock + * perf_event::child_mutex; + * perf_event::mmap_mutex + * mmap_sem + */ +static struct perf_event_context * +perf_event_ctx_lock_nested(struct perf_event *event, int nesting) +{ + struct perf_event_context *ctx; + +again: + rcu_read_lock(); + ctx = ACCESS_ONCE(event->ctx); + if (!atomic_inc_not_zero(&ctx->refcount)) { + rcu_read_unlock(); + goto again; + } + rcu_read_unlock(); + + mutex_lock_nested(&ctx->mutex, nesting); + if (event->ctx != ctx) { + mutex_unlock(&ctx->mutex); + put_ctx(ctx); + goto again; + } + + return ctx; +} + +static inline struct perf_event_context * +perf_event_ctx_lock(struct perf_event *event) +{ + return perf_event_ctx_lock_nested(event, 0); +} + +static void perf_event_ctx_unlock(struct perf_event *event, + struct perf_event_context *ctx) +{ + mutex_unlock(&ctx->mutex); + put_ctx(ctx); +} + +/* * This must be done under the ctx->lock, such as to serialize against * context_equiv(), therefore we cannot call put_ctx() since that might end up * calling scheduler related locks and ctx->lock nests inside those. @@ -1155,8 +1243,6 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) ctx->nr_branch_stack++; list_add_rcu(&event->event_entry, &ctx->event_list); - if (!ctx->nr_events) - perf_pmu_rotate_start(ctx->pmu); ctx->nr_events++; if (event->attr.inherit_stat) ctx->nr_stat++; @@ -1275,6 +1361,8 @@ static void perf_group_attach(struct perf_event *event) if (group_leader == event) return; + WARN_ON_ONCE(group_leader->ctx != event->ctx); + if (group_leader->group_flags & PERF_GROUP_SOFTWARE && !is_software_event(event)) group_leader->group_flags &= ~PERF_GROUP_SOFTWARE; @@ -1296,6 +1384,10 @@ static void list_del_event(struct perf_event *event, struct perf_event_context *ctx) { struct perf_cpu_context *cpuctx; + + WARN_ON_ONCE(event->ctx != ctx); + lockdep_assert_held(&ctx->lock); + /* * We can have double detach due to exit/hot-unplug + close. */ @@ -1380,6 +1472,8 @@ static void perf_group_detach(struct perf_event *event) /* Inherit group flags from the previous leader */ sibling->group_flags = event->group_flags; + + WARN_ON_ONCE(sibling->ctx != event->ctx); } out: @@ -1442,6 +1536,10 @@ event_sched_out(struct perf_event *event, { u64 tstamp = perf_event_time(event); u64 delta; + + WARN_ON_ONCE(event->ctx != ctx); + lockdep_assert_held(&ctx->lock); + /* * An event which could not be activated because of * filter mismatch still needs to have its timings @@ -1471,7 +1569,8 @@ event_sched_out(struct perf_event *event, if (!is_software_event(event)) cpuctx->active_oncpu--; - ctx->nr_active--; + if (!--ctx->nr_active) + perf_event_ctx_deactivate(ctx); if (event->attr.freq && event->attr.sample_freq) ctx->nr_freq--; if (event->attr.exclusive || !cpuctx->active_oncpu) @@ -1654,7 +1753,7 @@ int __perf_event_disable(void *info) * is the current context on this CPU and preemption is disabled, * hence we can't get into perf_event_task_sched_out for this context. */ -void perf_event_disable(struct perf_event *event) +static void _perf_event_disable(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; struct task_struct *task = ctx->task; @@ -1695,6 +1794,19 @@ retry: } raw_spin_unlock_irq(&ctx->lock); } + +/* + * Strictly speaking kernel users cannot create groups and therefore this + * interface does not need the perf_event_ctx_lock() magic. + */ +void perf_event_disable(struct perf_event *event) +{ + struct perf_event_context *ctx; + + ctx = perf_event_ctx_lock(event); + _perf_event_disable(event); + perf_event_ctx_unlock(event, ctx); +} EXPORT_SYMBOL_GPL(perf_event_disable); static void perf_set_shadow_time(struct perf_event *event, @@ -1782,7 +1894,8 @@ event_sched_in(struct perf_event *event, if (!is_software_event(event)) cpuctx->active_oncpu++; - ctx->nr_active++; + if (!ctx->nr_active++) + perf_event_ctx_activate(ctx); if (event->attr.freq && event->attr.sample_freq) ctx->nr_freq++; @@ -2158,7 +2271,7 @@ unlock: * perf_event_for_each_child or perf_event_for_each as described * for perf_event_disable. */ -void perf_event_enable(struct perf_event *event) +static void _perf_event_enable(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; struct task_struct *task = ctx->task; @@ -2214,9 +2327,21 @@ retry: out: raw_spin_unlock_irq(&ctx->lock); } + +/* + * See perf_event_disable(); + */ +void perf_event_enable(struct perf_event *event) +{ + struct perf_event_context *ctx; + + ctx = perf_event_ctx_lock(event); + _perf_event_enable(event); + perf_event_ctx_unlock(event, ctx); +} EXPORT_SYMBOL_GPL(perf_event_enable); -int perf_event_refresh(struct perf_event *event, int refresh) +static int _perf_event_refresh(struct perf_event *event, int refresh) { /* * not supported on inherited events @@ -2225,10 +2350,25 @@ int perf_event_refresh(struct perf_event *event, int refresh) return -EINVAL; atomic_add(refresh, &event->event_limit); - perf_event_enable(event); + _perf_event_enable(event); return 0; } + +/* + * See perf_event_disable() + */ +int perf_event_refresh(struct perf_event *event, int refresh) +{ + struct perf_event_context *ctx; + int ret; + + ctx = perf_event_ctx_lock(event); + ret = _perf_event_refresh(event, refresh); + perf_event_ctx_unlock(event, ctx); + + return ret; +} EXPORT_SYMBOL_GPL(perf_event_refresh); static void ctx_sched_out(struct perf_event_context *ctx, @@ -2612,12 +2752,6 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, perf_pmu_enable(ctx->pmu); perf_ctx_unlock(cpuctx, ctx); - - /* - * Since these rotations are per-cpu, we need to ensure the - * cpu-context we got scheduled on is actually rotating. - */ - perf_pmu_rotate_start(ctx->pmu); } /* @@ -2905,25 +3039,18 @@ static void rotate_ctx(struct perf_event_context *ctx) list_rotate_left(&ctx->flexible_groups); } -/* - * perf_pmu_rotate_start() and perf_rotate_context() are fully serialized - * because they're strictly cpu affine and rotate_start is called with IRQs - * disabled, while rotate_context is called from IRQ context. - */ static int perf_rotate_context(struct perf_cpu_context *cpuctx) { struct perf_event_context *ctx = NULL; - int rotate = 0, remove = 1; + int rotate = 0; if (cpuctx->ctx.nr_events) { - remove = 0; if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active) rotate = 1; } ctx = cpuctx->task_ctx; if (ctx && ctx->nr_events) { - remove = 0; if (ctx->nr_events != ctx->nr_active) rotate = 1; } @@ -2947,8 +3074,6 @@ static int perf_rotate_context(struct perf_cpu_context *cpuctx) perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); done: - if (remove) - list_del_init(&cpuctx->rotation_list); return rotate; } @@ -2966,9 +3091,8 @@ bool perf_event_can_stop_tick(void) void perf_event_task_tick(void) { - struct list_head *head = this_cpu_ptr(&rotation_list); - struct perf_cpu_context *cpuctx, *tmp; - struct perf_event_context *ctx; + struct list_head *head = this_cpu_ptr(&active_ctx_list); + struct perf_event_context *ctx, *tmp; int throttled; WARN_ON(!irqs_disabled()); @@ -2976,14 +3100,8 @@ void perf_event_task_tick(void) __this_cpu_inc(perf_throttled_seq); throttled = __this_cpu_xchg(perf_throttled_count, 0); - list_for_each_entry_safe(cpuctx, tmp, head, rotation_list) { - ctx = &cpuctx->ctx; + list_for_each_entry_safe(ctx, tmp, head, active_ctx_list) perf_adjust_freq_unthr_context(ctx, throttled); - - ctx = cpuctx->task_ctx; - if (ctx) - perf_adjust_freq_unthr_context(ctx, throttled); - } } static int event_enable_on_exec(struct perf_event *event, @@ -3142,6 +3260,7 @@ static void __perf_event_init_context(struct perf_event_context *ctx) { raw_spin_lock_init(&ctx->lock); mutex_init(&ctx->mutex); + INIT_LIST_HEAD(&ctx->active_ctx_list); INIT_LIST_HEAD(&ctx->pinned_groups); INIT_LIST_HEAD(&ctx->flexible_groups); INIT_LIST_HEAD(&ctx->event_list); @@ -3421,7 +3540,16 @@ static void perf_remove_from_owner(struct perf_event *event) rcu_read_unlock(); if (owner) { - mutex_lock(&owner->perf_event_mutex); + /* + * If we're here through perf_event_exit_task() we're already + * holding ctx->mutex which would be an inversion wrt. the + * normal lock order. + * + * However we can safely take this lock because its the child + * ctx->mutex. + */ + mutex_lock_nested(&owner->perf_event_mutex, SINGLE_DEPTH_NESTING); + /* * We have to re-check the event->owner field, if it is cleared * we raced with perf_event_exit_task(), acquiring the mutex @@ -3440,7 +3568,7 @@ static void perf_remove_from_owner(struct perf_event *event) */ static void put_event(struct perf_event *event) { - struct perf_event_context *ctx = event->ctx; + struct perf_event_context *ctx; if (!atomic_long_dec_and_test(&event->refcount)) return; @@ -3448,7 +3576,6 @@ static void put_event(struct perf_event *event) if (!is_kernel_event(event)) perf_remove_from_owner(event); - WARN_ON_ONCE(ctx->parent_ctx); /* * There are two ways this annotation is useful: * @@ -3461,7 +3588,8 @@ static void put_event(struct perf_event *event) * the last filedesc died, so there is no possibility * to trigger the AB-BA case. */ - mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING); + ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING); + WARN_ON_ONCE(ctx->parent_ctx); perf_remove_from_context(event, true); mutex_unlock(&ctx->mutex); @@ -3547,12 +3675,13 @@ static int perf_event_read_group(struct perf_event *event, u64 read_format, char __user *buf) { struct perf_event *leader = event->group_leader, *sub; - int n = 0, size = 0, ret = -EFAULT; struct perf_event_context *ctx = leader->ctx; - u64 values[5]; + int n = 0, size = 0, ret; u64 count, enabled, running; + u64 values[5]; + + lockdep_assert_held(&ctx->mutex); - mutex_lock(&ctx->mutex); count = perf_event_read_value(leader, &enabled, &running); values[n++] = 1 + leader->nr_siblings; @@ -3567,7 +3696,7 @@ static int perf_event_read_group(struct perf_event *event, size = n * sizeof(u64); if (copy_to_user(buf, values, size)) - goto unlock; + return -EFAULT; ret = size; @@ -3581,14 +3710,11 @@ static int perf_event_read_group(struct perf_event *event, size = n * sizeof(u64); if (copy_to_user(buf + ret, values, size)) { - ret = -EFAULT; - goto unlock; + return -EFAULT; } ret += size; } -unlock: - mutex_unlock(&ctx->mutex); return ret; } @@ -3660,8 +3786,14 @@ static ssize_t perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct perf_event *event = file->private_data; + struct perf_event_context *ctx; + int ret; - return perf_read_hw(event, buf, count); + ctx = perf_event_ctx_lock(event); + ret = perf_read_hw(event, buf, count); + perf_event_ctx_unlock(event, ctx); + + return ret; } static unsigned int perf_poll(struct file *file, poll_table *wait) @@ -3687,7 +3819,7 @@ static unsigned int perf_poll(struct file *file, poll_table *wait) return events; } -static void perf_event_reset(struct perf_event *event) +static void _perf_event_reset(struct perf_event *event) { (void)perf_event_read(event); local64_set(&event->count, 0); @@ -3706,6 +3838,7 @@ static void perf_event_for_each_child(struct perf_event *event, struct perf_event *child; WARN_ON_ONCE(event->ctx->parent_ctx); + mutex_lock(&event->child_mutex); func(event); list_for_each_entry(child, &event->child_list, child_list) @@ -3719,14 +3852,13 @@ static void perf_event_for_each(struct perf_event *event, struct perf_event_context *ctx = event->ctx; struct perf_event *sibling; - WARN_ON_ONCE(ctx->parent_ctx); - mutex_lock(&ctx->mutex); + lockdep_assert_held(&ctx->mutex); + event = event->group_leader; perf_event_for_each_child(event, func); list_for_each_entry(sibling, &event->sibling_list, group_entry) perf_event_for_each_child(sibling, func); - mutex_unlock(&ctx->mutex); } static int perf_event_period(struct perf_event *event, u64 __user *arg) @@ -3796,25 +3928,24 @@ static int perf_event_set_output(struct perf_event *event, struct perf_event *output_event); static int perf_event_set_filter(struct perf_event *event, void __user *arg); -static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned long arg) { - struct perf_event *event = file->private_data; void (*func)(struct perf_event *); u32 flags = arg; switch (cmd) { case PERF_EVENT_IOC_ENABLE: - func = perf_event_enable; + func = _perf_event_enable; break; case PERF_EVENT_IOC_DISABLE: - func = perf_event_disable; + func = _perf_event_disable; break; case PERF_EVENT_IOC_RESET: - func = perf_event_reset; + func = _perf_event_reset; break; case PERF_EVENT_IOC_REFRESH: - return perf_event_refresh(event, arg); + return _perf_event_refresh(event, arg); case PERF_EVENT_IOC_PERIOD: return perf_event_period(event, (u64 __user *)arg); @@ -3861,6 +3992,19 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return 0; } +static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct perf_event *event = file->private_data; + struct perf_event_context *ctx; + long ret; + + ctx = perf_event_ctx_lock(event); + ret = _perf_ioctl(event, cmd, arg); + perf_event_ctx_unlock(event, ctx); + + return ret; +} + #ifdef CONFIG_COMPAT static long perf_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) @@ -3883,11 +4027,15 @@ static long perf_compat_ioctl(struct file *file, unsigned int cmd, int perf_event_task_enable(void) { + struct perf_event_context *ctx; struct perf_event *event; mutex_lock(¤t->perf_event_mutex); - list_for_each_entry(event, ¤t->perf_event_list, owner_entry) - perf_event_for_each_child(event, perf_event_enable); + list_for_each_entry(event, ¤t->perf_event_list, owner_entry) { + ctx = perf_event_ctx_lock(event); + perf_event_for_each_child(event, _perf_event_enable); + perf_event_ctx_unlock(event, ctx); + } mutex_unlock(¤t->perf_event_mutex); return 0; @@ -3895,11 +4043,15 @@ int perf_event_task_enable(void) int perf_event_task_disable(void) { + struct perf_event_context *ctx; struct perf_event *event; mutex_lock(¤t->perf_event_mutex); - list_for_each_entry(event, ¤t->perf_event_list, owner_entry) - perf_event_for_each_child(event, perf_event_disable); + list_for_each_entry(event, ¤t->perf_event_list, owner_entry) { + ctx = perf_event_ctx_lock(event); + perf_event_for_each_child(event, _perf_event_disable); + perf_event_ctx_unlock(event, ctx); + } mutex_unlock(¤t->perf_event_mutex); return 0; @@ -5889,6 +6041,8 @@ end: rcu_read_unlock(); } +DEFINE_PER_CPU(struct pt_regs, __perf_regs[4]); + int perf_swevent_get_recursion_context(void) { struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable); @@ -5904,21 +6058,30 @@ inline void perf_swevent_put_recursion_context(int rctx) put_recursion_context(swhash->recursion, rctx); } -void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) +void ___perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { struct perf_sample_data data; - int rctx; - preempt_disable_notrace(); - rctx = perf_swevent_get_recursion_context(); - if (rctx < 0) + if (WARN_ON_ONCE(!regs)) return; perf_sample_data_init(&data, addr, 0); - do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, &data, regs); +} + +void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) +{ + int rctx; + + preempt_disable_notrace(); + rctx = perf_swevent_get_recursion_context(); + if (unlikely(rctx < 0)) + goto fail; + + ___perf_sw_event(event_id, nr, regs, addr); perf_swevent_put_recursion_context(rctx); +fail: preempt_enable_notrace(); } @@ -6780,7 +6943,6 @@ skip_type: __perf_cpu_hrtimer_init(cpuctx, cpu); - INIT_LIST_HEAD(&cpuctx->rotation_list); cpuctx->unique_pmu = pmu; } @@ -6853,6 +7015,20 @@ void perf_pmu_unregister(struct pmu *pmu) } EXPORT_SYMBOL_GPL(perf_pmu_unregister); +static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) +{ + int ret; + + if (!try_module_get(pmu->module)) + return -ENODEV; + event->pmu = pmu; + ret = pmu->event_init(event); + if (ret) + module_put(pmu->module); + + return ret; +} + struct pmu *perf_init_event(struct perf_event *event) { struct pmu *pmu = NULL; @@ -6865,24 +7041,14 @@ struct pmu *perf_init_event(struct perf_event *event) pmu = idr_find(&pmu_idr, event->attr.type); rcu_read_unlock(); if (pmu) { - if (!try_module_get(pmu->module)) { - pmu = ERR_PTR(-ENODEV); - goto unlock; - } - event->pmu = pmu; - ret = pmu->event_init(event); + ret = perf_try_init_event(pmu, event); if (ret) pmu = ERR_PTR(ret); goto unlock; } list_for_each_entry_rcu(pmu, &pmus, entry) { - if (!try_module_get(pmu->module)) { - pmu = ERR_PTR(-ENODEV); - goto unlock; - } - event->pmu = pmu; - ret = pmu->event_init(event); + ret = perf_try_init_event(pmu, event); if (!ret) goto unlock; @@ -7246,6 +7412,15 @@ out: return ret; } +static void mutex_lock_double(struct mutex *a, struct mutex *b) +{ + if (b < a) + swap(a, b); + + mutex_lock(a); + mutex_lock_nested(b, SINGLE_DEPTH_NESTING); +} + /** * sys_perf_event_open - open a performance event, associate it to a task/cpu * @@ -7261,7 +7436,7 @@ SYSCALL_DEFINE5(perf_event_open, struct perf_event *group_leader = NULL, *output_event = NULL; struct perf_event *event, *sibling; struct perf_event_attr attr; - struct perf_event_context *ctx; + struct perf_event_context *ctx, *uninitialized_var(gctx); struct file *event_file = NULL; struct fd group = {NULL, 0}; struct task_struct *task = NULL; @@ -7459,43 +7634,68 @@ SYSCALL_DEFINE5(perf_event_open, } if (move_group) { - struct perf_event_context *gctx = group_leader->ctx; - - mutex_lock(&gctx->mutex); - perf_remove_from_context(group_leader, false); + gctx = group_leader->ctx; /* - * Removing from the context ends up with disabled - * event. What we want here is event in the initial - * startup state, ready to be add into new context. + * See perf_event_ctx_lock() for comments on the details + * of swizzling perf_event::ctx. */ - perf_event__state_init(group_leader); + mutex_lock_double(&gctx->mutex, &ctx->mutex); + + perf_remove_from_context(group_leader, false); + list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { perf_remove_from_context(sibling, false); - perf_event__state_init(sibling); put_ctx(gctx); } - mutex_unlock(&gctx->mutex); - put_ctx(gctx); + } else { + mutex_lock(&ctx->mutex); } WARN_ON_ONCE(ctx->parent_ctx); - mutex_lock(&ctx->mutex); if (move_group) { + /* + * Wait for everybody to stop referencing the events through + * the old lists, before installing it on new lists. + */ synchronize_rcu(); - perf_install_in_context(ctx, group_leader, group_leader->cpu); - get_ctx(ctx); + + /* + * Install the group siblings before the group leader. + * + * Because a group leader will try and install the entire group + * (through the sibling list, which is still in-tact), we can + * end up with siblings installed in the wrong context. + * + * By installing siblings first we NO-OP because they're not + * reachable through the group lists. + */ list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { + perf_event__state_init(sibling); perf_install_in_context(ctx, sibling, sibling->cpu); get_ctx(ctx); } + + /* + * Removing from the context ends up with disabled + * event. What we want here is event in the initial + * startup state, ready to be add into new context. + */ + perf_event__state_init(group_leader); + perf_install_in_context(ctx, group_leader, group_leader->cpu); + get_ctx(ctx); } perf_install_in_context(ctx, event, event->cpu); perf_unpin_context(ctx); + + if (move_group) { + mutex_unlock(&gctx->mutex); + put_ctx(gctx); + } mutex_unlock(&ctx->mutex); put_online_cpus(); @@ -7603,7 +7803,11 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) src_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, src_cpu)->ctx; dst_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, dst_cpu)->ctx; - mutex_lock(&src_ctx->mutex); + /* + * See perf_event_ctx_lock() for comments on the details + * of swizzling perf_event::ctx. + */ + mutex_lock_double(&src_ctx->mutex, &dst_ctx->mutex); list_for_each_entry_safe(event, tmp, &src_ctx->event_list, event_entry) { perf_remove_from_context(event, false); @@ -7611,11 +7815,36 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) put_ctx(src_ctx); list_add(&event->migrate_entry, &events); } - mutex_unlock(&src_ctx->mutex); + /* + * Wait for the events to quiesce before re-instating them. + */ synchronize_rcu(); - mutex_lock(&dst_ctx->mutex); + /* + * Re-instate events in 2 passes. + * + * Skip over group leaders and only install siblings on this first + * pass, siblings will not get enabled without a leader, however a + * leader will enable its siblings, even if those are still on the old + * context. + */ + list_for_each_entry_safe(event, tmp, &events, migrate_entry) { + if (event->group_leader == event) + continue; + + list_del(&event->migrate_entry); + if (event->state >= PERF_EVENT_STATE_OFF) + event->state = PERF_EVENT_STATE_INACTIVE; + account_event_cpu(event, dst_cpu); + perf_install_in_context(dst_ctx, event, dst_cpu); + get_ctx(dst_ctx); + } + + /* + * Once all the siblings are setup properly, install the group leaders + * to make it go. + */ list_for_each_entry_safe(event, tmp, &events, migrate_entry) { list_del(&event->migrate_entry); if (event->state >= PERF_EVENT_STATE_OFF) @@ -7625,6 +7854,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) get_ctx(dst_ctx); } mutex_unlock(&dst_ctx->mutex); + mutex_unlock(&src_ctx->mutex); } EXPORT_SYMBOL_GPL(perf_pmu_migrate_context); @@ -7811,14 +8041,19 @@ static void perf_free_event(struct perf_event *event, put_event(parent); + raw_spin_lock_irq(&ctx->lock); perf_group_detach(event); list_del_event(event, ctx); + raw_spin_unlock_irq(&ctx->lock); free_event(event); } /* - * free an unexposed, unused context as created by inheritance by + * Free an unexposed, unused context as created by inheritance by * perf_event_init_task below, used by fork() in case of fail. + * + * Not all locks are strictly required, but take them anyway to be nice and + * help out with the lockdep assertions. */ void perf_event_free_task(struct task_struct *task) { @@ -8137,7 +8372,7 @@ static void __init perf_event_init_all_cpus(void) for_each_possible_cpu(cpu) { swhash = &per_cpu(swevent_htable, cpu); mutex_init(&swhash->hlist_mutex); - INIT_LIST_HEAD(&per_cpu(rotation_list, cpu)); + INIT_LIST_HEAD(&per_cpu(active_ctx_list, cpu)); } } @@ -8158,22 +8393,11 @@ static void perf_event_init_cpu(int cpu) } #if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC -static void perf_pmu_rotate_stop(struct pmu *pmu) -{ - struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); - - WARN_ON(!irqs_disabled()); - - list_del_init(&cpuctx->rotation_list); -} - static void __perf_event_exit_context(void *__info) { struct remove_event re = { .detach_group = true }; struct perf_event_context *ctx = __info; - perf_pmu_rotate_stop(ctx->pmu); - rcu_read_lock(); list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry) __perf_remove_from_context(&re); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 146a5792b1d..eadb95ce7aa 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -13,12 +13,13 @@ #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/circ_buf.h> +#include <linux/poll.h> #include "internal.h" static void perf_output_wakeup(struct perf_output_handle *handle) { - atomic_set(&handle->rb->poll, POLL_IN); + atomic_set(&handle->rb->poll, POLLIN); handle->event->pending_wakeup = 1; irq_work_queue(&handle->event->pending); diff --git a/kernel/fork.c b/kernel/fork.c index 4dc2ddade9f..b379d9abddc 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -438,12 +438,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) atomic_inc(&mapping->i_mmap_writable); flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ - if (unlikely(tmp->vm_flags & VM_NONLINEAR)) - vma_nonlinear_insert(tmp, - &mapping->i_mmap_nonlinear); - else - vma_interval_tree_insert_after(tmp, mpnt, - &mapping->i_mmap); + vma_interval_tree_insert_after(tmp, mpnt, + &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); i_mmap_unlock_write(mapping); } diff --git a/kernel/futex.c b/kernel/futex.c index 63678b573d6..4eeb63de7e5 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2258,7 +2258,7 @@ static long futex_wait_restart(struct restart_block *restart) * if there are waiters then it will block, it does PI, etc. (Due to * races the kernel might see a 0 value of the futex too.) */ -static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, int detect, +static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock) { struct hrtimer_sleeper timeout, *to = NULL; @@ -2953,11 +2953,11 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, case FUTEX_WAKE_OP: return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); case FUTEX_LOCK_PI: - return futex_lock_pi(uaddr, flags, val, timeout, 0); + return futex_lock_pi(uaddr, flags, timeout, 0); case FUTEX_UNLOCK_PI: return futex_unlock_pi(uaddr, flags); case FUTEX_TRYLOCK_PI: - return futex_lock_pi(uaddr, flags, 0, timeout, 1); + return futex_lock_pi(uaddr, flags, NULL, 1); case FUTEX_WAIT_REQUEUE_PI: val3 = FUTEX_BITSET_MATCH_ANY; return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, diff --git a/kernel/kexec.c b/kernel/kexec.c index 9a8a01abbae..c85277639b3 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -2512,7 +2512,7 @@ static int kexec_apply_relocations(struct kimage *image) continue; /* - * Respective archicture needs to provide support for applying + * Respective architecture needs to provide support for applying * relocations of type SHT_RELA/SHT_REL. */ if (sechdrs[i].sh_type == SHT_RELA) diff --git a/kernel/livepatch/Kconfig b/kernel/livepatch/Kconfig new file mode 100644 index 00000000000..04502255793 --- /dev/null +++ b/kernel/livepatch/Kconfig @@ -0,0 +1,18 @@ +config HAVE_LIVEPATCH + bool + help + Arch supports kernel live patching + +config LIVEPATCH + bool "Kernel Live Patching" + depends on DYNAMIC_FTRACE_WITH_REGS + depends on MODULES + depends on SYSFS + depends on KALLSYMS_ALL + depends on HAVE_LIVEPATCH + help + Say Y here if you want to support kernel live patching. + This option has no runtime impact until a kernel "patch" + module uses the interface provided by this option to register + a patch, causing calls to patched functions to be redirected + to new function code contained in the patch module. diff --git a/kernel/livepatch/Makefile b/kernel/livepatch/Makefile new file mode 100644 index 00000000000..e8780c0901d --- /dev/null +++ b/kernel/livepatch/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_LIVEPATCH) += livepatch.o + +livepatch-objs := core.o diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c new file mode 100644 index 00000000000..ff7f47d026a --- /dev/null +++ b/kernel/livepatch/core.c @@ -0,0 +1,1015 @@ +/* + * core.c - Kernel Live Patching Core + * + * Copyright (C) 2014 Seth Jennings <sjenning@redhat.com> + * Copyright (C) 2014 SUSE + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/ftrace.h> +#include <linux/list.h> +#include <linux/kallsyms.h> +#include <linux/livepatch.h> + +/** + * struct klp_ops - structure for tracking registered ftrace ops structs + * + * A single ftrace_ops is shared between all enabled replacement functions + * (klp_func structs) which have the same old_addr. This allows the switch + * between function versions to happen instantaneously by updating the klp_ops + * struct's func_stack list. The winner is the klp_func at the top of the + * func_stack (front of the list). + * + * @node: node for the global klp_ops list + * @func_stack: list head for the stack of klp_func's (active func is on top) + * @fops: registered ftrace ops struct + */ +struct klp_ops { + struct list_head node; + struct list_head func_stack; + struct ftrace_ops fops; +}; + +/* + * The klp_mutex protects the global lists and state transitions of any + * structure reachable from them. References to any structure must be obtained + * under mutex protection (except in klp_ftrace_handler(), which uses RCU to + * ensure it gets consistent data). + */ +static DEFINE_MUTEX(klp_mutex); + +static LIST_HEAD(klp_patches); +static LIST_HEAD(klp_ops); + +static struct kobject *klp_root_kobj; + +static struct klp_ops *klp_find_ops(unsigned long old_addr) +{ + struct klp_ops *ops; + struct klp_func *func; + + list_for_each_entry(ops, &klp_ops, node) { + func = list_first_entry(&ops->func_stack, struct klp_func, + stack_node); + if (func->old_addr == old_addr) + return ops; + } + + return NULL; +} + +static bool klp_is_module(struct klp_object *obj) +{ + return obj->name; +} + +static bool klp_is_object_loaded(struct klp_object *obj) +{ + return !obj->name || obj->mod; +} + +/* sets obj->mod if object is not vmlinux and module is found */ +static void klp_find_object_module(struct klp_object *obj) +{ + if (!klp_is_module(obj)) + return; + + mutex_lock(&module_mutex); + /* + * We don't need to take a reference on the module here because we have + * the klp_mutex, which is also taken by the module notifier. This + * prevents any module from unloading until we release the klp_mutex. + */ + obj->mod = find_module(obj->name); + mutex_unlock(&module_mutex); +} + +/* klp_mutex must be held by caller */ +static bool klp_is_patch_registered(struct klp_patch *patch) +{ + struct klp_patch *mypatch; + + list_for_each_entry(mypatch, &klp_patches, list) + if (mypatch == patch) + return true; + + return false; +} + +static bool klp_initialized(void) +{ + return klp_root_kobj; +} + +struct klp_find_arg { + const char *objname; + const char *name; + unsigned long addr; + /* + * If count == 0, the symbol was not found. If count == 1, a unique + * match was found and addr is set. If count > 1, there is + * unresolvable ambiguity among "count" number of symbols with the same + * name in the same object. + */ + unsigned long count; +}; + +static int klp_find_callback(void *data, const char *name, + struct module *mod, unsigned long addr) +{ + struct klp_find_arg *args = data; + + if ((mod && !args->objname) || (!mod && args->objname)) + return 0; + + if (strcmp(args->name, name)) + return 0; + + if (args->objname && strcmp(args->objname, mod->name)) + return 0; + + /* + * args->addr might be overwritten if another match is found + * but klp_find_object_symbol() handles this and only returns the + * addr if count == 1. + */ + args->addr = addr; + args->count++; + + return 0; +} + +static int klp_find_object_symbol(const char *objname, const char *name, + unsigned long *addr) +{ + struct klp_find_arg args = { + .objname = objname, + .name = name, + .addr = 0, + .count = 0 + }; + + kallsyms_on_each_symbol(klp_find_callback, &args); + + if (args.count == 0) + pr_err("symbol '%s' not found in symbol table\n", name); + else if (args.count > 1) + pr_err("unresolvable ambiguity (%lu matches) on symbol '%s' in object '%s'\n", + args.count, name, objname); + else { + *addr = args.addr; + return 0; + } + + *addr = 0; + return -EINVAL; +} + +struct klp_verify_args { + const char *name; + const unsigned long addr; +}; + +static int klp_verify_callback(void *data, const char *name, + struct module *mod, unsigned long addr) +{ + struct klp_verify_args *args = data; + + if (!mod && + !strcmp(args->name, name) && + args->addr == addr) + return 1; + + return 0; +} + +static int klp_verify_vmlinux_symbol(const char *name, unsigned long addr) +{ + struct klp_verify_args args = { + .name = name, + .addr = addr, + }; + + if (kallsyms_on_each_symbol(klp_verify_callback, &args)) + return 0; + + pr_err("symbol '%s' not found at specified address 0x%016lx, kernel mismatch?\n", + name, addr); + return -EINVAL; +} + +static int klp_find_verify_func_addr(struct klp_object *obj, + struct klp_func *func) +{ + int ret; + +#if defined(CONFIG_RANDOMIZE_BASE) + /* KASLR is enabled, disregard old_addr from user */ + func->old_addr = 0; +#endif + + if (!func->old_addr || klp_is_module(obj)) + ret = klp_find_object_symbol(obj->name, func->old_name, + &func->old_addr); + else + ret = klp_verify_vmlinux_symbol(func->old_name, + func->old_addr); + + return ret; +} + +/* + * external symbols are located outside the parent object (where the parent + * object is either vmlinux or the kmod being patched). + */ +static int klp_find_external_symbol(struct module *pmod, const char *name, + unsigned long *addr) +{ + const struct kernel_symbol *sym; + + /* first, check if it's an exported symbol */ + preempt_disable(); + sym = find_symbol(name, NULL, NULL, true, true); + preempt_enable(); + if (sym) { + *addr = sym->value; + return 0; + } + + /* otherwise check if it's in another .o within the patch module */ + return klp_find_object_symbol(pmod->name, name, addr); +} + +static int klp_write_object_relocations(struct module *pmod, + struct klp_object *obj) +{ + int ret; + struct klp_reloc *reloc; + + if (WARN_ON(!klp_is_object_loaded(obj))) + return -EINVAL; + + if (WARN_ON(!obj->relocs)) + return -EINVAL; + + for (reloc = obj->relocs; reloc->name; reloc++) { + if (!klp_is_module(obj)) { + ret = klp_verify_vmlinux_symbol(reloc->name, + reloc->val); + if (ret) + return ret; + } else { + /* module, reloc->val needs to be discovered */ + if (reloc->external) + ret = klp_find_external_symbol(pmod, + reloc->name, + &reloc->val); + else + ret = klp_find_object_symbol(obj->mod->name, + reloc->name, + &reloc->val); + if (ret) + return ret; + } + ret = klp_write_module_reloc(pmod, reloc->type, reloc->loc, + reloc->val + reloc->addend); + if (ret) { + pr_err("relocation failed for symbol '%s' at 0x%016lx (%d)\n", + reloc->name, reloc->val, ret); + return ret; + } + } + + return 0; +} + +static void notrace klp_ftrace_handler(unsigned long ip, + unsigned long parent_ip, + struct ftrace_ops *fops, + struct pt_regs *regs) +{ + struct klp_ops *ops; + struct klp_func *func; + + ops = container_of(fops, struct klp_ops, fops); + + rcu_read_lock(); + func = list_first_or_null_rcu(&ops->func_stack, struct klp_func, + stack_node); + rcu_read_unlock(); + + if (WARN_ON_ONCE(!func)) + return; + + klp_arch_set_pc(regs, (unsigned long)func->new_func); +} + +static int klp_disable_func(struct klp_func *func) +{ + struct klp_ops *ops; + int ret; + + if (WARN_ON(func->state != KLP_ENABLED)) + return -EINVAL; + + if (WARN_ON(!func->old_addr)) + return -EINVAL; + + ops = klp_find_ops(func->old_addr); + if (WARN_ON(!ops)) + return -EINVAL; + + if (list_is_singular(&ops->func_stack)) { + ret = unregister_ftrace_function(&ops->fops); + if (ret) { + pr_err("failed to unregister ftrace handler for function '%s' (%d)\n", + func->old_name, ret); + return ret; + } + + ret = ftrace_set_filter_ip(&ops->fops, func->old_addr, 1, 0); + if (ret) + pr_warn("function unregister succeeded but failed to clear the filter\n"); + + list_del_rcu(&func->stack_node); + list_del(&ops->node); + kfree(ops); + } else { + list_del_rcu(&func->stack_node); + } + + func->state = KLP_DISABLED; + + return 0; +} + +static int klp_enable_func(struct klp_func *func) +{ + struct klp_ops *ops; + int ret; + + if (WARN_ON(!func->old_addr)) + return -EINVAL; + + if (WARN_ON(func->state != KLP_DISABLED)) + return -EINVAL; + + ops = klp_find_ops(func->old_addr); + if (!ops) { + ops = kzalloc(sizeof(*ops), GFP_KERNEL); + if (!ops) + return -ENOMEM; + + ops->fops.func = klp_ftrace_handler; + ops->fops.flags = FTRACE_OPS_FL_SAVE_REGS | + FTRACE_OPS_FL_DYNAMIC | + FTRACE_OPS_FL_IPMODIFY; + + list_add(&ops->node, &klp_ops); + + INIT_LIST_HEAD(&ops->func_stack); + list_add_rcu(&func->stack_node, &ops->func_stack); + + ret = ftrace_set_filter_ip(&ops->fops, func->old_addr, 0, 0); + if (ret) { + pr_err("failed to set ftrace filter for function '%s' (%d)\n", + func->old_name, ret); + goto err; + } + + ret = register_ftrace_function(&ops->fops); + if (ret) { + pr_err("failed to register ftrace handler for function '%s' (%d)\n", + func->old_name, ret); + ftrace_set_filter_ip(&ops->fops, func->old_addr, 1, 0); + goto err; + } + + + } else { + list_add_rcu(&func->stack_node, &ops->func_stack); + } + + func->state = KLP_ENABLED; + + return 0; + +err: + list_del_rcu(&func->stack_node); + list_del(&ops->node); + kfree(ops); + return ret; +} + +static int klp_disable_object(struct klp_object *obj) +{ + struct klp_func *func; + int ret; + + for (func = obj->funcs; func->old_name; func++) { + if (func->state != KLP_ENABLED) + continue; + + ret = klp_disable_func(func); + if (ret) + return ret; + } + + obj->state = KLP_DISABLED; + + return 0; +} + +static int klp_enable_object(struct klp_object *obj) +{ + struct klp_func *func; + int ret; + + if (WARN_ON(obj->state != KLP_DISABLED)) + return -EINVAL; + + if (WARN_ON(!klp_is_object_loaded(obj))) + return -EINVAL; + + for (func = obj->funcs; func->old_name; func++) { + ret = klp_enable_func(func); + if (ret) + goto unregister; + } + obj->state = KLP_ENABLED; + + return 0; + +unregister: + WARN_ON(klp_disable_object(obj)); + return ret; +} + +static int __klp_disable_patch(struct klp_patch *patch) +{ + struct klp_object *obj; + int ret; + + /* enforce stacking: only the last enabled patch can be disabled */ + if (!list_is_last(&patch->list, &klp_patches) && + list_next_entry(patch, list)->state == KLP_ENABLED) + return -EBUSY; + + pr_notice("disabling patch '%s'\n", patch->mod->name); + + for (obj = patch->objs; obj->funcs; obj++) { + if (obj->state != KLP_ENABLED) + continue; + + ret = klp_disable_object(obj); + if (ret) + return ret; + } + + patch->state = KLP_DISABLED; + + return 0; +} + +/** + * klp_disable_patch() - disables a registered patch + * @patch: The registered, enabled patch to be disabled + * + * Unregisters the patched functions from ftrace. + * + * Return: 0 on success, otherwise error + */ +int klp_disable_patch(struct klp_patch *patch) +{ + int ret; + + mutex_lock(&klp_mutex); + + if (!klp_is_patch_registered(patch)) { + ret = -EINVAL; + goto err; + } + + if (patch->state == KLP_DISABLED) { + ret = -EINVAL; + goto err; + } + + ret = __klp_disable_patch(patch); + +err: + mutex_unlock(&klp_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(klp_disable_patch); + +static int __klp_enable_patch(struct klp_patch *patch) +{ + struct klp_object *obj; + int ret; + + if (WARN_ON(patch->state != KLP_DISABLED)) + return -EINVAL; + + /* enforce stacking: only the first disabled patch can be enabled */ + if (patch->list.prev != &klp_patches && + list_prev_entry(patch, list)->state == KLP_DISABLED) + return -EBUSY; + + pr_notice_once("tainting kernel with TAINT_LIVEPATCH\n"); + add_taint(TAINT_LIVEPATCH, LOCKDEP_STILL_OK); + + pr_notice("enabling patch '%s'\n", patch->mod->name); + + for (obj = patch->objs; obj->funcs; obj++) { + klp_find_object_module(obj); + + if (!klp_is_object_loaded(obj)) + continue; + + ret = klp_enable_object(obj); + if (ret) + goto unregister; + } + + patch->state = KLP_ENABLED; + + return 0; + +unregister: + WARN_ON(__klp_disable_patch(patch)); + return ret; +} + +/** + * klp_enable_patch() - enables a registered patch + * @patch: The registered, disabled patch to be enabled + * + * Performs the needed symbol lookups and code relocations, + * then registers the patched functions with ftrace. + * + * Return: 0 on success, otherwise error + */ +int klp_enable_patch(struct klp_patch *patch) +{ + int ret; + + mutex_lock(&klp_mutex); + + if (!klp_is_patch_registered(patch)) { + ret = -EINVAL; + goto err; + } + + ret = __klp_enable_patch(patch); + +err: + mutex_unlock(&klp_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(klp_enable_patch); + +/* + * Sysfs Interface + * + * /sys/kernel/livepatch + * /sys/kernel/livepatch/<patch> + * /sys/kernel/livepatch/<patch>/enabled + * /sys/kernel/livepatch/<patch>/<object> + * /sys/kernel/livepatch/<patch>/<object>/<func> + */ + +static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct klp_patch *patch; + int ret; + unsigned long val; + + ret = kstrtoul(buf, 10, &val); + if (ret) + return -EINVAL; + + if (val != KLP_DISABLED && val != KLP_ENABLED) + return -EINVAL; + + patch = container_of(kobj, struct klp_patch, kobj); + + mutex_lock(&klp_mutex); + + if (val == patch->state) { + /* already in requested state */ + ret = -EINVAL; + goto err; + } + + if (val == KLP_ENABLED) { + ret = __klp_enable_patch(patch); + if (ret) + goto err; + } else { + ret = __klp_disable_patch(patch); + if (ret) + goto err; + } + + mutex_unlock(&klp_mutex); + + return count; + +err: + mutex_unlock(&klp_mutex); + return ret; +} + +static ssize_t enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct klp_patch *patch; + + patch = container_of(kobj, struct klp_patch, kobj); + return snprintf(buf, PAGE_SIZE-1, "%d\n", patch->state); +} + +static struct kobj_attribute enabled_kobj_attr = __ATTR_RW(enabled); +static struct attribute *klp_patch_attrs[] = { + &enabled_kobj_attr.attr, + NULL +}; + +static void klp_kobj_release_patch(struct kobject *kobj) +{ + /* + * Once we have a consistency model we'll need to module_put() the + * patch module here. See klp_register_patch() for more details. + */ +} + +static struct kobj_type klp_ktype_patch = { + .release = klp_kobj_release_patch, + .sysfs_ops = &kobj_sysfs_ops, + .default_attrs = klp_patch_attrs, +}; + +static void klp_kobj_release_func(struct kobject *kobj) +{ +} + +static struct kobj_type klp_ktype_func = { + .release = klp_kobj_release_func, + .sysfs_ops = &kobj_sysfs_ops, +}; + +/* + * Free all functions' kobjects in the array up to some limit. When limit is + * NULL, all kobjects are freed. + */ +static void klp_free_funcs_limited(struct klp_object *obj, + struct klp_func *limit) +{ + struct klp_func *func; + + for (func = obj->funcs; func->old_name && func != limit; func++) + kobject_put(&func->kobj); +} + +/* Clean up when a patched object is unloaded */ +static void klp_free_object_loaded(struct klp_object *obj) +{ + struct klp_func *func; + + obj->mod = NULL; + + for (func = obj->funcs; func->old_name; func++) + func->old_addr = 0; +} + +/* + * Free all objects' kobjects in the array up to some limit. When limit is + * NULL, all kobjects are freed. + */ +static void klp_free_objects_limited(struct klp_patch *patch, + struct klp_object *limit) +{ + struct klp_object *obj; + + for (obj = patch->objs; obj->funcs && obj != limit; obj++) { + klp_free_funcs_limited(obj, NULL); + kobject_put(obj->kobj); + } +} + +static void klp_free_patch(struct klp_patch *patch) +{ + klp_free_objects_limited(patch, NULL); + if (!list_empty(&patch->list)) + list_del(&patch->list); + kobject_put(&patch->kobj); +} + +static int klp_init_func(struct klp_object *obj, struct klp_func *func) +{ + INIT_LIST_HEAD(&func->stack_node); + func->state = KLP_DISABLED; + + return kobject_init_and_add(&func->kobj, &klp_ktype_func, + obj->kobj, func->old_name); +} + +/* parts of the initialization that is done only when the object is loaded */ +static int klp_init_object_loaded(struct klp_patch *patch, + struct klp_object *obj) +{ + struct klp_func *func; + int ret; + + if (obj->relocs) { + ret = klp_write_object_relocations(patch->mod, obj); + if (ret) + return ret; + } + + for (func = obj->funcs; func->old_name; func++) { + ret = klp_find_verify_func_addr(obj, func); + if (ret) + return ret; + } + + return 0; +} + +static int klp_init_object(struct klp_patch *patch, struct klp_object *obj) +{ + struct klp_func *func; + int ret; + const char *name; + + if (!obj->funcs) + return -EINVAL; + + obj->state = KLP_DISABLED; + + klp_find_object_module(obj); + + name = klp_is_module(obj) ? obj->name : "vmlinux"; + obj->kobj = kobject_create_and_add(name, &patch->kobj); + if (!obj->kobj) + return -ENOMEM; + + for (func = obj->funcs; func->old_name; func++) { + ret = klp_init_func(obj, func); + if (ret) + goto free; + } + + if (klp_is_object_loaded(obj)) { + ret = klp_init_object_loaded(patch, obj); + if (ret) + goto free; + } + + return 0; + +free: + klp_free_funcs_limited(obj, func); + kobject_put(obj->kobj); + return ret; +} + +static int klp_init_patch(struct klp_patch *patch) +{ + struct klp_object *obj; + int ret; + + if (!patch->objs) + return -EINVAL; + + mutex_lock(&klp_mutex); + + patch->state = KLP_DISABLED; + + ret = kobject_init_and_add(&patch->kobj, &klp_ktype_patch, + klp_root_kobj, patch->mod->name); + if (ret) + goto unlock; + + for (obj = patch->objs; obj->funcs; obj++) { + ret = klp_init_object(patch, obj); + if (ret) + goto free; + } + + list_add_tail(&patch->list, &klp_patches); + + mutex_unlock(&klp_mutex); + + return 0; + +free: + klp_free_objects_limited(patch, obj); + kobject_put(&patch->kobj); +unlock: + mutex_unlock(&klp_mutex); + return ret; +} + +/** + * klp_unregister_patch() - unregisters a patch + * @patch: Disabled patch to be unregistered + * + * Frees the data structures and removes the sysfs interface. + * + * Return: 0 on success, otherwise error + */ +int klp_unregister_patch(struct klp_patch *patch) +{ + int ret = 0; + + mutex_lock(&klp_mutex); + + if (!klp_is_patch_registered(patch)) { + ret = -EINVAL; + goto out; + } + + if (patch->state == KLP_ENABLED) { + ret = -EBUSY; + goto out; + } + + klp_free_patch(patch); + +out: + mutex_unlock(&klp_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(klp_unregister_patch); + +/** + * klp_register_patch() - registers a patch + * @patch: Patch to be registered + * + * Initializes the data structure associated with the patch and + * creates the sysfs interface. + * + * Return: 0 on success, otherwise error + */ +int klp_register_patch(struct klp_patch *patch) +{ + int ret; + + if (!klp_initialized()) + return -ENODEV; + + if (!patch || !patch->mod) + return -EINVAL; + + /* + * A reference is taken on the patch module to prevent it from being + * unloaded. Right now, we don't allow patch modules to unload since + * there is currently no method to determine if a thread is still + * running in the patched code contained in the patch module once + * the ftrace registration is successful. + */ + if (!try_module_get(patch->mod)) + return -ENODEV; + + ret = klp_init_patch(patch); + if (ret) + module_put(patch->mod); + + return ret; +} +EXPORT_SYMBOL_GPL(klp_register_patch); + +static void klp_module_notify_coming(struct klp_patch *patch, + struct klp_object *obj) +{ + struct module *pmod = patch->mod; + struct module *mod = obj->mod; + int ret; + + ret = klp_init_object_loaded(patch, obj); + if (ret) + goto err; + + if (patch->state == KLP_DISABLED) + return; + + pr_notice("applying patch '%s' to loading module '%s'\n", + pmod->name, mod->name); + + ret = klp_enable_object(obj); + if (!ret) + return; + +err: + pr_warn("failed to apply patch '%s' to module '%s' (%d)\n", + pmod->name, mod->name, ret); +} + +static void klp_module_notify_going(struct klp_patch *patch, + struct klp_object *obj) +{ + struct module *pmod = patch->mod; + struct module *mod = obj->mod; + int ret; + + if (patch->state == KLP_DISABLED) + goto disabled; + + pr_notice("reverting patch '%s' on unloading module '%s'\n", + pmod->name, mod->name); + + ret = klp_disable_object(obj); + if (ret) + pr_warn("failed to revert patch '%s' on module '%s' (%d)\n", + pmod->name, mod->name, ret); + +disabled: + klp_free_object_loaded(obj); +} + +static int klp_module_notify(struct notifier_block *nb, unsigned long action, + void *data) +{ + struct module *mod = data; + struct klp_patch *patch; + struct klp_object *obj; + + if (action != MODULE_STATE_COMING && action != MODULE_STATE_GOING) + return 0; + + mutex_lock(&klp_mutex); + + list_for_each_entry(patch, &klp_patches, list) { + for (obj = patch->objs; obj->funcs; obj++) { + if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) + continue; + + if (action == MODULE_STATE_COMING) { + obj->mod = mod; + klp_module_notify_coming(patch, obj); + } else /* MODULE_STATE_GOING */ + klp_module_notify_going(patch, obj); + + break; + } + } + + mutex_unlock(&klp_mutex); + + return 0; +} + +static struct notifier_block klp_module_nb = { + .notifier_call = klp_module_notify, + .priority = INT_MIN+1, /* called late but before ftrace notifier */ +}; + +static int klp_init(void) +{ + int ret; + + ret = klp_check_compiler_support(); + if (ret) { + pr_info("Your compiler is too old; turning off.\n"); + return -EINVAL; + } + + ret = register_module_notifier(&klp_module_nb); + if (ret) + return ret; + + klp_root_kobj = kobject_create_and_add("livepatch", kernel_kobj); + if (!klp_root_kobj) { + ret = -ENOMEM; + goto unregister; + } + + return 0; + +unregister: + unregister_module_notifier(&klp_module_nb); + return ret; +} + +module_init(klp_init); diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 8541bfdfd23..4ca8eb15197 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -1,5 +1,5 @@ -obj-y += mutex.o semaphore.o rwsem.o mcs_spinlock.o +obj-y += mutex.o semaphore.o rwsem.o ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_lockdep.o = -pg @@ -14,6 +14,7 @@ ifeq ($(CONFIG_PROC_FS),y) obj-$(CONFIG_LOCKDEP) += lockdep_proc.o endif obj-$(CONFIG_SMP) += spinlock.o +obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o obj-$(CONFIG_SMP) += lglock.o obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_RT_MUTEXES) += rtmutex.o diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index 4d60986fcbe..d1fe2ba5bac 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -108,20 +108,4 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) arch_mcs_spin_unlock_contended(&next->locked); } -/* - * Cancellable version of the MCS lock above. - * - * Intended for adaptive spinning of sleeping locks: - * mutex_lock()/rwsem_down_{read,write}() etc. - */ - -struct optimistic_spin_node { - struct optimistic_spin_node *next, *prev; - int locked; /* 1 if lock acquired */ - int cpu; /* encoded CPU # value */ -}; - -extern bool osq_lock(struct optimistic_spin_queue *lock); -extern void osq_unlock(struct optimistic_spin_queue *lock); - #endif /* __LINUX_MCS_SPINLOCK_H */ diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 454195194d4..94674e5919c 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -81,7 +81,7 @@ __visible void __sched __mutex_lock_slowpath(atomic_t *lock_count); * The mutex must later on be released by the same task that * acquired it. Recursive locking is not allowed. The task * may not exit without first unlocking the mutex. Also, kernel - * memory where the mutex resides mutex must not be freed with + * memory where the mutex resides must not be freed with * the mutex still locked. The mutex must first be initialized * (or statically defined) before it can be locked. memset()-ing * the mutex to 0 is not allowed. @@ -147,7 +147,7 @@ static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, } /* - * after acquiring lock with fastpath or when we lost out in contested + * After acquiring lock with fastpath or when we lost out in contested * slowpath, set ctx and wake up any waiters so they can recheck. * * This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set, @@ -191,19 +191,32 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, spin_unlock_mutex(&lock->base.wait_lock, flags); } - -#ifdef CONFIG_MUTEX_SPIN_ON_OWNER /* - * In order to avoid a stampede of mutex spinners from acquiring the mutex - * more or less simultaneously, the spinners need to acquire a MCS lock - * first before spinning on the owner field. + * After acquiring lock in the slowpath set ctx and wake up any + * waiters so they can recheck. * + * Callers must hold the mutex wait_lock. */ +static __always_inline void +ww_mutex_set_context_slowpath(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx) +{ + struct mutex_waiter *cur; -/* - * Mutex spinning code migrated from kernel/sched/core.c - */ + ww_mutex_lock_acquired(lock, ctx); + lock->ctx = ctx; + + /* + * Give any possible sleeping processes the chance to wake up, + * so they can recheck if they have to back off. + */ + list_for_each_entry(cur, &lock->base.wait_list, list) { + debug_mutex_wake_waiter(&lock->base, cur); + wake_up_process(cur->task); + } +} +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER static inline bool owner_running(struct mutex *lock, struct task_struct *owner) { if (lock->owner != owner) @@ -307,6 +320,11 @@ static bool mutex_optimistic_spin(struct mutex *lock, if (!mutex_can_spin_on_owner(lock)) goto done; + /* + * In order to avoid a stampede of mutex spinners trying to + * acquire the mutex all at once, the spinners need to take a + * MCS (queued) lock first before spinning on the owner field. + */ if (!osq_lock(&lock->osq)) goto done; @@ -469,7 +487,7 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock) EXPORT_SYMBOL(ww_mutex_unlock); static inline int __sched -__mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx) +__ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx) { struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx); @@ -557,7 +575,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, } if (use_ww_ctx && ww_ctx->acquired > 0) { - ret = __mutex_lock_check_stamp(lock, ww_ctx); + ret = __ww_mutex_lock_check_stamp(lock, ww_ctx); if (ret) goto err; } @@ -569,6 +587,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, schedule_preempt_disabled(); spin_lock_mutex(&lock->wait_lock, flags); } + __set_task_state(task, TASK_RUNNING); + mutex_remove_waiter(lock, &waiter, current_thread_info()); /* set it to 0 if there are no waiters left: */ if (likely(list_empty(&lock->wait_list))) @@ -582,23 +602,7 @@ skip_wait: if (use_ww_ctx) { struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); - struct mutex_waiter *cur; - - /* - * This branch gets optimized out for the common case, - * and is only important for ww_mutex_lock. - */ - ww_mutex_lock_acquired(ww, ww_ctx); - ww->ctx = ww_ctx; - - /* - * Give any possible sleeping processes the chance to wake up, - * so they can recheck if they have to back off. - */ - list_for_each_entry(cur, &lock->wait_list, list) { - debug_mutex_wake_waiter(lock, cur); - wake_up_process(cur->task); - } + ww_mutex_set_context_slowpath(ww, ww_ctx); } spin_unlock_mutex(&lock->wait_lock, flags); diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/osq_lock.c index 9887a905a76..c112d00341b 100644 --- a/kernel/locking/mcs_spinlock.c +++ b/kernel/locking/osq_lock.c @@ -1,8 +1,6 @@ #include <linux/percpu.h> #include <linux/sched.h> -#include "mcs_spinlock.h" - -#ifdef CONFIG_SMP +#include <linux/osq_lock.h> /* * An MCS like lock especially tailored for optimistic spinning for sleeping @@ -111,7 +109,7 @@ bool osq_lock(struct optimistic_spin_queue *lock) * cmpxchg in an attempt to undo our queueing. */ - while (!smp_load_acquire(&node->locked)) { + while (!ACCESS_ONCE(node->locked)) { /* * If we need to reschedule bail... so we can block. */ @@ -203,6 +201,3 @@ void osq_unlock(struct optimistic_spin_queue *lock) if (next) ACCESS_ONCE(next->locked) = 1; } - -#endif - diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 7c98873a307..3059bc2f022 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1130,6 +1130,7 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, set_current_state(state); } + __set_current_state(TASK_RUNNING); return ret; } @@ -1188,10 +1189,9 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk); if (likely(!ret)) + /* sleep on the mutex */ ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); - set_current_state(TASK_RUNNING); - if (unlikely(ret)) { remove_waiter(lock, &waiter); rt_mutex_handle_deadlock(ret, chwalk, &waiter); @@ -1626,10 +1626,9 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, set_current_state(TASK_INTERRUPTIBLE); + /* sleep on the mutex */ ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter); - set_current_state(TASK_RUNNING); - if (unlikely(ret)) remove_waiter(lock, waiter); diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c index 2c93571162c..2555ae15ec1 100644 --- a/kernel/locking/rwsem-spinlock.c +++ b/kernel/locking/rwsem-spinlock.c @@ -154,7 +154,7 @@ void __sched __down_read(struct rw_semaphore *sem) set_task_state(tsk, TASK_UNINTERRUPTIBLE); } - tsk->state = TASK_RUNNING; + __set_task_state(tsk, TASK_RUNNING); out: ; } diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 7628c3fc37c..2f7cc4076f5 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -242,8 +242,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) schedule(); } - tsk->state = TASK_RUNNING; - + __set_task_state(tsk, TASK_RUNNING); return sem; } EXPORT_SYMBOL(rwsem_down_read_failed); diff --git a/kernel/notifier.c b/kernel/notifier.c index 4803da6eab6..ae9fc7cc360 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -402,6 +402,7 @@ int raw_notifier_call_chain(struct raw_notifier_head *nh, } EXPORT_SYMBOL_GPL(raw_notifier_call_chain); +#ifdef CONFIG_SRCU /* * SRCU notifier chain routines. Registration and unregistration * use a mutex, and call_chain is synchronized by SRCU (no locks). @@ -528,6 +529,8 @@ void srcu_init_notifier_head(struct srcu_notifier_head *nh) } EXPORT_SYMBOL_GPL(srcu_init_notifier_head); +#endif /* CONFIG_SRCU */ + static ATOMIC_NOTIFIER_HEAD(die_chain); int notrace notify_die(enum die_val val, const char *str, diff --git a/kernel/panic.c b/kernel/panic.c index 4d8d6f906de..8136ad76e5f 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -226,6 +226,7 @@ static const struct tnt tnts[] = { { TAINT_OOT_MODULE, 'O', ' ' }, { TAINT_UNSIGNED_MODULE, 'E', ' ' }, { TAINT_SOFTLOCKUP, 'L', ' ' }, + { TAINT_LIVEPATCH, 'K', ' ' }, }; /** @@ -246,6 +247,7 @@ static const struct tnt tnts[] = { * 'O' - Out-of-tree module has been loaded. * 'E' - Unsigned module has been loaded. * 'L' - A soft lockup has previously occurred. + * 'K' - Kernel has been live patched. * * The string is overwritten by the next call to print_tainted(). */ diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 48b28d387c7..7e01f78f041 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -251,6 +251,7 @@ config APM_EMULATION config PM_OPP bool + select SRCU ---help--- SOCs have a standard set of tuples consisting of frequency and voltage pairs that the device will support per voltage domain. This diff --git a/kernel/power/qos.c b/kernel/power/qos.c index 5f4c006c4b1..97b0df71303 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -41,6 +41,8 @@ #include <linux/platform_device.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> #include <linux/uaccess.h> #include <linux/export.h> @@ -182,6 +184,81 @@ static inline void pm_qos_set_value(struct pm_qos_constraints *c, s32 value) c->target_value = value; } +static inline int pm_qos_get_value(struct pm_qos_constraints *c); +static int pm_qos_dbg_show_requests(struct seq_file *s, void *unused) +{ + struct pm_qos_object *qos = (struct pm_qos_object *)s->private; + struct pm_qos_constraints *c; + struct pm_qos_request *req; + char *type; + unsigned long flags; + int tot_reqs = 0; + int active_reqs = 0; + + if (IS_ERR_OR_NULL(qos)) { + pr_err("%s: bad qos param!\n", __func__); + return -EINVAL; + } + c = qos->constraints; + if (IS_ERR_OR_NULL(c)) { + pr_err("%s: Bad constraints on qos?\n", __func__); + return -EINVAL; + } + + /* Lock to ensure we have a snapshot */ + spin_lock_irqsave(&pm_qos_lock, flags); + if (plist_head_empty(&c->list)) { + seq_puts(s, "Empty!\n"); + goto out; + } + + switch (c->type) { + case PM_QOS_MIN: + type = "Minimum"; + break; + case PM_QOS_MAX: + type = "Maximum"; + break; + case PM_QOS_SUM: + type = "Sum"; + break; + default: + type = "Unknown"; + } + + plist_for_each_entry(req, &c->list, node) { + char *state = "Default"; + + if ((req->node).prio != c->default_value) { + active_reqs++; + state = "Active"; + } + tot_reqs++; + seq_printf(s, "%d: %d: %s\n", tot_reqs, + (req->node).prio, state); + } + + seq_printf(s, "Type=%s, Value=%d, Requests: active=%d / total=%d\n", + type, pm_qos_get_value(c), active_reqs, tot_reqs); + +out: + spin_unlock_irqrestore(&pm_qos_lock, flags); + return 0; +} + +static int pm_qos_dbg_open(struct inode *inode, struct file *file) +{ + return single_open(file, pm_qos_dbg_show_requests, + inode->i_private); +} + +static const struct file_operations pm_qos_debug_fops = { + .open = pm_qos_dbg_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + /** * pm_qos_update_target - manages the constraints list and calls the notifiers * if needed @@ -509,12 +586,17 @@ int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier) EXPORT_SYMBOL_GPL(pm_qos_remove_notifier); /* User space interface to PM QoS classes via misc devices */ -static int register_pm_qos_misc(struct pm_qos_object *qos) +static int register_pm_qos_misc(struct pm_qos_object *qos, struct dentry *d) { qos->pm_qos_power_miscdev.minor = MISC_DYNAMIC_MINOR; qos->pm_qos_power_miscdev.name = qos->name; qos->pm_qos_power_miscdev.fops = &pm_qos_power_fops; + if (d) { + (void)debugfs_create_file(qos->name, S_IRUGO, d, + (void *)qos, &pm_qos_debug_fops); + } + return misc_register(&qos->pm_qos_power_miscdev); } @@ -608,11 +690,16 @@ static int __init pm_qos_power_init(void) { int ret = 0; int i; + struct dentry *d; BUILD_BUG_ON(ARRAY_SIZE(pm_qos_array) != PM_QOS_NUM_CLASSES); + d = debugfs_create_dir("pm_qos", NULL); + if (IS_ERR_OR_NULL(d)) + d = NULL; + for (i = PM_QOS_CPU_DMA_LATENCY; i < PM_QOS_NUM_CLASSES; i++) { - ret = register_pm_qos_misc(pm_qos_array[i]); + ret = register_pm_qos_misc(pm_qos_array[i], d); if (ret < 0) { printk(KERN_ERR "pm_qos_param: %s setup failed\n", pm_qos_array[i]->name); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 0c40c16174b..c24d5a23bf9 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1472,9 +1472,9 @@ static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages, /** * free_unnecessary_pages - Release preallocated pages not needed for the image */ -static void free_unnecessary_pages(void) +static unsigned long free_unnecessary_pages(void) { - unsigned long save, to_free_normal, to_free_highmem; + unsigned long save, to_free_normal, to_free_highmem, free; save = count_data_pages(); if (alloc_normal >= save) { @@ -1495,6 +1495,7 @@ static void free_unnecessary_pages(void) else to_free_normal = 0; } + free = to_free_normal + to_free_highmem; memory_bm_position_reset(©_bm); @@ -1518,6 +1519,8 @@ static void free_unnecessary_pages(void) swsusp_unset_page_free(page); __free_page(page); } + + return free; } /** @@ -1707,7 +1710,7 @@ int hibernate_preallocate_memory(void) * pages in memory, but we have allocated more. Release the excessive * ones now. */ - free_unnecessary_pages(); + pages -= free_unnecessary_pages(); out: stop = ktime_get(); @@ -2310,8 +2313,6 @@ static inline void free_highmem_data(void) free_image_page(buffer, PG_UNSAFE_CLEAR); } #else -static inline int get_safe_write_buffer(void) { return 0; } - static unsigned int count_highmem_image_pages(struct memory_bitmap *bm) { return 0; } diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile index e6fae503d1b..50a808424b0 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -1,4 +1,5 @@ -obj-y += update.o srcu.o +obj-y += update.o +obj-$(CONFIG_SRCU) += srcu.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o obj-$(CONFIG_TREE_RCU) += tree.o obj-$(CONFIG_PREEMPT_RCU) += tree.o diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 07bb02eda84..80adef7d4c3 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -137,4 +137,10 @@ int rcu_jiffies_till_stall_check(void); void rcu_early_boot_tests(void); +/* + * This function really isn't for public consumption, but RCU is special in + * that context switches can allow the state machine to make progress. + */ +extern void resched_cpu(int cpu); + #endif /* __LINUX_RCU_H */ diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 4d559baf06e..30d42aa55d8 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -244,7 +244,8 @@ struct rcu_torture_ops { int (*readlock)(void); void (*read_delay)(struct torture_random_state *rrsp); void (*readunlock)(int idx); - int (*completed)(void); + unsigned long (*started)(void); + unsigned long (*completed)(void); void (*deferred_free)(struct rcu_torture *p); void (*sync)(void); void (*exp_sync)(void); @@ -296,11 +297,6 @@ static void rcu_torture_read_unlock(int idx) __releases(RCU) rcu_read_unlock(); } -static int rcu_torture_completed(void) -{ - return rcu_batches_completed(); -} - /* * Update callback in the pipe. This should be invoked after a grace period. */ @@ -356,7 +352,7 @@ rcu_torture_cb(struct rcu_head *p) cur_ops->deferred_free(rp); } -static int rcu_no_completed(void) +static unsigned long rcu_no_completed(void) { return 0; } @@ -377,7 +373,8 @@ static struct rcu_torture_ops rcu_ops = { .readlock = rcu_torture_read_lock, .read_delay = rcu_read_delay, .readunlock = rcu_torture_read_unlock, - .completed = rcu_torture_completed, + .started = rcu_batches_started, + .completed = rcu_batches_completed, .deferred_free = rcu_torture_deferred_free, .sync = synchronize_rcu, .exp_sync = synchronize_rcu_expedited, @@ -407,11 +404,6 @@ static void rcu_bh_torture_read_unlock(int idx) __releases(RCU_BH) rcu_read_unlock_bh(); } -static int rcu_bh_torture_completed(void) -{ - return rcu_batches_completed_bh(); -} - static void rcu_bh_torture_deferred_free(struct rcu_torture *p) { call_rcu_bh(&p->rtort_rcu, rcu_torture_cb); @@ -423,7 +415,8 @@ static struct rcu_torture_ops rcu_bh_ops = { .readlock = rcu_bh_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = rcu_bh_torture_read_unlock, - .completed = rcu_bh_torture_completed, + .started = rcu_batches_started_bh, + .completed = rcu_batches_completed_bh, .deferred_free = rcu_bh_torture_deferred_free, .sync = synchronize_rcu_bh, .exp_sync = synchronize_rcu_bh_expedited, @@ -466,6 +459,7 @@ static struct rcu_torture_ops rcu_busted_ops = { .readlock = rcu_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = rcu_torture_read_unlock, + .started = rcu_no_completed, .completed = rcu_no_completed, .deferred_free = rcu_busted_torture_deferred_free, .sync = synchronize_rcu_busted, @@ -510,7 +504,7 @@ static void srcu_torture_read_unlock(int idx) __releases(&srcu_ctl) srcu_read_unlock(&srcu_ctl, idx); } -static int srcu_torture_completed(void) +static unsigned long srcu_torture_completed(void) { return srcu_batches_completed(&srcu_ctl); } @@ -564,6 +558,7 @@ static struct rcu_torture_ops srcu_ops = { .readlock = srcu_torture_read_lock, .read_delay = srcu_read_delay, .readunlock = srcu_torture_read_unlock, + .started = NULL, .completed = srcu_torture_completed, .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, @@ -600,7 +595,8 @@ static struct rcu_torture_ops sched_ops = { .readlock = sched_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = sched_torture_read_unlock, - .completed = rcu_no_completed, + .started = rcu_batches_started_sched, + .completed = rcu_batches_completed_sched, .deferred_free = rcu_sched_torture_deferred_free, .sync = synchronize_sched, .exp_sync = synchronize_sched_expedited, @@ -638,6 +634,7 @@ static struct rcu_torture_ops tasks_ops = { .readlock = tasks_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = tasks_torture_read_unlock, + .started = rcu_no_completed, .completed = rcu_no_completed, .deferred_free = rcu_tasks_torture_deferred_free, .sync = synchronize_rcu_tasks, @@ -1015,8 +1012,8 @@ static void rcutorture_trace_dump(void) static void rcu_torture_timer(unsigned long unused) { int idx; - int completed; - int completed_end; + unsigned long started; + unsigned long completed; static DEFINE_TORTURE_RANDOM(rand); static DEFINE_SPINLOCK(rand_lock); struct rcu_torture *p; @@ -1024,7 +1021,10 @@ static void rcu_torture_timer(unsigned long unused) unsigned long long ts; idx = cur_ops->readlock(); - completed = cur_ops->completed(); + if (cur_ops->started) + started = cur_ops->started(); + else + started = cur_ops->completed(); ts = rcu_trace_clock_local(); p = rcu_dereference_check(rcu_torture_current, rcu_read_lock_bh_held() || @@ -1047,14 +1047,16 @@ static void rcu_torture_timer(unsigned long unused) /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } - completed_end = cur_ops->completed(); + completed = cur_ops->completed(); if (pipe_count > 1) { do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts, - completed, completed_end); + started, completed); rcutorture_trace_dump(); } __this_cpu_inc(rcu_torture_count[pipe_count]); - completed = completed_end - completed; + completed = completed - started; + if (cur_ops->started) + completed++; if (completed > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ completed = RCU_TORTURE_PIPE_LEN; @@ -1073,8 +1075,8 @@ static void rcu_torture_timer(unsigned long unused) static int rcu_torture_reader(void *arg) { - int completed; - int completed_end; + unsigned long started; + unsigned long completed; int idx; DEFINE_TORTURE_RANDOM(rand); struct rcu_torture *p; @@ -1093,7 +1095,10 @@ rcu_torture_reader(void *arg) mod_timer(&t, jiffies + 1); } idx = cur_ops->readlock(); - completed = cur_ops->completed(); + if (cur_ops->started) + started = cur_ops->started(); + else + started = cur_ops->completed(); ts = rcu_trace_clock_local(); p = rcu_dereference_check(rcu_torture_current, rcu_read_lock_bh_held() || @@ -1114,14 +1119,16 @@ rcu_torture_reader(void *arg) /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } - completed_end = cur_ops->completed(); + completed = cur_ops->completed(); if (pipe_count > 1) { do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, - ts, completed, completed_end); + ts, started, completed); rcutorture_trace_dump(); } __this_cpu_inc(rcu_torture_count[pipe_count]); - completed = completed_end - completed; + completed = completed - started; + if (cur_ops->started) + completed++; if (completed > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ completed = RCU_TORTURE_PIPE_LEN; @@ -1420,6 +1427,9 @@ static int rcu_torture_barrier(void *arg) cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */ if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) { n_rcu_torture_barrier_error++; + pr_err("barrier_cbs_invoked = %d, n_barrier_cbs = %d\n", + atomic_read(&barrier_cbs_invoked), + n_barrier_cbs); WARN_ON_ONCE(1); } n_barrier_successes++; diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c index e037f3eb2f7..445bf8ffe3f 100644 --- a/kernel/rcu/srcu.c +++ b/kernel/rcu/srcu.c @@ -546,7 +546,7 @@ EXPORT_SYMBOL_GPL(srcu_barrier); * Report the number of batches, correlated with, but not necessarily * precisely the same as, the number of grace periods that have elapsed. */ -long srcu_batches_completed(struct srcu_struct *sp) +unsigned long srcu_batches_completed(struct srcu_struct *sp) { return sp->completed; } diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 0db5649f881..cc9ceca7bde 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -47,54 +47,14 @@ static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), struct rcu_ctrlblk *rcp); -static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; - #include "tiny_plugin.h" -/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcu/tree.c. */ -static void rcu_idle_enter_common(long long newval) -{ - if (newval) { - RCU_TRACE(trace_rcu_dyntick(TPS("--="), - rcu_dynticks_nesting, newval)); - rcu_dynticks_nesting = newval; - return; - } - RCU_TRACE(trace_rcu_dyntick(TPS("Start"), - rcu_dynticks_nesting, newval)); - if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) { - struct task_struct *idle __maybe_unused = idle_task(smp_processor_id()); - - RCU_TRACE(trace_rcu_dyntick(TPS("Entry error: not idle task"), - rcu_dynticks_nesting, newval)); - ftrace_dump(DUMP_ALL); - WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", - current->pid, current->comm, - idle->pid, idle->comm); /* must be idle task! */ - } - rcu_sched_qs(); /* implies rcu_bh_inc() */ - barrier(); - rcu_dynticks_nesting = newval; -} - /* * Enter idle, which is an extended quiescent state if we have fully - * entered that mode (i.e., if the new value of dynticks_nesting is zero). + * entered that mode. */ void rcu_idle_enter(void) { - unsigned long flags; - long long newval; - - local_irq_save(flags); - WARN_ON_ONCE((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0); - if ((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == - DYNTICK_TASK_NEST_VALUE) - newval = 0; - else - newval = rcu_dynticks_nesting - DYNTICK_TASK_NEST_VALUE; - rcu_idle_enter_common(newval); - local_irq_restore(flags); } EXPORT_SYMBOL_GPL(rcu_idle_enter); @@ -103,55 +63,14 @@ EXPORT_SYMBOL_GPL(rcu_idle_enter); */ void rcu_irq_exit(void) { - unsigned long flags; - long long newval; - - local_irq_save(flags); - newval = rcu_dynticks_nesting - 1; - WARN_ON_ONCE(newval < 0); - rcu_idle_enter_common(newval); - local_irq_restore(flags); } EXPORT_SYMBOL_GPL(rcu_irq_exit); -/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcu/tree.c. */ -static void rcu_idle_exit_common(long long oldval) -{ - if (oldval) { - RCU_TRACE(trace_rcu_dyntick(TPS("++="), - oldval, rcu_dynticks_nesting)); - return; - } - RCU_TRACE(trace_rcu_dyntick(TPS("End"), oldval, rcu_dynticks_nesting)); - if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) { - struct task_struct *idle __maybe_unused = idle_task(smp_processor_id()); - - RCU_TRACE(trace_rcu_dyntick(TPS("Exit error: not idle task"), - oldval, rcu_dynticks_nesting)); - ftrace_dump(DUMP_ALL); - WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", - current->pid, current->comm, - idle->pid, idle->comm); /* must be idle task! */ - } -} - /* * Exit idle, so that we are no longer in an extended quiescent state. */ void rcu_idle_exit(void) { - unsigned long flags; - long long oldval; - - local_irq_save(flags); - oldval = rcu_dynticks_nesting; - WARN_ON_ONCE(rcu_dynticks_nesting < 0); - if (rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) - rcu_dynticks_nesting += DYNTICK_TASK_NEST_VALUE; - else - rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; - rcu_idle_exit_common(oldval); - local_irq_restore(flags); } EXPORT_SYMBOL_GPL(rcu_idle_exit); @@ -160,15 +79,6 @@ EXPORT_SYMBOL_GPL(rcu_idle_exit); */ void rcu_irq_enter(void) { - unsigned long flags; - long long oldval; - - local_irq_save(flags); - oldval = rcu_dynticks_nesting; - rcu_dynticks_nesting++; - WARN_ON_ONCE(rcu_dynticks_nesting == 0); - rcu_idle_exit_common(oldval); - local_irq_restore(flags); } EXPORT_SYMBOL_GPL(rcu_irq_enter); @@ -179,23 +89,13 @@ EXPORT_SYMBOL_GPL(rcu_irq_enter); */ bool notrace __rcu_is_watching(void) { - return rcu_dynticks_nesting; + return true; } EXPORT_SYMBOL(__rcu_is_watching); #endif /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */ /* - * Test whether the current CPU was interrupted from idle. Nested - * interrupts don't count, we must be running at the first interrupt - * level. - */ -static int rcu_is_cpu_rrupt_from_idle(void) -{ - return rcu_dynticks_nesting <= 1; -} - -/* * Helper function for rcu_sched_qs() and rcu_bh_qs(). * Also irqs are disabled to avoid confusion due to interrupt handlers * invoking call_rcu(). @@ -250,7 +150,7 @@ void rcu_bh_qs(void) void rcu_check_callbacks(int user) { RCU_TRACE(check_cpu_stalls()); - if (user || rcu_is_cpu_rrupt_from_idle()) + if (user) rcu_sched_qs(); else if (!in_softirq()) rcu_bh_qs(); @@ -357,6 +257,11 @@ static void __call_rcu(struct rcu_head *head, rcp->curtail = &head->next; RCU_TRACE(rcp->qlen++); local_irq_restore(flags); + + if (unlikely(is_idle_task(current))) { + /* force scheduling for rcu_sched_qs() */ + resched_cpu(0); + } } /* @@ -383,6 +288,8 @@ EXPORT_SYMBOL_GPL(call_rcu_bh); void __init rcu_init(void) { open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); + RCU_TRACE(reset_cpu_stall_ticks(&rcu_sched_ctrlblk)); + RCU_TRACE(reset_cpu_stall_ticks(&rcu_bh_ctrlblk)); rcu_early_boot_tests(); } diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h index 858c5656912..f94e209a10d 100644 --- a/kernel/rcu/tiny_plugin.h +++ b/kernel/rcu/tiny_plugin.h @@ -145,17 +145,16 @@ static void check_cpu_stall(struct rcu_ctrlblk *rcp) rcp->ticks_this_gp++; j = jiffies; js = ACCESS_ONCE(rcp->jiffies_stall); - if (*rcp->curtail && ULONG_CMP_GE(j, js)) { + if (rcp->rcucblist && ULONG_CMP_GE(j, js)) { pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n", - rcp->name, rcp->ticks_this_gp, rcu_dynticks_nesting, + rcp->name, rcp->ticks_this_gp, DYNTICK_TASK_EXIT_IDLE, jiffies - rcp->gp_start, rcp->qlen); dump_stack(); - } - if (*rcp->curtail && ULONG_CMP_GE(j, js)) ACCESS_ONCE(rcp->jiffies_stall) = jiffies + 3 * rcu_jiffies_till_stall_check() + 3; - else if (ULONG_CMP_GE(j, js)) + } else if (ULONG_CMP_GE(j, js)) { ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check(); + } } static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 7680fc27503..48d640ca1a0 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -156,6 +156,10 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) static void invoke_rcu_core(void); static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); +/* rcuc/rcub kthread realtime priority */ +static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO; +module_param(kthread_prio, int, 0644); + /* * Track the rcutorture test sequence number and the update version * number within a given test. The rcutorture_testseq is incremented @@ -215,6 +219,9 @@ static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { #endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ }; +DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr); +EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr); + /* * Let the RCU core know that this CPU has gone through the scheduler, * which is a quiescent state. This is called when the need for a @@ -284,6 +291,22 @@ void rcu_note_context_switch(void) } EXPORT_SYMBOL_GPL(rcu_note_context_switch); +/* + * Register a quiesecent state for all RCU flavors. If there is an + * emergency, invoke rcu_momentary_dyntick_idle() to do a heavy-weight + * dyntick-idle quiescent state visible to other CPUs (but only for those + * RCU flavors in desparate need of a quiescent state, which will normally + * be none of them). Either way, do a lightweight quiescent state for + * all RCU flavors. + */ +void rcu_all_qs(void) +{ + if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) + rcu_momentary_dyntick_idle(); + this_cpu_inc(rcu_qs_ctr); +} +EXPORT_SYMBOL_GPL(rcu_all_qs); + static long blimit = 10; /* Maximum callbacks per rcu_do_batch. */ static long qhimark = 10000; /* If this many pending, ignore blimit. */ static long qlowmark = 100; /* Once only this many pending, use blimit. */ @@ -315,18 +338,54 @@ static void force_quiescent_state(struct rcu_state *rsp); static int rcu_pending(void); /* - * Return the number of RCU-sched batches processed thus far for debug & stats. + * Return the number of RCU batches started thus far for debug & stats. + */ +unsigned long rcu_batches_started(void) +{ + return rcu_state_p->gpnum; +} +EXPORT_SYMBOL_GPL(rcu_batches_started); + +/* + * Return the number of RCU-sched batches started thus far for debug & stats. + */ +unsigned long rcu_batches_started_sched(void) +{ + return rcu_sched_state.gpnum; +} +EXPORT_SYMBOL_GPL(rcu_batches_started_sched); + +/* + * Return the number of RCU BH batches started thus far for debug & stats. */ -long rcu_batches_completed_sched(void) +unsigned long rcu_batches_started_bh(void) +{ + return rcu_bh_state.gpnum; +} +EXPORT_SYMBOL_GPL(rcu_batches_started_bh); + +/* + * Return the number of RCU batches completed thus far for debug & stats. + */ +unsigned long rcu_batches_completed(void) +{ + return rcu_state_p->completed; +} +EXPORT_SYMBOL_GPL(rcu_batches_completed); + +/* + * Return the number of RCU-sched batches completed thus far for debug & stats. + */ +unsigned long rcu_batches_completed_sched(void) { return rcu_sched_state.completed; } EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); /* - * Return the number of RCU BH batches processed thus far for debug & stats. + * Return the number of RCU BH batches completed thus far for debug & stats. */ -long rcu_batches_completed_bh(void) +unsigned long rcu_batches_completed_bh(void) { return rcu_bh_state.completed; } @@ -759,39 +818,71 @@ void rcu_irq_enter(void) /** * rcu_nmi_enter - inform RCU of entry to NMI context * - * If the CPU was idle with dynamic ticks active, and there is no - * irq handler running, this updates rdtp->dynticks_nmi to let the - * RCU grace-period handling know that the CPU is active. + * If the CPU was idle from RCU's viewpoint, update rdtp->dynticks and + * rdtp->dynticks_nmi_nesting to let the RCU grace-period handling know + * that the CPU is active. This implementation permits nested NMIs, as + * long as the nesting level does not overflow an int. (You will probably + * run out of stack space first.) */ void rcu_nmi_enter(void) { struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + int incby = 2; - if (rdtp->dynticks_nmi_nesting == 0 && - (atomic_read(&rdtp->dynticks) & 0x1)) - return; - rdtp->dynticks_nmi_nesting++; - smp_mb__before_atomic(); /* Force delay from prior write. */ - atomic_inc(&rdtp->dynticks); - /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */ - smp_mb__after_atomic(); /* See above. */ - WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); + /* Complain about underflow. */ + WARN_ON_ONCE(rdtp->dynticks_nmi_nesting < 0); + + /* + * If idle from RCU viewpoint, atomically increment ->dynticks + * to mark non-idle and increment ->dynticks_nmi_nesting by one. + * Otherwise, increment ->dynticks_nmi_nesting by two. This means + * if ->dynticks_nmi_nesting is equal to one, we are guaranteed + * to be in the outermost NMI handler that interrupted an RCU-idle + * period (observation due to Andy Lutomirski). + */ + if (!(atomic_read(&rdtp->dynticks) & 0x1)) { + smp_mb__before_atomic(); /* Force delay from prior write. */ + atomic_inc(&rdtp->dynticks); + /* atomic_inc() before later RCU read-side crit sects */ + smp_mb__after_atomic(); /* See above. */ + WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); + incby = 1; + } + rdtp->dynticks_nmi_nesting += incby; + barrier(); } /** * rcu_nmi_exit - inform RCU of exit from NMI context * - * If the CPU was idle with dynamic ticks active, and there is no - * irq handler running, this updates rdtp->dynticks_nmi to let the - * RCU grace-period handling know that the CPU is no longer active. + * If we are returning from the outermost NMI handler that interrupted an + * RCU-idle period, update rdtp->dynticks and rdtp->dynticks_nmi_nesting + * to let the RCU grace-period handling know that the CPU is back to + * being RCU-idle. */ void rcu_nmi_exit(void) { struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - if (rdtp->dynticks_nmi_nesting == 0 || - --rdtp->dynticks_nmi_nesting != 0) + /* + * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks. + * (We are exiting an NMI handler, so RCU better be paying attention + * to us!) + */ + WARN_ON_ONCE(rdtp->dynticks_nmi_nesting <= 0); + WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); + + /* + * If the nesting level is not 1, the CPU wasn't RCU-idle, so + * leave it in non-RCU-idle state. + */ + if (rdtp->dynticks_nmi_nesting != 1) { + rdtp->dynticks_nmi_nesting -= 2; return; + } + + /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */ + rdtp->dynticks_nmi_nesting = 0; /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */ smp_mb__before_atomic(); /* See above. */ atomic_inc(&rdtp->dynticks); @@ -898,17 +989,14 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp, trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); return 1; } else { + if (ULONG_CMP_LT(ACCESS_ONCE(rdp->gpnum) + ULONG_MAX / 4, + rdp->mynode->gpnum)) + ACCESS_ONCE(rdp->gpwrap) = true; return 0; } } /* - * This function really isn't for public consumption, but RCU is special in - * that context switches can allow the state machine to make progress. - */ -extern void resched_cpu(int cpu); - -/* * Return true if the specified CPU has passed through a quiescent * state by virtue of being in or having passed through an dynticks * idle state since the last call to dyntick_save_progress_counter() @@ -1011,6 +1099,22 @@ static void record_gp_stall_check_time(struct rcu_state *rsp) j1 = rcu_jiffies_till_stall_check(); ACCESS_ONCE(rsp->jiffies_stall) = j + j1; rsp->jiffies_resched = j + j1 / 2; + rsp->n_force_qs_gpstart = ACCESS_ONCE(rsp->n_force_qs); +} + +/* + * Complain about starvation of grace-period kthread. + */ +static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) +{ + unsigned long gpa; + unsigned long j; + + j = jiffies; + gpa = ACCESS_ONCE(rsp->gp_activity); + if (j - gpa > 2 * HZ) + pr_err("%s kthread starved for %ld jiffies!\n", + rsp->name, j - gpa); } /* @@ -1033,11 +1137,13 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp) } } -static void print_other_cpu_stall(struct rcu_state *rsp) +static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) { int cpu; long delta; unsigned long flags; + unsigned long gpa; + unsigned long j; int ndetected = 0; struct rcu_node *rnp = rcu_get_root(rsp); long totqlen = 0; @@ -1075,30 +1181,34 @@ static void print_other_cpu_stall(struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp->lock, flags); } - /* - * Now rat on any tasks that got kicked up to the root rcu_node - * due to CPU offlining. - */ - rnp = rcu_get_root(rsp); - raw_spin_lock_irqsave(&rnp->lock, flags); - ndetected += rcu_print_task_stall(rnp); - raw_spin_unlock_irqrestore(&rnp->lock, flags); - print_cpu_stall_info_end(); for_each_possible_cpu(cpu) totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen; pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n", smp_processor_id(), (long)(jiffies - rsp->gp_start), (long)rsp->gpnum, (long)rsp->completed, totqlen); - if (ndetected == 0) - pr_err("INFO: Stall ended before state dump start\n"); - else + if (ndetected) { rcu_dump_cpu_stacks(rsp); + } else { + if (ACCESS_ONCE(rsp->gpnum) != gpnum || + ACCESS_ONCE(rsp->completed) == gpnum) { + pr_err("INFO: Stall ended before state dump start\n"); + } else { + j = jiffies; + gpa = ACCESS_ONCE(rsp->gp_activity); + pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld\n", + rsp->name, j - gpa, j, gpa, + jiffies_till_next_fqs); + /* In this case, the current CPU might be at fault. */ + sched_show_task(current); + } + } /* Complain about tasks blocking the grace period. */ - rcu_print_detail_task_stall(rsp); + rcu_check_gp_kthread_starvation(rsp); + force_quiescent_state(rsp); /* Kick them all. */ } @@ -1123,6 +1233,9 @@ static void print_cpu_stall(struct rcu_state *rsp) pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n", jiffies - rsp->gp_start, (long)rsp->gpnum, (long)rsp->completed, totqlen); + + rcu_check_gp_kthread_starvation(rsp); + rcu_dump_cpu_stacks(rsp); raw_spin_lock_irqsave(&rnp->lock, flags); @@ -1193,7 +1306,7 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) { /* They had a few time units to dump stack, so complain. */ - print_other_cpu_stall(rsp); + print_other_cpu_stall(rsp, gpnum); } } @@ -1530,7 +1643,8 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, bool ret; /* Handle the ends of any preceding grace periods first. */ - if (rdp->completed == rnp->completed) { + if (rdp->completed == rnp->completed && + !unlikely(ACCESS_ONCE(rdp->gpwrap))) { /* No grace period end, so just accelerate recent callbacks. */ ret = rcu_accelerate_cbs(rsp, rnp, rdp); @@ -1545,7 +1659,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend")); } - if (rdp->gpnum != rnp->gpnum) { + if (rdp->gpnum != rnp->gpnum || unlikely(ACCESS_ONCE(rdp->gpwrap))) { /* * If the current grace period is waiting for this CPU, * set up to detect a quiescent state, otherwise don't @@ -1554,8 +1668,10 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, rdp->gpnum = rnp->gpnum; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart")); rdp->passed_quiesce = 0; + rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask); zero_cpu_stall_ticks(rdp); + ACCESS_ONCE(rdp->gpwrap) = false; } return ret; } @@ -1569,7 +1685,8 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) local_irq_save(flags); rnp = rdp->mynode; if ((rdp->gpnum == ACCESS_ONCE(rnp->gpnum) && - rdp->completed == ACCESS_ONCE(rnp->completed)) || /* w/out lock. */ + rdp->completed == ACCESS_ONCE(rnp->completed) && + !unlikely(ACCESS_ONCE(rdp->gpwrap))) || /* w/out lock. */ !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */ local_irq_restore(flags); return; @@ -1589,6 +1706,7 @@ static int rcu_gp_init(struct rcu_state *rsp) struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); + ACCESS_ONCE(rsp->gp_activity) = jiffies; rcu_bind_gp_kthread(); raw_spin_lock_irq(&rnp->lock); smp_mb__after_unlock_lock(); @@ -1649,6 +1767,7 @@ static int rcu_gp_init(struct rcu_state *rsp) rnp->grphi, rnp->qsmask); raw_spin_unlock_irq(&rnp->lock); cond_resched_rcu_qs(); + ACCESS_ONCE(rsp->gp_activity) = jiffies; } mutex_unlock(&rsp->onoff_mutex); @@ -1665,6 +1784,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) unsigned long maxj; struct rcu_node *rnp = rcu_get_root(rsp); + ACCESS_ONCE(rsp->gp_activity) = jiffies; rsp->n_force_qs++; if (fqs_state == RCU_SAVE_DYNTICK) { /* Collect dyntick-idle snapshots. */ @@ -1703,6 +1823,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); + ACCESS_ONCE(rsp->gp_activity) = jiffies; raw_spin_lock_irq(&rnp->lock); smp_mb__after_unlock_lock(); gp_duration = jiffies - rsp->gp_start; @@ -1739,6 +1860,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) nocb += rcu_future_gp_cleanup(rsp, rnp); raw_spin_unlock_irq(&rnp->lock); cond_resched_rcu_qs(); + ACCESS_ONCE(rsp->gp_activity) = jiffies; } rnp = rcu_get_root(rsp); raw_spin_lock_irq(&rnp->lock); @@ -1788,6 +1910,7 @@ static int __noreturn rcu_gp_kthread(void *arg) if (rcu_gp_init(rsp)) break; cond_resched_rcu_qs(); + ACCESS_ONCE(rsp->gp_activity) = jiffies; WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), @@ -1831,9 +1954,11 @@ static int __noreturn rcu_gp_kthread(void *arg) ACCESS_ONCE(rsp->gpnum), TPS("fqsend")); cond_resched_rcu_qs(); + ACCESS_ONCE(rsp->gp_activity) = jiffies; } else { /* Deal with stray signal. */ cond_resched_rcu_qs(); + ACCESS_ONCE(rsp->gp_activity) = jiffies; WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), @@ -2010,8 +2135,10 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum || - rnp->completed == rnp->gpnum) { + if ((rdp->passed_quiesce == 0 && + rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) || + rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum || + rdp->gpwrap) { /* * The grace period in which this quiescent state was @@ -2020,6 +2147,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) * within the current grace period. */ rdp->passed_quiesce = 0; /* need qs for new gp. */ + rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); raw_spin_unlock_irqrestore(&rnp->lock, flags); return; } @@ -2064,7 +2192,8 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) * Was there a quiescent state since the beginning of the grace * period? If no, then exit and wait for the next call. */ - if (!rdp->passed_quiesce) + if (!rdp->passed_quiesce && + rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) return; /* @@ -2195,6 +2324,46 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) } /* + * All CPUs for the specified rcu_node structure have gone offline, + * and all tasks that were preempted within an RCU read-side critical + * section while running on one of those CPUs have since exited their RCU + * read-side critical section. Some other CPU is reporting this fact with + * the specified rcu_node structure's ->lock held and interrupts disabled. + * This function therefore goes up the tree of rcu_node structures, + * clearing the corresponding bits in the ->qsmaskinit fields. Note that + * the leaf rcu_node structure's ->qsmaskinit field has already been + * updated + * + * This function does check that the specified rcu_node structure has + * all CPUs offline and no blocked tasks, so it is OK to invoke it + * prematurely. That said, invoking it after the fact will cost you + * a needless lock acquisition. So once it has done its work, don't + * invoke it again. + */ +static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) +{ + long mask; + struct rcu_node *rnp = rnp_leaf; + + if (rnp->qsmaskinit || rcu_preempt_has_tasks(rnp)) + return; + for (;;) { + mask = rnp->grpmask; + rnp = rnp->parent; + if (!rnp) + break; + raw_spin_lock(&rnp->lock); /* irqs already disabled. */ + smp_mb__after_unlock_lock(); /* GP memory ordering. */ + rnp->qsmaskinit &= ~mask; + if (rnp->qsmaskinit) { + raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + return; + } + raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + } +} + +/* * The CPU has been completely removed, and some other CPU is reporting * this fact from process context. Do the remainder of the cleanup, * including orphaning the outgoing CPU's RCU callbacks, and also @@ -2204,8 +2373,6 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) { unsigned long flags; - unsigned long mask; - int need_report = 0; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ @@ -2219,40 +2386,15 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) /* Orphan the dead CPU's callbacks, and adopt them if appropriate. */ rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp); rcu_adopt_orphan_cbs(rsp, flags); + raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags); - /* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */ - mask = rdp->grpmask; /* rnp->grplo is constant. */ - do { - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ - smp_mb__after_unlock_lock(); - rnp->qsmaskinit &= ~mask; - if (rnp->qsmaskinit != 0) { - if (rnp != rdp->mynode) - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - break; - } - if (rnp == rdp->mynode) - need_report = rcu_preempt_offline_tasks(rsp, rnp, rdp); - else - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - mask = rnp->grpmask; - rnp = rnp->parent; - } while (rnp != NULL); - - /* - * We still hold the leaf rcu_node structure lock here, and - * irqs are still disabled. The reason for this subterfuge is - * because invoking rcu_report_unblock_qs_rnp() with ->orphan_lock - * held leads to deadlock. - */ - raw_spin_unlock(&rsp->orphan_lock); /* irqs remain disabled. */ - rnp = rdp->mynode; - if (need_report & RCU_OFL_TASKS_NORM_GP) - rcu_report_unblock_qs_rnp(rnp, flags); - else - raw_spin_unlock_irqrestore(&rnp->lock, flags); - if (need_report & RCU_OFL_TASKS_EXP_GP) - rcu_report_exp_rnp(rsp, rnp, true); + /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); /* Enforce GP memory-order guarantee. */ + rnp->qsmaskinit &= ~rdp->grpmask; + if (rnp->qsmaskinit == 0 && !rcu_preempt_has_tasks(rnp)) + rcu_cleanup_dead_rnp(rnp); + rcu_report_qs_rnp(rdp->grpmask, rsp, rnp, flags); /* Rlses rnp->lock. */ WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL, "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n", cpu, rdp->qlen, rdp->nxtlist); @@ -2268,6 +2410,10 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) { } +static void __maybe_unused rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) +{ +} + static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) { } @@ -2464,12 +2610,6 @@ static void force_qs_rnp(struct rcu_state *rsp, } raw_spin_unlock_irqrestore(&rnp->lock, flags); } - rnp = rcu_get_root(rsp); - if (rnp->qsmask == 0) { - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); - rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */ - } } /* @@ -2569,7 +2709,7 @@ static void rcu_process_callbacks(struct softirq_action *unused) * Schedule RCU callback invocation. If the specified type of RCU * does not support RCU priority boosting, just do a direct call, * otherwise wake up the per-CPU kernel kthread. Note that because we - * are running on the current CPU with interrupts disabled, the + * are running on the current CPU with softirqs disabled, the * rcu_cpu_kthread_task cannot disappear out from under us. */ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) @@ -3109,9 +3249,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) /* Is the RCU core waiting for a quiescent state from this CPU? */ if (rcu_scheduler_fully_active && - rdp->qs_pending && !rdp->passed_quiesce) { + rdp->qs_pending && !rdp->passed_quiesce && + rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) { rdp->n_rp_qs_pending++; - } else if (rdp->qs_pending && rdp->passed_quiesce) { + } else if (rdp->qs_pending && + (rdp->passed_quiesce || + rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) { rdp->n_rp_report_qs++; return 1; } @@ -3135,7 +3278,8 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) } /* Has a new RCU grace period started? */ - if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum) { /* outside lock */ + if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum || + unlikely(ACCESS_ONCE(rdp->gpwrap))) { /* outside lock */ rdp->n_rp_gp_started++; return 1; } @@ -3318,6 +3462,7 @@ static void _rcu_barrier(struct rcu_state *rsp) } else { _rcu_barrier_trace(rsp, "OnlineNoCB", cpu, rsp->n_barrier_done); + smp_mb__before_atomic(); atomic_inc(&rsp->barrier_cpu_count); __call_rcu(&rdp->barrier_head, rcu_barrier_callback, rsp, cpu, 0); @@ -3385,9 +3530,6 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) /* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave(&rnp->lock, flags); rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo); - init_callback_list(rdp); - rdp->qlen_lazy = 0; - ACCESS_ONCE(rdp->qlen) = 0; rdp->dynticks = &per_cpu(rcu_dynticks, cpu); WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); @@ -3444,6 +3586,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->gpnum = rnp->completed; rdp->completed = rnp->completed; rdp->passed_quiesce = 0; + rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); rdp->qs_pending = 0; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); } @@ -3535,17 +3678,35 @@ static int rcu_pm_notify(struct notifier_block *self, static int __init rcu_spawn_gp_kthread(void) { unsigned long flags; + int kthread_prio_in = kthread_prio; struct rcu_node *rnp; struct rcu_state *rsp; + struct sched_param sp; struct task_struct *t; + /* Force priority into range. */ + if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1) + kthread_prio = 1; + else if (kthread_prio < 0) + kthread_prio = 0; + else if (kthread_prio > 99) + kthread_prio = 99; + if (kthread_prio != kthread_prio_in) + pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n", + kthread_prio, kthread_prio_in); + rcu_scheduler_fully_active = 1; for_each_rcu_flavor(rsp) { - t = kthread_run(rcu_gp_kthread, rsp, "%s", rsp->name); + t = kthread_create(rcu_gp_kthread, rsp, "%s", rsp->name); BUG_ON(IS_ERR(t)); rnp = rcu_get_root(rsp); raw_spin_lock_irqsave(&rnp->lock, flags); rsp->gp_kthread = t; + if (kthread_prio) { + sp.sched_priority = kthread_prio; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + } + wake_up_process(t); raw_spin_unlock_irqrestore(&rnp->lock, flags); } rcu_spawn_nocb_kthreads(); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 8e7b1843896..119de399eb2 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -27,7 +27,6 @@ #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/seqlock.h> -#include <linux/irq_work.h> /* * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and @@ -172,11 +171,6 @@ struct rcu_node { /* queued on this rcu_node structure that */ /* are blocking the current grace period, */ /* there can be no such task. */ - struct completion boost_completion; - /* Used to ensure that the rt_mutex used */ - /* to carry out the boosting is fully */ - /* released with no future boostee accesses */ - /* before that rt_mutex is re-initialized. */ struct rt_mutex boost_mtx; /* Used only for the priority-boosting */ /* side effect, not as a lock. */ @@ -257,9 +251,12 @@ struct rcu_data { /* in order to detect GP end. */ unsigned long gpnum; /* Highest gp number that this CPU */ /* is aware of having started. */ + unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */ + /* for rcu_all_qs() invocations. */ bool passed_quiesce; /* User-mode/idle loop etc. */ bool qs_pending; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ + bool gpwrap; /* Possible gpnum/completed wrap. */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ unsigned long grpmask; /* Mask to apply to leaf qsmask. */ #ifdef CONFIG_RCU_CPU_STALL_INFO @@ -340,14 +337,10 @@ struct rcu_data { #ifdef CONFIG_RCU_NOCB_CPU struct rcu_head *nocb_head; /* CBs waiting for kthread. */ struct rcu_head **nocb_tail; - atomic_long_t nocb_q_count; /* # CBs waiting for kthread */ - atomic_long_t nocb_q_count_lazy; /* (approximate). */ + atomic_long_t nocb_q_count; /* # CBs waiting for nocb */ + atomic_long_t nocb_q_count_lazy; /* invocation (all stages). */ struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */ struct rcu_head **nocb_follower_tail; - atomic_long_t nocb_follower_count; /* # CBs ready to invoke. */ - atomic_long_t nocb_follower_count_lazy; /* (approximate). */ - int nocb_p_count; /* # CBs being invoked by kthread */ - int nocb_p_count_lazy; /* (approximate). */ wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */ struct task_struct *nocb_kthread; int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ @@ -356,8 +349,6 @@ struct rcu_data { struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp; /* CBs waiting for GP. */ struct rcu_head **nocb_gp_tail; - long nocb_gp_count; - long nocb_gp_count_lazy; bool nocb_leader_sleep; /* Is the nocb leader thread asleep? */ struct rcu_data *nocb_next_follower; /* Next follower in wakeup chain. */ @@ -488,10 +479,14 @@ struct rcu_state { /* due to no GP active. */ unsigned long gp_start; /* Time at which GP started, */ /* but in jiffies. */ + unsigned long gp_activity; /* Time of last GP kthread */ + /* activity in jiffies. */ unsigned long jiffies_stall; /* Time at which to check */ /* for CPU stalls. */ unsigned long jiffies_resched; /* Time at which to resched */ /* a reluctant CPU. */ + unsigned long n_force_qs_gpstart; /* Snapshot of n_force_qs at */ + /* GP start. */ unsigned long gp_max; /* Maximum GP duration in */ /* jiffies. */ const char *name; /* Name of structure. */ @@ -514,13 +509,6 @@ extern struct list_head rcu_struct_flavors; #define for_each_rcu_flavor(rsp) \ list_for_each_entry((rsp), &rcu_struct_flavors, flavors) -/* Return values for rcu_preempt_offline_tasks(). */ - -#define RCU_OFL_TASKS_NORM_GP 0x1 /* Tasks blocking normal */ - /* GP were moved to root. */ -#define RCU_OFL_TASKS_EXP_GP 0x2 /* Tasks blocking expedited */ - /* GP were moved to root. */ - /* * RCU implementation internal declarations: */ @@ -546,27 +534,16 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work); /* Forward declarations for rcutree_plugin.h */ static void rcu_bootup_announce(void); -long rcu_batches_completed(void); static void rcu_preempt_note_context_switch(void); static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU -static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, - unsigned long flags); +static bool rcu_preempt_has_tasks(struct rcu_node *rnp); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ static void rcu_print_detail_task_stall(struct rcu_state *rsp); static int rcu_print_task_stall(struct rcu_node *rnp); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); -#ifdef CONFIG_HOTPLUG_CPU -static int rcu_preempt_offline_tasks(struct rcu_state *rsp, - struct rcu_node *rnp, - struct rcu_data *rdp); -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ static void rcu_preempt_check_callbacks(void); void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); -#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PREEMPT_RCU) -static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, - bool wake); -#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PREEMPT_RCU) */ static void __init __rcu_init_preempt(void); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); @@ -622,24 +599,15 @@ static void rcu_dynticks_task_exit(void); #endif /* #ifndef RCU_TREE_NONCORE */ #ifdef CONFIG_RCU_TRACE -#ifdef CONFIG_RCU_NOCB_CPU -/* Sum up queue lengths for tracing. */ +/* Read out queue lengths for tracing. */ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) { - *ql = atomic_long_read(&rdp->nocb_q_count) + - rdp->nocb_p_count + - atomic_long_read(&rdp->nocb_follower_count) + - rdp->nocb_p_count + rdp->nocb_gp_count; - *qll = atomic_long_read(&rdp->nocb_q_count_lazy) + - rdp->nocb_p_count_lazy + - atomic_long_read(&rdp->nocb_follower_count_lazy) + - rdp->nocb_p_count_lazy + rdp->nocb_gp_count_lazy; -} +#ifdef CONFIG_RCU_NOCB_CPU + *ql = atomic_long_read(&rdp->nocb_q_count); + *qll = atomic_long_read(&rdp->nocb_q_count_lazy); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ -static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) -{ *ql = 0; *qll = 0; -} #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ +} #endif /* #ifdef CONFIG_RCU_TRACE */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 3ec85cb5d54..2e850a51bb8 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -34,10 +34,6 @@ #include "../locking/rtmutex_common.h" -/* rcuc/rcub kthread realtime priority */ -static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO; -module_param(kthread_prio, int, 0644); - /* * Control variables for per-CPU and per-rcu_node kthreads. These * handle all flavors of RCU. @@ -103,6 +99,8 @@ RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu); static struct rcu_state *rcu_state_p = &rcu_preempt_state; static int rcu_preempted_readers_exp(struct rcu_node *rnp); +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, + bool wake); /* * Tell them what RCU they are running. @@ -114,25 +112,6 @@ static void __init rcu_bootup_announce(void) } /* - * Return the number of RCU-preempt batches processed thus far - * for debug and statistics. - */ -static long rcu_batches_completed_preempt(void) -{ - return rcu_preempt_state.completed; -} -EXPORT_SYMBOL_GPL(rcu_batches_completed_preempt); - -/* - * Return the number of RCU batches processed thus far for debug & stats. - */ -long rcu_batches_completed(void) -{ - return rcu_batches_completed_preempt(); -} -EXPORT_SYMBOL_GPL(rcu_batches_completed); - -/* * Record a preemptible-RCU quiescent state for the specified CPU. Note * that this just means that the task currently running on the CPU is * not in a quiescent state. There might be any number of tasks blocked @@ -307,15 +286,25 @@ static struct list_head *rcu_next_node_entry(struct task_struct *t, } /* + * Return true if the specified rcu_node structure has tasks that were + * preempted within an RCU read-side critical section. + */ +static bool rcu_preempt_has_tasks(struct rcu_node *rnp) +{ + return !list_empty(&rnp->blkd_tasks); +} + +/* * Handle special cases during rcu_read_unlock(), such as needing to * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ void rcu_read_unlock_special(struct task_struct *t) { - int empty; - int empty_exp; - int empty_exp_now; + bool empty; + bool empty_exp; + bool empty_norm; + bool empty_exp_now; unsigned long flags; struct list_head *np; #ifdef CONFIG_RCU_BOOST @@ -367,7 +356,8 @@ void rcu_read_unlock_special(struct task_struct *t) break; raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ } - empty = !rcu_preempt_blocked_readers_cgp(rnp); + empty = !rcu_preempt_has_tasks(rnp); + empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); empty_exp = !rcu_preempted_readers_exp(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ np = rcu_next_node_entry(t, rnp); @@ -387,13 +377,21 @@ void rcu_read_unlock_special(struct task_struct *t) #endif /* #ifdef CONFIG_RCU_BOOST */ /* + * If this was the last task on the list, go see if we + * need to propagate ->qsmaskinit bit clearing up the + * rcu_node tree. + */ + if (!empty && !rcu_preempt_has_tasks(rnp)) + rcu_cleanup_dead_rnp(rnp); + + /* * If this was the last task on the current list, and if * we aren't waiting on any CPUs, report the quiescent state. * Note that rcu_report_unblock_qs_rnp() releases rnp->lock, * so we must take a snapshot of the expedited state. */ empty_exp_now = !rcu_preempted_readers_exp(rnp); - if (!empty && !rcu_preempt_blocked_readers_cgp(rnp)) { + if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) { trace_rcu_quiescent_state_report(TPS("preempt_rcu"), rnp->gpnum, 0, rnp->qsmask, @@ -408,10 +406,8 @@ void rcu_read_unlock_special(struct task_struct *t) #ifdef CONFIG_RCU_BOOST /* Unboost if we were boosted. */ - if (drop_boost_mutex) { + if (drop_boost_mutex) rt_mutex_unlock(&rnp->boost_mtx); - complete(&rnp->boost_completion); - } #endif /* #ifdef CONFIG_RCU_BOOST */ /* @@ -519,99 +515,13 @@ static int rcu_print_task_stall(struct rcu_node *rnp) static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) { WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); - if (!list_empty(&rnp->blkd_tasks)) + if (rcu_preempt_has_tasks(rnp)) rnp->gp_tasks = rnp->blkd_tasks.next; WARN_ON_ONCE(rnp->qsmask); } #ifdef CONFIG_HOTPLUG_CPU -/* - * Handle tasklist migration for case in which all CPUs covered by the - * specified rcu_node have gone offline. Move them up to the root - * rcu_node. The reason for not just moving them to the immediate - * parent is to remove the need for rcu_read_unlock_special() to - * make more than two attempts to acquire the target rcu_node's lock. - * Returns true if there were tasks blocking the current RCU grace - * period. - * - * Returns 1 if there was previously a task blocking the current grace - * period on the specified rcu_node structure. - * - * The caller must hold rnp->lock with irqs disabled. - */ -static int rcu_preempt_offline_tasks(struct rcu_state *rsp, - struct rcu_node *rnp, - struct rcu_data *rdp) -{ - struct list_head *lp; - struct list_head *lp_root; - int retval = 0; - struct rcu_node *rnp_root = rcu_get_root(rsp); - struct task_struct *t; - - if (rnp == rnp_root) { - WARN_ONCE(1, "Last CPU thought to be offlined?"); - return 0; /* Shouldn't happen: at least one CPU online. */ - } - - /* If we are on an internal node, complain bitterly. */ - WARN_ON_ONCE(rnp != rdp->mynode); - - /* - * Move tasks up to root rcu_node. Don't try to get fancy for - * this corner-case operation -- just put this node's tasks - * at the head of the root node's list, and update the root node's - * ->gp_tasks and ->exp_tasks pointers to those of this node's, - * if non-NULL. This might result in waiting for more tasks than - * absolutely necessary, but this is a good performance/complexity - * tradeoff. - */ - if (rcu_preempt_blocked_readers_cgp(rnp) && rnp->qsmask == 0) - retval |= RCU_OFL_TASKS_NORM_GP; - if (rcu_preempted_readers_exp(rnp)) - retval |= RCU_OFL_TASKS_EXP_GP; - lp = &rnp->blkd_tasks; - lp_root = &rnp_root->blkd_tasks; - while (!list_empty(lp)) { - t = list_entry(lp->next, typeof(*t), rcu_node_entry); - raw_spin_lock(&rnp_root->lock); /* irqs already disabled */ - smp_mb__after_unlock_lock(); - list_del(&t->rcu_node_entry); - t->rcu_blocked_node = rnp_root; - list_add(&t->rcu_node_entry, lp_root); - if (&t->rcu_node_entry == rnp->gp_tasks) - rnp_root->gp_tasks = rnp->gp_tasks; - if (&t->rcu_node_entry == rnp->exp_tasks) - rnp_root->exp_tasks = rnp->exp_tasks; -#ifdef CONFIG_RCU_BOOST - if (&t->rcu_node_entry == rnp->boost_tasks) - rnp_root->boost_tasks = rnp->boost_tasks; -#endif /* #ifdef CONFIG_RCU_BOOST */ - raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */ - } - - rnp->gp_tasks = NULL; - rnp->exp_tasks = NULL; -#ifdef CONFIG_RCU_BOOST - rnp->boost_tasks = NULL; - /* - * In case root is being boosted and leaf was not. Make sure - * that we boost the tasks blocking the current grace period - * in this case. - */ - raw_spin_lock(&rnp_root->lock); /* irqs already disabled */ - smp_mb__after_unlock_lock(); - if (rnp_root->boost_tasks != NULL && - rnp_root->boost_tasks != rnp_root->gp_tasks && - rnp_root->boost_tasks != rnp_root->exp_tasks) - rnp_root->boost_tasks = rnp_root->gp_tasks; - raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */ -#endif /* #ifdef CONFIG_RCU_BOOST */ - - return retval; -} - #endif /* #ifdef CONFIG_HOTPLUG_CPU */ /* @@ -771,7 +681,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - if (list_empty(&rnp->blkd_tasks)) { + if (!rcu_preempt_has_tasks(rnp)) { raw_spin_unlock_irqrestore(&rnp->lock, flags); } else { rnp->exp_tasks = rnp->blkd_tasks.next; @@ -933,15 +843,6 @@ static void __init rcu_bootup_announce(void) } /* - * Return the number of RCU batches processed thus far for debug & stats. - */ -long rcu_batches_completed(void) -{ - return rcu_batches_completed_sched(); -} -EXPORT_SYMBOL_GPL(rcu_batches_completed); - -/* * Because preemptible RCU does not exist, we never have to check for * CPUs being in quiescent states. */ @@ -960,11 +861,12 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) #ifdef CONFIG_HOTPLUG_CPU -/* Because preemptible RCU does not exist, no quieting of tasks. */ -static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) - __releases(rnp->lock) +/* + * Because there is no preemptible RCU, there can be no readers blocked. + */ +static bool rcu_preempt_has_tasks(struct rcu_node *rnp) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + return false; } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ @@ -996,23 +898,6 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) WARN_ON_ONCE(rnp->qsmask); } -#ifdef CONFIG_HOTPLUG_CPU - -/* - * Because preemptible RCU does not exist, it never needs to migrate - * tasks that were blocked within RCU read-side critical sections, and - * such non-existent tasks cannot possibly have been blocking the current - * grace period. - */ -static int rcu_preempt_offline_tasks(struct rcu_state *rsp, - struct rcu_node *rnp, - struct rcu_data *rdp) -{ - return 0; -} - -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - /* * Because preemptible RCU does not exist, it never has any callbacks * to check. @@ -1031,20 +916,6 @@ void synchronize_rcu_expedited(void) } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); -#ifdef CONFIG_HOTPLUG_CPU - -/* - * Because preemptible RCU does not exist, there is never any need to - * report on tasks preempted in RCU read-side critical sections during - * expedited RCU grace periods. - */ -static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, - bool wake) -{ -} - -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - /* * Because preemptible RCU does not exist, rcu_barrier() is just * another name for rcu_barrier_sched(). @@ -1080,7 +951,7 @@ void exit_rcu(void) static void rcu_initiate_boost_trace(struct rcu_node *rnp) { - if (list_empty(&rnp->blkd_tasks)) + if (!rcu_preempt_has_tasks(rnp)) rnp->n_balk_blkd_tasks++; else if (rnp->exp_tasks == NULL && rnp->gp_tasks == NULL) rnp->n_balk_exp_gp_tasks++; @@ -1127,7 +998,8 @@ static int rcu_boost(struct rcu_node *rnp) struct task_struct *t; struct list_head *tb; - if (rnp->exp_tasks == NULL && rnp->boost_tasks == NULL) + if (ACCESS_ONCE(rnp->exp_tasks) == NULL && + ACCESS_ONCE(rnp->boost_tasks) == NULL) return 0; /* Nothing left to boost. */ raw_spin_lock_irqsave(&rnp->lock, flags); @@ -1175,15 +1047,11 @@ static int rcu_boost(struct rcu_node *rnp) */ t = container_of(tb, struct task_struct, rcu_node_entry); rt_mutex_init_proxy_locked(&rnp->boost_mtx, t); - init_completion(&rnp->boost_completion); raw_spin_unlock_irqrestore(&rnp->lock, flags); /* Lock only for side effect: boosts task t's priority. */ rt_mutex_lock(&rnp->boost_mtx); rt_mutex_unlock(&rnp->boost_mtx); /* Then keep lockdep happy. */ - /* Wait for boostee to be done w/boost_mtx before reinitializing. */ - wait_for_completion(&rnp->boost_completion); - return ACCESS_ONCE(rnp->exp_tasks) != NULL || ACCESS_ONCE(rnp->boost_tasks) != NULL; } @@ -1416,12 +1284,8 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) if ((mask & 0x1) && cpu != outgoingcpu) cpumask_set_cpu(cpu, cm); - if (cpumask_weight(cm) == 0) { + if (cpumask_weight(cm) == 0) cpumask_setall(cm); - for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) - cpumask_clear_cpu(cpu, cm); - WARN_ON_ONCE(cpumask_weight(cm) == 0); - } set_cpus_allowed_ptr(t, cm); free_cpumask_var(cm); } @@ -1446,12 +1310,8 @@ static void __init rcu_spawn_boost_kthreads(void) for_each_possible_cpu(cpu) per_cpu(rcu_cpu_has_work, cpu) = 0; BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); - rnp = rcu_get_root(rcu_state_p); - (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); - if (NUM_RCU_NODES > 1) { - rcu_for_each_leaf_node(rcu_state_p, rnp) - (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); - } + rcu_for_each_leaf_node(rcu_state_p, rnp) + (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); } static void rcu_prepare_kthreads(int cpu) @@ -1605,7 +1465,8 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void) * completed since we last checked and there are * callbacks not yet ready to invoke. */ - if (rdp->completed != rnp->completed && + if ((rdp->completed != rnp->completed || + unlikely(ACCESS_ONCE(rdp->gpwrap))) && rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_NEXT_TAIL]) note_gp_changes(rsp, rdp); @@ -1898,11 +1759,12 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) ticks_value = rsp->gpnum - rdp->gpnum; } print_cpu_stall_fast_no_hz(fast_no_hz, cpu); - pr_err("\t%d: (%lu %s) idle=%03x/%llx/%d softirq=%u/%u %s\n", + pr_err("\t%d: (%lu %s) idle=%03x/%llx/%d softirq=%u/%u fqs=%ld %s\n", cpu, ticks_value, ticks_title, atomic_read(&rdtp->dynticks) & 0xfff, rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting, rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu), + ACCESS_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart, fast_no_hz); } @@ -2056,9 +1918,26 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force) static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) { struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + unsigned long ret; +#ifdef CONFIG_PROVE_RCU struct rcu_head *rhp; +#endif /* #ifdef CONFIG_PROVE_RCU */ - /* No-CBs CPUs might have callbacks on any of three lists. */ + /* + * Check count of all no-CBs callbacks awaiting invocation. + * There needs to be a barrier before this function is called, + * but associated with a prior determination that no more + * callbacks would be posted. In the worst case, the first + * barrier in _rcu_barrier() suffices (but the caller cannot + * necessarily rely on this, not a substitute for the caller + * getting the concurrency design right!). There must also be + * a barrier between the following load an posting of a callback + * (if a callback is in fact needed). This is associated with an + * atomic_inc() in the caller. + */ + ret = atomic_long_read(&rdp->nocb_q_count); + +#ifdef CONFIG_PROVE_RCU rhp = ACCESS_ONCE(rdp->nocb_head); if (!rhp) rhp = ACCESS_ONCE(rdp->nocb_gp_head); @@ -2072,8 +1951,9 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) cpu, rhp->func); WARN_ON_ONCE(1); } +#endif /* #ifdef CONFIG_PROVE_RCU */ - return !!rhp; + return !!ret; } /* @@ -2095,9 +1975,10 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, struct task_struct *t; /* Enqueue the callback on the nocb list and update counts. */ + atomic_long_add(rhcount, &rdp->nocb_q_count); + /* rcu_barrier() relies on ->nocb_q_count add before xchg. */ old_rhpp = xchg(&rdp->nocb_tail, rhtp); ACCESS_ONCE(*old_rhpp) = rhp; - atomic_long_add(rhcount, &rdp->nocb_q_count); atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy); smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */ @@ -2288,9 +2169,6 @@ wait_again: /* Move callbacks to wait-for-GP list, which is empty. */ ACCESS_ONCE(rdp->nocb_head) = NULL; rdp->nocb_gp_tail = xchg(&rdp->nocb_tail, &rdp->nocb_head); - rdp->nocb_gp_count = atomic_long_xchg(&rdp->nocb_q_count, 0); - rdp->nocb_gp_count_lazy = - atomic_long_xchg(&rdp->nocb_q_count_lazy, 0); gotcbs = true; } @@ -2338,9 +2216,6 @@ wait_again: /* Append callbacks to follower's "done" list. */ tail = xchg(&rdp->nocb_follower_tail, rdp->nocb_gp_tail); *tail = rdp->nocb_gp_head; - atomic_long_add(rdp->nocb_gp_count, &rdp->nocb_follower_count); - atomic_long_add(rdp->nocb_gp_count_lazy, - &rdp->nocb_follower_count_lazy); smp_mb__after_atomic(); /* Store *tail before wakeup. */ if (rdp != my_rdp && tail == &rdp->nocb_follower_head) { /* @@ -2415,13 +2290,11 @@ static int rcu_nocb_kthread(void *arg) trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "WokeNonEmpty"); ACCESS_ONCE(rdp->nocb_follower_head) = NULL; tail = xchg(&rdp->nocb_follower_tail, &rdp->nocb_follower_head); - c = atomic_long_xchg(&rdp->nocb_follower_count, 0); - cl = atomic_long_xchg(&rdp->nocb_follower_count_lazy, 0); - rdp->nocb_p_count += c; - rdp->nocb_p_count_lazy += cl; /* Each pass through the following loop invokes a callback. */ - trace_rcu_batch_start(rdp->rsp->name, cl, c, -1); + trace_rcu_batch_start(rdp->rsp->name, + atomic_long_read(&rdp->nocb_q_count_lazy), + atomic_long_read(&rdp->nocb_q_count), -1); c = cl = 0; while (list) { next = list->next; @@ -2443,9 +2316,9 @@ static int rcu_nocb_kthread(void *arg) list = next; } trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1); - ACCESS_ONCE(rdp->nocb_p_count) = rdp->nocb_p_count - c; - ACCESS_ONCE(rdp->nocb_p_count_lazy) = - rdp->nocb_p_count_lazy - cl; + smp_mb__before_atomic(); /* _add after CB invocation. */ + atomic_long_add(-c, &rdp->nocb_q_count); + atomic_long_add(-cl, &rdp->nocb_q_count_lazy); rdp->n_nocbs_invoked += c; } return 0; diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index 5cdc62e1bee..fbb6240509e 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -46,6 +46,8 @@ #define RCU_TREE_NONCORE #include "tree.h" +DECLARE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr); + static int r_open(struct inode *inode, struct file *file, const struct seq_operations *op) { @@ -115,11 +117,13 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) if (!rdp->beenonline) return; - seq_printf(m, "%3d%cc=%ld g=%ld pq=%d qp=%d", + seq_printf(m, "%3d%cc=%ld g=%ld pq=%d/%d qp=%d", rdp->cpu, cpu_is_offline(rdp->cpu) ? '!' : ' ', ulong2long(rdp->completed), ulong2long(rdp->gpnum), - rdp->passed_quiesce, rdp->qs_pending); + rdp->passed_quiesce, + rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu), + rdp->qs_pending); seq_printf(m, " dt=%d/%llx/%d df=%lu", atomic_read(&rdp->dynticks->dynticks), rdp->dynticks->dynticks_nesting, diff --git a/kernel/resource.c b/kernel/resource.c index 0bcebffc4e7..19f2357dfda 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -22,6 +22,7 @@ #include <linux/device.h> #include <linux/pfn.h> #include <linux/mm.h> +#include <linux/resource_ext.h> #include <asm/io.h> @@ -1529,6 +1530,30 @@ int iomem_is_exclusive(u64 addr) return err; } +struct resource_entry *resource_list_create_entry(struct resource *res, + size_t extra_size) +{ + struct resource_entry *entry; + + entry = kzalloc(sizeof(*entry) + extra_size, GFP_KERNEL); + if (entry) { + INIT_LIST_HEAD(&entry->node); + entry->res = res ? res : &entry->__res; + } + + return entry; +} +EXPORT_SYMBOL(resource_list_create_entry); + +void resource_list_free(struct list_head *head) +{ + struct resource_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, head, node) + resource_list_destroy_entry(entry); +} +EXPORT_SYMBOL(resource_list_free); + static int __init strict_iomem(char *str) { if (strstr(str, "relaxed")) diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index 607f852b4d0..7052d3fd4e7 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -268,6 +268,15 @@ bool try_wait_for_completion(struct completion *x) unsigned long flags; int ret = 1; + /* + * Since x->done will need to be locked only + * in the non-blocking case, we check x->done + * first without taking the lock so we can + * return early in the blocking case. + */ + if (!ACCESS_ONCE(x->done)) + return 0; + spin_lock_irqsave(&x->wait.lock, flags); if (!x->done) ret = 0; @@ -288,13 +297,6 @@ EXPORT_SYMBOL(try_wait_for_completion); */ bool completion_done(struct completion *x) { - unsigned long flags; - int ret = 1; - - spin_lock_irqsave(&x->wait.lock, flags); - if (!x->done) - ret = 0; - spin_unlock_irqrestore(&x->wait.lock, flags); - return ret; + return !!ACCESS_ONCE(x->done); } EXPORT_SYMBOL(completion_done); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e628cb11b56..1f37fe7f77a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -119,7 +119,9 @@ void update_rq_clock(struct rq *rq) { s64 delta; - if (rq->skip_clock_update > 0) + lockdep_assert_held(&rq->lock); + + if (rq->clock_skip_update & RQCF_ACT_SKIP) return; delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; @@ -490,6 +492,11 @@ static __init void init_hrtick(void) */ void hrtick_start(struct rq *rq, u64 delay) { + /* + * Don't schedule slices shorter than 10000ns, that just + * doesn't make sense. Rely on vruntime for fairness. + */ + delay = max_t(u64, delay, 10000LL); __hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0, HRTIMER_MODE_REL_PINNED, 0); } @@ -1046,7 +1053,7 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) * this case, we can save a useless back to back clock update. */ if (task_on_rq_queued(rq->curr) && test_tsk_need_resched(rq->curr)) - rq->skip_clock_update = 1; + rq_clock_skip_update(rq, true); } #ifdef CONFIG_SMP @@ -1082,7 +1089,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) if (p->sched_class->migrate_task_rq) p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; - perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0); + perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); } __set_task_cpu(p, new_cpu); @@ -1814,6 +1821,10 @@ void __dl_clear_params(struct task_struct *p) dl_se->dl_period = 0; dl_se->flags = 0; dl_se->dl_bw = 0; + + dl_se->dl_throttled = 0; + dl_se->dl_new = 1; + dl_se->dl_yielded = 0; } /* @@ -1832,6 +1843,9 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->se.prev_sum_exec_runtime = 0; p->se.nr_migrations = 0; p->se.vruntime = 0; +#ifdef CONFIG_SMP + p->se.avg.decay_count = 0; +#endif INIT_LIST_HEAD(&p->se.group_node); #ifdef CONFIG_SCHEDSTATS @@ -1839,7 +1853,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) #endif RB_CLEAR_NODE(&p->dl.rb_node); - hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + init_dl_task_timer(&p->dl); __dl_clear_params(p); INIT_LIST_HEAD(&p->rt.run_list); @@ -2049,6 +2063,9 @@ static inline int dl_bw_cpus(int i) * allocated bandwidth to reflect the new situation. * * This function is called while holding p's rq->lock. + * + * XXX we should delay bw change until the task's 0-lag point, see + * __setparam_dl(). */ static int dl_overflow(struct task_struct *p, int policy, const struct sched_attr *attr) @@ -2748,6 +2765,10 @@ again: * - explicit schedule() call * - return from syscall or exception to user-space * - return from interrupt-handler to user-space + * + * WARNING: all callers must re-check need_resched() afterward and reschedule + * accordingly in case an event triggered the need for rescheduling (such as + * an interrupt waking up a task) while preemption was disabled in __schedule(). */ static void __sched __schedule(void) { @@ -2756,7 +2777,6 @@ static void __sched __schedule(void) struct rq *rq; int cpu; -need_resched: preempt_disable(); cpu = smp_processor_id(); rq = cpu_rq(cpu); @@ -2776,6 +2796,8 @@ need_resched: smp_mb__before_spinlock(); raw_spin_lock_irq(&rq->lock); + rq->clock_skip_update <<= 1; /* promote REQ to ACT */ + switch_count = &prev->nivcsw; if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { if (unlikely(signal_pending_state(prev->state, prev))) { @@ -2800,13 +2822,13 @@ need_resched: switch_count = &prev->nvcsw; } - if (task_on_rq_queued(prev) || rq->skip_clock_update < 0) + if (task_on_rq_queued(prev)) update_rq_clock(rq); next = pick_next_task(rq, prev); clear_tsk_need_resched(prev); clear_preempt_need_resched(); - rq->skip_clock_update = 0; + rq->clock_skip_update = 0; if (likely(prev != next)) { rq->nr_switches++; @@ -2821,8 +2843,6 @@ need_resched: post_schedule(rq); sched_preempt_enable_no_resched(); - if (need_resched()) - goto need_resched; } static inline void sched_submit_work(struct task_struct *tsk) @@ -2842,7 +2862,9 @@ asmlinkage __visible void __sched schedule(void) struct task_struct *tsk = current; sched_submit_work(tsk); - __schedule(); + do { + __schedule(); + } while (need_resched()); } EXPORT_SYMBOL(schedule); @@ -2877,6 +2899,21 @@ void __sched schedule_preempt_disabled(void) preempt_disable(); } +static void preempt_schedule_common(void) +{ + do { + __preempt_count_add(PREEMPT_ACTIVE); + __schedule(); + __preempt_count_sub(PREEMPT_ACTIVE); + + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + barrier(); + } while (need_resched()); +} + #ifdef CONFIG_PREEMPT /* * this is the entry point to schedule() from in-kernel preemption @@ -2892,17 +2929,7 @@ asmlinkage __visible void __sched notrace preempt_schedule(void) if (likely(!preemptible())) return; - do { - __preempt_count_add(PREEMPT_ACTIVE); - __schedule(); - __preempt_count_sub(PREEMPT_ACTIVE); - - /* - * Check again in case we missed a preemption opportunity - * between schedule and now. - */ - barrier(); - } while (need_resched()); + preempt_schedule_common(); } NOKPROBE_SYMBOL(preempt_schedule); EXPORT_SYMBOL(preempt_schedule); @@ -3251,15 +3278,31 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr) { struct sched_dl_entity *dl_se = &p->dl; - init_dl_task_timer(dl_se); dl_se->dl_runtime = attr->sched_runtime; dl_se->dl_deadline = attr->sched_deadline; dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline; dl_se->flags = attr->sched_flags; dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime); - dl_se->dl_throttled = 0; - dl_se->dl_new = 1; - dl_se->dl_yielded = 0; + + /* + * Changing the parameters of a task is 'tricky' and we're not doing + * the correct thing -- also see task_dead_dl() and switched_from_dl(). + * + * What we SHOULD do is delay the bandwidth release until the 0-lag + * point. This would include retaining the task_struct until that time + * and change dl_overflow() to not immediately decrement the current + * amount. + * + * Instead we retain the current runtime/deadline and let the new + * parameters take effect after the current reservation period lapses. + * This is safe (albeit pessimistic) because the 0-lag point is always + * before the current scheduling deadline. + * + * We can still have temporary overloads because we do not delay the + * change in bandwidth until that time; so admission control is + * not on the safe side. It does however guarantee tasks will never + * consume more than promised. + */ } /* @@ -3382,6 +3425,20 @@ static bool check_same_owner(struct task_struct *p) return match; } +static bool dl_param_changed(struct task_struct *p, + const struct sched_attr *attr) +{ + struct sched_dl_entity *dl_se = &p->dl; + + if (dl_se->dl_runtime != attr->sched_runtime || + dl_se->dl_deadline != attr->sched_deadline || + dl_se->dl_period != attr->sched_period || + dl_se->flags != attr->sched_flags) + return true; + + return false; +} + static int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user) @@ -3510,7 +3567,7 @@ recheck: goto change; if (rt_policy(policy) && attr->sched_priority != p->rt_priority) goto change; - if (dl_policy(policy)) + if (dl_policy(policy) && dl_param_changed(p, attr)) goto change; p->sched_reset_on_fork = reset_on_fork; @@ -4202,17 +4259,10 @@ SYSCALL_DEFINE0(sched_yield) return 0; } -static void __cond_resched(void) -{ - __preempt_count_add(PREEMPT_ACTIVE); - __schedule(); - __preempt_count_sub(PREEMPT_ACTIVE); -} - int __sched _cond_resched(void) { if (should_resched()) { - __cond_resched(); + preempt_schedule_common(); return 1; } return 0; @@ -4237,7 +4287,7 @@ int __cond_resched_lock(spinlock_t *lock) if (spin_needbreak(lock) || resched) { spin_unlock(lock); if (resched) - __cond_resched(); + preempt_schedule_common(); else cpu_relax(); ret = 1; @@ -4253,7 +4303,7 @@ int __sched __cond_resched_softirq(void) if (should_resched()) { local_bh_enable(); - __cond_resched(); + preempt_schedule_common(); local_bh_disable(); return 1; } @@ -4508,9 +4558,10 @@ void sched_show_task(struct task_struct *p) { unsigned long free = 0; int ppid; - unsigned state; + unsigned long state = p->state; - state = p->state ? __ffs(p->state) + 1 : 0; + if (state) + state = __ffs(state) + 1; printk(KERN_INFO "%-15.15s %c", p->comm, state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'); #if BITS_PER_LONG == 32 @@ -4642,6 +4693,9 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur, struct dl_bw *cur_dl_b; unsigned long flags; + if (!cpumask_weight(cur)) + return ret; + rcu_read_lock_sched(); cur_dl_b = dl_bw_of(cpumask_any(cur)); trial_cpus = cpumask_weight(trial); @@ -4740,7 +4794,7 @@ static struct rq *move_queued_task(struct task_struct *p, int new_cpu) void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { - if (p->sched_class && p->sched_class->set_cpus_allowed) + if (p->sched_class->set_cpus_allowed) p->sched_class->set_cpus_allowed(p, new_mask); cpumask_copy(&p->cpus_allowed, new_mask); @@ -7250,6 +7304,11 @@ void __init sched_init(void) enter_lazy_tlb(&init_mm, current); /* + * During early bootup we pretend to be a normal task: + */ + current->sched_class = &fair_sched_class; + + /* * Make us the idle thread. Technically, schedule() should not be * called from this thread, however somewhere below it might be, * but because we are the idle thread, we just pick up running again @@ -7259,11 +7318,6 @@ void __init sched_init(void) calc_load_update = jiffies + LOAD_FREQ; - /* - * During early bootup we pretend to be a normal task: - */ - current->sched_class = &fair_sched_class; - #ifdef CONFIG_SMP zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT); /* May be allocated at isolcpus cmdline parse time */ @@ -7324,6 +7378,9 @@ void ___might_sleep(const char *file, int line, int preempt_offset) in_atomic(), irqs_disabled(), current->pid, current->comm); + if (task_stack_end_corrupted(current)) + printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); + debug_show_held_locks(current); if (irqs_disabled()) print_irqtrace_events(current); diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index 539ca3ce071..c6acb07466b 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -107,7 +107,8 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, int best_cpu = -1; const struct sched_dl_entity *dl_se = &p->dl; - if (later_mask && cpumask_and(later_mask, later_mask, cp->free_cpus)) { + if (later_mask && + cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) { best_cpu = cpumask_any(later_mask); goto out; } else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) && @@ -186,6 +187,26 @@ out: } /* + * cpudl_set_freecpu - Set the cpudl.free_cpus + * @cp: the cpudl max-heap context + * @cpu: rd attached cpu + */ +void cpudl_set_freecpu(struct cpudl *cp, int cpu) +{ + cpumask_set_cpu(cpu, cp->free_cpus); +} + +/* + * cpudl_clear_freecpu - Clear the cpudl.free_cpus + * @cp: the cpudl max-heap context + * @cpu: rd attached cpu + */ +void cpudl_clear_freecpu(struct cpudl *cp, int cpu) +{ + cpumask_clear_cpu(cpu, cp->free_cpus); +} + +/* * cpudl_init - initialize the cpudl structure * @cp: the cpudl max-heap context */ @@ -203,7 +224,7 @@ int cpudl_init(struct cpudl *cp) if (!cp->elements) return -ENOMEM; - if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) { + if (!zalloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) { kfree(cp->elements); return -ENOMEM; } @@ -211,8 +232,6 @@ int cpudl_init(struct cpudl *cp) for_each_possible_cpu(i) cp->elements[i].idx = IDX_INVALID; - cpumask_setall(cp->free_cpus); - return 0; } diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h index 020039bd132..1a0a6ef2fbe 100644 --- a/kernel/sched/cpudeadline.h +++ b/kernel/sched/cpudeadline.h @@ -24,6 +24,8 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, struct cpumask *later_mask); void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid); int cpudl_init(struct cpudl *cp); +void cpudl_set_freecpu(struct cpudl *cp, int cpu); +void cpudl_clear_freecpu(struct cpudl *cp, int cpu); void cpudl_cleanup(struct cpudl *cp); #endif /* CONFIG_SMP */ diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index b52092f2636..a027799ae13 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -350,6 +350,11 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; dl_se->runtime = pi_se->dl_runtime; } + + if (dl_se->dl_yielded) + dl_se->dl_yielded = 0; + if (dl_se->dl_throttled) + dl_se->dl_throttled = 0; } /* @@ -536,23 +541,19 @@ again: sched_clock_tick(); update_rq_clock(rq); - dl_se->dl_throttled = 0; - dl_se->dl_yielded = 0; - if (task_on_rq_queued(p)) { - enqueue_task_dl(rq, p, ENQUEUE_REPLENISH); - if (dl_task(rq->curr)) - check_preempt_curr_dl(rq, p, 0); - else - resched_curr(rq); + enqueue_task_dl(rq, p, ENQUEUE_REPLENISH); + if (dl_task(rq->curr)) + check_preempt_curr_dl(rq, p, 0); + else + resched_curr(rq); #ifdef CONFIG_SMP - /* - * Queueing this task back might have overloaded rq, - * check if we need to kick someone away. - */ - if (has_pushable_dl_tasks(rq)) - push_dl_task(rq); + /* + * Queueing this task back might have overloaded rq, + * check if we need to kick someone away. + */ + if (has_pushable_dl_tasks(rq)) + push_dl_task(rq); #endif - } unlock: raw_spin_unlock(&rq->lock); @@ -613,10 +614,9 @@ static void update_curr_dl(struct rq *rq) dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec; if (dl_runtime_exceeded(rq, dl_se)) { + dl_se->dl_throttled = 1; __dequeue_task_dl(rq, curr, 0); - if (likely(start_dl_timer(dl_se, curr->dl.dl_boosted))) - dl_se->dl_throttled = 1; - else + if (unlikely(!start_dl_timer(dl_se, curr->dl.dl_boosted))) enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH); if (!is_leftmost(curr, &rq->dl)) @@ -853,7 +853,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) * its rq, the bandwidth timer callback (which clearly has not * run yet) will take care of this. */ - if (p->dl.dl_throttled) + if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) return; enqueue_dl_entity(&p->dl, pi_se, flags); @@ -1073,7 +1073,13 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued) { update_curr_dl(rq); - if (hrtick_enabled(rq) && queued && p->dl.runtime > 0) + /* + * Even when we have runtime, update_curr_dl() might have resulted in us + * not being the leftmost task anymore. In that case NEED_RESCHED will + * be set and schedule() will start a new hrtick for the next task. + */ + if (hrtick_enabled(rq) && queued && p->dl.runtime > 0 && + is_leftmost(p, &rq->dl)) start_hrtick_dl(rq, p); } @@ -1094,6 +1100,7 @@ static void task_dead_dl(struct task_struct *p) * Since we are TASK_DEAD we won't slip out of the domain! */ raw_spin_lock_irq(&dl_b->lock); + /* XXX we should retain the bw until 0-lag */ dl_b->total_bw -= p->dl.dl_bw; raw_spin_unlock_irq(&dl_b->lock); @@ -1165,9 +1172,6 @@ static int find_later_rq(struct task_struct *task) * We have to consider system topology and task affinity * first, then we can look for a suitable cpu. */ - cpumask_copy(later_mask, task_rq(task)->rd->span); - cpumask_and(later_mask, later_mask, cpu_active_mask); - cpumask_and(later_mask, later_mask, &task->cpus_allowed); best_cpu = cpudl_find(&task_rq(task)->rd->cpudl, task, later_mask); if (best_cpu == -1) @@ -1562,6 +1566,7 @@ static void rq_online_dl(struct rq *rq) if (rq->dl.overloaded) dl_set_overload(rq); + cpudl_set_freecpu(&rq->rd->cpudl, rq->cpu); if (rq->dl.dl_nr_running > 0) cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr, 1); } @@ -1573,6 +1578,7 @@ static void rq_offline_dl(struct rq *rq) dl_clear_overload(rq); cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0); + cpudl_clear_freecpu(&rq->rd->cpudl, rq->cpu); } void init_sched_dl_class(void) @@ -1614,8 +1620,8 @@ static void cancel_dl_timer(struct rq *rq, struct task_struct *p) static void switched_from_dl(struct rq *rq, struct task_struct *p) { + /* XXX we should retain the bw until 0-lag */ cancel_dl_timer(rq, p); - __dl_clear_params(p); /* diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 92cc52001e7..8baaf858d25 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -305,6 +305,7 @@ do { \ PN(next_balance); SEQ_printf(m, " .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr))); PN(clock); + PN(clock_task); P(cpu_load[0]); P(cpu_load[1]); P(cpu_load[2]); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 40667cbf371..7ce18f3c097 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -676,7 +676,6 @@ void init_task_runnable_average(struct task_struct *p) { u32 slice; - p->se.avg.decay_count = 0; slice = sched_slice(task_cfs_rq(p), &p->se) >> 10; p->se.avg.runnable_avg_sum = slice; p->se.avg.runnable_avg_period = slice; @@ -1730,7 +1729,7 @@ static int preferred_group_nid(struct task_struct *p, int nid) nodes = node_online_map; for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) { unsigned long max_faults = 0; - nodemask_t max_group; + nodemask_t max_group = NODE_MASK_NONE; int a, b; /* Are there nodes at this distance from each other? */ @@ -2574,11 +2573,11 @@ static inline u64 __synchronize_entity_decay(struct sched_entity *se) u64 decays = atomic64_read(&cfs_rq->decay_counter); decays -= se->avg.decay_count; + se->avg.decay_count = 0; if (!decays) return 0; se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays); - se->avg.decay_count = 0; return decays; } @@ -5157,7 +5156,7 @@ static void yield_task_fair(struct rq *rq) * so we don't do microscopic update in schedule() * and double the fastpath cost. */ - rq->skip_clock_update = 1; + rq_clock_skip_update(rq, true); } set_skip_buddy(se); @@ -5949,8 +5948,8 @@ static unsigned long scale_rt_capacity(int cpu) */ age_stamp = ACCESS_ONCE(rq->age_stamp); avg = ACCESS_ONCE(rq->rt_avg); + delta = __rq_clock_broken(rq) - age_stamp; - delta = rq_clock(rq) - age_stamp; if (unlikely(delta < 0)) delta = 0; diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index c47fce75e66..aaf1c1d5cf5 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -47,7 +47,8 @@ static inline int cpu_idle_poll(void) rcu_idle_enter(); trace_cpu_idle_rcuidle(0, smp_processor_id()); local_irq_enable(); - while (!tif_need_resched()) + while (!tif_need_resched() && + (cpu_idle_force_poll || tick_check_broadcast_expired())) cpu_relax(); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); rcu_idle_exit(); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index ee15f5a0d1c..f4d4b077eba 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -831,11 +831,14 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) enqueue = 1; /* - * Force a clock update if the CPU was idle, - * lest wakeup -> unthrottle time accumulate. + * When we're idle and a woken (rt) task is + * throttled check_preempt_curr() will set + * skip_update and the time between the wakeup + * and this unthrottle will get accounted as + * 'runtime'. */ if (rt_rq->rt_nr_running && rq->curr == rq->idle) - rq->skip_clock_update = -1; + rq_clock_skip_update(rq, false); } if (rt_rq->rt_time || rt_rq->rt_nr_running) idle = 0; @@ -1337,7 +1340,12 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags) curr->prio <= p->prio)) { int target = find_lowest_rq(p); - if (target != -1) + /* + * Don't bother moving it if the destination CPU is + * not running a lower priority task. + */ + if (target != -1 && + p->prio < cpu_rq(target)->rt.highest_prio.curr) cpu = target; } rcu_read_unlock(); @@ -1614,6 +1622,16 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) lowest_rq = cpu_rq(cpu); + if (lowest_rq->rt.highest_prio.curr <= task->prio) { + /* + * Target rq has tasks of equal or higher priority, + * retrying does not release any lock and is unlikely + * to yield a different result. + */ + lowest_rq = NULL; + break; + } + /* if the prio of this runqueue changed, try again */ if (double_lock_balance(rq, lowest_rq)) { /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 9a2a45c970e..0870db23d79 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -558,8 +558,6 @@ struct rq { #ifdef CONFIG_NO_HZ_FULL unsigned long last_sched_tick; #endif - int skip_clock_update; - /* capture load from *all* tasks on this cpu: */ struct load_weight load; unsigned long nr_load_updates; @@ -588,6 +586,7 @@ struct rq { unsigned long next_balance; struct mm_struct *prev_mm; + unsigned int clock_skip_update; u64 clock; u64 clock_task; @@ -687,16 +686,35 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); #define cpu_curr(cpu) (cpu_rq(cpu)->curr) #define raw_rq() raw_cpu_ptr(&runqueues) +static inline u64 __rq_clock_broken(struct rq *rq) +{ + return ACCESS_ONCE(rq->clock); +} + static inline u64 rq_clock(struct rq *rq) { + lockdep_assert_held(&rq->lock); return rq->clock; } static inline u64 rq_clock_task(struct rq *rq) { + lockdep_assert_held(&rq->lock); return rq->clock_task; } +#define RQCF_REQ_SKIP 0x01 +#define RQCF_ACT_SKIP 0x02 + +static inline void rq_clock_skip_update(struct rq *rq, bool skip) +{ + lockdep_assert_held(&rq->lock); + if (skip) + rq->clock_skip_update |= RQCF_REQ_SKIP; + else + rq->clock_skip_update &= ~RQCF_REQ_SKIP; +} + #ifdef CONFIG_NUMA enum numa_topology_type { NUMA_DIRECT, diff --git a/kernel/smpboot.c b/kernel/smpboot.c index f032fb5284e..40190f28db3 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -280,6 +280,7 @@ int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) unsigned int cpu; int ret = 0; + get_online_cpus(); mutex_lock(&smpboot_threads_lock); for_each_online_cpu(cpu) { ret = __smpboot_create_thread(plug_thread, cpu); @@ -292,6 +293,7 @@ int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) list_add(&plug_thread->list, &hotplug_threads); out: mutex_unlock(&smpboot_threads_lock); + put_online_cpus(); return ret; } EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread); diff --git a/kernel/softirq.c b/kernel/softirq.c index 501baa9ac1b..479e4436f78 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -114,8 +114,12 @@ void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) trace_softirqs_off(ip); raw_local_irq_restore(flags); - if (preempt_count() == cnt) + if (preempt_count() == cnt) { +#ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = get_parent_ip(CALLER_ADDR1); +#endif trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + } } EXPORT_SYMBOL(__local_bh_disable_ip); #endif /* CONFIG_TRACE_IRQFLAGS */ @@ -656,9 +660,8 @@ static void run_ksoftirqd(unsigned int cpu) * in the task stack here. */ __do_softirq(); - rcu_note_context_switch(); local_irq_enable(); - cond_resched(); + cond_resched_rcu_qs(); return; } local_irq_enable(); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 137c7f69b26..88ea2d6e003 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1248,7 +1248,6 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = hugetlb_sysctl_handler, - .extra1 = &zero, }, #ifdef CONFIG_NUMA { @@ -1257,7 +1256,6 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = &hugetlb_mempolicy_sysctl_handler, - .extra1 = &zero, }, #endif { @@ -1280,7 +1278,6 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = hugetlb_overcommit_handler, - .extra1 = &zero, }, #endif { diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 37e50aadd47..3f5e183c3d9 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -122,7 +122,7 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base) mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai); boot = ktime_add(mono, off_boot); xtim = ktime_add(mono, off_real); - tai = ktime_add(xtim, off_tai); + tai = ktime_add(mono, off_tai); base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim; base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono; @@ -266,7 +266,7 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) /* * Divide a ktime value by a nanosecond value */ -u64 ktime_divns(const ktime_t kt, s64 div) +u64 __ktime_divns(const ktime_t kt, s64 div) { u64 dclc; int sft = 0; @@ -282,7 +282,7 @@ u64 ktime_divns(const ktime_t kt, s64 div) return dclc; } -EXPORT_SYMBOL_GPL(ktime_divns); +EXPORT_SYMBOL_GPL(__ktime_divns); #endif /* BITS_PER_LONG >= 64 */ /* @@ -440,6 +440,37 @@ static inline void debug_deactivate(struct hrtimer *timer) trace_hrtimer_cancel(timer); } +#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) +static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base) +{ + struct hrtimer_clock_base *base = cpu_base->clock_base; + ktime_t expires, expires_next = { .tv64 = KTIME_MAX }; + int i; + + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) { + struct timerqueue_node *next; + struct hrtimer *timer; + + next = timerqueue_getnext(&base->active); + if (!next) + continue; + + timer = container_of(next, struct hrtimer, node); + expires = ktime_sub(hrtimer_get_expires(timer), base->offset); + if (expires.tv64 < expires_next.tv64) + expires_next = expires; + } + /* + * clock_was_set() might have changed base->offset of any of + * the clock bases so the result might be negative. Fix it up + * to prevent a false positive in clockevents_program_event(). + */ + if (expires_next.tv64 < 0) + expires_next.tv64 = 0; + return expires_next; +} +#endif + /* High resolution timer related functions */ #ifdef CONFIG_HIGH_RES_TIMERS @@ -488,32 +519,7 @@ static inline int hrtimer_hres_active(void) static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) { - int i; - struct hrtimer_clock_base *base = cpu_base->clock_base; - ktime_t expires, expires_next; - - expires_next.tv64 = KTIME_MAX; - - for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) { - struct hrtimer *timer; - struct timerqueue_node *next; - - next = timerqueue_getnext(&base->active); - if (!next) - continue; - timer = container_of(next, struct hrtimer, node); - - expires = ktime_sub(hrtimer_get_expires(timer), base->offset); - /* - * clock_was_set() has changed base->offset so the - * result might be negative. Fix it up to prevent a - * false positive in clockevents_program_event() - */ - if (expires.tv64 < 0) - expires.tv64 = 0; - if (expires.tv64 < expires_next.tv64) - expires_next = expires; - } + ktime_t expires_next = __hrtimer_get_next_event(cpu_base); if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64) return; @@ -587,6 +593,15 @@ static int hrtimer_reprogram(struct hrtimer *timer, return 0; /* + * When the target cpu of the timer is currently executing + * hrtimer_interrupt(), then we do not touch the clock event + * device. hrtimer_interrupt() will reevaluate all clock bases + * before reprogramming the device. + */ + if (cpu_base->in_hrtirq) + return 0; + + /* * If a hang was detected in the last timer interrupt then we * do not schedule a timer which is earlier than the expiry * which we enforced in the hang detection. We want the system @@ -1104,29 +1119,14 @@ EXPORT_SYMBOL_GPL(hrtimer_get_remaining); ktime_t hrtimer_get_next_event(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); - struct hrtimer_clock_base *base = cpu_base->clock_base; - ktime_t delta, mindelta = { .tv64 = KTIME_MAX }; + ktime_t mindelta = { .tv64 = KTIME_MAX }; unsigned long flags; - int i; raw_spin_lock_irqsave(&cpu_base->lock, flags); - if (!hrtimer_hres_active()) { - for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) { - struct hrtimer *timer; - struct timerqueue_node *next; - - next = timerqueue_getnext(&base->active); - if (!next) - continue; - - timer = container_of(next, struct hrtimer, node); - delta.tv64 = hrtimer_get_expires_tv64(timer); - delta = ktime_sub(delta, base->get_time()); - if (delta.tv64 < mindelta.tv64) - mindelta.tv64 = delta.tv64; - } - } + if (!hrtimer_hres_active()) + mindelta = ktime_sub(__hrtimer_get_next_event(cpu_base), + ktime_get()); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); @@ -1253,7 +1253,7 @@ void hrtimer_interrupt(struct clock_event_device *dev) raw_spin_lock(&cpu_base->lock); entry_time = now = hrtimer_update_base(cpu_base); retry: - expires_next.tv64 = KTIME_MAX; + cpu_base->in_hrtirq = 1; /* * We set expires_next to KTIME_MAX here with cpu_base->lock * held to prevent that a timer is enqueued in our queue via @@ -1291,28 +1291,20 @@ retry: * are right-of a not yet expired timer, because that * timer will have to trigger a wakeup anyway. */ - - if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) { - ktime_t expires; - - expires = ktime_sub(hrtimer_get_expires(timer), - base->offset); - if (expires.tv64 < 0) - expires.tv64 = KTIME_MAX; - if (expires.tv64 < expires_next.tv64) - expires_next = expires; + if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) break; - } __run_hrtimer(timer, &basenow); } } - + /* Reevaluate the clock bases for the next expiry */ + expires_next = __hrtimer_get_next_event(cpu_base); /* * Store the new expiry value so the migration code can verify * against it. */ cpu_base->expires_next = expires_next; + cpu_base->in_hrtirq = 0; raw_spin_unlock(&cpu_base->lock); /* Reprogramming necessary ? */ diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 28bf91c60a0..4b585e0fdd2 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -488,13 +488,13 @@ static void sync_cmos_clock(struct work_struct *work) getnstimeofday64(&now); if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) { - struct timespec adjust = timespec64_to_timespec(now); + struct timespec64 adjust = now; fail = -ENODEV; if (persistent_clock_is_local) adjust.tv_sec -= (sys_tz.tz_minuteswest * 60); #ifdef CONFIG_GENERIC_CMOS_UPDATE - fail = update_persistent_clock(adjust); + fail = update_persistent_clock(timespec64_to_timespec(adjust)); #endif #ifdef CONFIG_RTC_SYSTOHC if (fail == -ENODEV) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 6a931852082..b124af25980 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1659,24 +1659,24 @@ out: } /** - * getboottime - Return the real time of system boot. - * @ts: pointer to the timespec to be set + * getboottime64 - Return the real time of system boot. + * @ts: pointer to the timespec64 to be set * - * Returns the wall-time of boot in a timespec. + * Returns the wall-time of boot in a timespec64. * * This is based on the wall_to_monotonic offset and the total suspend * time. Calls to settimeofday will affect the value returned (which * basically means that however wrong your real time clock is at boot time, * you get the right time here). */ -void getboottime(struct timespec *ts) +void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); - *ts = ktime_to_timespec(t); + *ts = ktime_to_timespec64(t); } -EXPORT_SYMBOL_GPL(getboottime); +EXPORT_SYMBOL_GPL(getboottime64); unsigned long get_seconds(void) { diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c index 1c71382b283..eb4220a132e 100644 --- a/kernel/trace/power-traces.c +++ b/kernel/trace/power-traces.c @@ -13,5 +13,6 @@ #define CREATE_TRACE_POINTS #include <trace/events/power.h> +EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume); EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle); diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 4b9c114ee9d..6fa484de2ba 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -261,7 +261,7 @@ void perf_trace_del(struct perf_event *p_event, int flags) } void *perf_trace_buf_prepare(int size, unsigned short type, - struct pt_regs *regs, int *rctxp) + struct pt_regs **regs, int *rctxp) { struct trace_entry *entry; unsigned long flags; @@ -280,6 +280,8 @@ void *perf_trace_buf_prepare(int size, unsigned short type, if (*rctxp < 0) return NULL; + if (regs) + *regs = this_cpu_ptr(&__perf_regs[*rctxp]); raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]); /* zero the dead bytes from align to not leak stack to user */ diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 5edb518be34..296079ae658 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1148,7 +1148,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); + entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx); if (!entry) return; @@ -1179,7 +1179,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); + entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx); if (!entry) return; diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index c6ee36fcbf9..f97f6e3a676 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -574,7 +574,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) size -= sizeof(u32); rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size, - sys_data->enter_event->event.type, regs, &rctx); + sys_data->enter_event->event.type, NULL, &rctx); if (!rec) return; @@ -647,7 +647,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) size -= sizeof(u32); rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size, - sys_data->exit_event->event.type, regs, &rctx); + sys_data->exit_event->event.type, NULL, &rctx); if (!rec) return; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 8520acc34b1..b11441321e7 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1111,7 +1111,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, if (hlist_empty(head)) goto out; - entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx); + entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx); if (!entry) goto out; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index a8f3c999322..e5ea3ab856b 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -636,7 +636,7 @@ config DEBUG_STACKOVERFLOW depends on DEBUG_KERNEL && HAVE_DEBUG_STACKOVERFLOW ---help--- Say Y here if you want to check for overflows of kernel, IRQ - and exception stacks (if your archicture uses them). This + and exception stacks (if your architecture uses them). This option will show detailed messages if free stack space drops below a certain limit. @@ -1215,6 +1215,7 @@ config RCU_TORTURE_TEST tristate "torture tests for RCU" depends on DEBUG_KERNEL select TORTURE_TEST + select SRCU default n help This option provides a kernel module that runs torture tests @@ -1257,7 +1258,7 @@ config RCU_CPU_STALL_TIMEOUT config RCU_CPU_STALL_INFO bool "Print additional diagnostics on RCU CPU stall" depends on (TREE_RCU || PREEMPT_RCU) && DEBUG_KERNEL - default n + default y help For each stalled CPU that is aware of the current RCU grace period, print out additional per-CPU diagnostic information diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 527799d4447..d8f3d315060 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -641,7 +641,7 @@ static __init int ddebug_setup_query(char *str) __setup("ddebug_query=", ddebug_setup_query); /* - * File_ops->write method for <debugfs>/dynamic_debug/conrol. Gathers the + * File_ops->write method for <debugfs>/dynamic_debug/control. Gathers the * command text from userspace, parses and executes it. */ #define USER_BUF_PAGE 4096 diff --git a/mm/Kconfig b/mm/Kconfig index 1d1ae6b078f..4395b12869c 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -325,6 +325,7 @@ config VIRT_TO_BUS config MMU_NOTIFIER bool + select SRCU config KSM bool "Enable KSM for page merging" diff --git a/mm/Makefile b/mm/Makefile index 4bf586e6637..3548460ab7b 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -3,7 +3,7 @@ # mmu-y := nommu.o -mmu-$(CONFIG_MMU) := fremap.o gup.o highmem.o memory.o mincore.o \ +mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \ mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \ vmalloc.o pagewalk.o pgtable-generic.o diff --git a/mm/cleancache.c b/mm/cleancache.c index d0eac435040..053bcd8f12f 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -25,7 +25,7 @@ static struct cleancache_ops *cleancache_ops __read_mostly; /* - * Counters available via /sys/kernel/debug/frontswap (if debugfs is + * Counters available via /sys/kernel/debug/cleancache (if debugfs is * properly configured. These are for information only so are not protected * against increment races. */ diff --git a/mm/debug.c b/mm/debug.c index 0e58f3211f8..d69cb5a7ba9 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -130,7 +130,6 @@ static const struct trace_print_flags vmaflags_names[] = { {VM_ACCOUNT, "account" }, {VM_NORESERVE, "noreserve" }, {VM_HUGETLB, "hugetlb" }, - {VM_NONLINEAR, "nonlinear" }, #if defined(CONFIG_X86) {VM_PAT, "pat" }, #elif defined(CONFIG_PPC) diff --git a/mm/filemap.c b/mm/filemap.c index 673e4581a2e..bf7a2714270 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2087,7 +2087,6 @@ const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; /* This is used for a general mmap of a disk file */ diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 0d105aeff82..70c09da1a41 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -301,7 +301,6 @@ out: static const struct vm_operations_struct xip_file_vm_ops = { .fault = xip_file_fault, .page_mkwrite = filemap_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; int xip_file_mmap(struct file * file, struct vm_area_struct * vma) diff --git a/mm/fremap.c b/mm/fremap.c deleted file mode 100644 index 2805d71cf47..00000000000 --- a/mm/fremap.c +++ /dev/null @@ -1,283 +0,0 @@ -/* - * linux/mm/fremap.c - * - * Explicit pagetable population and nonlinear (random) mappings support. - * - * started by Ingo Molnar, Copyright (C) 2002, 2003 - */ -#include <linux/export.h> -#include <linux/backing-dev.h> -#include <linux/mm.h> -#include <linux/swap.h> -#include <linux/file.h> -#include <linux/mman.h> -#include <linux/pagemap.h> -#include <linux/swapops.h> -#include <linux/rmap.h> -#include <linux/syscalls.h> -#include <linux/mmu_notifier.h> - -#include <asm/mmu_context.h> -#include <asm/cacheflush.h> -#include <asm/tlbflush.h> - -#include "internal.h" - -static int mm_counter(struct page *page) -{ - return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES; -} - -static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) -{ - pte_t pte = *ptep; - struct page *page; - swp_entry_t entry; - - if (pte_present(pte)) { - flush_cache_page(vma, addr, pte_pfn(pte)); - pte = ptep_clear_flush_notify(vma, addr, ptep); - page = vm_normal_page(vma, addr, pte); - if (page) { - if (pte_dirty(pte)) - set_page_dirty(page); - update_hiwater_rss(mm); - dec_mm_counter(mm, mm_counter(page)); - page_remove_rmap(page); - page_cache_release(page); - } - } else { /* zap_pte() is not called when pte_none() */ - if (!pte_file(pte)) { - update_hiwater_rss(mm); - entry = pte_to_swp_entry(pte); - if (non_swap_entry(entry)) { - if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); - dec_mm_counter(mm, mm_counter(page)); - } - } else { - free_swap_and_cache(entry); - dec_mm_counter(mm, MM_SWAPENTS); - } - } - pte_clear_not_present_full(mm, addr, ptep, 0); - } -} - -/* - * Install a file pte to a given virtual memory address, release any - * previously existing mapping. - */ -static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, unsigned long pgoff, pgprot_t prot) -{ - int err = -ENOMEM; - pte_t *pte, ptfile; - spinlock_t *ptl; - - pte = get_locked_pte(mm, addr, &ptl); - if (!pte) - goto out; - - ptfile = pgoff_to_pte(pgoff); - - if (!pte_none(*pte)) - zap_pte(mm, vma, addr, pte); - - set_pte_at(mm, addr, pte, pte_file_mksoft_dirty(ptfile)); - /* - * We don't need to run update_mmu_cache() here because the "file pte" - * being installed by install_file_pte() is not a real pte - it's a - * non-present entry (like a swap entry), noting what file offset should - * be mapped there when there's a fault (in a non-linear vma where - * that's not obvious). - */ - pte_unmap_unlock(pte, ptl); - err = 0; -out: - return err; -} - -int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, - unsigned long size, pgoff_t pgoff) -{ - struct mm_struct *mm = vma->vm_mm; - int err; - - do { - err = install_file_pte(mm, vma, addr, pgoff, vma->vm_page_prot); - if (err) - return err; - - size -= PAGE_SIZE; - addr += PAGE_SIZE; - pgoff++; - } while (size); - - return 0; -} -EXPORT_SYMBOL(generic_file_remap_pages); - -/** - * sys_remap_file_pages - remap arbitrary pages of an existing VM_SHARED vma - * @start: start of the remapped virtual memory range - * @size: size of the remapped virtual memory range - * @prot: new protection bits of the range (see NOTE) - * @pgoff: to-be-mapped page of the backing store file - * @flags: 0 or MAP_NONBLOCKED - the later will cause no IO. - * - * sys_remap_file_pages remaps arbitrary pages of an existing VM_SHARED vma - * (shared backing store file). - * - * This syscall works purely via pagetables, so it's the most efficient - * way to map the same (large) file into a given virtual window. Unlike - * mmap()/mremap() it does not create any new vmas. The new mappings are - * also safe across swapout. - * - * NOTE: the @prot parameter right now is ignored (but must be zero), - * and the vma's default protection is used. Arbitrary protections - * might be implemented in the future. - */ -SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, - unsigned long, prot, unsigned long, pgoff, unsigned long, flags) -{ - struct mm_struct *mm = current->mm; - struct address_space *mapping; - struct vm_area_struct *vma; - int err = -EINVAL; - int has_write_lock = 0; - vm_flags_t vm_flags = 0; - - pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. " - "See Documentation/vm/remap_file_pages.txt.\n", - current->comm, current->pid); - - if (prot) - return err; - /* - * Sanitize the syscall parameters: - */ - start = start & PAGE_MASK; - size = size & PAGE_MASK; - - /* Does the address range wrap, or is the span zero-sized? */ - if (start + size <= start) - return err; - - /* Does pgoff wrap? */ - if (pgoff + (size >> PAGE_SHIFT) < pgoff) - return err; - - /* Can we represent this offset inside this architecture's pte's? */ -#if PTE_FILE_MAX_BITS < BITS_PER_LONG - if (pgoff + (size >> PAGE_SHIFT) >= (1UL << PTE_FILE_MAX_BITS)) - return err; -#endif - - /* We need down_write() to change vma->vm_flags. */ - down_read(&mm->mmap_sem); - retry: - vma = find_vma(mm, start); - - /* - * Make sure the vma is shared, that it supports prefaulting, - * and that the remapped range is valid and fully within - * the single existing vma. - */ - if (!vma || !(vma->vm_flags & VM_SHARED)) - goto out; - - if (!vma->vm_ops || !vma->vm_ops->remap_pages) - goto out; - - if (start < vma->vm_start || start + size > vma->vm_end) - goto out; - - /* Must set VM_NONLINEAR before any pages are populated. */ - if (!(vma->vm_flags & VM_NONLINEAR)) { - /* - * vm_private_data is used as a swapout cursor - * in a VM_NONLINEAR vma. - */ - if (vma->vm_private_data) - goto out; - - /* Don't need a nonlinear mapping, exit success */ - if (pgoff == linear_page_index(vma, start)) { - err = 0; - goto out; - } - - if (!has_write_lock) { -get_write_lock: - up_read(&mm->mmap_sem); - down_write(&mm->mmap_sem); - has_write_lock = 1; - goto retry; - } - mapping = vma->vm_file->f_mapping; - /* - * page_mkclean doesn't work on nonlinear vmas, so if - * dirty pages need to be accounted, emulate with linear - * vmas. - */ - if (mapping_cap_account_dirty(mapping)) { - unsigned long addr; - struct file *file = get_file(vma->vm_file); - /* mmap_region may free vma; grab the info now */ - vm_flags = vma->vm_flags; - - addr = mmap_region(file, start, size, vm_flags, pgoff); - fput(file); - if (IS_ERR_VALUE(addr)) { - err = addr; - } else { - BUG_ON(addr != start); - err = 0; - } - goto out_freed; - } - i_mmap_lock_write(mapping); - flush_dcache_mmap_lock(mapping); - vma->vm_flags |= VM_NONLINEAR; - vma_interval_tree_remove(vma, &mapping->i_mmap); - vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); - flush_dcache_mmap_unlock(mapping); - i_mmap_unlock_write(mapping); - } - - if (vma->vm_flags & VM_LOCKED) { - /* - * drop PG_Mlocked flag for over-mapped range - */ - if (!has_write_lock) - goto get_write_lock; - vm_flags = vma->vm_flags; - munlock_vma_pages_range(vma, start, start + size); - vma->vm_flags = vm_flags; - } - - mmu_notifier_invalidate_range_start(mm, start, start + size); - err = vma->vm_ops->remap_pages(vma, start, size, pgoff); - mmu_notifier_invalidate_range_end(mm, start, start + size); - - /* - * We can't clear VM_NONLINEAR because we'd have to do - * it after ->populate completes, and that would prevent - * downgrading the lock. (Locks can't be upgraded). - */ - -out: - if (vma) - vm_flags = vma->vm_flags; -out_freed: - if (likely(!has_write_lock)) - up_read(&mm->mmap_sem); - else - up_write(&mm->mmap_sem); - if (!err && ((vm_flags & VM_LOCKED) || !(flags & MAP_NONBLOCK))) - mm_populate(start, size); - - return err; -} @@ -55,7 +55,7 @@ retry: */ if (likely(!(flags & FOLL_MIGRATION))) goto no_page; - if (pte_none(pte) || pte_file(pte)) + if (pte_none(pte)) goto no_page; entry = pte_to_swp_entry(pte); if (!is_migration_entry(entry)) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 85032de5e20..be0e5d0db5e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -35,7 +35,7 @@ #include <linux/node.h> #include "internal.h" -unsigned long hugepages_treat_as_movable; +int hugepages_treat_as_movable; int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; diff --git a/mm/interval_tree.c b/mm/interval_tree.c index 8da581fa906..f2c2492681b 100644 --- a/mm/interval_tree.c +++ b/mm/interval_tree.c @@ -21,8 +21,8 @@ static inline unsigned long vma_last_pgoff(struct vm_area_struct *v) return v->vm_pgoff + ((v->vm_end - v->vm_start) >> PAGE_SHIFT) - 1; } -INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.linear.rb, - unsigned long, shared.linear.rb_subtree_last, +INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb, + unsigned long, shared.rb_subtree_last, vma_start_pgoff, vma_last_pgoff,, vma_interval_tree) /* Insert node immediately after prev in the interval tree */ @@ -36,26 +36,26 @@ void vma_interval_tree_insert_after(struct vm_area_struct *node, VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node); - if (!prev->shared.linear.rb.rb_right) { + if (!prev->shared.rb.rb_right) { parent = prev; - link = &prev->shared.linear.rb.rb_right; + link = &prev->shared.rb.rb_right; } else { - parent = rb_entry(prev->shared.linear.rb.rb_right, - struct vm_area_struct, shared.linear.rb); - if (parent->shared.linear.rb_subtree_last < last) - parent->shared.linear.rb_subtree_last = last; - while (parent->shared.linear.rb.rb_left) { - parent = rb_entry(parent->shared.linear.rb.rb_left, - struct vm_area_struct, shared.linear.rb); - if (parent->shared.linear.rb_subtree_last < last) - parent->shared.linear.rb_subtree_last = last; + parent = rb_entry(prev->shared.rb.rb_right, + struct vm_area_struct, shared.rb); + if (parent->shared.rb_subtree_last < last) + parent->shared.rb_subtree_last = last; + while (parent->shared.rb.rb_left) { + parent = rb_entry(parent->shared.rb.rb_left, + struct vm_area_struct, shared.rb); + if (parent->shared.rb_subtree_last < last) + parent->shared.rb_subtree_last = last; } - link = &parent->shared.linear.rb.rb_left; + link = &parent->shared.rb.rb_left; } - node->shared.linear.rb_subtree_last = last; - rb_link_node(&node->shared.linear.rb, &parent->shared.linear.rb, link); - rb_insert_augmented(&node->shared.linear.rb, root, + node->shared.rb_subtree_last = last; + rb_link_node(&node->shared.rb, &parent->shared.rb, link); + rb_insert_augmented(&node->shared.rb, root, &vma_interval_tree_augment); } @@ -1748,7 +1748,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, */ if (*vm_flags & (VM_MERGEABLE | VM_SHARED | VM_MAYSHARE | VM_PFNMAP | VM_IO | VM_DONTEXPAND | - VM_HUGETLB | VM_NONLINEAR | VM_MIXEDMAP)) + VM_HUGETLB | VM_MIXEDMAP)) return 0; /* just ignore the advice */ #ifdef VM_SAO diff --git a/mm/madvise.c b/mm/madvise.c index a271adc9328..d79fb5e8f80 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -155,7 +155,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, pte = *(orig_pte + ((index - start) / PAGE_SIZE)); pte_unmap_unlock(orig_pte, ptl); - if (pte_present(pte) || pte_none(pte) || pte_file(pte)) + if (pte_present(pte) || pte_none(pte)) continue; entry = pte_to_swp_entry(pte); if (unlikely(non_swap_entry(entry))) @@ -278,14 +278,7 @@ static long madvise_dontneed(struct vm_area_struct *vma, if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)) return -EINVAL; - if (unlikely(vma->vm_flags & VM_NONLINEAR)) { - struct zap_details details = { - .nonlinear_vma = vma, - .last_index = ULONG_MAX, - }; - zap_page_range(vma, start, end - start, &details); - } else - zap_page_range(vma, start, end - start, NULL); + zap_page_range(vma, start, end - start, NULL); return 0; } @@ -303,7 +296,7 @@ static long madvise_remove(struct vm_area_struct *vma, *prev = NULL; /* tell sys_madvise we drop mmap_sem */ - if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB)) + if (vma->vm_flags & (VM_LOCKED | VM_HUGETLB)) return -EINVAL; f = vma->vm_file; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 683b4782019..f3f8a4f52a0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -343,9 +343,6 @@ struct mem_cgroup { struct cg_proto tcp_mem; #endif #if defined(CONFIG_MEMCG_KMEM) - /* analogous to slab_common's slab_caches list, but per-memcg; - * protected by memcg_slab_mutex */ - struct list_head memcg_slab_caches; /* Index in the kmem_cache->memcg_params->memcg_caches array */ int kmemcg_id; #endif @@ -2476,27 +2473,8 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg, } #ifdef CONFIG_MEMCG_KMEM -/* - * The memcg_slab_mutex is held whenever a per memcg kmem cache is created or - * destroyed. It protects memcg_caches arrays and memcg_slab_caches lists. - */ -static DEFINE_MUTEX(memcg_slab_mutex); - -/* - * This is a bit cumbersome, but it is rarely used and avoids a backpointer - * in the memcg_cache_params struct. - */ -static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p) -{ - struct kmem_cache *cachep; - - VM_BUG_ON(p->is_root_cache); - cachep = p->root_cache; - return cache_from_memcg_idx(cachep, memcg_cache_id(p->memcg)); -} - -static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, - unsigned long nr_pages) +int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, + unsigned long nr_pages) { struct page_counter *counter; int ret = 0; @@ -2533,8 +2511,7 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, return ret; } -static void memcg_uncharge_kmem(struct mem_cgroup *memcg, - unsigned long nr_pages) +void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages) { page_counter_uncharge(&memcg->memory, nr_pages); if (do_swap_account) @@ -2579,10 +2556,7 @@ static int memcg_alloc_cache_id(void) else if (size > MEMCG_CACHES_MAX_SIZE) size = MEMCG_CACHES_MAX_SIZE; - mutex_lock(&memcg_slab_mutex); err = memcg_update_all_caches(size); - mutex_unlock(&memcg_slab_mutex); - if (err) { ida_simple_remove(&kmem_limited_groups, id); return err; @@ -2605,123 +2579,20 @@ void memcg_update_array_size(int num) memcg_limited_groups_array_size = num; } -static void memcg_register_cache(struct mem_cgroup *memcg, - struct kmem_cache *root_cache) -{ - static char memcg_name_buf[NAME_MAX + 1]; /* protected by - memcg_slab_mutex */ - struct kmem_cache *cachep; - int id; - - lockdep_assert_held(&memcg_slab_mutex); - - id = memcg_cache_id(memcg); - - /* - * Since per-memcg caches are created asynchronously on first - * allocation (see memcg_kmem_get_cache()), several threads can try to - * create the same cache, but only one of them may succeed. - */ - if (cache_from_memcg_idx(root_cache, id)) - return; - - cgroup_name(memcg->css.cgroup, memcg_name_buf, NAME_MAX + 1); - cachep = memcg_create_kmem_cache(memcg, root_cache, memcg_name_buf); - /* - * If we could not create a memcg cache, do not complain, because - * that's not critical at all as we can always proceed with the root - * cache. - */ - if (!cachep) - return; - - list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches); - - /* - * Since readers won't lock (see cache_from_memcg_idx()), we need a - * barrier here to ensure nobody will see the kmem_cache partially - * initialized. - */ - smp_wmb(); - - BUG_ON(root_cache->memcg_params->memcg_caches[id]); - root_cache->memcg_params->memcg_caches[id] = cachep; -} - -static void memcg_unregister_cache(struct kmem_cache *cachep) -{ - struct kmem_cache *root_cache; - struct mem_cgroup *memcg; - int id; - - lockdep_assert_held(&memcg_slab_mutex); - - BUG_ON(is_root_cache(cachep)); - - root_cache = cachep->memcg_params->root_cache; - memcg = cachep->memcg_params->memcg; - id = memcg_cache_id(memcg); - - BUG_ON(root_cache->memcg_params->memcg_caches[id] != cachep); - root_cache->memcg_params->memcg_caches[id] = NULL; - - list_del(&cachep->memcg_params->list); - - kmem_cache_destroy(cachep); -} - -int __memcg_cleanup_cache_params(struct kmem_cache *s) -{ - struct kmem_cache *c; - int i, failed = 0; - - mutex_lock(&memcg_slab_mutex); - for_each_memcg_cache_index(i) { - c = cache_from_memcg_idx(s, i); - if (!c) - continue; - - memcg_unregister_cache(c); - - if (cache_from_memcg_idx(s, i)) - failed++; - } - mutex_unlock(&memcg_slab_mutex); - return failed; -} - -static void memcg_unregister_all_caches(struct mem_cgroup *memcg) -{ - struct kmem_cache *cachep; - struct memcg_cache_params *params, *tmp; - - if (!memcg_kmem_is_active(memcg)) - return; - - mutex_lock(&memcg_slab_mutex); - list_for_each_entry_safe(params, tmp, &memcg->memcg_slab_caches, list) { - cachep = memcg_params_to_cache(params); - memcg_unregister_cache(cachep); - } - mutex_unlock(&memcg_slab_mutex); -} - -struct memcg_register_cache_work { +struct memcg_kmem_cache_create_work { struct mem_cgroup *memcg; struct kmem_cache *cachep; struct work_struct work; }; -static void memcg_register_cache_func(struct work_struct *w) +static void memcg_kmem_cache_create_func(struct work_struct *w) { - struct memcg_register_cache_work *cw = - container_of(w, struct memcg_register_cache_work, work); + struct memcg_kmem_cache_create_work *cw = + container_of(w, struct memcg_kmem_cache_create_work, work); struct mem_cgroup *memcg = cw->memcg; struct kmem_cache *cachep = cw->cachep; - mutex_lock(&memcg_slab_mutex); - memcg_register_cache(memcg, cachep); - mutex_unlock(&memcg_slab_mutex); + memcg_create_kmem_cache(memcg, cachep); css_put(&memcg->css); kfree(cw); @@ -2730,10 +2601,10 @@ static void memcg_register_cache_func(struct work_struct *w) /* * Enqueue the creation of a per-memcg kmem_cache. */ -static void __memcg_schedule_register_cache(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { - struct memcg_register_cache_work *cw; + struct memcg_kmem_cache_create_work *cw; cw = kmalloc(sizeof(*cw), GFP_NOWAIT); if (!cw) @@ -2743,18 +2614,18 @@ static void __memcg_schedule_register_cache(struct mem_cgroup *memcg, cw->memcg = memcg; cw->cachep = cachep; + INIT_WORK(&cw->work, memcg_kmem_cache_create_func); - INIT_WORK(&cw->work, memcg_register_cache_func); schedule_work(&cw->work); } -static void memcg_schedule_register_cache(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { /* * We need to stop accounting when we kmalloc, because if the * corresponding kmalloc cache is not yet created, the first allocation - * in __memcg_schedule_register_cache will recurse. + * in __memcg_schedule_kmem_cache_create will recurse. * * However, it is better to enclose the whole function. Depending on * the debugging options enabled, INIT_WORK(), for instance, can @@ -2763,24 +2634,10 @@ static void memcg_schedule_register_cache(struct mem_cgroup *memcg, * the safest choice is to do it like this, wrapping the whole function. */ current->memcg_kmem_skip_account = 1; - __memcg_schedule_register_cache(memcg, cachep); + __memcg_schedule_kmem_cache_create(memcg, cachep); current->memcg_kmem_skip_account = 0; } -int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order) -{ - unsigned int nr_pages = 1 << order; - - return memcg_charge_kmem(cachep->memcg_params->memcg, gfp, nr_pages); -} - -void __memcg_uncharge_slab(struct kmem_cache *cachep, int order) -{ - unsigned int nr_pages = 1 << order; - - memcg_uncharge_kmem(cachep->memcg_params->memcg, nr_pages); -} - /* * Return the kmem_cache we're supposed to use for a slab allocation. * We try to use the current memcg's version of the cache. @@ -2825,7 +2682,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep) * could happen with the slab_mutex held. So it's better to * defer everything. */ - memcg_schedule_register_cache(memcg, cachep); + memcg_schedule_kmem_cache_create(memcg, cachep); out: css_put(&memcg->css); return cachep; @@ -4154,7 +4011,7 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) static void memcg_destroy_kmem(struct mem_cgroup *memcg) { - memcg_unregister_all_caches(memcg); + memcg_destroy_kmem_caches(memcg); mem_cgroup_sockets_destroy(memcg); } #else @@ -4682,7 +4539,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) spin_lock_init(&memcg->event_list_lock); #ifdef CONFIG_MEMCG_KMEM memcg->kmemcg_id = -1; - INIT_LIST_HEAD(&memcg->memcg_slab_caches); #endif return &memcg->css; @@ -4926,10 +4782,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, return NULL; mapping = vma->vm_file->f_mapping; - if (pte_none(ptent)) - pgoff = linear_page_index(vma, addr); - else /* pte_file(ptent) is true */ - pgoff = pte_to_pgoff(ptent); + pgoff = linear_page_index(vma, addr); /* page is moved even if it's not RSS of this task(page-faulted). */ #ifdef CONFIG_SWAP @@ -4961,7 +4814,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, page = mc_handle_present_pte(vma, addr, ptent); else if (is_swap_pte(ptent)) page = mc_handle_swap_pte(vma, addr, ptent, &ent); - else if (pte_none(ptent) || pte_file(ptent)) + else if (pte_none(ptent)) page = mc_handle_file_pte(vma, addr, ptent, &ent); if (!page && !ent.val) @@ -5773,7 +5626,7 @@ void mem_cgroup_uncharge_list(struct list_head *page_list) * mem_cgroup_migrate - migrate a charge to another page * @oldpage: currently charged page * @newpage: page to transfer the charge to - * @lrucare: both pages might be on the LRU already + * @lrucare: either or both pages might be on the LRU already * * Migrate the charge from @oldpage to @newpage. * diff --git a/mm/memory.c b/mm/memory.c index 2c3536cc6c6..d63849b5188 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -754,6 +754,8 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, if (HAVE_PTE_SPECIAL) { if (likely(!pte_special(pte))) goto check_pfn; + if (vma->vm_ops && vma->vm_ops->find_special_page) + return vma->vm_ops->find_special_page(vma, addr); if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; if (!is_zero_pfn(pfn)) @@ -811,42 +813,40 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, /* pte contains position in swap or file, so copy. */ if (unlikely(!pte_present(pte))) { - if (!pte_file(pte)) { - swp_entry_t entry = pte_to_swp_entry(pte); - - if (likely(!non_swap_entry(entry))) { - if (swap_duplicate(entry) < 0) - return entry.val; - - /* make sure dst_mm is on swapoff's mmlist. */ - if (unlikely(list_empty(&dst_mm->mmlist))) { - spin_lock(&mmlist_lock); - if (list_empty(&dst_mm->mmlist)) - list_add(&dst_mm->mmlist, - &src_mm->mmlist); - spin_unlock(&mmlist_lock); - } - rss[MM_SWAPENTS]++; - } else if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); - - if (PageAnon(page)) - rss[MM_ANONPAGES]++; - else - rss[MM_FILEPAGES]++; - - if (is_write_migration_entry(entry) && - is_cow_mapping(vm_flags)) { - /* - * COW mappings require pages in both - * parent and child to be set to read. - */ - make_migration_entry_read(&entry); - pte = swp_entry_to_pte(entry); - if (pte_swp_soft_dirty(*src_pte)) - pte = pte_swp_mksoft_dirty(pte); - set_pte_at(src_mm, addr, src_pte, pte); - } + swp_entry_t entry = pte_to_swp_entry(pte); + + if (likely(!non_swap_entry(entry))) { + if (swap_duplicate(entry) < 0) + return entry.val; + + /* make sure dst_mm is on swapoff's mmlist. */ + if (unlikely(list_empty(&dst_mm->mmlist))) { + spin_lock(&mmlist_lock); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); + spin_unlock(&mmlist_lock); + } + rss[MM_SWAPENTS]++; + } else if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); + + if (PageAnon(page)) + rss[MM_ANONPAGES]++; + else + rss[MM_FILEPAGES]++; + + if (is_write_migration_entry(entry) && + is_cow_mapping(vm_flags)) { + /* + * COW mappings require pages in both + * parent and child to be set to read. + */ + make_migration_entry_read(&entry); + pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*src_pte)) + pte = pte_swp_mksoft_dirty(pte); + set_pte_at(src_mm, addr, src_pte, pte); } } goto out_set_pte; @@ -1020,11 +1020,9 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ - if (!(vma->vm_flags & (VM_HUGETLB | VM_NONLINEAR | - VM_PFNMAP | VM_MIXEDMAP))) { - if (!vma->anon_vma) - return 0; - } + if (!(vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && + !vma->anon_vma) + return 0; if (is_vm_hugetlb_page(vma)) return copy_hugetlb_page_range(dst_mm, src_mm, vma); @@ -1082,6 +1080,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, spinlock_t *ptl; pte_t *start_pte; pte_t *pte; + swp_entry_t entry; again: init_rss_vec(rss); @@ -1107,28 +1106,12 @@ again: if (details->check_mapping && details->check_mapping != page->mapping) continue; - /* - * Each page->index must be checked when - * invalidating or truncating nonlinear. - */ - if (details->nonlinear_vma && - (page->index < details->first_index || - page->index > details->last_index)) - continue; } ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); if (unlikely(!page)) continue; - if (unlikely(details) && details->nonlinear_vma - && linear_page_index(details->nonlinear_vma, - addr) != page->index) { - pte_t ptfile = pgoff_to_pte(page->index); - if (pte_soft_dirty(ptent)) - ptfile = pte_file_mksoft_dirty(ptfile); - set_pte_at(mm, addr, pte, ptfile); - } if (PageAnon(page)) rss[MM_ANONPAGES]--; else { @@ -1151,33 +1134,25 @@ again: } continue; } - /* - * If details->check_mapping, we leave swap entries; - * if details->nonlinear_vma, we leave file entries. - */ + /* If details->check_mapping, we leave swap entries. */ if (unlikely(details)) continue; - if (pte_file(ptent)) { - if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) - print_bad_pte(vma, addr, ptent, NULL); - } else { - swp_entry_t entry = pte_to_swp_entry(ptent); - if (!non_swap_entry(entry)) - rss[MM_SWAPENTS]--; - else if (is_migration_entry(entry)) { - struct page *page; + entry = pte_to_swp_entry(ptent); + if (!non_swap_entry(entry)) + rss[MM_SWAPENTS]--; + else if (is_migration_entry(entry)) { + struct page *page; - page = migration_entry_to_page(entry); + page = migration_entry_to_page(entry); - if (PageAnon(page)) - rss[MM_ANONPAGES]--; - else - rss[MM_FILEPAGES]--; - } - if (unlikely(!free_swap_and_cache(entry))) - print_bad_pte(vma, addr, ptent, NULL); + if (PageAnon(page)) + rss[MM_ANONPAGES]--; + else + rss[MM_FILEPAGES]--; } + if (unlikely(!free_swap_and_cache(entry))) + print_bad_pte(vma, addr, ptent, NULL); pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, addr != end); @@ -1277,7 +1252,7 @@ static void unmap_page_range(struct mmu_gather *tlb, pgd_t *pgd; unsigned long next; - if (details && !details->check_mapping && !details->nonlinear_vma) + if (details && !details->check_mapping) details = NULL; BUG_ON(addr >= end); @@ -1371,7 +1346,7 @@ void unmap_vmas(struct mmu_gather *tlb, * @vma: vm_area_struct holding the applicable pages * @start: starting address of pages to zap * @size: number of bytes to zap - * @details: details of nonlinear truncation or shared cache invalidation + * @details: details of shared cache invalidation * * Caller must protect the VMA list */ @@ -1397,7 +1372,7 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start, * @vma: vm_area_struct holding the applicable pages * @address: starting address of pages to zap * @size: number of bytes to zap - * @details: details of nonlinear truncation or shared cache invalidation + * @details: details of shared cache invalidation * * The range must fit into one VMA. */ @@ -1922,12 +1897,11 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, EXPORT_SYMBOL_GPL(apply_to_page_range); /* - * handle_pte_fault chooses page fault handler according to an entry - * which was read non-atomically. Before making any commitment, on - * those architectures or configurations (e.g. i386 with PAE) which - * might give a mix of unmatched parts, do_swap_page and do_nonlinear_fault - * must check under lock before unmapping the pte and proceeding - * (but do_wp_page is only called after already making such a check; + * handle_pte_fault chooses page fault handler according to an entry which was + * read non-atomically. Before making any commitment, on those architectures + * or configurations (e.g. i386 with PAE) which might give a mix of unmatched + * parts, do_swap_page must check under lock before unmapping the pte and + * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). */ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, @@ -2033,7 +2007,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, pte_t entry; int ret = 0; int page_mkwrite = 0; - struct page *dirty_page = NULL; + bool dirty_shared = false; unsigned long mmun_start = 0; /* For mmu_notifiers */ unsigned long mmun_end = 0; /* For mmu_notifiers */ struct mem_cgroup *memcg; @@ -2084,6 +2058,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unlock_page(old_page); } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { + page_cache_get(old_page); /* * Only catch write-faults on shared writable pages, * read-only shared pages can get COWed by @@ -2091,7 +2066,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, */ if (vma->vm_ops && vma->vm_ops->page_mkwrite) { int tmp; - page_cache_get(old_page); + pte_unmap_unlock(page_table, ptl); tmp = do_page_mkwrite(vma, old_page, address); if (unlikely(!tmp || (tmp & @@ -2111,11 +2086,10 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unlock_page(old_page); goto unlock; } - page_mkwrite = 1; } - dirty_page = old_page; - get_page(dirty_page); + + dirty_shared = true; reuse: /* @@ -2134,20 +2108,20 @@ reuse: pte_unmap_unlock(page_table, ptl); ret |= VM_FAULT_WRITE; - if (!dirty_page) - return ret; - - if (!page_mkwrite) { + if (dirty_shared) { struct address_space *mapping; int dirtied; - lock_page(dirty_page); - dirtied = set_page_dirty(dirty_page); - VM_BUG_ON_PAGE(PageAnon(dirty_page), dirty_page); - mapping = dirty_page->mapping; - unlock_page(dirty_page); + if (!page_mkwrite) + lock_page(old_page); - if (dirtied && mapping) { + dirtied = set_page_dirty(old_page); + VM_BUG_ON_PAGE(PageAnon(old_page), old_page); + mapping = old_page->mapping; + unlock_page(old_page); + page_cache_release(old_page); + + if ((dirtied || page_mkwrite) && mapping) { /* * Some device drivers do not set page.mapping * but still dirty their pages @@ -2155,25 +2129,9 @@ reuse: balance_dirty_pages_ratelimited(mapping); } - /* file_update_time outside page_lock */ - if (vma->vm_file) + if (!page_mkwrite) file_update_time(vma->vm_file); } - put_page(dirty_page); - if (page_mkwrite) { - struct address_space *mapping = dirty_page->mapping; - - set_page_dirty(dirty_page); - unlock_page(dirty_page); - page_cache_release(dirty_page); - if (mapping) { - /* - * Some device drivers do not set page.mapping - * but still dirty their pages - */ - balance_dirty_pages_ratelimited(mapping); - } - } return ret; } @@ -2331,25 +2289,11 @@ static inline void unmap_mapping_range_tree(struct rb_root *root, } } -static inline void unmap_mapping_range_list(struct list_head *head, - struct zap_details *details) -{ - struct vm_area_struct *vma; - - /* - * In nonlinear VMAs there is no correspondence between virtual address - * offset and file offset. So we must perform an exhaustive search - * across *all* the pages in each nonlinear VMA, not just the pages - * whose virtual address lies outside the file truncation point. - */ - list_for_each_entry(vma, head, shared.nonlinear) { - details->nonlinear_vma = vma; - unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details); - } -} - /** - * unmap_mapping_range - unmap the portion of all mmaps in the specified address_space corresponding to the specified page range in the underlying file. + * unmap_mapping_range - unmap the portion of all mmaps in the specified + * address_space corresponding to the specified page range in the underlying + * file. + * * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE @@ -2378,7 +2322,6 @@ void unmap_mapping_range(struct address_space *mapping, } details.check_mapping = even_cows? NULL: mapping; - details.nonlinear_vma = NULL; details.first_index = hba; details.last_index = hba + hlen - 1; if (details.last_index < details.first_index) @@ -2388,8 +2331,6 @@ void unmap_mapping_range(struct address_space *mapping, i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap))) unmap_mapping_range_tree(&mapping->i_mmap, &details); - if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) - unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details); i_mmap_unlock_write(mapping); } EXPORT_SYMBOL(unmap_mapping_range); @@ -2750,8 +2691,6 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, entry = mk_pte(page, vma->vm_page_prot); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); - else if (pte_file(*pte) && pte_file_soft_dirty(*pte)) - entry = pte_mksoft_dirty(entry); if (anon) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address); @@ -2886,8 +2825,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, * if page by the offset is not ready to be mapped (cold cache or * something). */ - if (vma->vm_ops->map_pages && !(flags & FAULT_FLAG_NONLINEAR) && - fault_around_bytes >> PAGE_SHIFT > 1) { + if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { pte = pte_offset_map_lock(mm, pmd, address, &ptl); do_fault_around(vma, address, pte, pgoff, flags); if (!pte_same(*pte, orig_pte)) @@ -3019,8 +2957,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, balance_dirty_pages_ratelimited(mapping); } - /* file_update_time outside page_lock */ - if (vma->vm_file && !vma->vm_ops->page_mkwrite) + if (!vma->vm_ops->page_mkwrite) file_update_time(vma->vm_file); return ret; @@ -3032,7 +2969,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, * The mmap_sem may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ -static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, +static int do_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, unsigned int flags, pte_t orig_pte) { @@ -3049,46 +2986,6 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); } -/* - * Fault of a previously existing named mapping. Repopulate the pte - * from the encoded file_pte if possible. This enables swappable - * nonlinear vmas. - * - * We enter with non-exclusive mmap_sem (to exclude vma changes, - * but allow concurrent faults), and pte mapped but not yet locked. - * We return with pte unmapped and unlocked. - * The mmap_sem may have been released depending on flags and our - * return value. See filemap_fault() and __lock_page_or_retry(). - */ -static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - unsigned int flags, pte_t orig_pte) -{ - pgoff_t pgoff; - - flags |= FAULT_FLAG_NONLINEAR; - - if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) - return 0; - - if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) { - /* - * Page table corrupted: show pte and kill process. - */ - print_bad_pte(vma, address, orig_pte, NULL); - return VM_FAULT_SIGBUS; - } - - pgoff = pte_to_pgoff(orig_pte); - if (!(flags & FAULT_FLAG_WRITE)) - return do_read_fault(mm, vma, address, pmd, pgoff, flags, - orig_pte); - if (!(vma->vm_flags & VM_SHARED)) - return do_cow_fault(mm, vma, address, pmd, pgoff, flags, - orig_pte); - return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); -} - static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags) @@ -3216,15 +3113,12 @@ static int handle_pte_fault(struct mm_struct *mm, if (pte_none(entry)) { if (vma->vm_ops) { if (likely(vma->vm_ops->fault)) - return do_linear_fault(mm, vma, address, - pte, pmd, flags, entry); + return do_fault(mm, vma, address, pte, + pmd, flags, entry); } return do_anonymous_page(mm, vma, address, pte, pmd, flags); } - if (pte_file(entry)) - return do_nonlinear_fault(mm, vma, address, - pte, pmd, flags, entry); return do_swap_page(mm, vma, address, pte, pmd, flags, entry); } diff --git a/mm/migrate.c b/mm/migrate.c index 344cdf692fc..6e284bcca8b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -179,37 +179,6 @@ out: } /* - * Congratulations to trinity for discovering this bug. - * mm/fremap.c's remap_file_pages() accepts any range within a single vma to - * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then - * replace the specified range by file ptes throughout (maybe populated after). - * If page migration finds a page within that range, while it's still located - * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem: - * zap_pte() clears the temporary migration entry before mmap_sem is dropped. - * But if the migrating page is in a part of the vma outside the range to be - * remapped, then it will not be cleared, and remove_migration_ptes() needs to - * deal with it. Fortunately, this part of the vma is of course still linear, - * so we just need to use linear location on the nonlinear list. - */ -static int remove_linear_migration_ptes_from_nonlinear(struct page *page, - struct address_space *mapping, void *arg) -{ - struct vm_area_struct *vma; - /* hugetlbfs does not support remap_pages, so no huge pgoff worries */ - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - unsigned long addr; - - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); - if (addr >= vma->vm_start && addr < vma->vm_end) - remove_migration_pte(page, vma, addr, arg); - } - return SWAP_AGAIN; -} - -/* * Get rid of all migration entries and replace them by * references to the indicated page. */ @@ -218,7 +187,6 @@ static void remove_migration_ptes(struct page *old, struct page *new) struct rmap_walk_control rwc = { .rmap_one = remove_migration_pte, .arg = old, - .file_nonlinear = remove_linear_migration_ptes_from_nonlinear, }; rmap_walk(new, &rwc); diff --git a/mm/mincore.c b/mm/mincore.c index c8c528b3664..46527c023e0 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -124,17 +124,13 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd, ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); do { pte_t pte = *ptep; - pgoff_t pgoff; next = addr + PAGE_SIZE; if (pte_none(pte)) mincore_unmapped_range(vma, addr, next, vec); else if (pte_present(pte)) *vec = 1; - else if (pte_file(pte)) { - pgoff = pte_to_pgoff(pte); - *vec = mincore_page(vma->vm_file->f_mapping, pgoff); - } else { /* pte is a swap entry */ + else { /* pte is a swap entry */ swp_entry_t entry = pte_to_swp_entry(pte); if (non_swap_entry(entry)) { @@ -145,9 +141,8 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd, *vec = 1; } else { #ifdef CONFIG_SWAP - pgoff = entry.val; *vec = mincore_page(swap_address_space(entry), - pgoff); + entry.val); #else WARN_ON(1); *vec = 1; diff --git a/mm/mmap.c b/mm/mmap.c index 7f684d5a808..14d84666e8b 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -243,10 +243,7 @@ static void __remove_shared_vm_struct(struct vm_area_struct *vma, mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); - if (unlikely(vma->vm_flags & VM_NONLINEAR)) - list_del_init(&vma->shared.nonlinear); - else - vma_interval_tree_remove(vma, &mapping->i_mmap); + vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } @@ -649,10 +646,7 @@ static void __vma_link_file(struct vm_area_struct *vma) atomic_inc(&mapping->i_mmap_writable); flush_dcache_mmap_lock(mapping); - if (unlikely(vma->vm_flags & VM_NONLINEAR)) - vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); - else - vma_interval_tree_insert(vma, &mapping->i_mmap); + vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } } @@ -789,14 +783,11 @@ again: remove_next = 1 + (end > next->vm_end); if (file) { mapping = file->f_mapping; - if (!(vma->vm_flags & VM_NONLINEAR)) { - root = &mapping->i_mmap; - uprobe_munmap(vma, vma->vm_start, vma->vm_end); + root = &mapping->i_mmap; + uprobe_munmap(vma, vma->vm_start, vma->vm_end); - if (adjust_next) - uprobe_munmap(next, next->vm_start, - next->vm_end); - } + if (adjust_next) + uprobe_munmap(next, next->vm_start, next->vm_end); i_mmap_lock_write(mapping); if (insert) { @@ -2634,6 +2625,75 @@ SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) return vm_munmap(addr, len); } + +/* + * Emulation of deprecated remap_file_pages() syscall. + */ +SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, + unsigned long, prot, unsigned long, pgoff, unsigned long, flags) +{ + + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long populate = 0; + unsigned long ret = -EINVAL; + struct file *file; + + pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. " + "See Documentation/vm/remap_file_pages.txt.\n", + current->comm, current->pid); + + if (prot) + return ret; + start = start & PAGE_MASK; + size = size & PAGE_MASK; + + if (start + size <= start) + return ret; + + /* Does pgoff wrap? */ + if (pgoff + (size >> PAGE_SHIFT) < pgoff) + return ret; + + down_write(&mm->mmap_sem); + vma = find_vma(mm, start); + + if (!vma || !(vma->vm_flags & VM_SHARED)) + goto out; + + if (start < vma->vm_start || start + size > vma->vm_end) + goto out; + + if (pgoff == linear_page_index(vma, start)) { + ret = 0; + goto out; + } + + prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; + prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; + prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; + + flags &= MAP_NONBLOCK; + flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; + if (vma->vm_flags & VM_LOCKED) { + flags |= MAP_LOCKED; + /* drop PG_Mlocked flag for over-mapped range */ + munlock_vma_pages_range(vma, start, start + size); + } + + file = get_file(vma->vm_file); + ret = do_mmap_pgoff(vma->vm_file, start, size, + prot, flags, pgoff, &populate); + fput(file); +out: + up_write(&mm->mmap_sem); + if (populate) + mm_populate(ret, populate); + if (!IS_ERR_VALUE(ret)) + ret = 0; + return ret; +} + static inline void verify_mm_writelocked(struct mm_struct *mm) { #ifdef CONFIG_DEBUG_VM @@ -3108,8 +3168,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) * * mmap_sem in write mode is required in order to block all operations * that could modify pagetables and free pages without need of - * altering the vma layout (for example populate_range() with - * nonlinear vmas). It's also needed in write mode to avoid new + * altering the vma layout. It's also needed in write mode to avoid new * anon_vmas to be associated with existing vmas. * * A single task can't take more than one mm_take_all_locks() in a row diff --git a/mm/mprotect.c b/mm/mprotect.c index ace93454ce8..33121662f08 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -105,7 +105,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } if (updated) pages++; - } else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) { + } else if (IS_ENABLED(CONFIG_MIGRATION)) { swp_entry_t entry = pte_to_swp_entry(oldpte); if (is_write_migration_entry(entry)) { diff --git a/mm/mremap.c b/mm/mremap.c index 17fa018f5f3..57dadc025c6 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -81,8 +81,6 @@ static pte_t move_soft_dirty_pte(pte_t pte) pte = pte_mksoft_dirty(pte); else if (is_swap_pte(pte)) pte = pte_swp_mksoft_dirty(pte); - else if (pte_file(pte)) - pte = pte_file_mksoft_dirty(pte); #endif return pte; } diff --git a/mm/msync.c b/mm/msync.c index 992a1673d48..bb04d53ae85 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -86,10 +86,7 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) (vma->vm_flags & VM_SHARED)) { get_file(file); up_read(&mm->mmap_sem); - if (vma->vm_flags & VM_NONLINEAR) - error = vfs_fsync(file, 1); - else - error = vfs_fsync_range(file, fstart, fend, 1); + error = vfs_fsync_range(file, fstart, fend, 1); fput(file); if (error || start >= end) goto out; diff --git a/mm/nommu.c b/mm/nommu.c index b51eadf6d95..541bed64e34 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -59,6 +59,7 @@ #endif void *high_memory; +EXPORT_SYMBOL(high_memory); struct page *mem_map; unsigned long max_mapnr; unsigned long highest_memmap_pfn; @@ -1983,14 +1984,6 @@ void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf) } EXPORT_SYMBOL(filemap_map_pages); -int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, - unsigned long size, pgoff_t pgoff) -{ - BUG(); - return 0; -} -EXPORT_SYMBOL(generic_file_remap_pages); - static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, int write) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8e20f9c2fa5..f121050e853 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -552,17 +552,15 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, return 0; if (page_is_guard(buddy) && page_order(buddy) == order) { - VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); - if (page_zone_id(page) != page_zone_id(buddy)) return 0; + VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + return 1; } if (PageBuddy(buddy) && page_order(buddy) == order) { - VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); - /* * zone check is done late to avoid uselessly * calculating zone/node ids for pages that could @@ -571,6 +569,8 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, if (page_zone_id(page) != page_zone_id(buddy)) return 0; + VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + return 1; } return 0; diff --git a/mm/pagewalk.c b/mm/pagewalk.c index ad83195521f..b264bda46e1 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -199,7 +199,10 @@ int walk_page_range(unsigned long addr, unsigned long end, */ if ((vma->vm_start <= addr) && (vma->vm_flags & VM_PFNMAP)) { - next = vma->vm_end; + if (walk->pte_hole) + err = walk->pte_hole(addr, next, walk); + if (err) + break; pgd = pgd_offset(walk->mm, next); continue; } diff --git a/mm/rmap.c b/mm/rmap.c index 71cd5bd0c17..70b32498d4f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -590,9 +590,8 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; - } else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) { - if (!vma->vm_file || - vma->vm_file->f_mapping != page->mapping) + } else if (page->mapping) { + if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) return -EFAULT; } else return -EFAULT; @@ -1274,7 +1273,6 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); set_pte_at(mm, address, pte, swp_pte); - BUG_ON(pte_file(*pte)); } else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION)) { /* Establish migration entry for a file page */ @@ -1316,211 +1314,6 @@ out_mlock: return ret; } -/* - * objrmap doesn't work for nonlinear VMAs because the assumption that - * offset-into-file correlates with offset-into-virtual-addresses does not hold. - * Consequently, given a particular page and its ->index, we cannot locate the - * ptes which are mapping that page without an exhaustive linear search. - * - * So what this code does is a mini "virtual scan" of each nonlinear VMA which - * maps the file to which the target page belongs. The ->vm_private_data field - * holds the current cursor into that scan. Successive searches will circulate - * around the vma's virtual address space. - * - * So as more replacement pressure is applied to the pages in a nonlinear VMA, - * more scanning pressure is placed against them as well. Eventually pages - * will become fully unmapped and are eligible for eviction. - * - * For very sparsely populated VMAs this is a little inefficient - chances are - * there there won't be many ptes located within the scan cluster. In this case - * maybe we could scan further - to the end of the pte page, perhaps. - * - * Mlocked pages: check VM_LOCKED under mmap_sem held for read, if we can - * acquire it without blocking. If vma locked, mlock the pages in the cluster, - * rather than unmapping them. If we encounter the "check_page" that vmscan is - * trying to unmap, return SWAP_MLOCK, else default SWAP_AGAIN. - */ -#define CLUSTER_SIZE min(32*PAGE_SIZE, PMD_SIZE) -#define CLUSTER_MASK (~(CLUSTER_SIZE - 1)) - -static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, - struct vm_area_struct *vma, struct page *check_page) -{ - struct mm_struct *mm = vma->vm_mm; - pmd_t *pmd; - pte_t *pte; - pte_t pteval; - spinlock_t *ptl; - struct page *page; - unsigned long address; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ - unsigned long end; - int ret = SWAP_AGAIN; - int locked_vma = 0; - - address = (vma->vm_start + cursor) & CLUSTER_MASK; - end = address + CLUSTER_SIZE; - if (address < vma->vm_start) - address = vma->vm_start; - if (end > vma->vm_end) - end = vma->vm_end; - - pmd = mm_find_pmd(mm, address); - if (!pmd) - return ret; - - mmun_start = address; - mmun_end = end; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - - /* - * If we can acquire the mmap_sem for read, and vma is VM_LOCKED, - * keep the sem while scanning the cluster for mlocking pages. - */ - if (down_read_trylock(&vma->vm_mm->mmap_sem)) { - locked_vma = (vma->vm_flags & VM_LOCKED); - if (!locked_vma) - up_read(&vma->vm_mm->mmap_sem); /* don't need it */ - } - - pte = pte_offset_map_lock(mm, pmd, address, &ptl); - - /* Update high watermark before we lower rss */ - update_hiwater_rss(mm); - - for (; address < end; pte++, address += PAGE_SIZE) { - if (!pte_present(*pte)) - continue; - page = vm_normal_page(vma, address, *pte); - BUG_ON(!page || PageAnon(page)); - - if (locked_vma) { - if (page == check_page) { - /* we know we have check_page locked */ - mlock_vma_page(page); - ret = SWAP_MLOCK; - } else if (trylock_page(page)) { - /* - * If we can lock the page, perform mlock. - * Otherwise leave the page alone, it will be - * eventually encountered again later. - */ - mlock_vma_page(page); - unlock_page(page); - } - continue; /* don't unmap */ - } - - /* - * No need for _notify because we're within an - * mmu_notifier_invalidate_range_ {start|end} scope. - */ - if (ptep_clear_flush_young(vma, address, pte)) - continue; - - /* Nuke the page table entry. */ - flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush_notify(vma, address, pte); - - /* If nonlinear, store the file page offset in the pte. */ - if (page->index != linear_page_index(vma, address)) { - pte_t ptfile = pgoff_to_pte(page->index); - if (pte_soft_dirty(pteval)) - ptfile = pte_file_mksoft_dirty(ptfile); - set_pte_at(mm, address, pte, ptfile); - } - - /* Move the dirty bit to the physical page now the pte is gone. */ - if (pte_dirty(pteval)) - set_page_dirty(page); - - page_remove_rmap(page); - page_cache_release(page); - dec_mm_counter(mm, MM_FILEPAGES); - (*mapcount)--; - } - pte_unmap_unlock(pte - 1, ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - if (locked_vma) - up_read(&vma->vm_mm->mmap_sem); - return ret; -} - -static int try_to_unmap_nonlinear(struct page *page, - struct address_space *mapping, void *arg) -{ - struct vm_area_struct *vma; - int ret = SWAP_AGAIN; - unsigned long cursor; - unsigned long max_nl_cursor = 0; - unsigned long max_nl_size = 0; - unsigned int mapcount; - - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - cursor = (unsigned long) vma->vm_private_data; - if (cursor > max_nl_cursor) - max_nl_cursor = cursor; - cursor = vma->vm_end - vma->vm_start; - if (cursor > max_nl_size) - max_nl_size = cursor; - } - - if (max_nl_size == 0) { /* all nonlinears locked or reserved ? */ - return SWAP_FAIL; - } - - /* - * We don't try to search for this page in the nonlinear vmas, - * and page_referenced wouldn't have found it anyway. Instead - * just walk the nonlinear vmas trying to age and unmap some. - * The mapcount of the page we came in with is irrelevant, - * but even so use it as a guide to how hard we should try? - */ - mapcount = page_mapcount(page); - if (!mapcount) - return ret; - - cond_resched(); - - max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK; - if (max_nl_cursor == 0) - max_nl_cursor = CLUSTER_SIZE; - - do { - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - cursor = (unsigned long) vma->vm_private_data; - while (cursor < max_nl_cursor && - cursor < vma->vm_end - vma->vm_start) { - if (try_to_unmap_cluster(cursor, &mapcount, - vma, page) == SWAP_MLOCK) - ret = SWAP_MLOCK; - cursor += CLUSTER_SIZE; - vma->vm_private_data = (void *) cursor; - if ((int)mapcount <= 0) - return ret; - } - vma->vm_private_data = (void *) max_nl_cursor; - } - cond_resched(); - max_nl_cursor += CLUSTER_SIZE; - } while (max_nl_cursor <= max_nl_size); - - /* - * Don't loop forever (perhaps all the remaining pages are - * in locked vmas). Reset cursor on all unreserved nonlinear - * vmas, now forgetting on which ones it had fallen behind. - */ - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.nonlinear) - vma->vm_private_data = NULL; - - return ret; -} - bool is_vma_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); @@ -1566,7 +1359,6 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = page_not_mapped, - .file_nonlinear = try_to_unmap_nonlinear, .anon_lock = page_lock_anon_vma_read, }; @@ -1612,12 +1404,6 @@ int try_to_munlock(struct page *page) .rmap_one = try_to_unmap_one, .arg = (void *)TTU_MUNLOCK, .done = page_not_mapped, - /* - * We don't bother to try to find the munlocked page in - * nonlinears. It's costly. Instead, later, page reclaim logic - * may call try_to_unmap() and recover PG_mlocked lazily. - */ - .file_nonlinear = NULL, .anon_lock = page_lock_anon_vma_read, }; @@ -1748,13 +1534,6 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) goto done; } - if (!rwc->file_nonlinear) - goto done; - - if (list_empty(&mapping->i_mmap_nonlinear)) - goto done; - - ret = rwc->file_nonlinear(page, mapping, rwc->arg); done: i_mmap_unlock_read(mapping); return ret; diff --git a/mm/shmem.c b/mm/shmem.c index 73ba1df7c8b..b3e40318198 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1013,7 +1013,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, */ oldpage = newpage; } else { - mem_cgroup_migrate(oldpage, newpage, false); + mem_cgroup_migrate(oldpage, newpage, true); lru_cache_add_anon(newpage); *pagep = newpage; } @@ -3201,7 +3201,6 @@ static const struct vm_operations_struct shmem_vm_ops = { .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, #endif - .remap_pages = generic_file_remap_pages, }; static struct dentry *shmem_mount(struct file_system_type *fs_type, diff --git a/mm/slab.h b/mm/slab.h index 1cf4005482d..90430d6f665 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -235,7 +235,7 @@ static __always_inline int memcg_charge_slab(struct kmem_cache *s, return 0; if (is_root_cache(s)) return 0; - return __memcg_charge_slab(s, gfp, order); + return memcg_charge_kmem(s->memcg_params->memcg, gfp, 1 << order); } static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order) @@ -244,7 +244,7 @@ static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order) return; if (is_root_cache(s)) return; - __memcg_uncharge_slab(s, order); + memcg_uncharge_kmem(s->memcg_params->memcg, 1 << order); } #else static inline bool is_root_cache(struct kmem_cache *s) diff --git a/mm/slab_common.c b/mm/slab_common.c index e03dd6f2a27..6e1e4cf6583 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -331,7 +331,7 @@ out: out_free_cache: memcg_free_cache_params(s); - kfree(s); + kmem_cache_free(kmem_cache, s); goto out; } @@ -425,21 +425,64 @@ out_unlock: } EXPORT_SYMBOL(kmem_cache_create); +static int do_kmem_cache_shutdown(struct kmem_cache *s, + struct list_head *release, bool *need_rcu_barrier) +{ + if (__kmem_cache_shutdown(s) != 0) { + printk(KERN_ERR "kmem_cache_destroy %s: " + "Slab cache still has objects\n", s->name); + dump_stack(); + return -EBUSY; + } + + if (s->flags & SLAB_DESTROY_BY_RCU) + *need_rcu_barrier = true; + +#ifdef CONFIG_MEMCG_KMEM + if (!is_root_cache(s)) { + struct kmem_cache *root_cache = s->memcg_params->root_cache; + int memcg_id = memcg_cache_id(s->memcg_params->memcg); + + BUG_ON(root_cache->memcg_params->memcg_caches[memcg_id] != s); + root_cache->memcg_params->memcg_caches[memcg_id] = NULL; + } +#endif + list_move(&s->list, release); + return 0; +} + +static void do_kmem_cache_release(struct list_head *release, + bool need_rcu_barrier) +{ + struct kmem_cache *s, *s2; + + if (need_rcu_barrier) + rcu_barrier(); + + list_for_each_entry_safe(s, s2, release, list) { +#ifdef SLAB_SUPPORTS_SYSFS + sysfs_slab_remove(s); +#else + slab_kmem_cache_release(s); +#endif + } +} + #ifdef CONFIG_MEMCG_KMEM /* * memcg_create_kmem_cache - Create a cache for a memory cgroup. * @memcg: The memory cgroup the new cache is for. * @root_cache: The parent of the new cache. - * @memcg_name: The name of the memory cgroup (used for naming the new cache). * * This function attempts to create a kmem cache that will serve allocation * requests going from @memcg to @root_cache. The new cache inherits properties * from its parent. */ -struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, - struct kmem_cache *root_cache, - const char *memcg_name) +void memcg_create_kmem_cache(struct mem_cgroup *memcg, + struct kmem_cache *root_cache) { + static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */ + int memcg_id = memcg_cache_id(memcg); struct kmem_cache *s = NULL; char *cache_name; @@ -448,8 +491,18 @@ struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, mutex_lock(&slab_mutex); + /* + * Since per-memcg caches are created asynchronously on first + * allocation (see memcg_kmem_get_cache()), several threads can try to + * create the same cache, but only one of them may succeed. + */ + if (cache_from_memcg_idx(root_cache, memcg_id)) + goto out_unlock; + + cgroup_name(mem_cgroup_css(memcg)->cgroup, + memcg_name_buf, sizeof(memcg_name_buf)); cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, - memcg_cache_id(memcg), memcg_name); + memcg_cache_id(memcg), memcg_name_buf); if (!cache_name) goto out_unlock; @@ -457,49 +510,73 @@ struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, root_cache->size, root_cache->align, root_cache->flags, root_cache->ctor, memcg, root_cache); + /* + * If we could not create a memcg cache, do not complain, because + * that's not critical at all as we can always proceed with the root + * cache. + */ if (IS_ERR(s)) { kfree(cache_name); - s = NULL; + goto out_unlock; } + /* + * Since readers won't lock (see cache_from_memcg_idx()), we need a + * barrier here to ensure nobody will see the kmem_cache partially + * initialized. + */ + smp_wmb(); + root_cache->memcg_params->memcg_caches[memcg_id] = s; + out_unlock: mutex_unlock(&slab_mutex); put_online_mems(); put_online_cpus(); - - return s; } -static int memcg_cleanup_cache_params(struct kmem_cache *s) +void memcg_destroy_kmem_caches(struct mem_cgroup *memcg) { - int rc; + LIST_HEAD(release); + bool need_rcu_barrier = false; + struct kmem_cache *s, *s2; - if (!s->memcg_params || - !s->memcg_params->is_root_cache) - return 0; + get_online_cpus(); + get_online_mems(); - mutex_unlock(&slab_mutex); - rc = __memcg_cleanup_cache_params(s); mutex_lock(&slab_mutex); + list_for_each_entry_safe(s, s2, &slab_caches, list) { + if (is_root_cache(s) || s->memcg_params->memcg != memcg) + continue; + /* + * The cgroup is about to be freed and therefore has no charges + * left. Hence, all its caches must be empty by now. + */ + BUG_ON(do_kmem_cache_shutdown(s, &release, &need_rcu_barrier)); + } + mutex_unlock(&slab_mutex); - return rc; -} -#else -static int memcg_cleanup_cache_params(struct kmem_cache *s) -{ - return 0; + put_online_mems(); + put_online_cpus(); + + do_kmem_cache_release(&release, need_rcu_barrier); } #endif /* CONFIG_MEMCG_KMEM */ void slab_kmem_cache_release(struct kmem_cache *s) { + memcg_free_cache_params(s); kfree(s->name); kmem_cache_free(kmem_cache, s); } void kmem_cache_destroy(struct kmem_cache *s) { + int i; + LIST_HEAD(release); + bool need_rcu_barrier = false; + bool busy = false; + get_online_cpus(); get_online_mems(); @@ -509,35 +586,23 @@ void kmem_cache_destroy(struct kmem_cache *s) if (s->refcount) goto out_unlock; - if (memcg_cleanup_cache_params(s) != 0) - goto out_unlock; + for_each_memcg_cache_index(i) { + struct kmem_cache *c = cache_from_memcg_idx(s, i); - if (__kmem_cache_shutdown(s) != 0) { - printk(KERN_ERR "kmem_cache_destroy %s: " - "Slab cache still has objects\n", s->name); - dump_stack(); - goto out_unlock; + if (c && do_kmem_cache_shutdown(c, &release, &need_rcu_barrier)) + busy = true; } - list_del(&s->list); - - mutex_unlock(&slab_mutex); - if (s->flags & SLAB_DESTROY_BY_RCU) - rcu_barrier(); - - memcg_free_cache_params(s); -#ifdef SLAB_SUPPORTS_SYSFS - sysfs_slab_remove(s); -#else - slab_kmem_cache_release(s); -#endif - goto out; + if (!busy) + do_kmem_cache_shutdown(s, &release, &need_rcu_barrier); out_unlock: mutex_unlock(&slab_mutex); -out: + put_online_mems(); put_online_cpus(); + + do_kmem_cache_release(&release, need_rcu_barrier); } EXPORT_SYMBOL(kmem_cache_destroy); diff --git a/mm/slub.c b/mm/slub.c index fe376fe1f4f..8b8508adf9c 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2398,13 +2398,24 @@ redo: * reading from one cpu area. That does not matter as long * as we end up on the original cpu again when doing the cmpxchg. * - * Preemption is disabled for the retrieval of the tid because that - * must occur from the current processor. We cannot allow rescheduling - * on a different processor between the determination of the pointer - * and the retrieval of the tid. + * We should guarantee that tid and kmem_cache are retrieved on + * the same cpu. It could be different if CONFIG_PREEMPT so we need + * to check if it is matched or not. */ - preempt_disable(); - c = this_cpu_ptr(s->cpu_slab); + do { + tid = this_cpu_read(s->cpu_slab->tid); + c = raw_cpu_ptr(s->cpu_slab); + } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); + + /* + * Irqless object alloc/free algorithm used here depends on sequence + * of fetching cpu_slab's data. tid should be fetched before anything + * on c to guarantee that object and page associated with previous tid + * won't be used with current tid. If we fetch tid first, object and + * page could be one associated with next tid and our alloc/free + * request will be failed. In this case, we will retry. So, no problem. + */ + barrier(); /* * The transaction ids are globally unique per cpu and per operation on @@ -2412,8 +2423,6 @@ redo: * occurs on the right processor and that there was no operation on the * linked list in between. */ - tid = c->tid; - preempt_enable(); object = c->freelist; page = c->page; @@ -2512,7 +2521,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_trace); #endif /* - * Slow patch handling. This may still be called frequently since objects + * Slow path handling. This may still be called frequently since objects * have a longer lifetime than the cpu slabs in most processing loads. * * So we still attempt to reduce cache line usage. Just take the slab @@ -2659,11 +2668,13 @@ redo: * data is retrieved via this pointer. If we are on the same cpu * during the cmpxchg then the free will succedd. */ - preempt_disable(); - c = this_cpu_ptr(s->cpu_slab); + do { + tid = this_cpu_read(s->cpu_slab->tid); + c = raw_cpu_ptr(s->cpu_slab); + } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); - tid = c->tid; - preempt_enable(); + /* Same with comment on barrier() in slab_alloc_node() */ + barrier(); if (likely(page == c->page)) { set_freepointer(s, object, c->freelist); diff --git a/mm/swap.c b/mm/swap.c index 8a12b33936b..5b3087228b9 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1140,10 +1140,8 @@ void __init swap_setup(void) if (bdi_init(swapper_spaces[0].backing_dev_info)) panic("Failed to init swap bdi"); - for (i = 0; i < MAX_SWAPFILES; i++) { + for (i = 0; i < MAX_SWAPFILES; i++) spin_lock_init(&swapper_spaces[i].tree_lock); - INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear); - } #endif /* Use a smaller cluster for small-memory machines */ diff --git a/mm/vmstat.c b/mm/vmstat.c index 1284f89fca0..9943e5fd74e 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -17,6 +17,9 @@ #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/vmstat.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> #include <linux/sched.h> #include <linux/math64.h> #include <linux/writeback.h> @@ -670,66 +673,6 @@ int fragmentation_index(struct zone *zone, unsigned int order) } #endif -#if defined(CONFIG_PROC_FS) || defined(CONFIG_COMPACTION) -#include <linux/proc_fs.h> -#include <linux/seq_file.h> - -static char * const migratetype_names[MIGRATE_TYPES] = { - "Unmovable", - "Reclaimable", - "Movable", - "Reserve", -#ifdef CONFIG_CMA - "CMA", -#endif -#ifdef CONFIG_MEMORY_ISOLATION - "Isolate", -#endif -}; - -static void *frag_start(struct seq_file *m, loff_t *pos) -{ - pg_data_t *pgdat; - loff_t node = *pos; - for (pgdat = first_online_pgdat(); - pgdat && node; - pgdat = next_online_pgdat(pgdat)) - --node; - - return pgdat; -} - -static void *frag_next(struct seq_file *m, void *arg, loff_t *pos) -{ - pg_data_t *pgdat = (pg_data_t *)arg; - - (*pos)++; - return next_online_pgdat(pgdat); -} - -static void frag_stop(struct seq_file *m, void *arg) -{ -} - -/* Walk all the zones in a node and print using a callback */ -static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, - void (*print)(struct seq_file *m, pg_data_t *, struct zone *)) -{ - struct zone *zone; - struct zone *node_zones = pgdat->node_zones; - unsigned long flags; - - for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { - if (!populated_zone(zone)) - continue; - - spin_lock_irqsave(&zone->lock, flags); - print(m, pgdat, zone); - spin_unlock_irqrestore(&zone->lock, flags); - } -} -#endif - #if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA) #ifdef CONFIG_ZONE_DMA #define TEXT_FOR_DMA(xx) xx "_dma", @@ -907,7 +850,66 @@ const char * const vmstat_text[] = { #endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */ +#if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)) || \ + defined(CONFIG_PROC_FS) +static void *frag_start(struct seq_file *m, loff_t *pos) +{ + pg_data_t *pgdat; + loff_t node = *pos; + + for (pgdat = first_online_pgdat(); + pgdat && node; + pgdat = next_online_pgdat(pgdat)) + --node; + + return pgdat; +} + +static void *frag_next(struct seq_file *m, void *arg, loff_t *pos) +{ + pg_data_t *pgdat = (pg_data_t *)arg; + + (*pos)++; + return next_online_pgdat(pgdat); +} + +static void frag_stop(struct seq_file *m, void *arg) +{ +} + +/* Walk all the zones in a node and print using a callback */ +static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, + void (*print)(struct seq_file *m, pg_data_t *, struct zone *)) +{ + struct zone *zone; + struct zone *node_zones = pgdat->node_zones; + unsigned long flags; + + for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { + if (!populated_zone(zone)) + continue; + + spin_lock_irqsave(&zone->lock, flags); + print(m, pgdat, zone); + spin_unlock_irqrestore(&zone->lock, flags); + } +} +#endif + #ifdef CONFIG_PROC_FS +static char * const migratetype_names[MIGRATE_TYPES] = { + "Unmovable", + "Reclaimable", + "Movable", + "Reserve", +#ifdef CONFIG_CMA + "CMA", +#endif +#ifdef CONFIG_MEMORY_ISOLATION + "Isolate", +#endif +}; + static void frag_show_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) { @@ -1536,8 +1538,6 @@ static int __init setup_vmstat(void) module_init(setup_vmstat) #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION) -#include <linux/debugfs.h> - /* * Return an index indicating how much of the available free memory is diff --git a/samples/Kconfig b/samples/Kconfig index 6181c2cc9ca..224ebb46bed 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -63,4 +63,11 @@ config SAMPLE_RPMSG_CLIENT to communicate with an AMP-configured remote processor over the rpmsg bus. +config SAMPLE_LIVEPATCH + tristate "Build live patching sample -- loadable modules only" + depends on LIVEPATCH && m + help + Builds a sample live patch that replaces the procfs handler + for /proc/cmdline to print "this has been live patched". + endif # SAMPLES diff --git a/samples/Makefile b/samples/Makefile index 1a60c62e204..f00257bcc5a 100644 --- a/samples/Makefile +++ b/samples/Makefile @@ -1,4 +1,4 @@ # Makefile for Linux samples code -obj-$(CONFIG_SAMPLES) += kobject/ kprobes/ trace_events/ \ +obj-$(CONFIG_SAMPLES) += kobject/ kprobes/ trace_events/ livepatch/ \ hw_breakpoint/ kfifo/ kdb/ hidraw/ rpmsg/ seccomp/ diff --git a/samples/livepatch/Makefile b/samples/livepatch/Makefile new file mode 100644 index 00000000000..10319d7ea0b --- /dev/null +++ b/samples/livepatch/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_SAMPLE_LIVEPATCH) += livepatch-sample.o diff --git a/samples/livepatch/livepatch-sample.c b/samples/livepatch/livepatch-sample.c new file mode 100644 index 00000000000..fb8c8614e72 --- /dev/null +++ b/samples/livepatch/livepatch-sample.c @@ -0,0 +1,91 @@ +/* + * livepatch-sample.c - Kernel Live Patching Sample Module + * + * Copyright (C) 2014 Seth Jennings <sjenning@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/livepatch.h> + +/* + * This (dumb) live patch overrides the function that prints the + * kernel boot cmdline when /proc/cmdline is read. + * + * Example: + * + * $ cat /proc/cmdline + * <your cmdline> + * + * $ insmod livepatch-sample.ko + * $ cat /proc/cmdline + * this has been live patched + * + * $ echo 0 > /sys/kernel/livepatch/livepatch_sample/enabled + * $ cat /proc/cmdline + * <your cmdline> + */ + +#include <linux/seq_file.h> +static int livepatch_cmdline_proc_show(struct seq_file *m, void *v) +{ + seq_printf(m, "%s\n", "this has been live patched"); + return 0; +} + +static struct klp_func funcs[] = { + { + .old_name = "cmdline_proc_show", + .new_func = livepatch_cmdline_proc_show, + }, { } +}; + +static struct klp_object objs[] = { + { + /* name being NULL means vmlinux */ + .funcs = funcs, + }, { } +}; + +static struct klp_patch patch = { + .mod = THIS_MODULE, + .objs = objs, +}; + +static int livepatch_init(void) +{ + int ret; + + ret = klp_register_patch(&patch); + if (ret) + return ret; + ret = klp_enable_patch(&patch); + if (ret) { + WARN_ON(klp_unregister_patch(&patch)); + return ret; + } + return 0; +} + +static void livepatch_exit(void) +{ + WARN_ON(klp_disable_patch(&patch)); + WARN_ON(klp_unregister_patch(&patch)); +} + +module_init(livepatch_init); +module_exit(livepatch_exit); +MODULE_LICENSE("GPL"); diff --git a/security/tomoyo/Kconfig b/security/tomoyo/Kconfig index 8eb779b9d77..604e718d68d 100644 --- a/security/tomoyo/Kconfig +++ b/security/tomoyo/Kconfig @@ -5,6 +5,7 @@ config SECURITY_TOMOYO select SECURITYFS select SECURITY_PATH select SECURITY_NETWORK + select SRCU default n help This selects TOMOYO Linux, pathname-based access control. diff --git a/sound/i2c/other/ak4113.c b/sound/i2c/other/ak4113.c index 1a3a6fa2715..c6bba99a90b 100644 --- a/sound/i2c/other/ak4113.c +++ b/sound/i2c/other/ak4113.c @@ -56,8 +56,7 @@ static inline unsigned char reg_read(struct ak4113 *ak4113, unsigned char reg) static void snd_ak4113_free(struct ak4113 *chip) { - chip->init = 1; /* don't schedule new work */ - mb(); + atomic_inc(&chip->wq_processing); /* don't schedule new work */ cancel_delayed_work_sync(&chip->work); kfree(chip); } @@ -89,6 +88,7 @@ int snd_ak4113_create(struct snd_card *card, ak4113_read_t *read, chip->write = write; chip->private_data = private_data; INIT_DELAYED_WORK(&chip->work, ak4113_stats); + atomic_set(&chip->wq_processing, 0); for (reg = 0; reg < AK4113_WRITABLE_REGS ; reg++) chip->regmap[reg] = pgm[reg]; @@ -139,13 +139,11 @@ static void ak4113_init_regs(struct ak4113 *chip) void snd_ak4113_reinit(struct ak4113 *chip) { - chip->init = 1; - mb(); - flush_delayed_work(&chip->work); + if (atomic_inc_return(&chip->wq_processing) == 1) + cancel_delayed_work_sync(&chip->work); ak4113_init_regs(chip); /* bring up statistics / event queing */ - chip->init = 0; - if (chip->kctls[0]) + if (atomic_dec_and_test(&chip->wq_processing)) schedule_delayed_work(&chip->work, HZ / 10); } EXPORT_SYMBOL_GPL(snd_ak4113_reinit); @@ -632,8 +630,9 @@ static void ak4113_stats(struct work_struct *work) { struct ak4113 *chip = container_of(work, struct ak4113, work.work); - if (!chip->init) + if (atomic_inc_return(&chip->wq_processing) == 1) snd_ak4113_check_rate_and_errors(chip, chip->check_flags); - schedule_delayed_work(&chip->work, HZ / 10); + if (atomic_dec_and_test(&chip->wq_processing)) + schedule_delayed_work(&chip->work, HZ / 10); } diff --git a/sound/i2c/other/ak4114.c b/sound/i2c/other/ak4114.c index c7f56339415..b70e6eccbd0 100644 --- a/sound/i2c/other/ak4114.c +++ b/sound/i2c/other/ak4114.c @@ -66,8 +66,7 @@ static void reg_dump(struct ak4114 *ak4114) static void snd_ak4114_free(struct ak4114 *chip) { - chip->init = 1; /* don't schedule new work */ - mb(); + atomic_inc(&chip->wq_processing); /* don't schedule new work */ cancel_delayed_work_sync(&chip->work); kfree(chip); } @@ -100,6 +99,7 @@ int snd_ak4114_create(struct snd_card *card, chip->write = write; chip->private_data = private_data; INIT_DELAYED_WORK(&chip->work, ak4114_stats); + atomic_set(&chip->wq_processing, 0); for (reg = 0; reg < 6; reg++) chip->regmap[reg] = pgm[reg]; @@ -152,13 +152,11 @@ static void ak4114_init_regs(struct ak4114 *chip) void snd_ak4114_reinit(struct ak4114 *chip) { - chip->init = 1; - mb(); - flush_delayed_work(&chip->work); + if (atomic_inc_return(&chip->wq_processing) == 1) + cancel_delayed_work_sync(&chip->work); ak4114_init_regs(chip); /* bring up statistics / event queing */ - chip->init = 0; - if (chip->kctls[0]) + if (atomic_dec_and_test(&chip->wq_processing)) schedule_delayed_work(&chip->work, HZ / 10); } @@ -612,10 +610,10 @@ static void ak4114_stats(struct work_struct *work) { struct ak4114 *chip = container_of(work, struct ak4114, work.work); - if (!chip->init) + if (atomic_inc_return(&chip->wq_processing) == 1) snd_ak4114_check_rate_and_errors(chip, chip->check_flags); - - schedule_delayed_work(&chip->work, HZ / 10); + if (atomic_dec_and_test(&chip->wq_processing)) + schedule_delayed_work(&chip->work, HZ / 10); } EXPORT_SYMBOL(snd_ak4114_create); diff --git a/sound/oss/dmasound/dmasound_atari.c b/sound/oss/dmasound/dmasound_atari.c index 13c214466d3..1c56bf58eff 100644 --- a/sound/oss/dmasound/dmasound_atari.c +++ b/sound/oss/dmasound/dmasound_atari.c @@ -851,7 +851,7 @@ static int __init AtaIrqInit(void) st_mfp.tim_dt_a = 1; /* Cause interrupt after first event. */ st_mfp.tim_ct_a = 8; /* Turn on event counting. */ /* Register interrupt handler. */ - if (request_irq(IRQ_MFP_TIMA, AtaInterrupt, IRQ_TYPE_SLOW, "DMA sound", + if (request_irq(IRQ_MFP_TIMA, AtaInterrupt, 0, "DMA sound", AtaInterrupt)) return 0; st_mfp.int_en_a |= 0x20; /* Turn interrupt on. */ diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c index 99ff35e2a25..35e44e463cf 100644 --- a/sound/soc/atmel/atmel_ssc_dai.c +++ b/sound/soc/atmel/atmel_ssc_dai.c @@ -348,7 +348,6 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, struct atmel_pcm_dma_params *dma_params; int dir, channels, bits; u32 tfmr, rfmr, tcmr, rcmr; - int start_event; int ret; int fslen, fslen_ext; @@ -457,19 +456,10 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, * The SSC transmit clock is obtained from the BCLK signal on * on the TK line, and the SSC receive clock is * generated from the transmit clock. - * - * For single channel data, one sample is transferred - * on the falling edge of the LRC clock. - * For two channel data, one sample is - * transferred on both edges of the LRC clock. */ - start_event = ((channels == 1) - ? SSC_START_FALLING_RF - : SSC_START_EDGE_RF); - rcmr = SSC_BF(RCMR_PERIOD, 0) | SSC_BF(RCMR_STTDLY, START_DELAY) - | SSC_BF(RCMR_START, start_event) + | SSC_BF(RCMR_START, SSC_START_FALLING_RF) | SSC_BF(RCMR_CKI, SSC_CKI_RISING) | SSC_BF(RCMR_CKO, SSC_CKO_NONE) | SSC_BF(RCMR_CKS, ssc->clk_from_rk_pin ? @@ -478,14 +468,14 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, rfmr = SSC_BF(RFMR_FSEDGE, SSC_FSEDGE_POSITIVE) | SSC_BF(RFMR_FSOS, SSC_FSOS_NONE) | SSC_BF(RFMR_FSLEN, 0) - | SSC_BF(RFMR_DATNB, 0) + | SSC_BF(RFMR_DATNB, (channels - 1)) | SSC_BIT(RFMR_MSBF) | SSC_BF(RFMR_LOOP, 0) | SSC_BF(RFMR_DATLEN, (bits - 1)); tcmr = SSC_BF(TCMR_PERIOD, 0) | SSC_BF(TCMR_STTDLY, START_DELAY) - | SSC_BF(TCMR_START, start_event) + | SSC_BF(TCMR_START, SSC_START_FALLING_RF) | SSC_BF(TCMR_CKI, SSC_CKI_FALLING) | SSC_BF(TCMR_CKO, SSC_CKO_NONE) | SSC_BF(TCMR_CKS, ssc->clk_from_rk_pin ? @@ -495,7 +485,7 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, | SSC_BF(TFMR_FSDEN, 0) | SSC_BF(TFMR_FSOS, SSC_FSOS_NONE) | SSC_BF(TFMR_FSLEN, 0) - | SSC_BF(TFMR_DATNB, 0) + | SSC_BF(TFMR_DATNB, (channels - 1)) | SSC_BIT(TFMR_MSBF) | SSC_BF(TFMR_DATDEF, 0) | SSC_BF(TFMR_DATLEN, (bits - 1)); @@ -512,7 +502,7 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, rcmr = SSC_BF(RCMR_PERIOD, ssc_p->rcmr_period) | SSC_BF(RCMR_STTDLY, 1) | SSC_BF(RCMR_START, SSC_START_RISING_RF) - | SSC_BF(RCMR_CKI, SSC_CKI_RISING) + | SSC_BF(RCMR_CKI, SSC_CKI_FALLING) | SSC_BF(RCMR_CKO, SSC_CKO_NONE) | SSC_BF(RCMR_CKS, SSC_CKS_DIV); @@ -527,7 +517,7 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, tcmr = SSC_BF(TCMR_PERIOD, ssc_p->tcmr_period) | SSC_BF(TCMR_STTDLY, 1) | SSC_BF(TCMR_START, SSC_START_RISING_RF) - | SSC_BF(TCMR_CKI, SSC_CKI_RISING) + | SSC_BF(TCMR_CKI, SSC_CKI_FALLING) | SSC_BF(TCMR_CKO, SSC_CKO_CONTINUOUS) | SSC_BF(TCMR_CKS, SSC_CKS_DIV); @@ -556,7 +546,7 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream, rcmr = SSC_BF(RCMR_PERIOD, 0) | SSC_BF(RCMR_STTDLY, START_DELAY) | SSC_BF(RCMR_START, SSC_START_RISING_RF) - | SSC_BF(RCMR_CKI, SSC_CKI_RISING) + | SSC_BF(RCMR_CKI, SSC_CKI_FALLING) | SSC_BF(RCMR_CKO, SSC_CKO_NONE) | SSC_BF(RCMR_CKS, ssc->clk_from_rk_pin ? SSC_CKS_PIN : SSC_CKS_CLOCK); diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c index c3f2decd643..1ff726c2924 100644 --- a/sound/soc/codecs/rt5640.c +++ b/sound/soc/codecs/rt5640.c @@ -2124,6 +2124,7 @@ MODULE_DEVICE_TABLE(of, rt5640_of_match); static struct acpi_device_id rt5640_acpi_match[] = { { "INT33CA", 0 }, { "10EC5640", 0 }, + { "10EC5642", 0 }, { }, }; MODULE_DEVICE_TABLE(acpi, rt5640_acpi_match); diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index 29cf7ce610f..aa98be32bb6 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -483,21 +483,21 @@ static int sgtl5000_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) /* setting i2s data format */ switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { case SND_SOC_DAIFMT_DSP_A: - i2sctl |= SGTL5000_I2S_MODE_PCM; + i2sctl |= SGTL5000_I2S_MODE_PCM << SGTL5000_I2S_MODE_SHIFT; break; case SND_SOC_DAIFMT_DSP_B: - i2sctl |= SGTL5000_I2S_MODE_PCM; + i2sctl |= SGTL5000_I2S_MODE_PCM << SGTL5000_I2S_MODE_SHIFT; i2sctl |= SGTL5000_I2S_LRALIGN; break; case SND_SOC_DAIFMT_I2S: - i2sctl |= SGTL5000_I2S_MODE_I2S_LJ; + i2sctl |= SGTL5000_I2S_MODE_I2S_LJ << SGTL5000_I2S_MODE_SHIFT; break; case SND_SOC_DAIFMT_RIGHT_J: - i2sctl |= SGTL5000_I2S_MODE_RJ; + i2sctl |= SGTL5000_I2S_MODE_RJ << SGTL5000_I2S_MODE_SHIFT; i2sctl |= SGTL5000_I2S_LRPOL; break; case SND_SOC_DAIFMT_LEFT_J: - i2sctl |= SGTL5000_I2S_MODE_I2S_LJ; + i2sctl |= SGTL5000_I2S_MODE_I2S_LJ << SGTL5000_I2S_MODE_SHIFT; i2sctl |= SGTL5000_I2S_LRALIGN; break; default: @@ -1462,6 +1462,9 @@ static int sgtl5000_i2c_probe(struct i2c_client *client, if (ret) return ret; + /* Need 8 clocks before I2C accesses */ + udelay(1); + /* read chip information */ ret = regmap_read(sgtl5000->regmap, SGTL5000_CHIP_ID, ®); if (ret) diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c index b7ebce054b4..dd222b10ce1 100644 --- a/sound/soc/codecs/tlv320aic3x.c +++ b/sound/soc/codecs/tlv320aic3x.c @@ -1046,7 +1046,7 @@ static int aic3x_prepare(struct snd_pcm_substream *substream, delay += aic3x->tdm_delay; /* Configure data delay */ - snd_soc_write(codec, AIC3X_ASD_INTF_CTRLC, aic3x->tdm_delay); + snd_soc_write(codec, AIC3X_ASD_INTF_CTRLC, delay); return 0; } diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c index b9211b42f6e..b115ed815db 100644 --- a/sound/soc/codecs/wm8731.c +++ b/sound/soc/codecs/wm8731.c @@ -717,6 +717,8 @@ static int wm8731_i2c_probe(struct i2c_client *i2c, if (wm8731 == NULL) return -ENOMEM; + mutex_init(&wm8731->lock); + wm8731->regmap = devm_regmap_init_i2c(i2c, &wm8731_regmap); if (IS_ERR(wm8731->regmap)) { ret = PTR_ERR(wm8731->regmap); diff --git a/sound/soc/codecs/wm9705.c b/sound/soc/codecs/wm9705.c index 3eddb18fefd..5cc457ef889 100644 --- a/sound/soc/codecs/wm9705.c +++ b/sound/soc/codecs/wm9705.c @@ -344,23 +344,27 @@ static int wm9705_soc_probe(struct snd_soc_codec *codec) struct snd_ac97 *ac97; int ret = 0; - ac97 = snd_soc_new_ac97_codec(codec); + ac97 = snd_soc_alloc_ac97_codec(codec); if (IS_ERR(ac97)) { ret = PTR_ERR(ac97); dev_err(codec->dev, "Failed to register AC97 codec\n"); return ret; } - snd_soc_codec_set_drvdata(codec, ac97); - ret = wm9705_reset(codec); if (ret) - goto reset_err; + goto err_put_device; + + ret = device_add(&ac97->dev); + if (ret) + goto err_put_device; + + snd_soc_codec_set_drvdata(codec, ac97); return 0; -reset_err: - snd_soc_free_ac97_codec(ac97); +err_put_device: + put_device(&ac97->dev); return ret; } diff --git a/sound/soc/codecs/wm9712.c b/sound/soc/codecs/wm9712.c index e04643d2bb2..9517571e820 100644 --- a/sound/soc/codecs/wm9712.c +++ b/sound/soc/codecs/wm9712.c @@ -666,7 +666,7 @@ static int wm9712_soc_probe(struct snd_soc_codec *codec) struct wm9712_priv *wm9712 = snd_soc_codec_get_drvdata(codec); int ret = 0; - wm9712->ac97 = snd_soc_new_ac97_codec(codec); + wm9712->ac97 = snd_soc_alloc_ac97_codec(codec); if (IS_ERR(wm9712->ac97)) { ret = PTR_ERR(wm9712->ac97); dev_err(codec->dev, "Failed to register AC97 codec: %d\n", ret); @@ -675,15 +675,19 @@ static int wm9712_soc_probe(struct snd_soc_codec *codec) ret = wm9712_reset(codec, 0); if (ret < 0) - goto reset_err; + goto err_put_device; + + ret = device_add(&wm9712->ac97->dev); + if (ret) + goto err_put_device; /* set alc mux to none */ ac97_write(codec, AC97_VIDEO, ac97_read(codec, AC97_VIDEO) | 0x3000); return 0; -reset_err: - snd_soc_free_ac97_codec(wm9712->ac97); +err_put_device: + put_device(&wm9712->ac97->dev); return ret; } diff --git a/sound/soc/codecs/wm9713.c b/sound/soc/codecs/wm9713.c index 71b9d5b0734..6ab1122a387 100644 --- a/sound/soc/codecs/wm9713.c +++ b/sound/soc/codecs/wm9713.c @@ -1225,7 +1225,7 @@ static int wm9713_soc_probe(struct snd_soc_codec *codec) struct wm9713_priv *wm9713 = snd_soc_codec_get_drvdata(codec); int ret = 0, reg; - wm9713->ac97 = snd_soc_new_ac97_codec(codec); + wm9713->ac97 = snd_soc_alloc_ac97_codec(codec); if (IS_ERR(wm9713->ac97)) return PTR_ERR(wm9713->ac97); @@ -1234,7 +1234,11 @@ static int wm9713_soc_probe(struct snd_soc_codec *codec) wm9713_reset(codec, 0); ret = wm9713_reset(codec, 1); if (ret < 0) - goto reset_err; + goto err_put_device; + + ret = device_add(&wm9713->ac97->dev); + if (ret) + goto err_put_device; /* unmute the adc - move to kcontrol */ reg = ac97_read(codec, AC97_CD) & 0x7fff; @@ -1242,8 +1246,8 @@ static int wm9713_soc_probe(struct snd_soc_codec *codec) return 0; -reset_err: - snd_soc_free_ac97_codec(wm9713->ac97); +err_put_device: + put_device(&wm9713->ac97->dev); return ret; } diff --git a/sound/soc/intel/sst-haswell-ipc.c b/sound/soc/intel/sst-haswell-ipc.c index 5bf14040c24..8156cc1accb 100644 --- a/sound/soc/intel/sst-haswell-ipc.c +++ b/sound/soc/intel/sst-haswell-ipc.c @@ -651,11 +651,11 @@ static void hsw_notification_work(struct work_struct *work) } /* tell DSP that notification has been handled */ - sst_dsp_shim_update_bits_unlocked(hsw->dsp, SST_IPCD, + sst_dsp_shim_update_bits(hsw->dsp, SST_IPCD, SST_IPCD_BUSY | SST_IPCD_DONE, SST_IPCD_DONE); /* unmask busy interrupt */ - sst_dsp_shim_update_bits_unlocked(hsw->dsp, SST_IMRX, SST_IMRX_BUSY, 0); + sst_dsp_shim_update_bits(hsw->dsp, SST_IMRX, SST_IMRX_BUSY, 0); } static struct ipc_message *reply_find_msg(struct sst_hsw *hsw, u32 header) diff --git a/sound/soc/intel/sst/sst_acpi.c b/sound/soc/intel/sst/sst_acpi.c index 2ac72eb5e75..b3360139c41 100644 --- a/sound/soc/intel/sst/sst_acpi.c +++ b/sound/soc/intel/sst/sst_acpi.c @@ -350,7 +350,7 @@ static struct sst_machines sst_acpi_bytcr[] = { /* Cherryview-based platforms: CherryTrail and Braswell */ static struct sst_machines sst_acpi_chv[] = { - {"10EC5670", "cht-bsw", "cht-bsw-rt5672", NULL, "fw_sst_22a8.bin", + {"10EC5670", "cht-bsw", "cht-bsw-rt5672", NULL, "intel/fw_sst_22a8.bin", &chv_platform_data }, {}, }; diff --git a/sound/soc/soc-ac97.c b/sound/soc/soc-ac97.c index 2e10e9a3837..08d7259bbaa 100644 --- a/sound/soc/soc-ac97.c +++ b/sound/soc/soc-ac97.c @@ -48,15 +48,18 @@ static void soc_ac97_device_release(struct device *dev) } /** - * snd_soc_new_ac97_codec - initailise AC97 device - * @codec: audio codec + * snd_soc_alloc_ac97_codec() - Allocate new a AC'97 device + * @codec: The CODEC for which to create the AC'97 device * - * Initialises AC97 codec resources for use by ad-hoc devices only. + * Allocated a new snd_ac97 device and intializes it, but does not yet register + * it. The caller is responsible to either call device_add(&ac97->dev) to + * register the device, or to call put_device(&ac97->dev) to free the device. + * + * Returns: A snd_ac97 device or a PTR_ERR in case of an error. */ -struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec) +struct snd_ac97 *snd_soc_alloc_ac97_codec(struct snd_soc_codec *codec) { struct snd_ac97 *ac97; - int ret; ac97 = kzalloc(sizeof(struct snd_ac97), GFP_KERNEL); if (ac97 == NULL) @@ -73,7 +76,28 @@ struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec) codec->component.card->snd_card->number, 0, codec->component.name); - ret = device_register(&ac97->dev); + device_initialize(&ac97->dev); + + return ac97; +} +EXPORT_SYMBOL(snd_soc_alloc_ac97_codec); + +/** + * snd_soc_new_ac97_codec - initailise AC97 device + * @codec: audio codec + * + * Initialises AC97 codec resources for use by ad-hoc devices only. + */ +struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec) +{ + struct snd_ac97 *ac97; + int ret; + + ac97 = snd_soc_alloc_ac97_codec(codec); + if (IS_ERR(ac97)) + return ac97; + + ret = device_add(&ac97->dev); if (ret) { put_device(&ac97->dev); return ERR_PTR(ret); diff --git a/tools/lib/api/fs/debugfs.c b/tools/lib/api/fs/debugfs.c index 86ea2d7b884..d2b18e88707 100644 --- a/tools/lib/api/fs/debugfs.c +++ b/tools/lib/api/fs/debugfs.c @@ -1,3 +1,4 @@ +#define _GNU_SOURCE #include <errno.h> #include <stdio.h> #include <stdlib.h> @@ -98,3 +99,45 @@ char *debugfs_mount(const char *mountpoint) out: return debugfs_mountpoint; } + +int debugfs__strerror_open(int err, char *buf, size_t size, const char *filename) +{ + char sbuf[128]; + + switch (err) { + case ENOENT: + if (debugfs_found) { + snprintf(buf, size, + "Error:\tFile %s/%s not found.\n" + "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n", + debugfs_mountpoint, filename); + break; + } + snprintf(buf, size, "%s", + "Error:\tUnable to find debugfs\n" + "Hint:\tWas your kernel compiled with debugfs support?\n" + "Hint:\tIs the debugfs filesystem mounted?\n" + "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'"); + break; + case EACCES: + snprintf(buf, size, + "Error:\tNo permissions to read %s/%s\n" + "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n", + debugfs_mountpoint, filename, debugfs_mountpoint); + break; + default: + snprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf))); + break; + } + + return 0; +} + +int debugfs__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name) +{ + char path[PATH_MAX]; + + snprintf(path, PATH_MAX, "tracing/events/%s/%s", sys, name ?: "*"); + + return debugfs__strerror_open(err, buf, size, path); +} diff --git a/tools/lib/api/fs/debugfs.h b/tools/lib/api/fs/debugfs.h index f19d3df9609..0739881a989 100644 --- a/tools/lib/api/fs/debugfs.h +++ b/tools/lib/api/fs/debugfs.h @@ -26,4 +26,7 @@ char *debugfs_mount(const char *mountpoint); extern char debugfs_mountpoint[]; +int debugfs__strerror_open(int err, char *buf, size_t size, const char *filename); +int debugfs__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name); + #endif /* __API_DEBUGFS_H__ */ diff --git a/tools/lib/lockdep/.gitignore b/tools/lib/lockdep/.gitignore new file mode 100644 index 00000000000..cc0e7a9f99e --- /dev/null +++ b/tools/lib/lockdep/.gitignore @@ -0,0 +1 @@ +liblockdep.so.* diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile index 52f9279c6c1..4b866c54f62 100644 --- a/tools/lib/lockdep/Makefile +++ b/tools/lib/lockdep/Makefile @@ -104,7 +104,7 @@ N = export Q VERBOSE -INCLUDES = -I. -I/usr/local/include -I./uinclude -I./include -I../../include $(CONFIG_INCLUDES) +INCLUDES = -I. -I./uinclude -I./include -I../../include $(CONFIG_INCLUDES) # Set compile option CFLAGS if not set elsewhere CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index cf3a44bf1ec..afe20ed9fac 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -32,6 +32,7 @@ #include <stdint.h> #include <limits.h> +#include <netinet/ip6.h> #include "event-parse.h" #include "event-utils.h" @@ -4149,6 +4150,324 @@ static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size, trace_seq_printf(s, fmt, buf[0], buf[1], buf[2], buf[3], buf[4], buf[5]); } +static void print_ip4_addr(struct trace_seq *s, char i, unsigned char *buf) +{ + const char *fmt; + + if (i == 'i') + fmt = "%03d.%03d.%03d.%03d"; + else + fmt = "%d.%d.%d.%d"; + + trace_seq_printf(s, fmt, buf[0], buf[1], buf[2], buf[3]); +} + +static inline bool ipv6_addr_v4mapped(const struct in6_addr *a) +{ + return ((unsigned long)(a->s6_addr32[0] | a->s6_addr32[1]) | + (unsigned long)(a->s6_addr32[2] ^ htonl(0x0000ffff))) == 0UL; +} + +static inline bool ipv6_addr_is_isatap(const struct in6_addr *addr) +{ + return (addr->s6_addr32[2] | htonl(0x02000000)) == htonl(0x02005EFE); +} + +static void print_ip6c_addr(struct trace_seq *s, unsigned char *addr) +{ + int i, j, range; + unsigned char zerolength[8]; + int longest = 1; + int colonpos = -1; + uint16_t word; + uint8_t hi, lo; + bool needcolon = false; + bool useIPv4; + struct in6_addr in6; + + memcpy(&in6, addr, sizeof(struct in6_addr)); + + useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6); + + memset(zerolength, 0, sizeof(zerolength)); + + if (useIPv4) + range = 6; + else + range = 8; + + /* find position of longest 0 run */ + for (i = 0; i < range; i++) { + for (j = i; j < range; j++) { + if (in6.s6_addr16[j] != 0) + break; + zerolength[i]++; + } + } + for (i = 0; i < range; i++) { + if (zerolength[i] > longest) { + longest = zerolength[i]; + colonpos = i; + } + } + if (longest == 1) /* don't compress a single 0 */ + colonpos = -1; + + /* emit address */ + for (i = 0; i < range; i++) { + if (i == colonpos) { + if (needcolon || i == 0) + trace_seq_printf(s, ":"); + trace_seq_printf(s, ":"); + needcolon = false; + i += longest - 1; + continue; + } + if (needcolon) { + trace_seq_printf(s, ":"); + needcolon = false; + } + /* hex u16 without leading 0s */ + word = ntohs(in6.s6_addr16[i]); + hi = word >> 8; + lo = word & 0xff; + if (hi) + trace_seq_printf(s, "%x%02x", hi, lo); + else + trace_seq_printf(s, "%x", lo); + + needcolon = true; + } + + if (useIPv4) { + if (needcolon) + trace_seq_printf(s, ":"); + print_ip4_addr(s, 'I', &in6.s6_addr[12]); + } + + return; +} + +static void print_ip6_addr(struct trace_seq *s, char i, unsigned char *buf) +{ + int j; + + for (j = 0; j < 16; j += 2) { + trace_seq_printf(s, "%02x%02x", buf[j], buf[j+1]); + if (i == 'I' && j < 14) + trace_seq_printf(s, ":"); + } +} + +/* + * %pi4 print an IPv4 address with leading zeros + * %pI4 print an IPv4 address without leading zeros + * %pi6 print an IPv6 address without colons + * %pI6 print an IPv6 address with colons + * %pI6c print an IPv6 address in compressed form with colons + * %pISpc print an IP address based on sockaddr; p adds port. + */ +static int print_ipv4_arg(struct trace_seq *s, const char *ptr, char i, + void *data, int size, struct event_format *event, + struct print_arg *arg) +{ + unsigned char *buf; + + if (arg->type == PRINT_FUNC) { + process_defined_func(s, data, size, event, arg); + return 0; + } + + if (arg->type != PRINT_FIELD) { + trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type); + return 0; + } + + if (!arg->field.field) { + arg->field.field = + pevent_find_any_field(event, arg->field.name); + if (!arg->field.field) { + do_warning("%s: field %s not found", + __func__, arg->field.name); + return 0; + } + } + + buf = data + arg->field.field->offset; + + if (arg->field.field->size != 4) { + trace_seq_printf(s, "INVALIDIPv4"); + return 0; + } + print_ip4_addr(s, i, buf); + + return 0; +} + +static int print_ipv6_arg(struct trace_seq *s, const char *ptr, char i, + void *data, int size, struct event_format *event, + struct print_arg *arg) +{ + char have_c = 0; + unsigned char *buf; + int rc = 0; + + /* pI6c */ + if (i == 'I' && *ptr == 'c') { + have_c = 1; + ptr++; + rc++; + } + + if (arg->type == PRINT_FUNC) { + process_defined_func(s, data, size, event, arg); + return rc; + } + + if (arg->type != PRINT_FIELD) { + trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type); + return rc; + } + + if (!arg->field.field) { + arg->field.field = + pevent_find_any_field(event, arg->field.name); + if (!arg->field.field) { + do_warning("%s: field %s not found", + __func__, arg->field.name); + return rc; + } + } + + buf = data + arg->field.field->offset; + + if (arg->field.field->size != 16) { + trace_seq_printf(s, "INVALIDIPv6"); + return rc; + } + + if (have_c) + print_ip6c_addr(s, buf); + else + print_ip6_addr(s, i, buf); + + return rc; +} + +static int print_ipsa_arg(struct trace_seq *s, const char *ptr, char i, + void *data, int size, struct event_format *event, + struct print_arg *arg) +{ + char have_c = 0, have_p = 0; + unsigned char *buf; + struct sockaddr_storage *sa; + int rc = 0; + + /* pISpc */ + if (i == 'I') { + if (*ptr == 'p') { + have_p = 1; + ptr++; + rc++; + } + if (*ptr == 'c') { + have_c = 1; + ptr++; + rc++; + } + } + + if (arg->type == PRINT_FUNC) { + process_defined_func(s, data, size, event, arg); + return rc; + } + + if (arg->type != PRINT_FIELD) { + trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type); + return rc; + } + + if (!arg->field.field) { + arg->field.field = + pevent_find_any_field(event, arg->field.name); + if (!arg->field.field) { + do_warning("%s: field %s not found", + __func__, arg->field.name); + return rc; + } + } + + sa = (struct sockaddr_storage *) (data + arg->field.field->offset); + + if (sa->ss_family == AF_INET) { + struct sockaddr_in *sa4 = (struct sockaddr_in *) sa; + + if (arg->field.field->size < sizeof(struct sockaddr_in)) { + trace_seq_printf(s, "INVALIDIPv4"); + return rc; + } + + print_ip4_addr(s, i, (unsigned char *) &sa4->sin_addr); + if (have_p) + trace_seq_printf(s, ":%d", ntohs(sa4->sin_port)); + + + } else if (sa->ss_family == AF_INET6) { + struct sockaddr_in6 *sa6 = (struct sockaddr_in6 *) sa; + + if (arg->field.field->size < sizeof(struct sockaddr_in6)) { + trace_seq_printf(s, "INVALIDIPv6"); + return rc; + } + + if (have_p) + trace_seq_printf(s, "["); + + buf = (unsigned char *) &sa6->sin6_addr; + if (have_c) + print_ip6c_addr(s, buf); + else + print_ip6_addr(s, i, buf); + + if (have_p) + trace_seq_printf(s, "]:%d", ntohs(sa6->sin6_port)); + } + + return rc; +} + +static int print_ip_arg(struct trace_seq *s, const char *ptr, + void *data, int size, struct event_format *event, + struct print_arg *arg) +{ + char i = *ptr; /* 'i' or 'I' */ + char ver; + int rc = 0; + + ptr++; + rc++; + + ver = *ptr; + ptr++; + rc++; + + switch (ver) { + case '4': + rc += print_ipv4_arg(s, ptr, i, data, size, event, arg); + break; + case '6': + rc += print_ipv6_arg(s, ptr, i, data, size, event, arg); + break; + case 'S': + rc += print_ipsa_arg(s, ptr, i, data, size, event, arg); + break; + default: + return 0; + } + + return rc; +} + static int is_printable_array(char *p, unsigned int len) { unsigned int i; @@ -4337,6 +4656,15 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event ptr++; arg = arg->next; break; + } else if (*(ptr+1) == 'I' || *(ptr+1) == 'i') { + int n; + + n = print_ip_arg(s, ptr+1, data, size, event, arg); + if (n > 0) { + ptr += n; + arg = arg->next; + break; + } } /* fall through */ diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index fd77d81ea74..0294c57b1f5 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -38,7 +38,7 @@ OPTIONS --remove=:: Remove specified file from the cache. -M:: ---missing=:: +--missing=:: List missing build ids in the cache for the specified file. -u:: --update:: diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index cbb4f743d92..3e2aec94f80 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -89,6 +89,19 @@ raw encoding of 0x1A8 can be used: You should refer to the processor specific documentation for getting these details. Some of them are referenced in the SEE ALSO section below. +PARAMETERIZED EVENTS +-------------------- + +Some pmu events listed by 'perf-list' will be displayed with '?' in them. For +example: + + hv_gpci/dtbp_ptitc,phys_processor_idx=?/ + +This means that when provided as an event, a value for '?' must +also be supplied. For example: + + perf stat -C 0 -e 'hv_gpci/dtbp_ptitc,phys_processor_idx=0x2/' ... + OPTIONS ------- diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 1d78a4064da..43310d8661f 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -12,11 +12,12 @@ SYNOPSIS DESCRIPTION ----------- -"perf mem -t <TYPE> record" runs a command and gathers memory operation data +"perf mem record" runs a command and gathers memory operation data from it, into perf.data. Perf record options are accepted and are passed through. -"perf mem -t <TYPE> report" displays the result. It invokes perf report with the -right set of options to display a memory access profile. +"perf mem report" displays the result. It invokes perf report with the +right set of options to display a memory access profile. By default, loads +and stores are sampled. Use the -t option to limit to loads or stores. Note that on Intel systems the memory latency reported is the use-latency, not the pure load (or store latency). Use latency includes any pipeline @@ -29,7 +30,7 @@ OPTIONS -t:: --type=:: - Select the memory operation type: load or store (default: load) + Select the memory operation type: load or store (default: load,store) -D:: --dump-raw-samples=:: diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index af9a54ece02..31e977459c5 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -33,12 +33,27 @@ OPTIONS - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a hexadecimal event descriptor. - - a hardware breakpoint event in the form of '\mem:addr[:access]' + - a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where + 'param1', 'param2', etc are defined as formats for the PMU in + /sys/bus/event_sources/devices/<pmu>/format/*. + + - a symbolically formed event like 'pmu/config=M,config1=N,config3=K/' + + where M, N, K are numbers (in decimal, hex, octal format). Acceptable + values for each of 'config', 'config1' and 'config2' are defined by + corresponding entries in /sys/bus/event_sources/devices/<pmu>/format/* + param1 and param2 are defined as formats for the PMU in: + /sys/bus/event_sources/devices/<pmu>/format/* + + - a hardware breakpoint event in the form of '\mem:addr[/len][:access]' where addr is the address in memory you want to break in. Access is the memory access type (read, write, execute) it can - be passed as follows: '\mem:addr[:[r][w][x]]'. + be passed as follows: '\mem:addr[:[r][w][x]]'. len is the range, + number of bytes from specified addr, which the breakpoint will cover. If you want to profile read-write accesses in 0x1000, just set 'mem:0x1000:rw'. + If you want to profile write accesses in [0x1000~1008), just set + 'mem:0x1000/8:w'. --filter=<filter>:: Event filter. diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 21494806c0a..a21eec05bc4 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -125,46 +125,46 @@ OPTIONS is equivalent to: perf script -f trace:<fields> -f sw:<fields> -f hw:<fields> - + i.e., the specified fields apply to all event types if the type string is not given. - + The arguments are processed in the order received. A later usage can reset a prior request. e.g.: - + -f trace: -f comm,tid,time,ip,sym - + The first -f suppresses trace events (field list is ""), but then the second invocation sets the fields to comm,tid,time,ip,sym. In this case a warning is given to the user: - + "Overriding previous field request for all events." - + Alternatively, consider the order: - + -f comm,tid,time,ip,sym -f trace: - + The first -f sets the fields for all events and the second -f suppresses trace events. The user is given a warning message about the override, and the result of the above is that only S/W and H/W events are displayed with the given fields. - + For the 'wildcard' option if a user selected field is invalid for an event type, a message is displayed to the user that the option is ignored for that type. For example: - + $ perf script -f comm,tid,trace 'trace' not valid for hardware events. Ignoring. 'trace' not valid for software events. Ignoring. - + Alternatively, if the type is given an invalid field is specified it is an error. For example: - + perf script -v -f sw:comm,tid,trace 'trace' not valid for software events. - + At this point usage is displayed, and perf-script exits. - + Finally, a user may not set fields to none for all event types. i.e., -f "" is not allowed. diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 29ee857c09c..04e150d83e7 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -25,10 +25,22 @@ OPTIONS -e:: --event=:: - Select the PMU event. Selection can be a symbolic event name - (use 'perf list' to list all events) or a raw PMU - event (eventsel+umask) in the form of rNNN where NNN is a - hexadecimal event descriptor. + Select the PMU event. Selection can be: + + - a symbolic event name (use 'perf list' to list all events) + + - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a + hexadecimal event descriptor. + + - a symbolically formed event like 'pmu/param1=0x3,param2/' where + param1 and param2 are defined as formats for the PMU in + /sys/bus/event_sources/devices/<pmu>/format/* + + - a symbolically formed event like 'pmu/config=M,config1=N,config2=K/' + where M, N, K are numbers (in decimal, hex, octal format). + Acceptable values for each of 'config', 'config1' and 'config2' + parameters are defined by corresponding entries in + /sys/bus/event_sources/devices/<pmu>/format/* -i:: --no-inherit:: diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h index 71f2844cf97..7ed22ff1e1a 100644 --- a/tools/perf/bench/futex.h +++ b/tools/perf/bench/futex.h @@ -68,4 +68,17 @@ futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wak val, opflags); } +#ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP +#include <pthread.h> +static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr, + size_t cpusetsize, + cpu_set_t *cpuset) +{ + attr = attr; + cpusetsize = cpusetsize; + cpuset = cpuset; + return 0; +} +#endif + #endif /* _FUTEX_H */ diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 77d5cae54c6..50e6b66aea1 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -236,10 +236,10 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused) if (errno == ENOENT) return false; - pr_warning("Problems with %s file, consider removing it from the cache\n", + pr_warning("Problems with %s file, consider removing it from the cache\n", filename); } else if (memcmp(dso->build_id, build_id, sizeof(dso->build_id))) { - pr_warning("Problems with %s file, consider removing it from the cache\n", + pr_warning("Problems with %s file, consider removing it from the cache\n", filename); } diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 1fd96c13f19..74aada554b1 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -390,6 +390,15 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist) } } +static struct data__file *fmt_to_data_file(struct perf_hpp_fmt *fmt) +{ + struct diff_hpp_fmt *dfmt = container_of(fmt, struct diff_hpp_fmt, fmt); + void *ptr = dfmt - dfmt->idx; + struct data__file *d = container_of(ptr, struct data__file, fmt); + + return d; +} + static struct hist_entry* get_pair_data(struct hist_entry *he, struct data__file *d) { @@ -407,8 +416,7 @@ get_pair_data(struct hist_entry *he, struct data__file *d) static struct hist_entry* get_pair_fmt(struct hist_entry *he, struct diff_hpp_fmt *dfmt) { - void *ptr = dfmt - dfmt->idx; - struct data__file *d = container_of(ptr, struct data__file, fmt); + struct data__file *d = fmt_to_data_file(&dfmt->fmt); return get_pair_data(he, d); } @@ -430,7 +438,7 @@ static void hists__baseline_only(struct hists *hists) next = rb_next(&he->rb_node_in); if (!hist_entry__next_pair(he)) { rb_erase(&he->rb_node_in, root); - hist_entry__free(he); + hist_entry__delete(he); } } } @@ -448,26 +456,30 @@ static void hists__precompute(struct hists *hists) next = rb_first(root); while (next != NULL) { struct hist_entry *he, *pair; + struct data__file *d; + int i; he = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&he->rb_node_in); - pair = get_pair_data(he, &data__files[sort_compute]); - if (!pair) - continue; + data__for_each_file_new(i, d) { + pair = get_pair_data(he, d); + if (!pair) + continue; - switch (compute) { - case COMPUTE_DELTA: - compute_delta(he, pair); - break; - case COMPUTE_RATIO: - compute_ratio(he, pair); - break; - case COMPUTE_WEIGHTED_DIFF: - compute_wdiff(he, pair); - break; - default: - BUG_ON(1); + switch (compute) { + case COMPUTE_DELTA: + compute_delta(he, pair); + break; + case COMPUTE_RATIO: + compute_ratio(he, pair); + break; + case COMPUTE_WEIGHTED_DIFF: + compute_wdiff(he, pair); + break; + default: + BUG_ON(1); + } } } } @@ -517,7 +529,7 @@ __hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, static int64_t hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, - int c) + int c, int sort_idx) { bool pairs_left = hist_entry__has_pairs(left); bool pairs_right = hist_entry__has_pairs(right); @@ -529,8 +541,8 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, if (!pairs_left || !pairs_right) return pairs_left ? -1 : 1; - p_left = get_pair_data(left, &data__files[sort_compute]); - p_right = get_pair_data(right, &data__files[sort_compute]); + p_left = get_pair_data(left, &data__files[sort_idx]); + p_right = get_pair_data(right, &data__files[sort_idx]); if (!p_left && !p_right) return 0; @@ -546,90 +558,102 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, } static int64_t -hist_entry__cmp_nop(struct hist_entry *left __maybe_unused, +hist_entry__cmp_compute_idx(struct hist_entry *left, struct hist_entry *right, + int c, int sort_idx) +{ + struct hist_entry *p_right, *p_left; + + p_left = get_pair_data(left, &data__files[sort_idx]); + p_right = get_pair_data(right, &data__files[sort_idx]); + + if (!p_left && !p_right) + return 0; + + if (!p_left || !p_right) + return p_left ? -1 : 1; + + if (c != COMPUTE_DELTA) { + /* + * The delta can be computed without the baseline, but + * others are not. Put those entries which have no + * values below. + */ + if (left->dummy && right->dummy) + return 0; + + if (left->dummy || right->dummy) + return left->dummy ? 1 : -1; + } + + return __hist_entry__cmp_compute(p_left, p_right, c); +} + +static int64_t +hist_entry__cmp_nop(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left __maybe_unused, struct hist_entry *right __maybe_unused) { return 0; } static int64_t -hist_entry__cmp_baseline(struct hist_entry *left, struct hist_entry *right) +hist_entry__cmp_baseline(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) { - if (sort_compute) - return 0; - if (left->stat.period == right->stat.period) return 0; return left->stat.period > right->stat.period ? 1 : -1; } static int64_t -hist_entry__cmp_delta(struct hist_entry *left, struct hist_entry *right) +hist_entry__cmp_delta(struct perf_hpp_fmt *fmt, + struct hist_entry *left, struct hist_entry *right) { - return hist_entry__cmp_compute(right, left, COMPUTE_DELTA); + struct data__file *d = fmt_to_data_file(fmt); + + return hist_entry__cmp_compute(right, left, COMPUTE_DELTA, d->idx); } static int64_t -hist_entry__cmp_ratio(struct hist_entry *left, struct hist_entry *right) +hist_entry__cmp_ratio(struct perf_hpp_fmt *fmt, + struct hist_entry *left, struct hist_entry *right) { - return hist_entry__cmp_compute(right, left, COMPUTE_RATIO); + struct data__file *d = fmt_to_data_file(fmt); + + return hist_entry__cmp_compute(right, left, COMPUTE_RATIO, d->idx); } static int64_t -hist_entry__cmp_wdiff(struct hist_entry *left, struct hist_entry *right) +hist_entry__cmp_wdiff(struct perf_hpp_fmt *fmt, + struct hist_entry *left, struct hist_entry *right) { - return hist_entry__cmp_compute(right, left, COMPUTE_WEIGHTED_DIFF); + struct data__file *d = fmt_to_data_file(fmt); + + return hist_entry__cmp_compute(right, left, COMPUTE_WEIGHTED_DIFF, d->idx); } -static void insert_hist_entry_by_compute(struct rb_root *root, - struct hist_entry *he, - int c) +static int64_t +hist_entry__cmp_delta_idx(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) { - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - struct hist_entry *iter; - - while (*p != NULL) { - parent = *p; - iter = rb_entry(parent, struct hist_entry, rb_node); - if (hist_entry__cmp_compute(he, iter, c) < 0) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, root); + return hist_entry__cmp_compute_idx(right, left, COMPUTE_DELTA, + sort_compute); } -static void hists__compute_resort(struct hists *hists) +static int64_t +hist_entry__cmp_ratio_idx(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) { - struct rb_root *root; - struct rb_node *next; - - if (sort__need_collapse) - root = &hists->entries_collapsed; - else - root = hists->entries_in; - - hists->entries = RB_ROOT; - next = rb_first(root); - - hists__reset_stats(hists); - hists__reset_col_len(hists); - - while (next != NULL) { - struct hist_entry *he; - - he = rb_entry(next, struct hist_entry, rb_node_in); - next = rb_next(&he->rb_node_in); - - insert_hist_entry_by_compute(&hists->entries, he, compute); - hists__inc_stats(hists, he); + return hist_entry__cmp_compute_idx(right, left, COMPUTE_RATIO, + sort_compute); +} - if (!he->filtered) - hists__calc_col_len(hists, he); - } +static int64_t +hist_entry__cmp_wdiff_idx(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) +{ + return hist_entry__cmp_compute_idx(right, left, COMPUTE_WEIGHTED_DIFF, + sort_compute); } static void hists__process(struct hists *hists) @@ -637,12 +661,8 @@ static void hists__process(struct hists *hists) if (show_baseline_only) hists__baseline_only(hists); - if (sort_compute) { - hists__precompute(hists); - hists__compute_resort(hists); - } else { - hists__output_resort(hists, NULL); - } + hists__precompute(hists); + hists__output_resort(hists, NULL); hists__fprintf(hists, true, 0, 0, 0, stdout); } @@ -841,7 +861,7 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt, char pfmt[20] = " "; if (!pair) - goto dummy_print; + goto no_print; switch (comparison_method) { case COMPUTE_DELTA: @@ -850,8 +870,6 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt, else diff = compute_delta(he, pair); - if (fabs(diff) < 0.01) - goto dummy_print; scnprintf(pfmt, 20, "%%%+d.2f%%%%", dfmt->header_width - 1); return percent_color_snprintf(hpp->buf, hpp->size, pfmt, diff); @@ -883,6 +901,9 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt, } dummy_print: return scnprintf(hpp->buf, hpp->size, "%*s", + dfmt->header_width, "N/A"); +no_print: + return scnprintf(hpp->buf, hpp->size, "%*s", dfmt->header_width, pfmt); } @@ -932,14 +953,15 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair, else diff = compute_delta(he, pair); - if (fabs(diff) >= 0.01) - scnprintf(buf, size, "%+4.2F%%", diff); + scnprintf(buf, size, "%+4.2F%%", diff); break; case PERF_HPP_DIFF__RATIO: /* No point for ratio number if we are dummy.. */ - if (he->dummy) + if (he->dummy) { + scnprintf(buf, size, "N/A"); break; + } if (pair->diff.computed) ratio = pair->diff.period_ratio; @@ -952,8 +974,10 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair, case PERF_HPP_DIFF__WEIGHTED_DIFF: /* No point for wdiff number if we are dummy.. */ - if (he->dummy) + if (he->dummy) { + scnprintf(buf, size, "N/A"); break; + } if (pair->diff.computed) wdiff = pair->diff.wdiff; @@ -1105,9 +1129,10 @@ static void data__hpp_register(struct data__file *d, int idx) perf_hpp__register_sort_field(fmt); } -static void ui_init(void) +static int ui_init(void) { struct data__file *d; + struct perf_hpp_fmt *fmt; int i; data__for_each_file(i, d) { @@ -1137,6 +1162,46 @@ static void ui_init(void) data__hpp_register(d, i ? PERF_HPP_DIFF__PERIOD : PERF_HPP_DIFF__PERIOD_BASELINE); } + + if (!sort_compute) + return 0; + + /* + * Prepend an fmt to sort on columns at 'sort_compute' first. + * This fmt is added only to the sort list but not to the + * output fields list. + * + * Note that this column (data) can be compared twice - one + * for this 'sort_compute' fmt and another for the normal + * diff_hpp_fmt. But it shouldn't a problem as most entries + * will be sorted out by first try or baseline and comparing + * is not a costly operation. + */ + fmt = zalloc(sizeof(*fmt)); + if (fmt == NULL) { + pr_err("Memory allocation failed\n"); + return -1; + } + + fmt->cmp = hist_entry__cmp_nop; + fmt->collapse = hist_entry__cmp_nop; + + switch (compute) { + case COMPUTE_DELTA: + fmt->sort = hist_entry__cmp_delta_idx; + break; + case COMPUTE_RATIO: + fmt->sort = hist_entry__cmp_ratio_idx; + break; + case COMPUTE_WEIGHTED_DIFF: + fmt->sort = hist_entry__cmp_wdiff_idx; + break; + default: + BUG_ON(1); + } + + list_add(&fmt->sort_list, &perf_hpp__sort_list); + return 0; } static int data_init(int argc, const char **argv) @@ -1202,7 +1267,8 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) if (data_init(argc, argv) < 0) return -1; - ui_init(); + if (ui_init() < 0) + return -1; sort__mode = SORT_MODE__DIFF; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 84df2deed98..a13641e066f 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -343,6 +343,7 @@ static int __cmd_inject(struct perf_inject *inject) int ret = -EINVAL; struct perf_session *session = inject->session; struct perf_data_file *file_out = &inject->output; + int fd = perf_data_file__fd(file_out); signal(SIGINT, sig_handler); @@ -376,7 +377,7 @@ static int __cmd_inject(struct perf_inject *inject) } if (!file_out->is_pipe) - lseek(file_out->fd, session->header.data_offset, SEEK_SET); + lseek(fd, session->header.data_offset, SEEK_SET); ret = perf_session__process_events(session, &inject->tool); @@ -385,7 +386,7 @@ static int __cmd_inject(struct perf_inject *inject) perf_header__set_feat(&session->header, HEADER_BUILD_ID); session->header.data_size = inject->bytes_written; - perf_session__write_header(session, session->evlist, file_out->fd, true); + perf_session__write_header(session, session->evlist, fd, true); } return ret; diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 24db6ffe295..9b5663950a4 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -7,44 +7,47 @@ #include "util/session.h" #include "util/data.h" -#define MEM_OPERATION_LOAD "load" -#define MEM_OPERATION_STORE "store" - -static const char *mem_operation = MEM_OPERATION_LOAD; +#define MEM_OPERATION_LOAD 0x1 +#define MEM_OPERATION_STORE 0x2 struct perf_mem { struct perf_tool tool; char const *input_name; bool hide_unresolved; bool dump_raw; + int operation; const char *cpu_list; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); }; -static int __cmd_record(int argc, const char **argv) +static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) { int rec_argc, i = 0, j; const char **rec_argv; - char event[64]; int ret; - rec_argc = argc + 4; + rec_argc = argc + 7; /* max number of arguments */ rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (!rec_argv) return -1; - rec_argv[i++] = strdup("record"); - if (!strcmp(mem_operation, MEM_OPERATION_LOAD)) - rec_argv[i++] = strdup("-W"); - rec_argv[i++] = strdup("-d"); - rec_argv[i++] = strdup("-e"); + rec_argv[i++] = "record"; - if (strcmp(mem_operation, MEM_OPERATION_LOAD)) - sprintf(event, "cpu/mem-stores/pp"); - else - sprintf(event, "cpu/mem-loads/pp"); + if (mem->operation & MEM_OPERATION_LOAD) + rec_argv[i++] = "-W"; + + rec_argv[i++] = "-d"; + + if (mem->operation & MEM_OPERATION_LOAD) { + rec_argv[i++] = "-e"; + rec_argv[i++] = "cpu/mem-loads/pp"; + } + + if (mem->operation & MEM_OPERATION_STORE) { + rec_argv[i++] = "-e"; + rec_argv[i++] = "cpu/mem-stores/pp"; + } - rec_argv[i++] = strdup(event); for (j = 1; j < argc; j++, i++) rec_argv[i] = argv[j]; @@ -162,17 +165,17 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem) if (!rep_argv) return -1; - rep_argv[i++] = strdup("report"); - rep_argv[i++] = strdup("--mem-mode"); - rep_argv[i++] = strdup("-n"); /* display number of samples */ + rep_argv[i++] = "report"; + rep_argv[i++] = "--mem-mode"; + rep_argv[i++] = "-n"; /* display number of samples */ /* * there is no weight (cost) associated with stores, so don't print * the column */ - if (strcmp(mem_operation, MEM_OPERATION_LOAD)) - rep_argv[i++] = strdup("--sort=mem,sym,dso,symbol_daddr," - "dso_daddr,tlb,locked"); + if (!(mem->operation & MEM_OPERATION_LOAD)) + rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr," + "dso_daddr,tlb,locked"; for (j = 1; j < argc; j++, i++) rep_argv[i] = argv[j]; @@ -182,6 +185,75 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem) return ret; } +struct mem_mode { + const char *name; + int mode; +}; + +#define MEM_OPT(n, m) \ + { .name = n, .mode = (m) } + +#define MEM_END { .name = NULL } + +static const struct mem_mode mem_modes[]={ + MEM_OPT("load", MEM_OPERATION_LOAD), + MEM_OPT("store", MEM_OPERATION_STORE), + MEM_END +}; + +static int +parse_mem_ops(const struct option *opt, const char *str, int unset) +{ + int *mode = (int *)opt->value; + const struct mem_mode *m; + char *s, *os = NULL, *p; + int ret = -1; + + if (unset) + return 0; + + /* str may be NULL in case no arg is passed to -t */ + if (str) { + /* because str is read-only */ + s = os = strdup(str); + if (!s) + return -1; + + /* reset mode */ + *mode = 0; + + for (;;) { + p = strchr(s, ','); + if (p) + *p = '\0'; + + for (m = mem_modes; m->name; m++) { + if (!strcasecmp(s, m->name)) + break; + } + if (!m->name) { + fprintf(stderr, "unknown sampling op %s," + " check man page\n", s); + goto error; + } + + *mode |= m->mode; + + if (!p) + break; + + s = p + 1; + } + } + ret = 0; + + if (*mode == 0) + *mode = MEM_OPERATION_LOAD; +error: + free(os); + return ret; +} + int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) { struct stat st; @@ -197,10 +269,15 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) .ordered_events = true, }, .input_name = "perf.data", + /* + * default to both load an store sampling + */ + .operation = MEM_OPERATION_LOAD | MEM_OPERATION_STORE, }; const struct option mem_options[] = { - OPT_STRING('t', "type", &mem_operation, - "type", "memory operations(load/store)"), + OPT_CALLBACK('t', "type", &mem.operation, + "type", "memory operations(load,store) Default load,store", + parse_mem_ops), OPT_BOOLEAN('D', "dump-raw-samples", &mem.dump_raw, "dump raw samples in ASCII"), OPT_BOOLEAN('U', "hide-unresolved", &mem.hide_unresolved, @@ -225,7 +302,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands, mem_usage, PARSE_OPT_STOP_AT_NON_OPTION); - if (!argc || !(strncmp(argv[0], "rec", 3) || mem_operation)) + if (!argc || !(strncmp(argv[0], "rec", 3) || mem.operation)) usage_with_options(mem_usage, mem_options); if (!mem.input_name || !strlen(mem.input_name)) { @@ -236,7 +313,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) } if (!strncmp(argv[0], "rec", 3)) - return __cmd_record(argc, argv); + return __cmd_record(argc, argv, &mem); else if (!strncmp(argv[0], "rep", 3)) return report_events(argc, argv, &mem); else diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 8648c6d3003..404ab343405 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -190,16 +190,30 @@ out: return rc; } +static int process_sample_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) +{ + struct record *rec = container_of(tool, struct record, tool); + + rec->samples++; + + return build_id__mark_dso_hit(tool, event, sample, evsel, machine); +} + static int process_buildids(struct record *rec) { struct perf_data_file *file = &rec->file; struct perf_session *session = rec->session; - u64 start = session->header.data_offset; - u64 size = lseek(file->fd, 0, SEEK_CUR); + u64 size = lseek(perf_data_file__fd(file), 0, SEEK_CUR); if (size == 0) return 0; + file->size = size; + /* * During this process, it'll load kernel map and replace the * dso->long_name to a real pathname it found. In this case @@ -211,9 +225,7 @@ static int process_buildids(struct record *rec) */ symbol_conf.ignore_vmlinux_buildid = true; - return __perf_session__process_events(session, start, - size - start, - size, &build_id__mark_dso_hit_ops); + return perf_session__process_events(session, &rec->tool); } static void perf_event__synthesize_guest_os(struct machine *machine, void *data) @@ -322,6 +334,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) struct perf_data_file *file = &rec->file; struct perf_session *session; bool disabled = false, draining = false; + int fd; rec->progname = argv[0]; @@ -336,6 +349,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) return -1; } + fd = perf_data_file__fd(file); rec->session = session; record__init_features(rec); @@ -360,12 +374,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) perf_header__clear_feat(&session->header, HEADER_GROUP_DESC); if (file->is_pipe) { - err = perf_header__write_pipe(file->fd); + err = perf_header__write_pipe(fd); if (err < 0) goto out_child; } else { - err = perf_session__write_header(session, rec->evlist, - file->fd, false); + err = perf_session__write_header(session, rec->evlist, fd, false); if (err < 0) goto out_child; } @@ -397,7 +410,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * return this more properly and also * propagate errors that now are calling die() */ - err = perf_event__synthesize_tracing_data(tool, file->fd, rec->evlist, + err = perf_event__synthesize_tracing_data(tool, fd, rec->evlist, process_synthesized_event); if (err <= 0) { pr_err("Couldn't record tracing data.\n"); @@ -504,19 +517,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) goto out_child; } - if (!quiet) { + if (!quiet) fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking); - /* - * Approximate RIP event size: 24 bytes. - */ - fprintf(stderr, - "[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n", - (double)rec->bytes_written / 1024.0 / 1024.0, - file->path, - rec->bytes_written / 24); - } - out_child: if (forks) { int exit_status; @@ -535,13 +538,29 @@ out_child: } else status = err; + /* this will be recalculated during process_buildids() */ + rec->samples = 0; + if (!err && !file->is_pipe) { rec->session->header.data_size += rec->bytes_written; if (!rec->no_buildid) process_buildids(rec); - perf_session__write_header(rec->session, rec->evlist, - file->fd, true); + perf_session__write_header(rec->session, rec->evlist, fd, true); + } + + if (!err && !quiet) { + char samples[128]; + + if (rec->samples) + scnprintf(samples, sizeof(samples), + " (%" PRIu64 " samples)", rec->samples); + else + samples[0] = '\0'; + + fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s ]\n", + perf_data_file__size(file) / 1024.0 / 1024.0, + file->path, samples); } out_delete_session: @@ -720,6 +739,13 @@ static struct record record = { .default_per_cpu = true, }, }, + .tool = { + .sample = process_sample_event, + .fork = perf_event__process_fork, + .comm = perf_event__process_comm, + .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, + }, }; #define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: " diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 072ae8ad67f..2f91094e228 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -86,17 +86,6 @@ static int report__config(const char *var, const char *value, void *cb) return perf_default_config(var, value, cb); } -static void report__inc_stats(struct report *rep, struct hist_entry *he) -{ - /* - * The @he is either of a newly created one or an existing one - * merging current sample. We only want to count a new one so - * checking ->nr_events being 1. - */ - if (he->stat.nr_events == 1) - rep->nr_entries++; -} - static int hist_iter__report_callback(struct hist_entry_iter *iter, struct addr_location *al, bool single, void *arg) @@ -108,8 +97,6 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter, struct mem_info *mi; struct branch_info *bi; - report__inc_stats(rep, he); - if (!ui__has_annotation()) return 0; @@ -499,6 +486,9 @@ static int __cmd_report(struct report *rep) report__warn_kptr_restrict(rep); + evlist__for_each(session->evlist, pos) + rep->nr_entries += evsel__hists(pos)->nr_entries; + if (use_browser == 0) { if (verbose > 3) perf_session__fprintf(session, stdout); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 89108637638..e598e4e9817 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1730,7 +1730,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) "detailed run - start a lot of events"), OPT_BOOLEAN('S', "sync", &sync_run, "call sync() before starting a run"), - OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, + OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, "print large numbers with thousands\' separators", stat__set_big_num), OPT_STRING('C', "cpu", &target.cpu_list, "cpu", diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 616f0fcb470..c4c7eac69de 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -165,7 +165,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip) err ? "[unknown]" : uts.release, perf_version_string); if (use_browser <= 0) sleep(5); - + map->erange_warned = true; } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index badfabc6a01..7e935f1083e 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -929,66 +929,66 @@ static struct syscall_fmt { .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, }, { .name = "clock_gettime", .errmsg = true, STRARRAY(0, clk_id, clockid), }, { .name = "close", .errmsg = true, - .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, { .name = "connect", .errmsg = true, }, { .name = "dup", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "dup2", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "dup3", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "epoll_ctl", .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), }, { .name = "eventfd2", .errmsg = true, .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, }, { .name = "faccessat", .errmsg = true, .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "fadvise64", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fallocate", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fchdir", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fchmod", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fchmodat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "fchown", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fchownat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "fcntl", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ [1] = SCA_STRARRAY, /* cmd */ }, .arg_parm = { [1] = &strarray__fcntl_cmds, /* cmd */ }, }, { .name = "fdatasync", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "flock", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ [1] = SCA_FLOCK, /* cmd */ }, }, { .name = "fsetxattr", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fstat", .errmsg = true, .alias = "newfstat", - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fstatat", .errmsg = true, .alias = "newfstatat", - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "fstatfs", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "fsync", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "ftruncate", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "futex", .errmsg = true, .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, }, { .name = "futimesat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "getdents", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "getdents64", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "getitimer", .errmsg = true, STRARRAY(0, which, itimers), }, { .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, { .name = "ioctl", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ + .arg_scnprintf = { [0] = SCA_FD, /* fd */ #if defined(__i386__) || defined(__x86_64__) /* * FIXME: Make this available to all arches. @@ -1002,7 +1002,7 @@ static struct syscall_fmt { { .name = "kill", .errmsg = true, .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, { .name = "linkat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "lseek", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ [2] = SCA_STRARRAY, /* whence */ }, @@ -1012,9 +1012,9 @@ static struct syscall_fmt { .arg_scnprintf = { [0] = SCA_HEX, /* start */ [2] = SCA_MADV_BHV, /* behavior */ }, }, { .name = "mkdirat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "mknodat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, { .name = "mlock", .errmsg = true, .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, { .name = "mlockall", .errmsg = true, @@ -1036,9 +1036,9 @@ static struct syscall_fmt { { .name = "munmap", .errmsg = true, .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, { .name = "name_to_handle_at", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "newfstatat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "open", .errmsg = true, .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, }, { .name = "open_by_handle_at", .errmsg = true, @@ -1052,20 +1052,20 @@ static struct syscall_fmt { { .name = "poll", .errmsg = true, .timeout = true, }, { .name = "ppoll", .errmsg = true, .timeout = true, }, { .name = "pread", .errmsg = true, .alias = "pread64", - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "preadv", .errmsg = true, .alias = "pread", - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "prlimit64", .errmsg = true, STRARRAY(1, resource, rlimit_resources), }, { .name = "pwrite", .errmsg = true, .alias = "pwrite64", - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "pwritev", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "read", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "readlinkat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "readv", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "recvfrom", .errmsg = true, .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, { .name = "recvmmsg", .errmsg = true, @@ -1073,7 +1073,7 @@ static struct syscall_fmt { { .name = "recvmsg", .errmsg = true, .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, }, { .name = "renameat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "rt_sigaction", .errmsg = true, .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, }, { .name = "rt_sigprocmask", .errmsg = true, STRARRAY(0, how, sighow), }, @@ -1091,7 +1091,7 @@ static struct syscall_fmt { { .name = "setitimer", .errmsg = true, STRARRAY(0, which, itimers), }, { .name = "setrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, { .name = "shutdown", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "socket", .errmsg = true, .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */ [1] = SCA_SK_TYPE, /* type */ }, @@ -1102,7 +1102,7 @@ static struct syscall_fmt { .arg_parm = { [0] = &strarray__socket_families, /* family */ }, }, { .name = "stat", .errmsg = true, .alias = "newstat", }, { .name = "symlinkat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, { .name = "tgkill", .errmsg = true, .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, }, { .name = "tkill", .errmsg = true, @@ -1113,9 +1113,9 @@ static struct syscall_fmt { { .name = "utimensat", .errmsg = true, .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, }, { .name = "write", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "writev", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, }; static int syscall_fmt__cmp(const void *name, const void *fmtp) @@ -1191,7 +1191,7 @@ static struct thread_trace *thread__trace(struct thread *thread, FILE *fp) if (thread__priv(thread) == NULL) thread__set_priv(thread, thread_trace__new()); - + if (thread__priv(thread) == NULL) goto fail; @@ -2056,23 +2056,24 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (trace->trace_syscalls && perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, trace__sys_exit)) - goto out_error_tp; + goto out_error_raw_syscalls; if (trace->trace_syscalls) perf_evlist__add_vfs_getname(evlist); if ((trace->trace_pgfaults & TRACE_PFMAJ) && - perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ)) - goto out_error_tp; + perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ)) { + goto out_error_mem; + } if ((trace->trace_pgfaults & TRACE_PFMIN) && perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MIN)) - goto out_error_tp; + goto out_error_mem; if (trace->sched && - perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime", - trace__sched_stat_runtime)) - goto out_error_tp; + perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime", + trace__sched_stat_runtime)) + goto out_error_sched_stat_runtime; err = perf_evlist__create_maps(evlist, &trace->opts.target); if (err < 0) { @@ -2202,8 +2203,12 @@ out: { char errbuf[BUFSIZ]; -out_error_tp: - perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf)); +out_error_sched_stat_runtime: + debugfs__strerror_open_tp(errno, errbuf, sizeof(errbuf), "sched", "sched_stat_runtime"); + goto out_error; + +out_error_raw_syscalls: + debugfs__strerror_open_tp(errno, errbuf, sizeof(errbuf), "raw_syscalls", "sys_(enter|exit)"); goto out_error; out_error_mmap: @@ -2217,6 +2222,9 @@ out_error: fprintf(trace->output, "%s\n", errbuf); goto out_delete_evlist; } +out_error_mem: + fprintf(trace->output, "Not enough memory to run!\n"); + goto out_delete_evlist; } static int trace__replay(struct trace *trace) diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 648e31ff402..cc224080b52 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -198,6 +198,7 @@ CORE_FEATURE_TESTS = \ libpython-version \ libslang \ libunwind \ + pthread-attr-setaffinity-np \ stackprotector-all \ timerfd \ libdw-dwarf-unwind \ @@ -226,6 +227,7 @@ VF_FEATURE_TESTS = \ libelf-getphdrnum \ libelf-mmap \ libpython-version \ + pthread-attr-setaffinity-np \ stackprotector-all \ timerfd \ libunwind-debug-frame \ @@ -301,6 +303,10 @@ ifeq ($(feature-sync-compare-and-swap), 1) CFLAGS += -DHAVE_SYNC_COMPARE_AND_SWAP_SUPPORT endif +ifeq ($(feature-pthread-attr-setaffinity-np), 1) + CFLAGS += -DHAVE_PTHREAD_ATTR_SETAFFINITY_NP +endif + ifndef NO_BIONIC $(call feature_check,bionic) ifeq ($(feature-bionic), 1) diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile index 53f19b5dbc3..42ac05aaf8a 100644 --- a/tools/perf/config/feature-checks/Makefile +++ b/tools/perf/config/feature-checks/Makefile @@ -25,6 +25,7 @@ FILES= \ test-libslang.bin \ test-libunwind.bin \ test-libunwind-debug-frame.bin \ + test-pthread-attr-setaffinity-np.bin \ test-stackprotector-all.bin \ test-timerfd.bin \ test-libdw-dwarf-unwind.bin \ @@ -47,6 +48,9 @@ test-all.bin: test-hello.bin: $(BUILD) +test-pthread-attr-setaffinity-np.bin: + $(BUILD) -Werror -lpthread + test-stackprotector-all.bin: $(BUILD) -Werror -fstack-protector-all diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c index 652e0098eba..6d4d0932392 100644 --- a/tools/perf/config/feature-checks/test-all.c +++ b/tools/perf/config/feature-checks/test-all.c @@ -97,6 +97,10 @@ # include "test-zlib.c" #undef main +#define main main_test_pthread_attr_setaffinity_np +# include "test-pthread_attr_setaffinity_np.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -121,6 +125,7 @@ int main(int argc, char *argv[]) main_test_libdw_dwarf_unwind(); main_test_sync_compare_and_swap(argc, argv); main_test_zlib(); + main_test_pthread_attr_setaffinity_np(); return 0; } diff --git a/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c b/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c new file mode 100644 index 00000000000..0a0d3ecb4e8 --- /dev/null +++ b/tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c @@ -0,0 +1,14 @@ +#include <stdint.h> +#include <pthread.h> + +int main(void) +{ + int ret = 0; + pthread_attr_t thread_attr; + + pthread_attr_init(&thread_attr); + /* don't care abt exact args, just the API itself in libpthread */ + ret = pthread_attr_setaffinity_np(&thread_attr, 0, NULL); + + return ret; +} diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index c9b4b6269b5..1091bd47adf 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -104,7 +104,6 @@ class Event(dict): continue if not self.compare_data(self[t], other[t]): log.warning("expected %s=%s, got %s" % (t, self[t], other[t])) - # Test file description needs to have following sections: # [config] diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 8d110dec393..18619966454 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -140,7 +140,7 @@ static void del_hist_entries(struct hists *hists) he = rb_entry(node, struct hist_entry, rb_node); rb_erase(node, root_out); rb_erase(&he->rb_node_in, root_in); - hist_entry__free(he); + hist_entry__delete(he); } } diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index f5547610da0..b52c9faea22 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -106,7 +106,7 @@ static void del_hist_entries(struct hists *hists) he = rb_entry(node, struct hist_entry, rb_node); rb_erase(node, root_out); rb_erase(&he->rb_node_in, root_in); - hist_entry__free(he); + hist_entry__delete(he); } } diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 69a71ff84e0..75709d2b17b 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -222,7 +222,6 @@ tarpkg: @cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \ echo "- $@: $$cmd" && echo $$cmd > $@ && \ ( eval $$cmd ) >> $@ 2>&1 - all: $(run) $(run_O) tarpkg @echo OK diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 7f2f51f9361..1cdab0ce00e 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1145,6 +1145,49 @@ static int test__pinned_group(struct perf_evlist *evlist) return 0; } +static int test__checkevent_breakpoint_len(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config); + TEST_ASSERT_VAL("wrong bp_type", (HW_BREAKPOINT_R | HW_BREAKPOINT_W) == + evsel->attr.bp_type); + TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_1 == + evsel->attr.bp_len); + + return 0; +} + +static int test__checkevent_breakpoint_len_w(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config); + TEST_ASSERT_VAL("wrong bp_type", HW_BREAKPOINT_W == + evsel->attr.bp_type); + TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_2 == + evsel->attr.bp_len); + + return 0; +} + +static int +test__checkevent_breakpoint_len_rw_modifier(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + + return test__checkevent_breakpoint_rw(evlist); +} + static int count_tracepoints(void) { char events_path[PATH_MAX]; @@ -1420,6 +1463,21 @@ static struct evlist_test test__events[] = { .check = test__pinned_group, .id = 41, }, + { + .name = "mem:0/1", + .check = test__checkevent_breakpoint_len, + .id = 42, + }, + { + .name = "mem:0/2:w", + .check = test__checkevent_breakpoint_len_w, + .id = 43, + }, + { + .name = "mem:0/4:rw:u", + .check = test__checkevent_breakpoint_len_rw_modifier, + .id = 44 + }, #if defined(__s390x__) { .name = "kvm-s390:kvm_s390_create_vm", @@ -1471,7 +1529,7 @@ static int test_event(struct evlist_test *e) } else { ret = e->check(evlist); } - + perf_evlist__delete(evlist); return ret; diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 4908c648a59..30c02181e78 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -110,7 +110,7 @@ static bool samples_same(const struct perf_sample *s1, if (type & PERF_SAMPLE_STACK_USER) { COMP(user_stack.size); - if (memcmp(s1->user_stack.data, s1->user_stack.data, + if (memcmp(s1->user_stack.data, s2->user_stack.data, s1->user_stack.size)) { pr_debug("Samples differ at 'user_stack'\n"); return false; diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 1e0a2fd8011..9d32e3c0cfe 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -517,7 +517,7 @@ static bool annotate_browser__jump(struct annotate_browser *browser) } annotate_browser__set_top(browser, dl, idx); - + return true; } @@ -867,7 +867,6 @@ static void annotate_browser__mark_jump_targets(struct annotate_browser *browser ++browser->nr_jumps; } - } static inline int width_jumps(int n) diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 482adae3cc4..25d608394d7 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -285,7 +285,8 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \ } #define __HPP_SORT_FN(_type, _field) \ -static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \ +static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ + struct hist_entry *a, struct hist_entry *b) \ { \ return __hpp__sort(a, b, he_get_##_field); \ } @@ -312,7 +313,8 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \ } #define __HPP_SORT_ACC_FN(_type, _field) \ -static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \ +static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ + struct hist_entry *a, struct hist_entry *b) \ { \ return __hpp__sort_acc(a, b, he_get_acc_##_field); \ } @@ -331,7 +333,8 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \ } #define __HPP_SORT_RAW_FN(_type, _field) \ -static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \ +static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ + struct hist_entry *a, struct hist_entry *b) \ { \ return __hpp__sort(a, b, he_get_raw_##_field); \ } @@ -361,7 +364,8 @@ HPP_PERCENT_ACC_FNS(overhead_acc, period) HPP_RAW_FNS(samples, nr_events) HPP_RAW_FNS(period, period) -static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused, +static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *a __maybe_unused, struct hist_entry *b __maybe_unused) { return 0; diff --git a/tools/perf/ui/progress.h b/tools/perf/ui/progress.h index f34f89eb607..717d39d3052 100644 --- a/tools/perf/ui/progress.h +++ b/tools/perf/ui/progress.h @@ -4,12 +4,12 @@ #include <linux/types.h> void ui_progress__finish(void); - + struct ui_progress { const char *title; u64 curr, next, step, total; }; - + void ui_progress__init(struct ui_progress *p, u64 total, const char *title); void ui_progress__update(struct ui_progress *p, u64 adv); diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c index 1c8b9afd5d6..88f5143a598 100644 --- a/tools/perf/ui/tui/helpline.c +++ b/tools/perf/ui/tui/helpline.c @@ -9,6 +9,7 @@ #include "../libslang.h" char ui_helpline__last_msg[1024]; +bool tui_helpline__set; static void tui_helpline__pop(void) { @@ -35,6 +36,8 @@ static int tui_helpline__show(const char *format, va_list ap) sizeof(ui_helpline__last_msg) - backlog, format, ap); backlog += ret; + tui_helpline__set = true; + if (ui_helpline__last_msg[backlog - 1] == '\n') { ui_helpline__puts(ui_helpline__last_msg); SLsmg_refresh(); diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index 3c38f25b169..b77e1d77136 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -17,6 +17,7 @@ static volatile int ui__need_resize; extern struct perf_error_ops perf_tui_eops; +extern bool tui_helpline__set; extern void hist_browser__init_hpp(void); @@ -159,7 +160,7 @@ out: void ui__exit(bool wait_for_ok) { - if (wait_for_ok) + if (wait_for_ok && tui_helpline__set) ui__question_window("Fatal Error", ui_helpline__last_msg, "Press any key...", 0); diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 01bc4e23a2c..61bf9128e1f 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -239,7 +239,7 @@ static int mov__parse(struct ins_operands *ops) *s = '\0'; ops->source.raw = strdup(ops->raw); *s = ','; - + if (ops->source.raw == NULL) return -1; diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index f4654183d39..55355b3d4f8 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -5,132 +5,6 @@ int perf_use_color_default = -1; -static int parse_color(const char *name, int len) -{ - static const char * const color_names[] = { - "normal", "black", "red", "green", "yellow", - "blue", "magenta", "cyan", "white" - }; - char *end; - int i; - - for (i = 0; i < (int)ARRAY_SIZE(color_names); i++) { - const char *str = color_names[i]; - if (!strncasecmp(name, str, len) && !str[len]) - return i - 1; - } - i = strtol(name, &end, 10); - if (end - name == len && i >= -1 && i <= 255) - return i; - return -2; -} - -static int parse_attr(const char *name, int len) -{ - static const int attr_values[] = { 1, 2, 4, 5, 7 }; - static const char * const attr_names[] = { - "bold", "dim", "ul", "blink", "reverse" - }; - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(attr_names); i++) { - const char *str = attr_names[i]; - if (!strncasecmp(name, str, len) && !str[len]) - return attr_values[i]; - } - return -1; -} - -void color_parse(const char *value, const char *var, char *dst) -{ - color_parse_mem(value, strlen(value), var, dst); -} - -void color_parse_mem(const char *value, int value_len, const char *var, - char *dst) -{ - const char *ptr = value; - int len = value_len; - int attr = -1; - int fg = -2; - int bg = -2; - - if (!strncasecmp(value, "reset", len)) { - strcpy(dst, PERF_COLOR_RESET); - return; - } - - /* [fg [bg]] [attr] */ - while (len > 0) { - const char *word = ptr; - int val, wordlen = 0; - - while (len > 0 && !isspace(word[wordlen])) { - wordlen++; - len--; - } - - ptr = word + wordlen; - while (len > 0 && isspace(*ptr)) { - ptr++; - len--; - } - - val = parse_color(word, wordlen); - if (val >= -1) { - if (fg == -2) { - fg = val; - continue; - } - if (bg == -2) { - bg = val; - continue; - } - goto bad; - } - val = parse_attr(word, wordlen); - if (val < 0 || attr != -1) - goto bad; - attr = val; - } - - if (attr >= 0 || fg >= 0 || bg >= 0) { - int sep = 0; - - *dst++ = '\033'; - *dst++ = '['; - if (attr >= 0) { - *dst++ = '0' + attr; - sep++; - } - if (fg >= 0) { - if (sep++) - *dst++ = ';'; - if (fg < 8) { - *dst++ = '3'; - *dst++ = '0' + fg; - } else { - dst += sprintf(dst, "38;5;%d", fg); - } - } - if (bg >= 0) { - if (sep++) - *dst++ = ';'; - if (bg < 8) { - *dst++ = '4'; - *dst++ = '0' + bg; - } else { - dst += sprintf(dst, "48;5;%d", bg); - } - } - *dst++ = 'm'; - } - *dst = 0; - return; -bad: - die("bad color value '%.*s' for variable '%s'", value_len, value, var); -} - int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty) { if (value) { diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index 0a594b8a0c2..38146f922c5 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -30,8 +30,6 @@ extern int perf_use_color_default; int perf_color_default_config(const char *var, const char *value, void *cb); int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty); -void color_parse(const char *value, const char *var, char *dst); -void color_parse_mem(const char *value, int len, const char *var, char *dst); int color_vsnprintf(char *bf, size_t size, const char *color, const char *fmt, va_list args); int color_vfprintf(FILE *fp, const char *color, const char *fmt, va_list args); diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 45be944d450..c2f7d3b9096 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -532,12 +532,8 @@ dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size) break; cache_offset = offset & DSO__DATA_CACHE_MASK; - ret = -EINVAL; - if (-1 == lseek(dso->data.fd, cache_offset, SEEK_SET)) - break; - - ret = read(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE); + ret = pread(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE, cache_offset); if (ret <= 0) break; diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 3782c82c6e4..ced92841ff9 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -139,6 +139,7 @@ struct dso { u32 status_seen; size_t file_size; struct list_head open_entry; + u64 frame_offset; } data; union { /* Tool specific area */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 2e507b5025a..28b8ce86bf1 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1436,33 +1436,6 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp) return printed + fprintf(fp, "\n"); } -int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused, - int err, char *buf, size_t size) -{ - char sbuf[128]; - - switch (err) { - case ENOENT: - scnprintf(buf, size, "%s", - "Error:\tUnable to find debugfs\n" - "Hint:\tWas your kernel compiled with debugfs support?\n" - "Hint:\tIs the debugfs filesystem mounted?\n" - "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'"); - break; - case EACCES: - scnprintf(buf, size, - "Error:\tNo permissions to read %s/tracing/events/raw_syscalls\n" - "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n", - debugfs_mountpoint, debugfs_mountpoint); - break; - default: - scnprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf))); - break; - } - - return 0; -} - int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused, int err, char *buf, size_t size) { diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 0ba93f67ab9..c94a9e03ecf 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -183,7 +183,6 @@ static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist) size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp); -int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size); int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size); int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 1e90c8557ed..ea51a90e20a 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -709,6 +709,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (opts->sample_weight) perf_evsel__set_sample_bit(evsel, WEIGHT); + attr->task = track; attr->mmap = track; attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; @@ -797,6 +798,9 @@ int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads) int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) { + if (ncpus == 0 || nthreads == 0) + return 0; + if (evsel->system_wide) nthreads = 1; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index b20e40c7446..1f407f7352a 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2237,6 +2237,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz, * - unique number to identify actual perf.data files * - encode endianness of file */ + ph->version = PERF_HEADER_VERSION_2; /* check magic number with one endianness */ if (magic == __perf_magic2) @@ -2247,7 +2248,6 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz, return -1; ph->needs_swap = true; - ph->version = PERF_HEADER_VERSION_2; return 0; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 182395546dd..70b48a65064 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -241,6 +241,20 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) return he->stat.period == 0; } +static void hists__delete_entry(struct hists *hists, struct hist_entry *he) +{ + rb_erase(&he->rb_node, &hists->entries); + + if (sort__need_collapse) + rb_erase(&he->rb_node_in, &hists->entries_collapsed); + + --hists->nr_entries; + if (!he->filtered) + --hists->nr_non_filtered_entries; + + hist_entry__delete(he); +} + void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) { struct rb_node *next = rb_first(&hists->entries); @@ -258,16 +272,7 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel) (zap_kernel && n->level != '.') || hists__decay_entry(hists, n)) && !n->used) { - rb_erase(&n->rb_node, &hists->entries); - - if (sort__need_collapse) - rb_erase(&n->rb_node_in, &hists->entries_collapsed); - - --hists->nr_entries; - if (!n->filtered) - --hists->nr_non_filtered_entries; - - hist_entry__free(n); + hists__delete_entry(hists, n); } } } @@ -281,16 +286,7 @@ void hists__delete_entries(struct hists *hists) n = rb_entry(next, struct hist_entry, rb_node); next = rb_next(&n->rb_node); - rb_erase(&n->rb_node, &hists->entries); - - if (sort__need_collapse) - rb_erase(&n->rb_node_in, &hists->entries_collapsed); - - --hists->nr_entries; - if (!n->filtered) - --hists->nr_non_filtered_entries; - - hist_entry__free(n); + hists__delete_entry(hists, n); } } @@ -433,6 +429,8 @@ static struct hist_entry *add_hist_entry(struct hists *hists, if (!he) return NULL; + hists->nr_entries++; + rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, hists->entries_in); out: @@ -915,7 +913,7 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) if (perf_hpp__should_skip(fmt)) continue; - cmp = fmt->cmp(left, right); + cmp = fmt->cmp(fmt, left, right); if (cmp) break; } @@ -933,7 +931,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) if (perf_hpp__should_skip(fmt)) continue; - cmp = fmt->collapse(left, right); + cmp = fmt->collapse(fmt, left, right); if (cmp) break; } @@ -941,7 +939,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) return cmp; } -void hist_entry__free(struct hist_entry *he) +void hist_entry__delete(struct hist_entry *he) { zfree(&he->branch_info); zfree(&he->mem_info); @@ -981,7 +979,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, iter->callchain, he->callchain); } - hist_entry__free(he); + hist_entry__delete(he); return false; } @@ -1063,7 +1061,7 @@ static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) if (perf_hpp__should_skip(fmt)) continue; - cmp = fmt->sort(a, b); + cmp = fmt->sort(fmt, a, b); if (cmp) break; } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 46bd50344f8..2b690d02890 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -119,7 +119,7 @@ int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); int hist_entry__transaction_len(void); int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size, struct hists *hists); -void hist_entry__free(struct hist_entry *); +void hist_entry__delete(struct hist_entry *he); void hists__output_resort(struct hists *hists, struct ui_progress *prog); void hists__collapse_resort(struct hists *hists, struct ui_progress *prog); @@ -195,9 +195,12 @@ struct perf_hpp_fmt { struct hist_entry *he); int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he); - int64_t (*cmp)(struct hist_entry *a, struct hist_entry *b); - int64_t (*collapse)(struct hist_entry *a, struct hist_entry *b); - int64_t (*sort)(struct hist_entry *a, struct hist_entry *b); + int64_t (*cmp)(struct perf_hpp_fmt *fmt, + struct hist_entry *a, struct hist_entry *b); + int64_t (*collapse)(struct perf_hpp_fmt *fmt, + struct hist_entry *a, struct hist_entry *b); + int64_t (*sort)(struct perf_hpp_fmt *fmt, + struct hist_entry *a, struct hist_entry *b); struct list_head list; struct list_head sort_list; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 77b43fe43d5..7f8ec6ce282 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -526,7 +526,7 @@ do { \ } int parse_events_add_breakpoint(struct list_head *list, int *idx, - void *ptr, char *type) + void *ptr, char *type, u64 len) { struct perf_event_attr attr; @@ -536,14 +536,15 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, if (parse_breakpoint_type(type, &attr)) return -EINVAL; - /* - * We should find a nice way to override the access length - * Provide some defaults for now - */ - if (attr.bp_type == HW_BREAKPOINT_X) - attr.bp_len = sizeof(long); - else - attr.bp_len = HW_BREAKPOINT_LEN_4; + /* Provide some defaults if len is not specified */ + if (!len) { + if (attr.bp_type == HW_BREAKPOINT_X) + len = sizeof(long); + else + len = HW_BREAKPOINT_LEN_4; + } + + attr.bp_len = len; attr.type = PERF_TYPE_BREAKPOINT; attr.sample_period = 1; @@ -1121,7 +1122,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, return; for_each_subsystem(sys_dir, sys_dirent, sys_next) { - if (subsys_glob != NULL && + if (subsys_glob != NULL && !strglobmatch(sys_dirent.d_name, subsys_glob)) continue; @@ -1132,7 +1133,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, continue; for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { - if (event_glob != NULL && + if (event_glob != NULL && !strglobmatch(evt_dirent.d_name, event_glob)) continue; @@ -1305,7 +1306,7 @@ static void print_symbol_events(const char *event_glob, unsigned type, for (i = 0; i < max; i++, syms++) { - if (event_glob != NULL && + if (event_glob != NULL && !(strglobmatch(syms->symbol, event_glob) || (syms->alias && strglobmatch(syms->alias, event_glob)))) continue; @@ -1366,7 +1367,7 @@ void print_events(const char *event_glob, bool name_only) printf("\n"); printf(" %-50s [%s]\n", - "mem:<addr>[:access]", + "mem:<addr>[/len][:access]", event_type_descriptors[PERF_TYPE_BREAKPOINT]); printf("\n"); } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index db2cf78ff0f..ff6e1fa4111 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -71,6 +71,7 @@ struct parse_events_term { int type_val; int type_term; struct list_head list; + bool used; }; struct parse_events_evlist { @@ -104,7 +105,7 @@ int parse_events_add_numeric(struct list_head *list, int *idx, int parse_events_add_cache(struct list_head *list, int *idx, char *type, char *op_result1, char *op_result2); int parse_events_add_breakpoint(struct list_head *list, int *idx, - void *ptr, char *type); + void *ptr, char *type, u64 len); int parse_events_add_pmu(struct list_head *list, int *idx, char *pmu , struct list_head *head_config); enum perf_pmu_event_symbol_type diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 906630bbf8e..94eacb6c1ef 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -159,6 +159,7 @@ branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE <mem>{ {modifier_bp} { return str(yyscanner, PE_MODIFIER_BP); } : { return ':'; } +"/" { return '/'; } {num_dec} { return value(yyscanner, 10); } {num_hex} { return value(yyscanner, 16); } /* diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 93c4c9fbc92..72def077dbb 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -326,6 +326,28 @@ PE_NAME_CACHE_TYPE } event_legacy_mem: +PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_breakpoint(list, &data->idx, + (void *) $2, $6, $4)); + $$ = list; +} +| +PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc +{ + struct parse_events_evlist *data = _data; + struct list_head *list; + + ALLOC_LIST(list); + ABORT_ON(parse_events_add_breakpoint(list, &data->idx, + (void *) $2, NULL, $4)); + $$ = list; +} +| PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc { struct parse_events_evlist *data = _data; @@ -333,7 +355,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc ALLOC_LIST(list); ABORT_ON(parse_events_add_breakpoint(list, &data->idx, - (void *) $2, $4)); + (void *) $2, $4, 0)); $$ = list; } | @@ -344,7 +366,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc ALLOC_LIST(list); ABORT_ON(parse_events_add_breakpoint(list, &data->idx, - (void *) $2, NULL)); + (void *) $2, NULL, 0)); $$ = list; } diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index f62dee7bd92..4a015f77e2b 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -46,7 +46,7 @@ static int get_value(struct parse_opt_ctx_t *p, return opterror(opt, "is not usable", flags); if (opt->flags & PARSE_OPT_EXCLUSIVE) { - if (p->excl_opt) { + if (p->excl_opt && p->excl_opt != opt) { char msg[128]; if (((flags & OPT_SHORT) && p->excl_opt->short_name) || diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 5c9c4947cfb..48411674da0 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -551,31 +551,68 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v, } /* + * Term is a string term, and might be a param-term. Try to look up it's value + * in the remaining terms. + * - We have a term like "base-or-format-term=param-term", + * - We need to find the value supplied for "param-term" (with param-term named + * in a config string) later on in the term list. + */ +static int pmu_resolve_param_term(struct parse_events_term *term, + struct list_head *head_terms, + __u64 *value) +{ + struct parse_events_term *t; + + list_for_each_entry(t, head_terms, list) { + if (t->type_val == PARSE_EVENTS__TERM_TYPE_NUM) { + if (!strcmp(t->config, term->config)) { + t->used = true; + *value = t->val.num; + return 0; + } + } + } + + if (verbose) + printf("Required parameter '%s' not specified\n", term->config); + + return -1; +} + +/* * Setup one of config[12] attr members based on the * user input data - term parameter. */ static int pmu_config_term(struct list_head *formats, struct perf_event_attr *attr, struct parse_events_term *term, + struct list_head *head_terms, bool zero) { struct perf_pmu_format *format; __u64 *vp; + __u64 val; + + /* + * If this is a parameter we've already used for parameterized-eval, + * skip it in normal eval. + */ + if (term->used) + return 0; /* - * Support only for hardcoded and numnerial terms. * Hardcoded terms should be already in, so nothing * to be done for them. */ if (parse_events__is_hardcoded_term(term)) return 0; - if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) - return -EINVAL; - format = pmu_find_format(formats, term->config); - if (!format) + if (!format) { + if (verbose) + printf("Invalid event/parameter '%s'\n", term->config); return -EINVAL; + } switch (format->value) { case PERF_PMU_FORMAT_VALUE_CONFIG: @@ -592,11 +629,25 @@ static int pmu_config_term(struct list_head *formats, } /* - * XXX If we ever decide to go with string values for - * non-hardcoded terms, here's the place to translate - * them into value. + * Either directly use a numeric term, or try to translate string terms + * using event parameters. */ - pmu_format_value(format->bits, term->val.num, vp, zero); + if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) + val = term->val.num; + else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) { + if (strcmp(term->val.str, "?")) { + if (verbose) + pr_info("Invalid sysfs entry %s=%s\n", + term->config, term->val.str); + return -EINVAL; + } + + if (pmu_resolve_param_term(term, head_terms, &val)) + return -EINVAL; + } else + return -EINVAL; + + pmu_format_value(format->bits, val, vp, zero); return 0; } @@ -607,9 +658,10 @@ int perf_pmu__config_terms(struct list_head *formats, { struct parse_events_term *term; - list_for_each_entry(term, head_terms, list) - if (pmu_config_term(formats, attr, term, zero)) + list_for_each_entry(term, head_terms, list) { + if (pmu_config_term(formats, attr, term, head_terms, zero)) return -EINVAL; + } return 0; } @@ -767,10 +819,36 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to) set_bit(b, bits); } +static int sub_non_neg(int a, int b) +{ + if (b > a) + return 0; + return a - b; +} + static char *format_alias(char *buf, int len, struct perf_pmu *pmu, struct perf_pmu_alias *alias) { - snprintf(buf, len, "%s/%s/", pmu->name, alias->name); + struct parse_events_term *term; + int used = snprintf(buf, len, "%s/%s", pmu->name, alias->name); + + list_for_each_entry(term, &alias->terms, list) { + if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) + used += snprintf(buf + used, sub_non_neg(len, used), + ",%s=%s", term->config, + term->val.str); + } + + if (sub_non_neg(len, used) > 0) { + buf[used] = '/'; + used++; + } + if (sub_non_neg(len, used) > 0) { + buf[used] = '\0'; + used++; + } else + buf[len - 1] = '\0'; + return buf; } diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 3dda85ca50c..d906d0ad5d4 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -768,7 +768,7 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, Py_DECREF(file); goto free_list; } - + Py_DECREF(file); } diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index d808a328f4d..0c815a40a6e 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -89,7 +89,7 @@ static void handler_call_die(const char *handler_name) /* * Insert val into into the dictionary and decrement the reference counter. - * This is necessary for dictionaries since PyDict_SetItemString() does not + * This is necessary for dictionaries since PyDict_SetItemString() does not * steal a reference, as opposed to PyTuple_SetItem(). */ static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObject *val) diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 5f0e05a76c0..0baf75f12b7 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -274,7 +274,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool) if (tool->id_index == NULL) tool->id_index = process_id_index_stub; } - + static void swap_sample_id_all(union perf_event *event, void *data) { void *end = (void *) event + event->header.size; @@ -1251,9 +1251,9 @@ fetch_mmaped_event(struct perf_session *session, #define NUM_MMAPS 128 #endif -int __perf_session__process_events(struct perf_session *session, - u64 data_offset, u64 data_size, - u64 file_size, struct perf_tool *tool) +static int __perf_session__process_events(struct perf_session *session, + u64 data_offset, u64 data_size, + u64 file_size, struct perf_tool *tool) { int fd = perf_data_file__fd(session->file); u64 head, page_offset, file_offset, file_pos, size; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index dc26ebf60fe..6d663dc7640 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -49,9 +49,6 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset, union perf_event **event_ptr, struct perf_sample *sample); -int __perf_session__process_events(struct perf_session *session, - u64 data_offset, u64 data_size, u64 size, - struct perf_tool *tool); int perf_session__process_events(struct perf_session *session, struct perf_tool *tool); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 9139dda9f9a..7a39c1ed8d3 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1304,6 +1304,37 @@ static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, return hse->se->se_snprintf(he, hpp->buf, hpp->size, len); } +static int64_t __sort__hpp_cmp(struct perf_hpp_fmt *fmt, + struct hist_entry *a, struct hist_entry *b) +{ + struct hpp_sort_entry *hse; + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + return hse->se->se_cmp(a, b); +} + +static int64_t __sort__hpp_collapse(struct perf_hpp_fmt *fmt, + struct hist_entry *a, struct hist_entry *b) +{ + struct hpp_sort_entry *hse; + int64_t (*collapse_fn)(struct hist_entry *, struct hist_entry *); + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + collapse_fn = hse->se->se_collapse ?: hse->se->se_cmp; + return collapse_fn(a, b); +} + +static int64_t __sort__hpp_sort(struct perf_hpp_fmt *fmt, + struct hist_entry *a, struct hist_entry *b) +{ + struct hpp_sort_entry *hse; + int64_t (*sort_fn)(struct hist_entry *, struct hist_entry *); + + hse = container_of(fmt, struct hpp_sort_entry, hpp); + sort_fn = hse->se->se_sort ?: hse->se->se_cmp; + return sort_fn(a, b); +} + static struct hpp_sort_entry * __sort_dimension__alloc_hpp(struct sort_dimension *sd) { @@ -1322,9 +1353,9 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd) hse->hpp.entry = __sort__hpp_entry; hse->hpp.color = NULL; - hse->hpp.cmp = sd->entry->se_cmp; - hse->hpp.collapse = sd->entry->se_collapse ? : sd->entry->se_cmp; - hse->hpp.sort = sd->entry->se_sort ? : hse->hpp.collapse; + hse->hpp.cmp = __sort__hpp_cmp; + hse->hpp.collapse = __sort__hpp_collapse; + hse->hpp.sort = __sort__hpp_sort; INIT_LIST_HEAD(&hse->hpp.list); INIT_LIST_HEAD(&hse->hpp.sort_list); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 06fcd1bf98b..b24f9d8727a 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -574,13 +574,16 @@ static int decompress_kmodule(struct dso *dso, const char *name, const char *ext = strrchr(name, '.'); char tmpbuf[] = "/tmp/perf-kmod-XXXXXX"; - if ((type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP && - type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP) || - type != dso->symtab_type) + if (type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP && + type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP && + type != DSO_BINARY_TYPE__BUILD_ID_CACHE) return -1; - if (!ext || !is_supported_compression(ext + 1)) - return -1; + if (!ext || !is_supported_compression(ext + 1)) { + ext = strrchr(dso->name, '.'); + if (!ext || !is_supported_compression(ext + 1)) + return -1; + } fd = mkstemp(tmpbuf); if (fd < 0) diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index a194702a0a2..a69066865a5 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -685,7 +685,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta, struct machine *machine = kmaps->machine; struct map *curr_map = map; struct symbol *pos; - int count = 0, moved = 0; + int count = 0, moved = 0; struct rb_root *root = &dso->symbols[map->type]; struct rb_node *next = rb_first(root); int kernel_range = 0; diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 6edf535f65c..e3c40a520a2 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -266,14 +266,17 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine, u64 *fde_count) { int ret = -EINVAL, fd; - u64 offset; + u64 offset = dso->data.frame_offset; - fd = dso__data_fd(dso, machine); - if (fd < 0) - return -EINVAL; + if (offset == 0) { + fd = dso__data_fd(dso, machine); + if (fd < 0) + return -EINVAL; - /* Check the .eh_frame section for unwinding info */ - offset = elf_section_offset(fd, ".eh_frame_hdr"); + /* Check the .eh_frame section for unwinding info */ + offset = elf_section_offset(fd, ".eh_frame_hdr"); + dso->data.frame_offset = offset; + } if (offset) ret = unwind_spec_ehframe(dso, machine, offset, @@ -287,14 +290,20 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine, static int read_unwind_spec_debug_frame(struct dso *dso, struct machine *machine, u64 *offset) { - int fd = dso__data_fd(dso, machine); + int fd; + u64 ofs = dso->data.frame_offset; - if (fd < 0) - return -EINVAL; + if (ofs == 0) { + fd = dso__data_fd(dso, machine); + if (fd < 0) + return -EINVAL; - /* Check the .debug_frame section for unwinding info */ - *offset = elf_section_offset(fd, ".debug_frame"); + /* Check the .debug_frame section for unwinding info */ + ofs = elf_section_offset(fd, ".debug_frame"); + dso->data.frame_offset = ofs; + } + *offset = ofs; if (*offset) return 0; diff --git a/tools/power/acpi/common/cmfsize.c b/tools/power/acpi/common/cmfsize.c index f4b953354ff..eec68804150 100644 --- a/tools/power/acpi/common/cmfsize.c +++ b/tools/power/acpi/common/cmfsize.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/common/getopt.c b/tools/power/acpi/common/getopt.c index 2f0f34a36db..5da129e10aa 100644 --- a/tools/power/acpi/common/getopt.c +++ b/tools/power/acpi/common/getopt.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/oslibcfs.c b/tools/power/acpi/os_specific/service_layers/oslibcfs.c index c13ff9c51d7..b51e40a9a12 100644 --- a/tools/power/acpi/os_specific/service_layers/oslibcfs.c +++ b/tools/power/acpi/os_specific/service_layers/oslibcfs.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c index 0dc2485dedf..92f1fd70034 100644 --- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c +++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/osunixdir.c b/tools/power/acpi/os_specific/service_layers/osunixdir.c index 733f9e490fc..e153fcb12b1 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixdir.c +++ b/tools/power/acpi/os_specific/service_layers/osunixdir.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/osunixmap.c b/tools/power/acpi/os_specific/service_layers/osunixmap.c index 99b47b6194a..3853a735044 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixmap.c +++ b/tools/power/acpi/os_specific/service_layers/osunixmap.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c index 7ccb073f831..6858c0893c9 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixxf.c +++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/acpidump.h b/tools/power/acpi/tools/acpidump/acpidump.h index a2d37d61063..84bdef0136c 100644 --- a/tools/power/acpi/tools/acpidump/acpidump.h +++ b/tools/power/acpi/tools/acpidump/acpidump.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c index 24d32968802..c736adf5fb5 100644 --- a/tools/power/acpi/tools/acpidump/apdump.c +++ b/tools/power/acpi/tools/acpidump/apdump.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c index d470046a6d8..8f2fe168228 100644 --- a/tools/power/acpi/tools/acpidump/apfiles.c +++ b/tools/power/acpi/tools/acpidump/apfiles.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c index 853b4da22c3..d0ba6535f5a 100644 --- a/tools/power/acpi/tools/acpidump/apmain.c +++ b/tools/power/acpi/tools/acpidump/apmain.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2014, Intel Corp. + * Copyright (C) 2000 - 2015, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile index 2e2ba2efa0d..3ed7c0476d4 100644 --- a/tools/power/cpupower/Makefile +++ b/tools/power/cpupower/Makefile @@ -209,7 +209,7 @@ $(OUTPUT)%.o: %.c $(OUTPUT)cpupower: $(UTIL_OBJS) $(OUTPUT)libcpupower.so.$(LIB_MAJ) $(ECHO) " CC " $@ - $(QUIET) $(CC) $(CFLAGS) $(LDFLAGS) $(UTIL_OBJS) -lcpupower -lrt -lpci -L$(OUTPUT) -o $@ + $(QUIET) $(CC) $(CFLAGS) $(LDFLAGS) $(UTIL_OBJS) -lcpupower -Wl,-rpath=./ -lrt -lpci -L$(OUTPUT) -o $@ $(QUIET) $(STRIPCMD) $@ $(OUTPUT)po/$(PACKAGE).pot: $(UTIL_SRC) diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 56bfb523c5b..9b950699e63 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -12,16 +12,16 @@ turbostat \- Report processor frequency and idle statistics .RB [ "\-i interval_sec" ] .SH DESCRIPTION \fBturbostat \fP reports processor topology, frequency, -idle power-state statistics, temperature and power on modern X86 processors. -Either \fBcommand\fP is forked and statistics are printed -upon its completion, or statistics are printed periodically. - -\fBturbostat \fP -must be run on root, and -minimally requires that the processor -supports an "invariant" TSC, plus the APERF and MPERF MSRs. -Additional information is reported depending on hardware counter support. - +idle power-state statistics, temperature and power on X86 processors. +There are two ways to invoke turbostat. +The first method is to supply a +\fBcommand\fP, which is forked and statistics are printed +upon its completion. +The second method is to omit the command, +and turbodstat will print statistics every 5 seconds. +The 5-second interval can changed using the -i option. + +Some information is not availalbe on older processors. .SS Options The \fB-p\fP option limits output to the 1st thread in 1st core of each package. .PP @@ -130,12 +130,13 @@ cpu3: MSR_IA32_THERM_STATUS: 0x884e0000 (27 C +/- 1) ... .fi The \fBmax efficiency\fP frequency, a.k.a. Low Frequency Mode, is the frequency -available at the minimum package voltage. The \fBTSC frequency\fP is the nominal -maximum frequency of the processor if turbo-mode were not available. This frequency +available at the minimum package voltage. The \fBTSC frequency\fP is the base +frequency of the processor -- this should match the brand string +in /proc/cpuinfo. This base frequency should be sustainable on all CPUs indefinitely, given nominal power and cooling. The remaining rows show what maximum turbo frequency is possible -depending on the number of idle cores. Note that this information is -not available on all processors. +depending on the number of idle cores. Note that not all information is +available on all processors. .SH FORK EXAMPLE If turbostat is invoked with a command, it will fork that command and output the statistics gathered when the command exits. @@ -176,6 +177,11 @@ not including any non-busy idle time. .B "turbostat " must be run as root. +Alternatively, non-root users can be enabled to run turbostat this way: + +# setcap cap_sys_rawio=ep ./turbostat + +# chmod +r /dev/cpu/*/msr .B "turbostat " reads hardware counters, but doesn't write them. @@ -184,15 +190,33 @@ multiple invocations of itself. \fBturbostat \fP may work poorly on Linux-2.6.20 through 2.6.29, -as \fBacpi-cpufreq \fPperiodically cleared the APERF and MPERF +as \fBacpi-cpufreq \fPperiodically cleared the APERF and MPERF MSRs in those kernels. -If the TSC column does not make sense, then -the other numbers will also make no sense. -Turbostat is lightweight, and its data collection is not atomic. -These issues are usually caused by an extremely short measurement -interval (much less than 1 second), or system activity that prevents -turbostat from being able to run on all CPUS to quickly collect data. +AVG_MHz = APERF_delta/measurement_interval. This is the actual +number of elapsed cycles divided by the entire sample interval -- +including idle time. Note that this calculation is resiliant +to systems lacking a non-stop TSC. + +TSC_MHz = TSC_delta/measurement_interval. +On a system with an invariant TSC, this value will be constant +and will closely match the base frequency value shown +in the brand string in /proc/cpuinfo. On a system where +the TSC stops in idle, TSC_MHz will drop +below the processor's base frequency. + +%Busy = MPERF_delta/TSC_delta + +Bzy_MHz = TSC_delta/APERF_delta/MPERF_delta/measurement_interval + +Note that these calculations depend on TSC_delta, so they +are not reliable during intervals when TSC_MHz is not running at the base frequency. + +Turbostat data collection is not atomic. +Extremely short measurement intervals (much less than 1 second), +or system activity that prevents turbostat from being able +to run on all CPUS to quickly collect data, will result in +inconsistent results. The APERF, MPERF MSRs are defined to count non-halted cycles. Although it is not guaranteed by the architecture, turbostat assumes diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 5b1b807265a..a02c02f25e8 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -38,6 +38,8 @@ #include <ctype.h> #include <sched.h> #include <cpuid.h> +#include <linux/capability.h> +#include <errno.h> char *proc_stat = "/proc/stat"; unsigned int interval_sec = 5; /* set with -i interval_sec */ @@ -59,8 +61,8 @@ unsigned int has_epb; unsigned int units = 1000000; /* MHz etc */ unsigned int genuine_intel; unsigned int has_invariant_tsc; -unsigned int do_nehalem_platform_info; -unsigned int do_nehalem_turbo_ratio_limit; +unsigned int do_nhm_platform_info; +unsigned int do_nhm_turbo_ratio_limit; unsigned int do_ivt_turbo_ratio_limit; unsigned int extra_msr_offset32; unsigned int extra_msr_offset64; @@ -81,6 +83,9 @@ unsigned int tcc_activation_temp; unsigned int tcc_activation_temp_override; double rapl_power_units, rapl_energy_units, rapl_time_units; double rapl_joule_counter_range; +unsigned int do_core_perf_limit_reasons; +unsigned int do_gfx_perf_limit_reasons; +unsigned int do_ring_perf_limit_reasons; #define RAPL_PKG (1 << 0) /* 0x610 MSR_PKG_POWER_LIMIT */ @@ -251,15 +256,13 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) sprintf(pathname, "/dev/cpu/%d/msr", cpu); fd = open(pathname, O_RDONLY); if (fd < 0) - return -1; + err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname); retval = pread(fd, msr, sizeof *msr, offset); close(fd); - if (retval != sizeof *msr) { - fprintf(stderr, "%s offset 0x%llx read failed\n", pathname, (unsigned long long)offset); - return -1; - } + if (retval != sizeof *msr) + err(-1, "%s offset 0x%llx read failed", pathname, (unsigned long long)offset); return 0; } @@ -281,7 +284,7 @@ void print_header(void) outp += sprintf(outp, " CPU"); if (has_aperf) outp += sprintf(outp, " Avg_MHz"); - if (do_nhm_cstates) + if (has_aperf) outp += sprintf(outp, " %%Busy"); if (has_aperf) outp += sprintf(outp, " Bzy_MHz"); @@ -337,7 +340,7 @@ void print_header(void) outp += sprintf(outp, " PKG_%%"); if (do_rapl & RAPL_DRAM_PERF_STATUS) outp += sprintf(outp, " RAM_%%"); - } else { + } else if (do_rapl && rapl_joules) { if (do_rapl & RAPL_PKG) outp += sprintf(outp, " Pkg_J"); if (do_rapl & RAPL_CORES) @@ -457,25 +460,25 @@ int format_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "%8d", t->cpu_id); } - /* AvgMHz */ + /* Avg_MHz */ if (has_aperf) outp += sprintf(outp, "%8.0f", 1.0 / units * t->aperf / interval_float); - /* %c0 */ - if (do_nhm_cstates) { + /* %Busy */ + if (has_aperf) { if (!skip_c0) outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc); else outp += sprintf(outp, "********"); } - /* BzyMHz */ + /* Bzy_MHz */ if (has_aperf) outp += sprintf(outp, "%8.0f", 1.0 * t->tsc / units * t->aperf / t->mperf / interval_float); - /* TSC */ + /* TSC_MHz */ outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float); /* SMI */ @@ -561,7 +564,7 @@ int format_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); if (do_rapl & RAPL_DRAM_PERF_STATUS) outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); - } else { + } else if (do_rapl && rapl_joules) { if (do_rapl & RAPL_PKG) outp += sprintf(outp, fmt8, p->energy_pkg * rapl_energy_units); @@ -578,8 +581,8 @@ int format_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); if (do_rapl & RAPL_DRAM_PERF_STATUS) outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); - outp += sprintf(outp, fmt8, interval_float); + outp += sprintf(outp, fmt8, interval_float); } done: outp += sprintf(outp, "\n"); @@ -670,24 +673,26 @@ delta_thread(struct thread_data *new, struct thread_data *old, old->c1 = new->c1 - old->c1; - if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) { - old->aperf = new->aperf - old->aperf; - old->mperf = new->mperf - old->mperf; - } else { + if (has_aperf) { + if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) { + old->aperf = new->aperf - old->aperf; + old->mperf = new->mperf - old->mperf; + } else { - if (!aperf_mperf_unstable) { - fprintf(stderr, "%s: APERF or MPERF went backwards *\n", progname); - fprintf(stderr, "* Frequency results do not cover entire interval *\n"); - fprintf(stderr, "* fix this by running Linux-2.6.30 or later *\n"); + if (!aperf_mperf_unstable) { + fprintf(stderr, "%s: APERF or MPERF went backwards *\n", progname); + fprintf(stderr, "* Frequency results do not cover entire interval *\n"); + fprintf(stderr, "* fix this by running Linux-2.6.30 or later *\n"); - aperf_mperf_unstable = 1; + aperf_mperf_unstable = 1; + } + /* + * mperf delta is likely a huge "positive" number + * can not use it for calculating c0 time + */ + skip_c0 = 1; + skip_c1 = 1; } - /* - * mperf delta is likely a huge "positive" number - * can not use it for calculating c0 time - */ - skip_c0 = 1; - skip_c1 = 1; } @@ -1019,7 +1024,7 @@ void print_verbose_header(void) unsigned long long msr; unsigned int ratio; - if (!do_nehalem_platform_info) + if (!do_nhm_platform_info) return; get_msr(0, MSR_NHM_PLATFORM_INFO, &msr); @@ -1132,7 +1137,7 @@ print_nhm_turbo_ratio_limits: } fprintf(stderr, ")\n"); - if (!do_nehalem_turbo_ratio_limit) + if (!do_nhm_turbo_ratio_limit) return; get_msr(0, MSR_NHM_TURBO_RATIO_LIMIT, &msr); @@ -1178,6 +1183,7 @@ print_nhm_turbo_ratio_limits: if (ratio) fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 1 active cores\n", ratio, bclk, ratio * bclk); + } void free_all_buffers(void) @@ -1458,17 +1464,60 @@ void check_dev_msr() struct stat sb; if (stat("/dev/cpu/0/msr", &sb)) - err(-5, "no /dev/cpu/0/msr\n" - "Try \"# modprobe msr\""); + err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" "); } -void check_super_user() +void check_permissions() { - if (getuid() != 0) - errx(-6, "must be root"); + struct __user_cap_header_struct cap_header_data; + cap_user_header_t cap_header = &cap_header_data; + struct __user_cap_data_struct cap_data_data; + cap_user_data_t cap_data = &cap_data_data; + extern int capget(cap_user_header_t hdrp, cap_user_data_t datap); + int do_exit = 0; + + /* check for CAP_SYS_RAWIO */ + cap_header->pid = getpid(); + cap_header->version = _LINUX_CAPABILITY_VERSION; + if (capget(cap_header, cap_data) < 0) + err(-6, "capget(2) failed"); + + if ((cap_data->effective & (1 << CAP_SYS_RAWIO)) == 0) { + do_exit++; + warnx("capget(CAP_SYS_RAWIO) failed," + " try \"# setcap cap_sys_rawio=ep %s\"", progname); + } + + /* test file permissions */ + if (euidaccess("/dev/cpu/0/msr", R_OK)) { + do_exit++; + warn("/dev/cpu/0/msr open failed, try chown or chmod +r /dev/cpu/*/msr"); + } + + /* if all else fails, thell them to be root */ + if (do_exit) + if (getuid() != 0) + warnx("... or simply run as root"); + + if (do_exit) + exit(-6); } -int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model) +/* + * NHM adds support for additional MSRs: + * + * MSR_SMI_COUNT 0x00000034 + * + * MSR_NHM_PLATFORM_INFO 0x000000ce + * MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2 + * + * MSR_PKG_C3_RESIDENCY 0x000003f8 + * MSR_PKG_C6_RESIDENCY 0x000003f9 + * MSR_CORE_C3_RESIDENCY 0x000003fc + * MSR_CORE_C6_RESIDENCY 0x000003fd + * + */ +int has_nhm_msrs(unsigned int family, unsigned int model) { if (!genuine_intel) return 0; @@ -1495,13 +1544,27 @@ int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model) case 0x3D: /* BDW */ case 0x4F: /* BDX */ case 0x56: /* BDX-DE */ - return 1; case 0x2E: /* Nehalem-EX Xeon - Beckton */ case 0x2F: /* Westmere-EX Xeon - Eagleton */ + return 1; default: return 0; } } +int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model) +{ + if (!has_nhm_msrs(family, model)) + return 0; + + switch (model) { + /* Nehalem compatible, but do not include turbo-ratio limit support */ + case 0x2E: /* Nehalem-EX Xeon - Beckton */ + case 0x2F: /* Westmere-EX Xeon - Eagleton */ + return 0; + default: + return 1; + } +} int has_ivt_turbo_ratio_limit(unsigned int family, unsigned int model) { if (!genuine_intel) @@ -1564,6 +1627,103 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; } +/* + * print_perf_limit() + */ +int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ + unsigned long long msr; + int cpu; + + cpu = t->cpu_id; + + /* per-package */ + if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) + return 0; + + if (cpu_migrate(cpu)) { + fprintf(stderr, "Could not migrate to CPU %d\n", cpu); + return -1; + } + + if (do_core_perf_limit_reasons) { + get_msr(cpu, MSR_CORE_PERF_LIMIT_REASONS, &msr); + fprintf(stderr, "cpu%d: MSR_CORE_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr); + fprintf(stderr, " (Active: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)", + (msr & 1 << 0) ? "PROCHOT, " : "", + (msr & 1 << 1) ? "ThermStatus, " : "", + (msr & 1 << 2) ? "bit2, " : "", + (msr & 1 << 4) ? "Graphics, " : "", + (msr & 1 << 5) ? "Auto-HWP, " : "", + (msr & 1 << 6) ? "VR-Therm, " : "", + (msr & 1 << 8) ? "Amps, " : "", + (msr & 1 << 9) ? "CorePwr, " : "", + (msr & 1 << 10) ? "PkgPwrL1, " : "", + (msr & 1 << 11) ? "PkgPwrL2, " : "", + (msr & 1 << 12) ? "MultiCoreTurbo, " : "", + (msr & 1 << 13) ? "Transitions, " : "", + (msr & 1 << 14) ? "bit14, " : "", + (msr & 1 << 15) ? "bit15, " : ""); + fprintf(stderr, " (Logged: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)\n", + (msr & 1 << 16) ? "PROCHOT, " : "", + (msr & 1 << 17) ? "ThermStatus, " : "", + (msr & 1 << 18) ? "bit18, " : "", + (msr & 1 << 20) ? "Graphics, " : "", + (msr & 1 << 21) ? "Auto-HWP, " : "", + (msr & 1 << 22) ? "VR-Therm, " : "", + (msr & 1 << 24) ? "Amps, " : "", + (msr & 1 << 25) ? "CorePwr, " : "", + (msr & 1 << 26) ? "PkgPwrL1, " : "", + (msr & 1 << 27) ? "PkgPwrL2, " : "", + (msr & 1 << 28) ? "MultiCoreTurbo, " : "", + (msr & 1 << 29) ? "Transitions, " : "", + (msr & 1 << 30) ? "bit30, " : "", + (msr & 1 << 31) ? "bit31, " : ""); + + } + if (do_gfx_perf_limit_reasons) { + get_msr(cpu, MSR_GFX_PERF_LIMIT_REASONS, &msr); + fprintf(stderr, "cpu%d: MSR_GFX_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr); + fprintf(stderr, " (Active: %s%s%s%s%s%s%s%s)", + (msr & 1 << 0) ? "PROCHOT, " : "", + (msr & 1 << 1) ? "ThermStatus, " : "", + (msr & 1 << 4) ? "Graphics, " : "", + (msr & 1 << 6) ? "VR-Therm, " : "", + (msr & 1 << 8) ? "Amps, " : "", + (msr & 1 << 9) ? "GFXPwr, " : "", + (msr & 1 << 10) ? "PkgPwrL1, " : "", + (msr & 1 << 11) ? "PkgPwrL2, " : ""); + fprintf(stderr, " (Logged: %s%s%s%s%s%s%s%s)\n", + (msr & 1 << 16) ? "PROCHOT, " : "", + (msr & 1 << 17) ? "ThermStatus, " : "", + (msr & 1 << 20) ? "Graphics, " : "", + (msr & 1 << 22) ? "VR-Therm, " : "", + (msr & 1 << 24) ? "Amps, " : "", + (msr & 1 << 25) ? "GFXPwr, " : "", + (msr & 1 << 26) ? "PkgPwrL1, " : "", + (msr & 1 << 27) ? "PkgPwrL2, " : ""); + } + if (do_ring_perf_limit_reasons) { + get_msr(cpu, MSR_RING_PERF_LIMIT_REASONS, &msr); + fprintf(stderr, "cpu%d: MSR_RING_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr); + fprintf(stderr, " (Active: %s%s%s%s%s%s)", + (msr & 1 << 0) ? "PROCHOT, " : "", + (msr & 1 << 1) ? "ThermStatus, " : "", + (msr & 1 << 6) ? "VR-Therm, " : "", + (msr & 1 << 8) ? "Amps, " : "", + (msr & 1 << 10) ? "PkgPwrL1, " : "", + (msr & 1 << 11) ? "PkgPwrL2, " : ""); + fprintf(stderr, " (Logged: %s%s%s%s%s%s)\n", + (msr & 1 << 16) ? "PROCHOT, " : "", + (msr & 1 << 17) ? "ThermStatus, " : "", + (msr & 1 << 22) ? "VR-Therm, " : "", + (msr & 1 << 24) ? "Amps, " : "", + (msr & 1 << 26) ? "PkgPwrL1, " : "", + (msr & 1 << 27) ? "PkgPwrL2, " : ""); + } + return 0; +} + #define RAPL_POWER_GRANULARITY 0x7FFF /* 15 bit power granularity */ #define RAPL_TIME_GRANULARITY 0x3F /* 6 bit time granularity */ @@ -1653,6 +1813,27 @@ void rapl_probe(unsigned int family, unsigned int model) return; } +void perf_limit_reasons_probe(family, model) +{ + if (!genuine_intel) + return; + + if (family != 6) + return; + + switch (model) { + case 0x3C: /* HSW */ + case 0x45: /* HSW */ + case 0x46: /* HSW */ + do_gfx_perf_limit_reasons = 1; + case 0x3F: /* HSX */ + do_core_perf_limit_reasons = 1; + do_ring_perf_limit_reasons = 1; + default: + return; + } +} + int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p) { unsigned long long msr; @@ -1842,8 +2023,15 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; } +/* + * SNB adds support for additional MSRs: + * + * MSR_PKG_C7_RESIDENCY 0x000003fa + * MSR_CORE_C7_RESIDENCY 0x000003fe + * MSR_PKG_C2_RESIDENCY 0x0000060d + */ -int is_snb(unsigned int family, unsigned int model) +int has_snb_msrs(unsigned int family, unsigned int model) { if (!genuine_intel) return 0; @@ -1865,7 +2053,14 @@ int is_snb(unsigned int family, unsigned int model) return 0; } -int has_c8_c9_c10(unsigned int family, unsigned int model) +/* + * HSW adds support for additional MSRs: + * + * MSR_PKG_C8_RESIDENCY 0x00000630 + * MSR_PKG_C9_RESIDENCY 0x00000631 + * MSR_PKG_C10_RESIDENCY 0x00000632 + */ +int has_hsw_msrs(unsigned int family, unsigned int model) { if (!genuine_intel) return 0; @@ -1917,7 +2112,7 @@ double slm_bclk(void) double discover_bclk(unsigned int family, unsigned int model) { - if (is_snb(family, model)) + if (has_snb_msrs(family, model)) return 100.00; else if (is_slm(family, model)) return slm_bclk(); @@ -1965,7 +2160,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk } /* Temperature Target MSR is Nehalem and newer only */ - if (!do_nehalem_platform_info) + if (!do_nhm_platform_info) goto guess; if (get_msr(0, MSR_IA32_TEMPERATURE_TARGET, &msr)) @@ -2029,18 +2224,15 @@ void check_cpuid() ebx = ecx = edx = 0; __get_cpuid(0x80000000, &max_level, &ebx, &ecx, &edx); - if (max_level < 0x80000007) - errx(1, "CPUID: no invariant TSC (max_level 0x%x)", max_level); + if (max_level >= 0x80000007) { - /* - * Non-Stop TSC is advertised by CPUID.EAX=0x80000007: EDX.bit8 - * this check is valid for both Intel and AMD - */ - __get_cpuid(0x80000007, &eax, &ebx, &ecx, &edx); - has_invariant_tsc = edx & (1 << 8); - - if (!has_invariant_tsc) - errx(1, "No invariant TSC"); + /* + * Non-Stop TSC is advertised by CPUID.EAX=0x80000007: EDX.bit8 + * this check is valid for both Intel and AMD + */ + __get_cpuid(0x80000007, &eax, &ebx, &ecx, &edx); + has_invariant_tsc = edx & (1 << 8); + } /* * APERF/MPERF is advertised by CPUID.EAX=0x6: ECX.bit0 @@ -2054,26 +2246,22 @@ void check_cpuid() has_epb = ecx & (1 << 3); if (verbose) - fprintf(stderr, "CPUID(6): %s%s%s%s\n", - has_aperf ? "APERF" : "No APERF!", - do_dts ? ", DTS" : "", - do_ptm ? ", PTM": "", - has_epb ? ", EPB": ""); - - if (!has_aperf) - errx(-1, "No APERF"); - - do_nehalem_platform_info = genuine_intel && has_invariant_tsc; - do_nhm_cstates = genuine_intel; /* all Intel w/ non-stop TSC have NHM counters */ - do_smi = do_nhm_cstates; - do_snb_cstates = is_snb(family, model); - do_c8_c9_c10 = has_c8_c9_c10(family, model); + fprintf(stderr, "CPUID(6): %sAPERF, %sDTS, %sPTM, %sEPB\n", + has_aperf ? "" : "No ", + do_dts ? "" : "No ", + do_ptm ? "" : "No ", + has_epb ? "" : "No "); + + do_nhm_platform_info = do_nhm_cstates = do_smi = has_nhm_msrs(family, model); + do_snb_cstates = has_snb_msrs(family, model); + do_c8_c9_c10 = has_hsw_msrs(family, model); do_slm_cstates = is_slm(family, model); bclk = discover_bclk(family, model); - do_nehalem_turbo_ratio_limit = has_nehalem_turbo_ratio_limit(family, model); + do_nhm_turbo_ratio_limit = has_nhm_turbo_ratio_limit(family, model); do_ivt_turbo_ratio_limit = has_ivt_turbo_ratio_limit(family, model); rapl_probe(family, model); + perf_limit_reasons_probe(family, model); return; } @@ -2299,10 +2487,9 @@ void setup_all_buffers(void) void turbostat_init() { - check_cpuid(); - check_dev_msr(); - check_super_user(); + check_permissions(); + check_cpuid(); setup_all_buffers(); @@ -2313,6 +2500,9 @@ void turbostat_init() for_all_cpus(print_epb, ODD_COUNTERS); if (verbose) + for_all_cpus(print_perf_limit, ODD_COUNTERS); + + if (verbose) for_all_cpus(print_rapl, ODD_COUNTERS); for_all_cpus(set_temperature_target, ODD_COUNTERS); @@ -2441,7 +2631,7 @@ int main(int argc, char **argv) cmdline(argc, argv); if (verbose) - fprintf(stderr, "turbostat v3.7 Feb 6, 2014" + fprintf(stderr, "turbostat v3.9 23-Jan, 2015" " - Len Brown <lenb@kernel.org>\n"); turbostat_init(); diff --git a/tools/testing/selftests/rcutorture/bin/cpus2use.sh b/tools/testing/selftests/rcutorture/bin/cpus2use.sh index abe14b7f36e..bb99cde3f5f 100755 --- a/tools/testing/selftests/rcutorture/bin/cpus2use.sh +++ b/tools/testing/selftests/rcutorture/bin/cpus2use.sh @@ -24,7 +24,7 @@ ncpus=`grep '^processor' /proc/cpuinfo | wc -l` idlecpus=`mpstat | tail -1 | \ - awk -v ncpus=$ncpus '{ print ncpus * ($7 + $12) / 100 }'` + awk -v ncpus=$ncpus '{ print ncpus * ($7 + $NF) / 100 }'` awk -v ncpus=$ncpus -v idlecpus=$idlecpus < /dev/null ' BEGIN { cpus2use = idlecpus; diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh index d6cc07fc137..559e01ac86b 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh @@ -30,6 +30,7 @@ else echo Unreadable results directory: $i exit 1 fi +. tools/testing/selftests/rcutorture/bin/functions.sh configfile=`echo $i | sed -e 's/^.*\///'` ngps=`grep ver: $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* ver: //' -e 's/ .*$//'` @@ -48,4 +49,21 @@ else title="$title ($ngpsps per second)" fi echo $title + nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'` + if test -z "$nclosecalls" + then + exit 0 + fi + if test "$nclosecalls" -eq 0 + then + exit 0 + fi + # Compute number of close calls per tenth of an hour + nclosecalls10=`awk -v nclosecalls=$nclosecalls -v dur=$dur 'BEGIN { print int(nclosecalls * 36000 / dur) }' < /dev/null` + if test $nclosecalls10 -gt 5 -a $nclosecalls -gt 1 + then + print_bug $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i + else + print_warning $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i + fi fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 8ca9f21f2ef..5236e073919 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -8,9 +8,9 @@ # # Usage: kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args # -# qemu-args defaults to "-nographic", along with arguments specifying the -# number of CPUs and other options generated from -# the underlying CPU architecture. +# qemu-args defaults to "-enable-kvm -soundhw pcspk -nographic", along with +# arguments specifying the number of CPUs and other +# options generated from the underlying CPU architecture. # boot_args defaults to value returned by the per_version_boot_params # shell function. # @@ -138,7 +138,7 @@ then fi # Generate -smp qemu argument. -qemu_args="-nographic $qemu_args" +qemu_args="-enable-kvm -soundhw pcspk -nographic $qemu_args" cpu_count=`configNR_CPUS.sh $config_template` cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"` vcpus=`identify_qemu_vcpus` @@ -168,6 +168,7 @@ then touch $resdir/buildonly exit 0 fi +echo "NOTE: $QEMU either did not run or was interactive" > $builddir/console.log echo $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd ( $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) & qemu_pid=$! diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh index 499d1e598e4..a6b57622c2e 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-build.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh @@ -26,12 +26,15 @@ # # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> -T=$1 +F=$1 title=$2 +T=/tmp/parse-build.sh.$$ +trap 'rm -rf $T' 0 +mkdir $T . functions.sh -if grep -q CC < $T +if grep -q CC < $F then : else @@ -39,18 +42,21 @@ else exit 1 fi -if grep -q "error:" < $T +if grep -q "error:" < $F then print_bug $title build errors: - grep "error:" < $T + grep "error:" < $F exit 2 fi -exit 0 -if egrep -q "rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T +grep warning: < $F > $T/warnings +grep "include/linux/*rcu*\.h:" $T/warnings > $T/hwarnings +grep "kernel/rcu/[^/]*:" $T/warnings > $T/cwarnings +cat $T/hwarnings $T/cwarnings > $T/rcuwarnings +if test -s $T/rcuwarnings then print_warning $title build errors: - egrep "rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T + cat $T/rcuwarnings exit 2 fi exit 0 diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index f962ba4cf68..d8f35cf116b 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -36,7 +36,7 @@ if grep -Pq '\x00' < $file then print_warning Console output contains nul bytes, old qemu still running? fi -egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T +egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T if test -s $T then print_warning Assertion failure in $file $title |